Understanding architectural heritage: 3D-MELL framework of architectural heritage large language model based on 3D point cloud

• This study introduces an innovative 3D-MELL network architecture aimed at overcoming the deficiencies of big language models in the processing and comprehending of 3D point cloud data. This architecture enhances the semantic understanding of intricate 3D architectural components through big language models. • This research creates a front-end page utilizing HTML and CSS, facilitating the visual representation of architectural heritage and enabling intelligent dialogue, thus enhancing the interactive experience. • The study employs high-precision LiDAR scanning data to deliver comprehensive annotations of ancient architectural components, incorporating unique identification markers and spatial relationship indicators for each feature. The markers establish a robust data basis for comprehensive analysis and comprehension of items within 3D environments. The swift advancement of artificial intelligence technology indicates that large language models provide significant promise for comprehension and creative endeavors. Point cloud data has emerged as an essential technology resource in urban building, providing extensive information that facilitates many operations. Current research has thoroughly examined the utilization of point cloud data in semantic segmentation and target detection; nevertheless, the perceptual outcomes of these methods are sometimes challenging to implement in scene design directly. This study presents a novel 3D-MELL network architecture designed to enhance the limits of large-scale language modelling in processing 3D data. The architecture employs elements from ancient architectural components as the data source, with each element assigned distinct ID attribute markers and spatial relationship markers. These markers accurately represent the characteristics of the items and their interactions within the 3D environment. The model can be optimized by a distributed training technique to accommodate diverse downstream jobs with particular commands during the fine-tuning phase, demonstrating favorable training metrics and fitting outcomes. This project created a front-end page utilizing HTML and CSS frameworks to represent the chat interface, offering a novel approach to transmitting and developing architectural historical knowledge.