深圳大学学报（理工版）2026，Vol.43Issue(5)：533-540,8.DOI:10.3724/SP.J.1249.2026.05533
面向领域知识抽取的动态提示调度与上下文协同优化
Dynamic prompt scheduling and context co-optimization for domain-oriented knowledge extraction
摘要
Abstract
To address the problems of insufficient extraction accuracy and inadequate utilization of contextual conditions for structured knowledge extraction from vertical domain documents,this paper proposes a dynamic prompt scheduling and context co-optimization knowledge graph extraction(DyPOKE)method.By adopting semantic chunking,dynamic prompt template scheduling and context-injection mechanisms,this method enables collaborative modeling of prompt strategies and semantic condition.Experiments are conducted based on texts of manufacturing-processing and antenna-design domains,with comparisons against the baseline methods such as one-stage joint neural information extraction with global features(OneIE),relation extraction by end-to-end language generation(REBEL),and extract-define-canonicalize(EDC),as well as against various prompting configurations.The experimental results show that DyPOKE method achieves favorable performance on both entity recognition and relation extraction tasks,with F1 scores of 0.90 and 0.86,respectively.Ablation experimental results further indicate that for the relation-extraction task,DyPOKE method improves the F1 score by 7.5%compared with the second-best prompt configuration.Cross-model transfer experiments further demonstrate that DyPOKE method maintains stable output performance over different underlying large language models.These results indicate that the collaborative design of dynamic prompt scheduling and contextual constraints contributes to improving the reliability of structured knowledge extraction in vertical domains,providing a reusable framework for the automatic construction of specialized domain knowledge graphs.关键词
人工智能/动态提示调度/垂直领域知识图谱构建/大语言模型/结构化信息抽取/自然语言处理Key words
artificial intelligence/dynamic prompt scheduling/vertical domain knowledge graph construction/large language model/structured information extraction/natural language processing分类
信息技术与安全科学引用本文复制引用
丛智鑫,袁一帆,吴秉哲,李坚强,金雄男,黄鑫彬,李天波,李庆庆,林健铭,王利,宋代强,刘彦熙..面向领域知识抽取的动态提示调度与上下文协同优化[J].深圳大学学报（理工版）,2026,43(5):533-540,8.基金项目
National Natural Science Foundation of China(62306287) （62306287）
Scientific Foundation for Youth Scholars of Shenzhen University(868-000001032902) （868-000001032902）
State Key Laboratory of Radio Frequency Heterogeneous Integration Independent Scientific Research Program(2025006) 国家自然科学基金资助项目(62306287) （2025006）
深圳大学青年教师科研启动经费资助项目(868-000001032902) （868-000001032902）
射频异质异构集成全国重点实验室自主课题资助项目(2025006) （2025006）
