Agentic Search Engine for Real-Time IoT Data

2025-03-15

AI Summary

To address data fragmentation, inefficient retrieval, weak semantic understanding, and insufficient real-time responsiveness in Internet-of-Things (IoT) systems, this paper proposes an IoT-native real-time search engine. Methodologically, it introduces the first architecture integrating large language models (LLMs) with retrieval-augmented generation (RAG), incorporating sensor stream indexing, intent parsing, and dynamic context modeling to support complex intent-based queries and context-aware responses. The key contributions are: (1) the first real-time semantic search system explicitly designed for city-scale IoT deployments, validated on real-world, multi-source, heterogeneous IoT data; and (2) intent-driven service retrieval achieving 92% accuracy, with responses that are significantly more concise, relevant, and context-adapted than those generated by general-purpose LLMs such as Gemini.

Technology Category

• Search and Optimization: Learning to Search
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The Internet of Things (IoT) has enabled diverse devices to communicate over the Internet, yet the fragmentation of IoT systems limits seamless data sharing and coordinated management. We have recently introduced SensorsConnect, a unified framework to enable seamless content and sensor data sharing in collaborative IoT systems, inspired by how the World Wide Web (WWW) enabled a shared and accessible space for information among humans. This paper presents the IoT Agentic Search Engine (IoT-ASE), a real-time search engine tailored for IoT environments. IoT-ASE leverages Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) techniques to address the challenge of searching vast, real-time IoT data, enabling it to handle complex queries and deliver accurate, contextually relevant results. We implemented a use-case scenario in Toronto to demonstrate how IoT-ASE can improve service quality recommendations by leveraging real-time IoT data. Our evaluation shows that IoT-ASE achieves a 92% accuracy in retrieving intent-based services and produces responses that are concise, relevant, and context-aware, outperforming generalized responses from systems like Gemini. These findings highlight the potential IoT-ASE to make real-time IoT data accessible and support effective, real-time decision-making.

Problem

• Fragmentation limits seamless IoT data sharing.
• IoT-ASE enables real-time search in IoT environments.
• IoT-ASE improves service quality with accurate, context-aware results.

Innovation

• IoT-ASE uses LLMs for real-time data search.
• RAG techniques enhance query handling in IoT-ASE.
• IoT-ASE improves service recommendations with real-time data.