顺序或带时间戳的交互日志提供了数字应用程序使用情况的客观记录,，但它们的粒度和噪音常常掩盖了对人们工作的有意义的洞察。这些见解对于以现实世界用户交互的方式改进数字产品至关重要。先前的研究已应用深度学习模型将用户操作聚类为高级活动,，但这些方法对噪声高度敏感，并且难以跨应用程序推广。为了解决此限制,，我们引入了 WorkflowView, 框架，该框架使用大型语言模型 (LLMs) 将低级操作序列抽象为高级活动。我们在三个不同的,具有挑战性的顺序任务和不同的领域中建立了我们的方法的有效性和通用性: (a)从浏览器日志进行零样本任务描述重建(实现高语义相似性, $\mu_{sim} = 0.91$), (b)使用MOOC交互日志进行小样本学生辍学预测(达到加权$F_1 = 0.90$ 只有五个少量示例), 和 (c) 匿名, 对 Microsoft Word 文档工作流程中的 AI 工具集成进行隐私保护分析。我们的工作表明，基于 LLM 的抽象是将低级行为数据转换为高级, 可解释, 和可操作见解的稳健且有效的前进道路。我们还讨论了在日志基础设施, 中部署基于 LLM 的推理的实际注意事项，包括计算效率和用户隐私。

Sequential or time-stamped interaction logs provide objective records of digital application usage, yet their granularity and noise often obscure meaningful insights into people的 work. Such insights are essential for improving digital products in ways grounded in real-world user interactions. Prior research has applied deep learning models to cluster user actions into high-level activities, but these approaches are highly sensitive to noise and struggle to generalize across applications. To address this limitation, we introduce WorkflowView, a framework that uses large language models (LLMs) to abstract low-level action sequences into high-level activities. We establish the effectiveness and generality of our approach across three distinct, challenging sequential tasks and diverse domains: (a) zero-shot task description reconstruction from browser logs (achieving high semantic similarity, $\mu_{sim} = 0.91$), (b) few-shot student dropout prediction using MOOC interaction logs (reaching weighted $F_1 = 0.90$ with only five few-shot examples), and (c) anonymized, privacy-preserving analysis of AI tool integration within document workflows in Microsoft Word. Our work demonstrates that LLM-based abstraction is a robust and efficient path forward for transforming low-level behavioral data into high-level, interpretable, and actionable insights. We also discuss practical considerations for deploying LLM-based inferences within logging infrastructures, including computational efficiency and user privacy.

科目: 人工智能 (cs.AI); 计算和语言 (cs.CL); 机器学习 (cs.LG)

Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)