4results about How to "Improve editability" patented technology

This invention relates to the field of natural language processing and information extraction technology, and discloses a method for automatic generation and iterative optimization of annotation guidelines for event extraction. The method includes: generating initial annotation guidelines based on annotation samples using a large language model and compressing them into lightweight guidelines for predefined event types; employing a two-stage extraction strategy, first identifying event types using the lightweight guidelines, and then recalling complete guidelines based on the types for end-to-end extraction to obtain prediction results; identifying and clustering prediction errors based on a predefined set of event-layer and argument-layer error types to form error clusters; and generating update operations for the annotation guidelines using a large model for each error cluster, and completing iterative optimization after verification of effectiveness. This invention achieves automated generation and continuous evolution of annotation guidelines, and significantly improves the maintainability, generalization ability, and event extraction performance of the guidelines through structured representation and error clustering mechanisms.

The application provides a city space layout generation method and device, which can be applied to the field of artificial intelligence technology. The method comprises the following steps: inputting a basic base map of a space to be planned into a layout generation model, taking space constraint elements included in the basic base map as constraint conditions, and generating an initial layout map including space layout elements; performing layout structure visualization and layout structure correction on the initial layout map based on the element state of each space layout element in the initial layout map and the space constraint elements, to obtain a corrected layout map; performing layout quality evaluation on the corrected layout map based on the distribution characteristics of the structured space layout elements in the corrected layout map, to obtain evaluation indexes; performing hierarchical decoupling processing on the corrected layout map, to obtain a hierarchical layout map including element layers; associating the element layers with the evaluation indexes, and displaying them in a display interface, so that a target object can edit each element layer; and generating a target layout map based on the edited hierarchical layout map.

The invention provides a fluid material reconstruction method and system based on three-dimensional Gaussian sputtering and physical prior, and the method comprises the steps: S1, reconstructing a time sequence three-dimensional geometric model of fluid through three-dimensional Gaussian representation based on a multi-frame image sequence of an input video, and estimating a velocity field of the surface of the fluid; s2, constructing an initial three-dimensional fluid volume velocity field, and constraining a physical boundary to obtain a physically reasonable three-dimensional fluid volume velocity field; and S3, taking the physically reasonable three-dimensional fluid volume velocity field as a supervision target, optimizing physical parameters of the fluid, further coupling the optimized physical parameters and the time sequence three-dimensional geometric model, and generating dynamic fluid assets capable of physical simulation. According to the method, full-automatic reconstruction of the three-dimensional dynamic fluid material assets from the single-view video is realized, and compared with the existing technology depending on multiple views, manual adjustment or a non-physical method, the process automation degree and the physical consistency of reconstruction are remarkably improved.

This invention discloses a method and system for medical image segmentation and 3D reconstruction based on region growing. The method includes the following steps: S1, acquiring the original medical image data of the target object and preprocessing it to generate a preprocessed 2D image sequence; S2, selecting seed points on the preprocessed 2D image sequence; S3, segmenting based on the seed points to generate segmented regions; S4, optimizing the boundaries of the segmented regions to generate an optimized binary mask; S5, generating the final binary mask; S6, completing the 3D model reconstruction; S7, spatially registering and fusing the reconstructed 3D model. The semi-automated segmentation process of this invention reduces the subjective differences of manual delineation, achieving over 90% consistency in reconstruction results for the same image across different operators, providing a reproducible technical basis for multi-center studies and efficacy evaluation.