Customized Information and Domain-centric Knowledge Graph Construction with Large Language Models

TL;DR

This paper introduces a scalable, knowledge graph-based framework utilizing large language models for domain-specific information extraction and decision-making in cyber-physical systems, demonstrated on automotive electrical systems.

Contribution

It presents a novel, ontology-supported knowledge graph construction method that outperforms existing models like GraphGPT and REBEL in class recognition and relationship accuracy.

Findings

Outperforms GraphGPT and REBEL in key metrics

Effective in automotive electrical systems domain

Supports reasoning and decision-making applications

Abstract

In this paper we propose a novel approach based on knowledge graphs to provide timely access to structured information, to enable actionable technology intelligence, and improve cyber-physical systems planning. Our framework encompasses a text mining process, which includes information retrieval, keyphrase extraction, semantic network creation, and topic map visualization. Following this data exploration process, we employ a selective knowledge graph construction (KGC) approach supported by an electronics and innovation ontology-backed pipeline for multi-objective decision-making with a focus on cyber-physical systems. We apply our methodology to the domain of automotive electrical systems to demonstrate the approach, which is scalable. Our results demonstrate that our construction process outperforms GraphGPT as well as our bi-LSTM and transformer REBEL with a pre-defined dataset by several times in terms of class recognition, relationship construction and correct "sublass of" categorization. Additionally, we outline reasoning applications and provide a comparison with Wikidata to show the differences and advantages of the approach.