基于BiGRU和图对比学习的突发事件时序知识图谱补全方法研究OA

[Purpose/significance]During emergencies,social media short texts contain critical information but are heav-ily interfered with by noise.Traditional static knowledge graph completion techniques struggle to effectively address their dynamic evolution and data sparsity issues,making it imperative to introduce temporal modeling methods.[Meth-od/process]This study proposes a dynamic completion framework that combines the temporal feature capture capabili-ty of Bidirectional Gated Recurrent Units(BiGRU)with the noise-resistant representation learning advantages of Graph Contrastive Learning(GCL).At the completion level,the ConBiTE method is introduced,which captures tempo-ral dependencies through self-attention mechanisms and BiGRU,while leveraging GCL to enhance the completion of missing entities and relationships.At the construction level,RoBERTa-CNN-BiLSTM-CRF is employed for entity recognition,and the Wenxin large language model is utilized for relationship extraction,thereby improving the quality and efficiency of graph construction.[Result/conclusion]Experiments demonstrate that the proposed method outper-forms traditional approaches in both completion and construction tasks,providing comprehensive technical support for dynamic information analysis and emergency response during emergencies,with significant theoretical and practical implications.