基于结构感知的煤矿标准文档解析方法OA

To enhance the efficiency of knowledge supply and the accuracy of compliance determination for coal mine safety relev-ant standard documents in intelligent applications,and to address the issues of semantic representation drift and lack of logical boundaries caused by physical chunking in traditional Retrieval-Augmented Generation(RAG)systems,this study proposes and con-structs a Structure-Aware Logical Chunking(SALC)algorithm.First,based on a fine-tuned Layout Language Model version 3(Lay-outLMv3)model,the method integrates text,layout,and image features to perform fine-grained semantic annotation on documents.Second,a semantic conflict self-correcting document topology parsing algorithm is designed to construct a Document Tree with Path Semantics(DTPS).Finally,a semantic retrieval tag-driven dynamic aggregation strategy is employed to generate structurally com-plete logical chunks.Experimental results show that the model achieves a Macro F1 score of 93.53％and a Clause-Level F1 score of 91.79％,outperforming Bidirectional Encoder Representations from Transformers(BERT)and Document Understanding Trans-former(Donut).In end-to-end retrieval evaluation,the SALC algorithm achieves a Hit Rate of 93.36％,a Mean Reciprocal Rank(MRR)of 0.89,and a Context Precision of 71.92％,surpassing the Recursive Character Text Splitter(RCTS)and the Query Decom-position driven iterative Retrieval Augmented Generation(QD-RAG)model.Compared with the coal mine domain document pars-ing models of Coal Mine Safety Equipment Knowledge Graph Construction Method(CMSE-KGM)and Prompt Relation oriented Parsing Engine-Universal Information Extraction(PRoPE-UIE),SALC improves the Hit Rate by 3.60 and 6.94 percentage points re-spectively,the MRR by 0.09 and 0.06.Results regarding different document lengths indicate that SALC maintains a Hit Rate of 82.17％for long documents exceeding 20 pages and scenarios with Optical Character Recognition(OCR)noise interference,signific-antly outperforming comparative models.Ablation studies further validate the effectiveness of the topology self-correction and dy-namic aggregation strategies.