电子学报2025，Vol.53Issue(10)：3705-3717,13.DOI:10.12263/DZXB.20250599
融合多维过程视角:一种基于上下文感知图注意力的业务流程预测框架
Fusing Multi-Dimensional Process Views:A Context-Aware Graph Attention Framework for Business Process Prediction
摘要
Abstract
Amidst deepening digital transformation,data-driven process analysis,with Predictive Process Monitoring(PPM)at its core,has become pivotal for enhancing enterprise operational efficiency and decision-making.To improve the accuracy and generalization of PPM,existing research focuses on mining deep representations from vast event logs.Howev-er,the evolution of real-world business processes is influenced not only by temporal logic but also by underlying structural factors such as resource allocation and data dependencies.This complexity poses a formidable challenge to the representa-tional capabilities of existing predictive models.Specifically,the performance of mainstream predictive methods is often constrained by their reliance on a singular process view and static information fusion strategies.Most approaches,even those based on Graph Neural Networks(GNNs),tend to model processes from a single control-flow perspective.This over-looks critical dimensions such as resource interactions and data dependencies,creating a gap in the representation of deep process structures and multi-dimensional relationships.Furthermore,the few studies that attempt to integrate multi-dimen-sional information typically employ static fusion strategies,lacking a context-aware fusion capability and resulting in mod-els with insufficient adaptability.To address these challenges,this paper proposes a context-aware multi-view graph fusion(CAM-GF)framework.The framework first transcends the limitations of the control-flow perspective by systematically con-structing a process graph map.This graph map comprises not only basic control-flow views,such as a long-term dependen-cy graph that captures macroscopic patterns,but also extended semantic views,like a resource interaction graph that reveals organizational collaboration,thereby capturing holistic and multi-level structural knowledge.Subsequently,a novel context-aware graph attention mechanism is designed for spatio-temporal information fusion.It takes the real-time prefix of a case as input to dynamically learn and assign fusion weights to each view.Finally,a Transformer is introduced to perform deep temporal modeling on the dynamically fused feature sequence to achieve precise next-activity prediction.To validate the framework's effectiveness and practical value,comprehensive experiments were conducted on six public,real-world busi-ness process datasets.The results demonstrate that,compared to various mainstream baseline models,the CAM-GF frame-work achieves an average accuracy improvement of 4.16 percentage points on the next-activity prediction task.Further-more,the dynamically generated attention weights provide high-value interpretability for the model's behavior,revealing how the model,based on predictive feedback and real-time context,can both rely on global process structures when local context fails and pivot to focus on critical semantic views,such as resource allocation,in specific situations.This thorough-ly validates the proposed framework's advancement in both accuracy and transparency.关键词
预测性流程监控/图注意力网络/多视角表征/上下文感知融合/可解释Key words
predictive process monitoring/graph attention networks/multi-view representation/context-aware fu-sion/interpretability分类
信息技术与安全科学引用本文复制引用
张希为,方贤文,毛古宝..融合多维过程视角:一种基于上下文感知图注意力的业务流程预测框架[J].电子学报,2025,53(10):3705-3717,13.基金项目
国家自然科学基金(No.61572035,No.61402011) （No.61572035,No.61402011）
嵌入式系统与服务计算教育部重点实验室开放课题(No.ESSCKF2021-05) （No.ESSCKF2021-05）
安徽省重点研究与开发计划项目(No.2022a05020005) （No.2022a05020005）
安徽省自然科学基金(水科学联合基金)(No.2308085US11) （水科学联合基金）
安徽省高校领军骨干人才项目(No.2020-01-12) （No.2020-01-12）
安徽省学术和技术带头人资助项目(No.2022D327) National Natural Science Foundation of China(No.61572035,No.61402011) （No.2022D327）
Open Project Program of the Key Laboratory of Embedded System and Service Computing of Ministry of Education(No.ESSCKF2021-05) （No.ESSCKF2021-05）
Key Research and Development Program of Anhui Province(No.2022a05020005) （No.2022a05020005）
Anhui Provincial Natural Science Foundation(Water Science Joint Fund)(No.2308085US11) （Water Science Joint Fund）
Leading Backbone Talent Project in Anhui Province of China(No.2020-01-12) （No.2020-01-12）
Anhui Province Academic and Technical Leader Foundation(No.2022D327) （No.2022D327）
