638 results about "Subnetwork" patented technology

The invention belongs to the field of artificial intelligence, particularly relates to a power plant infrastructure multi-target intelligent scheduling optimization method, and aims to solve the problems of static weight imbalance, disturbance response hysteresis and process coupling effect modeling insufficiency of traditional scheduling. According to the method, a multi-dimensional space-time semantic model is constructed, BIM, sensor and environment data are integrated, construction period, cost, resource and safety four-dimensional target weights are dynamically set, and an improved non-dominated sorting genetic algorithm is adopted to generate an initial Pareto optimal schedule; and then inferring an inter-process nonlinear coupling delay factor through a graph neural network, embedding a disturbance response module, starting local rolling re-optimization when a progress deviation or an external event is detected, limiting an influence subnet and freezing a stable region. According to the scheme, stage self-adaptive target focusing, chain risk pre-buffering and minute-level robust adjustment are achieved, the stability of a critical path is improved by 45%, the secondary optimization frequency is reduced by 60%, the calculation efficiency and the execution toughness are both considered, and efficient and accurate landing of a large power plant infrastructure project is supported.

A distributed cloud computing system is disclosed that includes a controller configured to deploy network constructs including any of transit gateways, spoke gateways, subnets, or private networks and logic that, upon execution by one or more processors, causes performance of operations including: causing rendering of a graphical user interface that includes a display panel configured to display progress of a build process for a network topology graph, receiving first user input through the graphical user interface indicating selection of a first cloud service provider, a first access account, and a first cloud region, receiving second user input through the graphical user interface indicating selection of one or more of the network constructs to be deployed in the first cloud region, instructing the controller to deploy the one or more of the network constructs in the first cloud region according to the first user input and the second user input.

The invention discloses a generative adversarial network architecture search method and system and an image generation method, and belongs to the technical field of network architecture search. The searching method comprises the following steps: performing single-path sampling on a pre-constructed generator super network according to a parameter quantity constraint range to obtain an effective subnetwork; training the generator super-net by adopting a complexity adaptive learning rate optimization strategy to obtain a pre-trained generator super-net; adversarial training is carried out on the generator hypernet and the discriminator to obtain a pre-trained discriminator; generating a generator super-network candidate architecture through a genetic algorithm in the early stage of the evolution stage and through a covariance matrix self-adaptive evolution strategy in the later stage of the evolution stage; and performing multi-target non-dominated sorting on the generator super-network candidate architecture, updating an effective sub-network and keeping a Pareto optimal solution to obtain a searched optimal generator architecture and further obtain a searched optimal generative adversarial network architecture. The method not only ensures the search quality, but also improves the calculation efficiency.

The invention discloses a rail transit comprehensive dispatching emergency response method and system based on the Internet of Things, and relates to the technical field of the Internet of Things. The method comprises the following steps: acquiring a rail transit comprehensive scheduling instruction queue through a rail transit Internet of Things terminal; sending the instruction queue to an emergency analysis engine, performing emergency scoring, and obtaining a scoring index queue; an RS-485 subnet layer is built by a plurality of paths of RS-485 interfaces arranged by the gateway; the mapping relation between the instruction queue and the RS-485 subnets is established according to the scoring index queue, and the gateway responds to the instruction queue on the RS-485 subnets in a grading mode on the basis of the mapping relation. The technical problems that the emergency response is delayed and the communication efficiency is low due to the fact that an existing rail transit dispatching system cannot intelligently recognize the emergency degree of an instruction are solved, and the technical effects of improving the emergency response efficiency and optimizing network resource utilization through emergency scoring and RS-485 subnet grading response are achieved.

A system and method to protect resource servers from DDOS attacks is disclosed. A proxy gateway hides resource server using IP subnet addressing and receives authenticated IP packets. A cryptographic hash is generated, and destination IP packets address / ports are encrypted using a secret, algorithm, client IP address, resource server IP address, and port. The cryptographic hash and destination server are mapped into existing IP packet addresses, ports, or payload bits. The IP packets are routed to a redirect node in the public IP subnet of the proxy gateway. At the redirected node, the cryptographic hash is validated, and the resource server IP address and the port are extracted from mapping. Redirect node maps the clients public IP / port to an internal IP address and port associated with resource server and tunnels the IP packets from the redirect node to the resource server using the internal IP address and port.

The invention discloses a knowledge graph enhanced retrieval method, system and device based on a large reasoning model and a medium, and the method comprises the steps: collecting documents processed by operation and maintenance personnel for establishing a knowledge graph database; performing network topology division on the knowledge graph in the knowledge graph database by adopting a grid division algorithm to obtain a plurality of sub-grids, and mapping a data set in the sub-grids into a sub-knowledge graph; inputting the question into the large model, selecting the sub-knowledge graph as a query range according to a keyword in the question, performing node expansion query and relation expansion query by the large model in the knowledge graph database, and returning an answer; matching the answers with the sub-knowledge maps, performing quadrant positioning on nodes of the sub-knowledge maps, and jointly generating a report by node coordinates, grid IDs and information associated with the answers; and calculating the text confusion degree of the report for measuring the performance of the large model, and if the text confusion degree is higher than a threshold value, adjusting the parameters of the large model. The knowledge retrieval speed is high, and the accuracy is high.

The invention discloses an urban road intelligent drainage scheduling system and method based on the Internet of Things. The method comprises the following steps that an urban road drainage Internet of Things sensing network is constructed, and a multi-source heterogeneous data set corresponding to an urban road target area is collected; performing space-time alignment and noise filtration processing on the multi-source heterogeneous data set, and meanwhile, performing ponding increase rate and pipe network pressure bearing evaluation to obtain urban ponding increase rates and drainage pipe network pressure bearing degrees corresponding to different urban road subnetworks; calculating drainage pipe network negative pressure indexes corresponding to the different urban road section sub-networks according to the urban water accumulation increasing rates and the drainage pipe network pressure bearing degrees corresponding to the different urban road section sub-networks; and acquiring an urban road network topological structure, performing drainage hierarchical scheduling processing, issuing the urban road network topological structure to drainage facilities in corresponding areas to execute drainage scheduling and feed back scheduled drainage effect data, and re-executing closed-loop scheduling if the drainage effect data is not accordant with the drainage effect data. According to the invention, accurate drainage scheduling of the urban road area can be realized.

The invention provides a network topology relation graph dynamic generation method, which belongs to the technical field of network topology, and comprises the following steps: starting an improved Tarjan strong connectivity component algorithm in each subnet partition to carry out loop detection, executing distributed loop verification on cross-subnet boundary nodes, collecting ARP table entries, routing table entries, OpenFlow flow tables and virtualization platform interface data, and sending the ARP table entries, the routing table entries, the OpenFlow flow tables and the virtualization platform interface data to each subnet partition; the method comprises the following steps: performing power spectrum analysis on an optical power monitoring point on optical network equipment to identify a wavelength channel occupancy state, reconstructing a wavelength routing path of a DWDM system, and performing two-stage submission on topological data acquired by distributed detection nodes by adopting a causal consistency protocol to synchronously generate a global unified network topological relation graph; the technical problems that the incremental updating efficiency is low and the cross-layer mapping relation is difficult to reconstruct in real time when the network topology dynamically changes are solved.

A wireless communication method includes: obtaining subnet information of a first subnet corresponding to a first session; receiving a data packet, where the data packet is a multicast packet or a broadcast packet; determining, based on the subnet information, that the data packet corresponds to the first session in the first subnet; and sending the data packet via the first session.

The invention relates to the technical field of video analysis and processing, and discloses a key frame extraction method based on hierarchical attention and potential gating and related equipment. The method comprises the following steps: analyzing an original video stream and separating frames, adjusting the resolution and normalizing to obtain a standardized sequence; inputting the standardized sequence to a multi-stage convolutional neural network encoder, generating multi-stage spatial features, and obtaining a spatial attention map through attention mapping; pooling the lowest resolution feature to obtain a frame-level embedded vector sequence, and performing time sequence conversion to obtain time sequence attention association information; constructing a potential gating sub-network containing a strategy network, wherein the strategy network outputs spatial feature weights of all levels; the fusion unit sums the spatial features and the corresponding attention maps according to weights, and fuses time sequence results to obtain a fusion feature sequence; and outputting a frame importance score after the scoring network processing, and screening according to the importance score to obtain a target key frame. According to the method, key frame extraction accuracy is improved, and redundant frames are effectively reduced.

The invention discloses a reverse knowledge distillation-based cross-stage feature fusion method for industrial anomaly detection and positioning, and relates to the technical field of knowledge distillation and transfer learning. The method comprises the following steps: step 1, constructing a teacher network encoder, a student network encoder and a decoder; 2, extracting input image features through a student network encoder, and reconstructing the features through a student decoder; step 3, student network cross-stage feature fusion design; 4, locally sensing a dynamic attention module LDA, and adding a sliding window and convolution to replace original global pooling; and step 5, a self-adaptive multi-scale feature fusion module CAAMS-FF establishes a dependency relationship of a context so as to realize a fine-grained high-quality feature reconstruction effect. And step 6, inputting an anomaly graph obtained by the teacher-student network into the segmentation sub-network to obtain a final anomaly detection and positioning result. While the calculation efficiency is maintained, the spatial positioning precision and the multi-scale adaptability are significantly improved.

The invention provides a data processing method and system based on intelligent teaching, and the method comprises the steps: obtaining a real-time interaction data flow uploaded by a multi-mode interaction terminal through a knowledge graph processing engine, carrying out the spatial-temporal feature decoupling of the real-time interaction data flow, and extracting an interaction behavior feature vector; mapping the interactive behavior feature vector to a preset teaching resource knowledge graph, positioning a target knowledge node, and constructing a dynamic semantic topology subnet based on an adjacency relationship; calculating the projection deviation of the interactive behavior feature vector in the dynamic semantic topology subnet, and generating a cognitive divergence vector representing the cognitive state deviation degree; and generating a data stream reconstruction instruction based on the cognitive divergence vector, calling the associated semantic slice from the teaching resource knowledge graph according to the instruction to synthesize and encode the basic teaching data packet in real time, generating a target compensation data stream, and issuing the target compensation data stream. According to the invention, the real-time accurate adaptation of the teaching data stream and the user cognitive state is realized.

The application discloses a display method and device of topology information, equipment and computer readable storage medium, and belongs to the technical field of communication. The method comprises the following steps: acquiring topology information of a public subnet corresponding to a display request for a first network resource, wherein the public subnet comprises a first subnet and a second subnet, the first subnet is a subnet comprising the first network resource, the second subnet is a subnet other than the first subnet, the topology information comprises information of at least one network resource of the first subnet and the second subnet and a connection relationship between the at least one network resource; and on the basis of displaying the topology information, the first network resource is displayed differently. By displaying the topology information comprising the information of at least one network resource of the first subnet and the second subnet and the connection relationship between the at least one network resource, the displayed topology information is more comprehensive, the first network resource is displayed differently in the topology information, and the first network resource is displayed with a better visual effect.

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

The invention relates to the technical field of control and regulation systems, and discloses an LED energy-saving lamp internet-of-things control system with an edge computing function, which comprises a central management platform, an edge computing gateway and an LED energy-saving lamp control terminal, and the edge computing gateway processes environment sensing data in real time and generates a dimming instruction through a local decision engine and a collaborative scheduling algorithm, constructs a regional autonomous control subnet to realize lamp collaborative control, and improves illumination continuity and system robustness through a cross-gateway collaboration and local cache mechanism. According to the invention, cloud dependence and bandwidth requirements are reduced, visual flicker is eliminated, and accurate energy consumption control is realized.

The invention belongs to the technical field of biological information calculation, and discloses a pet feed additive formula calculation model optimization system, which comprises a data interface for acquiring raw material parameters and data containing environmental stress factors; the memory stores a heterogeneous neural network model, and comprises a first time sequence convolution subnet, a second cascade processing subnet and a global gating distribution unit which are arranged in parallel and are coupled through a lateral suppression channel; the processor operates the model, the global gating distribution unit is used for dynamically adjusting the computing power weight between the subnets according to the system energy state tensor, and back propagation iteration is carried out based on a nonlinear constraint penalty term. The problems of convergence difficulty and negative migration when a general model processes high-dimensional strong-coupling biological data are solved, and the prediction precision and safety of formula optimization are improved.

Systems and methods herein are for one or more processing units that can communicate in a network using a subnet manager (SM) that includes a mapping of one virtual network address to two or more physical ports, where the one virtual network address may be associated with different switches of different data planes, and where data may be communicated concurrently and separately using the one virtual network address and using the two or more physical ports.

A method for discovering ownership assignment of computer devices includes obtaining a set of unassigned internet protocol (IP) addresses. The multiple computer devices are assigned to multiple teams of an organization such that each team is assigned to a segment of the sequence of IP addresses. The method includes converting each IP address into a numerical value. The method includes obtaining a set of assigned IP addresses from an assigned IP address database and obtaining a subnet allocation for each IP address in the set of assigned IP addresses. For a particular unassigned IP address, the method includes a reference IP address from the set of assigned IP addresses and determining whether the particular IP address and the reference IP address have a same subnet allocation. The method includes determining the ownership assignment based on the subnet allocation.

A method and a system for networking a water network system are provided, including: collecting digital elevation raster data of a study area, identifying rivers within the study area, and dividing the study area into several subnets, each contains several sub-basins; constructing evaluation models for each subnet and optimizing model parameters and hyperparameters, and calculating comprehensive evaluation results of a coordinated state of water resources-ecological environment-economic and society; sorting the characteristic values and evaluation indicator values, constructing a feasible networking scheme set, constructing complementary indicators, forming a matched networking scheme set and calculating engineering construction cost, constructing an optimal scheduling model, and calculating to obtain an optimal scheduling mode and networking benefit; setting a networking cost range, determining the networking scheme and inputting it into a pre-constructed optimal networking decision model, and calculating to obtain a networking scheme of the water network system.

The invention relates to the technical field of artificial intelligence and brain-computer interfaces, and discloses a brain-computer interface method and system based on dynamic hierarchical splitting federated learning and a medium, and the method comprises the steps that a client reports a local state; the reinforcement learning agent dynamically decides a joint action for each client based on the global state; the client calculates and uploads an intermediate activation value to the central server; and the server completes residual calculation and returns the gradient, and the client and the server update the subnet parameters respectively. According to the method, joint optimization is carried out on split layer selection and wireless resource and computing resource allocation through reinforcement learning, dynamic self-adaptive decision is realized by taking comprehensive reward of model identification precision, training time delay and client energy consumption as a target, communication overhead and training time delay are remarkably reduced on the premise of strictly protecting user data privacy, and user experience is improved. The terminal energy consumption is reduced, and the training efficiency and the final recognition performance of the model in the dynamic heterogeneous network environment are improved.

The invention belongs to the technical field of mental disease auxiliary diagnosis, and particularly relates to a mental disease I auxiliary diagnosis method based on a Transform sub-network asynchronous model. Based on a sub-network embedded Transform asynchronous model, taking fMRI data as input, and taking an evaluation result as output; the Transform asynchronous model based on sub-network embedding comprises a time sequence partitioning device, an SNP-n sub-network partitioning module, a self-attention module and an asynchronism capturing module, and is obtained by performing end-to-end supervised learning on the basis of a PyTorch framework in a three-level core architecture of time sequence partitioning, sub-network partitioning and asynchronous capturing. And finally, a result obtained through the sub-network embedded Transform asynchronous model is classified and evaluated through a classification module. The auxiliary diagnosis accuracy is remarkably improved through the method, and the method comprehensively exceeds static and traditional dynamic methods.

The invention discloses a multi-modal fusion automatic modulation identification modal importance analysis method, which comprises the following steps: constructing a multi-modal data set comprising four modals of IQ, AP, PSD and FFT, and dividing the data set; a Transform encoder based on an attention module is designed, so that features with more comprehensive and deeper modals can be extracted; a heterogeneous sub-network is designed for the four modes, and the features of each mode are extracted; respectively constructing a multi-modal feature fusion network MF-AMC and four single-modal networks based on the constructed dual-branch feature fusion module and the above modules, and training the networks; according to the method, an SHAP interpretability analysis method is innovatively introduced, and the contribution degree of different modals to a classification result is quantitatively evaluated by calculating the Shapley value of each modal feature. According to the method, an interpretable theoretical basis is provided for modal selection and fusion strategy optimization in multi-modal modulation recognition, and the accuracy and robustness of signal recognition in a complex channel environment are remarkably improved.

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for training a denoising neural network and, once the denoising neural network is trained, generating new images using the denoising neural network. In particular, the described techniques include obtaining data specifying a trained initial denoising neural network, obtaining training data, and training, using the training data and on a denoising objective, a target denoising neural network. The target denoising neural network includes the core-subnetwork of the trained initial denoising neural network, but also includes a target encoder and decoder neural networks that are not included in the trained initial denoising neural network. By training a target neural network that includes the core-subnetwork of a trained initial denoising neural network, the system achieves stable training of a large-scale target denoising neural networks that can be used to generate high resolution images.

Disclosed are a panoramic image super-resolution method and system, an electronic device, and a storage medium. The method comprises: establishing a panoramic image super-resolution model based on latitude-graded enhancement, the model comprising a feature extraction sub-network, a deep feature enhancement sub-network, an upsampling sub-network, and a reconstruction sub-network, wherein the feature extraction sub-network is used for extracting shallow features of an input panoramic image; the deep feature enhancement sub-network, by means of cascaded latitude-graded enhancement units, performs graded deep enhancement on shallow features of different latitude regions, and refines high-frequency information of different latitudes on the basis of differences in feature distribution across different latitude regions in the panoramic image, so as to obtain enhanced features; the upsampling sub-network uses sub-pixel convolution layers to amplify the spatial resolution dimensions of the enhanced features; and the reconstruction sub-network restores the amplified enhanced features into a high-resolution panoramic image. The present invention solves the problem of differences in feature distribution across different latitudes in panoramic images, and improves the super-resolution performance of panoramic images in various scene environments.

Various aspects of the subject technology relate to systems, methods, and machine-readable media for generating a heterogeneous network of blockchains. The method includes generating a platform blockchain having a single replicated state machine. The method includes generating at least one subnet based in part on the platform blockchain, the subnet including at least one blockchain, the generating causing bonding or burning of a base asset of the platform blockchain. The method includes specifying validators for the at least one subnet. The platform blockchain includes a source of truth for transactions across the subnets.

The present application relates to a kind of hierarchical concurrent state migration net methods for digital twin virtual debugging, the main principle and structure of mechanism that the method has and main construction process are listed;The method is realized by composite state and subnet mechanism hierarchical abstract management of macroscopic process and microscopic execution details, utilizes global event publishing-response and cross-subnet state dependence mechanism to realize the dynamic linkage and synchronous interlocking between concurrent components, and the mutual exclusion access and release of shared resources are completed in combination with global resource token mechanism.Based on this, visual and verifiable concurrent process model can be generated in virtual debugging environment, and deadlock detection and resource bottleneck analysis are supported, thereby significantly improving the accuracy, reliability and maintainability of complex production unit or software system digital twin virtual debugging.

The embodiment of the invention relates to a resource configuration method and device, computer equipment and a storage medium, when it is detected that a first virtual private cloud creates a product instance, bottom layer resources corresponding to the product instance are deployed to a target subnet of a second virtual private cloud, and a target address field is preset in the second virtual private cloud; the target address field comprises a target subnet; binding an elastic network card in the first virtual private cloud with a cloud server of a second virtual private cloud to enable the first virtual private cloud and the second virtual private cloud to communicate through the bound elastic network card; and configuring the underlying resources of the product instance in the communication process. Therefore, the bottom layer resource of the product instance of the first virtual private cloud can be deployed in the fixed second virtual private cloud, and communication between the two virtual private clouds is constructed, so that configuration of the deployed bottom layer resource is realized, direct configuration of the bottom layer resource on a user side is avoided, and the security of cloud product resource deployment is improved.

A neural network system includes a separable convolution subnetwork. The separable convolution subnetwork includes a plurality of separable convolutional neural network (SCNN) layers arranged in a stack manner in sequence. Each of the plurality of SCNN layers applies a first grouped convolution to an input to the SCNN layer. An input to the first grouped convolution includes a plurality of channels, and the first grouped convolution is a spatial convolution which divides channels of an input to the first grouped convolution into groups in a channel-wise manner, convolves the grouped channels, and couples the convolved channels to generate an output.

The application discloses a dynamic communication path selection and switching method for a full interconnection network, specifically comprising the following steps: renumbering all nodes in the full interconnection network; planning a communication path between any two nodes in the full interconnection network; after all the communication paths are sorted out, each communication path is tried in turn, and the message sending time corresponding to each path is recorded; and the time of acquiring the message transmission of each path is taken as the basis to select the shortest message transmission path from the historical record of message transmission as the message transmission path in the future. The application is based on the improved e greedy algorithm, dynamically adjusts the communication path of concurrent tasks, frequently selects and switches the communication path between communication nodes, avoids the subnet area that may have a conflict in the interconnection network, and further reduces the communication delay and the processing time of concurrent tasks in the network.

The invention discloses an OFDM (Orthogonal Frequency Division Multiplexing) communication channel estimation and signal detection method and system, and belongs to the technical field of channel estimation. The OFDM communication channel estimation and signal detection method comprises the following steps: receiving an LDACS downlink OFDM baseband signal; pilot frequency and data subcarriers are separated; arranging pilot frequency observation into a time sequence block according to a frequency index, and constructing a channel estimation subnet input tensor; performing convolution feature extraction and LSTM (Long Short Term Memory) time sequence modeling on the pilot frequency time sequence block in sequence, and outputting channel estimation of each subcarrier; performing frequency domain equalization on the data subcarriers; the signal detection subnet firstly extracts time sequence features through LSTM, then distributes weights through a self-attention mechanism, and finally outputs bit judgment through full connection; performing parameter optimization on the channel estimation subnet and the signal detection subnet by adopting a two-stage training strategy; the number K of subcarriers, the number P of pilots, the CP length and subcarrier mapping are set according to an LDACS frame structure and a protection interval, and an LDACS link layer interface is directly connected. By adopting the OFDM communication channel estimation and signal detection method and system provided by the invention, the problems of poor estimation precision and insufficient robustness of the existing method in a complex LDACS airspace channel environment can be solved.