基于多模态信息融合的铁路安全知识深度挖掘与生成式推荐方法OA北大核心

The rapid digital and intelligent transformation of railway information systems has created an urgent de-mand for fine-grained,explainable safety knowledge recommendations.To address the fragmentation of cross-mod-al associations and insufficient alignment with operational rules exhibited by traditional approaches,a framework in-tegrating multimodal feature fusion with generative reasoning is investigated.A hierarchical railway safety knowl-edge graph is constructed,and topological features under business constraints are extracted via the Node2Vec algo-rithm.Simultaneously,a lightweight Transformer encoder(GTE)captured deep semantic embeddings of individual safety clauses.To balance contributions from graph and text features,a tunable weighting strategy is introduced,dy-namically controlling the fusion ratio of text vectors and graph embeddings and applying a dual-constraint mecha-nism based on cosine similarity and predefined rules to generate candidate recommendations.A three-stage progres-sive retrieval architecture is designed to achieve precise multimodal alignment and suppress noise.Finally,the Deep-Seek-R1 large language model served as the reasoning engine,with domain-specific prompting converting retrieved candidates into executable decision plans,thereby enhancing coherence and interpretability.Experiments on 27 safe-ty documents from a railway operator,using a similarity threshold of 0.85 and a maximum of 10 recommendations per query,demonstrated a recommendation accuracy of 95%(an 8-percentage-point improvement over traditional methods)along with significant gains in contextual relevance and explainability.This investigation confirms the syn-ergistic benefits of multimodal retrieval and generative reasoning,providing a robust technical foundation for evolv-ing railway safety knowledge services from precise recommendation to intelligent decision support.