35results about How to "Rich learning" patented technology

The invention discloses an automatic fine ore sorting method and system based on XRT (X ray tomography) and hyperspectrum, which are used for realizing comprehensive fusion of ore surface and internal information by combining X-ray tomography and hyperspectral imaging technologies so as to improve the recognition precision and the sorting efficiency. XRT is used for extracting the internal structure and density characteristics of the ore, hyperspectral imaging is used for identifying the mineral composition characteristics of the ore surface, and information complementation is achieved. The system adopts a multi-modal convolutional neural network to perform independent feature extraction on XRT and hyperspectral data, and the extracted features are fused through a deep residual network. And the fused features are processed by a cross-modal attention mechanism to ensure that key features of different modals are fully integrated and optimized, and finally high-precision ore classification and sorting are realized. According to the method, the limitation of a single data source on feature extraction is overcome, the ore recognition and sorting precision is greatly improved, and the refined and intelligent development of ore sorting is promoted.

The invention discloses an operation site safety management and control method and system based on a multi-modal large model, and the method comprises the steps: collecting site violation data, and carrying out the preprocessing, and obtaining multi-modal data; constructing a multi-modal large model; carrying out training and optimization on the multi-modal large model by utilizing the preprocessed multi-modal data; and using the optimized multi-modal large model to realize operation site safety management and control. According to the invention, a visible light image, a safety violation knowledge base and other modal data are fused, and a comprehensive safety monitoring and management platform is constructed by using a large model and a big data processing technology, so that real-time monitoring, early warning and intelligent response of potential safety hazards of a complex operation site are realized, and the safety management level of the operation site is improved.

The invention relates to the technical field of transformer detection, in particular to a millimeter wave radar-based transformer vibration anomaly detection method, which comprises the following steps of: acquiring an original reflection signal on the surface of a transformer, performing time domain and frequency domain analysis on the original reflection signal, and constructing a vibration feature vector; based on the constructed vibration feature vector, unsupervised learning is carried out on the vibration mode of the normal transformer through a deep self-encoding network, and potential features of the normal vibration mode are automatically learned; converting the new reflected signal into a new vibration feature vector, reconstructing the new vibration feature vector by using a deep self-encoding network, calculating a reconstruction error, and if the reconstruction error exceeds a predetermined threshold, judging that the vibration mode is an abnormal vibration mode; a self-adaptive threshold strategy is adopted, and a preset threshold is automatically adjusted so as to adapt to the change of the operation states of different transformer devices along with time. According to the invention, a self-adaptive threshold strategy is introduced, so that running characteristics of different transformer devices and fluctuation of an external environment can be adapted in real time.

The invention discloses a PVA film gas permeability intelligent detection method based on machine learning, and relates to the technical field of material testing. The method comprises the following steps: acquiring experimental environment data, first detection data, first diffusion theory characteristic data and second detection data, and constructing and training a neural network model; setting application environment parameters, obtaining third detection data, and calculating second diffusion theory characteristic data according to the application environment parameters and the third detection data; and inputting the application environment parameters, the third detection data and the second diffusion theory characteristic data into a neural network model to obtain a gas permeability prediction value. According to the method, the neural network model is constructed and trained, and the gas permeability is predicted through the neural network model, the application environment parameters, the third detection data and the second diffusion theory characteristic data, so that the dependence on a differential pressure method gas permeability experiment is reduced, the time cost of material testing and experiment is reduced, and the test efficiency is improved. And meanwhile, online monitoring and adjustment of the production process are facilitated, and production benefits are improved.

The invention relates to the medical instrument technology, and discloses an ultrasonic intervention automatic puncture surgical robot and a control method, and the ultrasonic intervention automatic puncture surgical robot comprises a needle feeding mechanism, a rotating mechanism, a probe clamping mechanism, a depth control mechanism and a force sensor mechanism; wherein the probe feeding mechanism is connected with the depth control mechanism through the rotating mechanism, the depth control mechanism is connected with the back surface of a main body substrate of the probe clamping mechanism, the front surface of the main body substrate is provided with a clamping piece of an ultrasonic probe, and the main body substrate is also fixedly provided with the force sensor mechanism; the rotating mechanism is used for adjusting the needle inserting angle of the needle inserting mechanism; the depth control mechanism is used for controlling the needle feeding mechanism to move in the vertical direction; a puncture needle which advances and retreats in a linear motion manner is arranged in the needle feeding mechanism, and the puncture needle is arranged on the coronal plane of the ultrasonic probe; the force sensor mechanism is used for measuring the force applied to the human tissue by the puncture needle. The invention aims to realize automation, precision and safety of the puncture operation and reduce the workload of doctors.

The invention relates to the technical field of vulnerability detection, in particular to a vulnerability detection method based on a pre-training code language model and a convolutional neural network, and the method comprises the following steps: S1, obtaining a vulnerability data set, preprocessing the vulnerability data set, and constructing a model training data set; s2, acquiring a data propagation chain and a code token sequence according to the source code of the model training data set, and embedding the data propagation chain and the token sequence to obtain an embedded vector corresponding to the source code; s3, constructing a vulnerability detection model, and training the vulnerability detection model to obtain a trained vulnerability detection model; and S4, outputting whether the source code to be detected has vulnerabilities or not through the trained vulnerability detection model. According to the method, the vulnerability detection model based on the pre-training code language model and the convolutional neural network is constructed, the data propagation chain and the code token sequence are adopted as model input, semantic information and structural information of source codes can be learned, key vulnerability features can be captured, and the vulnerability detection accuracy and effectiveness are improved.

The invention relates to a tongue feature analysis method and device, electronic equipment and a storage medium. A trained tongue detection model and a trained tongue segmentation model are fused to obtain a target segmentation model, an image data set is segmented through the target segmentation model to obtain a tongue segmentation image data set, and the tongue segmentation image data set is labeled to obtain a tongue feature classification data set. Training a tongue feature classification model based on the tongue feature classification data set to obtain a trained tongue feature classification model, obtaining to-be-detected target image data, inputting the target image data into a target segmentation model to obtain tongue segmentation image data of the to-be-detected target image data, and obtaining the tongue segmentation image data of the to-be-detected target image data. According to the method, the trained tongue feature classification model is used for performing feature analysis on the tongue segmentation image data to obtain a tongue feature analysis result, so that the training efficiency of the model is improved, and the classification stability and reliability are also remarkably improved.

The invention discloses a lightweight multi-stage point cloud classification method based on a fusion Transform network. The lightweight multi-stage point cloud classification method comprises the steps of original point embedding module construction, local feature extraction, global feature aggregation and multi-stage learning. The network is composed of an efficient feature aggregation branch and a Transform branch, the efficient feature aggregation branch is provided with a learnable position code, and position information which is often neglected by most point cloud classification networks can be fully captured. Sampling points with similar characteristics are clustered by the Transform branch, so that the balance between capturing long-range dependence and calculation complexity is realized. Meanwhile, an extrusion-excitation module is introduced into original point embedding, so that representation of point cloud features is enhanced, and subsequent point cloud learning performance is improved. And a four-stage learning strategy is adopted, so that the understanding capability of the network on the point cloud is effectively enhanced. A large number of experiments prove that excellent classification performance can be achieved while the number of parameters is kept low.

The invention discloses an image classification method based on deep learning multi-scale feature fusion, which utilizes a deep learning multi-scale feature fusion method to improve the accuracy of image classification by combining self-calibration convolution, an attention module and a feature adjustment module. Firstly, feature extraction is carried out on an image through the self-calibration convolution module, then the attention module enhances the features, important areas in the image are highlighted, and finally the feature adjustment module adjusts the enhanced features to improve the expressive power of the features. Besides, through multi-time iteration enhancement and adjustment and adoption of various loss function optimization features, complex image data can be processed and classified more accurately, and the method is suitable for various application scenes requiring high classification precision. Compared with existing methods such as ResNet and Vision Transformer, the method has the advantages that the loss value is lower, the classification accuracy is higher, and excellent performance and wide application prospects are shown in the field of image classification.

The invention discloses a neural tensor ring fusion method for traffic flow data completion, which belongs to the field of traffic data completion, and comprises the following steps: step 1, acquiring traffic flow data in a road network system, and modeling the traffic flow data into a third-order tensor; 2, constructing an objective function of a neural tensor ring fusion model by referring to a tensor ring decomposition thought; and step 3, traffic flow data completion is carried out based on the neural tensor ring fusion model. According to the method, a neural tensor ring fusion model is constructed by adopting a tensor ring decomposition thought, potential features of data are learned by adopting a three-order factor tensor form, and the structure and information of original data can be better stored while high-order data tensor is expressed and processed; meanwhile, multi-dimensional interaction of traffic data in time is captured by adopting a convolutional long-short-term memory network, and missing data are complemented together by using a plurality of matrixes containing historical time characteristics.

The invention relates to a semi-supervised SAR target identification method and system based on contour enhancement and cooperative training. Specifically, according to the method, a to-be-recognized SAR image is input into a trained target recognition model to generate a corresponding target prediction result. The training process is divided into two stages: in the first stage, contour extraction and enhancement processing are carried out on an SAR image sample without a label, and then semi-supervised learning is carried out by using a FixMatch framework; and in the second stage, the weak augmented images of the label samples in the first stage are input into the cooperative training network for training, judgment results of different rounds are summarized, and the reliability of each judgment result is judged through an entropy value. The common judgment results of the cooperative training network form a sampling pool, a certain number of high-confidence samples are extracted from the sampling pool to serve as pseudo-label samples to expand a label training set of the first stage, and then the expanded label training set is used for continuing to train FixMatch. According to the method, the accuracy, the reliability and the robustness of SAR target recognition are remarkably improved.

The invention discloses an unmanned aerial vehicle game decision-making system based on anomaly detection. The unmanned aerial vehicle game decision-making system comprises an unmanned aerial vehicle sensor database, an upper computer and a sensor real-time data receiver, the unmanned aerial vehicle sensor database and the sensor real-time data receiver are respectively connected with the upper computer; the upper computer comprises a data preprocessing module, a pre-training module and an anomaly detection module. And the unmanned aerial vehicle sensor database stores the unmanned aerial vehicle flight state data accumulated in the historical flight process. The sensor real-time data receiver collects real-time state data of the unmanned aerial vehicle in the flight process and transmits the real-time state data to the unmanned aerial vehicle anomaly detection module of the upper computer for anomaly detection. The upper computer comprises a data preprocessing module, a pre-training module and an anomaly detection module, data transmitted by the database and the receiver are preprocessed, adversarial pre-training is carried out by using normal data in the database, and a trained model is used for carrying out anomaly detection on real-time data of the receiver. According to the method, the antagonism training framework anomaly detection model is innovatively introduced to fully learn the intrinsic characteristics of normal data, the difference between the normal data and the abnormal data is enhanced, the problem that a traditional anomaly detection system cannot completely recognize tiny anomalies is solved, and the anomaly detection precision of the unmanned aerial vehicle is remarkably improved.

The invention provides a construction method, system, equipment, medium and program product of a traditional Chinese medicine origin traceability model fusing element fingerprints and secondary metabolite outlines, and correspondingly provides a traditional Chinese medicine origin traceability method, equipment, medium and program product based on the model. Relates to the field of medicinal material identification. According to the method, element fingerprints and chemical component profiles are fused according to metallomics and metabonomics, and an element fingerprint substance and secondary metabolite profile substance combined recognition mode is innovatively put forward and is used for geographical source recognition of traditional Chinese medicine with radix peucedani as a mode. And an aggregation model is innovatively adopted, and respective optimal models of elements and chemical components are further integrated, so that the classification precision is improved, and the scientificity and accuracy of traditional Chinese medicine quality evaluation are remarkably improved.

The invention relates to a language learning system, which comprises a learning system, a video player and a foreign language video material, and is characterized in that the output end of the learning system is electrically connected with the video player, and the foreign language video material is in data connection with the learning system and the video player through a data memory. By adopting the translation algorithm module and the subtitle display module, an English learning program is highly simplified, English learning becomes closer to a native language learning process, information of a foreign language video material is decomposed, extracted, translated and combined, a learner can comprehensively and accurately learn the foreign language video material, and meanwhile, the learning efficiency is improved. The translated subtitle information is transmitted to the video player in real time to be displayed, so that a learner can view the translated subtitle information while watching the video, and the learning efficiency and effect are improved.

The invention provides a power equipment defect identification method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a to-be-identified defect text of target equipment into a pre-constructed text extraction model, and converting the to-be-identified defect text into an initial word vector by an input layer; the transform coding layer calculates a semantic relationship between each initial word vector and a context thereof based on a multi-head attention mechanism, and updates the initial word vectors to obtain intermediate word vectors containing semantic information; the BI-LSTM output layer performs bidirectional semantic extraction on the context semantic information of the intermediate word vector to obtain a target word vector containing the bidirectional semantic information; and inputting the target word vector and the power equipment information into a pre-constructed equipment defect identification model, constructing a relation topological graph between the target word vector and the power equipment information, and performing defect classification based on the relation topological graph. According to the invention, the defect identification accuracy is improved.

Methods, systems and apparatus for compressing and decompressing data, including computer programs encoded on computer storage media. In one aspect, a method includes: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a super encoder neural network to generate a latent representation of an entropy model; generating an entropy coded representation of the latent representation of the entropy model; generating an entropy coded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy coded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.

The present invention relates to the field of navigation information technology, and in particular to a Beidou navigation device cluster timing method. The method comprises the following steps: starting a navigation device in a Beidou navigation device cluster, placing it in a standby state, and detecting a spread spectrum signal to determine whether a timing broadcast signal exists; if a spread spectrum signal is detected, controlling the navigation device to capture the spread spectrum signal to obtain the spread spectrum signal; demodulating the spread spectrum signal to obtain the signal content, wherein the signal content includes timing information and telegram content; extracting time information from the signal content to obtain time information, and performing time synchronization operations on each navigation device in the Beidou navigation device cluster according to the time information. Based on the high-precision ranging characteristics of the spread spectrum signal and utilizing the spread spectrum signal processing capability of the existing navigation receiver, the present invention provides a safe, reliable, higher-precision solution that is fully compatible with the existing Beidou navigation receiver hardware and software.

The invention discloses a heart electrophysiological analysis method, system and device and a storage medium. The method comprises the following steps: acquiring electrocardiogram data, cardiac ultrasound image data and clinical index data, and preprocessing the acquired data; extracting features of the preprocessed electrocardiogram data, the preprocessed cardiac ultrasound image data and the preprocessed clinical index data; fusing the features of the electrocardiogram data, the cardiac ultrasound image data and the clinical index data to realize interaction of different modal information and generate fused features; decoding the fusion feature into fusion output data; and analyzing the cardiac electrophysiological performance based on the fused output data. According to the method, massive heart electrophysiological data can be learned, and then the heart electrophysiological performance is accurately analyzed; and by designing an interpretability module, key features can be highlighted, an analysis and interpretation report of a visual source is generated, a reliable basis is provided for clinical decision making of doctors, and the credibility and acceptability of the doctors are improved.

A multimodal knowledge graph completion method based on neighborhood semantic enhancement belongs to the field of multimodal knowledge graphs. Specifically, a neighborhood semantic enhancement module is first designed to fuse different neighborhood information into the representation of the central entity to enhance the semantic expression ability of the model. Then, the cross-modal attention mechanism is used to capture the interaction and common semantic features of information between different modalities to achieve the learning of neighborhood-guided features. Then, based on the contrastive learning method, the similarities and differences between positive and negative samples are compared to learn richer entity representations, and finally improve the multimodal knowledge graph completion results.

The invention relates to the technical field of artificial intelligence optimization operation systems, and particularly discloses a sequence recommendation method based on adaptive global graph modeling and intention contrast learning, the method comprises the steps of sequence global graph construction, module output fusion, sequence recommendation learning and recommendation result optimization, and the method comprises the steps of firstly obtaining a user historical behavior sequence; the method comprises the following steps: constructing an association graph, improving and optimizing the association graph to obtain and record a user behavior sequence global graph, and respectively injecting the user behavior sequence global graph into a local module and a global module of a sequence encoder, so that the outputs of the local module and the global module are fused, and the sequence encoder can comprehensively learn intentions with more expressive power, so as to carry out intention contrast learning; according to the method, the sequence recommendation of the user is comprehensively obtained, the user is predicted, the sequence recommendation of adaptive global graph modeling and intention contrast learning is completed, the recommendation effect under the noise condition and the data sparse condition is improved, the user experience is improved, and the robustness and generalization ability of the sequence recommendation method are enhanced in multiple dimensions.

The invention discloses a small sample bearing fault diagnosis method based on hierarchical contrast learning optimization, and relates to the technical field of fault diagnosis. The method comprises the following steps: collecting bearing vibration signals of different fault types through a sensor, extracting samples according to the length N of the signals, and obtaining time-frequency domain characteristics of the signals by using short-time Fourier transform; designing a hierarchical contrast learning module and a parallel attention fusion module, introducing a stacking activation function and a Brownian distance covariance measurement method, and constructing a small sample bearing fault diagnosis model (CMBDC) based on hierarchical contrast learning optimization; inputting training set data into the CMBDC model, calculating a gradient by using a back propagation algorithm, and continuously optimizing network parameters through a plurality of training iteration cycles to obtain a final model; inputting test set data into the trained model to obtain a prediction result of the test set data; according to the method, fault diagnosis can be carried out under the condition that the number of samples is limited, and an excellent experimental result is obtained.

The invention belongs to the technical field of MIMO radars and neural networks, and discloses a through-wall human body posture estimation method based on MIMO radars, which adopts an MIMO radar system to capture signals, and extracts Doppler information by analyzing original radar signals generated by human body reflection in a scene and processing the obtained signals through Fourier transform. A horizontal feature matrix and a vertical feature matrix of a human body posture are constructed in combination with an original signal and a Doppler signal, and then the feature matrixes are input into a Transform network for training and learning so as to realize human body posture estimation. The method can improve the generalization ability of the system under the condition of light data and light network, and has the characteristics of strong robustness, high stability, real-time performance and high efficiency.

The invention relates to the technical field of health management of satellite-borne products with performance degradation characteristics, and discloses a time sequence anomaly detection method for satellite segmented telemetry based on deep learning, which comprises the following steps: firstly, acquiring satellite telemetry data, and performing segmentation and standardization processing to obtain physically continuous data segments; performing point-by-point reconstruction on the data by using a pre-trained time sequence auto-encoder model, calculating a reconstruction error and performing in-segment limited sliding window smoothing to generate an abnormal score; then determining an anomaly judgment threshold based on normal sample distribution, and defining a boundary exclusion region according to the physical boundary of the data segment; and finally, performing classification judgment on each time step by combining a threshold value and the exclusion region, and outputting a detection result. According to the method, by introducing a segmentation constraint mechanism and a boundary elimination strategy, the problem of false alarm caused by data discontinuity and equipment start-stop transition is effectively solved, and the accuracy and stability of satellite telemetry data anomaly detection are remarkably improved.

The present application discloses a Transformer-based image classification method, system, device and storage medium, which can make full use of a small amount of labeled data and feature aliasing technology for model training, and quickly build a high-performance image classification model in the case of scarce labeled samples to achieve accurate classification of images. The present application method includes: obtaining a collection of labeled training images, wherein the training image collection contains training images of multiple categories; training a Transformer model and a first feature classifier according to the training image collection to improve the first feature representation capability of the Transformer model and the second feature representation capability of the first feature classifier; linearly interpolating the hidden layer features of the two training images to obtain the target hidden layer features; decoding the target hidden layer features, and calculating the cross entropy loss with the category label of the training image; training the Transformer model according to the cross entropy loss to improve the third feature representation capability of the Transformer model.

The invention discloses a space-time trajectory data driven virus transmission tracing method and system. The method comprises the following steps: firstly, cleaning and preprocessing an obtained patient space-time trajectory data set; then, based on the risk area grading system and the infection theory, a set propagation chain conforming to the infection theory is constructed for the high-risk province; then coding the preprocessed patient space-time trajectory data into patient features by using a suitable coding mode; training a traceability model for high-risk provinces based on the constructed set propagation chain and the encoded patient features; and finally, applying the trained high-risk province traceability model to related high-risk provinces based on a knowledge migration mode, and performing a propagation chain construction task. The virus propagation chain constructed by the method disclosed by the invention has the characteristics of expandability in data volume, diversity in propagation mode and high conformity with the real situation.

The present invention discloses a code summary generation method and device based on structural attention, which are specifically as follows: S1, splitting the nodes of an original abstract syntax tree into type nodes and value nodes to obtain a split abstract syntax tree; S2, based on the split abstract syntax tree, obtaining original edges, constructing control flow edges and data flow edges, and designing an adjacency matrix of the original edges; S3, performing joint operations on the adjacency matrix of the original edges and the control flow, and on the adjacency matrix of the original edges and the data flow, respectively, to obtain a structure-based attention score matrix; S4, constructing a code summary model based on structural attention using the structure-based attention score matrix, a sequence of pre-order traversal, an edge relationship matrix and a hierarchy matrix; S5, generating a code summary using the constructed code summary model based on structural attention. The present invention can learn the features of the source code more comprehensively, thereby better generating a code summary.

The invention provides a remote sensing image classification method and system and a storage medium, and relates to the technical field of remote sensing image classification. Preprocessing images in the remote sensing image set; extracting multilayer features of the preprocessed remote sensing image through a pre-trained CNN model; performing dimension reduction processing on the extracted multi-layer features by applying PCA, extracting non-overlapping image blocks from the features after dimension reduction, performing spatial feature extraction on the extracted image blocks by applying 3D-CNN flow, and performing spectrum feature extraction on the extracted image blocks by applying CV-CNN flow; carrying out series fusion on the spatial features and the spectrum features; the fused features are enhanced through an SE attention mechanism; and inputting the enhanced features into an SVM (Support Vector Machine) for classification. The method integrates the advantages of multiple technologies, accurately extracts features, optimizes calculation, is high in adaptability, and effectively improves the classification precision and application value of the remote sensing image.

The present invention provides a method, device and medium for classifying benign and malignant breast tumors based on ultrasound images. The method comprises: preprocessing an original ultrasound image of a breast tumor with a classification label to obtain a preprocessed image; obtaining a region of interest in the preprocessed image; performing three types of processing on the region of interest to obtain a deep residual network feature vector, a texture feature vector and a morphological feature vector respectively; performing dimensionality reduction processing on the deep residual network feature vector and the texture feature vector respectively, and then performing feature fusion on the two to obtain fused vector data; using a support vector machine classifier to learn a certain amount of fused vector data, and using a naive Bayes classifier to learn the morphological feature vector, and obtaining a tumor classification model by weighting the two classifiers; inputting the breast tumor ultrasound image to be classified into the breast tumor classification model to obtain a classification result. The method of the present invention can realize more accurate automatic classification of breast tumor ultrasound images.

The present invention discloses a network intrusion detection system that introduces sample geometry and multi-view information, including a process of constructing a highly separable metric space on a training set and classifying the network intrusion data to be detected using a K-nearest neighbor classifier. First, the collected intrusion data is subjected to a large margin criterion framework at each viewpoint; second, the density between heterogeneous sample clusters in the training set at each viewpoint is minimized; then, an adjacency matrix with label information is introduced for each viewpoint; and then, an adaptive maximization viewpoint cross-correlation method is adopted. The above steps are substituted into a unified learning framework, the optimal solution is calculated and the final metric space is obtained; finally, the network intrusion data to be detected is sent into the metric space and classified using a K-nearest neighbor classifier. The present invention makes up for the defect that the existing system cannot mine sample and viewpoint data information, and can make full use of sample geometry information and viewpoint complementary information to guide multi-viewpoint network intrusion detection tasks.

The present invention proposes a target pose estimation method, comprising the following steps: acquiring image data of a target object to be identified; fusing a multi-branch structural block of multi-scale convolution to construct a pose estimation model; inputting the image data of the target object to be identified into the pose estimation model to obtain a pose estimation value of the target object; processing the target pose estimation value by adopting a hybrid voxel grid method to obtain the volume density and color information of the voxel, and inputting the volume density and color information of the voxel into a neural radiation field model to obtain a rendering key frame; acquiring a real-time observed true value of the target object, and calculating the loss between the rendering key frame and the real-time observed true value of the target object according to a photometric loss function to obtain a loss value; the method constructs a pose estimation model by fusing the multi-branch structural block of multi-scale convolution, can replace the convolution structure of a traditional detection network and construct a pose estimation network branch, and realizes high-precision and high-efficiency pose estimation value inference.