Creating Dashboards for Decision-Making using an LLM and Knowledge Graph-Driven Approach

Abstract

This master’s thesis addresses the inefficiency of manual dashboard creation for digital twins (DT) of telecommunications network management systems (TNMS). It develops and evaluates an AI-driven pipeline that uses a large language model (LLM) augmented by a domain-specific knowledge graph (KG) and retrieval mechanisms (RAG) to automate the generation of dashboards in a compatible format.