9results about How to "Extract complete" patented technology

The invention discloses a judgment document element extraction method based on a large model, a storage medium and equipment, and the method comprises the steps: collecting a large number of judgment documents, carrying out the cleaning and word segmentation of each judgment document, and marking key element information; taking the judgment document as the input of the large language model, outputting a key element extraction result of the judgment document, setting a reward function based on the marked key element information, and performing feedback optimization on the large language model in combination with a dominant actor-commentator algorithm; and inputting a newly obtained judgment document into the optimized large language model, and extracting key element information. The judgment document element information can be accurately extracted, the analysis efficiency and accuracy of the judgment document are effectively improved, and manual intervention is reduced.

The invention discloses a processing method and system for OFD document conversion, and the method comprises the steps: triggering an OFD conversion operation when a PDF document is exported, so as to extract document structure information and document resource data; performing format conversion on the document structure information and the document resource data, and then adding the document structure information and the document resource data to an OFD resource library; performing text recognition on the text resource data to obtain text segment content information; performing position identification on the text segment content information and storing the text segment content information in the OFD resource library; according to the OFD document conversion method, the image resource data are subjected to image recognition to obtain image feature information, so that the image resource data are identified in the OFD resource library, the problems of format and style loss, incomplete resource processing, low conversion efficiency, insufficient integration level, poor cross-platform compatibility and the like in the existing OFD document conversion technology are solved, and low-cost, high-safety and multifunctional OFD document conversion is realized.

The embodiment of the application provides an IPSA-based ship target identification method and system for an airborne infrared image, wherein the method comprises the following steps: preprocessing an acquired original airborne image; performing global threshold segmentation on the preprocessed image based on an improved PID search algorithm to obtain a global water mask, and performing processing on the preprocessed image based on a local adaptive threshold segmentation method to obtain a local water mask; generating a final water mask according to the global water mask and the local water mask; constructing a candidate target region in a non-water region constrained by the final water mask; determining all connected regions in the candidate target region, calculating the geometric features and the gray features of each connected region, and screening the connected regions according to a preset feature threshold to determine the connected regions meeting the screening condition as ship targets. The technical scheme provided by the application can adapt to a complex marine environment and efficiently and accurately extract ship targets.

The invention belongs to the field of coal gangue grading recognition, and particularly discloses a coal gangue grading recognition system based on deep learning, which comprises a coal gangue image acquisition module, a coal gangue edge separation module and a coal gangue classification module. According to the scheme, gray level inversion is carried out on the initial image to improve the detail definition, a bounded sum operator is applied to realize migration of low-brightness area pixels to a high-brightness area, adaptive threshold processing is adopted to screen edge pixels, and complete and accurate extraction of coal gangue edges is realized; the method comprises the following steps: extracting texture features by adopting empirical wavelet transform, fusing mean value, contrast and homogeneity features calculated by a gray-level co-occurrence matrix, building a deep convolutional pulse neural network fused with a pulse coding technology, introducing an arithmetic optimization algorithm to optimize key parameters of a coal gangue classification model, capturing spatial features and time sequence pulse features of a coal gangue image, and constructing a deep convolutional pulse neural network fused with a pulse coding technology; and comprehensive mining and efficient fusion of the multidimensional key features of the coal gangue image are realized.

The invention relates to the field of image detection, in particular to an illite and pine needle oil load uniformity detection method based on image recognition, which comprises the following steps: acquiring a composite powder microscopic image under a lateral illumination condition to obtain an effective detection grayscale image and a seed point set; carrying out joint evaluation on local gradient and curvature response of the effective detection grayscale image to obtain an artifact suppression factor; performing joint evaluation on the consistency of the region growth direction and the local flux characteristic to obtain a flux compensation factor; carrying out fusion modulation on the gray difference judgment cost through an artifact inhibition factor and a flux compensation factor, obtaining a final growth judgment cost, and generating a load region binary mask; a load uniformity index is obtained by carrying out gridding load rate statistics and dispersion calculation on a binary mask of a load area, so that the problem of load uniformity quantization misalignment caused by shadow error growth leakage and coexistence of early stop and missing detection on an oil film weak edge is solved.

This invention belongs to the field of accounting voucher recognition technology, specifically a deep learning-based intelligent recognition and automatic classification system for accounting vouchers. It includes: a multimodal acquisition and preprocessing module, a deep learning feature extraction module, an accounting voucher recognition module, an intelligent classification module, an intelligent verification and risk warning module, a voucher structure generation module, a record learning module, a system update module, a distributed storage and retrieval module, and an interface interaction and control module. The beneficial effects of this invention are: it can stably handle complex vouchers such as those that are blurry, have overlapping seals, are handwritten, or are mixed with other documents; it has a high accuracy rate in extracting key information; it can guarantee the accuracy of recognizing blurry, tilted, wrinkled, stamped, handwritten, and mixed-document overlapping vouchers; and it extracts key information completely to meet the needs of actual business scenarios.

The application relates to the technical field of underwater acoustic positioning, in particular to a self-adaptive underwater acoustic positioning correction method and system based on swarm intelligence, which comprises the following steps: reconstructing original signals of mutual detection of underwater acoustic reference nodes in a high-dimensional phase space, and extracting an arrival time characteristic vector from a phase domain trajectory; based on multi-target particle swarm optimization, performing multi-target optimization on a local neighborhood geometric structure of the characteristic vector to obtain optimal local linear embedding parameters; according to the parameters, globally splicing the characteristic vector manifold to obtain a time delay space manifold; performing variational mode decomposition on the time delay space manifold to obtain a dynamic deviation residual; according to a projection position of a target emission signal on the manifold, fusing the dynamic deviation residual to correct time delay distortion, and obtaining a self-adaptive time delay correction amount; and analyzing the correction amount intersection positioning to obtain a space position of a target to be positioned; the application can improve the correction efficiency of self-adaptive underwater acoustic positioning.

This invention provides a polyp image segmentation method based on depth guidance and a triple decoder. Using RGB images as input, the method expands the channels of the depth image, extracts its multi-layer features, and performs layer-by-layer feature fusion. This effectively utilizes the spatial structural characteristics of polyps in the depth image, enhances multi-scale semantic and spatial location information, and helps the network extract the polyp region more completely. A triple decoder architecture is designed to extract fine-grained detail features and deep semantic features of the polyps. The combined decoder integrates the advantages of both types of features, improving multi-scale feature extraction and fusion capabilities. A high- and low-resolution dual-branch feature extraction strategy is adopted to adapt to high-resolution input. Combined with the advantages of a pre-trained backbone network, this method reduces model computational complexity while ensuring no loss of polyp detail information, thus balancing segmentation performance and operational efficiency.

This invention relates to the field of image data processing technology, and in particular to an image data edge preprocessing method and system adapted to a tongue image analyzer. This invention pre-identifies and enhances weak boundary candidate regions, constructs and adaptively fuses a dual-branch system of high-frequency edge preservation and low-frequency noise reduction, accurately preserving weak boundary details while suppressing noise. Through gradient-guided directional enhancement, it achieves targeted enhancement and protection of low-contrast weak boundaries in tongue images, while effectively suppressing background noise. Ultimately, it provides high-quality input images with significantly improved signal-to-noise ratio and enhanced weak boundary features for classic Canny edge detection, enabling the stable and complete extraction of key anatomical edges that cannot be identified in traditional processes.