143 results about "Feature transform" patented technology

The present invention relates to the field of pipeline leakage monitoring. Disclosed is an oil and gas pipeline leakage wave identification and monitoring system. In the present invention, an mCNN is combined with LFLBs for performing feature extraction on an acoustic wave signal collected by a DFB, and the collected data improves information completeness; a three-way parallel one-dimensional CNN used in the present invention exhibits good temporal resolution and sensitivity to high-frequency feature transformations in signals; and the present invention integrates advantages of different scales, enabling the algorithm to learn more features, and incorporating the LFLBs to further extract high-level local features. An mCNN-LFLBs network model of the present invention exhibits significant innovation and advancement on the technical level, and also demonstrates extremely high value in actual application. The network model not only provides a novel and efficient technical means for critical fields such as natural gas pipeline inspection, but also introduces new ideas and methods to research fields related to deep learning and signal processing.

The invention relates to an embankment slope stability assessment method based on artificial intelligence, and belongs to the technical field of embankment slope monitoring and assessment. The method comprises the following steps: acquiring and marking embankment slope stress sensing data; dividing the data into a plurality of spatio-temporal data blocks; constructing a stability evaluation model; extracting multi-scale convolution features by adopting multi-scale cavity convolution of a high-frequency channel and pooling-deconvolution operation of a low-frequency channel to obtain a fused multi-scale feature matrix; a hidden state sequence is obtained through a space attention mechanism and a double-door-setting mechanism; calculating time interval saliency based on the hidden state vector, then calculating a weighted feature vector, further obtaining a weighted feature matrix, and processing through deep convolution and point-by-point convolution to obtain a pooling feature vector; carrying out stability evaluation grade classification through learnable category prototype and gating feature transformation; and dynamically adjusting sample weight and constraint attention distribution by adopting a total loss function. According to the method, the progressive instability identification capability can be improved.

The invention discloses an electromagnetic field intelligent calculation method based on deep learning, and the method specifically comprises the steps: inputting a space-time input vector into an MFF-PINN neural network, the MFF-PINN neural network comprises parallel sub-networks and a linear superposition module, the sub-network comprises a scale transformation module, a Fourier feature transformation module and an MLP processing module, and the MFF-PINN neural network comprises a linear superposition module; firstly, scale transformation is carried out on a space-time input vector, then Fourier feature transformation is carried out on the vector after scale transformation, and the Fourier feature transformation module carries out Fourier transformation on the vector after scale transformation based on an effective frequency matrix; all the sub-networks share the Fourier feature transformation, and the output obtained by the Fourier feature transformation is input to the MLP processing module in the first sub-network; and carrying out linear superposition on the output of the sub-networks. According to the invention, the expression capability of the network on the high-frequency component and multi-scale characteristics of the electromagnetic field is obviously enhanced.

The invention relates to the technical field of intelligent control and reinforcement learning technologies, in particular to a trajectory tracking control method fusing multi-objective optimization and a physical sensing network, which comprises the following steps: acquiring a real-time state vector of a to-be-controlled object, decomposing the acquired state vector into a sphere dynamic flow and a platform attitude flow, coding features of different attitude flows are extracted, a fusion feature vector is constructed, and at the same time, an attention mechanism is used to carry out feature transformation to determine control decision features; and for the determined control decision features, utilizing a multi-objective optimization function to carry out cooperative constraint on the generated actions, carrying out feature training in combination with an experience playback mechanism and a self-adaptive stable learning mechanism, and after training is completed, determining a trajectory tracking control instruction of the object to be controlled through dynamic adjustment of learning parameters. According to the invention, by establishing an adaptive stable learning mechanism, the learning rate and exploration noise are dynamically adjusted based on performance stagnation detection, and the training stability and convergence speed are improved.

Provided in the present disclosure are a digital-human processing method and apparatus, and a device, a medium and a product. The method comprises: performing semantic analysis processing and / or representation generation processing on 3D data which is represented on the basis of a neural radiance field; and performing feature transformation, quantization processing and encoding processing on processed data.

The invention provides a machine vision coding method based on feature distillation, and relates to the technical field of image processing.The method comprises the steps that an image to be processed is input into a machine vision coding model, and the model extracts first potential feature representation of multiple channels through an analysis encoder; the method comprises the following steps: quantitatively dividing into basic layer quantitative features containing semantic and spatial structure features and enhancement layer quantitative features containing detail and texture features; the hyper-priori correlation module encodes hyper-priori information and generates enhanced auxiliary features and basic auxiliary features, and the conditional entropy coding network realizes encoding and decoding of the basic layer quantization features and the enhanced layer quantization features based on the enhanced auxiliary features and the basic auxiliary features. A machine vision task result is obtained through a feature transformation and task processing module, and after splicing is conducted through a splicer, a reconstructed image is output through a synthesis decoder. According to the invention, both machine vision and image reconstruction can be considered.

The invention discloses a road snow-blown visibility recognition method and system based on image recognition, and the method comprises the steps: carrying out the sequential processing of an original snow-blown image through initial feature extraction, multi-level down-sampling and feature enhancement, and multi-scale context fusion, and directly outputting a visibility interval and confidence, according to the method, downsampling, feature transformation and feature enhancement processing processes are repeatedly executed for multiple times, deep feature maps with gradually reduced scales are sequentially obtained, automatic and objective recognition of the visibility of the whole road line blown snow is achieved, the adaptability to the scene of the blown snow which is high in burstiness and non-uniform in space is improved, and the visibility of the whole road line blown snow is improved. Therefore, the model can more accurately capture the key depth of field and texture degradation characteristics which influence the visibility, and the recognition result is more accurate.

The application discloses an aerial view generation method based on multi-scale feature transformation and time sequence context, and relates to the technical field of map generation. The method fully utilizes the complementarity of image and laser radar data by fusing the image and the laser radar data, improves the accuracy and robustness of aerial view generation, and can still remain stable under bad weather; a multi-scale space conversion module extracts different scale features, enhances the feature expression capability, and makes the aerial view clearer and more accurate; time sequence information is introduced, past time features are used to enhance current features, and dynamic perception capability is improved; an advanced backbone network and a feature alignment and fusion module are adopted, so that high efficiency and flexibility are ensured; and specific network structures such as Swin-T, PointPillars and random inactivation layers are applied, so that the accuracy and generalization capability are further improved.

The invention discloses an intelligent substation equipment fault diagnosis method, device and equipment, and relates to the technical field of intelligent substation fault diagnosis, and the method comprises the following steps: carrying out the space alignment of a power sampling signal based on an equipment connection relation, and obtaining a structured graph signal; performing feature transformation on the structured graph signal to obtain a statistical incidence matrix and mapping the statistical incidence matrix into real-time state feature points in a Riemannian manifold space; according to curvature characteristics of the Riemannian manifold space, obtaining geometric deviation between the real-time state feature point and a preset ideal state point by adopting a logarithm mapping operator; and calculating the fault contribution degree of each device by using the geometric deviation, determining a fault device, and outputting a device diagnosis result. The method is used for solving the problems that weak fault sensing sensitivity is insufficient and faults are difficult to trace accurately under complex working conditions in the prior art.

A method for point cloud segmentation is disclosed. The method may comprise performing a down-sampling and feature transformation step on an embedding feature extracted from point cloud data to produce a representation of the point cloud data, wherein performing the down-sampling and feature transformation step comprises performing a down-sampling sub-step for reducing a number of points by a pooling layer and performing one or more times of a feature transformation sub-step; and performing an up-sampling and feature transformation step on the representation of the point cloud data to produce the point cloud segmentation, wherein performing the up-sampling and feature transformation step comprises performing an up-sampling sub-step for restoring the number of points by an un-pooling layer and performing one or more times of the feature transformation sub-step. The feature transformation sub-step comprises at least one of capturing a local feature of the point cloud data by a local perceiver; capturing a global feature of the point cloud data by a selective state space model (SSM) block; and capturing a cross-channel dependency of the point cloud data by a channel modulator.

A multimodal entity linking method based on dual encoders and a hybrid expert mechanism is proposed. This invention relates to multimodal entity linking technology at the intersection of natural language processing and computer vision. Addressing the problems of low inference efficiency, insufficient cross-modal interaction, and shallow modal fusion in existing methods, this invention proposes a multimodal entity linking method based on dual encoders and a hybrid expert mechanism. A dual-tower architecture is used to independently encode mentions and entities. Entity embeddings can be pre-computed offline and indexed, and linking is completed during inference through fast vector retrieval. A hybrid expert mechanism is introduced to achieve adaptive feature transformation of samples, and a gating network dynamically selects expert combinations. Bidirectional cross-modal attention is used to establish fine-grained alignment at the word-image block granularity. A channel attention mechanism dynamically balances the contributions of textual and visual modalities. The model is jointly optimized by multiple constraints, including load balancing loss. This invention achieves efficient retrieval while maintaining deep inference capabilities, simplifies inference time complexity, and is suitable for scenarios such as knowledge graph construction and intelligent question answering systems.

The present application relates to the technical field of data processing, and more particularly to a dimension reduction and feature extraction method based on mutual information and genetic algorithm, comprising using an improved mutual information formula to calculate mutual information to measure the role of each dimension for each class; using the mutual information value as the fitness value of the feature dimension, first using the roulette method in the genetic algorithm to generate multiple information-carrying feature subsets; then using mutual information to optimize the generated feature subsets in dimension; optimizing the feature subsets, controlling the mutation and difference degree of the optimized feature subsets, and generating new feature subsets; and fusing the evaluation results of the multi-source feature subsets. The present application considers the fixity of the dimensionality after transformation, the high efficiency and small influence of feature extraction, and the neglect of small features; the feature subset is mutated, the dimensionality of the reduced feature subset is changed, and the effective difference degree between the feature subsets is effectively controlled.

The invention relates to the technical field of edge intelligence and federated learning, and provides an edge heterogeneous data enhancement method based on reinforcement learning and meta learning, and the method comprises the steps that a client constructs a strategy network based on a Monte Carlo algorithm; mapping local data into client features, performing spatial mapping on the client features based on a policy network, and outputting a feature transformation matrix; the feature transformation matrix is linearly mapped into alignment features, the Euclidean distance between the alignment features and global model parameters is calculated to serve as a feature alignment metric value, and a reward value is defined; and updating parameters of the strategy network by adopting a strategy gradient algorithm, and calculating an accumulated long-term discount reward based on a reward value to guide a network optimization direction. According to the method provided by the invention, through multi-module collaborative optimization, the generalization performance, the convergence speed and the reasoning precision of federal learning in a cross-domain task are remarkably improved, and the method has important technical value and application potential.

This application provides an image compression system, an image processing method, an encoding / decoding method, and an electronic device. The image compression system includes a first selection module, an entropy encoding module, an entropy decoding module, a quantization module, N encoding networks, and one decoding network. The N encoding networks have different encoding losses. The first selection module is used to select a target encoding network from the N encoding networks based on the number of times the image to be encoded has been encoded. The target encoding network is used to perform feature transformation on the image to be encoded to obtain a first feature map. The quantization module is used to quantize the first feature map to obtain a second feature map. The entropy encoding module is used to entropy encode the second feature map to obtain a bitstream. The entropy decoding module is used to entropy decode the bitstream to obtain a third feature map. The decoding network is used to perform feature transformation based on the third feature map to obtain a reconstructed image. This effectively reduces the loss ratio of the image after multiple encoding and decoding operations.

The present application relates to the technical field of speech recognition, and provides a speech recognition method and device, electronic equipment and storage medium, wherein the method comprises: performing feature extraction on a speech signal to be recognized, inputting an extracted acoustic feature sequence into a speech recognition model to obtain target recognition text that has been optimized by text; wherein the speech recognition model comprises an encoder and a decoder, and a hybrid expert module for a text optimization task is embedded in the encoder; the encoder is used for performing layer-by-layer encoding processing on the acoustic feature sequence, and performing feature transformation corresponding to the text optimization task on intermediate level features through the hybrid expert module in the encoding process to obtain encoding features containing text optimization semantics; and the decoder is used for decoding the encoding features to obtain the target recognition text, effectively solving the problems of bloated architecture and error accumulation caused by separation of recognition and text optimization in a traditional speech recognition system, and achieving dual improvement of inference efficiency and recognition quality.

The invention discloses a multivariate time sequence prediction method and system based on a graph diffusion space-time convolution network, and the method comprises the steps: inputting multivariate time sequence data, and obtaining an initial node feature; constructing a dynamic adjacency matrix, generating a global diffusion matrix through the dynamic adjacency matrix, and performing sparsification on the global diffusion matrix to obtain an adjacency matrix; sending the adjacent matrix and the initial node features into a graph convolution module to obtain spatial convolution features; sending the spatial convolution features into a time convolution module to obtain space-time convolution features; the graph convolution module and the time convolution module form a layer of the model, time dimension compression is carried out on output of each layer, jump connection is carried out along feature dimension splicing, and finally feature transformation and dimension remodeling are carried out to generate a prediction result; training the model; the method has the advantages that the model can effectively mine the hidden relation and long-distance dependence between the nodes, and prediction deviation in a dynamic scene is reduced.

The present application relates to the technical field of expression recognition, and in particular to an expression recognition method and system based on multi-scale features and spatial attention. The method comprises: using an HNFER neural network model to perform feature extraction on acquired facial image data to obtain an original input feature map; performing pooling and concatenation on the extracted features on the basis of a CoordAtt attention mechanism to obtain a feature map; performing deep convolution processing on the feature map to obtain an attention map, and then obtaining a final feature map by means of element multiplication; and performing feature transformation and normalization on the final feature map to obtain expression category probabilities and outputting the expression category probabilities . In the present application, by integrating scale-aware technology and spatial attention technology, a model can more accurately recognize and categorize different emotional states, and can maintain high performance even under complex environmental conditions.

The application discloses a micro bearing production and manufacturing detection data analysis method and system based on big data, relates to the technical field of data processing, and pre-trains a recurrent time sequence network through collection of vibration signals of bearings in a known state, obtains an evolution feature vector of bearings in the same batch through the network combined with a transient noise suppression operator, extracts a static feature vector combined with a machining time sequence and an end face image, corrects a visual missing sample after splicing, constructs a reconstructed kernel feature matrix, obtains a feature transformation and a mapping matrix based on two-way alternate optimization of the matrix and a real label, establishes a bearing state database, collects multi-modal data of a bearing to be detected to generate an initial to-be-detected feature vector, calculates the similarity of the to-be-detected feature vector with database samples after mapping, and finally outputs a detection result. The application deeply fuses multi-modal features, effectively overcomes interference such as workshop visual pollution, thermal expansion and group tolerance drift, and greatly improves detection accuracy and robustness.

The application discloses an industrial control abnormality detection method based on high-low frequency feature similarity, which firstly carries out periodic collection of monitoring data from an industrial control system field, and constructs corresponding low-frequency feature vectors and high-frequency feature sets. Through repeated data collection, a training data set containing multiple samples is formed. In the initialization process of the abnormality detection network, a combination of a feature transformation network and a projection network is adopted to ensure effective mapping and fusion of the low-frequency features and the high-frequency features. Specifically, the low-frequency feature vectors are mapped to a unified dimension through a linear transformation matrix, and the high-frequency features are directly input into an attention fusion mechanism to calculate the dynamic correlation degree of the high-frequency features to the low-frequency features. Finally, the projection network is used to map the fused features and the low-frequency features to generate a vector pair for similarity learning. The application can solve the technical problems of the deficiencies of the conventional industrial control system abnormality detection method in feature processing and fusion.

The invention discloses a multi-modal depression auxiliary detection algorithm, and the method comprises the steps: obtaining multi-modal data which comprises video data, voice data and scale data of a medical site; carrying out identity recognition, round labeling and format conversion processing on the multi-modal data to obtain structured data containing role information, time sequence round and content fields; performing feature extraction on the structured data to obtain a feature vector set containing an image mode, a text mode and a voice mode; carrying out fusion processing on the feature vector set by adopting a preset cross-modal attention mechanism dominated by a text mode to obtain multi-modal fusion feature information; and inputting the multi-modal fusion feature information into a pre-configured depression risk assessment model, performing feature transformation and compression through a full connection layer and a pooling layer, and outputting a depression disease probability for representing a target individual. According to the method, complementation and dynamic semantic modeling of multi-source data can be realized, and the accuracy and reliability of a detection result are improved.

The application discloses a welding quality monitoring method of resistance spot welding data multi-neighbor feature analysis, which collects process data when the resistance spot welding is normal and implements standardization processing; obtains a regression coefficient matrix of the standardized data matrix; obtains a multi-neighbor relationship matrix through the regression coefficient matrix, further obtains a generalized eigenvalue problem and solves it; obtains a feature transformation matrix according to the solving result, further obtains a score matrix, a covariance matrix and a monitoring index matrix; obtains control upper limits of two monitoring indexes according to the monitoring index matrix; implements standardization processing on the latest process data; obtains a score vector and an error vector of the standardized data vector according to the feature transformation matrix, further obtains the two monitoring indexes; determines whether the welding quality is normal or not by judging whether the two monitoring indexes are within the control upper limits; and the method has the advantage that the reliability of the welding quality monitoring can be effectively improved.

The invention discloses a power transmission line multi-target defect cooperative detection method, system and device and a medium, and relates to the technical field of defect detection.The method comprises the steps that feature extraction is conducted on historical multi-source data, and historical multi-source features are obtained; for each defect type, performing relevance evaluation on each feature dimension of the historical multi-source features and the defect type based on Bayesian conditional probability to obtain a relevance evaluation result; performing matrix standardization on the historical multi-source feature matrix to obtain a historical standardized feature matrix; performing weighted linear transformation on the historical standardized feature matrix according to the relevance evaluation result to obtain a historical feature transformation matrix; constructing a defect collaborative detection model according to the historical feature transformation matrix and the historical defect detection data; and based on the defect collaborative detection model, generating a defect detection result according to the current multi-source detection data. The defect detection method has the effect of improving the accuracy of defect detection.

The application discloses a thermal infrared electrical equipment image semantic segmentation method based on edge auxiliary learning, features extracted from an original input image are converted through a conversion module and a global information integration module, and edge detection and semantic segmentation tasks are simultaneously optimized, and meanwhile, a cross-guiding unit is used for simple feature transformation, two different branches in a decoder are interacted, and the two tasks achieve the effect of joint optimization. In addition, the application adds a true value supervision at the input end of the convolutional neural network module, so that the application can not only predict more accurate target boundaries, but also can obtain more accurate segmentation results through the edge detection branch to assist the semantic branch.

The application provides an evaluation result recognition method, device and equipment and a storage medium, which can be applied to the technical field of natural language processing. The evaluation result recognition method comprises the following steps: analyzing the dependency relationship between a plurality of words in text information comprising a plurality of evaluation subjects and description texts associated with the evaluation subjects, and constructing a syntactic dependency tree; determining the position weight of each word with respect to each evaluation subject based on the relative position relationship between each word in the text information and each evaluation subject, except the words constituting each evaluation subject; for each evaluation subject, constructing a weight matrix based on a plurality of position weights corresponding to the evaluation subject, fusing the weight matrix with the sentiment label of each opinion word recognized from the description text, and obtaining a semantic matrix; and fusing and transforming the syntactic matrix obtained by feature transformation of the syntactic dependency tree with the semantic matrix of each evaluation subject, and outputting an evaluation result.

The application relates to a partial discharge diagnosis method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an acoustic-electric signal to be analyzed and task constraint information for providing constraint information, performing feature coding processing on the acoustic-electric signal to be analyzed to obtain an acoustic-electric coupling feature, performing feature transformation on the acoustic-electric coupling feature and aligning the acoustic-electric coupling feature to a preset state parameter domain to obtain a state analysis feature, then performing acoustic-electric joint diagnosis reasoning based on the task constraint information and the state analysis feature to obtain a partial discharge reasoning feature, and performing semantic generation based on the partial discharge reasoning feature to obtain a diagnosis result. The method can solve the acoustic-electric cross-modal feature space dislocation problem, significantly improve the precision and robustness of partial discharge diagnosis under complex working conditions, can synchronously output accurate partial discharge state description and fault labels, and significantly improves the accuracy and intelligent analysis depth of partial discharge diagnosis.

This application discloses a method, apparatus, computer device, and storage medium for detecting hand key points, belonging to the field of computer technology. The method includes: acquiring feature information from a hand image; performing feature transformation on the feature information to obtain pose parameters and shape parameters corresponding to the hand; constructing a three-dimensional hand model based on the pose and shape parameters; determining the three-dimensional hand key points contained in the three-dimensional hand model; and projecting the three-dimensional hand key points onto the hand image to obtain two-dimensional hand key points in the hand image. The method provided in this application constructs a three-dimensional hand model contained in the hand image to constrain the positions of the three-dimensional hand key points in the three-dimensional hand model, thereby ensuring the accuracy of the three-dimensional hand key points. Then, using the three-dimensional hand key points as constraints, the corresponding two-dimensional hand key points are projected onto the hand image, thereby improving the accuracy of the two-dimensional hand key points.

This application relates to the field of video surveillance and image processing technology in coal mines, and discloses a method and apparatus for panoramic stitching of working faces using an improved optical flow algorithm. The method includes the following steps: First, multi-scale adaptive preprocessing is performed on the original image; an anti-interference weight model based on texture entropy and gradient is constructed, and a sparse optical flow field is generated using Retinex illumination component separation technology to suppress dust and illumination interference. Second, feature matching is guided by the sparse optical flow field, and a dynamic region mask is generated by combining target detection. The optical flow transformation and feature transformation matrices are then adaptively weighted and fused. Finally, an improved Poisson fusion algorithm is used to repair dynamically occluded areas, and the optimal seam path is planned by calculating the optical flow variance. A dynamic window is then used for smooth fusion. This invention effectively solves the problems of stitching misalignment and artifacts caused by high dust levels, illumination fluctuations, and rapid equipment movement in coal mines, achieving high-quality seamless panoramic stitching.

The invention relates to the technical field of three-dimensional photocuring forming, and discloses a liquid level control method, device, equipment and medium, and the method comprises the following steps: acquiring liquid level data, section image data of a current printing layer and pressure data of an inner cavity of a scraper; performing feature extraction based on the cross-section image data to obtain an image feature vector; feature transformation and coding are conducted on the basis of the liquid level data and the scraper inner cavity pressure data, and physical feature vectors are obtained; splicing the image feature vector and the physical feature vector to obtain a joint feature vector; and mapping the joint feature vector into a floating block displacement, and performing liquid level control based on the floating block displacement. By fusing liquid level data, section image data of a current printing layer and scraper inner cavity pressure data, liquid level control is spanned from single-dimension sensing to multi-mode high-dimension intelligent sensing, and the liquid level control precision and response speed in printing tasks of large breadth, full version and complex fine structures can be effectively improved; and the printing quality and efficiency are improved.

The invention discloses a traffic image defogging method based on wavelet convolution and semantic-content guide fusion. The method comprises the following steps: acquiring a foggy image and preprocessing the image; setting initialization model parameters; extracting features in an encoder through multi-scale wavelet convolution and performing feature enhancement, and performing down-sampling by using an image block embedding module to generate an embedded feature map; inputting the embedded feature map into a feature transformation layer, further extracting features, performing up-sampling, and fusing the features after up-sampling with shallow features in the encoder; and inputting the fused features into a decoder, gradually recovering the image size, combining the shallow detail features of the encoder, and finally outputting a defogged image. The structural similarity index and the peak signal-to-noise ratio of the defogged image and the real image are calculated and output, the model with the best effect is reserved, whether the preset number of iterations is reached or not is judged, defogging model parameters with the optimal effect are obtained after the number of iterations is reached, and the method is applied to traffic image defogging.