91 results about "Network level" patented technology

The invention provides a low-power-consumption cooperative sewer water body integrated monitoring method. The method comprises the following steps: carrying out model selection and deployment on sensing node hardware of an adaptive scene; a low-power-consumption internet of things network topology and power supply design; a time-sharing triggering acquisition strategy of the multi-modal data is carried out; node-level environment self-adaptive data calibration is carried out; node-level flow velocity-stink association anomaly recognition is carried out; carrying out network-level data fusion and validity verification; collaborative traceability, diffusion simulation and linkage control are carried out. According to the invention, the problems of data distortion, difficulty in source tracing of pollution sources, short equipment endurance and response lag caused by independent collection of flow and stink and environmental interference in traditional sewer monitoring are solved; the integrated effect of ultrasonic Doppler and electronic nose cooperative monitoring, environment self-adaption accurate calibration, odor source rapid positioning and diffusion simulation and low-power-consumption and long-endurance linkage control is achieved.

Systems and methods are disclosed that relate to Key Performance Indicator (KPI)-driven alarm threshold optimization using machine learning. In one embodiment, a computer-implemented method comprises obtaining network-level KPI data for a network and radio log data for one or more radio systems in the network. The KPI data comprises KPI values for one or more network-level KPIs, and the radio log data comprises a number of faulty or uncalibrated antenna branches in the radio system and cell or user beamforming weights. The method further comprises pre-processing the KPI data and the radio log data, labeling the pre-processed KPI data as degraded or non-degraded, and training, with the labeled KPI data and the pre-processed radio log data, a fault classifier Machine Learning (ML) model to output a value(s) that represent a probability that the KPI(s) will be degraded for a given input feature set.

A method and system are provided at a local network level and a remote cloud level. The local network level includes compressors and a controller configured to create a short-term schedule having a short-term switching sequence for operation of the compressors, perform a validation assessment on the short-term schedule, and send the short-term schedule to a platform embedded with the main controller of the system. A prediction model, a long-term scheduling approach, and cloud storage that stores measurements from the compressors and executable instructions are provided at the remote cloud level. The long-term schedule is transferred to a safety check module at the local network level. Following validation, the embedded platform refines the long-term switching sequence and the safety check module allows the system to implement the long-term schedule, having the short-term schedule as a backup option.

The application discloses an APT flow detection method based on a knowledge graph, which comprises the following steps: analyzing network data flow characteristics in network flow, establishing a knowledge graph of network data flow, and classifying the established network flow knowledge graph by using a graph neural network algorithm to detect APT attack flow in the network, so that the attack behavior of an APT organization can be detected from the network level. The application can detect unknown APT attack network data flow, and is helpful for flexibly and accurately detecting APT flow.

The invention discloses a distributed system and method for providing end-to-end deterministic time delay guarantee, a terminal and a storage medium. The system comprises a super object model time sequence extension module, a global time synchronization module and a distributed deterministic scheduling module. The super object model time sequence extension module is used for defining distributed tasks or equipment capabilities in the system, and the global time synchronization module is used for synchronizing clocks of whole network equipment by using a high-precision synchronization protocol to obtain a unified time reference; the distributed deterministic scheduling module is used for planning a scheduling period of a hard real-time task based on an end-to-end time sequence requirement and a time reference, calculating an end-to-end communication path meeting the time sequence requirement of the hard real-time task according to a real-time network state and the scheduling period, and scheduling the hard real-time task based on the time reference. According to the invention, resource reservation is carried out on an end-to-end communication path on a network level and an operating system kernel level, a service layer time sequence demand is associated with bottom layer network scheduling, and end-to-end microsecond-level deterministic guarantee is realized.

The application relates to a light wavelet enhancement fusion medical image segmentation method, and belongs to the technical field of medical image processing and computer-aided diagnosis. The core of the method is to construct a light WEF-Net network, which comprises an encoder, a bottleneck layer and a decoder. The encoder adopts a dual-domain perception module, extracts complementary features from the frequency domain and the time domain through wavelet transformation and convolution, and simultaneously extracts complementary features from the frequency domain and the time domain. The bottleneck layer is designed with a feature aggregation Kolmogorov-Arnold transformation module, which is used for efficiently fusing multi-scale semantic information and enhancing the nonlinear modeling capability. The network level also integrates a sawtooth rolling feature fusion module, which enhances the global continuity of the features through the channel rolling and spatial scanning mechanism to improve the integrity of the boundary segmentation. Experiments show that the method realizes excellent performance on multiple public medical image datasets, while maintaining low parameter quantity and low computational quantity, and significantly improves the segmentation precision.

The invention relates to the technical field of industrial Internet of Things communication, in particular to an AUTBUS node device and system with a CN-TN main and standby redundancy function. The device comprises a device main framework, a main CN module, a standby CN module, a high-speed internal communication bus and a local redundancy management module, the main CN module and the standby CN module are independent pluggable hardware units, and the main CN module synchronizes core state data to the standby CN module through a high-speed internal communication bus; the local redundancy management module is integrated on the device main framework, is logically independent of an AUTBUS bus protocol stack, and is used for monitoring an internal fault of the main CN module and triggering a local takeover process when monitoring that the main CN module has the internal fault; according to the method and the device, rapid seamless switching is realized on the premise of not triggering network-level re-election, so that the reliability of the AUTBUS node device is improved, and the continuity and the certainty of the time sensitive characteristic of the AUTBUS system are guaranteed.

Various embodiments of the present disclosure provide a network linking technique that improves the functionality of a computer in various aspects. The techniques comprise receiving a member-specific assertion request encapsulating an assertion request from a user of the first member platform; determining a local construct of a cross-platform data object; determining, using the local construct of the cross-platform data object, a second member platform; providing an internal member-specific assertion request to an internal service associated with the second member platform; providing, via the internal service, an incoming member-specific assertion request to the second member platform; responsive to receiving a user input at the second member platform, receiving an assertion response at the internal service and from the second member platform; and providing the assertion response to the first member platform.

A network level adaptive based lightweight feature map compression method, in the forward inference process of a convolutional neural network, when the intermediate feature map output by the activation function needs to be exchanged between the calculation unit and the off-chip memory due to the limited on-chip storage resource, the intermediate feature map is first compressed, that is, the network shallow layer feature map is subjected to transform domain processing by using integer discrete cosine transform, the network deep layer feature map is subjected to block maximum value extraction processing, then unified quantization processing and entropy coding processing are performed, the compressed feature map is written into the off-chip memory, so as to reduce the data size, thereby reducing the off-chip storage access bandwidth requirement and data carrying energy consumption. The present application is a feature map compression method which does not depend on neural network retraining, can fully utilize the spatial correlation of shallow layer feature map, has low calculation complexity and good hardware implementation characteristics, so as to significantly reduce the storage and energy consumption overhead in the inference process of the convolutional neural network under the premise of ensuring the inference accuracy.

Various embodiments of the present disclosure provide a network linking technique that improves the functionality of a computer in various aspects. The techniques comprise responsive to an exchange request, receiving, originating from a member platform within the member computing ecosystem, a linking code request comprising a member-specific identifier corresponding to the member platform; providing, to an internal service, the linking code request to generate an ephemeral transport object storing a linking code and a link reference corresponding to the member-specific identifier and the linking code; providing the linking code to the member platform; receiving, originating from the another member platform within the member computing ecosystem, a linking request comprising the linking code; and authorizing, using the second member platform, the exchange request based on the linking code.

The invention discloses an AI service strategy updating method and device, a functional entity, a medium and a product, and relates to the technical field of communication, and the method applied to a first functional entity specifically comprises the steps: determining the execution capability information of the first functional entity based on the network state information of the first functional entity, when it is detected that execution capability information does not meet a preset capability index, a first service strategy adopted for executing the first AI task is updated, and the execution capability information is used for representing the capability of the first functional entity for executing the first AI task; and / or, receiving a first policy adjustment request sent by a second functional entity, and updating the first service policy based on the first policy adjustment request, the second functional entity and the first functional entity being functional entities deployed at the same network level; the first service strategy comprises at least one of a connection control strategy, an AI model selection strategy, a radio bearer DBR configuration strategy and a resource configuration strategy of the first functional entity.

The application belongs to the technical field of launch vehicle electronic information system, and particularly relates to a launch vehicle communication network system based on Powerlink. The system comprises a two-stage star network of a launch vehicle, an inter-stage star network, a first-stage tail star network and a main bus adopting a Powerlink bus; a plurality of terminal slave nodes in the two-stage section access a two-stage network repeater through a star topology communication link, a master node and the two-stage network repeater are connected in series to the main bus through a two-stage interface; a plurality of terminal slave nodes in the inter-stage section access an inter-stage network repeater through a star topology communication link, a redundant master node and the inter-stage network repeater are connected in series to the main bus through an inter-stage interface; a plurality of terminal slave nodes in the first-stage tail section access a first-stage tail network repeater through a star topology communication link, and are connected to the main bus through a first-stage tail interface. The system has high real-time performance and high reliability.

The invention provides a rail transit heterogeneous network seamless roaming method and system based on multi-level switching, and relates to the technical field of rail transit network communication, and the method comprises the steps: constructing a space-time transfer matrix to predict a motion track, carrying out the level division of a candidate access network, and calculating an optimal switching path; and calculating a resource reservation time length and reserving resources in advance in combination with the prediction trajectory and the network coverage range, and setting a sampling point to determine a switching trigger point to complete network switching. According to the invention, smooth transition between network hierarchies can be realized, the seamless roaming success rate is improved, and switching delay and service interruption are reduced.

Various embodiments of the present disclosure provide a network linking technique that improves the functionality of a computer in various aspects. The techniques comprise receiving an exchange request comprising a universally unique ephemeral key (UUEK); identifying a local data construct of a cross-platform data object based on the UUEK; providing a value request to a internal service corresponding to a member platform using the cross-platform data object; receiving, based on a contribution ruleset corresponding to the member platform, an updated exchange request from the internal service; providing an adjusted authorization request to another member platform based on the updated exchange request; receiving, from the other member platform, an authorization response based on the adjusted authorization request; and providing the authorization response to the terminal.

The embodiment of the invention provides a task scheduling method and device, management equipment and a computing equipment cluster, and relates to the technical field of cloud computing, the task method is applied to the computing cluster, the computing cluster comprises different network levels, and each network level comprises one or more network performance domains. Computing resources with the same network performance are distributed in the same network performance domain, and the method comprises the steps that the computing resource demand quantity of each task in a plurality of tasks and computing resource position constraints of one or more tasks in the plurality of tasks are obtained; according to the computing resource demand quantity of each task and the computing resource position constraint of one or more tasks, respectively dividing one or more affinity groups from computing resources of each network performance domain under each network level; scheduling of a plurality of tasks is performed in one or more affinity groups of each network performance domain under each network level. The method and the device can be compatible with task scheduling of computing clusters in different network forms.

Various embodiments of the present disclosure provide a network linking technique that improves the functionality of a computer in various aspects. The techniques comprise receiving an exchange request comprising a universally unique ephemeral key (UUEK); identifying a local data construct of a cross-platform data object based on the UUEK; providing a value request to a internal service corresponding to a member platform using the cross-platform data object; receiving, based on a contribution ruleset corresponding to the member platform, an updated exchange request from the internal service; providing an adjusted authorization request to another member platform based on the updated exchange request; receiving, from the other member platform, an authorization response based on the adjusted authorization request; and providing the authorization response to the terminal.

The application discloses a kind of distributed database two-stage transaction submission method and device based on RDMA, it is related to distributed database high-performance transaction processing technical field, comprising: in pre-commitment stage, data jump is completed using RDMA unilateral writing operation;Through polling, transaction redo log data is written successfully;In the submission stage, the atomic update submission state flag bit is carried out through the RDMA atomic comparison and exchange operation;When the number of successful times reaches the majority threshold value through polling RDMA completion queue, exit waiting loop and execute consensus achievement processing. It can eliminate the multiple network round trip and software processing delay in traditional protocol, so that the end-to-end transaction delay is reduced from the software protocol level to the hardware network level, the system CPU resources are released so that it does not need to participate in the protocol processing, so that the computing resources can be efficiently utilized, and the overall throughput and concurrent processing capacity of the distributed cluster are significantly improved.

The application provides a network-level disaster recovery exercise method and device, electronic equipment and medium. A target node and a primary center and a backup center establish a wireless backup network connection in a multi-domain name manner. The backup wireless network connection is in a long-living mode. The domain name priority of the primary center is higher than that of the backup center. The method comprises the following steps: in response to a disaster recovery exercise request, disconnecting the wireless backup network connection; in response to first terminal connection information of the primary center, verifying whether the target node successfully accesses the wireless backup network based on the domain name of the primary center. If not, obtaining second terminal connection information of the backup center; and verifying whether the target node successfully accesses the backup network based on the domain name of the backup center based on the second terminal connection information. Through the above method, the application can effectively solve the problems of complex network disaster recovery exercise process, high cost and influence on normal business operation, and improve the effectiveness of the disaster recovery network verification process.

The application discloses a target station area identification method and device, computer equipment and a storage medium. The first signal-to-noise ratio data of a nearby node, the network level of the nearby node and the second signal-to-noise ratio data of a neighbor node are acquired; and based on the comparison result of the network level of the nearby node and the network level of the current node, a network level coefficient set is generated; thus the first signal-to-noise ratio data is corrected by using the network level coefficient set to obtain the target signal-to-noise ratio data of the nearby node; and then the first station area belonging relationship of the current node can be identified according to the Z-score calculation results corresponding to the second signal-to-noise ratio data and the target signal-to-noise ratio data, the SNR calculation function in the signal receiving measurement process based on the communication module itself and the network level topology level statistical function of the communication module itself are realized, the signal-to-noise ratio amplitude is calculated by using the Z-score algorithm, the station area belonging relationship of the current communication module can be determined, and the station area identification rate is improved.

The invention provides a congestion control selection method and system based on reinforcement learning, and relates to the technical field of network congestion control. The method comprises the following steps: firstly, in an offline preparation state, dividing a network state into a plurality of grades, and matching a candidate congestion control algorithm pool for each network grade; after entering an online running state, collecting currently running network performance data, determining the grade of the currently running network performance data, loading a corresponding candidate congestion control algorithm pool, and monitoring the network dynamic state so as to feed back and adjust a network grade division basis of an offline stage; and a reinforcement learning agent is introduced, the selection of the congestion control algorithm is used as the action of the reinforcement learning agent, the reinforcement learning agent is trained, and the trained reinforcement learning agent is utilized to decide and output the congestion control algorithm. The preparation of the offline stage accelerates the convergence speed of training, can quickly and dynamically switch to the current optimal congestion control algorithm, and ensures the stability and high efficiency of network transmission.

The invention discloses an inference method during point cloud testing based on domain coding and a calibration header library. The inference method comprises the implementation steps that a point cloud classification model formed by cascading a source domain backbone network, the calibration header library and a lightweight mapping network is constructed; extracting deep semantic features of each point cloud sample in the data batch; carrying out joint training on the calibration head library and the mapping network; generating a domain coding vector representing a current data batch distribution state; performing weighted summation on K groups of preset parameters of the calibration head library in the combined weight vector; and performing classification prediction on the point cloud by using the obtained self-adaptive calibration parameters. According to the method, the reasoning speed and the real-time response capability of the point cloud model on edge equipment are remarkably improved, and the perception robustness of the model on different types of geometric deformation and sensor noise in target domain data is enhanced.

The present disclosure provides a fault positioning method, device, electronic equipment, program product and storage medium. The positioning method comprises: acquiring network quality parameters of one or more user equipment in a network; determining one or more faulty user equipment in the one or more user equipment based on the network quality parameters; determining one or more groups of faulty user equipment groups based on time sequence characteristics of the network quality parameters of the one or more faulty user equipment; determining a multi-level fault network topology for one or more faulty user equipment in the faulty user equipment groups, and positioning the fault in the network level by level based on the multi-level fault network topology. The present disclosure identifies the faulty user equipment by acquiring and analyzing the network quality parameters of the user equipment, groups the faulty user equipment based on the time sequence characteristics, determines the multi-level fault network topology, and realizes the positioning of the fault in the network.

The application discloses a network channel switching method and device, a storage medium and a processor. The method comprises the following steps: receiving network switching request information of a target user, and receiving network load information of a target satellite, wherein the network switching request information comprises current network level information of the target user; determining a network switching candidate set based on the network switching request information and the network load information, wherein the network switching candidate set comprises at least one target base station; and determining a network channel of the target base station from the network switching candidate set to perform network channel switching. The application solves the technical problems of poor adaptability and high blocking rate of the network channel switching method in the prior art.

The present invention belongs to the field of industrial communications, and relates to an OPC UA-based industrial equipment plug-and-produce method and system. Equipment plug-and-produce at a network level is realized by designing an OPC UA-based automatic discovery mechanism; and equipment parameter configuration and integration standardization are realized by designing OPC UA information modeling for all industrial controllers and field equipment and using an OPC UA as a standard interface for inter-equipment communication. By designing an equipment parameter configuration method and an equipment integration method, parameter configuration of equipment and automatic integration between industrial controllers and field equipment are completed, thereby realizing equipment plug-and-produce at a semantic level; and by designing an equipment replacement method, real-time configuration parameters of old equipment that has failed or needs to be upgraded can be automatically transferred to new equipment, thereby reducing the time required for manual equipment replacement. The present invention reduces the time required for integrating and commissioning large-scale heterogeneous industrial equipment and systems, and eliminates potential human errors.

The application discloses a low-load flooding method and system for a layered large-scale satellite internet, and mainly solves the problems that an existing flooding method is difficult to reduce satellite transmission load, and topology frequently changes and satellite node resources are nervous. An implementation scheme comprises the following steps: initializing a satellite node, setting a link state instant flooding range parameter; the satellite node establishes a neighbor relationship with surrounding nodes, maintains a link state database, and divides network levels; when a link state changes, a link state update message is generated and sent to neighbor nodes of different levels; after the satellite node receives the message, the message is parsed to calculate a routing table item, and the routing table item is forwarded to the neighbor nodes; the satellite node periodically combines all messages in a message buffer area, generates a global link state update message, and floods the global link state update message in the whole network. The application can effectively reduce network flooding load, improve network transmission efficiency, and enhance the adaptability of the network to a dynamic environment, and can be applied to large-scale satellite internet network transmission.

This application provides a method and system for interference suppression in a multi-node power line carrier communication network. The method involves synchronously acquiring carrier signals from the connected power line to obtain the acquired signals from each communication node; extracting the original interference sensing vector from each communication node; determining the node-level interference feature vector and interference type label for each communication node based on the corresponding original interference sensing vector; uploading the corresponding node-level interference feature vector and interference type label to the network master node; performing spatial coupling modeling on the uploaded information to generate a network-level interference coupling model; and jointly optimizing the communication behavior of each communication node based on the network-level interference coupling model to generate a multi-node collaborative interference suppression strategy. The technical solution provided in this application can achieve refined perception and identification of interference from a global perspective, and based on this, make forward-looking collaborative decisions to improve the accuracy of communication network interference suppression.

The invention provides a traffic state prediction method and device, a terminal and a medium, and relates to the technical field of intelligent traffic, and the method comprises the steps: recognizing a key traffic road section as a key node based on the historical traffic state data of each traffic road section; constructing a double-layer traffic network structure according to an identification result; a first traffic network structure in the structure comprises all traffic road sections and a spatial connection relation thereof, and a second traffic network structure only comprises key traffic road sections serving as key nodes and a spatial connection relation thereof; and extracting network-level spatial features and key node spatial features based on a double-layer traffic network structure, guiding fusion of the network-level spatial features and the key node spatial features based on prior knowledge information related to each traffic road section, and predicting the traffic state based on the fused spatial features. According to the method, the key node characteristics in the traffic network can be combined, the traffic road segment priori knowledge is utilized to guide feature fusion, and the traffic state prediction accuracy and stability are improved.

A system of one embodiment that provides stateless symmetric forwarding of packets in a computer network. The system includes a memory and a processor. The system is operable to determine a cluster state of a plurality of border routers in a cluster. The system is operable to communicate the cluster state to at least one branch node in the computer network. The system is operable to generate a network level consistent hash based on the cluster state. The system is operable to route a first packet through a first border router of the plurality of border routers in the cluster using the network level consistent hash. After the first packet is sent through a first border router, the system is further operable to route a second packet through the first border router of the plurality of border routers in the cluster using the network level consistent hash.

The application discloses a dispatching control method for meeting the minimum water demand of municipal pipe network during peak and valley time, comprising the following steps: S1, preprocessing pipe network nodes; S2, dividing pipe network dispatching units; S3, judging whether to start the dispatching control logic; S4, valve opening degree calculation and adjustment of the total pipe network level; S5, valve opening degree calculation and adjustment of the branch pipe network level; S6, valve opening degree calculation and adjustment of the terminal node level; S7, self-learning optimization and time-sharing dispatching; the application has the following beneficial effects: the valve opening degree is adjusted according to the minimum basic water demand ratio, fine distribution of water flow is realized during the peak period with limited water supply capacity, basic water can be obtained by each effective dispatching node, the situation that some nodes excessively pump water to cause other nodes without available water is avoided, and the imbalance problem of water supply during the peak period is solved; the municipal pipe network is divided into multiple regional dispatching units, the overall complex dispatching is disassembled into small unit dispatching, and the operation difficulty of the overall dispatching of the municipal pipe network is reduced.