SHACR: A Graph-Augmented Semi-Autonomous Framework for Multi-Class Conflict Resolution in Smart Home IoT Automation

2026-06-20

AI Summary

This work addresses the challenge of hidden conflicts—arising from shared devices, environmental variables, and physical topology—in user-defined concurrent automation rules within smart homes, which can lead to safety hazards or resource inefficiencies and are difficult for existing methods to detect and resolve uniformly. The paper proposes the first semi-autonomous framework that integrates large language models (LLMs) with a formal, directed knowledge graph, encoding devices, states, and rules as typed entities and modeling physical causality as first-class graph edges. Leveraging multi-hop graph traversal, the framework enables deterministic conflict detection and drives a closed-loop “scan–explain–repair–verify” workflow, constraining the LLM’s action space to enhance reliability. Evaluated on 203 rules across 70 apartments, the approach improves F1 scores from 0.59 to 0.79 through knowledge graph integration, and achieves 0.95 with few-shot calibration, substantially outperforming LLM-only baselines.

Abstract

Smart home automation increasingly relies on user-defined rules across heterogeneous IoT devices. While these rules appear harmless in isolation, their concurrent execution creates hidden, cross-rule interactions via shared devices, environmental variables, and physical topology. These interactions result in unsafe, wasteful, or privacy-threatening behaviors that are completely invisible to text-only analysis. Existing conflict detectors remain siloed, catching either static syntactic conflicts or specific environment-mediated interactions without unifying the two or providing actionable repairs for non-expert users. This paper presents SHACR, a smart home conflict resolution framework that anchors Large Language Model (LLM) unpredictability by grounding its reasoning in a formal, directed knowledge graph. SHACR encodes devices, capabilities, physical states, and Trigger-Condition-Action rules as typed, traversable entities. By elevating physical cause-effect relationships to first-class graph edges, SHACR transforms conflict detection from fragile text inference into deterministic multi-hop graph traversal, unifying logical, semantic, and physical conflict classes. It drives a closed-loop Scan-Explain-Repair-Validate workflow that uses the graph to bound the LLM's action space. We evaluated SHACR on a testbed of 203 rules deployed across 70 apartments within a smart building. By holding the underlying LLM fixed and introducing SHACR's knowledge graph, classification errors drop by 36.7\%, F1 rises from 0.59 to 0.79, and few-shot calibration further lifts F1 to 0.95, whereas the same calibration barely helps a graph-free LLM. Ultimately, this work challenges the current AI paradigm, establishing that structured knowledge representation is a far more critical factor for dependable IoT automation management than prompt engineering or underlying model architecture.

Problem

• Smart Home Automation
• Rule Conflict
• IoT
• Conflict Resolution
• Knowledge Graph

Innovation

• knowledge graph
• conflict resolution
• smart home automation
• large language model
• graph traversal