AutoLife: Automatic Life Journaling with Smartphones and LLMs
This work addresses the problem of automated personal journaling for smartphone users, representing an incremental advancement in mobile sensing applications.
The authors tackled the problem of automatically generating semantic descriptions of users' daily lives by introducing AutoLife, a system that uses smartphone sensor data and LLMs to create life journals, with experiments showing it produces accurate and reliable results.
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.