DH-BPR框架:用LLM基于事件日志自动执行业务流程重构启发式规则
Data-Driven Heuristic-Guided Business Process Redesign
做流程挖掘或BPMN的同学可以看看这篇:它把事件日志喂给LLM,自动检测可套用的重构启发式规则,一次能改多处,实测平均完成时间最多降61.5%,比人工套规则省事很多。
论文提出DH-BPR框架,输入事件日志和BPMN模型,利用LLM实现数据驱动、启发式规则引导的业务流程重构(BPR)。传统方法依赖人工和领域知识来套用最佳实践启发式规则,已有LLM方案则是用户驱动、一次只能处理一处变更。DH-BPR先分析哪些启发式规则可以依据事件日志信息(如绕过某活动的案例比例)自动检测,然后用规则技术与LLM结合来检测和验证候选方案,再联合设计并记录应用计划,最终输出重构后的BPMN模型和更新后的资源模型。
评估采用合成基准和两个真实事件日志进行仿真,结果显示重构后的流程平均案例完成时间最多降低61.5%。
Data-Driven Heuristic-Guided Business Process Redesign
Business process redesign (BPR) has a long-standing catalog of best-practice redesign heuristics, yet, applying them remains a mostly manual task that requires extensive domain knowledge. Despite recent advances using Large Language Models (LLMs) for conversational process model redesign, limitations remain. For example, redesign is user-driven instead of data-driven and is not guided by best practices such as the redesign heuristics. Moreover, only one change can be handled at a time. To address these limitations, given an event log and a BPMN model, we present the DH-BPR framework to realize data-driven heuristic-guided BPR using LLMs. To design DH-BPR, we first conducted an analysis of which redesign heuristics can be automatically detected and applied given information contained in an event log such as the fraction of cases that bypass an activity. Based on this, DH-BPR detects and validates heuristic candidates through a combination of rule-based techniques and an LLM. After that, DH-BPR jointly designs and records an application plan for valid candidates, before finally yielding a redesigned BPMN model and an updated resource model (the way resources execute the process). Evaluation based on simulation using a synthetic benchmark and two real-world event logs shows that the framework's redesign reduces the mean case completion time by up to 61.5%.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include BPMN, LLM.
Source attribution: curated from arXiv cs.AI (@Nan Sai, Karolin Winter, Remco Dijkman).