Skip to content
Open access

AI-Assisted Ontology Development: Automating Enterprise Vocabulary Management using Large Language Models and SPARQL

2025 · American International Journal of Computer Science and Technology · 0 citations

Abstract

Properly designed ontologies are considered as a pillar in knowledge management in business and in the effective management of vocabulary and efficient retrieval of knowledge with the help of heterogeneous systems. Ontology engineering is nevertheless traditional and manual as it is labor intensive, in that manual corrections and a lot of domain knowledge are required. The paper proposes artificial intelligence with the help of An AI-Supported Ontology Engineering Framework (AIOEF) which automatized the task of managing vocabulary in an enterprise by using Large Language Models (LLMs) and SPARQL software. This point of view integrates the domain-specific document-ingestion, natural language-processing, entity and relation-extraction, ontology-schema-generation, semantic-validation, SPARQL-based querying and continuous ontology-refinement via the human-in-the-loop feedback. By contrast, SPARQL facilitates checking semantic consistency and querying of knowledge graphs, development of ontologies, LLMs deducing concepts, classes, properties, synonyms and hierarchical relationships within a document used in an enterprise and its automatic processing. Other mechanisms found in the framework are confidence scoring, explainable reasoning and governance mechanisms to ensure dependable updates on ontology in dynamic enterprise settings. The semantic consistency, knowledge reuse, and interoperability of enterprise applications (digital twins, business process management, intelligent search and decision-support systems) can also be enhanced by the proposed architecture by lowering the volume of manual work and maximizing the speed of ontology-building. The framework gives scaling ontology life-cycle management, and quality semantic representations, which are applicable in cloud-native and artificially intelligent based enterprise ecosystems. The proposed methodology incorporates a practical and intelligent methodological framework next-generation enterprise knowledge engineering, that enable organisations to transform unstructured data into manageable, machine-readable semantic value, which may be learnt by automated logic and intelligent business analytics.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.