111 results about "Routing algorithm" patented technology

The invention provides an artificial intelligence semantic processing system and method oriented to digital media creation, and relates to the technical field of artificial intelligence semantic process.The artificial intelligence semantic processing method comprises the steps that predicate argument relation pairs of language texts are extracted, object space relation pairs of sketch images are extracted at the same time, and a basic semantic unit set is constructed; the integrity and accuracy of cross-modal semantic understanding are ensured, further, semantic units are clustered by using a dynamic routing algorithm, a semantic concept cluster with a clear importance weight is generated, deep mining and structured representation of creation intentions are realized, and the creation intentions are quickly and accurately understood. An initial semantic relation graph is constructed, a graph attention network is used for dynamic reweighting, finally, an enhanced dynamic semantic graph is generated, complex association and a hierarchical structure between semantic concepts are effectively captured, finally, hierarchical analysis is carried out on the semantic graph, and a structured semantic blueprint is output, so that the dynamic semantic graph is obtained. And a reliable semantic processing technology is provided for creation of high-quality digital media contents.

The invention discloses a liquid drop routing method under fluid constraint in a digital micro-fluidic biochip based on reinforcement learning and imitation learning, and aims to solve the technical problems of low planning efficiency, low success rate and weak generalization ability of a traditional liquid drop routing algorithm under fluid constraint. The method adopts a strategy combining imitation learning and reinforcement learning and comprises the following steps: firstly, generating expert data by utilizing an expert algorithm meeting fluid constraint after transformation, and pre-training a network model through imitation learning to enable the network model to quickly grasp a basic routing strategy; the model and environment interaction are autonomously optimized through reinforcement learning, and the adaptability to the dynamic environment is improved. And finally fusing the weights to form a final model. Through the hybrid training framework, the success rate and planning efficiency of droplet routing are remarkably improved, and the generalization ability of the model to chip environments with different sizes is enhanced.

The invention provides a multi-source data fusion analysis system for electronic commerce digitization insight, and relates to the technical field of data processing, and the system comprises a reference analysis unit used for selecting a reference analysis unit in a spatial relation structure, calculating fractal dimension features of feature vectors, carrying out multi-level recursive division on the analysis unit based on fractal dimension values, and carrying out multi-level data fusion analysis on the fractal dimension values; each level of division keeps a self-similarity characteristic, and feature partitions are obtained; the partition space distribution module is used for mapping the feature vector distribution to corresponding feature partitions and calculating partition space distribution weights based on vector density distribution and space position relations of the feature partitions; the value evaluation module is used for performing parameter adjustment on the deep learning network by using the partition space distribution weight to obtain a value evaluation result; and the value evaluation module is used for processing a value evaluation result through a multi-modal fusion algorithm, generating a personalized recommendation strategy based on a reinforcement learning framework, and calculating resources and an intelligent routing algorithm so as to complete a digital insight analysis process. The e-commerce data utilization efficiency and the decision-making effect can be improved.

The invention provides an NoC low-delay data transmission method based on a dynamic routing algorithm, relates to the technical field of data transmission, and aims to solve the technical problems that an existing NoC routing algorithm cannot adapt to a link dynamic load, is lack of congestion trend prejudgment, is slow in path search convergence and is insufficient in QoS differential scheduling. The method comprises the following steps: constructing a dynamic sensing module containing a double-branch LSTM time sequence prediction model, collecting states such as link bandwidth and queue length in real time, and predicting a congestion trend in 50-100ms in the future; constructing a multi-objective evaluation function taking delay as a core, and dynamically adjusting the weight according to the QoS level; solving an optimal path by adopting an improved ant colony algorithm which introduces a congestion penalty and pruning strategy; during transmission, dynamic reselection is triggered through a pre-calculation + fast matching mechanism; and iteratively optimizing the prediction model based on incremental learning. According to the method, congestion is avoided in advance, the path search efficiency and the transmission reliability are improved, the delay is remarkably reduced compared with a traditional algorithm, and the method is adaptive to delay sensitive scenes such as a high-performance processor and an AI chip.

The invention relates to the field of network communication, and discloses a fast message pushing method and device based on converged communication and a medium, and the method comprises the steps: collecting message content data through a multi-source heterogeneous interface, carrying out the normalization processing of the data, and generating standard message metadata; key feature vectors are extracted from the standard message metadata by adopting a deep semantic analysis model, and a message priority evaluation matrix is generated in combination with a user portrait database; based on a multi-channel intelligent routing algorithm, generating an optimal transmission path decision tree according to the priority evaluation matrix and the real-time network state data; and distributing the message to the target communication channel according to the decision tree path through a dynamic load balancing engine, and executing multi-protocol adaptive transmission. According to the method, a whole-process message pushing method from matrix evaluation to intelligent routing and then to multi-protocol adaptive transmission is constructed, a high-reliability and low-delay communication solution is provided for a scene needing rapid message pushing, and the method has remarkable technical breakthrough and commercial application value.

The invention relates to the technical field of computer graphic processing, and discloses a method for automatically drawing a DCS (Distributed Control System) picture into a real-time database picture, which comprises the following steps of: firstly, identifying a DCS source file format, directly analyzing a public text format or intercepting a bottom layer rendering instruction for a private binary format, and extracting standardized discrete data; constructing an intermediate vector model, and performing coordinate normalization and curve smoothing processing on the static primitives by using an affine transformation matrix; meanwhile, syntactic analysis is conducted on the control script to construct an abstract syntax tree, and dynamic logic is converted; then recombining a composite object based on spatial semantics, and repairing pipeline topology connection by utilizing automatic adsorption and an orthogonal routing algorithm; and finally, calling a target system interface to complete object instantiation and persistent storage. According to the invention, the automatic high-fidelity migration of the DCS picture to the real-time database is realized, the labor cost is reduced, and the consistency and accuracy of the monitoring picture are ensured.

The invention discloses a link congestion control load balancing routing method based on routing domain division. The method belongs to the technical field of low-orbit satellite routing switching application. The problem that a traditional routing algorithm is high in complexity and slow in response time under the condition of a large network scale is solved. A giant constellation is divided into non-overlapping routing domains, global routing is divided into intra-domain local routing calculation and cross-domain routing interaction, on-satellite computing power consumption is reduced, and the method is adaptive to a large-scale satellite network. Meanwhile, a traditional distributed routing algorithm relates to signaling flooding when the state of a satellite link is changed, the signaling overhead is huge in a large-scale satellite network, local response is carried out in the congestion process by means of a sub-domain architecture and inter-satellite link availability prediction, and the signaling overhead of the whole network is reduced, so that the availability of the routing algorithm is improved.

The present application generally relates to electronic trading systems, and more specifically to systems and methods for electronic trade order routing. A routing algorithm may generate an execution style recommendation for incoming IG corporate orders. For example, the style recommendation may be shown as a new column in the trading application dashboard that suggests a course of action to traders for each order. In one implementation, automatic decision making may occur based on the style recommendation.

The embodiment of the invention provides a system-on-chip design method and device, a deadlock detection method and device, electronic equipment and a storage medium. The system-on-chip design method comprises the steps that a network-on-chip included in a system-on-chip in design is mapped into a first directed connected graph; determining a first directed connectivity dependency graph according to the first directed connectivity graph and a routing algorithm of the network-on-chip; mapping subsystems included in the system-on-chip in the design into a second directed connected graph; determining a second directed connectivity dependency graph according to the second directed connectivity graph and a logic routing algorithm of the subsystem; determining a third directed connected graph according to the first directed connected graph and the second directed connected graph; determining a third directed connectivity dependency graph according to the first directed connectivity dependency graph and the second directed connectivity dependency graph; and performing deadlock detection on the system-on-chip in design according to the third directed connectivity graph and the third directed connectivity dependency graph, and optimizing the system-on-chip in design according to a deadlock detection result. According to the scheme, the design cost of the system-on-chip can be reduced.

The invention relates to the technical field of network configuration for interconnection and intercommunication, in particular to a network configuration method, system and device for interconnection and intercommunication and a medium. Determining a network topology structure and dividing a logic area; distributing a unique multicast address field for each area; deploying a self-adaptive routing protocol; distributing preset channels in the core exchange layer through quantum communication; creating an intelligent traffic sculpture engine, predicting burst traffic by using a neural network and presetting a buffer space; implementing a heterogeneous equipment compatibility strategy; constructing an annular redundant architecture; starting a block chain verification mechanism; and deploying a holographic topology monitoring system. Through intelligent linkage of a dynamic routing algorithm and an optical layer self-healing loop, business migration of regional faults can be completed within a human perception threshold, and finance transaction sensitive operation can achieve zero-interruption extreme availability.

This invention discloses a routing method and system for a multi-layered, multi-path switching network. The method includes the following steps: constructing a directed graph based on the multi-layered network, wherein nodes in the directed graph represent switches, edges represent communication links, each node has the ability to switch between different switching technologies, and the communication link has the ability to transmit data according to the switching technologies of its two endpoints; for each node in the directed graph, initializing the routing table of that node and iteratively calculating the optimal routing table; given a starting node and a target node, obtaining the next hop of the minimum-cost continuous path from the starting node to the target node according to the optimal routing table of the current node, and sending data packets hop-by-hop to the next node. The routing algorithm proposed in this invention can solve the minimum-cost path problem between all node pairs.

Systems and methods of configuring and using a machine-learned safety risk model to predict a corresponding risk of vehicular collision for different candidate routes are disclosed herein. In some example embodiments, a computer system obtains accident data and feature data for historical routes that have been communicated electronically as navigation guidance, trains a safety risk model using the accident data and the feature data of the historical routes as training data in a machine learning process, and then evaluates one or more routing algorithms by generating a corresponding set of routes for each routing algorithm and generating a corresponding performance measurement for each set of routes using the trained safety risk model.

The embodiment of the invention relates to the technical field of data processing, in particular to a data caching method, a plug-in caching system, computer equipment and a storage medium. The method is applied to a proxy layer of the plug-in cache system, the proxy layer comprises a serialization layer and a routing layer, the serialization layer comprises a plurality of preset serialization protocol plug-ins, and the routing layer comprises a plurality of preset routing algorithm plug-ins. The data caching method comprises the following steps: receiving a caching operation request from a client; determining a target serialization plug-in from the plurality of serialization protocol plug-ins, and determining a target routing algorithm plug-in from the plurality of routing algorithm plug-ins; standardizing the cache operation request according to the target serialization protocol plug-in to obtain a standardized request; determining a target cache instance corresponding to the standardized request according to the target routing algorithm plug-in; and sending the standardized request to the target cache instance. By adopting the method, the development cost can be reduced, and the development period can be shortened.

The application discloses a satellite routing method and device based on multi-objective optimization, equipment and storage medium, relates to the technical field of satellite communication. The satellite routing method based on multi-objective optimization comprises the following steps: obtaining the running state information of a satellite communication network; according to the running state information, the satellites in the satellite communication network are divided into at least two stable satellite clusters; topology abstraction is performed on each stable satellite cluster to obtain a cluster time-varying graph corresponding to the satellite communication network; a target transmission path is generated according to the cluster time-varying graph, and satellite routing is performed based on the target transmission path. The application solves the technical problem of excessive operation resource consumption of the dynamic routing algorithm of the satellite communication network in the prior art.

The invention discloses a data transmission method, system and device and a computer readable storage medium, relates to the technical field of network-on-chip, and is applied to a routing node of the network-on-chip to determine a source node for transmitting target data and a destination node for receiving the target data. Determining a node routing direction according to the position relationship between the source node and the destination node; according to the position relation between the routing node and the destination node, screening a next node according to the node routing direction; transmitting target data to the next node through a conventional channel of the routing node in response to the fact that the coordinate of the next node and the coordinate of the routing node have the same value; and in response to the fact that the coordinate of the next node and the coordinate of the routing node do not have the same value, transmitting the target data to the next node through the virtual channel of the routing node. On the premise of not changing a network-on-chip architecture system, transmission congestion is reduced by modifying a routing algorithm on a software level, and the data transmission efficiency of the network-on-chip is improved.

The application relates to a routing algorithm for black hole attack and routing optimization in a MANET, which comprises two parts of malicious node detection S1 and routing optimization S2. When the malicious node detection is carried out, the difference between the behaviors of a malicious node and a safe node in the routing establishment stage of the black hole attack is used for judgment, and additional information of other nodes is not needed, that is, whether the node is a malicious node can be judged only by using the routing information returned by a next-hop node. A black and white list mechanism is used to improve the detection precision, reduce the false alarm rate and reduce the detection times. Meanwhile, when the routing optimization is carried out, the transmission path is optimized, when a next-hop node reaching a destination node is selected, the load state of the next-hop node and the hop number of the next-hop node to the destination node are considered, the load capacity of the transmission path is effectively improved, and the robustness of the network is improved.

This application relates to the field of electronic circuit design technology, and in particular to a PCB layout optimization method suitable for signal transmission. This method acquires manufacturer-specific process capability parameters, constructs a manufacturing disturbance model including conductor geometric deviations, dielectric non-uniformity, and interlayer alignment errors, and embeds an electromagnetic simulation engine to form a dynamic signal integrity analysis model. Based on this, an adaptive layout constraint rule set is generated, driving the layout and routing algorithm to perform manufacturing robustness-oriented automatic routing. This solves the problem of signal integrity degradation in high-speed signal links on PCBs due to manufacturing fluctuations, pre-compensating for manufacturing-introduced non-ideals during the design phase, and improving the first-pass success rate and signal performance consistency of high-speed PCBs.

This invention claims protection for an intelligent fault diagnosis method for rotating machinery based on semantics and capsule networks. The algorithm is implemented using the Keras deep learning framework and semantic web technology, and includes the following steps: Step 1: Preprocessing the original acceleration signal to input into a pre-constructed convolutional layer for automatic feature learning; Step 2: Introducing an Inception module into the capsule network to extract feature representations at multiple scales, preserving the spatial pose information of the features to the greatest extent; Step 3: Constructing and introducing a low-level capsule layer based on weight sharing to share the affine transformation matrix, obtaining predicted feature vectors, and then weighted summing them before inputting them into a high-level capsule layer; Step 4: Introducing a protocol-based dynamic routing algorithm into the high-level capsule layer for iterative weight updates; Step 5: Using rule-based reasoning based on Prolog+Lisp, leveraging existing knowledge in the rotating machinery knowledge domain ontology and the results of IWSCN predictions, to infer the cause of the fault, improving the level of diagnostic intelligence.

The invention discloses a satellite network simulation system and method based on an abstract packet and dual-path processing, and mainly solves the problem that the existing satellite network simulation technology is difficult to give consideration to high fidelity and high efficiency in a large-scale and high-traffic scene. The system comprises a switch, a control unit, an abstract packet construction unit, a satellite network simulator and an abstract packet deconstruction unit, and the switch is bidirectionally connected with the units and serves as a connection platform of the system to receive and forward data; the satellite network simulator is used for network layer protocol simulation. The abstract packet construction unit is used for distinguishing a control packet from a service data packet and aggregating the data packet into an abstract packet; the abstract package deconstruction unit restores the abstract package into an original data package, and modifies and verifies the data package according to a simulation result; the control unit manages operation parameters of the system and provides a time synchronization and human-computer interaction interface. According to the method, the system throughput can be improved while the simulation precision is guaranteed, high efficiency and high fidelity are achieved, configuration is flexible, deployment cost is low, and the method can be used for network protocol verification and routing algorithm performance evaluation of large-scale satellite constellations.

The invention relates to the technical field of big data and artificial intelligence, and particularly discloses a global digital rights intelligent configuration and distribution method based on multi-source data fusion. The method comprises the following steps: firstly, collecting user global multi-source heterogeneous data through a distributed network, extracting multi-modal features by using space-time alignment and a deep neural network, and constructing a user high-dimensional feature vector; then, inputting the feature vectors into a reinforcement learning model, and intelligently matching an optimal right configuration scheme from a right library through a multi-objective optimization function; thirdly, realizing cross-platform synchronous distribution according to the terminal state and the geofence by using a scene awareness routing algorithm; and finally, on the basis of a federated learning mechanism, realizing online iteration of the model by utilizing full-life-cycle feedback data. Through deep interleaving and intelligent decision making of multi-source data, accurate configuration and non-perception of digital rights and interests are achieved, the rights and interests cancel-after-verification rate and the user experience are improved, meanwhile, the user privacy is effectively protected, and the self-evolution ability is achieved.

The invention discloses a method and a system for generating an intelligent migration path of an optical cable migration and change service. The method comprises the steps of obtaining optical cable relocation event information; positioning an affected service list and an original path; constructing a weighted graph network model and temporarily removing the relocation and relocation optical cable; adopting a multi-strategy rerouting algorithm to calculate a plurality of migration paths for each service; evaluating feasibility, economy and risk indexes of each path; a recommendation scheme is generated through comprehensive score sorting, and alternative path analysis is carried out; and finally outputting a standardized relocation scheme report. The system can automatically and efficiently generate the optimal migration path and guarantee smooth migration of services.

The invention discloses a message forwarding method, device and equipment based on an ECMP dynamic algorithm, and the method comprises the steps: sending a message transmitted from an entrance to a Hash engine, and carrying out the Hash calculation of a specific field of the message through the Hash engine according to a key value, and generating a Hash value; in the ECMP, performing routing according to the hash value and the currently activated link to obtain a forwarding exit; wherein at least two links are included, and each link is configured with a different routing algorithm; and forwarding the message according to the forwarding exit. According to the method, algorithms with different characteristics are packaged in the ECMP and are combined with a Hash algorithm in the Hash engine to form a product-level algorithm combination, and a better load effect is achieved by analyzing, monitoring and counting the flow and switching the algorithms when the load is not uniform.

The application provides a multi-agent optimal allocation method of a dynamic routing algorithm, relates to the technical field of artificial intelligence, and comprises the following steps: obtaining a task characteristic matrix, constructing a multi-agent capability matrix, constructing a multi-objective optimization function containing a specialty matching degree, a cost and a performance standard degree based on the task characteristic matrix and the multi-agent capability matrix, and solving and obtaining an optimal allocation scheme by using an improved genetic algorithm; supporting user intervention and automatically checking and updating; and monitoring a load in real time and dynamically migrating tasks when overload is detected. The application improves resource allocation efficiency, enhances system robustness, and realizes intelligent load balancing.

The application discloses a kind of high reliability and flexibility routing methods for strong confrontation self-organizing network, mainly solve the problem of low business delivery rate and slow routing convergence speed in strong confrontation scene using traditional routing algorithm.The implementation scheme is divided into topology control and routing two parts:Among them, routing includes: using the node information obtained by topology control to complete the routing discovery process, and constructing the whole network routing table;Through routing-topology joint, periodic and active two ways are used to jointly maintain the whole network routing table.Topology control includes:1) constructing the network topology structure of bidirectional link;2) maintaining one-hop routing table according to logical neighbor list;3) repeating 1)-2) until the network stops running.The application can maintain high end-to-end business delivery rate in strong confrontation scene, quickly complete the routing discovery process, improve the routing convergence speed, improve the stability and reliability of path, and can be used for mobile self-organizing network business data transmission.

This paper proposes a method for detecting finger vein spoofing attacks based on capsule networks. Capsule networks are not only suitable for small-sample finger vein datasets, but also, by replacing neurons with vector-represented capsules on top of CNNs, they can better handle spatial information such as relative position and angle, enhancing the network's adaptability to finger offset and rotation scenarios. A Bayesian routing algorithm is proposed, incorporating the differential entropy of the capsules as a consideration in calculating activation values. During final classification, feature capsules with high activation probabilities and high concentration are selected, which helps improve the accuracy of classifying genuine and fake veins. By simulating the uncertainty of capsule parameters, training errors can be reduced, improving recognition accuracy.

The invention relates to the technical field of hyperspectral image classification, and discloses a hybrid network method for hyperspectral image classification, which comprises the following steps: preprocessing a hyperspectral image, dividing the hyperspectral image into a training set and a test set, inputting the data into a 3D CNN, extracting space and spectral features through three-dimensional convolution operation, introducing nonlinearity by applying an activation function ReLU, and extracting the hyperspectral image through a three-dimensional convolutional neural network; the method comprises the following steps: reducing image dimensions through respe operation, extracting spectral features through a 3D CNN, sending the spectral features into low-level capsules of a capsule network, extracting low-level features of HSI after passing through the 3D CNN, carrying out nonlinear compression on vectors of the capsules by using a nonlinear activation function Squash, updating connection weights between the capsules by using a dynamic routing algorithm through an iteration mode by using a high-level capsule, and carrying out nonlinear compression on the vectors of the capsules by using a high-level capsule. The extracted feature vectors are mapped to probability distributions of different categories by using a full connection layer, the trained classifier is evaluated and tested by using a test set, the classification accuracy is calculated, a spectrogram and a spatial feature map can be fully utilized, and the accuracy of spectral image classification is improved to the maximum extent.

The invention relates to a transformer area low-voltage communication dual-module networking method, device, equipment and medium, the method is applied to a central master control node deployed at the low-voltage side of a distribution transformer of a transformer area, and the method comprises the following steps: completing the division of a transformer area network through a broadcast mode based on a dual-module networking environment; calculating an optimal communication path to each network sink node in the transformer area network according to a routing algorithm; and generating a routing topological graph of the area network according to the optimal communication path, and issuing the routing topological graph to each network aggregation node to complete communication routing networking. According to the invention, communication quality and network stability can be improved.

Systems and methods for using InfiniBand routing algorithms for Ethernet fabrics in a high performance computing environment. The method can provide, at a computer comprising one or more microprocessors, a plurality of switches, a plurality of hosts, a topology provider (TP) module, a routing engine (RE) module, and a switch initializer (SI) module. The method can perform a discovery sweep, by the TP, of the plurality of hosts and the plurality of switches and assigns an address to each of the plurality of hosts and the plurality of switches. The method can calculate, by the routing engine, a routing map, based upon a routing scheme, for the plurality of hosts and the plurality of switches, the routing map comprising a plurality of forwarding tables. The method can configure, each of the plurality of switches with a forwarding table of the plurality of forwarding tables calculated by the routing engine.

The invention particularly relates to a time-triggered service scheduling method and system based on flow feature grouping. The method comprises the following steps: firstly, constructing a network scheduling model and acquiring cycle and frame length parameters of all TT services to be scheduled; then, a multi-target conflict awareness routing algorithm is adopted to plan a service route; secondly, extracting the period, frame length and routing characteristics of the service to construct a comprehensive distance matrix, and performing characteristic grouping on the service by using K-means clustering; then determining an intra-group scheduling sequence in each group according to a period, a frame length and a conflict index rule; and finally, optimizing the packet scheduling sequence through tabu search to generate a global scheduling table. According to the method, the scheduling problem scale is reduced through flow feature grouping, the TT service scheduling with high scheduling success rate, high calculation efficiency and strong adaptability in a large-scale complex scene is realized by combining heuristic sorting and tabu search optimization, and the problems of high calculation complexity, need of pre-training, poor flexibility and slow convergence in the prior art are solved.

The invention discloses a cryptographic service interface packaging technology based on a virtualized cryptographic module and an implementation device, and solves the problems of difficult resource expansion, complex interface integration, insufficient security isolation and the like of a traditional cryptographic scheme. The technical core comprises virtualized cryptographic module construction, interface packaging design and device integration, wherein physical cryptographic resources are abstracted through the Docker / KVM technology to generate virtual examples, and loads are dynamically adapted through a resource allocation model; the interface packaging layer provides uniform interfaces such as RESTfu API, PKCS # 11 and the like, and integrates a strategy engine and an intelligent routing algorithm; the device is composed of hardware such as a server cluster and a password acceleration card, a virtualization engine and an interface packaging module, and password services are provided according to a standardized process. Through verification of a power grid scene, the resource utilization rate of the technology is improved by more than 30%, the integration cost is reduced by 60%, the requirements of safety compliance and real-time performance are met, and the technology is suitable for multi-scene password service requirements of cloud native, energy and the like.