AI-Assisted Knowledge Access for Legacy Enterprise Asset Management in Energy Operations: A Practical Retrieval System
For energy utilities with costly-to-replace legacy systems, this work provides a practical improvement layer with measurable operational gains, though results are from a small pilot.
This paper presents a retrieval assistant for legacy enterprise asset management in energy operations, improving knowledge access across three modes. A pilot showed precision@5 rising from 0.56 to 0.72, MRR from 0.43 to 0.58, nDCG@5 from 0.51 to 0.66, and median task completion time dropping from 14.2 to 8.3 minutes.
Energy utilities still run engineering work management, engineering procurement, and inventory processes on long-lived enterprise asset management platforms. Replacing these platforms is often cost prohibitive and operationally disruptive, so practical improvement layers are required. This paper presents a retrieval assistant that improves day-to-day knowledge access across three operational modes: vendor documentation question answering, operational data store (ODS) schema question answering, and user interface usage and how-to question answering. The runtime method combines intent understanding, query rewriting, hybrid semantic and vector retrieval, context engineering under token limits, grounded answer generation, and deterministic hyperlink conversion for panel identifiers and cited documentation. The data preparation pipeline emphasizes semantic enrichment as the primary quality lever by adding table and field descriptions, normalizing acronyms across sources, and indexing representative row-level context when useful. A measured pilot shows consistent gains in retrieval quality and user outcomes. Precision at five improved from 0.56 to 0.72, mean reciprocal rank from 0.43 to 0.58, and normalized discounted cumulative gain (nDCG) at five from 0.51 to 0.66. Median task completion time dropped from 14.2 to 8.3 minutes, while usefulness and confidence both increased to 4.0 on a five-point scale. Results are based on a small sample and are reported as pilot findings, but they indicate that intent understanding and semantic enrichment can deliver meaningful operational value in legacy environments while also establishing reusable foundations for future analytics and automation tools.