Generating HomeAssistant Automations Using an LLM-based Chatbot

2025-05-05

AI Summary

This study addresses the disconnect between natural language interaction and sustainable practices in smart home automation. Methodologically, it introduces a large language model (LLM)-based chatbot framework integrated with Home Assistant: (1) it pioneers the use of GPT-series models to generate executable, JSON-structured automation scripts; (2) it proposes a “green prompting” mechanism that explicitly guides the LLM to produce energy-saving and carbon-reducing automation behaviors; and (3) it evaluates usability and sustainability orientation via a user study (N=56). Results demonstrate high script generation accuracy and statistically significant improvements—over conventional rule-based systems—in perceived usability, user engagement, and willingness to adopt sustainable behaviors. This work establishes a reproducible technical pathway and provides empirical validation for LLM-driven green smart homes.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Intelligent User Interfaces
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

To combat climate change, individuals are encouraged to adopt sustainable habits, in particular, with their household, optimizing their electrical consumption. Conversational agents, such as Smart Home Assistants, hold promise as effective tools for promoting sustainable practices within households. Our research investigated the application of Large Language Models (LLM) in enhancing smart home automation and promoting sustainable household practices, specifically using the HomeAssistant framework. In particular, it highlights the potential of GPT models in generating accurate automation routines. While the LLMs showed proficiency in understanding complex commands and creating valid JSON outputs, challenges such as syntax errors and message malformations were noted, indicating areas for further improvement. Still, despite minimal quantitative differences between"green"and"no green"prompts, qualitative feedback highlighted a positive shift towards sustainability in the routines generated with environmentally focused prompts. Then, an empirical evaluation (N=56) demonstrated that the system was well-received and found engaging by users compared to its traditional rule-based counterpart. Our findings highlight the role of LLMs in advancing smart home technologies and suggest further research to refine these models for broader, real-world applications to support sustainable living.

Problem

• Enhancing smart home automation using LLMs for sustainability
• Generating accurate HomeAssistant routines via GPT models
• Addressing syntax errors in LLM outputs for automation

Innovation

• LLM-based chatbot generates HomeAssistant automations
• GPT models create accurate automation routines
• Empirical evaluation shows user preference for LLM system