455results about How to "Enhanced Representational Capabilities" patented technology

The invention discloses a quality safety optimization method and system based on a multi-modal vertical large model technology, and relates to the technical field of quality safety optimization systems.The method comprises the steps that quality safety related data are collected from a multi-modal data source and preprocessed; fusing data through features and decision levels; a vertical large model of an improved Transform architecture is constructed by using fusion data, a quality feature extraction layer and a safety rule embedding layer are provided, and adaptive learning rate and gradient clipping training are used; inputting the new data into the large model to analyze the quality safety condition, including defect prediction, risk assessment and problem early warning; and according to an analysis result, generating an optimization suggestion through rule reasoning and reinforcement learning. According to the invention, multi-modal quality safety data can be comprehensively collected and preprocessed. The vertical large model is high in pertinence, quality defects, safety risks and potential problems are accurately analyzed, the optimization suggestion module is combined with rules and reinforcement learning, suggestions with expected effects and priorities are generated, and the quality safety level and the resource utilization efficiency are improved.

The invention provides an unmanned aerial vehicle accessory intelligent identification and access method and system based on a sensor, and relates to the technical field of unmanned aerial vehicle accessory management, and the method comprises the steps: collecting the three-dimensional contour information of unmanned aerial vehicle accessories, generating standard point cloud data, carrying out the feature extraction, and carrying out the feature alignment and interaction, generating a high-dimensional fusion feature matrix of the target unmanned aerial vehicle accessories; based on the feature pyramid network, constructing multi-scale feature representation, generating hierarchical feature descriptors, performing similarity calculation, generating a similarity score matrix, performing optimal matching, establishing an adaptive verification rule base and performing accessory verification; calculating an optimal action sequence of an access path based on model information, mapping the optimal action sequence into a motion track parameter of a mechanical arm, collecting multi-point stress data, predicting the optimal clamping force, establishing an accessory service life prediction model, performing prediction in combination with historical data, and generating an accessory state evaluation report and a maintenance suggestion.

The invention relates to the technical field of cold-chain logistics information, and discloses a multi-mode AIGC cold-chain logistics information processing method and system, and the method comprises the steps: carrying out the feature extraction and feature enhancement of video data, temperature data and position data in a cold-chain logistics system based on a logistics information AIGC model, and obtaining an enhanced feature matrix; carrying out digital twinborn modeling to obtain a digital twinborn model of the logistics system, and constructing a state parameter space; performing deep reinforcement learning and information delay index calculation to generate a real-time data synchronization scheme; constructing a distribution network graph structure, and performing depth map network coding on the distribution network graph structure to obtain a distribution network representation vector; and performing multi-agent collaborative decision-making on the distribution network representation vector to obtain a cold chain distribution scheduling scheme, and updating the cold chain distribution scheduling scheme to the logistics system digital twinborn model. Therefore, intelligent scheduling and accurate control of the cold-chain logistics system in a complex scene are realized.

The invention relates to the technical field of ozone concentration prediction, in particular to an ozone concentration prediction method, device, equipment and medium based on a space-time diagram convolutional network model.The method comprises the steps that historical ozone concentration and meteorological data of a target area are obtained, and training and prediction samples are constructed after standardization; a space diagram structure is established, nodes represent monitoring points, and edges represent the monitoring points with correlation exceeding a threshold value; extracting a spatial dependency relationship by adopting GCN and GAT, and generating time sequence data; tCN or RNN is adopted to extract time-dependent features, and spatial-temporal feature comprehensive representation is obtained; training a model by utilizing the training sample and the spatial-temporal characteristics, adopting MSE (mean square error) as a loss function, adjusting parameters by an Adam optimizer, and optimizing hyper-parameters to minimize errors; newest meteorological and historical data are input, future ozone concentration is predicted, GNN extracts spatial features, RNN processes a time sequence, time sequence data can be processed in parallel through convolution operation, and high calculation efficiency is achieved.

The invention discloses a multi-scale feature fusion triple branch network method for multi-organ segmentation, and the method comprises the following steps: extracting local features through a CNN, and extracting global features through Transform; the features extracted by the CNN and the Transfomer are processed by using space attention and channel attention respectively, the processed features are fused, and output features are obtained through a feature processing module; the method comprises the following steps: setting a mask mechanism Smart Mask, improving a fixed mask mode in a Swin Transform, and capturing a long-distance dependency relationship; according to the method, global features in a medical image are learned through parallel Vision Mama, features obtained after CNN and Transform fusion are guided, and a segmented image is obtained. The CNN, Transform and Mamba encoders are combined, so that efficient medical image segmentation is realized. And the introduced parallel Vision Mama layer increases a small number of parameters and enhances the global context capture capability at the same time, so that the performance and efficiency of the model are remarkably improved.

The invention discloses a micro-grid network topology flexible configuration method based on matrix topology, and relates to the field of micro-grids, and the method comprises the steps: constructing a heterogeneous database of a micro-grid network and equipment; mapping a micro-grid network and equipment into a graph structure, and constructing a graph neural network model; setting mapping strategies of different heterogeneous hardware units according to heterogeneous characteristics of the different heterogeneous hardware units, and constructing a scheduling model of the heterogeneous hardware units by adopting a reinforcement learning algorithm; inputting the preprocessed data into a graph neural network model to obtain an incidence relation between a micro-grid network topology structure and equipment parameters, and taking the incidence relation as a constraint condition; inputting the preprocessed data into a scheduling model to obtain a scheduling strategy of the heterogeneous hardware unit, and taking the scheduling strategy as an optimization target; constructing a multi-objective function of micro-grid network topology optimization; and solving the multi-objective function of the microgrid network topology optimization by adopting an intelligent algorithm, and generating a microgrid network topology scheme. According to the invention, the robustness of the topology scheme is improved.

The invention relates to the technical field of program similarity, in particular to a source code similarity analysis method and system based on semantic enhancement AST, and the method comprises the steps: respectively generating corresponding abstract syntax trees AST for two functions using different programming languages; enabling nodes with the same type but different names in different programming languages AST to have the same representation by utilizing a node vocabulary, and shielding the node representation difference of the different programming languages AST; a control flow edge and a data flow edge are expanded for the AST after node standardization processing, a semantic enhancement AST is generated, and the semantic enhancement AST integrates grammar, structure and semantic information of a function; a function similarity analysis network is designed, semantic enhancement AST is converted into graph vectors in combination with a graph convolutional network and an attention mechanism, the two graph vectors are spliced and then input into a full-connection neural network, and the similarity of different programming language functions is judged. According to the method, similarity judgment of different programming language functions can be realized, and the detection efficiency is improved while high accuracy of the detection effect is achieved.

The invention relates to a probe contact impedance real-time monitoring and compensating method and device and a storage medium. The method comprises the following steps: acquiring a first measurement data set containing a probe contact resistance value and a contact force, and inputting the first measurement data set into a double-layer deep learning neural network for training to obtain a probe contact resistance monitoring model; performing two-parameter fault detection to obtain a contact state classification result; generating a two-dimensional compensation matrix based on a contact state classification result, and performing nonlinear mapping calculation on the second measurement data set to obtain a compensation coefficient; the compensation coefficient, the original probe structure parameters and the original probe operation parameters are input into a graph attention stacking auto-encoder for parameter prediction, and target probe structure parameters and target probe operation parameters are obtained; cloud model calculation and weighting operation are carried out, a target compensation instruction is obtained, and the target compensation instruction is used for adjusting the probe position parameters and the probe pressure parameters. According to the invention, the probe testing precision of the chip is improved.

The invention relates to the technical field of artificial intelligence, in particular to a charging pile construction planning method and system based on artificial intelligence. The method comprises the following steps: acquiring existing power infrastructure data and multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises traffic data, geographic data, vehicle data and charging behavior data; performing time sequence feature extraction on the multi-source heterogeneous data, and performing cross-time scale fusion on different data source features by using a preset hierarchical attention network model to obtain factor weight data; and constructing a long-term charging demand prediction model through a sequence-to-sequence model according to the factor weight data and the multi-source heterogeneous data. According to the site selection method based on the risk minimum set coverage problem, initial site selection scheme data is generated by combining multi-objective optimization of the coverage rate, the service radius and the accessibility, and more scientific charging pile layout is achieved.

The invention discloses a photovoltaic grid-connected harmonic current prediction method based on deep learning, and relates to the technical field of power systems and photovoltaic grid connection. According to the method, three-phase load current and grid-connected point voltage data in a photovoltaic grid-connected system are obtained, the three-phase load current is converted into a two-phase direct-current component through Clark and Park conversion, fundamental current is extracted through a low-pass filter, and a harmonic current component is obtained. Time domain and frequency domain characteristics of grid-connected point voltage data are extracted through fast Fourier transform, correlation between voltage harmonic waves and load current harmonic waves is analyzed, and grid-connected point voltage characteristics are extracted. Local features of harmonic current components are extracted through a convolutional neural network, time sequence features are captured through a bidirectional long-short-term memory network, and a harmonic current prediction model is constructed. And finally, inputting the preprocessed current and voltage characteristics, and generating a harmonic current predicted value. And the problems of nonlinearity and uncertainty in the photovoltaic grid-connected system can be more effectively solved.

The invention relates to a migratory fly insect intelligent identification method based on trap lamp assisted radar database building. According to the method, insect monitoring data of the moth-killing lamp and the radar in the same night period are fused, the insect data set is established through matching of the two data, and the difficulty of a traditional insect data set database establishment mode in data acquisition is effectively overcome; secondly, a CL-GC-Swin Transform network model is provided, a contrast learning module and a global context block are introduced into the Swin Transform, and training is carried out by using the complete polarization time-frequency characteristic pattern of the insect, so that the characterization capability of the network on the time-frequency characteristic pattern of the insect is significantly enhanced, and the accuracy of insect type identification can be effectively improved. According to the method, the flight characteristics of the insects are directly utilized for identification, complex scattering characteristic calculation and accurate radar calibration are not depended on any more, the requirements for radar system precision and calibration are greatly reduced, and the adaptability and robustness of identification can be improved.

The invention discloses an implicit coding and geometric prior-based indoor three-dimensional scene reconstruction method and system. The method comprises the following steps of: performing data processing on image data to be reconstructed to obtain corresponding pre-processed data; calculating rays under a world coordinate system corresponding to pixels needing to be trained on the image data according to internal and external parameters of the camera; inputting a three-dimensional coordinate code and an observation angle code of a sampling point on a ray and an implicit appearance code of a corresponding image into the neural radiation field model to obtain a predicted density value and a predicted color value, and performing volume rendering prediction based on a symbolic distance function to obtain a pixel value so as to obtain a trained neural radiation field model; and obtaining a standard implicit appearance code based on the density value and the color value, and inputting data at least comprising the standard implicit appearance code into the trained neural radiation field model to obtain scene geometric information. According to the method, the dependence of the existing reconstruction scheme on the three-dimensional consistency of the acquired data can be reduced, and the robustness and representation capability of the algorithm in a complex scene can be improved.

The invention discloses a point switch part detection method and device based on a YOLOv8 model and a medium, and the method comprises the steps: marking a target part in a point switch part image, and generating a target image; the method comprises the following steps: replacing an original backbone network darknet53 of a YOLOv8 model with a Swin transfer network, and introducing a residual attention module into the Swin transfer network; the method comprises the following steps of: constructing an improved YOLOv8 model by combining a spatial pyramid pooling layer on the basis of a Swin transformer network and replacing an original loss function CIoU of the YOLOv8 model with a new loss function Focal-EIoU at the same time; and inputting the target image into the improved YOLOv8 model, and generating a prediction result. And accurate detection of the target part is realized based on the detection result output by the improved YOLOv8 model.

The invention discloses a photovoltaic power prediction method and system based on multi-stage time sequence feature mining, and the method comprises the steps: carrying out the feature extraction of a historical photovoltaic power sequence through an LSTM model, and obtaining a power time sequence feature; performing feature extraction on the historical satellite cloud picture sequence through a 3DCNN model to obtain cloud layer space-time dynamic features; performing feature fusion on the power time sequence feature and the cloud layer space-time dynamic feature based on a residual cross attention mechanism to obtain a multi-modal fusion feature; further mining time sequence characteristics in the fusion characteristics by using a Transform model to obtain deep multi-modal time sequence characteristics; and outputting a prediction result through the multi-layer perceptron to predict the photovoltaic power in the next 1-4 hours. The photovoltaic power prediction precision can be improved, support is provided for safe and stable operation of a power grid, and the method has certain engineering practical value.

The invention discloses an unsupervised microseismic denoising method and system based on a multi-channel Kalman filter network, and belongs to the crossing field of earth science and technology and artificial intelligence, and the method comprises the steps: obtaining multi-channel microseismic data, and carrying out the preprocessing; constructing a multi-channel Kalman earthquake denoising network based on the recurrent neural network; constructing a loss function, and carrying out unsupervised training on a multichannel Kalman seismic denoising network based on the preprocessed multichannel microseismic data and the loss function; and denoising is carried out on the real-time micro-seismic data through the trained multi-channel Kalman seismic denoising network. According to the method, the multi-channel Kalman filtering state prediction and update equation is established, the RNN operator is designed, automatic parameter optimization is achieved, and the denoising accuracy and efficiency are improved. The method makes full use of the correlation of microseismic data, improves the filtering effect, is suitable for time-varying signals, and provides support for subsequent data processing.

The invention discloses a corn irrigation and fertilization decision-making method and system based on future meteorological data, and relates to the technical field of agricultural informatization and intelligent agriculture, and the method comprises the steps: constructing a future meteorological prediction model based on an Informer + TSLANet + TimeBlock combined deep learning network; performing long-time sequence multi-dimensional feature extraction and long-term dependency relationship capture on historical meteorological data by using the model, and predicting to obtain future meteorological data; corn yield prediction is carried out through a DSSAT model, then a Monte Carlo + NSGA-III double-layer combination multi-objective optimization algorithm is utilized to formulate a corn irrigation and fertilization scheme, and an optimal irrigation and fertilization scheme is obtained after optimization. According to the method, the characterization capability of the future meteorological prediction model is enhanced, the accuracy of future meteorological data prediction is improved, and the accuracy and foresight of corn yield prediction and irrigation and fertilization decision prediction are further improved.

The invention provides an infrared weak and small target detection method and system, electronic equipment and a storage medium, and belongs to the technical field of target detection, and the method comprises the steps: improving a YOLOv8 model for the features of an infrared weak and small target image; and performing target detection on the infrared weak and small target image by using the improved YOLOv8 model. According to the invention, a stronger infrared weak and small target detection capability is provided for the YOLOv8 model, and the problem of target detection precision bottleneck of a traditional model in a complex scene is effectively solved.

The invention provides an equipment information management method and system based on a multi-modal large model in the technical field of equipment information management. The method comprises the following steps: S1, acquiring historical multi-modal data to construct a data set, and dividing the data set into a training set, a verification set and a test set; s2, creating a multi-modal large model based on a Vi T module, a Bert module, a numerical feature construction module, a feature fusion module and an output module, and setting hyper-parameters; s3, training and evaluating the multi-modal large model through the training set, the verification set and the test set; step S4, compressing the multi-modal large model which passes the evaluation; and S5, collecting real-time multi-modal data of installed equipment in the management area by each area server, and inputting the real-time multi-modal data into the multi-modal large model to obtain an equipment information analysis report. The method has the advantages that the efficiency, the quality, the traceability and the resource utilization rate of equipment information management are greatly improved, and then the reliability of equipment operation and maintenance is greatly improved.

The invention discloses a mass spectrometric detection method and system based on data twinning. The method comprises the following steps: acquiring original mass spectrometric data of a sample through mass spectrometric detection equipment; performing multi-stage intelligent mass spectrum data preprocessing on the original mass spectrum data; training the processed mass spectrum data by using a machine learning algorithm, and constructing a data twin model which is used for obtaining a mass spectrum analysis result; and inputting new mass spectrum data into the trained data twin model to obtain a mass spectrum analysis result. According to the invention, mass spectrum data are identified and classified, and specific chemical components in the sample are identified and quantitatively analyzed. By performing multi-stage intelligent mass spectrum data preprocessing on the original mass spectrum data, the quality and reliability of the data are improved, the accuracy of the data is improved, the mass spectrum data are analyzed through the data twin model, and the analysis efficiency of the mass spectrum data is improved.

The invention relates to the technical field of power regulation, and discloses a central air-conditioning refrigeration system load flexible regulation method which comprises the following steps: performing multi-modal feature extraction and short-term load analysis on a historical sensing data sequence to obtain short-term load data; and performing multi-scale expansion convolution, bidirectional time sequence feature extraction and long-term load analysis on the historical sensing data sequence to obtain long-term load data, and obtaining real-time sensing data according to the pre-obtained real-time sensing data. The short-term load data and the long-term load data are used for carrying out fitness calculation and global optimal iteration on the adjustment strategy set to obtain a primary adjustment strategy; and state space construction and state feedback updating are conducted on the primary adjusting strategy according to the real-time sensing data and the analysis load data, a standard adjusting strategy is obtained, and load adjusting is conducted on the central air conditioner through the standard adjusting strategy. The invention further provides a device and equipment for flexibly adjusting the load of the central air-conditioning refrigerating system. The sales volume of air conditioner load adjustment can be increased.

The invention provides a personalized book recommendation method and system based on reader behavior data analysis, and the method comprises the steps: carrying out the dynamic feature extraction of a content feature vector based on the obtained content feature vector corresponding to the book borrowing content data of a reader and the obtained behavior feature vector of the borrowing behavior data corresponding to the book borrowing content data of the reader; therefore, the dynamic and continuous borrowing content features in the book borrowing content data of the reader are obtained, and the characterization effect of the dynamic feature vector of the content data is improved. Fusing the behavior feature vector and the dynamic feature vector of the content data to obtain a multi-source feature vector, performing feature embedding on the multi-source feature vector to obtain a multi-source integration embedding vector, and further performing borrowing recommendation reduction mapping and reasoning on the multi-source integration embedding vector to obtain borrowing recommendation information corresponding to the book borrowing content data of the reader. The recommendation precision can be improved, the conversion rate is increased, and the user experience is improved.

The invention discloses a monocular 3D target detection method and device, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a to-be-detected target detection image; inputting the target detection image into a pre-trained target detection model to obtain target detection information of the target detection image; wherein the training process of the target detection model comprises the following steps of: adding a multi-modal feature fusion module in a ControlNet model architecture to establish a Fusion-ControlNet model architecture; introducing the Fusion-ControlNet model architecture as a guidance module for condition generation into the Stable Diffusion model architecture to obtain a data set expansion model; and performing expansion processing on the KITTI data set by using the data set expansion model to obtain a KITTI expanded data set. According to the invention, the problem of low accuracy during monocular 3D target identification in the prior art is solved.

The invention discloses a road rockfall detection method and device based on deep learning, electronic equipment and a program product. Training of the detection method is achieved through a completed rockfall detection model, a backbone network of the rockfall detection model is provided with an SDF module which is used for fusing image information extracted through basic convolution and detail information extracted through SPD convolution, and therefore the rockfall detection model can process low-resolution images or images containing small targets, and the detection accuracy is improved. Multi-angle and multi-level feature information can be adaptively fused, and the recognition problem caused by image view angle changes is relieved; an SLLGA module is arranged in the neck network to realize adaptive weighted fusion of global features and local features, so that the model can dynamically adapt to different concerns, and the rockfall detection effect in a complex scene is improved; a GE-SPP module is arranged behind the last scale of the backbone network, multi-scale features, global background features and edge features can be fused, and the precision of rockfall detection under different background environments and different scales is improved.

The invention discloses a vulnerability load classification method and system based on codes and semantic features, and belongs to the technical field of intrusion detection. The method comprises the following steps: encoding a vulnerability load, masking an encoding result, and obtaining a first representation of the vulnerability load through predicting a mask value; acquiring a second representation of the vulnerability load based on a TF-IDF encoder; synthesizing the first representation and the second representation to obtain a comprehensive representation of the vulnerability load; and classifying the comprehensive representation to obtain a classification result of the vulnerability load. According to the method and the device, the vulnerability detection accuracy is improved by enhancing the characterization capability of the vulnerability load.

The invention discloses an SAR image change detection method and system based on a dynamic bilinear fusion network, and the method comprises the steps: collecting dual-temporal SAR images of the same region in different periods, forming a dual-temporal data set, and selecting a part of image blocks and labels thereof as training samples for the training and optimization of a model; constructing an SAR image change detection model; double-time input in the training sample is sent into the dynamic bilinear fusion network for training, and model parameters are updated; inputting the dual-time SAR image into the trained model to obtain a change detection prediction result; according to the method, dynamic shift convolution and self-attention are combined in parallel, a self-attention mechanism is used for capturing global information, and the dynamic shift convolution dynamically gathers a plurality of convolution kernels and is combined with the shift convolution to extract more detailed and rich feature representation, so that the representation capability of the model is enhanced; the bilinear convergence module interactively fuses parallel features from among images and in the images, and captures spatial correlation among pixels in the images.

The invention discloses a recommendation method combining a large language model and a knowledge graph. The recommendation method comprises the following steps: processing a large language model text based on an iterative aggregation thought; carrying out text coding based on BERT; aligning entity embedding based on the graph attention network; and recommending and predicting. By effectively integrating the large language model, the knowledge graph and the graph neural network technology, the performance and accuracy of the recommendation system are remarkably improved.

The invention discloses a method for analyzing and predicting drug-target interaction by using deep learning, which comprises the following steps: encoding a drug and a target protein, and extracting the characteristics of the drug and the target protein for interaction; inputting the interaction characteristics of the drug and the target protein into a multi-head cross attention mechanism, and extracting the interaction characteristics of the drug and the target protein; obtaining independent characteristics of the drug and the target protein; fusing and re-classifying the independent characteristics of the drug, the independent characteristics of the target protein and the interaction characteristics of the drug and the target protein, and predicting drug-target interaction; the invention provides a network based on feature extraction between global molecules and local feature molecules of a drug-target, and the DTIs of the drug-target is predicted; according to the method, the interaction features of the drug target are extracted by adopting a cross attention mechanism, and the independent features of the drug target are extracted by using GAT and CNN, so that rich drug-target information is obtained, and the prediction performance is improved.

The invention discloses a multi-modal medical image classification method based on an improved DenseNet, a medical image classification network is constructed, the network comprises a preliminary feature extraction module, a feature refining module and a classification module, the feature refining module fuses the interlayer dense connection characteristic of the DenseNet and the efficient feature processing capability of a Mamba module, and the classification module is used for classifying the Mamba module. Extraction and fusion of complex image features are realized; and the classification module adopts a full connection layer and a Softmax function and is responsible for converting rich image feature representation into a specific image classification result. According to the invention, through the transition layer with the Mama module, the capturing capability of the model on the key features of the image is enhanced, so that the classification precision of the 3D medical image is further improved on the basis of maintaining the original advantages of the DenseNet, and powerful technical support is provided for the application of deep learning in medical image processing.

The invention discloses a virtual currency wallet address anomaly detection method and system based on self-adaptive different matching message aggregation, and the method comprises the steps: firstly, processing initial transaction data, obtaining the characteristics of nodes, carrying out the data normalization, converting the original data into an original transaction graph, carrying out the random walk sampling of the original transaction graph, obtaining the training graph data of a model, and carrying out the random walk sampling of the training graph data; carrying out information transmission among the nodes by adopting a graph neural network operator of self-adaptive disparity aggregation to obtain embedded vectors of the nodes; taking the obtained embedded vector of the node as the input of a prediction model; constructing a node prediction model by adopting a plurality of linear layers, and carrying out stochastic gradient descent parameter optimization on prediction of a node category probability score and calculation of node disparity; and finally, obtaining a virtual currency wallet address anomaly detection model through training, and detecting an abnormal wallet address in the virtual currency transaction network by using the model. According to the invention, the wallet address with illegal transaction in the virtual currency transaction network can be accurately identified.

The embodiment of the invention relates to the technical field of image processing, and discloses a multi-task image enhancement method, device and equipment and a storage medium, an end-to-end network architecture is adopted to construct a multi-task image enhancement model, and the network architecture comprises a shallow layer feature extraction module and a deep layer feature extraction module; symmetrical encoder, frequency regulator and decoder structures are adopted for the deep feature extraction module, and an encoder, a frequency regulator and a decoder are designed respectively; designing a loss function; and obtaining a data set, training the multi-task image enhancement model based on the data set and the loss function, and using the obtained multi-task image enhancement model to perform image enhancement on the to-be-enhanced image. According to the scheme, various image enhancement requirements can be processed at the same time, the universality and the effect of image enhancement are improved, important features can be extracted more effectively and the image enhancement result can be optimized more effectively through the processing and attention mechanism of the frequency regulator, and the characterization capability and the generalization capability of a multi-task image enhancement model are enhanced.