Simulating the Resident: Generating Executable Smart Home Schedules via LLM Personas

2026-07-09

AI Summary

This study addresses the high cost and privacy risks associated with collecting real-world smart home data, which hinder scalable research in human-computer interaction and security. To overcome these limitations, the authors propose a household simulation framework grounded in five socio-technical dimensions, integrated with a multi-stage large language model (LLM) pipeline. This approach enables, for the first time, end-to-end generation of executable smart device schedules directly from personalized resident role descriptions. Crucially, it preserves behavioral realism without requiring any real user data. The feasibility of the generated schedules was successfully validated on a physical testbed, establishing a privacy-preserving paradigm for large-scale smart home research.

Abstract

Smart homes have emerged as an important domain for HCI research, including work on usable security and privacy. Ideally, studies in these areas draw on datasets collected in real homes with real residents, capturing authentic device interactions, network traffic, and daily routines. However, creating such datasets is slow, expensive, and raises significant privacy concerns, as it requires long-term observation of people in their most private spaces. We propose using LLMs to generate diverse resident personas that interact with a simulated smart home, producing behaviorally grounded interaction schedules that can be executed on physical testbeds. We present (1) a design framework configuring simulated households across five socio-technical dimensions, (2) a multi-stage LLM pipeline that produces structured, executable device interaction schedules, and (3) a proof of concept demonstrating feasibility. As a work in progress, we aim to support scalable, privacy-conscious smart-home experimentation without relying on intrusive real-world data collection.

Problem

• smart home
• privacy
• dataset generation
• human-computer interaction
• real-world data collection

Innovation

• LLM personas
• executable schedules
• smart home simulation
• privacy-conscious HCI
• synthetic behavior generation