LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs

TL;DR

LogSyn leverages large language models with few-shot learning to transform unstructured aviation maintenance logs into structured data, enabling better safety analysis and predictive maintenance.

Contribution

This paper introduces LogSyn, a novel framework that applies LLMs for semantic structuring and insight extraction from unstructured maintenance logs using controlled abstraction and classification.

Findings

Achieved effective summarization and classification of maintenance logs.

Identified key failure patterns for safety insights.

Demonstrated scalability on over 6,000 records.

Abstract

Aircraft maintenance logs hold valuable safety data but remain underused due to their unstructured text format. This paper introduces LogSyn, a framework that uses Large Language Models (LLMs) to convert these logs into structured, machine-readable data. Using few-shot in-context learning on 6,169 records, LogSyn performs Controlled Abstraction Generation (CAG) to summarize problem-resolution narratives and classify events within a detailed hierarchical ontology. The framework identifies key failure patterns, offering a scalable method for semantic structuring and actionable insight extraction from maintenance logs. This work provides a practical path to improve maintenance workflows and predictive analytics in aviation and related industries.