1641 results about "Edge device" patented technology

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 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.

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.

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.

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 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.

The invention relates to an Internet of Vehicles multi-agent cooperative sensing method and system. The method comprises the following steps: constructing a collaborative sensing network, wherein the collaborative sensing network comprises a self-agent and a plurality of collaborative agents; acquiring and processing sensing data through the collaborative sensing network; performing feature extraction to obtain intermediate features; self-adaptive sparsification is carried out to obtain sparse features, and the sparse features are compressed and transmitted to a self-agent; performing time sequence feature enhancement on the features of all the agents at the self-agent end; fusing the features to obtain fused features; and constructing an Internet of Vehicles perception model, and realizing perception by the detection model according to the fused features. According to the method, the calculation complexity of traditional global attention is reduced from the square level to the linear level through an adaptive sparsification mechanism, the calculation overhead is remarkably reduced while the multi-agent feature interaction precision is kept, and the method is more suitable for real-time operation on the vehicle-mounted edge equipment with limited resources.

The invention relates to the field of artificial intelligence and computer science, in particular to a causal structure and latent variable-based adaptive reinforcement learning reasoning migration method, which comprises the following steps of: constructing a causal world model fused with multi-modal observation and a decoupling latent variable space; establishing a hierarchical inference engine comprising an intuition layer, a conventional layer and a planning layer; pre-training a quick response and judicial planning dual-mode strategy and generating an interpretable fuzzy rule base; performing calculation level coarse tuning based on task identification and causal complexity; evaluating the real-time state criticality through an adaptive neural fuzzy system and dynamically switching a decision mode; after the action is executed, the threshold and the rule are subjected to closed-loop optimization, and cross-environment efficient migration is realized by utilizing a causal modularization characteristic. According to the technical scheme, consumption of computing resources is remarkably reduced on the premise that decision precision and safety are guaranteed, and the response speed and cross-scene adaptive capacity of a system on edge equipment are improved.

The invention belongs to the technical field of network security, and provides a network threat real-time detection and defense method and system based on artificial intelligence. The method comprises the steps of multi-modal data acquisition and preprocessing, dynamic graph feature engineering and knowledge graph collaborative fusion, dual-adaptive model training and optimization, streaming real-time detection and anomaly scoring, DRL-driven hierarchical defense response and automatic disposal, and feedback-driven model adaptive updating and block chain auditing. According to the method, a mixed model of OS-ELM + dual-adaptive ridge regression + federated learning is designed, the training speed is higher than that of CNN, and over-fitting / under-fitting is avoided by dynamically adjusting a regularization coefficient; the federal learning realizes data local training and parameter uploading, and solves the problem of privacy disclosure; knowledge distillation enables the model volume to be reduced, edge equipment deployment is adapted while the accuracy is maintained, and the generalization ability is obviously superior to that of a traditional static model.

The invention provides a real-time command and control strategy optimization method and device based on multi-agent reinforcement learning, equipment and a storage medium, and the method comprises the steps: deploying a pre-trained cooperative intention network on edge equipment of each combat unit, and coding local observation data and a historical sequence thereof into a low-dimensional local cooperative intention vector; replacing original high-dimensional data as inter-unit communication content; whether broadcasting is carried out or not is dynamically determined according to observation uncertainty and a channel state by combining a self-adaptive intention broadcasting mechanism, and communication resources are distributed according to needs; after each unit receives an adjacent collaborative intention vector, a lightweight space-time attention module in a pre-trained local strategy execution network carries out space weighting on adjacent intentions and fuses time features of own historical intentions, and a collaborative and consistent real-time command and control instruction is generated under the condition that global information convergence is not needed.

A modular system designed for privacy-preserving content recognition and supplemental content delivery across web and mobile environments. The system employs lightweight character sampling and vision-based recognition to generate unique content fingerprints without storing or replicating original data. It features a hybrid processing architecture, using local computing resources for intensive tasks while optimizing performance on resource-constrained devices. Core functionalities include multi-method content fingerprinting, real-time monitoring with adaptive sampling, and secure supplemental content association. Operating entirely on the client-side, it complies with website terms of service and privacy regulations. Advanced features include AI-driven content recognition, blockchain-based verification, and granular content targeting through resizable selection interfaces. This technology enables seamless delivery of supplemental content while preserving privacy, reducing resource usage, and ensuring scalability across browsers, mobile applications, and edge devices. It is particularly applicable in industries such as education, retail, and secure data sharing.

A federated system and method for data compression optimization in distributed device networks. The system comprises multiple edge devices that analyze local data patterns to generate device characteristic profiles while performing local compression optimization and maintaining data privacy. Edge devices contribute to collaborative learning by generating privacy-preserved updates without transmitting raw data. A central coordination system aggregates encrypted contributions using secure multi-party computation protocols, identifies device groups based on data pattern similarities, and generates optimized compression parameters for each group. The system coordinates collaborative training of data reconstruction models across device groups and deploys group-optimized reconstruction capabilities. Device grouping is performed by calculating similarity scores between device characteristic profiles and clustering devices with scores above predetermined thresholds. The system dynamically adapts compression and reconstruction parameters through federated learning while preserving individual device data privacy, enabling efficient data compression and near-lossless recovery across heterogeneous Internet-of-Things networks.

The invention discloses a rolling bearing lightweight fault diagnosis method and system based on multi-source signal fusion. Vibration, temperature and rotating speed signals are synchronously collected, and timestamps are calibrated; respectively carrying out denoising and normalization preprocessing; dividing and aligning windows; differential feature extraction: extracting time-frequency features of the vibration signals by using a one-dimensional residual CNN, and extracting abnormal measurement of the temperature / rotating speed signals by using an LSTM in combination with an isolated forest algorithm; carrying out self-adaptive weighted fusion on the features through an attention mechanism; the lightweight diagnosis model (through knowledge distillation, pruning and quantification) deduces and outputs the fault category, the health index and the confidence coefficient. The system correspondingly comprises an acquisition module, a preprocessing module, a feature extraction module, a fusion module and a diagnosis module. The method improves the early fault sensitivity, enhances the variable working condition robustness, supports the real-time deployment of edge equipment, and is suitable for the intelligent monitoring of industrial bearings.

The invention discloses a medical image segmentation method based on a lightweight visual basis model, and the method comprises the steps: achieving the cross-modal and cross-anatomical region universal feature extraction through introducing a multi-scale token aggregation and a lightweight decoder; interlayer tokens are fused in a layered mode, global semantics and local textures are considered, and small target and boundary precision is remarkably improved. According to the multi-stage field adaptive pre-training, firstly, a fine-grained structure is captured by self-distillation, reconstruction and regularization composite loss, then, teacher-student distribution is aligned by Gram matrix anchoring loss, and finally, field migration and representation enhancement under the non-labeling condition are realized through high-resolution data refining. The lightweight compression selectively removes part of self-attention and retains MLP, and reduces parameter quantity and calculation quantity on the premise of almost no precision loss, so that the model can perform real-time reasoning on edge equipment. The end-to-end process reduces the annotation dependence, shortens the fine adjustment period, can support multi-organ and multi-focus segmentation through a unified frame, and improves the clinical deployment efficiency and generalization ability.

The invention discloses an apple leaf disease segmentation method based on a lightweight dual-path network, an apple leaf disease segmentation device based on the lightweight dual-path network, an apple leaf disease segmentation device and a computer readable storage medium. The problems that an existing disease segmentation method is high in model complexity and insufficient in multi-scale recognition capability are effectively solved. The lightweight encoder adopts a depth separable convolution and channel recombination technology, so that the parameter quantity and the calculation complexity are greatly reduced while the feature extraction capability is maintained, and the model can be deployed on edge equipment such as an unmanned aerial vehicle and a field robot. The enhanced cavity space pyramid pooling module constructs abundant multi-scale receptive fields through multi-branch parallel cavity convolution with different expansion rates, and can capture feature information of initial tiny disease spots and later fused disease spots at the same time.

The invention relates to the technical field of intelligent traffic, and discloses a camera state judgment method based on road surface covering and Hash comparison, and the method sequentially comprises the steps: extracting key frame pairs from a video stream at intervals; performing road surface region extraction on each frame of image to obtain a road surface mask; carrying out covering processing on the road surface area in each frame of image based on the mask to obtain a covered image; calculating a difference hash feature of each frame of covered image to obtain a hash code; calculating the Hamming distance between the Hash codes of the key frame pair; and judging whether the camera is in a rotating or stable state according to a comparison result of the Hamming distance and a threshold value. The method only depends on the video image data, does not need an external sensor, effectively eliminates the dynamic interference of the vehicle through covering the road surface, achieves the efficient and robust judgment of the state of the camera through combining the lightweight difference hash calculation, is low in calculation cost, and is suitable for edge equipment and complex road environments.

The invention relates to the technical field of edge computing and artificial intelligence model updating, and provides a cloud edge collaborative edge end equipment operator hot updating method, system and device and a medium. The method comprises the steps that a cloud detects a new version of an operator and generates an incremental update package between the new version and the old version; the edge node pulls the incremental update package and performs multiple security verification on the incremental update package; a double-instance inference engine is deployed in the edge node, operators passing verification are preloaded to a standby engine, and hot switching from an operation engine to the standby engine is achieved through a state synchronization mechanism; monitoring the running state of the new engine after switching, if the running state is abnormal, triggering a rollback mechanism, and switching back to the original engine; and optimizing edge node resources, cleaning old version operators, and reporting an update state and a resource use condition to the cloud. Core mechanisms such as differential updating, double-instance engine hot switching, multiple safety verification and dynamic resource scheduling are fused, and therefore efficient, safe and non-perceptual operator updating is achieved.

The invention belongs to the technical field of computer vision, and discloses an industrial product imperfect real-time detection system and method based on a lightweight network. A lightweight detection network fused with a cross-space attention perception module is constructed, and a dynamic sampling biased field generation technology is combined, so that precise capture of tiny defects is realized; a dynamic gradient modulation mechanism of an anchor frame outlier degree is introduced, and a network learning strategy is optimized; the detection frame confidence coefficient soft attenuation processing is adopted to replace the traditional non-maximum suppression, so that the dense defect identification problem is effectively solved; and the long-term operation reliability of the system is improved through a time sequence stability enhancement strategy. According to the method, lightweight calculation is realized while high detection precision is maintained, so that a high-performance detection system can be deployed on edge equipment, and the deployment cost is remarkably reduced.

The invention relates to the technical field of data security of the Internet of Things, in particular to an edge data security protection system and method based on a security chip, and the system comprises edge equipment which is deployed at the edge of a network and is used for detecting or collecting original data; the security chip is embedded in or externally connected to the edge equipment, and an encryption engine and a security storage area are integrated in the security chip; the encryption engine is integrated with an encryption algorithm, and a secret key is stored in the secure storage area; the security agent software runs on a control system of the edge equipment and is in communication connection with the security chip, and the security agent software is configured with a security policy; wherein the security agent software is configured to receive original data, call an encryption engine of the security chip according to a security policy to encrypt the original data, generate protected data, and send the protected data to a cloud or a data center; or the original data is monitored, and safety measures are taken for the original data with risks.

Devices, systems, and methods described herein are directed to configuring and provisioning edge components for building devices of a building. A building management system can receive a request for an edge component for a building device via a graphical user interface. The building management system can determine one or more interfaces and one or more target output protocols of the building device. The building management system can provide, in response to the request, an edge component based on the one or more interfaces and the one or more target output protocols.

The invention discloses a road crack deep learning segmentation method for a complex scene, and belongs to the technical field of image processing. Firstly, multi-illumination and multi-material road surface images are acquired at high altitude through carrying multi-spectral equipment by an unmanned aerial vehicle, and generalization is improved by adopting adaptive threshold graying, CLAHE illumination equalization and GAN data enhancement. Secondly, deformable convolution, a self-adaptive space attention mechanism and an object context representation module are introduced into the HRNet backbone network, and the problems of irregular fracture shapes and background interference are solved; and finally, class imbalance is relieved by adopting a focus loss function, and robustness is improved by combining stochastic gradient descent and a verification set dynamic weight storage strategy. In the test stage, edge equipment deployment is carried out, a pixel-level segmentation result is output, crack parameters are quantified, and decision support is provided for road maintenance. The method can significantly improve the crack segmentation precision in a complex scene, and especially has an engineering practical advantage in a fine crack and noise interference scene.

The invention provides a cloud edge collaboration algorithm arrangement and deployment method, system and device and a storage medium, and relates to the technical field of cloud edge collaboration.The method comprises the steps that algorithm task requirements input by a user are analyzed, and after corresponding task information is obtained, an intermediate representation file is generated; collecting computing power state information of the plurality of edge devices to determine a target edge device used for executing an algorithm link, and generating an operation parameter configuration file according to a hardware architecture of the target edge device and algorithm characteristics of the intermediate representation file; and issuing the intermediate representation file and the operation parameter configuration file to the target edge device, and performing automatic compiling and deployment according to the chip type of the target edge device. By issuing the intermediate representation file and the operation parameter configuration file to the target edge device and automatically executing compiling and deployment, the effects of cross-platform automatic adaptation, rapid deployment and efficient operation are achieved, and the problem that in the prior art, task organization and deployment flexibility is insufficient is solved.

The invention discloses a power distribution network edge voltage prediction method and system for lightweight deployment of edge devices, and the method specifically comprises the steps: firstly completing the localized deployment initialization of a prediction service on the power distribution network edge devices, obtaining a resource budget parameter and an allowable error upper bound, and calculating an edge side constraint parameter set; then, voltage measurement data of a target node and net power measurement data of a corresponding node are collected, data processing is carried out, and a compressed input vector is generated; then predicting a target node voltage by using a compressed input vector, and updating a threshold value and an event triggering threshold value; and finally, judging whether to trigger redeployment or reconfiguration according to a data monitoring result, updating a resource budget parameter and an allowable error upper bound, and recalculating a constraint parameter set to form closed-loop operation. According to the method, on the premise that prediction precision constraints are met, edge side calculation overhead and communication dependence are reduced, the real-time performance and stability of voltage prediction are improved, and the method is suitable for power distribution network voltage online prediction and early warning in weak communication or offline scenes.

The invention provides a large language model quantification method, related equipment and a computer program product, and the method comprises the steps: carrying out the reasoning of a to-be-quantized large language model through calibration data, obtaining the activation of the large language model, and carrying out the statistics of the activation distribution of a target layer according to channels; calculating a smoothing factor of each channel according to the activation distribution; compensating the weight of the target layer channel by channel according to the smoothing factor to obtain a compensated weight; performing 4-bit quantization on the compensated weight; in the model reasoning process, activation of a target layer is smoothed, and 16-bit quantization is carried out on the smoothed activation. According to the method, a W4A16 quantification scheme is adopted, compared with W8A8, the weight storage amount is compressed by half, meanwhile, the precision loss is controlled to be smaller than 3%, and deployment of a large language model on edge equipment is facilitated.

The invention relates to the field of edge computing, in particular to a primary and secondary fusion complete ring main unit energy efficiency optimization system based on cloud edge collaboration. The system comprises an edge device deployment and data acquisition module used for collecting operation electric parameters and device states and generating a service calling request; the service calling module is used for screening target control parameters under security constraints based on the energy efficiency optimization service package; the data synchronization module unloads the data to a cloud platform through a message queue protocol; the cloud service arrangement module aggregates the data updating service package and issues the data updating service package to the edge; and the real-time control module converts the parameters into instructions to drive equipment to act. A cloud training and edge reasoning collaborative architecture is adopted, the problems that local control lacks adaptivity, edge resources are limited and full-cloud control communication time delay exists are solved, and real-time energy efficiency optimization is achieved.

The invention discloses a mobile robot autonomous search navigation method based on a visual language large model. The method comprises the steps of receiving a natural language instruction of a user, and synchronously collecting an RGB image and a laser point cloud; two-stage visual language reasoning is adopted, and target semantic analysis and existence judgment are completed in sequence; when the target does not exist, autonomous exploration is executed based on the point cloud data and is parallel to target judgment, and an exploration-judgment closed loop is formed; after determining that the target exists, switching to a visual language navigation model, generating an incremental motion instruction, and guiding the robot to approach the target; target state monitoring is continuously carried out during navigation, if the target is lost, a dynamic backtracking mechanism is triggered, the robot is driven to return to the historical state of the recently confirmed target, and navigation is restarted. The method does not need to depend on a prior map, can execute efficient and robust autonomous search and navigation tasks on edge equipment through task collaboration, model quantification and state backtracking, and is suitable for complex scenes such as industrial inspection and emergency rescue.

The invention belongs to the technical field of machine state prediction, and particularly relates to a fault diagnosis method and system based on a coding and decoding attention mechanism enhanced pulse neural network, and the method comprises the steps: collecting a device vibration signal, and segmenting the device vibration signal into time sequence segments; converting each fragment into a two-dimensional time-frequency image by using S transformation to construct a data set; the image is input into a lightweight hybrid network model to extract deep features, the model is composed of a pulse convolution encoder and a pulse efficient additive attention mechanism encoder which are alternately cascaded, and the pulse convolution encoder extracts local features through pulse neurons and depth separable convolution; the global context dependency is modeled by adopting an efficient additive attention mechanism with low linear complexity; and finally, fault classification is completed based on deep features. Through fusion of pulse calculation and an efficient attention mechanism, the feature extraction capability and diagnosis precision are improved while the parameter quantity of the model is remarkably reduced, and the method is particularly suitable for being deployed on edge equipment with limited resources to realize fault diagnosis.