PITCH:通过日常对话交互进行生产力与心理健康辅导
PITCH: Productivity and Mental Well-being Coaching through Daily Conversational Interaction
AI总结:
PITCH 系统利用大语言模型构建对话智能体,通过每日轮换的上下文感知提示帮助用户外化计划并反思,从而提升生产力、心理健康和用户参与度。
摘要:
高效的任务规划对于生产力和心理健康至关重要,然而个体往往难以制定切实可行的计划并反思自身的生产力状况。借助人工智能(AI)的进步,对话智能体已成为提升生产力的一种有前景的工具。我们的工作聚焦于通过对话将计划外化,旨在巩固意图并促进行动专注,从而对其生产力和心理健康产生积极影响。我们分享了设计一个对话智能体的计划,该智能体通过利用自然对话的社交互动性,提供富有洞察力的问题和反思性提示,以提高计划依从性。先前研究表明此类智能体的有效性,但许多干预措施仍然是静态的,导致用户参与度随时间下降。为解决这一局限性,我们提出了一种新颖的轮换与上下文感知提示策略,每天为用户提供多样化的干预。我们的系统 PITCH 利用大语言模型(LLMs)促进日常计划的外化和反思。通过本研究,我们考察了利用对话智能体外化任务对生产力和心理健康的影响,以及轮换策略在维持用户参与度方面的有效性。
英文摘要:
Efficient task planning is essential for productivity and mental well-being, yet individuals often struggle to create realistic plans and reflect upon their productivity. Leveraging the advancement in artificial intelligence (AI), conversational agents have emerged as a promising tool for enhancing productivity. Our work focuses on externalizing plans through conversation, aiming to solidify intentions and foster focused action, thereby positively impacting their productivity and mental well-being. We share our plan of designing a conversational agent to offer insightful questions and reflective prompts for increasing plan adherence by leveraging the social interactivity of natural conversations. Previous studies have shown the effectiveness of such agents, but many interventions remain static, leading to decreased user engagement over time. To address this limitation, we propose a novel rotation and context-aware prompting strategy, providing users with varied interventions daily. Our system, PITCH, utilizes large language models (LLMs) to facilitate externalization and reflection on daily plans. Through this study, we investigate the impact of externalizing tasks with conversational agents on productivity and mental well-being, and the effectiveness of a rotation strategy in maintaining user engagement.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。