韧性电网下的时空多图卷积网络恐怖主义事件模型

打开文本图片集

关键词：恐怖主义；事件预测；知识图谱；时空多图卷积网络；韧性电网DOI：10.15938/j. jhust.2025.05.010中图分类号：TM73 文献标志码：A 文章编号：1007-2683（2025）05-0096-10

Abstract：Terrorsm isoneof themostimportantthreats totoday’scivilization.Terorsmnotonlydisturbsthesocialorderbut alsoaffctstequalityofifArtifialintellgencesowsgreatpotetialinprovdingsuportfodataanalysandpateentiatio incounter-terorismactivites.Onthisbasis，tispaperproposesanelectricpower terorismevent predictionmethodbasedonhe knowledgegraphndspatial-temporalulti-graphonvolutioalnetworkundertheresilientpowergid，whichcaefectivelymieth data nglobal terorismdatabase（GTD），andconstructaknowledge graph.Theknowledge graphcontainsnodesandrelationsipsthat describethecharacteristicsofachteroristattackThen，weobtainthetrendandperiodcityofterristeventsthroughtewavelet transform，andeploytespatiapoalultiapovolutioaletwrktodeltespa-poraldamicelatiosf timeseriesdataoftrroristevents.Finally，thebehaviorof teroristeventsispredictedthroughtherainedmodel.Theexperiental results show that the performance of the proposed method is more than 90% in terms of accuracy，precision，recall， and F1-score .Our method is significantly superior to the existing methods.

Keywords：terorism；eventprediction；knowledgegraph；spatial-temporal multi-graphconvolutionalnetworks；resilient power grid

0 引言

电力系统是国家关键基础设施，电力安全与政治安全、经济安全、网络安全、社会安全等总体国家安全体系中的诸多领域密切关联。（剩余14038字）