13results about How to "Solve the scarcity" patented technology

The application discloses a water acoustic signal time-frequency spectrum line spectrum extraction method and system, and belongs to the technical field of signal processing. A noisy time domain signal is generated through simulation, and a mask label of a time-frequency spectrum of the noisy time domain signal belonging to a line spectrum is generated through a soft threshold function; a denoising model is trained according to the time-frequency spectrum and the mask label; a target water acoustic signal is acquired, the time-frequency spectrum of the target water acoustic signal is input into the denoising model, and a mask label corresponding to the time-frequency spectrum input is output through inference; the time-frequency spectrum of the denoised target water acoustic signal is acquired according to the mask label and the time-frequency spectrum; an initial candidate point set of the time-frequency spectrum of the denoised target water acoustic signal is acquired, and an initial candidate point of a current frame time-frequency spectrum in the initial candidate point set is acquired; a correlation cost matrix is constructed, the initial candidate point and a trajectory are correlated and matched with the minimum difference as a target, and a line spectrum of the trajectory and the candidate point dynamic correlation is acquired. The method can balance denoising fidelity, detection accuracy and real-time performance.

This invention belongs to the field of power system risk assessment and control technology, and provides a method for generating extreme weather load scenarios based on a conditional diffusion model. The method includes: acquiring extreme weather load samples, and performing preprocessing, sample expansion, and post-processing on these samples to obtain a normal weather sample set, a boundary weather sample set, and an extreme weather sample set; initially training a pre-constructed conditional diffusion model using the normal weather sample set to obtain first network parameters under normal weather scenarios; fine-tuning the conditional diffusion model sequentially using the boundary weather sample set and the extreme weather sample set based on the first network parameters to obtain second network parameters under extreme weather scenarios; and generating a set of extreme weather load scenarios under target extreme weather conditions using the conditional diffusion model based on the second network parameters. This scheme improves the accuracy and reliability of the extreme weather load scenario generation process.

This application relates to the field of hyperspectral remote sensing application technology, and provides a hyperspectral methane detection method based on spatial-spectral joint analysis. First, a sample dataset is constructed, and simultaneously, a methane detection neural network is built to extract the spatial-spectral features of the methane plume from the sample dataset. Then, a preprocessing module based on fundamental laws is established to form a hard constraint mechanism, outputting standardized spatial-spectral features of the methane plume to obtain a predicted methane concentration distribution map. A physical information penalty term is constructed to form a soft physical constraint, minimizing the error between the predicted methane concentration distribution map and the pseudo-true label, thus incentivizing the network to generate a full-resolution methane concentration distribution map. Through a deeply fused spatial-spectral joint strategy, relying on the synergistic effect of the hard constraint mechanism and the soft physical constraint, effective suppression of background noise can be achieved in complex atmospheric environments and various background interference scenarios, significantly improving the accuracy and reliability of signal detection. The detection efficiency is high, making it suitable for large-scale and efficient processing of massive hyperspectral data.

This invention relates to the field of computer vision and image processing technology, specifically to an industrial image anomaly detection method and system based on multi-source feature fusion and synthetic anomaly enhancement. This invention aims to solve the problems of insufficient feature utilization and pixel-level segmentation edge blurring in existing unsupervised industrial image anomaly detection methods. By combining a non-parametric memory prior with a parametric fine-tuning filter network, and introducing a spatial attention mechanism to guide multi-source feature fusion, this method can effectively detect minute defects on industrial surfaces with only normal sample training. The technical solution includes: constructing a frozen multi-scale feature extractor; establishing a non-parametric feature memory; generating a coarse anomaly prior map; designing a multi-source feature parallel encoding network; constructing an attention-guided feature fusion and decoding module; generating synthetic anomaly samples based on a Berlin noise field; performing gradient-truncation hybrid forward propagation; and performing forward inference to obtain anomaly localization results.

The application discloses a multi-modal satire detection method based on a large language model, and comprises the following steps: constructing a large-scale high-quality text data set; constructing a pre-training language model; adopting a supervised fine-tuning strategy to optimize parameters of the pre-training language model, training the pre-training language model through a cross-entropy loss function of self-recurrence language modeling, and obtaining a multi-modal large language model; and inputting the large-scale high-quality text data set into the multi-modal large language model for processing, and obtaining a detection result.

The application discloses a kind of aircraft autopilot perception network training data set construction method and system.The method comprises: determining the scene richness requirement of data set collection;Each individual scene requirement and expected data proportion are refined;Each sample is combined category statistics, determines data volume according to existing data set information and project scene requirement, and is sampled based on Monte Carlo method;Actual scene building and data collection are carried out according to the sampling result.The application is based on manned electric aircraft autopilot neural network training data set scene richness requirement, designs a kind of scene richness building method, combines each scene, determines the sample quantity that needs to be collected, finally collects a large amount of sample data, and overcomes the defect that intelligent driving data set is insufficient for low-altitude flight.

The application discloses a kind of picture-text semantic alignment multimodal data expansion method and system, belong to data processing technical field, method includes: obtaining preprocessed water disaster original text and its corresponding water disaster original image;By large language model, obtain multiple texts based on water disaster original text and obtain multiple images based on corresponding water disaster original image by diffusion model;Based on the above text and image, obtain text features and visual features and are fused into multimodal fusion features, effectively expand data set, solve the problem that picture-text semantic dislocation in original data and social media images often contain a lot of noise or with text semantic not completely matched.

This invention discloses a method and system for rapid prediction of battery pack collision intrusion based on multi-fidelity data fusion. First, a training dataset containing high-fidelity and low-fidelity samples is constructed through finite element simulations with different mesh accuracies. Then, a two-level fusion model is established using Gaussian process regression. The predictions of the low-fidelity model are used as correction features to guide the high-fidelity model in accurate learning. Furthermore, based on an ensemble learning and Bayesian optimization framework, an improvement expectation criterion that incorporates simulation cost trade-offs is used for adaptive sampling. The location and accuracy level of newly added samples are intelligently determined, and the model is continuously optimized through iterative updates. This invention effectively resolves the contradiction between high-precision prediction and high computational cost, significantly reducing data acquisition overhead while ensuring prediction accuracy, providing an efficient and reliable technical means for battery pack collision safety assessment and optimization design.

This invention relates to the field of power grid information security technology, specifically a method, system, device, and storage medium for detecting malicious software in the power grid Internet of Things (IoT) based on active learning. The method involves acquiring application samples from power grid IoT nodes, extracting static features, dynamic features, and power grid context information to form a multi-dimensional feature vector, and organizing these into data blocks according to timestamps. Classification uncertainty scores are calculated from an unlabeled sample pool, a detector committee is constructed to calculate consensus entropy, and the sample with the most information content is selected by combining the two scores and submitted for expert annotation. A random forest classifier is trained to build a detection model. The F1 score of the current data block is evaluated; annotation stops when a preset threshold is reached and is applied to the next data block. Model performance changes are monitored, and when performance degradation is detected, batch retraining, rolling back historical configurations, or incremental updates are performed based on the evolution of the threat environment. The method reduces annotation costs through sample selection and addresses the conceptual drift problem of the power grid threat environment through an adaptive update strategy.

This invention relates to the field of computer vision and image processing technology, specifically to a dense debris detection method, velocity calculation method, and detection system based on YOLO and morphological contour extraction. The method includes: constructing a fused dataset; constructing and training an improved YOLOv5 model; detecting debris regions using the trained target YOLOv5 model; and obtaining the final detection results. This invention effectively solves the problem of scarce real data through virtual data generation technology, improving model training effectiveness and generalization ability. Through the fusion design of deep learning and traditional algorithms, it enhances the high-precision detection and localization performance of dense small debris while ensuring the continuity and stability of multi-target tracking, thereby improving the accuracy of velocity calculation for dense explosion debris. This invention enables high-precision identification, stable tracking, and accurate velocity measurement of explosion debris.

This invention discloses a semantically driven multi-camera collaborative shooting scheduling method for virtual studios, relating to the fields of broadcast television production and artificial intelligence control technology. The method includes the following steps: In a virtual studio production environment, video stream signals output from multiple physical cameras are frame-level aligned with rendered 3D scene data to generate multimodal synchronous input data; current program script information is acquired, and through multi-level feature extraction, a visual narrative vector representing the expected visual requirements is generated; based on the multimodal synchronous input data and combined with the 3D scene data, a camera position state vector representing the current image quality and content of each camera position is generated; based on the visual narrative vector and the camera position state vector, combined with the boundary constraints of the virtual scene, the optimal target camera position is selected, and a scheduling switching instruction is generated for executing multi-camera collaborative shooting scheduling. This invention improves the narrative coherence and visual professionalism of virtual studio content.

The present application relates to the technical field of battery curing detection, and more particularly to a method for detecting the curing degree of a semi-solid battery based on machine learning. The technical solution comprises the following steps: obtaining a multi-modal detection data set of the semi-solid battery to be detected; the multi-modal detection data set at least includes ultrasonic data, battery basic attribute parameters and curing process parameters; inputting the multi-modal detection data set into a pre-trained curing degree evaluation model, and directly outputting the curing degree prediction value and its prediction confidence interval of the semi-solid battery to be detected through model inference. By constructing a multi-modal data fusion and physically guided multi-task learning neural network, the present application realizes the comprehensive improvement of the semi-solid battery curing degree detection in detection accuracy, reliability and efficiency, and enables the model to have strong generalization ability and interpretability.