This paper introduces a novel mobile sensing application - life journaling - designed to generate semantic descriptions of users' daily lives. We present AutoLife, an automatic life journaling system based on commercial smartphones. AutoLife only inputs low-cost sensor data (without photos or audio) from smartphones and can automatically generate comprehensive life journals for users. To achieve this, we first derive time, motion, and location contexts from multimodal sensor data, and harness the zero-shot capabilities of Large Language Models (LLMs), enriched with commonsense knowledge about human lives, to interpret diverse contexts and generate life journals. To manage the task complexity and long sensing duration, a multilayer framework is proposed, which decomposes tasks and seamlessly integrates LLMs with other techniques for life journaling. This study establishes a real-life dataset as a benchmark and extensive experiment results demonstrate that AutoLife produces accurate and reliable life journals.

翻译：本文介绍了一种新颖的移动感知应用——生活日志记录，旨在生成用户日常生活的语义描述。我们提出了AutoLife，一个基于商用智能手机的自动生活日志系统。AutoLife仅输入来自智能手机的低成本传感器数据（不含照片或音频），即可自动为用户生成全面的生活日志。为实现这一目标，我们首先从多模态传感器数据中提取时间、运动与位置上下文，并利用大型语言模型（LLMs）的零样本能力，结合关于人类生活的常识知识，以解读多样化的上下文并生成生活日志。为应对任务复杂性与长时感知的挑战，本文提出了一个多层框架，该框架分解任务并将LLMs与其他技术无缝集成以完成生活日志记录。本研究建立了一个真实生活数据集作为基准，大量实验结果表明，AutoLife能够生成准确可靠的生活日志。