103results about How to "Speed ​​up the extraction process" patented technology

The invention provides a marine environment time sequence prediction method and system based on a recurrent neural network, and relates to the technical field of time sequence prediction, and the method comprises the steps: obtaining marine environment historical observation data, carrying out the preprocessing of the marine environment historical observation data, and removing abnormal values and missing values from the marine environment historical observation data; according to the preprocessed marine environment historical observation data, a recurrent neural network model is constructed, and the recurrent neural network model comprises an input layer, two stacked long short-term memory (LSTM) network layers and an output layer; acquiring marine environment observation data at the current moment, and inputting the marine environment observation data into the trained recurrent neural network model; predicting marine environment data of a plurality of time steps in the future through a recurrent neural network model, and obtaining a marine environment prediction result in a preset time; and according to the marine environment prediction result, identifying a hot spot region of marine environment change, and generating a visual result representing a dynamic change rule of the marine environment in the prediction time period.

The invention provides an abdomen multi-organ image segmentation method fusing multi-scale features, and the method comprises the steps: S1, constructing a space detail fusion module extraction network, which comprises a space attention module, a channel attention module, an up-sampling operation, a down-sampling operation and a feature smoothing operation; s2, designing an encoder, and connecting the encoder with the space detail fusion module; s3, transmitting a plurality of features with different resolutions obtained by the encoder to a decoder through jump connection for information recovery; and S4, arranging the abdominal multi-organ medical image data set to perform model training, and performing multi-organ segmentation prediction on the abdominal multi-organ medical image. According to the method, local and global information is fully utilized, multi-scale feature information is combined, the image feature extraction and expression capability of the model is improved, and the segmentation precision of multiple organs of the abdomen is improved.

The invention relates to a corn disease intelligent grading evaluation and renovation recommendation method fusing multi-modal information, and relates to a corn diversity disease identification and multi-stage evaluation model based on position coding. The method comprises the following steps: introducing a position attention mechanism, and carrying out multi-layer stacking by taking an inverse movement residual module integrated with position coding as an element movement block; the capabilities of complex image feature extraction and spatial information analysis are enhanced, and a scab region is segmented, so that disease type distinguishing and severity evaluation are realized; constructing a model based on a corn disease entity relationship triple library: performing deep context coding on a corn disease text, realizing classification and prediction of complex relationships among disease entities through a multi-layer structure, and analyzing complex links and influence factors among diseases; and a corn disease treatment method recommendation model combined with an implicit relationship: according to a disease identification and grading result and a disease triple, mining an optimal implicit relationship among different disease entities through complex number embedding and a graph neural network, and giving an accurate disease treatment method recommendation.

The invention discloses a rotary machine fault diagnosis method based on residual contraction convolution and an attention mechanism, and belongs to the field of rotary machine fault diagnosis. According to the method, firstly, a soft threshold filtering activation function is designed based on Meta-ACON, a soft threshold filtering module is developed around the activation function, and the module can adaptively learn a filtering threshold and a forward dynamic weighting coefficient, so that irrelevant features are effectively filtered, and the expression ability of effective features is enhanced. And then, in combination with multi-channel and multi-scale residual convolution, a multi-channel residual shrinkage convolution unit is constructed to realize multi-scale and multi-channel effective feature extraction. Besides, according to the method, a high-order statistical modeling idea is utilized, a GSoP attention mechanism is introduced behind a multi-channel residual shrinkage convolution unit, and the ability of extracting discriminative features is enhanced through second-order statistical information of a high-level channel feature map. Test results show that the method has good fault identification capability and generalization capability.

The invention discloses a back contact solar cell, an assembly and a system. The back contact solar cell comprises a silicon substrate, the back surface of the silicon substrate comprises a plurality of first areas and a plurality of second areas, the first areas and the second areas are arranged at intervals, and each of the first areas and the second areas comprises a passivation selective contact area and a non-passivation selective contact area; the non-passivation selective contact area comprises a passivation anti-reflection layer arranged on the surface of the silicon substrate; the passivation selective contact area of the first area comprises a first passivation layer, a selective transmission layer and a first metal electrode which are sequentially stacked on the surface of the silicon substrate from inside to outside. According to the back contact solar cell, the passivation layer and the selective transmission layer are arranged in the first region and combined with the passivation anti-reflection layer, the excellent passivation contact effect is achieved, a narrow-band-gap highly-doped silicon material does not need to be used, the optical parasitic absorption loss is reduced, the photoelectric conversion efficiency is improved, and then the performance of the back contact solar cell is improved.

The invention relates to integrated airborne communication antenna equipment and a communication method. The method comprises the following steps: carrying out CSI data acquisition and space-time focus modulation on a communication channel to obtain CSI space-time characteristic data; performing residual vector quantization operation to generate a quantized data stream, and performing recursive coding processing to obtain a target data stream; mapping the target data stream to a three-dimensional tensor space, constructing a real value tensor model, and performing iterative operation to obtain a CSI feature vector; performing fractional order wavelet transform decomposition on the CSI feature vector to obtain a radio frequency feature set, and inputting the radio frequency feature set into a federal fractional scattering network for feature processing to obtain an identity authentication result; and calculating an amplitude-phase weight coefficient of the antenna array, generating a beam parameter, and performing compensation matrix operation on the beam parameter according to the CSI feature vector to obtain a pre-coded signal. According to the invention, the dynamic adjustment of the antenna beam parameters is realized, and the accuracy and anti-interference capability of beam forming are improved.

The invention discloses an indoor point cloud semantic segmentation method based on self-adaption and multi-scale feature fusion. The indoor point cloud semantic segmentation method comprises the steps of indoor point cloud preprocessing, construction of an indoor point cloud semantic segmentation network, training of the indoor point cloud semantic segmentation network and testing of the indoor point cloud semantic segmentation network. A self-adaptive local neighborhood search module is adopted to construct a graph structure of indoor point cloud, and the problem that local details are lost due to the fixed neighborhood radius in an existing method is solved; a context perception attention convolution module and a graph space attention convolution module are adopted to obtain key context semantic features and complex space geometric features between the points respectively; indoor point cloud spatial pyramid pooling is introduced into a multi-scale feature fusion module based on double attention, multi-level features obtained by different receptive fields are combined, and the ability of the whole network to extract and express features of different scales is enhanced. Comparison experiments show that the method can accurately identify semantic categories of a few samples and easily-confused building structures in a complex indoor environment.

The invention discloses a real-time face change detection method, system and device based on deep learning and a medium. The method comprises the following steps: acquiring a key frame image sequence in a video stream in real time; processing the key frame image sequence according to a preset deep learning model to obtain a face change probability score of each key frame image; processing the key frame image sequence according to a preset frequency domain analysis algorithm to obtain a frequency domain anomaly score of each key frame image; processing the key frame image sequence according to a preset optical flow analysis algorithm to obtain a motion coherence score of each adjacent key frame image; and according to a preset multi-modal fusion algorithm, processing the face change probability score, the frequency domain anomaly score and the motion coherence score to obtain a face change detection result of the key frame image sequence. According to the method, the efficiency of real-time dynamic face change detection is improved by combining fusion of various processing algorithms.

The invention discloses an extended-period rainfall continuous distribution probability forecasting method fusing fine topographic features, and the method comprises the steps: obtaining the multi-member multi-element forecasting data of a standardized extended-period numerical mode ensemble forecasting system and regional historical long-time sequence rainfall observation data, and extracting historical rainfall continuous distribution features; based on regional high-resolution fine terrain data, a descaled key terrain multi-dimensional feature factor library is obtained; constructing a rainfall probability forecasting model based on limit gradient lifting U-Net mixed deep learning, and carrying out model training and optimization; and generating an improved extension period rainfall continuous distribution probability forecast result by adopting the trained model. According to the method, fine topographic data are fused, the weighted cross entropy loss function is adopted, the problem of rainfall distribution category imbalance is effectively solved, the generalization ability of the model is improved, the forecasting performance of rainfall continuous distribution probability forecasting is improved, and the method has extremely high application value.

The invention discloses a small target detection method for early-stage oil leakage of a transformer based on cavity convolution, and belongs to the technical field of computer vision and target detection. A detection model optimizes a backbone network and a head network of an original YOLOv8 model, and adds a feature enhancement module to the backbone network of the original YOLOv8 model; multiple pieces of discriminative semantic information are extracted by using a multi-branch structure, and the calculated amount is not increased and the context information in a larger range can be obtained by introducing hole convolution into branches; a feature fusion module of the head network adopts an improved feature fusion module, and the weights of channel features are adaptively adjusted by introducing learnable weight parameters; a normalized attention mechanism module is added to a head network, and weighted output of a channel is achieved in a residual connection mode. Compared with a traditional transformer early leakage detection means, the method has the advantages that the extraction and expression ability of effective features is enhanced, and high transformer early leakage oil detection accuracy can be obtained.

The invention provides an image processing method and system based on a neural network, a storage medium and electronic equipment, and relates to the technical field of neural networks, and the method comprises the steps: obtaining an initial tensor of a to-be-optimized feature image; in the first path, based on the initial tensor, performing convolution extraction to obtain a first tensor containing a channel dimension attention weight factor; in the second path, after the space dimension is converted into the channel dimension based on the initial tensor, a second tensor containing a space attention weight factor is obtained through convolution extraction; obtaining an attention weight matrix based on the first tensor and the second tensor; and based on the initial tensor and the attention weight matrix, obtaining the tensor of the feature image after attention enhancement. According to the method, the problem of insufficient global information extraction capability of the convolutional neural network is solved, pixel-level channel and spatial dimension attention modeling can be performed on the tensor of the feature image, and the correlation extraction and modeling capability of the convolutional neural network on the image features under a large scale is effectively improved.

The invention provides a continuous gravity detection method, medium and system based on a seabed crawler, and belongs to the technical field of geophysics, and the method comprises the steps: employing the seabed crawler provided with an absolute gravimeter and a relative gravimeter, and carrying out the grid detection of a to-be-detected region. The method comprises the following steps: firstly, acquiring relative gravity data of a central point of each grid unit, and establishing a relative gravity matrix; then, determining an abnormal point, a boundary point and a transition point of the relative gravity data by using a Bayesian probability model and a Markov chain Monte Carlo method; clustering the feature points to obtain a plurality of clustering centers and flying spots; and then, controlling a traversal path of the seabed crawler along the clustering center and the flying spot to obtain absolute gravity data. And finally, in combination with the relative gravity matrix, calculating an absolute gravity matrix of the whole to-be-detected area by using a Kriging interpolation method as a gravity detection result, and solving the technical problem that the detection of seabed high-precision gravity data is difficult to realize in the prior art.

The invention discloses a special-shaped copper strip defect real-time detection method and system, terminal equipment and a storage medium, and relates to the technical field of target detection. The method comprises the following steps: receiving special-shaped copper strip pictures, constructing an image data set, carrying out picture preprocessing, and dividing the preprocessed pictures into a training set, a verification set and a test set; a special-shaped copper strip defect detection model based on a YOLOv8 network structure is constructed, and the special-shaped copper strip defect detection model adopts an adaptive spatial feature fusion module to replace an original Head structure, adopts a slip-check module to replace an original Neck structure, and adopts an inner-SIoU loss function to replace an original CIoU loss function. According to the method, the performance is remarkably improved in the surface defect detection task of the special-shaped copper strip, high detection precision is achieved, superiority is shown in the model detection speed, the requirement for real-time detection is met, the accuracy and effectiveness of defect detection of the special-shaped copper strip are improved, and the detection efficiency is improved. Therefore, powerful support is provided for sustainable development of the copper processing industry.

The invention discloses a high-definition map processing method and device based on mobile laser radar data, and the method comprises the steps: obtaining sensor data collected by a plurality of sensors of an autonomous vehicle, carrying out the probability data processing, obtaining a structured 3D point cloud, carrying out the recognition of the 3D point cloud, distributing a semantic tag, and creating a geometric mapping function; the method comprises the following steps: constructing a 3D point cloud image, converting local Euclidean coordinates by adopting a geometric mapping function to obtain a semantic segmentation result, classifying and correcting the semantic segmentation result by adopting a confusion network to obtain object attributes, constructing a semantic graph of the 3D point cloud image based on the object attributes and the geometric mapping function, and outputting a high-definition map corresponding to the semantic graph. According to the method, the high-definition map is evaluated and optimized to obtain a path navigation result of the autonomous vehicle, multi-target optimization is applied to processing the mobile laser radar point cloud to create the high-definition map, a confusion matrix is used to merge uncertainty simulation and probability semantic mapping, and the reliability and accuracy of map generation are improved.

The invention discloses a lightweight multi-scale biomedical image segmentation method, and relates to the technical field of medical image processing, and the method comprises the steps: collecting and obtaining a reference position medical image for a target operation task; performing feature importance and feature dominance analysis in combination with key texture feature information of a target operation, and calibrating a datum positioning reference point; real-time image tracking segmentation is carried out, rapid positioning alignment and multi-scale feature extraction are carried out on continuous medical images, and a multi-scale feature map is generated; introducing a feature fusion mechanism, and performing layer-by-layer fusion on the multi-scale feature map to obtain a fused feature map; and obtaining an image segmentation result. The technical problems that existing biomedical image segmentation is difficult to adapt to complex and diversified image segmentation tasks, so that the image segmentation precision is low, and the reliability and safety of surgical navigation are reduced are solved, high-precision image segmentation is realized, and the technical effect of improving the reliability and safety of surgery is achieved.

The invention discloses a novel passivation selective contact structure, a solar cell, an assembly and a system. The novel passivation selective contact structure comprises a silicon substrate, wherein the surface of the silicon substrate comprises a passivation selective contact area and a non-passivation selective contact area; the non-passivation selective contact area comprises a passivation anti-reflection layer arranged on the surface of the silicon substrate; the passivation selective contact area comprises a passivation layer, a selective transmission layer and a metal electrode which are sequentially stacked from inside to outside, the passivation layer covers a partial area of the surface of the silicon substrate, and the projection of the selective transmission layer on the surface of the silicon substrate covers a partial area of the surface of the silicon substrate. According to the invention, the passivation anti-reflection layer, the selective transmission layer and the passivation layer act synergistically, so that an excellent passivation contact effect is realized; and a narrow-band-gap highly-doped silicon material does not need to be used, so that the optical parasitic absorption loss is reduced, the photoelectric conversion efficiency is improved, and the performance of the solar cell is further improved.

The invention relates to the technical field of cloud edge collaboration, in particular to an edge computing cloud edge collaboration method, system and device, and the method comprises the steps: obtaining a real-time monitoring video shot by each AI camera in a single target area, dividing the real-time monitoring video into an effective video segment and an invalid video segment, the effective video segment is divided into a dominant clear frame group and a hidden clear frame group according to the definition, a method for obtaining target information is determined according to the type of the clear frame group, the edge filtering module receives the target information of the dominant clear frame group and the clear enhanced frame group, all the target information of the single effective video segment is determined according to the time sequence relation, and the target information is obtained. And filtering to generate effective target information, and determining traffic information of each time period according to the effective target information. According to the method and the system, the dependence on cloud resources is reduced through a processing mode of cloud edge collaboration and cloud centralization removal, and the optimal configuration of the resources is realized.

The embodiment of the invention provides a data classification method and a work order classification method.The data classification method comprises the steps that a target data feature information set corresponding to a to-be-classified data set is obtained, and target data feature information in the target data feature information set has the same dimension; generating data distance information corresponding to the to-be-classified data set based on the target data feature information set; and determining at least one similar data set and a similar data abstract corresponding to each similar data set according to the data distance information. By extracting the target data feature information and generating the data distance information, the classification problem between the data sets is effectively solved. Through unified feature input, data distance information is generated and similar data abstracts are extracted, so that the processing bottleneck of a traditional model on mass data is broken through, and the data processing efficiency is improved under the condition that the accuracy rate is guaranteed when the mass data is processed.

The invention relates to the technical field of data analysis, in particular to a big data information analysis method and system based on cloud computing, and the method comprises the following steps: recognizing video data and extracting image information in a video based on input processing data, recognizing key content of the input video data in combination with voice recognition, and generating an audio-visual data analysis result. According to the invention, through processing of the video image information and analysis of the text data, the capability of extracting and utilizing key information from multi-source data is improved, abnormal data identification is carried out according to the data type and the application scene, detection and identification of abnormal data are realized, the risk of wrong decision making is reduced, and the accuracy of abnormal data identification is improved. According to the method, time sequence analysis of various input data is combined, the depth of data analysis is optimized, the capability of predicting the data trend is provided, the capability of market trend analysis and user behavior prediction is improved, and efficient execution of data processing tasks is ensured and the efficiency of input data analysis is improved by dynamically adjusting cloud computing resources.

The invention belongs to the technical field of bioinformatics, and particularly relates to a single-cell multi-omics data clustering framework based on deep collaborative contrast learning. According to the framework, the association relationship between cells is fully utilized, and meanwhile, the feature interaction of the same cell between different omics data is further enhanced, so that efficient clustering of multiple omics data is realized. In order to make full use of topological information between cells, a graph self-encoder and a feature information enhancement module under different omics are designed, and extraction and information enhancement of cell features are achieved. Meanwhile, a comparative learning technology is introduced to enhance interaction among different omics characteristics of the same cell, and finally single-cell multi-omics clustering is realized through a multi-omics deep collaborative clustering module.

The invention discloses a perovskite solar cell and a preparation method thereof, and a photovoltaic module, the perovskite solar cell comprises a substrate, a hole extraction layer, a perovskite layer, an electron transport layer and a first electrode which are sequentially laminated, the material of the hole extraction layer comprises R-2Ph-xPACz, and the structure of R-2Ph-xPACz is shown as a formula 1: # imgabs0 #, r is any one of CH3CH2O, CH3O, (CH3) 3C or a heterocyclic ring containing lone pair electrons, and x is 2-10. The R-2Ph-xPACz disclosed by the invention is relatively good in hole extraction and transmission effect and excellent in spreading uniformity, and the energy conversion efficiency of the solar cell can be further improved.

The invention relates to the technical field of intelligent traffic information, in particular to an intersection lane-level topology detection method, device and equipment based on trajectory data, and the method comprises the steps: obtaining the trajectory data in an intersection; extracting shape features, direction features and relation features among the tracks in the track data; and constructing a trajectory relationship graph according to the shape features, the direction features and the relationship features among the trajectories, inputting the trajectory relationship graph into a graph neural network architecture, and outputting a lane-level intersection topology by the graph neural network architecture. Therefore, the problems of high data source acquisition cost, high data processing complexity, insufficient algorithm precision and robustness, real-time dynamic update challenge and the like in the prior art are solved.

The invention discloses a deep forged audio identification method based on hybrid enhancement and a contrast loss function. The method comprises the following steps: step 1, preprocessing an original audio training data set by using a sliding window technology and a hybrid enhancement technology; step 2, for the preprocessed original audio training data set, using a contrast loss function to constrain and forge feature vector spacing of real audio training data in a high-dimensional space; and step 3, using a sliding window to divide the audio to be detected into a plurality of audio clips to be detected with the total length of 64600, and if any audio clip to be detected is detected to be forged, determining that the audio to be detected is forged. According to the method, the analysis and identification capability of the algorithm on weak and local counterfeit traces is improved, the accuracy, stability and generalization of the deep counterfeit audio identification algorithm are ensured, the extraction and analysis capability of the algorithm on essential counterfeit traces is improved, and the interference of environmental noise is reduced.

The invention relates to an intrusion object detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring to-be-detected image data; performing multi-scale feature extraction on the to-be-detected image data by adopting a mixed attention mechanism through a multi-scale feature extraction layer to obtain a plurality of image data intermediate features of different scales; performing multi-direction expansion convolution processing on each image data intermediate feature through a feature enhancement layer to obtain a plurality of image data enhancement features of different scales; and through a detection layer, feature fusion is carried out on the image data enhancement features to obtain multi-scale fusion features, and intrusion object detection is carried out based on the multi-scale fusion features. By adopting the method, the false detection rate of intrusion detection of small-size intrusion objects can be reduced.

The invention relates to the technical field of big data processing and information analysis, in particular to an information analysis method based on a big data processing framework, which constructs a domain-specific knowledge graph by introducing domain expert knowledge and literature data, and constructs a graph convolutional neural network model based on the knowledge graph. Semantic analysis and relation reasoning are carried out on the unstructured data, an association rule algorithm is utilized, modes and rules among the data are found, a more valuable association analysis result is generated, and the problem that when an existing information analysis technology is used for processing the multi-source heterogeneous unstructured data, the data processing efficiency is high is solved. The problems of difficulty in data fusion, insufficient semantic understanding and insufficient relationship mining depth exist.

The present invention discloses a method for forecasting the continuous distribution probability of extended-period precipitation by integrating fine terrain features, including: obtaining standardized multi-member multi-factor forecast data of the extended-period numerical model ensemble forecast system and regional historical long-term series precipitation observation data, and extracting the continuous distribution characteristics of historical precipitation; obtaining a descaled key terrain multidimensional feature factor library based on regional high-resolution fine terrain data; constructing an extreme gradient boosting U-Net hybrid deep learning precipitation probability forecast model, and carrying out model training and optimization; using the trained model to generate an improved forecast result of the continuous distribution probability of extended-period precipitation. The present invention integrates fine terrain data, adopts a weighted cross entropy loss function, effectively handles the problem of imbalanced precipitation distribution categories, improves the generalization ability of the model, and improves the forecast performance of the continuous distribution probability forecast of precipitation, which has extremely high application value.

The present invention discloses a multi-operation computing device courseware processing method and device, belonging to the technical field of electronic whiteboard computing devices, comprising the following steps: step 1, reading all current canvases at a predetermined time, obtaining each element in the canvas; step 2, identifying and determining the element type of the element, and judging the identified element type; step 3, for each element, based on the priority relationship between the preset element type and the computing device, obtaining the computing device corresponding to the current element; processing the element through the computing device; step 4, writing and saving other attribute contents of the element. The present invention improves the extraction speed and presentation efficiency of elements through dual computing devices, and improves the use efficiency of electronic whiteboard interactive software.

The application relates to the technical field of electronic reconnaissance and signal processing, and discloses a radiation source individual fine identification method and system based on multi-modal feature fusion, which comprises the following steps: performing preprocessing on obtained radiation source original signals to obtain signal pulse units; extracting time domain sequences of the signal pulse units and performing multi-domain transformation to generate a first time-frequency image, a second time-frequency image and a bispectrum image; inputting the first time-frequency image, the second time-frequency image, the bispectrum image and the time domain sequence into a multi-modal fusion neural network; extracting corresponding image depth features and comprehensive sequence features through three image processing branches and a sequence processing branch; performing cross-modal fusion on the three image depth features and the comprehensive sequence features through a fusion module to output a radiation source individual identification result. The application improves the identification accuracy of radiation source individuals in a complex electromagnetic environment.

The present invention provides a continuous gravity detection method, medium and system based on a seafloor crawler, which belongs to the field of geophysical technology, and includes: using a seafloor crawler equipped with an absolute gravimeter and a relative gravimeter to perform grid detection of a test area. First, the relative gravity data of the center point of each grid unit is obtained to establish a relative gravity matrix. Then, the Bayesian probability model and the Markov chain Monte Carlo method are used to determine the abnormal points, boundary points and transition points of the relative gravity data. These feature points are clustered to obtain multiple cluster centers and flying points. Next, the seafloor crawler is controlled to traverse the path of the cluster centers and flying points to obtain absolute gravity data. Finally, in combination with the relative gravity matrix, the Kriging interpolation method is used to calculate the absolute gravity matrix of the entire test area as the gravity detection result. The present invention solves the technical problem that the prior art is difficult to achieve the detection of high-precision seafloor gravity data.

The invention relates to the technical field of power grid operation and maintenance, and discloses an insulator defect detection method and system based on 3D attention focusing and pure convolution, by introducing a 3D attention mechanism and pure convolution, the model can enhance the extraction and focusing capability of insulator defect features, and reduce the interference of irrelevant background features; besides, through an improved mixed spatial pyramid pooling module and a lightweight upsampling operator, more detail information can be reserved, and the detection precision of a small defect target is remarkably improved; the technical innovation ensures that the model can realize high-precision and real-time insulator defect detection in a complex environment, and provides powerful guarantee for stable operation of a power system.