摘要
提出了一种面向俄乌冲突的时序知识图谱推理方法,该方法基于进化图演变的思路,将历史事件和相关知识构建成一个时序知识图谱,并通过对知识图谱中节点和边的演化过程进行建模,实现了对未来事件的预测和分析。具体而言,首先利用自然语言处理技术对公开的新闻报道、社交媒体信息等进行爬取和处理,提取关键词和时间信息,并将其转换为结构化数据。然后,利用这些数据构建起一个时序知识图谱,其中每个节点表示一个事件或概念,每条边表示它们之间的关系。其次,通过基于进化图演变的算法对知识图谱建模,从而能够模拟节点和边在不同时间段内的演化特征。最后,通过在俄乌冲突数据集上构建推理系统,实验结果表明该模型与系统设计具有良好的效果和应用前景。
This paper proposes a temporal knowledge graph inference method for the Russia-Ukraine conflict,which is based on the idea of evolutionary graph evolution.This method constructs historical events and related knowledge into a time-series knowledge graph,and achieves prediction and analysis of future events by modelling the evolutionary process of nodes and edges in the knowledge graph.Specifically,using natural language processing techniques,this study first crawls and processes publicly available data,like news reports and social media information,to extract keywords and temporal information,and converts them into structured data.These data are then used to construct a temporal knowledge graph,where each node represents an event or concept and each edge represents a relationship between them.Next,the knowledge graph is modelled by an algorithm based on the evolution of the evolutionary graph,thus enabling the simulation of the evolutionary characteristics of nodes and edges over different time periods.Last,by constructing an inference system on the Russian-Ukrainian conflict dataset,the experimental results demonstrate that the model and system design show good results and application prospects.
作者
张骁雄
杨琴琴
何浩然
丁鲲
Zhang Xiaoxiong;Yang Qinqin;He Haoran;Ding Kun(The Sixty-third Research Institute,National University of Defense Technology,Nanjing 210007,China;Laboratory for Big Data and Decision,National University of Defense Technology,Changsha 410073,China;School of Computer Science,Nanjing University of Information Science and Technology,Nanjing 210044,China;School of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China)
出处
《网络安全与数据治理》
2023年第S01期157-162,共6页
CYBER SECURITY AND DATA GOVERNANCE
关键词
时序知识图谱
俄乌冲突
推理
temporal knowledge graph
Russia-Ukraine conflict
reasoning
