Exploring and Complementing End Users' Requirements in IoT enabled System

2026-06-09

AI Summary

This study addresses the fragmentation of IoT automation rules, which often arises when users specify only low-level device actions without articulating high-level intent, leading to missing conditions, logical conflicts, and security vulnerabilities. To overcome these issues, the authors propose an intent-driven, bidirectional requirement completion method that first reconstructs user intent from fragmented rules and then synthesizes complete, secure automation rules grounded in that intent. The approach innovatively introduces a three-layer model—spanning rules, intent, and quality concerns—and a bidirectional requirement traceability tree, integrated within a multi-agent framework that combines large language model reasoning with structured traceability. This enables explainable, auditable, and inherently secure rule completion. Experimental results demonstrate a 43% improvement in rule completion rate and over 21% reduction in logical conflicts compared to baseline methods, significantly advancing system responsibility from users to the system itself and shifting the focus from mere functional correctness to holistic trustworthiness.

Abstract

End users create IoT automation rules via trigger action programming, but their expressions are often fragmented, capturing device operations rather than high level intents. This gap leads to missing conditions, logical conflicts, and overlooked safety constraints, risking hazardous behaviors. To address this, we propose an intent driven requirements completion approach that reframes rule completion as a dual process: reconstructing intent from fragmented rules, then regenerating rules from that intent, with safety embedded throughout. We introduce a Bidirectional Requirements Traceability Tree, a three layer model linking rules, intents, and quality concerns, and design a multiagent framework that combines LLM reasoning with structured traceability. This enables completions that are both functionally complete and inherently safe, while remaining traceable and explainable. Evaluation shows our method significantly outperforms the baselines, improving the rule completion rate by 43% and reducing logical conflicts by over 21%. By grounding completion in intent understanding, we shift the paradigm from user to system responsibility, and from functional correctness to holistic trustworthiness.

Problem

• IoT automation
• end-user requirements
• intent understanding
• safety constraints
• rule completion

Innovation

• intent-driven
• requirements completion
• bidirectional traceability
• multiagent framework
• LLM reasoning