5results about How to "Avoid false matches" patented technology

This invention provides a method and system for semantic novelty search of scientific and technological literature based on a large-scale pre-trained model, belonging to the field of information retrieval technology. The method includes: acquiring the target user's query input text and retrieval constraints; performing preprocessing and standardization to obtain preprocessed query input text; performing multi-granularity semantic encoding fusion to determine the semantic vector of the preprocessed query input text; performing domain-adaptive fine-tuning to obtain an optimized BERT model; constructing a feature classifier to generate feature semantic representations to obtain feature semantic representation results; performing comprehensive novelty assessment to obtain a comprehensive novelty rating; and performing automated difference analysis to obtain difference analysis results. This invention solves the technical problem in existing retrieval schemes based on pre-trained models that use single-granularity semantic representations, which cannot fully capture the complex semantic structure of professional terms, resulting in inaccurate novelty search results.

The application discloses a high-temperature target multi-view three-dimensional point cloud global registration method, calculates normal vectors of point clouds in different views respectively, adopts a preset registration method to obtain initial rigid body transformation parameters of each view, initializes covariance of points and covariance of corresponding normal vectors, then carries out iterative optimization, in each iteration, adopts a point-level Gaussian mixture model combined with geometric consistency constraint to calculate credibility of each point and its nearest neighbor in other views, and updates rigid body transformation parameters and covariance parameters based on the credibility, until an optimization end condition is reached, then adopts the optimized rigid body transformation parameters to transform point clouds of each view to a global coordinate system, so that registered point clouds are obtained. The point-level Gaussian mixture model combined with geometric consistency constraint fully utilizes relatively stable geometric features in different views, so that the quality of high-temperature target point cloud registration is improved.

The application relates to a text detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: performing a character shape restoration process on a text to be detected to obtain a restored text; performing keyword matching on the restored text based on a keyword library; when the restored text matches a keyword group in the keyword library, obtaining a detection result of the text to be detected according to a keyword segmentation result of the restored text and the matched keyword group; when the restored text does not match a keyword group in the keyword library, performing keyword matching on the pinyin of the restored text based on a pinyin form keyword library, the pinyin form keyword library being obtained by converting keywords in the keyword library into pinyin; and when the pinyin of the restored text matches a pinyin form keyword group in the pinyin form keyword library, obtaining the detection result of the text to be detected according to a pinyin matching restriction condition, thereby improving the text detection accuracy.

The invention belongs to the technical field of computer vision, and relates to a VSLAM feature point matching method and system based on semantic topology constraint, and the method comprises the following steps: generating a current feature point set containing a preliminary semantic tag and a semantic recognition result; generating an initial candidate matching pool; generating a dynamic geometric check threshold for each current feature point; performing forward filtering on the initial candidate matching pool by applying a dynamic geometric verification threshold, and performing initial round matching based on appearance description similarity to generate a high-potential pre-matching point pair list; the geometric structure consistency of the high-potential pre-matching point pair list is analyzed, and geometric structure confidence scores are generated; performing reverse calibration and confirmation on the high-potential pre-matching point pair list to generate a final matching result; and generating a semantic tag correction instruction according to the reverse calibration process. According to the method, the problem that adopted geometric correction is generally based on a fixed fault-tolerant threshold and lacks self-adaptive adjustment capability for credibility of different scenes and feature points is solved.

This invention provides a method, device, mobile device, and storage medium for detecting the motion state of obstacles. The method includes: projecting a 3D point cloud of a scene observed by a lidar onto a ground plane and rasterizing it into a 2D grid map; constructing a grid map of the scene using multiple consecutive frames of the 2D grid map; shrinking empty areas based on distance errors to create gaps between occupied grids adjacent to the shrunken empty areas and the shrunken empty areas; projecting the 3D point cloud of the scene in the current frame observed by the lidar onto the grid map, and determining the motion state corresponding to the 3D point cloud based on its location in the grid map; and detecting the motion state of obstacles based on the motion state of the 3D point cloud. This invention eliminates the need for point cloud clustering to obtain the motion state attributes of the point cloud, avoiding target mismatches caused by occlusion and clustering errors, and does not require specific target speed.