📄 中文摘要
预测建模在顺序事件数据中对于欺诈检测和医疗监控至关重要。现有的数据驱动方法从历史数据中学习相关性，但未能纳入特定领域的顺序约束和逻辑规则，限制了准确性和合规性。例如，医疗程序必须遵循特定顺序，金融交易必须遵循合规规则。研究提出了一种神经符号方法，将领域知识作为可微分的逻辑约束整合到逻辑网络中。通过线性时序逻辑和一阶逻辑对控制流、时间和负载知识进行形式化。关键贡献在于提出了一种两阶段优化方法，以提高预测过程监控的效果。
通过两阶段逻辑张量网络与规则剪枝的预测过程监控的神经符号学习
📄 English Summary
Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning
Predictive modeling on sequential event data is crucial for fraud detection and healthcare monitoring. Existing data-driven approaches learn correlations from historical data but fail to incorporate domain-specific sequential constraints and logical rules governing event relationships, which limits accuracy and regulatory compliance. For instance, healthcare procedures must follow specific sequences, and financial transactions must adhere to compliance rules. This research presents a neuro-symbolic approach that integrates domain knowledge as differentiable logical constraints using Logic Tensor Networks (LTNs). Control-flow, temporal, and payload knowledge are formalized using Linear Temporal Logic and first-order logic. A key contribution is the introduction of a two-stage optimization method to enhance the effectiveness of predictive process monitoring.