Patents
Literature
23results about How to "Enhanced representation" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Non-cooperative communication signal modulation identification method based on multi-scale feature fusion extraction
ActiveCN119299270Aenhanced representationimprove accuracyModulation type identificationBiological modelsTime domainModulation pattern
The invention relates to a non-cooperative communication signal modulation identification method based on multi-scale feature fusion extraction, which belongs to the technical field of cognitive radio communication, and comprises the following steps: generating time domain signals of communication signals in different modulation patterns, and preprocessing to obtain a plurality of baseband IQ signals as sample data; forming a communication signal data set with the corresponding modulation pattern as a sample label; initializing a multi-scale feature fusion extraction network model, and training the multi-scale feature fusion extraction network model by using the modulation signal data set to obtain a trained multi-scale feature fusion extraction network model; and obtaining a time domain signal of a non-cooperative communication signal in real time, performing preprocessing, inputting the trained multi-scale feature fusion extraction network model, and obtaining a recognition result of a corresponding time domain signal modulation pattern. Accurate and efficient identification of the non-cooperative communication signal modulation pattern is realized.
Owner:36TH RES INST OF CETC
Sleep sign monitoring method based on millimeter wave radar
ActiveCN119112101Alow costeasy to deployRespiratory organ evaluationSensorsIntermediate frequencyVital sign monitoring
The invention discloses a sleep sign monitoring method based on a millimeter-wave radar, which comprises the following steps: firstly, presetting acquisition parameters of the millimeter-wave radar, transmitting signals of the millimeter-wave radar, capturing reflected signals by a receiving antenna, sampling to obtain intermediate-frequency digital signals, and sending a sampling result to a rear-end computing device; extracting features related to the sleeping posture and the breathing frequency from the collected intermediate frequency digital signals; and recognizing the sleep posture of the user by using the point cloud features and the breathing features obtained after feature extraction. And then, effective reflection points are extracted, and the respiratory rate is accurately estimated by using the reflection points through a weighted average method. The invention aims to realize an accurate and reliable vital sign monitoring system by using commercial millimeter wave radar equipment which is low in cost and easy to deploy, stably recognize six sleeping postures and accurately measure the respiratory rate; rich and stable point cloud information is obtained; the characterization of the point cloud on the sleep posture is enhanced; and a more accurate respiratory rate estimation result is obtained.
Owner:THE ACAD OF TIANJIN UNIV HEFEI
Knowledge recommendation method and system based on cross-modal comparison and Riemannian hyperbolic geometry
ActiveCN119336999Aenhanced representationBiological modelsComplex mathematical operationsBasic knowledgeRecommendation model
The invention relates to the technical field of knowledge recommendation, and discloses a knowledge recommendation method and system based on cross-modal comparison and Riemannian hyperbolic geometry, and the method comprises the steps: obtaining a user and project interaction bipartite graph; obtaining a basic knowledge graph; combining the user and project interaction bipartite graph with the basic knowledge graph to obtain a collaborative knowledge graph; multi-modal features are set for each item in the collaborative knowledge graph, and the multi-modal features comprise visual modal features and text modal features; inputting the collaborative knowledge graph and the multi-modal features of the items into the trained knowledge recommendation model, and recommending the items to the user through the trained knowledge recommendation model; according to the trained knowledge recommendation model, potential information among different modals is further mined by using cross-modal comparative learning, and an extra supervision signal is introduced for a recommendation task. Movie items or game items that the user is interested in can be recommended to the user.
Owner:SHANDONG UNIV
Medical knowledge graph construction and reasoning method and system, medium and equipment
PendingCN119272861Aenhanced representationImprove efficiencyRelational databasesBiological modelsMedical knowledgeGraphics
The invention provides a medical knowledge graph construction and reasoning method and system, a medium and equipment. The medical knowledge graph construction and reasoning method comprises the steps that to-be-queried content and a constructed medical knowledge graph are acquired; according to the to-be-queried content, the constructed medical knowledge graph is subjected to recognition reasoning through the graph neural network, and a query result is determined and comprises the entity relation of the to-be-queried content in the medical knowledge graph. According to the method, the knowledge graph is reasoned by adopting the graph convolutional network, the graph data structure can be effectively processed, the complex relationship between entities can be captured, the problem of incomplete information can be solved, and the expression and reasoning efficiency of the medical knowledge graph is remarkably improved.
Owner:SHANGHAI MINGPIN MEDICAL DATA TECH CO LTD
Coronary artery stenosis detection method based on coronary angiography and space-time collaborative learning
ActiveCN119323546AEasy to detectenhanced representationImage analysisBiological modelsStenotic lesionCoronary arteries
The invention discloses a coronary artery stenosis detection method based on coronary angiography and space-time collaborative learning, and belongs to the field of intelligent medical treatment. According to the method, through a deep feature extraction network based on a channel shuffling structure re-parameterization convolution single aggregation module, through channel segmentation and multi-branch training, feature multiplexing and information flowing are enhanced, a double-flow path is introduced into a feature fusion network to realize adaptive weighted fusion of features of different scales, and the feature fusion efficiency is improved. The representation of spatial features is improved; a space-time collaborative analysis module capable of fusing time information and local space information at the same time is adopted, and blood vessel shape deformation and hemodynamic information in a space-time sequence are effectively captured and effective feature information is enhanced by constructing time sequence connection and fusing a space-time feature graph, so that the detection accuracy and robustness of coronary artery stenosis lesions are improved. According to the method, the time and space information of the coronary angiography sequence image is comprehensively considered, the number of false positive detection is reduced, and the detection capability of the model coronary artery stenosis lesion is comprehensively improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA
Method for multi-modal recommendation, electronic equipment and readable medium
ActiveCN119475241AEfficient use ofenhanced representationBiological modelsCommerceMessage deliveryTheoretical computer science
The invention relates to a method for multi-modal recommendation, electronic equipment and a readable medium, and the method comprises the steps: designing a graph purification strategy on an interaction graph, so as to eliminate a noise edge caused by non-uniform attention of a user; then, the three GCNs are applied in parallel to process multi-modal features and ID embedding respectively, and purified high-order representation of users and articles is obtained. For a second restriction, messaging is performed on the frozen user-user and item-item affinity maps to aggregate features between similar nodes. Summing learning results of the interaction graph and the affinity graph; afterwards, mutual information between ID embedding and modal features is maximized by introducing a contrast learning task and utilizing an inherent self-supervising signal of a multi-modal attribute, so that self-supervising learning without data enhancement is realized;
Owner:NAT UNIV OF DEFENSE TECH
Structural damage identification method based on deep reconstruction network and multi-dimensional feature fusion
ActiveCN121476428Benhanced representationImprove refactoring effectProcessing detected response signalBiological modelsCategory recognitionCharacteristic space
The application belongs to the technical field of bridge health monitoring, and particularly relates to a structure damage identification method based on a deep reconstruction network and multi-dimensional feature fusion, which comprises the following steps: obtaining an acceleration signal of a target bridge structure; inputting the acceleration signal into a Res-UNet-AE autoencoder to obtain a reconstructed signal, and calculating a reconstruction error and a signal-to-noise ratio according to the reconstructed signal; inputting the acceleration signal and the reconstructed signal into a perception autoencoder to obtain a perception index; fusing the reconstruction error, the signal-to-noise ratio and the perception index to obtain a three-dimensional damage feature space; and performing unsupervised clustering and identification according to the three-dimensional damage feature space to obtain a damage category identification result of the target bridge. The application can realize accurate differentiation of different working conditions of a structure without relying on any damage label.
Owner:GUANGDONG UNIV OF TECH
A small target detection method and system for unmanned aerial vehicle aerial image
The application discloses a small target detection method and system for unmanned aerial vehicle aerial image, relates to the technical field of computer vision and unmanned aerial vehicle target detection, and generates a C2f_iAFF module by embedding an iterative attention feature fusion mechanism iAFF in a C2F convolution module of a YOLOv8 network, trains the C2f_iAFF module by using an STDIoU loss function which is optimized based on MPDIoU and is suitable for small target detection characteristics, adds a small target detection head to an original network structure of the YOLOv8 to generate an improved network structure, and finally obtains a small target detection model which is used for detecting unmanned aerial vehicle aerial images, obtaining a small target detection type and result, and improving the precision and speed of small target detection.
Owner:NANJING UNIV OF POSTS & TELECOMM
Eye chamber angle state determination method and device, equipment and storage medium
PendingCN119423681Aenhanced representationimprove accuracyImage enhancementImage analysisOphthalmologyOptometry
Owner:LIAONING DRAGONFLY HEALTH TECH CO LTD
Method for enhancing epidemic prevention management of infectious diseases through network modeling
ActiveCN119541893Aaccurate analysisaccurate predictionMedical data miningEpidemiological alert systemsDiseaseData mining
The invention provides a method for enhancing epidemic prevention management of infectious diseases through network modeling. Comprising the following four processes: firstly, according to detailed epidemic situation contact information recorded by a flow scheduling report, constructing an epidemic situation association diagram; then, by defining a meta path, generating a node sequence in the heterogeneous graph by using random walk, and capturing semantic and structural correlation among various nodes in the heterogeneous graph; then, risk factors are introduced and adjusted, namely, the weight coefficient in the random walk process is adjusted according to the risk factor level provided by the disease prevention and control center, and the risk factors comprise the site ventilation condition, the contact duration, the personnel density and the behavior habits; and finally, carrying out point embedding and risk assessment, assessing the importance of nodes, and predicting high-risk individuals and places. Compared with a traditional network evaluation method, the scheme of the invention improves the accuracy of risk prediction.
Owner:BEIHANG UNIV
An adaptive coordinated attention network-based method for fatty liver ultrasound image classification
ActiveCN115984544BEasy diagnosisImprove inference speedImage analysisCharacter and pattern recognitionFatty liverFeature extraction
The present invention discloses a method for classifying fatty liver B-ultrasound images using an adaptive coordinated attention network, including a base plate. The method is designed to perform data enhancement preprocessing operations such as image histogram equalization, grayscale linear transformation, ROI selection, and average grayscale ratio comparison. The method uses an EfficientNet network combined with label smoothing and Adaptive Coordinate Attention to only use the pixels and labels of the original B-ultrasound image as input, thereby avoiding the decoupling of feature extraction and classification and achieving end-to-end automatic classification and recognition. The method is a lightweight network with fast training and reasoning, small model parameters, and based on adaptive coordinated attention, the method can adaptively encode horizontal and vertical position information as channel attention, while retaining position information in other spatial directions to enhance the representation of the attention object. Based on the method, the recognition ability of fatty liver B-ultrasound images has exceeded manual recognition and is also superior to other methods.
Owner:SHANDONG UNIV +1
A battery pack intelligent monitoring system and method based on deep learning
The present invention relates to the field of deep learning technology, and invents a deep learning-based intelligent monitoring system and method for a battery pack, comprising performing data standardization and outlier denoising operations on the historical electrical data set group to obtain an electrical data set sequence group; performing electrical feature extraction and correlation feature fusion on the electrical data set sequence group to obtain a fused electrical feature sequence group; performing graph reconstruction and graph feature extraction on the fused electrical feature sequence group according to the battery pack structure to obtain an electrical graph feature sequence; performing self-attention time series convolution on the electrical graph feature sequence to obtain electrical time series features; performing variational anomaly monitoring and anomaly recognition on the electrical time series features to obtain a battery pack monitoring result. The present invention can improve the accuracy of battery pack monitoring.
Owner:FUJIAN URBAN CONSTR INTELLIGENT CONTROL TECH CO LTD
Model training method, text error correction method, device, equipment, medium and product
PendingCN119272758AImplement error correctionImprove classification performanceNatural language data processingMachine learningAlgorithmTheoretical computer science
The invention discloses a model training method and device, a text error correction method and device, equipment, a medium and a product, and is applied to the technical field of artificial intelligence. The method comprises the following steps: firstly, carrying out word segmentation on a training text, and mapping to high-dimensional embedded representation so as to obtain target word vector representation through conversion, namely, the process of BERT embed; according to the scheme, the target word vector representation is input into the initial text error correction model for reinforcement learning, the method combines BERT embdingings and the aggregation operation of the reinforcement learning unit, training is completed only through few texts, the semantic relation can be captured, error correction of grammar, punctuation marks and words can be achieved, and meanwhile the text representation and classification capacity is improved. The method can adapt to an official document error correction scene, and has a good error correction effect.
Owner:CHINA MOBILE INFORMATION TECHNOLOGY CO LTD +1
Small sample relationship extraction method and device for content big data
ActiveCN113378573Bimprove accuracyEfficient integrationText processingBiological modelsPattern recognitionRelationship extraction
The present invention discloses a method and device for extracting small sample relations for content big data. The present invention firstly uses a pre-trained language model and a character-level LSTM to vectorize sentences; secondly, extracts text structure features through a dual affine mechanism and a graph neural network; simultaneously, uses a word-level LSTM and the [CLS] word vector representing semantic information in BERT to integrate context information into the word vector of an entity pair, and constructs entity pair features containing context information; finally, extracts the similarity and difference of sentence features through a similarity-difference relationship network to perform small sample relation extraction. The present invention applies small sample learning in a content big data scenario, fully extracts text features, and characterizes the differences between entity relations of different categories, thereby improving the accuracy of relation extraction.
Owner:BEIJING HUACHENGZHIYUN SOFT CO LTD
Small target detection method and device and medium thereof
PendingCN119206186Aenhanced representationImprove detection accuracyInternal combustion piston enginesBiological modelsData setAlgorithm
The invention relates to the technical field of target detection, in particular to a small target detection method and device and a medium thereof. The method comprises the following steps: S1, acquiring an original image, and preprocessing the original image to obtain a data set; step S2, constructing an original YOLOv8 model, improving the original YOLOv8 model, and replacing an SPPF structure of the original YOLOv8 model with an SPPF-MAA structure to obtain an improved YOLOv8 model; s3, inputting the data set into the improved YOLOv8 model, and training the improved YOLOv8 model by using a self-adaptive weight loss function; and S4, target detection is carried out by using the trained YOLOv8 model, so that the precision of small target detection can be remarkably improved.
Owner:CHANGZHOU XINGYU AUTOMOTIVE LIGHTING SYST CO LTD
Artificial intelligence-based cultural and tourism uniform light guide lighting fault diagnosis method and system
The present invention provides a method and system for diagnosing faults of uniform light guide lighting for cultural tourism based on artificial intelligence, which relates to the field of smart cultural tourism technology, including collecting multi-source heterogeneous data of a uniform light guide lighting system for cultural tourism, processing multimodal data, and outputting abnormal feature vectors and quantum state entanglement matrices; inputting into a biologically inspired self-organizing neural network, generating a hierarchical representation of fault modes through dynamic weight adjustment and synaptic growth algorithms, constructing a fault topological landscape, and generating multi-scale continuous homology feature descriptors; inputting into a pre-constructed fuzzy cognitive graph reasoning system, modeling through the causal relationship between concept nodes, generating a fault scenario model, diagnosing the fault, updating a fault diagnosis knowledge base, obtaining a diagnosis result, and generating a fault diagnosis report.
Owner:BEIJING LANDSKY LIGHTING TECH CO LTD
A non-cooperative communication signal modulation recognition method based on multi-scale feature fusion extraction
ActiveCN119299270Benhanced representationimprove accuracyModulation type identificationBiological modelsTime domainNetwork model
The present application relates to a kind of non-cooperative communication signal modulation identification method based on multiscale feature fusion extraction, belong to cognitive radio communication technical field, including generating the time domain signal of communication signal under different modulation style and being preprocessed to obtain multiple baseband IQ signal as sample data, with corresponding modulation style as sample label composition communication signal dataset;Initialization multiscale feature fusion extraction network model, utilize the modulation signal dataset to train the multiscale feature fusion extraction network model, obtain trained multiscale feature fusion extraction network model;Real-time acquisition non-cooperative communication signal time domain signal and pre-processing, input the trained multiscale feature fusion extraction network model, obtain the identification result of corresponding time domain signal modulation style.Accurate and efficient identification of non-cooperative communication signal modulation style is realized.
Owner:36TH RES INST OF CETC
Human pose estimation method and system based on dynamic perception sparse attention
ActiveCN118522068BReduce computational complexityimprove accuracyCharacter and pattern recognitionNeural learning methodsPattern recognitionComputation complexity
The application provides a human pose estimation method and system based on dynamic perception sparse attention, wherein the method steps comprise: preprocessing original image data to obtain a feature map of a person in the image; performing regional division and linear projection processing on the feature map according to a preset block size to obtain query, key and value tensors, and deriving a relevant region affinity graph in the feature map through a primary routing algorithm; filtering out the most valuable region in the relevant region affinity graph, performing attention calculation, obtaining a corresponding weight matrix, and inputting the weight matrix into a multi-layer perception machine to extract pose information; and inputting the pose information into an encoder to refine the pose information, and generating a key point heat map based on the pose information to detect a human pose. In this way, the processing capability for occluded poses is further enhanced, the accuracy of human pose estimation is overall improved, and the computational complexity is reduced.
Owner:SHANGHAI UNIV
A cell interference troubleshooting method based on AI and big data
ActiveCN122471371BOvercome the technical bottleneck of misjudgment as "disturbance source"enhanced representation
The application relates to the technical field of wireless communication network optimization, and discloses a cell interference investigation method based on AI and big data. The method comprises the following steps: a three-dimensional space-time index is established and is aggregated to form a space-time feature cube, the space-time feature cube is sliced along a time axis and is aggregated, and a dynamic graph snapshot sequence is output; based on the dynamic graph snapshot sequence and the space-time feature cube, an enhanced node feature vector is generated through multi-modal gating mechanism fusion, and an enhanced dynamic graph snapshot sequence is acquired; a causal direction bias of a structural causal model is injected into a message passing process of a graph neural network, a jamming probability of a candidate jamming cell is output based on the enhanced dynamic graph snapshot sequence, and after the confidence is corrected through counterfactual verification, a root cause positioning tuple is output. The application enhances features through multi-modal gating fusion, integrates a causal model to construct GNN causal attention, realizes interference tracing through counterfactual correction, and relies on digital twin deduction and SPC verification closed loop to avoid strategy issuing derived faults.
Owner:GUANGDONG TELECOM ENG
Deep learning reconstruction method for sea surface current field based on multi-source sea-air spatio-temporal characteristics
PendingCN122241613Aimplement refactoringImplement joint reconstructionOpen water surveyNeural learning methods
This invention provides a deep learning method for reconstructing sea surface current fields based on multi-source air-sea spatiotemporal features, relating to the field of marine data processing. Specifically, it includes: acquiring multi-year continuous sea surface current velocity data and multi-source environmental feature data for a target sea area; constructing a full-field training sample in a continuous time series manner, using multi-source environmental features from multiple consecutive historical moments as input to candidate deep learning models, and using the full-field data of the eastward and northward current velocity components at a future target time as prediction labels; constructing velocity moduli using the eastward and northward current components; training candidate deep learning models using a joint loss function; evaluating candidate deep learning models, selecting the optimal model, and using the optimal model to output the full-field current velocity results at the target time. The technical solution of this invention overcomes the problem in existing technologies of difficulty in obtaining long-term, large-scale, spatially continuous sea surface current field data.
Owner:SANYA INST OF OCEANOGRAPHY OCEAN UNIV OF CHINA
High-precision video SAR (Synthetic Aperture Radar) moving target detection method based on information geometry theory
ActiveCN119540292Aenhanced representationEasy to detectImage enhancementImage analysisSynthetic aperture radarVideo image
The invention discloses a high-precision video SAR (Synthetic Aperture Radar) moving target detection method based on an information geometry theory in the technical field of SAR moving target shadow detection. The high-precision video SAR moving target detection method based on the information geometry theory comprises the following steps of performing shadow enhancement and background suppression on a video SAR image sequence; rOI region extraction based on an information geometry theory; and through error detection suppression, a false ROI region is effectively removed. According to the high-precision video SAR moving target detection method based on the information geometry theory, on the premise of ensuring the detection precision, the detection probability of video SAR moving target shadow is improved.
Owner:NAT UNIV OF DEFENSE TECH
Image editing method and system based on pairs of visual cues
The application provides an image editing method and system based on a visual prompt pair, through given visual prompt pairs containing example source images and example edited images, a progressive structured training strategy is used to make the model learn the conversion relationship between the two and migrate to the query source image, and a condition compression and reuse mechanism is combined to generate edited images that are highly consistent with the visual prompt and retain the core features of the query image. The progressive structured training strategy of the application includes two stages of text decoupling training and superior-inferior comparison refinement, and the condition compression and reuse mechanism reduces the computational overhead by downsampling the example source image, the example edited image and the query image and reusing the approximately invariant features in the inference stage. The application can efficiently perform image editing based on the visual prompt pair in the inference stage, significantly improving the high-resolution generation speed while achieving high-fidelity following of the visual prompt.
Owner:COMMUNICATION UNIVERSITY OF CHINA +1
Road surface wave rapid identification model construction method, electronic device and storage medium
ActiveCN119152278Breduce dimensionalityeasy to identifyInternal combustion piston enginesBiological models
The invention relates to a method for constructing a road wave rapid identification model, an electronic device and a storage medium, and belongs to the technical field of road engineering. In order to solve the problem of rapid intelligent identification of road wave diseases, the invention includes collecting road images for compression processing to obtain compressed road images; labeling to obtain a data set of a road wave rapid identification model; constructing a basic model, a first auxiliary model, a second auxiliary model and an enhanced model for rapid identification of road waves; constructing a loss function between the basic model, the first auxiliary model, the second auxiliary model and the output layer of the enhanced model for rapid identification of road waves, constructing an overall loss function, and then constructing a model optimization method based on the overall loss function, and enhancing and improving the optimized basic model obtained through training to obtain a final road wave rapid identification model; constructing a digital twin model based on the final road wave rapid identification model for updating road wave diseases. The invention improves road safety.
Owner:SHENZHEN URBAN TRANSPORT PLANNING CENT CO LTD