Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

61 results about "Network strategy" patented technology

First of all, network strategy is grounded at a fundamental level in creating (strategic) connectivity, by building linkages and trust between key stakeholders and perhaps unusual bedfellows. This can be done by convening people ; sharing stories, data and other forms of information; co-creating knowledge;

Robot control optimization method based on deep reinforcement learning

The invention discloses a robot control optimization method based on deep reinforcement learning, and the method comprises the steps: firstly initializing a control system, constructing an experience playback buffer pool, and setting an Actor network strategy function, a Critic network weight, a hyper-parameter, and a target network parameter; then, the robot generates an action according to the Actor network, collects environment feedback after executing the action, and stores the state transition tuple into a buffer pool; next, a small batch of data is sampled, a time difference error is calculated, and a network parameter is updated accordingly to minimize a value estimation deviation, synchronously optimize the network parameter, maximize an expected value of a state-action value function, and improve control performance. According to the method, a multi-thread architecture and a deep reinforcement learning technology are fused, the real-time performance, stability and generalization ability of robot control are improved, the problem of algorithm convergence in a non-stationary environment is effectively solved, the cost of adjustment and calculation is reduced, and the robustness of long-term stable operation and deployment feasibility in a complex scene are enhanced.
Owner:HARBIN ENG UNIV

SDN (Software Defined Network) dynamic control system based on cloud native architecture

The invention provides an SDN (Software Defined Network) dynamic control system based on a cloud native architecture, and belongs to the technical field of SDN and cloud native. The system adopts a three-layer decoupling architecture of a service layer, a control layer and a data layer, wherein the service layer consists of a core network, a cloud platform and edge nodes and is used for issuing service requirements and executing a joint resource scheduling strategy; the control layer comprises four core modules, namely a micro-servitization SDN control module, a cross-domain collaborative engine module, an end-to-end service quality guarantee module and an edge collaborative optimization module, and is responsible for unified analysis, decision and scheduling to realize dynamic updating of a network strategy and multi-cluster collaborative optimization; the data layer is composed of an SDN switch and a router, and is used for executing a flow table rule and collecting network situation data. Through deep fusion of the SDN and the cloud native technology, the problems of upgrade interruption, low cross-domain collaboration efficiency and edge resource limitation of a traditional network architecture are solved, and the method can be widely applied to hybrid cloud management, industrial Internet of Things and intelligent city network scenes.
Owner:THE 54TH RESEARCH INSTITUTE OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION

Recommendation And Update Of Network Policies

Devices, systems, methods, and processes for recommendation and update of network policies. Existing network policy update solutions rely on human intervention in monitoring and analyzing traffic patterns in a network, checking for policy compliance, detecting any policy violations, and even updating new policies in the network. However, manual processes are prone to human error, introduce significant delays, and lack scalability and objectivity. To address these issues, an automated system is provided that monitors traffic across a network (in real-time or near real-time) and detects violations in a set of network policies associated with the network. The system utilizes one or more recommendation models to process network flow data and network inventory data, and generate one or more policy update recommendations to resolve the detected policy violations. The system further enforces the one or more policy update recommendations on various network devices within the network to resolve the detected policy violations.
Owner:CISCO TECHNOLOGY INC

Dynamic compensation control method and system for main shaft of numerical control machining center

The invention relates to the technical field of numerical control machine tool precision compensation and intelligent control, and discloses a numerical control machining center spindle dynamic compensation control method and system.The numerical control machining center spindle dynamic compensation control method comprises the steps that surface topography point cloud data of an online visual sensor, spindle motor current data and feed shaft position encoder feedback data are obtained, and a multi-source state monitoring data set is generated; a regularization method is adopted to solve reverse mapping from the surface low-frequency error component to radial runout and axial movement of the main shaft, and a main shaft rigidity state index and a tool abrasion index are output; describing an interaction relationship between the tool wear and the main shaft rigidity based on a coupling degradation kinetic equation, and calculating contribution weights of the tool wear and the main shaft rigidity to the machining precision; training a deep Q network strategy by using the deduced reward function, and outputting an optimal action; and executing spindle dynamic compensation parameter adjustment or generating a replacement instruction according to the optimal action type. According to the method, the factor of lacking a continuous learning improvement mechanism from historical data is overcome.
Owner:PRIMINER MASCH TOOLS DONGGUAN CO LTD

A / B link performance comparison and strategy optimization method and system based on service flow

The invention provides an A / B link performance comparison and strategy optimization method and system based on service flow, and belongs to the field of network performance monitoring and network strategy verification. The method comprises the following steps: firstly, performing bypass collection on real service traffic to obtain original data; copying the same copy of original data, injecting the original data into the link A and the link B at the same time, and then respectively collecting service flows of the link A and the link B; establishing a session alignment model, and judging whether the service traffic of the link A and the link B belongs to homologous traffic or not; after time drift compensation is carried out on sending timestamps of the homologous flow in the two paths, visible time sequence fields of homologous events are extracted respectively, differential indexes of the homologous events of the two paths on key time sequence parameters are calculated, and different percentile values of all the differential indexes under each parameter type in a preset time window are counted; and link performance comparison and strategy verification are carried out according to the difference index and the percentile value. According to the invention, the authenticity and efficiency of performance comparison and strategy optimization of different paths are improved.
Owner:BEIJING WANGSHEN TECH CO LTD

Intention-driven satellite-ground convergence network on-demand arrangement system and method

PendingCN121814592ABiological modelsRadio transmissionNetwork orchestrationNetwork on
The invention relates to the technical field of communication networks, in particular to an intention-driven satellite-ground convergence network on-demand arrangement system and method, and the method comprises an intention input layer which is used for receiving a multi-mode intention of a user; the intention analysis layer is used for analyzing the intention of the user to generate a recognizable network strategy; the arrangement control layer comprises a design state and an operation state; wherein the design state is used for dynamically generating a resource arrangement strategy based on an identifiable network strategy, and verifying the feasibility of the resource arrangement strategy in the digital twin network; the running state is used for generating an executable scheme based on the verified resource arrangement strategy; and the infrastructure layer comprises a satellite-ground unified atomic power abstraction module which is used for abstracting heterogeneous resources into standardized atomic power and executing an executable scheme. The scheme aims to provide a brand-new intention-driven satellite-ground fusion network arrangement architecture with dynamic generation, thorough decoupling and active prediction capabilities, so that the technical problem that complexity and dynamics of a 6G network cannot be handled at present is solved.
Owner:XIDIAN UNIV

Software engineering automation test system based on Internet

PendingCN121233460AError detection/correctionBiological modelsPathPingSoftware quality assurance
The invention relates to the technical field of software quality assurance, and discloses an internet-based software engineering automation test system, which comprises a test environment perception module, a test intelligent arrangement module and a test execution and optimization module, a server resource state, a network delay parameter and a code structure feature are collected in real time through an environment dynamic sensing module, a multi-dimensional environment adaptation degree evaluation model is constructed, and when it is detected that the environment adaptation degree is lower than a threshold value, container resource expansion and network strategy adjustment are automatically triggered; establishing a mapping relation between multi-level defect features and code modules through a defect root positioning system, searching an optimal diagnosis scheme in a strategy space by applying an improved particle swarm algorithm, and accurately positioning a fault point to a source code line number; finally, closed-loop control of test environment self-adaption, test path self-correction and defect positioning self-optimization is realized, and the accuracy of a test result and the fault repair efficiency are improved.
Owner:HAINAN SHENGHE XINSHUN TECHNOLOGY CO LTD

InSAR frozen soil deformation monitoring method based on U inspection and multi-level networking strategy

The invention relates to the technical field of frozen soil monitoring, in particular to an InSAR frozen soil deformation monitoring method based on U test and a multilevel network construction strategy, which comprises the following steps: for a target frozen soil region, selecting PS candidate points through an amplitude deviation index and acquiring interference phases of the PS candidate points; u inspection is adopted to identify a homogeneous pixel set, an EMI method is adopted to carry out time sequence phase optimization processing, goodness of fit is adopted to measure the quality of an optimal phase estimation result, and DS candidate points and interference phases thereof are obtained; a multi-level network construction strategy is adopted, high-quality PS candidate points and DS candidate points construct a first-level resolving network, and the remaining candidate points gradually construct a second-level resolving network for parameter resolving; and separating frozen soil deformation from the unwrapping phase of each measurement point obtained from the multi-level network construction strategy by adopting joint parameter modeling. According to the invention, the precision of the deformation parameter calculation result of the frozen soil region and the spatial density of the measurement points are obviously improved, so that the frozen soil deformation monitoring quality is obviously improved.
Owner:CENT SOUTH UNIV

Marine transportation network system toughness evaluation and monitoring early warning method

The invention relates to an ocean transportation network system toughness evaluation and monitoring early warning method. The method comprises the following steps: S1, identifying key nodes and vulnerabilities of a network model; s2, analyzing short-term or long-term influence of robustness and fault tolerance evaluation results and node or edge change on network performance; s3, analyzing a flow direction prediction result of the bulk cargos; s4, analyzing the adaptation mechanism of the network to the dynamic change; s5, analyzing a network toughness evaluation result, and optimizing a network strategy based on the network toughness evaluation result; and S6, outputting a prediction result by the prediction model, and outputting a monitoring and early warning result based on the ship trajectory semantic model and the real-time AIS data. Compared with the prior art, the method has the advantages of more effectively identifying modes, trends and potential risk points and the like.
Owner:SHANGHAI MARITIME UNIVERSITY

A local rapid reconstruction method for a killing net based on a complementary net strategy

The present application belongs to the field of military command control and combat simulation, and relates to a local rapid reconstruction method for a killing network based on a complementary network strategy. The method acquires current state information of the killing network and detects failed nodes or edges, constructs a local repair area centered on the failed nodes, establishes a multi-objective optimization model in the repair area aiming to maximize task recovery benefits, minimize resource use costs and minimize task completion delays, solves to obtain a Pareto optimal solution set by using a TM-NSGA-III algorithm guided by a conversion matrix, and finally screens and executes a reconstruction scheme according to a battlefield situation. The present application reduces the search space by localized modeling, combines the conversion matrix to inherit the effective information of the original network, realizes rapid and high-quality reconstruction of the killing network, and improves the resilience and self-healing ability of the killing network in a dynamic battlefield environment.
Owner:SUZHOU UNIV OF SCI & TECH

A multi-agent centralized decision-making method and system based on hierarchical representation and a storage medium

The application discloses a kind of multi-agent centralized decision-making method, system and storage medium based on hierarchical representation.The method is realized based on reinforcement learning policy network, specifically includes: the situation information perceived by multi-agent is input into policy network, the first module of policy network is based on the hierarchical feature extraction of the data type of situation information, each layer situation information data is processed respectively and then feature fusion is carried out, and the processed situation information is output;The second module of policy network further processes the processed situation information;The third module of policy network carries out hierarchical decision-making according to action parameter type, and each action parameter is output by processing in turn, to obtain the joint action of final output.The high-dimensional situation information and action information brought by multi-agent centralized decision-making are reduced in dimension by adopting hierarchical method based on type, and the search efficiency in high-dimensional space is effectively improved.
Owner:NAT UNIV OF DEFENSE TECH

Container-level network resource efficient management method for deterministic distributed computing scenarios

The application provides a container-level network resource efficient management method for a deterministic distributed computing scene, and mainly solves the problems that the prior art cannot effectively manage network resources at the container level, the real-time performance of task scheduling is low, the success rate is low, and resources are wasted and the like. For the deterministic distributed computing scene, efficient network resource management at the container level is needed, first, the network resource controller needs to be extended, and a Service service is configured so that the container can communicate with the external cloud server; then, the use of network resources by the container is controlled by configuring a network strategy; further, the container tasks are aggregated according to the real-time performance and determinacy requirements of the tasks, and the transmission efficiency of the container tasks is improved; finally, the aggregated tasks are stored and transmitted. The method takes the container virtualization technology as the implementation means, aggregates the container tasks in multiple time slots based on the dynamic programming algorithm, and continuously optimizes the algorithm parameters in combination with the artificial intelligence technology, which not only guarantees the real-time performance and success rate of the tasks, but also significantly improves the resource utilization.
Owner:SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI

Intelligent determination method and device of network strategy and storage medium

The invention discloses an intelligent determination method and device of a network strategy and a storage medium, relates to the field of communication, is used for accurately matching the network strategy for network equipment, and comprises the following steps: receiving strategy request information; the strategy request information comprises resource demand information; determining at least one candidate network strategy from a strategy knowledge base based on the strategy request information and a similarity model; the strategy knowledge base comprises a plurality of network strategies, and the similarity between each candidate network strategy in the at least one candidate network strategy and the strategy request information is greater than a first threshold value; determining a policy score of each candidate network policy in the at least one candidate network policy based on the policy request information, the at least one candidate network policy and a reordering model; based on the strategy score of each candidate network strategy, determining a target network strategy meeting a matching degree requirement from the at least one candidate network strategy; the target network strategy comprises a strategy name and API information. The method and the device are applied to a network policy matching process.
Owner:CHINA UNITED NETWORK COMM GRP CO LTD +1

E-SIM-based user behavior analysis method

The invention discloses a user behavior analysis method based on E-SIM, and particularly relates to the technical field of user behavior analysis. The method comprises the following steps: constructing a unified time sequence data set by collecting an E-SIM configuration switching log, a network strategy parameter and a user behavior event sequence; determining a configuration switching trigger window based on the unified time sequence data set, analyzing the correlation degree between network environment migration and user behavior change, and obtaining candidate drift fragments; respectively carrying out factor deconstruction on the equipment side and the network side, and outputting pseudo migration scores of the equipment side and the network side; performing comprehensive judgment of identity cognition drift based on the pseudo migration score, and calculating a behavior correction vector; and reconstructing a user behavior sequence by using the behavior correction vector, correcting an abnormal behavior tag, and outputting a corrected user behavior analysis result. And the accuracy and reliability of user behavior analysis are improved.
Owner:GUANGDONG LEGEND COMM CO LTD

Network policy approval method and device and electronic equipment

The invention discloses a network policy approval method and apparatus, and an electronic device. The method comprises the following steps: acquiring application work order information; network strategies in the application work order information are pre-screened according to a white list rule and a black list rule, a first examination and approval result is obtained, the white list rule comprises a predefined matching incidence relation of service attributes of a source IP and a target IP, and the black list rule comprises a predefined prohibition incidence relation of the service attributes or network segments of the source IP and the target IP; splitting a target network strategy which does not conform to a white list rule or a black list rule in the application work order information according to the system and the approval level to generate a corresponding approval process; and examining and approving the target network strategy according to the examination and approval process to obtain a second examination and approval result. According to the method and the device, the technical problems of missing pre-screening, disordered approval responsibility and insufficient later maintenance existing in network policy approval in related technologies are solved.
Owner:CHINA TELECOM CORP LTD

Communication method and apparatus

PCT designated stageWO2025140001A9Service provisioningNetwork dataNetwork strategy
Embodiments of the present application relate to the technical field of communications, and provide a communication method and apparatus. The communication method comprises: a network function service consumer entity sends a first request to a network data analytics function (NWDAF) network element, wherein the first request comprises priority indication information, the first request is used for requesting the NWDAF network element to feed back a plurality of analytics results of a network policy on the basis of the priority indication information, and the priority indication information is used for indicating feedback priorities of the plurality of analytics results of the network policy; and the NWDAF network element sends a first response to the network function service consumer entity, wherein the first response comprises at least one analytics result, and the at least one analytics result is determined from among the plurality of analytics results on the basis of the feedback priorities of the plurality of analytics results. In this way, the NWDAF network element can selectively feed back at least one analytics result to the network function service consumer entity on the basis of the priority indication information, thereby improving the value of recommendation of the NWDAF network element.
Owner:HUAWEI TECH CO LTD

Intelligent selection and optimization method of building composite phase change materials based on large language model

The present invention discloses a method for intelligent selection and optimization of building composite phase-change materials based on a large language model, belonging to the technical field of building energy conservation and intelligent material design. The method collects basic thermal property data, building environmental parameter data, and user demand data; utilizes deep reinforcement learning technology to construct an intelligent model based on a deep Q-network strategy, and integrates the generated data samples into a thermal property database; uses the large language model to output candidate material combination recommendations; uses semantic label vectors, and a ranking engine evaluates the candidate material combination recommendations to obtain performance evaluation results; generates a performance evaluation report based on the simulation model; and uses a multi-agent negotiation algorithm to optimize cross-region thermal control performance, generate multi-dimensional performance comparison charts and tuning suggestions, and record designer correction information, optimizing and adaptively providing feedback. The present invention screens building composite phase-change material combinations, optimizes cross-region thermal control, outputs adaptation solutions and suggestions, and enhances the system's adaptive optimization capabilities.
Owner:SANYA SCI & EDUCATION INNOVATION PARK WUHAN UNIV OF TECH

Network strategy conversion system of application program perception and identity perception

The invention discloses an application program aware and identity aware network policy conversion system, which comprises a user / application program input plane, a policy conversion plane and an execution plane, the user / application input plane reads a plurality of descriptive parameters from a post-set data input; the strategy conversion plane converts the descriptive parameters into a plurality of strategy parameters; the execution plane applies the policy parameters to a plurality of data packets associated with the metadata input. Therefore, according to the invention, corresponding strategy processing can be carried out on the data packet in the network according to the application related information and the identity related information.
Owner:HUANLIAN TECHNOLOGY CO LTD

Network control method and system

The invention discloses a network control method and system. The method comprises the following steps: collecting and maintaining network state information of forwarding layer equipment through a southbound interface; generating a network strategy on the basis of requirements of an application layer and in combination with the network state information, and issuing the network strategy to forwarding layer equipment through the southbound interface; and obtaining network state information from the forwarding layer, and scheduling and optimally distributing network traffic based on the network state information. A'strategy making and issuing 'module and a'flow scheduling and optimizing' module are integrated in the same controller layer, close cooperation and closed-loop control of strategy decision and flow execution are achieved, and the defects that in the prior art, strategies are difficult to execute efficiently and consistently, and the strategies cannot be dynamically adjusted according to the real-time flow state are overcome.
Owner:EASYSTACK INC

Resource allocation method and system for eMBB and URLLC mixed service

The invention belongs to the technical field of wireless communication, and discloses a resource allocation method for an eMBB and URLLC mixed service, and the method comprises the steps: 1, setting input variables: a round number T, a learning rate, an experience playback pool, a target network update frequency C, a state weight factor beta, a service weight factor sum, and a discount factor; 2, performing variable initialization: initializing a training network and a target network by using parameters selected in a randomized manner, wherein the parameters are selected in a randomized manner; step 3, randomly selecting power and a resource allocation strategy to initialize a network state in each turn (T in total); 4, in each round, selecting an action through a network strategy selection module, configuring a strategy in the network, then recording a network state and a corresponding return function after the action is executed, and finally storing an obtained parameter set in an experience playback pool; step 5, training; step 6, updating parameters of the target network; and the reliability is high.
Owner:XIAN UNIV OF POSTS & TELECOMM

Downhole tool face dynamic control method and system based on reinforcement learning

The embodiment of the application provides a kind of based on reinforcement learning's downhole tool face dynamic control method and system, belong to directional drilling technical field.The method comprises: the drilling state data of target well is collected, data preprocessing is executed to the drilling state data, corresponding state vector is constructed based on the drilling state data after preprocessing;Action decision model trained based on DDPG algorithm is called based on the state vector, and action instruction is obtained;Wherein, the network strategy parameter of the action decision model is obtained based on the deviation between current drilling state data and pre-constructed reward function after correction of last round network strategy parameter;The action instruction is executed to parse, and target physical action is determined;Based on target physical action, top drive wobble is executed, and execution result is recovered, until execution result indicates that tool face angle meets expectation.The stability and real-time control effect under complex well section and severe disturbance working condition are improved in the application scheme.
Owner:CHINA UNIV OF PETROLEUM (BEIJING)

Network attack detection method and device based on deep reinforcement learning and topology reconstruction

The embodiment of the invention relates to the field of network security, and provides a network attack detection method and device based on deep reinforcement learning and topology reconstruction, and the method comprises the steps: collecting network flow data, node state information and security logs in real time, carrying out the dynamic modeling of a connection relation and communication behaviors between nodes, and generating a dynamic attack graph; analyzing the current network state of the dynamic attack graph through a deep reinforcement learning agent to obtain an optimal defense action; generating a strategy instruction based on the optimal defense action, and sending the strategy instruction to a network strategy execution point; by calling an application programming interface of a strategy execution point, blocking of malicious IPs, isolation of infected nodes or redirection of malicious traffic is dynamically executed, network topology reconstruction is triggered to rapidly repair or isolate fault nodes, and instant detection and interception of attack behaviors are achieved. According to the embodiment of the invention, active perception and intervention are carried out on attack behaviors, and intelligent decision and dynamic self-healing of network topology are realized through deep reinforcement learning.
Owner:ZHUHAI HONGRUI INFORMATION TECH CO LTD +1

A large model and knowledge graph enabled intent-driven network design method

The application discloses a large model and knowledge graph enabled intention driving network design method, comprising the following steps: S101, a user inputs a user intention through a front-end natural language interaction interface, and performs a pretreatment operation on the user intention; S102, a pretreated user intention is classified based on a few-shot learning method, and a large model cooperation method extracts key information of the user intention and constructs an intention knowledge graph based on the key information; S103, a network state knowledge graph is constructed; S104, an application program interface provided by an underlying layer is called by using intention understanding and reasoning capability of the large model, so that mapping of the user intention to an underlying network strategy and issuing are realized; and S105, the large model performs dynamic real-time adjustment based on network state knowledge graph information. The application realizes intention semantic mining, adaptation of intention demand and underlying resource capability, so as to bridge a semantic gap between the user intention, strategy management and the underlying network, and improve network operation efficiency.
Owner:XIDIAN UNIV

Intention-driven sky-ground fusion intelligent network selection system and method

The invention discloses an intention-driven sky-ground fusion intelligent network selection system and method. The system comprises an intention enabling layer, a network strategy layer and an infrastructure layer. The intention enabling layer is responsible for processing intention information required by an access side service user, and extracting a key QoS index and a predicted user moving position sequence; the network strategy layer receives a translation result of the intention enabling layer, selects an optimal access network through a deep reinforcement learning algorithm, and transmits a selection result to the user scheduling module, and the user scheduling module schedules a user in a slice according to a slice type required by the user in the selected access network, and generates a scheduling strategy; and the infrastructure layer bears access and network services of terminal users, and dynamically adjusts access and slice distribution of the users by executing a scheduling strategy and cooperating with various base station resources, so that end-to-end high-quality communication services are realized. According to the invention, efficient management and optimization of network resources in a space-ground convergence network environment are realized.
Owner:XIDIAN UNIV

Network strategy optimization method and system based on user behavior and preference learning

The invention relates to the field of network communication, and provides a network strategy optimization method and system based on user behaviors and preference learning. The method comprises the following steps: collecting strategy operation behaviors and network quality sensing data of a user to obtain a user behavior data set; inputting the user behavior data set into a machine learning model for training so as to learn an association relationship between user behavior characteristics and network quality indexes, and obtaining a user preference weight vector; obtaining a quality parameter and available network strategies of the current network environment, and performing quantitative evaluation on the plurality of available network strategies according to the user preference weight vector to obtain a comprehensive score of the plurality of available network strategies; and performing priority ranking on the available network strategies based on the comprehensive score, and selecting a target network strategy according to a strategy availability state and a score result. According to the method, the personalized preference of the user on the network quality index can be learned, intelligent evaluation and dynamic switching of the network strategy are realized, and the user experience is improved.
Owner:E SURFING VISION TECHNOLOGY CO LTD

Scheduling method and device, storage medium, program product and computer equipment

The invention discloses a scheduling method and device, a storage medium, a program product and computer equipment, and the method comprises the steps: carrying out the processing of a collection end, generating merged data matched with user equipment, and generating network strategy information corresponding to the user equipment through a strategy management end according to the merged data through a strategy generation model, according to the method, the network strategy can be generated timely and intelligently, the adaptability between the network strategy and the user equipment is improved, then the target platform can respond to the network strategy information to generate the corresponding scheduling strategy information and send the strategy instruction to the second network element, and the second network element executes the scheduling operation. Therefore, the network policy scheduling of the user equipment can be completed, so that the flexibility, intelligence and timeliness of the network policy scheduling can be improved, and the real-time network service requirements of the terminal can be responded more timely, accurately and reliably; and the model can be generated according to the feedback data optimization strategy corresponding to the scheduling operation so as to improve the prediction accuracy and reliability of the model.
Owner:XINYANG BRANCH HENAN CO LTD OF CHINA MOBILE COMM CORP +1

A cross-network message pushing method based on a strategy model

PendingCN122437833ARouting modelNetwork link
The application relates to a cross-network message pushing method based on a strategy model and belongs to the technical field of computer networks. The application establishes node management, engine management, route management and application management aiming at a cross-network strategy model, establishes a cross-network route model in combination with cross-network, cross-center and cross-system application scenes, shields cross-network link construction in complex scenes only by configuration of the strategy model, solves the interconnection and interworking of various service systems in service and a system application difficulty, and achieves out-of-box use. The application can realize end-to-end message sending only by simple registration and configuration in scenes where different networks, different centers and different systems cannot directly interact.
Owner:BEIJING INST OF COMP TECH & APPL

Quality of experience policy engine for custom applications based on feedback

In one embodiment, a method herein may comprise: causing, for a quality-of-experience evaluation session, one or more network impairments to be injected according to a set of predefined scenarios on application traffic for a plurality of feedback sources that are using a particular application in a computer network; obtaining experience-based feedback from the plurality of feedback sources for the quality-of-experience evaluation session; correlating the experience-based feedback with the one or more network impairments to produce an evaluation result for the quality-of-experience evaluation session; and generating a quality-of-experience-based network policy recommendation for the particular application based on the evaluation result.
Owner:CISCO TECHNOLOGY INC

Communication method and communication device

The invention relates to the field of communication, in particular to a communication method and a communication device. In order to meet task requirements, a terminal device may need a plurality of networks in a heterogeneous network to execute tasks, but due to the fact that different networks have differences in resource scheduling modes or processes and the like, task execution of the heterogeneous network often needs to be based on complex processes and cross-network strategies, and the task execution efficiency is low. In the application, a first task credential is information associated with a first task, and each subnet independently determines a resource scheduling strategy for executing the first task based on an own operation condition and the first task credential; and the terminal equipment calls resources of each subnet based on the first task credential to execute the first task. As the resource scheduling strategy for executing the first task is independently determined by each network, a cross-network strategy does not need to be formulated for executing the first task, so that the efficiency of executing the task by the terminal equipment through the heterogeneous network can be improved.
Owner:HUAWEI TECH CO LTD

Bridge group maintenance priority dynamic decision method and device based on reinforcement learning

The application provides a kind of bridge group maintenance priority dynamic decision method and device based on reinforcement learning, it is related to bridge wisdom maintenance technical field.The method comprises: the topological structure of bridge network and road is constructed;Define the state space of bridge, maintenance action space and state transition matrix;Define the reliability index corresponding to the state of bridge, based on topological structure, design comprehensive reward function based on maintenance cost, asset risk and traffic network capacity loss risk;Bridge maintenance decision problem is constructed;Bridge maintenance decision problem is described as Markov decision process, pointer network is used to establish pointer network strategy model, Actor-Critic algorithm is used to train pointer network strategy model, and reinforcement learning-based maintenance decision model is obtained;The reinforcement learning-based maintenance decision model is trained until convergence, and the bridge maintenance action sequence under the limited constraint is output.The limitation problem of traditional single bridge evaluation can be solved by using the application.
Owner:UNIV OF SCI & TECH BEIJING