224276results about "Neural learning methods" patented technology

A system and method for implementing a convergent intelligence fabric (CIF) for distributed artificial intelligence operations. The CIF architecture integrates tensor-theoretic foundations, probabilistic cache management, precision-aware memory operations, quantum-resistant security, and neural-based optimization within a unified framework. The system orchestrates asynchronous, multi-hop data flow among computational resources while maintaining data security through per-block encryption and identity-based access control. Key components include a universal multi-model KV cache subsystem, agent-parallel disaggregation pipelines, reinforcement learning-based orchestration, and neuromorphic memory integration. Advanced implementations incorporate graphon-enhanced memory for sparse graph sequences, multi-modal cognitive persistent memory, and quantum-resistant asynchronous multi-domain trust protocols. The system enables efficient cross-agent collaboration, sophisticated knowledge sharing, and secure cross-domain operations while optimizing computational resources and maintaining strict privacy guarantees across distributed AI deployments.

An unsupervised learning-based power battery anomaly detection system, comprising: a battery parameter association reasoning module, configured to design a dynamic learnable graph neural network algorithm, and explore a potential association of battery parameters; a time sequence feature dependency analysis module, configured to model long-term and short-term time sequence dependency relationships on the basis of a temporal learning network; a coupling temporal-spatial neural architecture module, configured to perform coupling representation on the temporal learning network and a spatial learning network to integrate spatial-temporal association features; and a battery anomaly inference and evaluation module, configured to realize battery state prediction and evaluation by designing an adaptive threshold selection strategy and an experimental stage evaluation mechanism. The present application determines whether a power battery is in a normal operating state by analyzing a change mode of the key parameters of the power battery in a production process, and promptly stops the production process of a battery in an abnormal state, thereby preventing occurrence of accidents, and reducing resource loss in the production process.

The invention relates to the technical field of power equipment, and discloses a digital twin operation monitoring system for power equipment, which comprises a data sensing and acquisition system for acquiring key operation parameters of temperature, current, voltage, partial discharge, vibration and humidity of the power equipment in real time, and performing multi-dimensional data acquisition through a sensor and a data transmission module; the state evaluation and prediction system is used for performing equipment health evaluation and residual life prediction by using a prediction model LSTM based on the collected data, and updating a prediction result in real time; provided is a digital twin modeling system. Through the combination of edge calculation, an LSTM model and a digital twinning technology, the precision and real-time performance of health management of power equipment are improved, data quality is optimized through edge calculation, the LSTM model captures an equipment degradation trend, virtual-real fusion is realized through digital twinning, and accurate monitoring and early warning of the health state of the equipment are ensured, so that intelligent operation and maintenance decisions are optimized, the failure rate is reduced, and the safety of power equipment health management is improved. The equipment life is prolonged.

The present invention discloses an aero engine bearing fault diagnosis method based on STFT-IncepNext, which includes the following steps: step 1: collect acceleration signals under various working conditions and fault conditions of the bearing as sample data; step 2: determine the number of sampling points of each sensor first, and perform data merging by permuting and combining data collected by sensors at different positions in the same time series, and then use short-time Fourier transform to convert the fused vibration signal into a time-frequency diagram; step 3: data preprocessing: divide into training set, test set and validation set according to fault type, and normalize the converted time-frequency diagram using average value and standard difference; step 4: build an IncepNext model, train and validate it; and step 5: use the trained IncepNext model to diagnose aero engine bearing faults and obtain a diagnosis result. The present invention can effectively identify aero engine bearing faults, can guarantee the fault identification rate, and has good accuracy.

Provided are a digital twinning method and system for a scene flow based on a dynamic trajectory flow, which belong to the field of traffic control. The method includes: extracting and identifying a target semantic trajectory with a detecting and tracking integrated multi-modal fusion and perception enhancement network; extracting road traffic semantics, so as to obtain a highly parameterized virtual road layout top view; obtaining a road layout traffic semantic grid encoding vector based on the virtual road layout top view; constructing a target coupling relation model; constructing a traffic force constraint model; constructing a long short term memory trajectory prediction network; predicting a motion trajectory of a target with the long short term memory trajectory prediction network, so as to obtain the predicted motion trajectory; and obtaining a digital twin of the scene flow based on trajectory extraction, semantic identification and the predicted motion trajectory.

Systems, methods, and apparatuses for providing optimization of network resources. The system is operable to monitor the electromagnetic environment, analyze the electromagnetic environment, and extract environmental awareness of the electromagnetic environment. The system extracts the environmental awareness of the electromagnetic environment by including customer goals. The system is operable to use the environmental awareness with the customer goals and / or user defined policies and rules to extract actionable information to help the customer optimize the network resources.

The invention discloses a traffic engineering large model intelligent question answering system and method based on a knowledge graph, and the method comprises the steps: extracting a structured degree feature, a semantic ambiguity feature and a context association feature through receiving and analyzing a natural language query statement inputted by a user, generating a retrieval intention vector, and carrying out the retrieval of the retrieval intention vector; and dynamically selecting a retrieval path according to the intention classification model. And according to the retrieval path, constructing a structured query statement or a semantic vector, and respectively retrieving in the knowledge graph and the vector database to obtain a first retrieval result and a second retrieval result. Further performing bidirectional verification through entity consistency, semantic similarity and relation connectivity indexes, screening a candidate result set, and constructing a reasoning chain; if the inference chain is broken, a large model inference gap complementation mechanism is adopted to generate relay nodes, a complete inference chain is formed, and inference type answer output is generated based on the complete chain. According to the method, the retrieval accuracy and reasoning continuity of the question-answering system are improved.

Provided is a road crack detection method, a medium and a product. The lightweight YOLO-MCS road crack detection model is constructed based on an improved yolov8 network. A method of improving the yolov8 network includes: replacing a feature extraction network backbone with a lightweight convolutional neural network MobileNetV3, and embedding a Coordinate Attention Mechanism (CA) module in the lightweight convolutional neural network MobileNetV3; adding a small target detection layer and a Squeeze and Excitation (SE) module at a neck end; and introducing a loss function of power Intersection over Union (IoU) into a head prediction structure. The road crack detection method overcomes the problem that the existing detection algorithm has low detection precision for small cracks and is difficult to be applied to edge devices with limited computing resources.

The invention discloses a power grid dispatching decision-making method based on a graph neural network and a large model, and the method comprises the steps: collecting an original power grid data set, and generating a fusion feature tensor through adaptive distribution mapping and recursive decomposition; importing a fusion feature tensor and a power grid topology matrix, and generating a dynamic graph embedding matrix through spectral decomposition and matrix manifold analysis; performing Markov jump process analysis and optimal transmission fusion on the dynamic graph embedded matrix to generate an integrated feature matrix; a multi-target Lyapunov function is constructed on the basis of the integrated feature matrix, and a robust decision strategy is generated by solving a Hamilton-Jacobi-Bellman equation; and performing multi-dimensional performance monitoring and statistical manifold learning on the robust decision strategy to realize strategy optimization. According to the method, the uncertainty in power grid operation can be effectively processed, and the accuracy and reliability of scheduling decisions are improved.

Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and / or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.

A multi-layer artificial intelligence system includes a foundation layer comprising at least one general-purpose large language model (LLM); an expert array layer comprising a plurality of specialized reasoning models; and a meta-reasoning model configured to coordinate operations between the foundation layer and the expert array layer to generate a reasoned analysis.

Systems, methods, and apparatuses for providing optimization of network resources. The system is operable to monitor the electromagnetic environment, analyze the electromagnetic environment, and extract environmental awareness of the electromagnetic environment. The system extracts the environmental awareness of the electromagnetic environment by including customer goals. The system is operable to use the environmental awareness with the customer goals and / or user defined policies and rules to extract actionable information to help the customer optimize the network resources.

The invention provides a medical text big data intelligent labeling and knowledge graph construction method and system, and relates to the technical field of medical text processing, and the method comprises the steps: recognizing entities in a medical text through a pre-trained deep bidirectional coding model and a multi-level entity recognition network, and carrying out the normalization processing in combination with a medical knowledge base, according to the method, the semantic association degree between entities is calculated, a relation extraction result is optimized based on comparative learning, comprehensive relation representation is obtained through fusion of multi-granularity coding and a gating mechanism, the entity relation is determined in combination with an inference rule network, a medical knowledge graph is constructed based on an initial knowledge graph, and the accuracy of medical text entities and relation labeling can be effectively improved. And a more perfect medical knowledge graph is constructed, which is helpful for assisting medical diagnosis and decision making.

A method and system are introduced for recognizing cognitive engagement in classrooms by utilizing multimodal data. Associated modalities of cognitive engagement are learned from visual and audio data. This approach involves constructing a multidimensional representation model for cognitive engagement that includes behaviors, emotions, and speech. To identify engagement, three distinct deep learning models are employed: You Only Look Once version 8 (Yolov8) for analyzing body posture, Efficient Network (EfficientNet) for facial expressions, and Text Convolution Neural Network (TextCNN) for speech text. These models are trained and refined with the aid of student engagement surveys, leading to a decision-making process that integrates the results from the different modalities. Additionally, a dataset and a data annotation system are developed for engagement recognition. This innovative method aims to achieve detailed engagement recognition, addressing various perception needs in real-world applications.

Disclosed in the present invention is a salient contour matching-based method for target measurement in a severe imaging environment. The method specifically comprises: (1) acquiring a binocular image of a target; (2) establishing a global-local joint constraint-based background light estimation model, and removing a scattering effect of a medium in an imaging environment to obtain a restored left eye image and a restored right eye image; (3) learning an original image, and on the basis of a residual between a network reconstructed image and the original image, obtaining target localization prediction maps of the left eye image and the right eye image; and (4) respectively extracting contour lines of the target in the left eye image and the right eye image, constructing feature matching descriptors of contour points, performing stereo matching on the two sets of contour lines by minimizing matching cost, and performing three-dimensional reconstruction on the contour lines in light of calibrated intrinsic and extrinsic parameters to complete the measurement of a key size. According to the present invention, the key sizes of different targets in a severe environment can be accurately measured, thereby providing an effective solution for the problem of measuring the sizes of targets in a severe environment.

The invention provides an adaptive task scheduling execution unit management method and system, and relates to the technical field of computer task scheduling, and the method comprises the steps: collecting execution unit data, extracting features through federated learning and a hybrid neural network, evaluating the capability and predicting the state based on deep reinforcement learning, and generating a distribution scheme in combination with an improved algorithm. And performing spectral clustering and hierarchical analysis optimization decomposition, constructing a multi-dimensional dependency model, and performing optimization scheduling through Monte Carlo search and a multi-arm bandit algorithm to realize adaptive task allocation.

Provided are a text-guided multi-modal relationship extraction method and apparatus. The method comprises: for a given image, obtaining a plurality of local target objects in a global image; obtaining a text feature encoded representation of a given text and visual feature encoded representations of the global image and the local target objects; using the text feature encoded representation as a priori input for a visual encoder, and on the basis of a top-down attention mechanism, further guiding the visual encoder to learn a visual feature encoded representation more relevant to text semantics by means of backward decoding feedback; fusing the text feature encoded representation and the visual feature encoded representation by means of a cross attention mechanism to obtain a cross-modal text feature encoded representation; and performing relationship classification on the basis of the cross-modal text feature encoded representation to obtain a semantic relationship type between two entities in the given text. The present disclosure can effectively reduce the interference of irrelevant visual information, and improve the accuracy of relationship extraction.

The invention relates to the technical field of model analysis, in particular to a time-space fusion neural network line topology analysis method for a power distribution network. The method comprises the following steps: obtaining original line topology data corresponding to a power distribution network, and carrying out structured disassembly and preprocessing to construct a space-time double graph structure; constructing a bidirectional dynamic feature interaction mechanism based on the space-time double graph structure, performing multi-scale topological feature extraction, and generating a space-time separated feature vector set; performing deep coupling fusion on the feature vector set subjected to time-space separation to generate corresponding unified topological feature representation containing abnormal topology; and constructing a dynamic topology state prediction model based on the unified topology feature representation to optimize a space-time joint loss function and output a corresponding real-time topology connection relationship and an equipment state change trend, and meanwhile, performing dynamic topology reconstruction to generate a current-moment reliable topological graph corresponding to potential branch disconnection and temporary tripping. The topology analysis accuracy of the power distribution network can be improved.

The technology disclosed assigns quality scores to bases called by a neural network-based base caller by (i) quantizing classification scores of predicted base calls produced by the neural network-based base caller in response to processing training data during training, (ii) selecting a set of quantized classification scores, (iii) for each quantized classification score in the set, determining a base calling error rate by comparing its predicted base calls to corresponding ground truth base calls, (iv) determining a fit between the quantized classification scores and their base calling error rates, and (v) correlating the quality scores to the quantized classification scores based on the fit.

Systems, methods, and apparatuses for providing optimization of network resources. The system is operable to monitor the electromagnetic environment, analyze the electromagnetic environment, and extract environmental awareness of the electromagnetic environment. The system extracts the environmental awareness of the electromagnetic environment by including customer goals. The system is operable to use the environmental awareness with the customer goals and / or user defined policies and rules to extract actionable information to help the customer optimize the network resources.

Systems and methods for automated unmanned aerial vehicle recognition. A multiplicity of receivers captures RF data and transmits the RF data to at least one node device. The at least one node device comprises a signal processing engine, a detection engine, a classification engine, and a direction finding engine. The at least one node device is configured with an artificial intelligence algorithm. The detection engine and classification engine are trained to detect and classify signals from unmanned vehicles and their controllers based on processed data from the signal processing engine. The direction finding engine is operable to provide lines of bearing for detected unmanned vehicles.

The present invention relates to the technical field of image fusion. Disclosed is a method for fusing infrared light and visible light images. According to the present invention, design is carried out on the basis of a spatial channel attention mechanism and a gradient aggregation residual dense block, a strong texture and weak texture of a feature are retained by integrating Sobel and Laplacian operators while combining the advantages of ResNeXt and DenseNet, and channel information and spatial information of a feature map are refined by means of introducing a spatial and channel attention mechanism, thus the information capture capability of the feature map is increased, and refined spatial and channel feature maps are fused by using a pooled fusion block, to obtain a high-quality fusion feature.

The invention relates to the technical field of equipment fault diagnosis, and discloses an equipment fault diagnosis and prediction method based on deep learning, and the method comprises the following steps: S1, collecting multi-modal data in real time through a plurality of sensors installed on equipment; s2, preprocessing the collected data; s3, constructing a hybrid deep learning model; s4, dynamic weighted fusion is performed on the features of different modal data by using an attention mechanism, and comprehensive feature representation is generated; s5, using the marked fault data and normal data to supervise and train the model; s6, inputting equipment operation data acquired in real time into the trained model, and judging the state of the equipment; and S7, generating a potential fault early warning signal based on a prediction result of the model. A piezoelectric vibration sensor and a thermal infrared imager are arranged on a motor bearing through vibration, temperature and sound sensors, vibration waveforms, thermal imaging slices and time-frequency diagrams are synchronously captured, and composite state characteristics such as mechanical wear and temperature anomaly of equipment are comprehensively reflected.

The invention discloses an electric energy metering box fault prediction method and system based on big data analysis, relates to the technical field of smart power grids, and solves the problems of progressive aging missing detection and instantaneous interference misjudgment caused by dependence on single parameter threshold alarm and fault positioning misalignment caused by multi-source data isolated analysis in the prior art. According to the scheme, electrical, environment and equipment state parameters are collected in real time through a multi-dimensional sensing network; the error drift of the mutual inductor is dynamically predicted based on an LSTM-Kalman filtering model, and core breakdown early warning is realized in combination with wavelet transform; outputting a corrected resistance value and a fault mark by using a BP neural network; predicting the life of the piezoresistor by adopting a gradient boosting decision tree and fusing lightning overvoltage characteristics; the transient interference is suppressed through the combination of a Transform self-attention mechanism and dynamic time warping; according to the method, the aging detection precision and the complex environment adaptability are remarkably improved, the misjudgment rate is reduced, and the multi-fault associated positioning and active defense capability is realized.

An electronic device according to various embodiments comprises: a memory including instructions; and a processor that is electrically connected to the memory and executes the instructions. When the instructions are executed by the processor, the processor may: acquire a first traffic feature vector and a second traffic feature vector on the basis of traffic data generated in a wireless network device during a plurality of time intervals; generate a combined feature vector by combining the first traffic feature vector and the second traffic feature vector; and acquire predicted traffic data, to be generated in the wireless network device, on the basis of the combined feature vector. Various other embodiments are possible.

The invention relates to the technical field of intelligent operation and maintenance of a power system, in particular to a 10KV substation equipment multi-source heterogeneous data collaborative fault prediction method and system, and the method comprises the steps: integrating equipment sensing data, environment data, operation and maintenance data and video image data, and forming a multi-mode heterogeneous data set; through depth feature extraction and semantic alignment, heterogeneous data is converted into unified feature representation, and dynamic calibration is carried out by using space-time consistency constraints; carrying out adaptive weighted fusion and contradiction resolution on the calibrated features to generate fused features; based on an equipment state knowledge graph, performing multi-dimensional evaluation on the fusion feature to obtain an equipment state vector; predicting a fault through a multi-level fault prediction model by using the vector and the fusion feature; and comparing a prediction result with actual fault data, feeding back and updating a knowledge graph and prediction model parameters, realizing continuous optimization, and realizing deep fusion of heterogeneous data through multi-modal heterogeneous data depth feature extraction and semantic alignment.

Various embodiments discussed herein are directed to improving existing technologies by detecting a likelihood of hallucination arising from one-shot, few-shot, or outside knowledge contexts. For example, regarding the one-shot or few-shot contexts, some embodiments determine a set of tokens in a language model output that are not found in target content but are found in at least one example. When such phrases are not very common words, this is highly indicative that the model is hallucinating because these phrases should be located in the target content but are not, but are instead located in the examples.

The invention provides an unmanned intelligent inspection equipment cooperative scheduling method and system in a photovoltaic power generation scene, and relates to the technical field of photovoltaic power station intelligent inspection, and the method comprises the steps: carrying out the task priority classification and time sequence correlation analysis based on a dynamic adaptive neural network and a sequence predictor, constructing a task dependency graph, and carrying out the task priority classification and time sequence correlation analysis; a candidate task allocation scheme is generated based on a deep reinforcement learning framework, the candidate scheme is optimized in combination with a collaborative decision-making system constructed by a multi-target genetic algorithm and a graph attention mechanism by taking minimization of completion time, energy consumption and maximization of coverage rate as targets, and task allocation constraints are updated by using a confidence propagation network; and an abnormal condition is judged through a Bayesian reasoning algorithm, and an optimal scheduling scheme is finally output, so that the inspection efficiency of the photovoltaic power station can be effectively improved, the energy consumption is reduced, and the inspection coverage rate is improved.

The present disclosure belongs to the technical fields of computers and defect detection. Provided are a defect detection method and a related device. The method comprises: obtaining an image to be processed; processing said image by means of a feature extraction module in a deep-learning defect detection model, wherein the feature extraction module comprises an intermediate feature layer, the intermediate feature layer comprises a dropout layer, and the dropout layer is configured to randomly drop features which are extracted by means of the intermediate feature layer processing said image, such that a plurality of features subjected to random dropout are obtained after said image is processed by means of the feature extraction module; by means of a detection head in the deep-learning defect detection model, processing the plurality of features subjected to random dropout, so as to obtain a plurality of category prediction results and a plurality of position prediction results of defects in said image; and obtaining category detection results, position detection results, category uncertainties and position uncertainties of the defects in said image according to the plurality of category prediction results and the plurality of position prediction results of the defects. (FIG. 1)

The invention belongs to the technical field of equipment management, and discloses an industrial equipment fault prediction and health management method based on multi-sensor fusion, and the method comprises the steps: obtaining multi-source sensing data of industrial equipment, carrying out the signal decoupling analysis, and obtaining a decoupling characteristic spectrum; performing frequency domain conversion and modulation analysis to form a multi-dimensional characteristic spectrum system; analyzing the modal correlation of the multi-dimensional feature pedigree to obtain a fault feature mapping network; a mixed time sequence prediction model is constructed, residual life prediction and degradation trend evaluation are carried out, and an equipment health trend graph is obtained; establishing a health state evaluation index system, and performing reliability evaluation to obtain an equipment health state report; and generating a maintenance decision suggestion, and realizing real-time anomaly detection and maintenance suggestion pushing through edge calculation. Through multi-sensor data fusion and advanced analysis technologies, early warning and accurate prediction of industrial equipment faults are realized, and the operation reliability and production efficiency of the industrial equipment are remarkably improved.