7results about How to "Fully reserved" patented technology

The invention discloses a construction method, system and equipment of a power dispatching knowledge question-answering system and a storage medium. The construction method comprises the steps of obtaining a power dispatching semantic document needing to be processed by the power dispatching knowledge question-answering system; sequentially carrying out character-based segmentation, proposition conversion and proposition combination on the power dispatching semantic document on the basis of the large language model and the related cue words to obtain a plurality of text blocks; based on the large language model and the related prompt words, identifying and extracting entities related to power dispatching and relationships among the entities from each text block; constructing a local graph for each text block on the basis of the large language model and the related prompt words, the entities extracted from each text block and the relationship among the entities; traversing each text block, and combining all the local graphs into a global graph; and on the basis of the large language model and the related prompt words, according to the question type queried by the user, a reply text is correspondingly generated by matching a minimum local graph which is most related to the global graph in the global graph.

The invention discloses a brain stimulation reconstruction method based on visual experience retrieval, a medium and equipment, and relates to the technical field of computational vision, the method comprises the following steps: extracting low-level visual clues and high-level visual clues of a to-be-processed fMRI signal to ensure the retention of semantic information in a reconstruction process; by simulating the memory retrieval process of the human brain, the visual memory image is retrieved, context information is provided for degraded visual stimulation, the image reconstruction precision is further improved, and semantic details are enriched; a plurality of reconstructed images are generated by using low-level visual cues and super visual cues (a fusion result of high-level visual cues and CLIP features of visual memory images), and a final reconstructed image is selected from the reconstructed images, so that key semantic information in visual stimulation can be fully captured or reserved, and the accuracy of an image reconstruction result is improved.

The invention discloses a paragraph segmentation method and device based on content awareness, and relates to the field of document processing. In the method, an original file in an original format is converted into a target file in a target format, and a text and a table are identified and separated from the target file; traversing the text to identify paragraphs and outline levels corresponding to the paragraphs, and splicing paragraph contents according to the outline levels to form structured text data; traversing the table, extracting header data and data of each cell, and constructing key value pairs for the header data and the data of each cell to form table data; identifying a plain text from the text, segmenting the plain text into lexical units, and processing the lexical units by using a preset rule to form array data; and combining and outputting the text data, the table data and the array data. By implementing the technical scheme provided by the invention, the bid inviting word file is automatically and accurately segmented into logically independent paragraphs.

The invention relates to the technical field of image processing, and discloses a sparse CT projection reconstruction method based on dense large-core attention, comprising the following steps: interpolating a sparse sinusoidal graph by a cubic spline interpolation method to obtain an initial artifact sinusoidal graph; introducing a dense large-core attention block including a dense sub-block, a large-core attention sub-block and a convolutional layer to construct a dense large-core attention encoding and decoding network model; inputting the initial artifact sinusoidal graph and a non-sparse sinusoidal graph into the dense large-core attention encoding and decoding network model for training, learning the error between the artifact sinusoidal graph and the non-sparse sinusoidal graph, and obtaining a trained dense large-core attention encoding and decoding network model; reacquiring the sparse sinusoidal graph and inputting it into the trained dense large-core attention encoding and decoding network model, obtaining a repaired sinusoidal graph and reconstructing it by a filtered back-projection method, and obtaining a high-quality CT image; the method reduces the error between the output result and the label value, and improves the model performance and prediction accuracy.

This application relates to an AI model image generation method, system, device, and medium, belonging to the technical field of image processing. It involves collecting multimodal data of the target garment, including mannequin images, flat static images, and material close-up images; selecting a reference image from a target pose library whose pose matches the desired pose, and extracting the corresponding pose skeleton image as the target pose skeleton image; inputting the flat static image and the material close-up image into a visual language model to generate a text description; and inputting the target pose skeleton image, mannequin image, and text description into a pre-trained LoRA diffusion model to generate a preliminary dressed image. The LoRA diffusion model's input layer includes an independent pose condition injection channel, through which the target pose skeleton image is input into the LoRA diffusion model. This application has the beneficial technical effect of avoiding stiff and unnatural AI model poses, thereby improving the aesthetics of the generated images.

The invention belongs to the field of food processing, and particularly discloses paper-wrapped preserved meat with tea flavor and a processing method thereof, tea leaves or a tea leaf extract is added in the preparation process of the preserved meat, the tea leaf extract is prepared through cold extraction and freeze-drying processes, and it is ensured that nutritional ingredients and fragrance in the tea leaves are effectively reserved. The selected tea leaves comprise high-quality tea leaves such as Longjing, Tieguanyin or Pu'er tea leaves. The processing method of the preserved meat comprises the steps of raw material selection, pickling process, smoking, air drying and environment-friendly paper package packaging, and a tea extract and probiotic fermentation liquor are mixed in pickling seasoning, so that the taste and the nutritional value of the preserved meat are improved. The preserved meat is endowed with unique tea aroma flavor, the health attribute of the preserved meat is enhanced through the probiotic fermentation liquor, and meanwhile, environment-friendly paper bags are adopted for packaging, so that the requirements of modern consumers for health and environmental protection are met.

The present invention relates to the field of electrode material preparation, and in particular to a preparation method and application of a high entropy Prussian blue sodium ion battery positive electrode material. The preparation method of the high entropy Prussian blue sodium ion battery positive electrode material provided by the present invention comprises the following steps: mixing a solution of a transition metal salt and a sodium salt with a solution of sodium ferrocyanide, sodium citrate, and a surfactant, stirring and reacting, standing for aging, filtering, washing, and drying to obtain the high entropy Prussian blue sodium ion battery positive electrode material; wherein the metal ions in the transition metal salt are divalent iron ions, divalent manganese ions, divalent cobalt ions, divalent nickel ions, and divalent copper ions; the concentration of sodium citrate in the solution of sodium ferrocyanide, sodium citrate, and a surfactant is 120-3000mmol / L. The material obtained by the preparation method of the present invention is applied to sodium ion batteries to comprehensively improve the cycle stability, specific capacity, and voltage of sodium ion batteries.