3759 results about "Edge node" patented technology

The invention provides an intelligent Internet of Things public security management and control system and method based on multi-source data fusion, and belongs to the technical field of Internet of Things security. According to the system, unified collection and standardized processing of multi-source data are achieved by recognizing a system operation scene and loading corresponding model parameters and response strategies, and a unified semantic representation structure is constructed. And the system executes anomaly detection at an edge node, completes risk scoring and grading alarm judgment in combination with a semantic structure and anomaly feature information, and generates a control response instruction based on strategy matching. Meanwhile, dynamic optimization of the scoring model and identity authentication, behavior auditing and data compliance export in the operation process are supported. The system has intelligent identification, adaptive analysis and response closed loop capabilities, and improves the precision and credibility of public security management in the Internet of Things environment.

The invention relates to the technical field of energy scheduling, in particular to a multi-modal data fusion method and system based on energy scheduling and a storage medium. The method comprises the following steps: obtaining multi-modal data, and carrying out abnormal fluctuation feature extraction to obtain a space-time fusion abnormal feature labeling set; deducing a multi-objective optimization path according to the space-time fusion abnormal feature labeling set to obtain a dynamic scheduling decision map; performing edge node game equilibrium calculation according to the dynamic scheduling decision map to obtain a trusted scheduling verification chain; performing digital twinborn constraint optimization on the trusted scheduling verification chain to obtain a closed-loop scheduling digital twinborn body; compiling a dynamic scheduling instruction set based on the closed-loop scheduling digital twin to obtain an anti-disturbance energy scheduling strategy library; and obtaining real-time energy supply and demand data, and performing scheduling deviation tracing on the real-time energy supply and demand data according to the anti-disturbance energy scheduling strategy library to obtain an energy distribution decision. According to the invention, the efficiency and reliability of energy scheduling can be improved.

The invention belongs to the technical field of data transmission, and particularly relates to an SD-WAN low-delay data transmission method and system based on edge computing, a plurality of edge computing nodes are deployed in an SD-WAN architecture, and the edge computing nodes are distributed on a network edge side, close to terminal equipment or a branch mechanism and have data preprocessing and local computing capabilities; monitoring network state parameters of each link in the SD-WAN in real time, wherein the network state parameters comprise delay, bandwidth, packet loss rate and computing resource utilization rate of edge nodes; routing to-be-transmitted data to the target edge node, and if the node has local processing capability, executing data preprocessing or caching operation; otherwise, forwarding the data to an adjacent edge node or a cloud data center; a distributed cache strategy is adopted, when network congestion is detected according to data access frequency and timeliness requirements, non-real-time data is temporarily stored in a local cache, and asynchronous transmission is executed after a link is recovered, so that the method has the effect of providing higher-quality and more reliable network service for a user.

An Al -based energy edge platform is provided herein with a wide range of features, components and capabilities for management and improvement of legacy infrastructure, coordination, and orchestration with distributed systems to support important use cases for a range of enterprises. An Al -based energy edge platform may include a graph neural network including a set of nodes respectively representing at least one distributed energy resource (DER) and a set of edges respectively interconnecting the set of nodes, wherein each edge represents at least one energy - related feature among at least two nodes of the set of nodes. The platform may incorporate emerging technologies to enable ecosystem and individual energy edge node efficiencies, agility, engagement, and profitability. Embodiments may forecast, plan for, and manage the demand and utilization of energy in greater distributed environments. Embodiments may employ intelligent provisioning, data aggregation, and analytics to leverage energy market connection, communication, and transaction enablement platforms.

The invention provides a computing resource optimization method and system for analysis tasks, and belongs to the technical field of computers.The computing resource optimization method comprises the steps that the priority of each analysis task is determined according to feature information of each analysis task and current available computing resource state information of the system, and a priority queue is generated; obtaining a task load prediction value according to the historical task load data and the real-time system state data; according to the type of the analysis task, the data scale and the data source position, the analysis task with the real-time requirement higher than a preset standard is allocated to an edge node to be executed, and resource allocation of the edge node is dynamically adjusted according to a task load predicted value; and dynamically allocating available resources from the computing resource pool according to the priority queue and the task load prediction value so as to execute the plurality of parallel analysis tasks. According to the resource management method based on task priority dynamic adjustment, task load prediction and edge computing optimization scheduling, real-time prediction and dynamic self-adaptive scheduling of computing resources are achieved.

The invention discloses a big data auxiliary key generation method and system in communication data encryption transmission, and relates to the technical field of big data analysis and processing. The dynamic entropy source processing module is used for generating a high-randomness entropy pool by combining an information entropy quantification model and adopting a Shannon entropy and minimum entropy fusion algorithm; the anti-quantum key generation module is used for generating a dynamic variable-length key seed based on an entropy pool driven post-quantum cryptographic algorithm; the hierarchical key negotiation module adopts a clustering Diffie-Hellman protocol, dynamically divides negotiation according to network topology, and precomputes and reduces the load of a core network through edge nodes; and a lightweight verification and update module. According to the method, high-entropy sources such as environmental noise, user behaviors and equipment hardware fingerprints are fused with low-entropy sources such as network messages and sensor data, and an intelligent acquisition strategy and a nonlinear decorrelation technology are combined, so that the anti-quantum dynamic entropy pool is generated, and the randomness of a secret key and the reliability of the entropy sources are improved.

The invention relates to the technical field of tunnel power supply and distribution, in particular to a tunnel modular prefabricated cabin power supply and distribution intelligent substation self-adaptive regulation and control system based on edge calculation. Comprising an edge calculation and AI decision-making unit which is used for realizing rapid acquisition, processing and instant decision-making of tunnel power supply and distribution multi-dimensional data, generating a power supply and distribution adaptive regulation and control strategy by deploying calculation resources and a machine learning algorithm at edge nodes close to a data source, and converting the strategy into an executable regulation and control instruction; a cloud platform collaborative management unit; and an intelligent sensing and internet-of-things unit. According to the invention, hierarchical decision control of the tunnel power supply and distribution system is realized by constructing a hybrid architecture of edge computing and cloud platform collaboration and a priority judgment mechanism; according to the invention, multi-modal data are integrated through the multi-protocol communication link module and the full-scene data fusion analysis module, and data association analysis is realized through Kalman filtering, D-S evidence theory and other algorithms.

The invention relates to the technical field of data processing, and discloses a real-time data processing analysis method and system of an industrial PLC. The method comprises the following steps: transmitting temperature, pressure, current, vibration and acoustic parameters acquired by multiple sensors to an industrial PLC (Programmable Logic Controller) in real time to obtain multi-source heterogeneous original data; preprocessing the multi-source heterogeneous original data to obtain standardized fusion data; correlation calculation and anomaly recognition are carried out through the multivariate analysis model, and an abnormal state classification result is obtained; dynamically adjusting data interaction frequency and sampling rate between the edge nodes and the central PLC, and generating a real-time control decision instruction; and matching the real-time control decision instruction with the current motor load fluctuation state, and outputting the optimal frequency conversion control parameter. According to the invention, the response delay of the system is reduced, the control precision and reliability are improved, the dynamic balance between the safety and the energy efficiency is realized, and the system can intelligently adjust the control strategy according to the real-time safety situation.

The invention discloses a multi-modal data real-time identification and cooperative processing system based on edge computing and federated learning. The multi-modal data real-time identification and cooperative processing system comprises a cloud center coordination node, a plurality of edge computing nodes, a cross-modal encryption engine, a federated learning controller and a model updating verification module. The cloud center coordination node executes federated learning model aggregation and dynamic task allocation, and generates a cross-modal encryption strategy; and the edge computing node is configured with a multi-modal data acquisition module, a local model training unit and a co-processing gateway to realize multi-modal data acquisition and local processing. The system encrypts vision, acoustics and text data by using differentiated algorithms such as spatial confusion, frequency domain permutation and homomorphic encryption; the federated learning controller carries out multi-modal feature fusion, hierarchical encryption and dynamic networking at the edge node; and the model updating verification module performs aggregation updating after ensuring parameter consistency by using secure multi-party calculation. According to the method, real-time processing and privacy protection of multi-modal data are realized, and the data co-processing efficiency is improved.

The invention discloses an electric power data anomaly detection method and system combined with edge computing, and particularly relates to the field of electric power data anomaly detection.The electric power data anomaly detection method comprises the steps that a periodic abnormal behavior chain structure is established by extracting a continuous judgment result, actual physical feedback and a historical standard response track of edge nodes to electric power data; and a weighted residual trend path is generated, so that identification of a node judgment offset state and quantification of an abnormal trend are realized. By constructing a power data abnormal behavior chain and a multi-cycle residual error trend graph, an edge node misjudgment offset state is identified, and path suppression and channel structure correction are executed, so that the node safety judgment accuracy and the abnormal response stability in an edge computing environment are improved.

The invention discloses a cloud-edge collaborative intelligent storage node dynamic deployment method and system. The method comprises the following steps: monitoring performance indexes such as edge node data traffic and storage resource state in real time; a deep learning algorithm combining time sequence analysis and an LSTM neural network is adopted to analyze traffic information, and a data access demand is predicted; edge nodes and cloud storage resource configuration are dynamically adjusted based on a prediction result, and an intelligent scheduling algorithm, a data cold and hot separation strategy and a self-adaptive fragmentation technology are introduced to allocate resources; the storage node layout is optimized in real time, and an optimal data distribution path is selected through a reinforcement learning strategy; data security and access control are realized by adopting end-to-end encryption, multi-level access control and block chain technologies. The system comprises a monitoring acquisition module, a prediction analysis module, a resource scheduling module, a path optimization module and a security control module. According to the method, the utilization efficiency of storage resources is improved, data delay is reduced, system stability and data security are enhanced, and the method is suitable for a cloud edge collaborative storage scene.

The invention discloses a network attack AI detection analysis method and system based on the smart Internet, and belongs to the technical field of network security protection, and the method comprises the steps: building an attack feature library through distributed edge nodes in a cooperative manner, generating feature parameters of each node based on a local attack event, and transmitting the feature parameters to a central server for dynamic fusion through encryption; constructing a multi-modal interaction graph, identifying a potential attack link based on association strength among graph nodes, and deducing an attack intention to generate a defense strategy; deploying a virtualized network environment, dynamically injecting induction characteristics, and adjusting an induction strategy in real time according to the interaction behavior of an attacker; and monitoring an abnormal mode of the user behavior sequence, triggering an AI interaction verification process and storing a defense strategy. According to the method, rapid collection and fusion of network attack features are realized, the detection delay of network attacks is reduced, the accuracy of attack prediction is improved, the flexibility and effectiveness of network attack confrontation are enhanced, and the defense intelligence and adaptive ability of the whole network are improved.

The invention relates to the technical field of Internet of Things communication, and discloses an Internet of Things data information transmission method, a switch and a transmission system. The method comprises the following steps: acquiring multi-source data streams of Internet of Things terminal equipment, dynamically fragmenting according to types to generate fragmented data packets, matching a target transmission protocol for the fragmented data packets, generating a dynamic routing path in combination with a priority mark and the like, and transmitting the dynamic routing path. The system also has the functions of link quality evaluation and route adjustment, redundant coding packet loss recovery, transmission delay and integrity monitoring processing, encryption transmission based on security level, resource optimization, transmission strategy adjustment and the like. The switch is integrated with a data fragmentation module, a protocol matching module and the like. The transmission system comprises a terminal device cluster, an edge node network, a cloud server and a protocol conversion gateway. The data transmission efficiency, reliability and safety are improved, resource utilization is optimized, and the data transmission problem of the Internet of Things is effectively solved.

The invention discloses a power distribution network collaborative management method and system based on artificial intelligence, and relates to the technical field of electrochemical detection, and the method comprises the steps: constructing a distributed edge computing node network, deploying nodes at key positions of a power distribution network, achieving the collection and preprocessing of local power data, and reducing the cross-regional data transmission pressure; an AI real-time communication scheduling model is established based on the preprocessed data, communication resources are dynamically allocated according to the operation state of the power distribution network, and fault data transmission is guaranteed preferentially; seamless interaction of multi-protocol equipment is realized through a self-adaptive protocol conversion mechanism containing protocol identification, format conversion and data verification; training a fault diagnosis model by using a federated learning framework, and enabling edge nodes to only upload parameters to a coordination center for aggregation and updating, so as to balance model precision and data privacy; when a fault is detected, a millisecond response mechanism is started, and a processing strategy is generated and executed in combination with edge local decision and central global optimization.

The invention relates to the technical field of knowledge graph retrieval, in particular to a genuine medicinal material intelligent retrieval method and system based on a graph. The method comprises the following steps: performing semantic granularity analysis on a retrieval request input by a user, constructing a multi-level semantic edge and generating a hierarchical semantic graph structure; semantic enhancement is carried out on the map relation through semantic annotation, and a multi-condition intention is extracted in combination with dimensions such as regions, drug properties and channel tropism; further, the system executes multi-hop path combination, a structured semantic path conforming to the composite intention is mined, edge nodes in the path are inferred and complemented, and a genuine medicinal material retrieval result with a closed structure and complete semantics is generated. Compared with a traditional keyword matching and static field retrieval mode, the method has higher semantic perception ability and reasoning intelligence, and the accuracy and adaptability of the system in processing fuzzy, composite and path-incomplete retrieval scenes are remarkably improved.

The invention discloses a financial network security defense method and system based on multiple Agents and a dynamic large model. A detection Agent is deployed in an edge layer, financial network node flow data and system logs are collected in real time, time sequence features are extracted through a lightweight convolutional network, and a preliminary anomaly score is generated. And the cloud layer constructs a decision Agent, receives the feature abstract transmitted by the edge node in an encrypted manner, inputs the feature abstract into a dynamic large model for multi-modal feature fusion, and outputs defense action probability distribution. And the intelligence Agent constructs a cross-institution federated learning network. And constructing a dynamic game engine, constructing a revenue matrix based on the attack cost and the defense revenue, solving a Nash equilibrium strategy, and generating an optimal defense instruction set. And dynamically allocating detection tasks according to the threat level and the edge computing power state. According to the method, efficient acquisition and analysis are realized, the abnormal behavior recognition capability is improved, support is provided for making a defense strategy, the defense strategy is optimized, and the intelligent, automatic and efficient levels of defense are improved.

The invention discloses an end-side cloud collaborative intelligent fire-fighting fire monitoring system based on image fusion, and relates to the technical field of intelligent fire-fighting, the system is composed of a plurality of functional modules, and the system comprises a multi-modal image fusion module which generates a dynamic scanning priority map based on prior data, distinguishes a natural heat source from an abnormal fire by using a dual-light fusion algorithm, and sends an image fusion result to a cloud server; a scanning area is divided according to the thermal risk grade, and the thermal imaging resolution is dynamically adjusted; the distributed edge computing module is used for carrying out space-time synchronization on cross-modal data through a multi-modal feature alignment network, and carrying out dynamic allocation on a CUDA core and CPU resources through adaptive computing scheduling; an improved artificial bee colony algorithm is adopted, the bandwidth of the multi-sensor data flow is dynamically allocated through a time-sharing multiplexing protocol, and three-dimensional path planning is carried out; and the end-side cloud collaborative decision module constructs a federated learning driven model sharing network, and each edge node trains a lightweight YOLOv5s pruning model based on local data.

The invention relates to the technical field of logistics management, in particular to an intelligent logistics terminal equipment collaborative management and control system based on AI edge computing, and the system comprises an edge data fusion and state recognition module which is deployed at an edge node, collects multi-source data of an operation state, environment perception, a communication link and the like, and generates an equipment state representation vector through fusion; the intelligent prediction and task scheduling decision module uploads the state vector to a cloud, predicts task completion capability and fault probability, and generates a task scheduling decision packet; the scheduling strategy issuing and edge execution collaboration module issues a scheduling packet through a multi-protocol gateway, and an edge node completes task distribution, communication switching and resource scheduling and caches a key strategy. According to the invention, the real-time sensing of the state of the logistics terminal equipment, the intelligent prediction and resource optimization of task scheduling, and the quick response and fault-tolerant control in a fault scene are realized, and the operation efficiency, the intelligent level and the stability of the system are remarkably improved.

The invention relates to a weak current equipment abnormity judgment method and system based on the Internet of Things. The method comprises the steps that multi-dimensional parameters such as temperature, current, voltage and vibration frequency are collected through nodes of the Internet of Things, and a dynamic tracking identifier is generated; performing dynamic parameter association analysis on edge nodes, and establishing a real-time coupling degree relationship between parameters; according to the analysis result, evaluating the abnormity level in a grading manner, and distinguishing the primary abnormity of single parameter deviation and the advanced abnormity of multi-parameter collaborative deviation; the cloud platform starts a differential verification mechanism for different levels of anomalies, primary anomalies are transversely compared, and advanced anomalies execute full-life-cycle backtracking verification; the system comprises a data acquisition module, an edge calculation module, an analysis and evaluation module and a cloud analysis platform, and can realize the method. According to the invention, through dynamic coupling degree analysis and a hierarchical verification mechanism, the abnormality judgment accuracy is remarkably improved, and false alarms caused by environmental interference are effectively reduced.

The invention provides a dynamic routing selection method and system, electronic equipment and a storage medium, and aims to solve the problem that a routing strategy is difficult to adapt to a dynamically changing network, the method comprises the following steps: a terminal layer collects the state of a terminal and network data, and performs lightweight feature extraction; the edge node layer receives the data of the terminal layer, carries out space-time-semantic feature aggregation, and generates a region-level resource scheduling and routing decision strategy based on fragmented reinforcement learning; the central cloud service layer gathers whole network data, generates a global optimization strategy and issues the global optimization strategy; the edge node layer fuses global optimization and a region-level strategy, and executes dynamic routing selection; and security and privacy protection are provided through the trusted chain layer. According to the invention, adaptive path selection can be realized, the network resource utilization rate is improved, and the network stability is improved.

The invention relates to a distributed large two-layer network intelligent routing method and system based on edge cloud nodes, and belongs to the technical field of computer networks. Aiming at the problems of slow routing decision response and low fault recovery efficiency of the existing network in a dynamic environment, the invention provides a method for periodically collecting link bandwidth utilization rate, transmission delay and other state information through an edge cloud node, uploading the state information to a central cloud platform to generate a global routing strategy and issuing the global routing strategy to the edge node, and triggering fault switching in combination with local dynamic threshold monitoring. According to the technical scheme, bidirectional communication between edge nodes and a central platform, a neural network model of spatial-temporal feature fusion and a path priority generation mechanism of multi-objective optimization are included. The method and the system are suitable for a large-scale distributed network environment, and network resource utilization rate and service continuity can be improved.

The invention relates to the technical field of mining data processing, and particularly discloses a coal yard production operation real-time monitoring management system. Aiming at the problems of difficulty in dynamic matching of time series data caused by insufficient cache capacity of edge nodes and fault diagnosis delay caused by data flow breakpoints or redundancy, the system adopts a multi-stage cache architecture, and physical mapping and quick positioning of data are realized through dynamic resource allocation of a real-time processing layer and a batch buffer layer in combination with three-dimensional grid spatio-temporal indexing. A breakpoint compensation mechanism is utilized to trigger target area resampling and historical data prefetching, and data stream continuity is guaranteed; and dynamically screening the data based on the confidence coefficient weight, and inhibiting redundancy accumulation. The collaborative optimization engine establishes a parameter linkage rule of the collection frequency, the cache period and the fusion threshold value, and the resource priority is inclined during high-risk early warning. And through closed-loop feedback and edge-cloud collaborative learning, a data processing strategy is continuously optimized. The cache resource utilization rate and the diagnosis timeliness are improved, and the method is suitable for real-time safety monitoring of complex industrial scenes.

The invention provides a self-adaptive adjustment Internet operation and maintenance strategy generation method and system, and relates to the technical field of Internet, and the method comprises the steps: 1, dynamically collecting the operation state data of a target operation and maintenance environment through a distributed sensor and an edge node, and generating a multi-dimensional time series data set; 2, performing space-time correlation analysis on the multi-dimensional time sequence data set, determining a reference data node, constructing a two-dimensional correlation structure, and generating a dynamic judgment interval; and step 3, respectively selecting monitoring sample sets in the inner domain and the outer domain of the dynamic judgment interval, generating a trajectory feature sequence according to the time evolution relationship of the sample sets, and calculating a dynamic correction coefficient based on the trajectory feature sequence. According to the method, the self-adaptive circulation control is formed by dynamically adjusting the threshold baseline, the judgment interval and the strategy generation rule, the accuracy and effectiveness of the internet operation and maintenance strategy are improved, and the stability of internet operation is enhanced.

The invention relates to the technical field of edge calculation application and partial discharge detection, in particular to a partial discharge multichannel signal real-time synchronous acquisition method based on edge calculation. According to the method, the functions of multi-channel signal acquisition, time synchronization, feature analysis, hierarchical storage and the like are integrated at edge nodes, asynchronous acquisition, unified timestamp marking and data synchronous fusion of multiple types of partial discharge signals are realized, and extraction of multi-dimensional feature parameters such as time domain, frequency domain and energy and intelligent event discrimination are locally completed. For abnormal signals, the system realizes classified storage and remote uploading after encryption and compression processing; and for normal signals, dynamic management is carried out through circular caching. According to the method, the accuracy and efficiency of multichannel signal synchronous acquisition are remarkably improved, the data safety and the system adaptive capacity are enhanced, and the method is suitable for real-time online monitoring and intelligent diagnosis of partial discharge of power equipment.

The invention relates to the technical field of edge task scheduling, and discloses a smart city dynamic task scheduling method based on cloud end-to-end collaboration and a storage medium, and the method comprises the steps: training an XGBoost priority prediction model at a smart city cloud control center based on the resource characteristics of historical tasks and the state of end-side equipment, constructing a cloud experience pool through a genetic algorithm, and carrying out the optimization of the cloud experience pool; periodically issuing to an edge node; meanwhile, all the tasks to be distributed are distributed to edge nodes of corresponding jurisdictions in a balanced mode; an edge node constructs an edge experience pool, a cloud experience pool is fused, and a strategy generation model is obtained through near-end strategy optimization training; according to the order of the task priorities predicted by the XGBoost priority prediction model, sequentially inputting the task priorities into the strategy generation model, obtaining target end side equipment of the current to-be-allocated task, and issuing the to-be-allocated task; and after updating the edge experience pool and the strategy generation model in real time based on the distributed task, distributing the next task to be distributed.

The invention provides a three-dimensional space data analysis method and system based on deep learning, and relates to the field of computer vision, and the method comprises the steps: carrying out the modeling of a static scene fundamental model and a dynamic object motion track through a space-time separated dynamic nerve radiation field; a lightweight dynamic neural radiation field model is deployed at an edge computing node, multi-modal sensor data are processed in real time, local three-dimensional scene representation is generated, rendering and prediction computing of a neural radiation field are executed on the edge node, and the implicit feature difference quantity of scene change is uploaded to a cloud; and the cloud end aggregates feature difference data of multiple edge nodes through a federated learning framework, dynamically updates a global scene priori knowledge base and issues the global scene priori knowledge base to the edge nodes. The method can improve the processing efficiency, precision and applicability of the three-dimensional data, and is especially suitable for carrying out tasks such as object recognition, target detection and semantic segmentation in a complex environment.

The invention discloses a carbon emission intelligent prediction method and system based on big data, and relates to the technical field of carbon emission monitoring, and the method comprises the steps: collecting carbon emission associated data, and generating a carbon emission feature tensor through quantum time-space coding and time-space grid alignment; constructing a dynamic causal graph network through causal entropy on the basis of the carbon emission feature tensor, and generating a causal weight matrix by combining anti-fact intervention and a Bayesian false-rejecting causal relationship; constructing a federated learning framework based on the causal weight matrix, deploying a federated aggregator at a cloud end to aggregate the encryption gradient of each edge node, and embedding a causal regular term in a federated loss function to perform joint training to generate a global carbon emission prediction model; according to the method, efficient fusion of industrial sensor data, satellite remote sensing data and other multi-source heterogeneous data is realized by utilizing quantum bit superposition state mapping and quantum entanglement state association technologies.

The invention relates to the technical field of data processing, in particular to a multi-AI algorithm collaborative intelligent management system based on a large model, and the system comprises a data access module which collects original messages of terminal equipment of multiple manufacturers; the protocol adaptation module analyzes a device communication characteristic spectrum through a quantum entanglement separator, and outputs a standardized time-space event stream; a federation modeling module creates a parallel calculation instance, and a quantum tunneling mechanism is utilized to fuse the feature vectors to generate an equipment association topology model; the chaotic scheduling module generates an atomic task fractal network and assigns the atomic task fractal network to edge nodes; the interface optimization module calculates an interface field mapping relation through a quantum Boltzmann machine; and the closed-loop correction module triggers equipment communication characteristic spectrum re-calibration. Multi-source device communication differences are eliminated through quantum protocol analysis, federated quantum fusion breaks through algorithm collaboration barriers, chaotic fractal scheduling realizes resource dynamic optimization, a closed-loop collaboration system of device access to interface configuration is formed, and the problems of protocol incompatibility of multi-source heterogeneous devices and AI algorithm collaboration obstacles are solved.

The invention provides a complex scene-oriented AI large model lightweight deployment method, and relates to the technical field of edge computing, and the method comprises the steps: carrying out the structured pruning of a pre-trained Transform network based on the attention head importance score, carrying out the dynamic sparsification of the activation state of a feedforward network according to the input tensor entropy value, employing the dynamic mixing precision quantization, and carrying out the reconstruction of an AI large model. Obtaining network parameters after pruning quantization; deploying the pruned and quantized network parameters to an edge computing device, distributing a feature extraction operator to a neural network processor through a heterogeneous computing scheduler, and unloading a classification operator to a multi-core central processing unit; and managing an on-chip memory in combination with a virtual memory paging mechanism, realizing zero-copy data transmission by utilizing a direct memory access controller, and outputting a reasoning result tensor. According to the method, efficient and reliable operation of the large model at the resource-constrained edge node is realized.

The invention relates to the technical field of data management, in particular to a low-altitude economic flight data management method and system based on edge computing, and the system comprises edge computing nodes deployed on an aircraft and a ground base station, a sensor for collecting multi-source data, a module for preprocessing the data, and an annular data queue caching mechanism. The system comprises a composite biological feature code generation module, a distributed storage edge node, an abnormal fluctuation feature extraction module, an equipment health state and trend analysis and calculation module, a virtual power supply manager, a main power supply, a standby power supply, an abnormal behavior monitoring module and a defense strategy library. After preprocessing and caching, feature codes are generated and encrypted distributed storage is carried out, dynamic resource adjustment is realized through state evaluation and a digital twinning and optimization algorithm, a neural network is utilized to manage a power supply, data security is guaranteed in combination with abnormal monitoring, and a whole-process management system is formed.