教育大模型赋能隐性知识转化:价值意蕴、赋能逻辑与实践进路OA

Tacit knowledge,as a core resource underpinning teachers' professional judgment,classroom management,and con-textual sensitivity,has long been constrained by difficulties in its capture,transformation,and transfer.With the rapid advancement of generative artificial intelligence,educational large models,driven by large language models,multimodal systems,and semantic knowl-edge graph technologies,have opened up new possibilities for addressing these challenges.Grounded in the SECI knowledge conver-sion model,this study focuses on three key technological affordances of educational large models,which are multimodal integration,contextual reconstruction,and cognitive augmentation,and proposes an enabling logic through which they can facilitate tacit knowl-edge transformation.Furthermore,this study proposes a five-layer operational architecture for educational large models oriented to-ward tacit knowledge transformation,comprising the physical layer,data layer,analysis layer,interface layer,and service layer.This architecture provides technical support for knowledge transformation,which follows a pathway of perception-articulation-modeling-generation.It enables tacit knowledge to shift from inexpressible forms toward preliminary states of articulation and perceptibility.Ed-ucational large models are thus evolving from tools for content generation into cognitive partners in teaching,offering promising ways to address challenges of structural representation and contextual transfer of tacit knowledge.