Problem
Research questions and friction points this paper is trying to address.
Total Airport Management
Knowledge Engineering
Semantic Inconsistency
Data Silos
Airport Operations
Semi-Automated Knowledge Engineering and Process Mapping for Total Airport Management
🤖 AI Summary
This study addresses the challenge of fragmented information in airport operations documentation—characterized by complex terminology, stringent regulatory constraints, and dispersed data sources—that impedes the realization of Total Airport Management (TAM). To overcome this, the authors propose a two-stage framework integrating symbolic knowledge engineering with large language models (LLMs). First, expert-guided prompting extracts traceable knowledge triples from unstructured texts to synthesize operational procedures. The work introduces a novel scaffolding fusion strategy that effectively combines expert knowledge with LLM-generated content and demonstrates, for the first time in airport management, the superiority of document-level over fragment-level processing. By leveraging knowledge graph construction, probabilistic discovery models, deterministic anchoring algorithms, and the LangExtract library, the approach faithfully reconstructs nonlinear operational dependencies and produces a machine-readable knowledge graph with full provenance, enabling automated process mapping.
📝 Abstract
Documentation of airport operations is inherently complex due to extensive technical terminology, rigorous regulations, proprietary regional information, and fragmented communication across multiple stakeholders. The resulting data silos and semantic inconsistencies present a significant impediment to the Total Airport Management (TAM) initiative. This paper presents a methodological framework for constructing a domain-grounded, machine-readable Knowledge Graph (KG) through a dual-stage fusion of symbolic Knowledge Engineering (KE) and generative Large Language Models (LLMs).
The framework employs a scaffolded fusion strategy in which expert-curated KE structures guide LLM prompts to facilitate the discovery of semantically aligned knowledge triples. We evaluate this methodology on the Google LangExtract library and investigate the impact of context window utilization by comparing localized segment-based inference with document-level processing. Contrary to prior empirical observations of long-context degradation in LLMs, document-level processing improves the recovery of non-linear procedural dependencies.
To ensure the high-fidelity provenance required in airport operations, the proposed framework fuses a probabilistic model for discovery and a deterministic algorithm for anchoring every extraction to its ground source. This ensures absolute traceability and verifiability, bridging the gap between "black-box" generative outputs and the transparency required for operational tooling. Finally, we introduce an automated framework that operationalizes this pipeline to synthesize complex operational workflows from unstructured textual corpora.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Knowledge Graph
Large Language Models
Knowledge Engineering
Total Airport Management
Provenance Traceability
🔎 Similar Papers
No similar papers found.
