Digital preservation and dissemination of performance-based intangible cultural heritage based on artificial intelligence and deep learning

This study explores the application of deep learning (DL) technology in artificial intelligence; it realises the digital protection and dissemination of ethnic intangible cultural heritage (ICH).Taking performance-based ICH as the entry point, a multi-category and diversified video dataset is constructed.Strict screening and professional annotation ensure the coverage of typical cultural expression forms and movement characteristics.On this basis, a DL-based model framework is proposed; thus, it can achieve automatic recognition, classification, and sequence modelling of dynamic ICH behaviours.Through model training and optimisation, the proposed method can effectively capture the spatiotemporal features of complex cultural actions, thereby realising high-precision recognition of performance-based ICH.This study improves the efficiency of digital processing of performance-based ICH; it also provides technical support for structured storage and intelligent dissemination of ICH resources.Thus, this is of certain significance to promoting digital protection and global dissemination of ICH.