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.

Lenovo recently released a new combination desktop program/Windows Store app that helps add even more power to Cortana on Windows 10 PCs. Lenovo's Reachit lets you take Cortana into places it's never been before by connecting the digital assistant to your files within the likes of Dropbox and Google Drive. Lenovo released Reachit in beta form in 2015, but now it's available for anyone to use. First, you install the Windows Store version of Reachit. Once you've done that, you'll be prompted to install a desktop program as well.