2661 results about "Edge device" patented technology

An AI-enhanced distributed system for neural network-based data compression leverages reinforcement learning optimization and privacy-preserving computation across edge and central computing devices to autonomously optimize efficiency and quality. The system includes a lightweight compression subsystem at edge devices that applies privacy-preserving preprocessing and partially compresses input data before securely transmitting it to central computing devices. A reinforcement learning agent continuously monitors system performance and automatically optimizes compression parameters, model selection, and task allocation based on multi-objective rewards. The central compression subsystem processes data using AI-optimized parameters and temporal modeling components. The system incorporates hardware detection capabilities that automatically select optimal compression models based on available processing resources and implements homomorphic encryption for computation on encrypted data while coordinating federated learning across distributed devices. This AI-enhanced distributed approach improves bandwidth efficiency, energy consumption, and adaptability while ensuring data privacy and security.

A system and method for temporal acceleration encoding in Lorentzian latent space enables real-time event forecasting within navigable spatiotemporal media. The system encodes media data into compact Lorentzian latent patches using variational autoencoders and organizes them within a multi-dimensional hyperspace spanning spatial, temporal, orientation, scale, and spectral coordinates. Temporal acceleration encoding computes velocity and acceleration vectors along geodesic trajectories, extracting event signatures through multi-scale aggregation over sliding windows. An acceleration-indexed memory stores dynamic descriptors with composite keys comprising hyperspace coordinates and motion characteristics. Event forecasting retrieves similar historical patterns and conditions a forecast head to produce event probabilities and time-to-event estimates with uncertainty calibration. The system streams forecast metadata to edge devices for real-time prediction and adaptive navigation, supporting applications in surveillance, autonomous systems, predictive media exploration, and anomaly detection where both temporal forecasting and multidimensional navigation capabilities are essential.

The invention provides a multi-feature fusion rumor detection method, system and device based on knowledge distillation, and mainly solves the problems that an existing model is high in calculation overhead, insufficient in feature fusion and insufficient in emotion utilization. The method comprises the steps of firstly obtaining multi-dimensional data such as social media original texts and comments; extracting deep semantic representation by using a pre-training model, and analyzing comment emotion features in combination with a hybrid neural network; then, features such as semantics, emotions, emoticons and populations are input into a hierarchical gating interactive fusion network (GIFN), and weights are dynamically adjusted to achieve effective fusion of multi-granularity features; in order to reduce complexity, a knowledge distillation framework is designed: a deep GIFN is used as a teacher network to generate a soft label, and a lightweight student network (LSTM) is guided to perform training. According to the trained student model, the parameter quantity is remarkably reduced, meanwhile, good detection performance is kept, the student model can be conveniently deployed in an actual content auditing system or edge equipment, and social content rumors can be efficiently recognized and judged.

The invention relates to the field of building intellectualization, in particular to a digital twinborn mixed cloud edge collaborative intelligent house building group operation and maintenance intelligent system, which establishes a digital twinborn scene database by collecting building basic information, equipment operation data and environmental parameters, synchronizes the digital twinborn scene database to edge equipment, and uses BIM, GIS, Internet of Things, 5G and AI technologies to establish a digital twinborn scene database, so as to realize the intelligent operation and maintenance of a building group. A virtual-real combined digital intelligent building scene is constructed, real-time synchronization of a virtual scene and a physical environment is realized through AR / VR equipment, and an operation and maintenance module comprises multi-source heterogeneous data fusion, edge intelligent analysis decision, adaptive model training and iterative optimization, a predictive maintenance algorithm of virtual-real mapping and a multi-level collaborative decision and autonomous scheduling mechanism. And the monitoring module monitors the state and operation condition of the edge equipment, provides data service and supports visualization of management decisions, and the system effectively improves the intelligence and digitization level of operation and maintenance of the building group.

The invention discloses a battery full life cycle intelligent management method and system based on a large model, and the method comprises the following steps: S1, collecting the operation data of a battery, and carrying out the preprocessing; s2, inputting the pre-processed sample into a pre-trained Transform encoder model, and extracting a time sequence and cross-stage characteristics; s3, executing model reasoning, outputting a state index, and generating a battery state vector; s4, identifying an abnormal category and a position in combination with the working condition information; s5, generating a dynamically optimized battery management strategy based on the battery state index and the abnormity identification result; s6, deploying a lightweight model at the edge device, executing local reasoning and uploading data; s7, the cloud updates the model through self-supervised training and issues the model; and S8, repeatedly executing the steps S1 to S7, and carrying out optimized closed-loop management. According to the invention, large model modeling and an edge cloud cooperation mechanism are fused, and intelligent sensing and dynamic management of the whole life cycle of the battery are realized.

The invention relates to the technical field of edge device security policy deployment, in particular to an edge device-oriented lightweight AI security policy adaptive deployment method. The method comprises the following steps: collecting operation state information of edge equipment, and constructing a current multi-dimensional environment vector and a sliding window feature vector; constructing a strategy candidate library, constructing a strategy adaptability scoring function based on the current multi-dimensional environment vector and a real-time perceived network threat event, and scoring and sorting all candidate strategy items to obtain a strategy execution candidate set; and performing scheduling optimization on the strategy execution candidate set by adopting a multi-objective optimization algorithm, and selecting a strategy combination with the highest deployment score as a deployment result. According to the method, a multi-dimensional strategy adaptability scoring function is constructed, candidate strategy items are screened according to current network threat events and system resource conditions, a strategy screening mechanism from fixed template type configuration to resource awareness and attack scene linkage is converted, and the pertinence and accuracy of strategy deployment are improved.

The invention provides a large model lightweight reasoning deployment method under limited hardware resources, and the method comprises the steps: quantifying the weight importance of a large model through a composite index of gradient sensitivity and activation frequency, and carrying out pruning operation in combination with an improved index weighted moving average strategy, thereby obtaining a structured sparse model; the sparse model is divided into sub-networks by adopting double rules, a routing decision network is trained, and an adaptive feature shunting architecture model is constructed; a multi-precision weight set is generated through a nested quantization technology, quantization bit width is dynamically adjusted, and edge equipment hardware parameters are adapted to complete reasoning environment initialization; after a reasoning request is received, an optimal sub-network is selected based on the trained routing decision network, corresponding weights are loaded in parallel, and a reasoning result is fused and output; and converting a reasoning result format, and dynamically optimizing a scheduling strategy based on a system real-time monitoring index. The method is compatible with a mainstream large model and a hardware platform, and an efficient and universal deployment scheme is provided for end-side AI engineering landing.

The invention discloses a federated learning backdoor defense method based on pruning and fine tuning in the technical field of artificial intelligence and network security, the method realizes defense through two core mechanisms of dynamic pruning and gradient constraint fine tuning, and the method comprises the following steps: firstly, calculating a sensitivity score based on a neuron activation frequency and a weight outlier degree; dynamically identifying and cutting redundant neurons utilized by a backdoor, and blocking an abnormal activation path; secondly, gradient direction consistency detection and amplitude constraint are introduced in the fine tuning stage, and a malicious client is inhibited from reconstructing a back door through an abnormal gradient; the server continuously purifies model parameters and enhances robustness by cyclically executing pruning, fine tuning and aggregation operations; the method does not need to depend on an extra clean data set, strictly follows a federated learning privacy protection principle, reduces communication overhead through lightweight pruning, maintains main task performance in combination with gradient constraint, is suitable for a federated learning scene in which edge equipment participates, and effectively balances a defense effect and model stability.

The invention discloses a road safety early warning method and system based on a mixed precision quantification visual large model, and the method comprises the steps: collecting road traffic safety videos and pictures, and carrying out the preprocessing, data enhancement and marking, thereby forming a diversified data set; a pre-trained visual large model is selected as a teacher model, after fine tuning, output layer and middle layer knowledge is extracted, key features are weighted, and meanwhile, a lightweight neural network is taken as a student model, same input is received, and prediction and middle feature maps are output. And inputting data into the two models and the student model to carry out mixing precision quantification forward propagation, constructing a total loss function containing tasks, knowledge distillation and quantification learning loss, and updating parameters through back propagation. And after training is completed, exporting a quantitative model, and deploying the quantitative model to an edge computing platform to realize safety early warning. The lightweight model can realize rapid reasoning on edge equipment such as a vehicle-mounted road side, and the problem that performance and efficiency are difficult to consider in a traditional model compression method is solved.

The invention belongs to the technical field of smart city construction and intelligent construction management, and particularly relates to an intelligent scheduling and cooperation system and method for the whole life cycle of city reconstruction. The system comprises an edge sensing layer, a digital twinning network module, a space-time brain module, a block chain collaborative trust layer and an XR collaborative interaction layer. The system collects multi-source data of a construction site in real time through a 5G edge device, realizes fusion modeling of BIM, GIS and TIN models by using a graph convolutional neural network, and performs multi-target scheduling optimization in combination with meta reinforcement learning and a dynamic graph neural network; and meanwhile, construction task verification and fund payment linkage is realized through a block chain smart contract, and immersive cooperation and visual acceptance are provided in cooperation with an AR / VR platform. According to the method, the problems of model splitting, scheduling response lagging, low data collaboration efficiency, insufficient credibility of the performance process and the like in the urban reconstruction project are solved, and the intelligence, transparency and automation level of the construction process is remarkably improved.

Disclosed in the present invention are an edge-deployed semi-supervised anomaly detection method and system for a railway track foreign object. The method comprises the following steps: an edge device encoding and decoding a video stream captured by a camera to obtain an image frame sequence, and performing frame extraction; and using a semantic segmentation model to perform image segmentation on a certain image frame obtained by means of frame extraction, to obtain a railway track region segmentation image. The use of a single image as input may generate an expert model result having a high weight value; however, the determination based on a single image is not stable, multiple consecutive images of the task scene need to be inputted, the frequency of each expert model obtaining the highest weight is computed, and the expert model corresponding to the highest frequency is the final solution. The present invention supports scene-adaptive foreign object detection algorithm automatic selection, and a user can perform selection on the basis of prior knowledge, or selection may be performed by a scene-adaptive automatic algorithm selection method; the user only needs to provide a batch of image data of the current scene, and the optimal algorithm selection can be evaluated.

The invention discloses an air valve on-line self-adaptive adjusting method and system fusing digital twinning, and belongs to the field of air valve intelligent adjusting.The adjusting method comprises the following specific steps that firstly, edge devices collect and preprocess multi-source data of a corresponding air valve system, and based on the preprocessed multi-source data, the multi-source data of the corresponding air valve system are obtained; constructing a virtual simulation environment corresponding to the current air valve system; iI, in a virtual simulation environment, pre-training an air valve control model, identifying a causal relationship between each sensing parameter and an air valve adjustment result, and dynamically optimizing each control variable; according to the method, model prediction precision and simulation credibility are remarkably improved, dependence on a large amount of new data is reduced, cross-system rapid adaptive adjustment is realized, misjudgment and interference of confounding factors can be avoided during strategy optimization, interpretability and credibility of model decision are enhanced, data privacy is protected, convergence of a global strategy is accelerated, and the method is suitable for large-scale popularization and application. The overall intelligent level of the system is improved.

The invention discloses a light-weight instrument small target detection model and method for a complex industrial scene, belongs to the crossing field of deep learning and edge calculation, and aims to solve the problem that an existing method cannot meet the real-time detection requirements of edge equipment such as an inspection robot in the aspects of precision, efficiency and small target detection capability. The model comprises a lightweight backbone network used for extracting multi-scale features from an input image; the cross-scale feature fusion network is used for bidirectionally fusing the multi-scale features, retaining shallow space details and deep semantic information and outputting fused features; the deformable large-kernel target sensing module is deployed at a specified position of the cross-scale feature fusion network so as to better capture feature information related to a target area and improve the feature expression capability of a small target; and the multi-task decoupling prediction network performs classification, positioning regression and confidence prediction on the input image in parallel, and a positioning regression branch adopts an EIOU loss function of decoupling width and height optimization.

The invention relates to the technical field of data processing, in particular to a new energy uncertainty multi-type energy storage staged capacity optimization configuration method, which comprises the following steps: acquiring energy storage parameters, new energy output and user load data through edge equipment, and verifying photovoltaic conversion efficiency and lithium battery electrochemical behaviors through a physical model to generate a high-confidence data set; the federal cooperative system fuses distributed node data to output a health degree distribution diagram, and the memory network analyzes the temperature and the charge-discharge coupling effect to generate a dynamic compensation coefficient alpha; an optimization engine receives the alpha value and wind and light prediction, generates a staged scheme through a parallel algorithm, and inputs the staged scheme into a simulation system for verification; and the edge node executes the scheme and collects response data, and twin compares a simulation value with an actual deviation to update a collection strategy. The method eliminates data distortion through physical rule verification, corrects aging unit state deviation through a dynamic compensation mechanism, optimizes decision binding real-time health degree, and effectively defends charging and discharging analysis errors of a virtual power plant dispatching desk.

A system and method for real-time or near real-time multilingual language transformation in telecommunications environments using distributed artificial intelligence (Al). The system includes at least one processor configured to instantiate a plurality of Al agents, each corresponding to a user in a communication session, and to manage their operation via an Al-agent runtime adapter comprising a microkernel agent manager and a virtual machine layer. A language model abstraction layer enables access to language models and Al algorithm libraries through publish-subscribe interfaces. The system supports contextual transformation of speech based on user profile data such as sentiment, emotional tone, and cultural background. Execution can occur on telecommunication-class switches, edge devices, or general-purpose computing hardware. Al agents operate asynchronously, access shared or private memory, and produce personalized, bidirectional linguistic output. The architecture supports secure, scalable deployment across heterogeneous devices and networks.

The invention belongs to the technical field of computer vision and digital video processing, and discloses a video object segmentation method based on query adaptive attention and discriminative memory, which comprises the following steps: step 1, constructing a video data set and preprocessing data; step 2, constructing a video object segmentation model combining multi-scale semantic feature integration and query adaptive discriminant enhancement, and training the video object segmentation model; step 3, video object segmentation reasoning; performing target segmentation reasoning on the preprocessed video sequence, outputting a frame-by-frame target segmentation mask, and generating a time sequence tracking result; 4, exporting, deploying and applying the model; through lightweight network design and a discriminative memory optimization strategy, the model is deployed to edge equipment, and real-time segmentation and visualization are realized. According to the method, on one hand, comprehensive target representation is provided on multi-scale feature extraction, and on the basis of the characteristic that only high-confidence target features are stored, error propagation is avoided, and the long-term segmentation stability of the method is ensured.

A fault identification system and method. The system comprises an edge device and a server. The edge device can extract, from an original vibration signal, signal characteristics reflecting an abnormal vibration state of a device under test and report the signal characteristics to the server; and the server can identify a fault state of the device under test on the basis of the signal characteristics. The data volume of the signal characteristics reported in the process is small, thereby reducing the bandwidth requirement; and the signal characteristics can be used for accurate fault identification, thereby improving the accuracy of fault identification.

A first neural network (NN) model may generate labels for training a second NN model. The second NN model may represent instances of a NN model operating on multiple different devices (e.g., decentralized user and / or edge devices). The system may include using a “teacher” model to process data received by one or more of the devices to generate a labeled dataset. The system may use the labeled dataset and a “student” model to calculate gradient data for updating the student model. The student model may be the same or similar to NN model instances operating on the devices. The system may validate the updated student model to determine, for example, whether it exhibits improved performance when processing the newly received data and / or historical data. The system may distribute the validated update to the devices.

The invention relates to the technical field of network security, and particularly discloses an edge device network threat detection method and system based on an electric power large model, and the method comprises the steps: capturing a network message sequence in real time, extracting a time sequence randomness feature and a semantic deviation feature from a time dimension and a protocol dimension, and carrying out the fusion to form a comprehensive threat feature vector; performing multi-dimensional feature analysis and time sequence modeling by adopting a lightweight electric power large model to realize millisecond-level threat assessment; establishing a multi-level response mechanism, dynamically triggering a differential protection strategy according to the threat level, and ensuring the reliability and consistency of response actions through digital signature and collaborative verification; according to the method, the complex network attack in the power edge equipment can be effectively identified, the threat detection accuracy and the system defense capability are improved, and the strict requirements of a power system on real-time performance and reliability are met.

The invention discloses a multi-edge device collaborative reasoning method and system for a hybrid expert large model, and the method comprises the steps: collecting and analyzing system data, and adjusting the expert layout according to the system data; in the first stage, the number of experts required by each layer of a server is dynamically determined by balancing activation diversity and memory resource limitation; in the second stage, according to the expert number and the activation mode of each layer obtained in the first stage, low-time-delay reasoning is achieved by minimizing the calling times of remote experts, and the experts are distributed to all the servers. The system includes a global scheduler and an edge server participating in the system. By using the method, edge multi-machine joint reasoning is achieved, the deployment method is optimized, online adjustment deployment can be performed according to data changes, and the reasoning speed is increased compared with other deployment technologies. The method can be widely applied to the technical field of distributed machine learning.

The invention discloses a power distribution switchgear remote monitoring and maintenance method based on the Internet of Things, relates to the technical field of power system operation and maintenance, and solves the problems that in an existing power distribution system, the edge anomaly recognition capability is weak, a control feedback chain is not closed, and multi-terminal control conflicts occur frequently. According to the scheme, a structured time sequence index of multi-source data is constructed on edge equipment, and equipment state drift is judged based on residual function included angle change; a control command management mechanism of a unique transaction identifier is introduced, a dual-channel feedback structure and a control mutual exclusion stack are combined, and a remote command consistency control chain is established; a hidden danger propagation chain is constructed on the cloud based on the abnormal Boolean bitmap and the topological relation, and a multi-node state linkage analysis and risk priority intervention strategy is achieved; according to the invention, the abnormity identification accuracy, the remote control stability and the system-level operation and maintenance response efficiency of the power distribution switch equipment are obviously improved.

The embodiment of the invention discloses a riverway pollution detection method based on unmanned aerial vehicle inspection, and the method comprises the steps: firstly obtaining a label data set of a target riverway region, training an initial riverway pollution detection network based on the label data set after building the initial riverway pollution detection network, and obtaining a trained riverway pollution detection network; and inputting the obtained current multi-modal image of the river channel region into a river channel pollution detection network for pollution detection to obtain a river channel pollution detection result. The river pollution detection network optimizes a multi-modal feature fusion mechanism, and can avoid information interference caused by insufficient utilization of feature scale sensitivity, thereby effectively improving pollution detection precision. Meanwhile, the network is adaptive to edge equipment such as an unmanned aerial vehicle, the current multi-mode image of the river channel can be quickly processed, real-time pollution detection and early warning are realized, and the timeliness and practicability of river channel pollution monitoring are enhanced.

The invention provides a lightweight multi-model collaborative edge intelligent target detection system and a lightweight multi-model collaborative edge intelligent target detection method, belongs to the technical field of edge target detection, and aims to solve the problem that a traditional target monitoring scheme depends on a cloud server to carry out deep learning model reasoning; in order to solve the problem that high-precision and low-delay real-time target monitoring cannot be realized on a resource-limited edge device, the detection system comprises an edge calculation module, an image acquisition module and a storage module. The detection method comprises the following steps: acquiring a to-be-detected image, and calling an IPS module through a performance core and an energy efficiency core to pre-process the acquired image; optimizing the YOLO model, and inputting the preprocessed image into a deep learning model; performing target detection on the preprocessed image data through a deep learning model; and a detection result is input into the storage module for storage and is uploaded to equipment connected with the peripheral interface for visual display and a remote monitoring center.

The present invention provides a road crack detection method, a medium, and a product. The method comprises: acquiring a road crack image and inputting same into a pre-trained lightweight YOLO-MCS road crack detection model to obtain a road crack detection result, wherein the lightweight YOLO-MCS road crack detection model is constructed on the basis of an improved yolov8 network. A yolov8 network improvement method comprises: replacing a feature extraction network backbone with a lightweight convolutional neural network MobileNet V3, and embedding a coordinate attention (CA) mechanism module in the lightweight convolutional neural network MobileNet V3; adding a small target detection layer and a squeeze-and-excitation (SE) module at a neck end; and introducing a power IoU loss function to a head prediction structure. The low detection accuracy of existing detection algorithms for fine cracks and the difficulty in applying existing detection algorithms to edge devices having limited computing resources are overcome.

The invention discloses a multi-modal neural network fusion system fusing an attention mechanism, and particularly relates to the technical field of environmental monitoring artificial intelligence. The defects of high meteorological / water quality monitoring false alarm rate and large response delay caused by static weighted fusion, insufficient domain feature extraction and edge deployment bottleneck of an existing multi-modal fusion system are overcome. According to the method, meteorological satellite / water quality sensor data are fused in a cross-modal manner by adopting a dynamic attention mechanism, domain features are extracted in combination with space-time convolution and graph convolution, and the domain features are deployed to edge equipment through hybrid quantization compression. The severe convection weather identification and pollutant traceability precision is improved, and the real-time early warning capability of a field terminal is guaranteed.

A hybrid neural network architecture is disclosed that integrates matrix multiplication-free (MatMul-free) transformation layers with spiking neural network (SNN) layers for efficient, low-power computation. The system includes an interface module configured to convert intermediate continuous-valued data from MatMul-free layers into a spike-compatible format using encoding techniques such as rate coding, phase coding, or threshold-based conversion. The SNN layers process the spike-encoded data in an event-driven manner, enabling sparse, temporal inference. Training is supported by a hybrid optimization strategy combining backpropagation in MatMul-free components with surrogate gradient descent or spike-timing-dependent plasticity (STDP) in SNN layers. The architecture reduces computational complexity, supports real-time adaptability, and enables deployment in energy-constrained environments such as edge devices and neuromorphic platforms. The system may be implemented in hardware, software, or a co-designed pipeline optimized for dynamic sensor data, control signals, or continuous inference tasks.

The invention discloses a traffic monitoring video rapid target extraction method for edge equipment, and relates to the technical field of intelligent traffic video processing and edge calculation target detection, and the method comprises the steps: carrying out the adaptive downsampling processing of original video frame data, and generating downsampling video frame data; extracting a foreground target candidate region, and constructing a traffic region-of-interest mask in combination with a lane line detection result; carrying out pixel AND operation on the traffic region-of-interest mask and the foreground target candidate region to generate accurate candidate target region data, and extracting a target feature vector; carrying out weighted fusion on the target feature vector through a lightweight attention mechanism, generating a fusion feature descriptor, and calculating a target confidence score; and carrying out screening and duplicate removal processing on the accurate candidate target area data, and outputting traffic target extraction result data. According to the invention, the target in the traffic video can be rapidly and accurately extracted and processed in a low-delay manner on the edge equipment with limited computing resources.

The invention discloses a millimeter-wave radar sparse point cloud-based human body posture recognition method, which belongs to the technical field of human body posture recognition, and comprises the following steps of: acquiring three-dimensional point cloud data of human body actions through a millimeter-wave radar, and preprocessing the three-dimensional point cloud data; and training a lightweight neural network model by using the preprocessed point cloud data, wherein the model comprises an edge convolution module and a grouping sparse Transform encoder module. The edge convolution module extracts spatial geometric features and detects dynamics, static postures are directly classified, dynamic postures capture a time sequence dependency relationship through a grouping sparse Transform module, attention calculation is only carried out on frames with feature changes exceeding a threshold value, and mean pooling aggregation is carried out on other frames. And finally, classifying the human body postures based on the spatial geometric features and the time sequence dependency relationship to obtain a classification result. The device is simple in structure, accurate in recognition and suitable for efficient deployment of edge equipment.

The invention relates to the technical field of meteorological prediction, and discloses a meteorological element short-term prediction method and system based on spatio-temporal feature adaptive extraction, and the method comprises the steps: obtaining multi-source meteorological data, and carrying out the preprocessing of the multi-source meteorological data, and generating a spatio-temporal grid tensor; in the short-term prediction model of the meteorological elements of the space-time grid tensor, the model dynamically updates parameters of the model according to currently input data and outputs a meteorological element prediction value, and the method comprises the following steps: extracting multi-scale spatial features of meteorological data through a multilayer convolutional neural network based on the space-time grid tensor; generating enhanced spatio-temporal features based on an attention enhancement mechanism; and performing regression prediction on the enhanced spatial-temporal characteristics through a full connection layer, and outputting a meteorological element prediction value of a future time step. According to the method, the stable prediction precision is kept in different meteorological scenes, the calculation efficiency is improved by virtue of the convolution parallelism and the lightweight attention design, the hour-level real-time prediction requirement can be met, and timely and reliable meteorological prediction support can be conveniently provided for deployment in edge equipment or a service system.

The invention discloses an electric power communication network resource allocation lightweight method based on strategy distillation, and the method comprises the steps: carrying out the multi-modal state perception, fusing spatial topology, time sequence business and resource state three-dimensional data, and forming a multi-modal environment state vector; inputting a multi-modal state vector, and training a teacher model by using a flexible actor-commentator algorithm (SAC); injecting power business constraints by utilizing a decision track generated by the teacher model, and training a lightweight student model; compiling and optimizing the trained lightweight student model into an inference engine and deploying the inference engine to an edge device; and real-time decision and security verification are realized on the edge equipment. In order to realize the method, the invention also provides a power communication network resource allocation lightweight system based on strategy distillation. According to the technical scheme, the lightweight power grid communication network resource allocation model capable of being deployed at the edge equipment is constructed, and the requirements of high performance, safety and service constraint are met at the same time.