AI 中文总结
本研究结合LLMs与Neo4j知识图谱的神经符号管道，针对JITAIs面临的对话转日程难题，发现心智模型差距与生态不匹配问题，提出设计启发法以构建支持健康行为改变的主动智能体。
AI 中文摘要
即时自适应干预（JITAIs）越来越依赖对话智能体来提取用户的日常活动流程，但将流畅的人类对话转化为刚性的日程数据仍是一个重大挑战。我们对一种神经符号管道开展了质性研究，该管道结合了大语言模型（LLMs）与Neo4j知识图谱，用于将非结构化的口头叙事映射为可操作的干预措施。通过使用自然语言回放开展以人为中心的评估，我们发现了一个关键的“心智模型差距”：大语言模型的线性提取方式与人类分层、非线性的叙事方式相冲突，导致严重的实体碎片化。此外，我们阐明了一种“生态不匹配”，表明算法的日程可用性常常忽略用户波动的心理接受度和身体能量水平。为解决这些矛盾，我们提出了可操作的设计启发法，包括流程搭载、自适应协商和可扩展透明性。最终，这些指南为将刚性的日程追踪工具发展为富有同理心、具备情境感知能力的主动智能体提供了基础框架，这类智能体能够支持长期的健康行为改变。
英文摘要
Just-In-Time Adaptive Interventions (JITAIs) increasingly rely on conversational agents to elicit user routines, yet translating fluid human dialogue into rigid schedule data remains a significant challenge. We conducted a qualitative investigation of a neurosymbolic pipeline, combining Large Language Models (LLMs) with a Neo4j knowledge graph, to map unstructured verbal narratives into actionable interventions. Through human-centric evaluation using natural-language playbacks, we identified a critical "mental-model gap," where the linear extraction of LLMs clashes with hierarchical, non-linear human storytelling, causing severe entity fragmentation. Furthermore, we articulate an "ecological mismatch," demonstrating that algorithmic schedule availability frequently ignores the user's fluctuating psychological receptivity and physical energy levels. To resolve these tensions, we propose actionable design heuristics, including routine piggybacking, adaptive negotiation, and scalable transparency. Ultimately, these guidelines provide a foundational framework for evolving rigid schedule-trackers into empathetic, context-aware proactive agents capable of supporting long-term health behavior change.
CommentsAccepted at OzCHI 2026
