AI 中文总结
该研究提出一种图遍历流程管线，可自动从BPMN流程模型中提取ODRL策略，解决了大规模编写ODRL效率低、大型语言模型生成存在结构无效性的问题，捕捉了现有方法遗漏的等待语义，实现了可审计、互操作的合规策略生成。
AI 中文摘要
各组织维护着大量以业务流程模型与符号（BPMN）表示的流程模型，但这些模型中编码的规范性内容——约束参与者行为的义务、许可和禁止——对于政策基础设施而言仍不可访问。开放数字权利语言（ODRL）是机器可读政策的新兴通用语言，但大规模编写ODRL缓慢且需要专业知识，而由大型语言模型生成ODRL则存在已被充分证实的结构无效性风险。我们提出了一种流程管线，该管线基于BPMN控制流通过构造编码道义模态的观察结果，自动从BPMN XML中提取ODRL策略以填补这一空白。该管线遍历BPMN流程图，通过可达性检查将每个任务分类为odrl:Duty（义务）或odrl:Permission（许可），并对中间捕获事件采用新的处理方式，将其视为带有解除约束的odrl:Prohibition（禁止）规则，捕捉了现有方法遗漏的等待语义。最终得到一种“通过提取实现合规性”的方法，其中可审计、互操作的ODRL策略直接源自各组织已维护的流程模型。该实现及在线演示可在以下两个URL获取。
英文摘要
Organisations maintain large corpora of process models expressed in the Business Process Model and Notation (BPMN), yet the normative content encoded in those models, the obligations, permissions, and prohibitions that govern participant behaviour, remains inaccessible to policy infrastructure. The Open Digital Rights Language (ODRL) is the emerging lingua franca of machine-readable policy, but authoring ODRL at scale is slow, expert-intensive work, and generation by large language models introduces well-documented risks of structural invalidity. We present a pipeline that resolves this gap by extracting ODRL policies automatically from BPMN XML, grounded in the observation that BPMN control flow encodes deontic modalities by construction. The pipeline traverses the BPMN process graph, classifies each task as an odrl:Duty or odrl:Permission via a reachability check, and introduces a novel treatment of intermediate catch events as odrl:Prohibition rules with lifting constraints, capturing waiting semantics that prior approaches have dropped. The result is a compliance-by-extraction approach in which auditable, interoperable ODRL policies are derived directly from the process models organisations already maintain. The implementation and a live demonstration are available at https://github.com/manabcodes/bpmn2odrl and https://bpmn.linkeddata.es/.
Comments10 pages, 2 figures, ODRL and beyond: practical applications and challenges for policy-base access and usage control. OPAL 2026, 2nd edition Co-located with the Extended Semantic Web Conference Dubrovnik , Croatia, 10th-11th MAY (half-day), 2026
