397 results about "Feature mapping" patented technology

The application discloses a mirror highlight detection and removal method based on a double-flow convolutional neural network, which calculates the gradient of a pixel point in an x direction and a y direction of an input original image with highlights, extracts a first highlight feature mapping, subtracts the first highlight feature mapping after being processed by a first convolution block attention module CBAM from a preprocessed image, and outputs a first-stage highlight-free image; the first highlight feature mapping is progressively down-sampled and reduced in size, each highlight feature mapping after being down-sampled and reduced in size is processed by a convolution block attention module CBAM at each stage, and is subtracted from a highlight-free image output by a previous stage, and finally a rough highlight-free image is obtained. Then, highlight extraction and refinement are performed on the rough highlight-free image by a highlight extraction module to obtain a final highlight-free image. The application can effectively solve the image information degradation problem caused by the mirror highlight, thereby reducing the interference of the highlight on visual tasks such as target detection.

This invention discloses an underwater acoustic anti-interference transmission method and system based on sparse time-frequency feature mapping. The method includes: at the transmitting end, adaptively generating a fractional-order linear frequency-modulated waveform with a specific time-frequency shear slope based on the Doppler state of the underwater acoustic channel, achieving physical-layer focusing of transmitted energy; at the receiving end, constructing a hybrid observation model containing wide-block sparse channel components and narrow-block sparse burst noise components, and using a dual-channel variational Bayesian algorithm to jointly iteratively infer the posterior probability distribution of environmental burst noise in the fractional-order domain; finally, recovering the original signal through soft-threshold interference cancellation and fractional-order channel equalization. This invention effectively solves the communication failure problem caused by high-dynamic Doppler diffusion and marine biological impulse noise interference in underwater acoustics by actively mapping the waveform and using heterogeneous sparse joint inference at the receiving end, significantly improving transmission reliability in harsh underwater acoustic environments.

A central cloud server that includes a processor that obtains sensing information from a plurality of edge devices at different locations, obtains beam alignment information from the plurality of edge devices, and trains a machine learning model on training data. The training data comprises the obtained sensing information as input features and the beam alignment information as learning labels for different times-of-day. The machine learning model is trained to determine patterns that maps the input features to the learning labels and to generate a connectivity enhanced database. The connectivity enhanced database specifies a plurality of time-of-day specific uplink and downlink beam alignment-wireless connectivity relationships for a surrounding area of each edge device of the plurality of edge devices.

The present application discloses a bearing fault diagnosis method and system based on knowledge enhancement and multi-path distillation, which relates to the fields of intelligent operation and maintenance and industrial equipment health management. The method includes obtaining sensor signals and visual image data of the bearing operation; based on an asynchronous dual-channel architecture, correspondingly extracting signal features of the sensor signals and image features of the visual image data, and performing time synchronization on the signal features and the image features; using a multi-modal bottleneck Transformer module to fuse the synchronized signal features and the synchronized image features; based on a maintenance knowledge graph dynamically constructed from a bearing maintenance manual, combining a text generation model to map the fused features to a semantic space and generate a fault diagnosis report. The present application can improve the recognition accuracy, real-time performance and interpretability of diagnosis results of bearing faults.

This invention discloses a lightweight method for detecting foreign objects (FOOs) in power transmission lines, relating to the fields of power line inspection and computer vision. A YOLOv10-based FEO detection model is constructed, comprising a feature extraction part, a feature interaction part, and a detection head part. The C2f module in the feature extraction and feature interaction parts is replaced with an expert dynamic extraction module, and the detection module in the detection head part is replaced with a parameter-sharing detection module. The trained FEO detection model is obtained by collecting and evaluating a calibrated FEO dataset of power transmission lines. FEO keyframes are input into the trained FEO detection model to obtain detection results. The expert dynamic extraction module acquires feature maps from multiple receptive fields, achieving rich representation in FEO detection environments with varying scales. The parameter-sharing detection module, based on this, reduces redundant computation and enhances the semantic representation of small targets through parameter sharing and grouping normalization, effectively improving the efficiency of FEO detection in power transmission lines.

The application discloses a road centerline determination method and system based on a deep neural network satellite map, and relates to the technical field of satellite image processing; the method comprises the following steps: preprocessing time-phase satellite images of a collected to-be-processed region, vehicle GPS track data and street view image sequences to obtain a dynamic region in the to-be-processed region, a track density map and a street view feature mapping table; inputting the time-phase satellite images into a pre-trained road segmentation model to obtain multiple road probability maps; based on the multiple road probability maps, performing dynamic region weighted fusion, non-dynamic region logical or operation and threshold determination to obtain an initial road mask; vectorizing the initial road mask into a centerline network and extracting cross nodes to obtain an initial road network topology; and the application has the advantages of improving the accuracy of the road network topology and guaranteeing the rationality of path planning.

The application relates to the technical field of image recognition, and discloses a mouse species recognition method based on image recognition. An original mouse image is input into a posture decoupling recognition network, and a heat map is output based on an anatomical prior anchor point; a rotation bias angle is calculated according to the heat map coordinates, an affine transformation is performed on the image, and a distorted body is cut and reorganized into independent local image blocks of a head, a trunk and a tail at a standard visual angle; spatial features are extracted by using parallel convolution channels, local features are mapped to a global feature space by a cross-region cross-attention mechanism, a species discrimination vector is fused and generated, and a classification result is output. The application converts non-standard posture restoration into extraction and reorganization of standard local features, eliminates the interference of body distortion and local occlusion in a limited space on global feature extraction, and overcomes the misclassification defects caused by the sensitivity of a conventional network to non-standard postures.

This invention discloses a method and system for testing the compressive strength of concrete in building engineering, relating to the field of concrete strength testing technology. The method includes: acquiring ultrasonic propagation data, infrared thermal imaging sequences, and three-dimensional surface topography point clouds of concrete components to form a multi-dimensional physical field data set; performing cross-modal fusion processing on the data set to generate a feature mapping map of internal defects in the concrete and a material homogeneity distribution spectrum; calling a pre-trained strength prediction model to analyze the feature mapping map and distribution spectrum to obtain predicted compressive strength values ​​and markers of structurally weak areas; spatially weighting the predicted values ​​based on the markers to generate corrected compressive strength values; and outputting a test report and maintenance recommendations based on the corrected values ​​and distribution spectrum. This method improves the accuracy of strength testing and the comprehensiveness of defect identification.

The application discloses a power grid load prediction method and system based on deep learning, which comprises the following steps: collecting multi-dimensional load correlation data through an intelligent power grid data fusion calculation platform, cooperatively capturing space-time correlation characteristics through a space-time residual gated recurrent model, enhancing network and strengthening key feature representation through a gated recurrent unit, then inputting a multi-modal load prediction deep model to build feature mapping relationship, generating preliminary prediction results through feature weight distribution, abnormal value elimination and smoothing optimization, and outputting final data after platform verification. The space-time residual gated recurrent model, the gated recurrent unit enhancement network and the multi-modal load prediction deep model all have exclusive feature processing mechanisms, and the processing accuracy is guaranteed through feature classification, gate initialization, mode division, fusion calculation and other subdivided processes. The application effectively improves the comprehensiveness and reliability of load prediction, and is suitable for accurate scheduling and optimized operation of intelligent power grids.

This invention discloses a translation method and system based on structured segmentation and contextual memory, comprising: performing multi-dimensional vectorization representation of the long text to be translated to establish a full-text semantic feature mapping space; adaptively decomposing the long text to be translated to obtain a tree-like hierarchical structure; compressing key information of semantic units, extracting core semantic feature vectors, and storing them in a globally dynamically updated contextual memory pool; generating an enhanced prompt information sequence based on the core semantic feature vectors and the hierarchical attributes of the current semantic unit; inputting the enhanced prompt information sequence into a large-scale language model to generate a candidate translation sequence; performing boundary verification and smoothing on adjacent candidate translation sequences to output a complete structured translation. This invention improves the automation level of long text translation by systematically optimizing the processes of text deconstruction, contextual memory, constraint generation, and global verification, ensuring the structural integrity, logical coherence, and semantic fidelity of the translation.

This invention discloses a method for assessing the weathering of sandstone artifacts based on the fusion of multi-source heterogeneous data driven by physical-manifold collaboration, belonging to the field of cultural relic protection technology. Addressing the contradiction that surface spectral data of sandstone artifacts is dense but cannot probe the interior, while internal physical data is accurate but extremely sparse and lossy, this invention proposes a "surface-to-interior" fusion strategy. First, using a physical information deep learning model, physical partial differential equations are introduced as prior constraints to extrapolate sparse point data into a continuous deep physical tensor across the entire field, achieving a "penetrating" effect. Second, based on Riemannian manifold geometry, spectral-physical enhancement features are mapped to the tangent space to extract noise-resistant surface manifold features. Furthermore, through coupled tensor decomposition, deep mechanisms and surface properties are forcibly aligned in the latent feature space. Finally, a high-order Laplacian hypergraph model is used to achieve pixel-level classification of weathering degree. This method effectively solves the problems of spatial scale mismatch and missing physical mechanisms in multi-source data, achieving a non-destructive, full-field, and accurate quantitative assessment of the weathering status of cultural relics.

This invention discloses a continuous vector discretization representation method, system, and application, comprising: constructing an end-to-end unified architecture including an attention encoder, a binary spherical quantization module, and an attention decoder; utilizing the attention encoder combined with a block causal masking mechanism to uniformly extract high-dimensional feature vectors from single-frame images or multi-frame videos; performing dimensionality reduction, spherical normalization, and binary quantization based on a learnable hyperplane on the high-dimensional feature vectors through the BSQ module, mapping the features to a unit hypersphere and generating binary discrete codes without an explicit codebook; and using the attention decoder combined with spatiotemporal position coding to perform high-fidelity reconstruction of the discrete codes. This invention solves the problems of low parameter efficiency, incompatibility with image and video processing, imbalance between reconstruction quality and computational efficiency, and unstable training caused by the reliance on explicit codebooks in existing technologies. It achieves lightweight, high-fidelity, wide compatibility, and easy training, making it particularly suitable for efficient storage, transmission, and accurate reconstruction of multimodal medical images.

The application relates to the technical field of radars, in particular to a radar working mode small sample identification method based on a multi-modal model independent meta-learning, which comprises the following steps: simulating multiple radar working mode waveforms to extract corresponding pulse description word sequences and taking the pulse description word sequences as small sample tasks; converting the pulse description word sequences into multi-channel feature images and extracting sequence features and image features; mapping the sequence features and the image features to a shared feature space and obtaining fused features through weighted fusion; based on the fused features, training an initial multi-modal double-flow model independent network on the small sample tasks by adopting a model independent meta-learning framework to obtain a trained multi-modal double-flow model independent network; and classifying the working modes of query samples by using the trained multi-modal double-flow model independent network. The method can improve the rapid adaptability and reliability of a radar system in a dynamic electromagnetic environment.

The application relates to the technical field of algorithm and network cooperative scheduling, and discloses an algorithm and power cooperative scheduling method and system based on multi-dimensional classification of task value and time delay sensitivity, which comprises the following steps: acquiring multi-source data streams of computing power tasks, power markets and network topologies; performing multi-dimensional classification processing based on a time delay sensitivity index and a comprehensive value score to generate a task type code; extracting power market environment features to dynamically generate a multi-target optimization weight vector, and screening network topology nodes to generate a candidate data center set; combining the code and the weight vector to calculate the comprehensive cooperative utility of each node, generate a to-be-verified scheduling decision, input the decision into a consortium chain network to perform a quoted price tolerance check and consensus determination, and generate a scheduling instruction after the check and determination; collecting actual operation parameters according to the instruction to construct an experience four-tuple, and inputting the experience four-tuple into a meta-learning network for parameter fine-tuning. Through multi-dimensional feature mapping and distributed checking, the application realizes closed-loop cooperative scheduling of heterogeneous computing power and dynamic power.

The application discloses a distribution network fault identification method and system based on transient state feature, and belongs to the technical field of power system automation and intelligent operation and maintenance. The method obtains distribution network transient recording data and extracts multi-dimensional features, and constructs a state description vector mapping the underlying physical discharge state. The state description vector is combined with the multi-dimensional features to construct a mechanism collaborative feature subset, and redundant features in a random discrete state are removed in combination with distribution network grounding operation parameters. The remaining subset is projected into a transient latent variable space, and a state membership degree vector of the subset and a preset physical state anchor point is calculated. The state membership degree vector is converted into a control mask to inject a deep neural network, and a joint loss function is used to constrain the network hidden layer feature mapping result to fit the corresponding physical state anchor point, so that an initial classification is output. Finally, the feature marginal contribution degree of an inference link is calculated, and a final diagnosis result is output. The application realizes deep integration of physical mechanism and artificial intelligence, and solves the problem of lack of physical basis of a black box AI model.

This invention provides a state perception method and system for electric vehicle battery swapping networks based on edge computing, belonging to the field of electric vehicle battery swapping network technology. First, a state interaction topology for the battery swapping network is constructed, and dynamic data on battery storage at swapping stations, operation of swapping equipment, and swapping requests are collected to generate a multi-dimensional state perception stream. This stream is then transmitted to an edge computing state processing link for distributed feature mapping, resulting in a set of feature vectors. Next, a state association evolution model containing multiple state evolution relationships is constructed to trace the origin and diffusion path of operational bottlenecks and determine control priorities. Finally, a dynamic control stream is generated based on the priorities and the set of feature vectors, converted into a standardized instruction sequence, and transmitted to the corresponding link. This achieves real-time perception and dynamic control of the battery swapping network state, improving the operating efficiency and service quality of the battery swapping network.

The invention discloses a target fine-grained fusion classification method and device, and the method comprises the steps: inputting an obtained visible light target slice image and an SAR target slice image into a visible light image branch network and an SAR image branch network respectively, and extracting the depth features of the visible light image and the depth features of the SAR image respectively; connecting the extracted depth features of the visible light image with the depth features of the SAR image in a feature dimension to generate a fusion feature vector, inputting the fusion feature vector to a classification layer, and mapping the features to a category space through a full connection layer to obtain a target fusion classification result; an improved ResNet-34 is adopted as a feature extraction backbone network, and fine-grained feature learning is realized by adjusting the correlation between the number of output channels of a final convolutional layer Conv5x and the number of categories. In the training process, a multi-task loss mechanism combining a fine-grained loss function and weighted cross entropy loss is introduced, so that the classification accuracy and stability of the model in a complex scene are effectively improved.

The application relates to the technical field of artificial intelligence-based music melody automatic generation systems, and particularly discloses an artificial intelligence-based music melody automatic generation system. The system comprises an intention analysis and feature mapping module, which is used for converting a user intention into a structured semantic feature; an emotion evolution state machine module, which is used for dynamically generating a time-series emotion state vector according to the semantic feature; a hierarchical controllable generation network module, which is used for generating a note sequence with specific styles, coherent emotions and diversity based on the semantic feature and the emotion state vector; and a post-processing and music theory constraint module, which is used for performing compliance correction and optimization on the note sequence. The application can generate a melody with coherent emotion evolution logic, high matching of a user intention, various styles and compliance with music theory.

The application discloses a steel bridge deck roller compacted asphalt concrete construction simulation method based on BIM, and relates to the technical field of simulation. The method first analyzes the geometric boundary of the BIM model and constructs an adaptive space-time sampling point set; then constructs a deep neural network introducing Fourier feature mapping, maps low-dimensional space-time coordinates into high-dimensional features to capture high-frequency physical changes; then establishes a composite loss function containing heat conduction, thermal coupling and boundary condition residual error, and uses automatic differentiation technology and an adaptive weight algorithm based on gradient statistics for unsupervised training; finally, the trained lightweight model is integrated into the BIM rendering engine. The application solves the problems of long time consumption of traditional finite element simulation calculation, inability of real-time interaction, and poor generalization ability of pure data-driven AI due to lack of internal measured data, and realizes real-time, high-precision dynamic simulation of the temperature field and stress field of the steel bridge deck pavement.

The application discloses a multi-modal feature collaborative generation analysis method and system for tumor survival prediction, and relates to the technical field of computer vision. The method comprises the following steps: acquiring multi-modal data and preprocessing to obtain a training data set; learning a first feature mapping relationship between multiple modes based on complete mode samples, and training a generator based on missing mode samples and the first feature mapping relationship to obtain a target generator, which generates virtual coding features of the missing mode; acquiring partial mode medical data of a target object, inputting the partial mode medical data of the target object into the target generator to generate virtual missing mode coding features of the target object; extracting at least one other mode coding feature from the partial mode medical data, fusing the virtual missing mode coding features and the at least one other mode coding feature, and determining a survival prediction result of the target object according to the fused features. The application improves the accuracy and interpretability of tumor survival prediction.

This application discloses a temporal role recognition method based on knowledge graphs, relating to the field of data processing technology. It includes: acquiring first text data, second temporal record data, and third temporal event data of a target object; constructing event units for the target object and dividing them into first, second, and third temporal stages; extracting behavioral features from the first text data and mapping them to event nodes, extracting capability features from the second temporal record data and connecting them to basis nodes, and connecting the event nodes to result nodes to construct a role evidence graph; extracting continuous evidence chains and converting them into stage observation sequences; inputting the sequence inference model to generate role state trajectories, determining the role category based on the trajectory's continuity across the three stages, and outputting classification labels. This method transforms role recognition into a staged inference process based on temporal evidence chains, effectively distinguishing between continuous dominance and partial participation, thus improving the objectivity and accuracy of recognition.

This disclosure relates to the fields of food and traditional Chinese medicine quality testing, molecular spectroscopy analysis, and intelligent detection technology. In particular, it relates to a method and system for quality testing of donkey-hide gelatin (Ejiao) products based on multispectral manifold feature mapping and attention-enhanced convolutional networks. This method addresses the limitations of existing Ejiao products, such as the bottleneck in accuracy for distinguishing subtle differences between genuine and counterfeit products or those of different origins, the lack of ability to screen for abnormal samples like color anomalies and atypical adulteration caused by process deviations, and the difficulty in balancing detection efficiency and accuracy. This solution uses near-infrared spectral data and feature mapping deep learning to classify and distinguish the quality of Ejiao products, significantly shortening the testing cycle and making it suitable for batch release and process monitoring.

This invention relates to the field of intelligent manufacturing and industrial automation technology, specifically to an intelligent order scheduling and material management system for a milling and turning workshop. It includes a task parsing module, a feature mapping module, a state acquisition module, a potential field construction module, a scheduling calculation module, and a feedback execution module. The system receives task drawing data and bill of materials data, extracts geometric feature bounding dimension data and machining tool vector sequence data, and tensors and encodes them. It collects the current tool library configuration status parameters of the target machining equipment and the physical attribute parameters of work-in-process, constructs a continuous potential energy field distribution matrix, and dynamically refreshes it. It calculates the potential energy gradient descent direction of the multidimensional machining feature tensor flow, generates a task queue of associated paths and a theoretically estimated execution cycle time sequence, issues CNC machining task plans and automated guided vehicle (AGV) allocation instructions, and feeds back the actual cycle deviation correction value for closed-loop updates. This invention makes the scheduling results closer to the actual executable state of the workshop.

This invention provides a method for extracting three-dimensional features of steel stamps on water transfer printing paper based on multispectral fusion, relating to the fields of optical inspection, machine vision, and automated quality control. This method utilizes adaptive illumination and image acquisition, employing optimal band optimization, polarization decoupling, and dynamic structured light projection to obtain a series of images separating geometric deformation and pattern interference. Three-dimensional reconstruction is performed using a physically constrained neural network, embedding a double-layer reflection optical model into the network to decouple and predict the paper substrate normal map and integrate to generate a high-precision three-dimensional point cloud. Multi-dimensional geometric features such as height, curvature, and shape are then extracted from the point cloud. Finally, based on a three-dimensional lookup table, the features are mapped to a comprehensive defect level, and automated, differentiated graded processing is performed. This invention achieves non-contact, micron-level high-precision inspection and intelligent quality control of steel stamps on complex surfaces.

This application relates to the field of smart park management technology, and discloses a method for automatic triggering and closed-loop management of park tasks based on key semantic mining. It collects, cleans, and sorts park meeting audio and business text in real time to form a key data stream. Key semantics are extracted through lexical and syntactic analysis and converted into business feature tags through feature mapping. These tags are input into a pre-set task model for rule collision and constraint calculation to generate execution tasks. After trigger addressing and packetization, task distribution instructions are generated and delivered to vertical domain digital human agents via a collaborative distribution network to complete multi-agent collaborative execution and produce execution data. This solves the technical problem of lagging business perception and disconnected task execution in traditional park management.

The present application relates to the technical field of image recognition, in particular to a cross-border commodity compliance detection method and system based on image recognition, comprising the following steps: collecting a to-be-detected commodity image, and extracting a packaging label region and commodity appearance texture data in parallel; mapping to generate label semantics and visual form feature vectors; calculating feature distances using cross-attention, and constructing a graph-text semantic alignment matrix; comparing a dynamic safety threshold to determine a violation probability, and generating a final compliance detection result.In the present application, a bimodal feature mapping mechanism is constructed, commodity appearance and label text information are deeply fused, and graph-text semantic conflict features are accurately captured, effectively making up for the serious deficiency of traditional technology in feature extraction dimension, completely solving the difficult problem that disguised prohibited goods are difficult to identify in complex scenarios, and greatly improving the automation level and cargo clearance efficiency of cross-border logistics compliance detection.

This invention discloses an artificial intelligence-based method, system, and storage medium for generating panoramic sound audio. The method includes the following steps: S1. Inputting the original audio signal and scene parameters, obtaining the time-domain-frequency domain features and spatial scene features of the original audio signal through a multimodal feature extraction algorithm, and weighted fusing the time-domain-frequency domain features and spatial scene features to obtain fused features; S2. Constructing the mathematical expression basis of the 3D spatial sound field model based on the spherical harmonic function, mapping the fused features to three-dimensional spatial coordinates through a sound field modeling algorithm to obtain the 3D spatial sound field model; S3. Using an adaptive rendering algorithm, converting the 3D spatial sound field model into multi-channel panoramic sound audio output according to the parameters of the target playback device. This invention achieves automated panoramic sound audio generation by inputting the original audio signal and scene parameters for feature extraction, fusion, and sound field modeling, and converting the output based on adaptive rendering. It has the advantages of automation, high efficiency, and high precision.