Digital Preservation of Intangible Cultural Heritage Empowered by Blockchain Through Distributed Storage and Dynamic Traceability Algorithm Research

To address these persistent deficiencies in existing methodologies, we introduce a novel end-to-end framework consisting of two key innovations: the Heritage Language and Identity eXtractor (HeLiX) model and the relational alignment for indigenous semantic embedding (RAISE) strategy. HeLiX is a symbolic transformer designed to construct rich, interpretable graphs from complex multimodal, multilingual intangible cultural heritage (ICH) sequences. By incorporating community-level embeddings, role-sensitive alignment mechanisms, and epistemic context vectors, HeLiX ensures the traceability of knowledge, the ethical and faithful representation of cultural narratives, and the preservation of cross-generational fidelity essential for authentic heritage modeling. Complementing this, the RAISE strategy introduces a sophisticated alignment methodology that operates on symbolic structures across diverse traditions by leveraging domain-sensitive semantic kernels, role-grounded alignment constraints, and cultural canonicalization rules. This combination enables not only high-fidelity symbolic alignment but also supports critical goals such as ethical data co-governance, long-term narrative continuity, and computational rigor in heritage science workflows. Experimentally, our comprehensive framework demonstrates superior performance benchmarks across multiple tasks, including knowledge graph construction from heritage data, ritual sequence alignment across cultural contexts, and the induction of multi-community ontologies. These experimental outcomes substantiate the framework’s capability to advance symbolic, ethically grounded artificial intelligence, contributing meaningfully to the field of computational heritage science. Moreover, it aligns strongly with the overarching mission of developing explainable, transparent, and culturally-aware intelligent systems that drive forward responsible and inclusive knowledge discovery.