用手机传感器+大模型自动生成生活日记，无需拍照录音。
AutoLife: Automatic Life Journaling with Smartphones and LLMs
- 基于手机传感器数据提取时间、动作和位置上下文
- 利用大模型零样本能力生成准确可靠的生活日志
- 适合对自我记录感兴趣或想提升生活认知的用户
本文提出一种新型移动端感知应用——自动生活日记系统。AutoLife 是一个基于商用智能手机的自动生活日记系统，仅需低功耗传感器数据（不依赖照片或音频），即可为用户提供全面的生活日志。系统首先从多模态传感器数据中提取时间、运动与位置上下文，并借助具备常识知识的大语言模型（LLMs）的零样本能力，解读多样化上下文并生成日志。针对任务复杂性和长时间感知挑战，设计了分层框架，将大模型与其他技术无缝集成。本研究构建了一个真实生活数据集作为基准，大量实验结果表明，AutoLife 能生成准确且可靠的日常日记。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。