126 results about "Network intelligence" patented technology

The invention discloses an urban energy network intelligent allocation method and system, and the method comprises the steps: obtaining building energy consumption data and energy supply network topology information, building a supply and demand matching reference, recognizing a load peak value dense time period and a peak clipping and valley filling potential region, and exporting transferable load data to form a regional supply and demand distribution diagram; generating a peak shifting adjustment space in combination with the user response delay duration and the equipment start-stop period; performing gap matching analysis on the regional supply and demand distribution map and the peak shifting adjustment space, creating a hierarchical regulation instruction set, and differentially generating an instant response instruction and a delay response instruction; a regulation and control coordination parameter is formed through coordination configuration of the peak shifting revenue coefficient and the instant response instruction; finally, a regulation and control execution range is determined, cost benefit evaluation is implemented, an urban-level energy scheduling execution scheme is formed, accurate matching and efficient scheduling of urban energy supply and demand are achieved, and comprehensive and efficient scheduling decision support can be provided for application scenes such as an intelligent power grid, regional heat supply and comprehensive energy service.

A system and method for privacy-preserving communication validation and multi-attribute trust scoring is disclosed. The system analyzes communication metadata to determine pattern legitimacy by comparing current communication patterns against relationship fingerprints without accessing communication content. The system validates relationship context between communicating parties using interaction graph analysis and historical communication data. Cross-network intelligence correlation compares current patterns against aggregated patterns across voice, email, and messaging services, creating a self-strengthening security framework that recognizes emerging threat patterns while validating legitimate communication behaviors. The system generates comprehensive multi-attribute trust assessments comprising individual trust attribute scores including engagement rate, reliability index, channel preference, temporal pattern, and behavioral pattern, combined into overall trust levels. Trust context is displayed through a user interface presenting simplified, intuitive, and actionable information with progressive disclosure capabilities, enabling informed user decisions while preserving privacy. Communication processing actions provide users with appropriate engagement options tailored to specific trust assessment results.

According to the multi-source threat detection method based on the hybrid expert model, real-time collection and structured processing of network flow, system logs and user behavior data are achieved through a multi-mode intelligent collection engine, and high-quality multi-source input is provided for upper-layer analysis; the double-branch feature extractor carries out deep analysis on the network flow time sequence mode and the log semantic context to generate fine-grained feature vectors; the hybrid expert reasoning framework is based on expert models in three fields of a dynamic routing gating network, intelligent scheduling network behaviors, log semantics and user portraits, combines space-time alignment features through a cross-modal attention mechanism, and constructs an interpretable attack evidence chain in combination with a causal reasoning engine. Finally, a full-link closed loop from multi-modal data acquisition, feature collaborative extraction and intelligent threat reasoning is realized, and while millisecond-level real-time response is ensured, the complex internal threat detection accuracy is obviously improved.

The invention provides a digital twin enabling air-ground integrated dual power supply network supply-demand game method and system, and belongs to the technical field of intelligent management and control of energy and communication convergence networks. Comprising the following steps: constructing a digital twin system of an energy-communication fusion network, and accessing and mapping dynamic data from an energy network and a communication network in real time; based on the dynamic data, an energy side observation space and a communication side observation space are defined in the digital twin system, and the comprehensive supply and demand imbalance degree of the system is calculated; the energy side intelligent agent and the communication side intelligent agent output control instructions in a continuous action space according to respective observation spaces, and respectively aim at maximizing own long-term accumulated benefits; a final solution of the coordinated game framework is an optimal strategy combination meeting a Nash equilibrium condition; carrying out centralized training and distributed execution on the coordinated game framework by adopting a multi-agent depth deterministic strategy gradient algorithm based on supply and demand perception; and the intelligent agent carries out collaborative decision making based on the global supply-demand imbalance degree and local observation.

The invention discloses a wireless communication network intelligent optimization method and system based on neuron collaboration, and relates to the technical field of wireless communication. The method comprises the following steps: mapping a communication node into a bottom layer sensing neuron and constructing a neural state variable set; constructing a node neural situation function based on the variables; when the local threshold value is exceeded, excitation pulses are generated and uploaded to middle-layer convergence neurons; the middle layer carries out pulse space aggregation and extreme value search, and outputs a selection strategy and an adjustment strategy; and reporting to a top layer to execute whole network neural synchronization index analysis, and optimizing the wireless communication network. The technical problems of low spectrum resource utilization rate and unstable network performance caused by the fact that a traditional wireless communication network cannot realize high-efficiency spectrum allocation and dynamic topology reconstruction under user mobility change are solved, and the purposes of realizing local quick response and global collaborative optimization by constructing a layered neural network and improving the network performance are achieved. And the spectrum resource utilization rate is improved, and the network dynamic adaptive capability is enhanced, so that the user service quality is guaranteed.

The invention provides a communication network fault prediction method and system based on deep learning, and relates to the field of communication network intelligent operation and maintaining.The method comprises the steps that equipment state parameters, a traffic matrix, environment sensor data and topological relation data of a communication network are obtained in real time, graph neural network interpolation is carried out based on a topological graph, and a fault prediction result is obtained; filtering abnormal values by adopting a long-short-term memory auto-encoder, and aligning heterogeneous data time sequences through dynamic time warping to obtain cleaned communication network data; inputting the cleaned communication network data into a space-time double-flow deep learning model, extracting topological correlation characteristics and time sequence evolution characteristics of equipment, and generating a fault probability matrix through a gating fusion unit; and calculating a node risk value based on a network topological graph and the fault probability matrix, and identifying a high-risk node and a fault propagation path in combination with a preset dynamic threshold to obtain a communication network fault prediction result, so that the accuracy and timeliness of network fault prediction can be effectively improved.

The invention discloses an IPv4 / IPv6 dual-stack network intelligent operation and maintenance management method and system based on AI, and relates to the field of AI. The method comprises the steps that through full-link multi-source data collection and feature processing of network equipment, terminals, protocols and services, a structured data set is constructed; real-time evaluation and visual monitoring of the network state are realized by using a multi-task AI model; once an abnormality is found, a fault node and a propagation path are accurately positioned through a fault diagnosis model; integrating various model outputs to automatically generate and execute a targeted operation and maintenance strategy; and on-line iterative optimization of the AI model and the knowledge base is driven through continuous effect evaluation and data feedback, so that the dual-stack network intelligent operation and maintenance capability of autonomous circulation is formed. The method has the advantages that AI enabling and dual-stack adaptation are focused, full-link multi-source data acquisition is taken as support, accurate evaluation, rapid diagnosis and intelligent decision making are realized through a multi-task fusion AI model, the operation and maintenance efficiency and the network stability are improved, and the labor cost is reduced.

The invention relates to the field of communication, and discloses an intelligent traffic scheduling optimization method, device and equipment and a storage medium, and the method is used for 5G network intelligent traffic scheduling optimization. The method comprises the following steps: receiving a service request, analyzing the service request to obtain a 5G standard service type, an application scene and a 5G network slice identifier, then obtaining an SLA parameter corresponding to the service request and a candidate link required by service transmission, and converting the SLA parameter into an SLA preference vector; acquiring global data of the candidate link, and predicting by using the network state prediction model to obtain a predicted network state of the candidate link; the SLA preference vector is used as optimization target guidance, the predicted network state is used as a constraint condition, and a global optimization routing strategy is calculated through a multi-target optimization algorithm; and generating a control message packet based on the global optimization routing strategy, issuing the control message packet to the network forwarding equipment, and adjusting parameters of the network state prediction model and the multi-objective optimization algorithm based on the actual performance data after execution.

Embodiments are directed towards systems and methods for carrier aggregation and dual connectivity switching in a cellular network (e.g., a 5G network). Example embodiments include systems and methods for: the RAN functions supporting providing measuring and reporting particular items for dynamic carrier aggregation and dual connectivity switching; RAN dynamic carrier aggregation and dual connectivity switching with a network intelligence layer; RAN dynamic carrier aggregation and dual connectivity switching without a network intelligence layer; RAN dynamic carrier aggregation and dual connectivity switching based on availability of an inter-DU link and meeting latency / bandwidth criteria; RAN dynamic carrier aggregation and dual connectivity switching based on availability of an inter-DU link and meeting resource criteria; and prioritization for using CA instead of DC based on CQI information reported from UEs.

The invention relates to the technical field of network operation and maintenance, in particular to a network health automatic diagnosis and closed-loop repair method and related products, and the method comprises the steps: establishing a dynamic health baseline; abnormal deviation of the real-time operation data is recognized; predicting the risk probability that the network equipment has an operation fault in the future; selecting and executing a corresponding repairing action; verifying whether the abnormal deviation is eliminated; if the abnormal deviation is not eliminated, continuing to execute repair until the abnormal deviation is eliminated or the maximum repair frequency is reached; according to the method, the accuracy and the foresight of network fault diagnosis are improved by deeply fusing the artificial intelligence algorithm into a network operation and maintenance scene, and the intelligent and autonomous management of the network is realized by introducing a closed-loop repair mechanism with autonomous learning and decision-making capabilities. And the reliability, the stability and the self-repairing capability of the whole network infrastructure are enhanced.

The invention discloses an information fusion and reasoning method and system based on multi-agent collaborative networking search, and relates to the technical field of network information, and the method comprises the steps: a deep research strategy scheduling agent deconstructs an unstructured request through a task formalization mechanism, generates a high-dimensional instruction code, and dynamically optimizes an execution path. And the network intelligence index generation agent extracts and screens the trusted URL by using a rule engine and a semantic evaluator based on the code, and generates a structured link instruction stream. The structured analysis intelligent agent implements multi-level semantic distillation and conversion on an original document to obtain key value pair representations, and the key value pair representations are packaged into machine readable data. And generating a comprehensive intelligence abstract with consistent logic through the information fusion analysis agent. And the natural language generation engine converts the information into a professional report, and returns the professional report to the scheduling module through a feedback interface to realize cognitive closed-loop iterative optimization. The technical problem that in the prior art, it is difficult for geologists to obtain accurate, comprehensive and credible professional conclusions is solved.

The invention belongs to the field of network decision optimization, relates to a data analysis technology, and particularly relates to a network intelligent decision optimization system based on dynamic feature extraction, which is used for solving the problem that stage correlation analysis cannot be carried out according to a single performance parameter in a dynamic network in the prior art. Comprising a network test module, a feature extraction module, a performance monitoring module and a decision analysis module, and the network test module, the feature extraction module and the performance monitoring module are all in communication connection with a database; according to the method and the device, dynamic association analysis of the network performance parameters and the operation parameters is realized, and the system can accurately identify key factors causing performance abnormity in a complex and changeable network environment. Compared with a traditional static threshold judgment method, the dynamic feature extraction mechanism of the invention significantly improves the accuracy of anomaly diagnosis, and through the separate design of the test period and the monitoring period, the system can perform comprehensive feature analysis while ensuring the real-time monitoring efficiency.

The invention discloses a 6G-oriented cross-domain knowledge-driven network intelligent scheduling system and a 6G-oriented cross-domain knowledge-driven network intelligent scheduling method. The architecture comprises a cross-domain knowledge collaborative evolution module, a network closed-loop management module and a multi-normal-form learning decision module, the cross-domain knowledge collaborative evolution module is used for disassembling a network state into an environment domain, a network domain and a user behavior domain, and online incremental fusion of three-domain knowledge is realized through a graph neural network; dynamically updating the global knowledge base based on knowledge distillation; the network closed-loop management module is used for constructing a function closed loop of perception-reasoning-knowledge generation-decision issuing-verification optimization-memory retrieval; and the multi-normal-form learning decision module is used for fusing meta learning, reinforcement learning, federal learning and self-supervised learning to realize rapid migration and continuous evolution of the strategy. According to the method, the network data throughput, the fault recovery speed, the flow prediction precision, the resource fairness, the path efficiency and the task success rate are improved, and the method is suitable for complex 6G scenes such as air-ground integration and low-altitude traffic control.

The invention relates to the technical field of unmanned aerial vehicle path planning, and discloses an unmanned aerial vehicle path planning method based on deep reinforcement learning, and the method comprises the steps: firstly collecting point cloud data of a tunnel environment through a three-dimensional laser radar, carrying out the complementation processing, and carrying out the dynamic slicing in the main extension direction of a tunnel, the slice thickness is adaptively adjusted according to the local point cloud density, each slice is projected to generate a two-dimensional section grid map, a two-dimensional map sequence is used as a training environment, a deep Q network agent is adopted for exploration, a safe candidate path point set is generated, and finally, the candidate point set is evaluated and screened, so that the path point of the path is obtained. According to the method, the optimal path point of each slice is obtained, the discrete optimal point sequence is smoothed, the continuous and safe optimal flight path is finally formed, and simulation experiments verify that the method can effectively solve the problem that in a complex tunnel point cloud map, path planning is difficult to guarantee path safety, motion smoothness and calculation real-time performance at the same time.

The invention belongs to the technical field of base station intelligent monitoring, and provides a base station out-of-service prediction method and system based on big data analysis and a knowledge graph, and the method comprises the steps: obtaining first historical data information of a base station group, and carrying out the preprocessing of the first historical data information, and obtaining the preprocessed second historical data information; constructing a dynamic knowledge graph based on the second historical data information, and extracting multi-scale causal feature information according to the second historical data information and the dynamic knowledge graph; training an out-of-service prediction model based on the multi-scale causal feature information to obtain a trained target out-of-service prediction model; and acquiring real-time data information of the base station, and predicting the real-time data information by using the target out-of-service prediction model to obtain out-of-service prediction information of the base station. According to the invention, the prediction precision, timeliness and adaptability are remarkably improved, the engineering practicability and operation and maintenance operability are also considered, and a technical scheme with high accuracy, high interpretability and self-evolution capability is provided for intelligent operation and maintenance of the communication network.

The invention discloses an AI-based wireless communication network intelligent resource scheduling system, which belongs to the technical field of resource scheduling of wireless communication networks, and comprises the following steps: establishing a region prediction model; analyzing the region material data according to the region prediction model to obtain unit prediction data of each unit region in the prediction time in the prediction time period; generating a unit prediction map of prediction time according to the unit prediction data; establishing a digital twinborn model, and performing resource scheduling simulation on the unit prediction map according to the digital twinborn model to obtain a basic scheduling scheme; the device end collects user information in real time, and generates a unit area map according to the user information in the unit area; whether the basic scheduling scheme needs to be adjusted or not is evaluated according to the unit area graph; when the evaluation does not need to be adjusted, marking the basic scheduling scheme as a target scheduling scheme; and when the evaluation needs to be adjusted, optimizing and adjusting the basic scheduling scheme to obtain a target scheduling scheme.

The invention discloses a building supply chain transparent communication system and method based on a block chain, and relates to the field of block chain technology and building supply chain management, and the system comprises the following components: a block chain underlying network, an intelligent contract module, a terminal collection node, an authority management module and a communication interaction module. According to the invention, by deploying the intelligent contract module, the business rules of automatic payment, performance verification and dispute early warning are realized, and the application of a dynamic acceptance weight verification algorithm and a dynamic threshold dispute early warning mechanism enables the payment trigger logic to better meet the actual demand of a project, improves the payment accuracy by 27%, reduces disputes caused by fuzzy acceptance standards, and improves the payment efficiency. Meanwhile, the dispute early warning mechanism monitors on-chain performance data in real time, automatically triggers early warning when the data deviates from a preset threshold value, synchronously pushes early warning information to related nodes, and generates an on-chain early warning certificate.

The invention discloses a salinized frozen soil roadbed multi-parameter coupling monitoring method, and relates to the field of salinized frozen soil area roadbed monitoring, and the method comprises the steps: executing field investigation and demand analysis, outputting a field investigation and monitoring demand analysis report, executing a sensor network intelligent dynamic topology design, and outputting an intelligent dynamic sensor network layout detailed drawing. According to an intelligent dynamic sensor network layout detailed drawing, sensor preparation, verification and drilling channel construction are executed, and drilling holes and channels are output; cooperative arrangement, installation and fixation of a multi-parameter sensor are executed, an on-site sensing network is output, cables are led out and connected to an integrated data acquisition box in a tandem mode, cable tandem is executed, system integration and acquisition box installation and debugging are carried out, and an integrated on-site monitoring station is output. According to the method, the ultimate targets of comprehensive, synchronous and accurate monitoring and intelligent early warning of the roadbed water-salt-thermal coupling migration process are achieved, and the fundamental problems of data splitting and analysis lagging of a traditional method are effectively solved.

The invention provides an unmanned aerial vehicle multi-hop network intelligent resource allocation method based on deep reinforcement learning, and the method comprises the steps: abstracting task input into a virtual network, abstracting an unmanned aerial vehicle cluster into a physical network, and regarding a resource allocation process as embedding from the virtual network to the physical network. And processing a single node in the virtual network every time by taking the network state information as input, and updating the physical network resource information according to an output result. And a return value is obtained by counting the embedding success rate, evaluating the resource cost-effectiveness ratio and the network QoS (Quality of Service) performance. And calculating a dominant function expectation corresponding to the action by using the intelligent resource allocation network, and updating the strategy under constraint based on a strategy gradient optimization method until the network converges. Finally, task input is converted into a virtual network request, the virtual network request is input into the trained resource allocation network, an optimal embedding strategy is obtained, and efficient allocation of resources is achieved.

The application discloses a kind of hearing-impaired person intelligent terminal adaptive feedback method, intelligent terminal and system, it is related to smart home and barrier-free interaction technical field.The present application is aimed at the defects of single feedback mode, lack of intelligent scheduling and no adaptive capacity, constructs an end-to-end intelligent feedback scheme.First, the user situation characteristics are collected in real time by multidimensional sensor, and the situation characteristic vector is constructed;At the same time, the importance score of visitor is calculated by extracting the multi-modal features of visitor.Secondly, the situation characteristics and visitor characteristics are input into the deep Q network, and the optimal multi-modal feedback device combination and feedback intensity level are intelligently decided.Then, the graded response strategy is executed, and the reminder intensity is dynamically adjusted based on the user response.Finally, the decision model is continuously optimized through online learning mechanism.The present application realizes the leap from passive fixed reminder to active intelligent perception feedback, significantly improves the use experience and efficiency of hearing-impaired person intelligent terminal.

The application discloses a kind of train vehicle fault image intelligent analysis methods based on lightweight deep learning technology, comprising: obtaining train image data, then the train fault component to be detected in image is labeled, then the overall data is divided into training set, test set two parts;Data enhancement operation is carried out, the hyperparameter required by algorithm is configured, and the training sample is input into the MobileDetectNet neural network model formed after improvement to carry out feature learning;The learned feature model is input to the new vehicle image to identify faults, and finally the area of the fault occurs is framed and the corresponding alarm information is output.The MobileDetectNet network intelligent identification model of the application has few parameters, occupies less memory and has high recognition rate, can improve the recognition rate of EMU fault detection under the original equipment CPU environment, reduce the work intensity of artificial, shorten the maintenance operation time, reduce the missed detection probability, so as to ensure the safe operation of EMU.

Facilitating network slicing information preservation in advanced networks in advanced networks is provided herein. Operations of a system include receiving, from second network equipment, network slice configuration information for a user device during a first handover of the user device from the second network equipment to the first network equipment. The network slice configuration information can include information indicative of a first network slice and a second network slice generated via a microservice of a network intelligent controller. Further the operations can include transmitting, to third network equipment, the network slice configuration information for the user device during a second handover of the user device from the first network equipment to the third network equipment.

The invention relates to a network element service recovery method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: simulating a current network element network state in a virtual isolation environment, deploying a network element network agent, simulating a service fault through the network element network agent, obtaining a candidate switching network element, obtaining an evaluation parameter of the candidate switching network element under the condition that the current network element network state does not meet an emergency risk condition, performing comprehensive calculation on the evaluation parameters through an entropy weight method to obtain a comprehensive evaluation value of the candidate switching network element, inputting the comprehensive evaluation value, the current network element network state, the network topology and the service grading label into a pre-trained AI model to obtain a grading switching strategy, and simulating the grading switching strategy through a network element network agent to obtain a network element network state. And under the condition that the simulation result meets the network state condition, executing a hierarchical switching strategy, and recovering the service of the current damaged network element. By adopting the method, the service load capacity can be improved.

The application relates to the technical field of medical data processing, and discloses a mixed reality surgery training collaboration method and system supporting multi-role interaction. The method comprises the following steps: realizing surgery stage identification and dynamically adjusting multi-role permissions through weighted fusion of videos and instrument features, realizing virtual-actual accurate registration through non-rigid interpolation deformation, enhancing interactive immersion through spatial distance and motion parameter driven haptic feedback, guaranteeing data security through differential encryption and chain hash storage, and intelligently allocating bandwidth and dynamically adjusting model precision through a deep Q network. The application solves the problems of fixed multi-role collaboration permissions, insufficient virtual-actual registration accuracy, lack of feedback for gesture operation, unsafe data transmission and unreasonable network bandwidth allocation in the prior art.

The application discloses an unmanned aerial vehicle communication network intelligent cooperative switching system for suppressing multi-station interference, and belongs to the technical field of wireless communication networks.The technical problem to be solved by the application is how to actively avoid or reduce the same-frequency interference of unmanned aerial vehicles when communicating in the overlapping area of multiple ground stations, realize stable and efficient seamless switching, and improve the spectrum utilization and communication reliability of the whole network.The technical scheme adopted is as follows: the system comprises a synchronous ground station group, a network cooperative controller and an intelligent unmanned aerial vehicle terminal.The synchronous ground station group is the infrastructure of the communication network formed by multiple ground stations with time synchronization function, and each ground station has interference measurement and reporting functions.The network cooperative controller is used for acquiring global information including the position information of the intelligent unmanned aerial vehicle terminal and the network information of the subnetwork where the intelligent unmanned aerial vehicle terminal is located in real time, and constructing a network topology connection graph by using the global information, and dynamically constructing and maintaining a network interference relationship graph.

This invention discloses a space-based computing power network system, belonging to the field of integrated space-ground information network technology. The system includes space-based nodes deploying edge computing power resource pools, ground stations, and a ground-based cloud computing center. The ground station is equipped with a space-based computing power orchestration and management platform, including a computing power orchestration module and a network control module. The platform collects real-time information on the network's computing power, network, storage, and algorithm resources, forming a unified resource view. When a user station initiates a service computing power request including computing power scale, algorithm type, and network QoS requirements, the platform generates a computing power allocation strategy through the computing power orchestration module and a space-based network path through the network control module, supporting step-by-step or joint optimization to achieve resource collaborative scheduling and optimal configuration. Finally, the strategy and path are distributed to each node, and the system responds to the user station. This invention supports real-time on-orbit processing of services, reduces space-to-ground transmission latency and bandwidth requirements, and enhances the intelligence and autonomous operation capabilities of the space-based network.

The invention relates to the technical field of computing power networks, in particular to an intelligent scheduling method and system for a computing power network. The method comprises the following steps: collecting computing power node data, network link data and task demand data of each node in a computing power network, and generating a standardized data sample; inputting the standardized data sample into a demand analysis model to complete a task demand portrait; combining the task demand level with the real-time resource state of the computing power network, constructing a multi-target optimization scheduling model, and solving the model to obtain an optimal scheduling scheme adaptive to the task and the network state; according to the optimal scheduling scheme, computing power resource allocation and task issuing are completed; the system comprises a data acquisition module, a task demand analysis module, an intelligent scheduling decision module and an execution module. Through the above mode, systematic consideration of the computing power resource state, the task demand characteristics and the dynamic adaptation adjustment is realized, and accurate dynamic matching of the computing power resource and the task demand can be realized.

The invention relates to the technical field of commodity auditing and quality monitoring, in particular to a commodity auditing and intelligent inspection integrated traceability and quality monitoring system which comprises an information input unit, a data verification unit, a distributed storage network, an intelligent feedback module and a grading inspection unit. The system generates traceability tags through multi-level verification, dynamically collects the tags and executes hierarchical inspection, and ensures that data cannot be tampered in combination with a block chain technology. Meanwhile, the resource scheduling module optimizes load distribution, and the equipment compatibility detection module improves the terminal adaptability. According to the invention, high-efficiency auditing, accurate traceability and intelligent inspection of commodity information can be realized, and the quality monitoring efficiency and reliability are significantly improved.

The invention discloses a cross-regional edge node congestion collaborative early warning method based on federated learning. The method comprises the steps of data set construction, federated learning framework initialization, local model training, global model aggregation, congestion detection and congestion early warning. The invention relates to the technical field of cross-regional edge network intelligent monitoring, in particular to a cross-regional edge node congestion collaborative early warning method based on federated learning, which comprises the following steps of: initializing a sequence model at an edge node, constructing local loss combined with binary cross entropy and time sequence smooth punishment, and stably training by Adam and early stop; through weighted average aggregation disturbance parameters based on data volume and loss, performance degradation after fusion is prevented by adopting momentum fusion and a rollback threshold value; and meanwhile, an attention mechanism is embedded to realize joint prediction of probability, severity and duration, cross-regional propagation parameters of the graph neural network are utilized, loss is verified, and invalid sharing is rejected, so that prediction accuracy and timeliness are improved, and node congestion is effectively relieved.

The invention provides a radio access network intelligent controller (RIC), a dynamic resource block (RB) configuration method and a base station for dynamically configuring resource blocks. A plurality of base stations (BSs) continuously receive network state information from a plurality of associated UEs and transmit the network state information to the RIC. The RIC obtains network state information corresponding to a plurality of user equipments (UEs) from the plurality of BSs; the RIC identifies at least one interfered first UE in the plurality of UEs based on the network state information; the RIC sets a plurality of dynamic RB allocation strategies corresponding to the plurality of BSs based on the network state information, the at least one first UE and the at least one first BS; in response to receiving a dynamic RB allocation policy from an RIC, a plurality of BSs divide a plurality of dominant RBs into a plurality of first RB groups and a second RB group, thereby generating transmission resource allocation information corresponding to a plurality of UEs, so that the plurality of UEs identify respective plurality of allocated RBs.