4results about How to "Extract automatically" patented technology

This invention discloses a requirement tracking method, apparatus, device, and medium based on a large language model, relating to the field of artificial intelligence technology. The method includes: performing hierarchical structure tracking and nested table linearization on the document to be processed, and semantically segmenting it; submitting each text block in parallel to a large language model to extract structured requirement items according to preset fields; calculating the cosine similarity between requirement items using an embedding model to recall a candidate matching set; then using the large language model to perform semantic association matching and coverage determination to obtain association mapping data; using the large language model to perform multi-level semantic matching on the requirement items, constructing a multi-level tracking link that supports cross-level matching between non-adjacent documents; and parsing the test item result description text and mapping it to a completed state when the link ends and contains a test document. This invention can improve the automation and accuracy of requirement item extraction, association matching, coverage determination, and full-link tracking, and enhance the fault tolerance of the tracking link.

The invention relates to the technical field of remote sensing image processing, and provides a DOM ground object automatic extraction method and system based on key point detection. The method comprises the following steps: obtaining a DOM graph to be detected; cutting and partitioning the DOM image according to a preset partitioning size and an overlapping degree to obtain a partitioned image; inputting the block images into a target detection model based on a YOLOv8 key point network to obtain a target detection frame and key point coordinates of each block image; and carrying out vector merging on the detection result of each block image to generate a ground object extraction vector diagram with a target detection frame and key point coordinates. According to the method, the refined angular points of the specified ground feature can be quickly and automatically extracted, the high-precision vectorized contour is generated, a high-quality and high-precision surveying and mapping result is provided, and quick and high-precision recognition and extraction of the key points of the target ground feature are realized.

The present invention provides a depth camera calibration method, system, device and medium, including: obtaining a checkerboard image, binarizing the checkerboard image, generating a first checkerboard binarized image; extracting multiple first contours from the first checkerboard binarized image, and determining the central checkerboard area of ​​the checkerboard image according to the first contours; binarizing the target checkerboard image to generate a second checkerboard binarized image, and extracting multiple second contours from the second checkerboard binarized image; screening out grid contours from the multiple second contours, and then determining the center point of each grid contour, and determining the corner points of each grid area according to the center points of four adjacent grid contours; according to the corner points of each grid area, each grid area is numbered with the central checkerboard area as the center, and the internal and external parameters of the depth camera are determined according to the corner points and the numbers. The present invention can automatically calculate the internal and external parameters of the camera and realize automatic calibration of the depth camera.

The invention discloses a standard operation process extraction method and equipment based on a large language model, and relates to the technical field of computers. The method comprises the following steps: analyzing operation documents corresponding to a standard operation process extraction task, segmenting each operation document into at least one fragment, and determining fragment index information corresponding to each fragment; for each fragment, determining a structuring step corresponding to the fragment based on an extraction result of structuring extraction of the fragment by a large language model; and according to the fragment index information corresponding to each fragment, combining the structured steps corresponding to each fragment to obtain a structured process corresponding to the standard operation process extraction task. According to the technical scheme, through the technologies of text fragmentation, structured extraction, structured aggregation and the like, the problems of low extraction efficiency and low accuracy of the structured process are effectively solved, and automatic and intelligent extraction of the structured process is realized.