计算机应用研究2026，Vol.43Issue(2)：534-543,10.DOI:10.19734/j.issn.1001-3695.2025.06.0211
文本流中路线图在线抽取模型
Online roadmap extraction model in text streams
摘要
Abstract
This paper transformed user spatial transfer information contained in text streams into route maps to provide users with intuitive route and experience visualization.Firstly,it proposed a large model-based spatiotemporal event extraction model.The model constructed a route knowledge framework and extraction templates.It used a fine-tuning dataset for model adapta-tion.Then,the paper proposed a large model-based text segmentation model.This model employed text partitioning templates and a fine-tuning dataset for adaptation.Next,the paper proposed an online path generation method.This method designed in-ference techniques for entity attributes and relationships.It adopted a weighted scoring strategy to generate optimal paths.Final-ly,the experiments performed on real-world datasets.Results show that the proposed models achieve better performance than other large models in text segmentation and event extraction tasks.The proposed method increases entity reasoning accuracy by 16％compared to multi-feature entity matching methods.These findings validate the effectiveness of the proposed models and method.关键词
大语言模型/事件抽取/提示工程/指令微调/社交媒体数据/实体推理Key words
large language model/event extraction/prompt engineering/instruction fine-tuning/social media data/entity reasoning分类
信息技术与安全科学引用本文复制引用
刘俊岭,杨梦迪,孙焕良,许景科..文本流中路线图在线抽取模型[J].计算机应用研究,2026,43(2):534-543,10.基金项目
国家自然科学基金资助项目(62073227) （62073227）
国家重点研发计划资助项目(2021YFF0306303) （2021YFF0306303）
辽宁省教育厅资助项目(LJ212510153014) （LJ212510153014）
