You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact webmaster@ide.mdh.se

AI-Powered Semantic Search for Historical Documentation: A Collaborative Research with Hitachi Energy

Authors:

Ivan Hansson , Edvin Wiklund , Alessio Bucaioni, Luciana Provenzano

Research group:

Product and Production Development

Publication Type:

Conference/Workshop Paper

Abstract

Companies with long operational histories often face the challenge of managing vast repositories of documentation, which hold critical knowledge needed for maintaining ongoing projects. Retrieving relevant information from these extensive archives is a time-consuming and complex task, requiring special- ized expertise and familiarity with outdated terminology. Seman- tic search has emerged as a promising technology to address these issues by improving the precision and efficiency of information retrieval. In this paper, we present our collaborative research with Hitachi Energy, exploring the development of a semantic search engine based on existing open-source solutions to assist practitioners in searching large industrial historical document repositories. We first analyzed available No-SQL databases with search-engine interfaces, followed by an evaluation of pre-trained semantic transformers to determine which offers the best balance of accuracy and speed for semantic search. Our research iden- tified OpenSearch as the most suitable No-SQL database due to its flexibility, free usage, and support for semantic transformers. After evaluating various pre-trained semantic transformers, we found all-MiniLM-L6-v2 to offer the best balance of accuracy and speed for semantic search. Based on the findings, we developed a prototype AI-powered semantic search tool, which was tested in a workshop involving Hitachi Energy professionals. Our findings demonstrate the feasibility and effectiveness of AI- powered semantic search for handling historical documentation, offering significant potential for industries tasked with managing large legacy archives

Bibtex

@inproceedings{Hansson7112,
author = {Ivan Hansson and Edvin Wiklund and Alessio Bucaioni and Luciana Provenzano},
title = {AI-Powered Semantic Search for Historical Documentation: A Collaborative Research with Hitachi Energy},
month = {April},
year = {2025},
url = {http://www.es.mdu.se/publications/7112-}
}