# LLM-based event abstraction and integration for IoT-sourced logs

arXiv: https://arxiv.org/abs/2409.03478 · HTML: https://mlsanity.com/paper/2409.03478/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 8 of 8)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Abstractions, Scenarios, and Prompt Definitions for Process Mining with LLMs: A Case Study](https://mlsanity.com/paper/2307.02194/) (2023)
- [Chit-Chat or Deep Talk: Prompt Engineering for Process Mining](https://mlsanity.com/paper/2307.09909/) (2023)
- [Conformance Checking Approximation using Subset Selection and Edit Distance](https://mlsanity.com/paper/1912.05022/) (2019)
- [Mining Process Model Descriptions of Daily Life through Event Abstraction](https://mlsanity.com/paper/1705.10202/) (2017)
- [Extracting and Pre-Processing Event Logs](https://mlsanity.com/paper/2211.04338/) (2022)
- [Turning Logs into Lumber: Preprocessing Tasks in Process Mining](https://mlsanity.com/paper/2309.17100/) (2023)
- [From Internet of Things Data to Business Processes: Challenges and a Framework](https://mlsanity.com/paper/2405.08528/) (2024)

## Built on by (most cited first, 2 of 2)

- [From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications](https://mlsanity.com/paper/2505.22311/) (2025)
- [Clustered Edge Intelligence: Beyond Just Convergence of Edge Computing and AI](https://mlsanity.com/paper/2607.20937/) (2026)

## Abstract (arXiv)

The continuous flow of data collected by Internet of Things (IoT) devices, has revolutionised our ability to understand and interact with the world across various applications. However, this data must be prepared and transformed into event data before analysis can begin. In this paper, we shed light on the potential of leveraging Large Language Models (LLMs) in event abstraction and integration. Our approach aims to create event records from raw sensor readings and merge the logs from multiple IoT sources into a single event log suitable for further Process Mining applications. We demonstrate the capabilities of LLMs in event abstraction considering a case study for IoT application in elderly care and longitudinal health monitoring. The results, showing on average an accuracy of 90% in detecting high-level activities. These results highlight LLMs' promising potential in addressing event abstraction and integration challenges, effectively bridging the existing gap.