计算机应用研究2025，Vol.42Issue(9)：2599-2606,8.DOI:10.19734/j.issn.1001-3695.2025.03.0026
基于语义增强与候选排序优化的背景感知事件预测方法
Context-aware event forecast method based on semantic enhancement and candidate ranking optimization
摘要
Abstract
Event forecasting aims to integrate the event semantic information with structural relationships to precisely forecast future events.To address the issues of insufficient semantic capture and limited external knowledge integration in existing graph neural network methods,this paper proposed a context-aware event forecast method based on semantic enhancement and candi-date ranking optimization(SEC RO).The method employed a three-stage framework:firstly,a large language model generated high-quality event node embeddings to address semantic expression deficiencies;secondly,a graph neural network modeled the structural and relational connections among events,generating the preliminary prediction results;lastly,a candidate ranking op-timization mechanism integrated world knowledge from the large language model,enhancing the event prediction accuracy.Ex-periments on three public datasets show that the method improves mean reciprocal rank(MRR)by 8.34 and 6.84 percentage points over RGCN and SeCoGD respectively,achieving state-of-the-art performance.Extended experimental results further con-firm that the method enhances the performance of existing graph-based approaches for event prediction.关键词
语义增强/事件预测/图神经网络/大语言模型Key words
semantic enhancement/event forecasting/graph neural network/large language model分类
信息技术与安全科学引用本文复制引用
马荣,马博,王震,艾孜麦提·艾尼瓦尔,杨雅婷,王磊..基于语义增强与候选排序优化的背景感知事件预测方法[J].计算机应用研究,2025,42(9):2599-2606,8.基金项目
新疆维吾尔自治区"天山英才"科技创新领军人才资助项目(2022TSYCLJ0046) （2022TSYCLJ0046）
新疆维吾尔自治区自然科学基金重点项目(2023D01D17) （2023D01D17）
新疆维吾尔自治区"天山英才"培养计划资助项目(2023TSYCCX0041,022TSYCCX0059) （2023TSYCCX0041,022TSYCCX0059）
中国科学院青年创新促进会优秀会员资助项目(Y2023118,Y2021112) （Y2023118,Y2021112）
新疆维吾尔自治区重点研发任务专项资助项目(2023B03024) （2023B03024）
新疆维吾尔自治区自然科学基金资助项目(2022D01B207) （2022D01B207）
新疆维吾尔自治区上海合作组织科技伙伴计划及国际科技合作计划资助项目(2023E01019) （2023E01019）
