Supporting Knowledge Re-Use with Effective Searches of Related Engineering Documents - A Comparison of Search Engine and Natural Language Processing-Based Algorithms

Abstract

Product development companies are collecting data in form of Engineering Change Requests for logged design issues and Design Guidelines to accumulate best practices. These documents are rich in unstructured data (e.g., free text) and previous research has pointed out that product developers find current it systems lacking capabilities to accurately retrieve relevant documents with unstructured data. In this research we compare the performance of Search Engine & Natural Language Processing algorithms in order to find fast related documents from two databases with Engineering Change Request and Design Guideline documents. The aim is to turn hours of manual documents searching into seconds by utilizing such algorithms to effectively search for related engineering documents and rank them in order of significance. Domain knowledge experts evaluated the results and it shows that the models applied managed to find relevant documents with up to 90% accuracy of the cases tested. But accuracy varies based on selected algorithm and length of query.

Natural language processing methods for knowledge management—Applying document clustering for fast search and grouping of engineering documents

“…The single case study research design, including the analysis of only one ECR database, enables only limited claims to the transferability of results. However, we show in Arnarsson et al (2019) that the main steps of approach can be applied to search in a combination of an ECR database and a design guideline database. Nevertheless, additional case studies are needed.…”

KMSBOT: Enhancing Educational Institutions with an AI-Powered Semantic Search Engine and Graph Database

“…The research involved a comparative analysis of the performance of NLP and traditional search engines. The results of the analysis revealed that the NLP-based search engine achieved a document retrieval accuracy of 90% [11]. In 2021, researchers introduced a semantic search engine employing NLP and RDF techniques.…”

Semantic Networks for Engineering Design: A Survey

“…The aim of this paper is to explore the current state of academic research and implementation of largescale semantic networks as knowledge bases for engineering design, and illuminate potential directions for future research. Our work addresses the growing requirement for designers and design researchers to be knowledgeable about and use text mining (TM), natural-language-processing (NLP) and semantic networks (Arnarsson et al, 2019;Chiarello et al, 2019). To be more specific, the paper provides an overview of 1) the research that constructs engineering semantic networks (data sources and construction methods), and 2) the research that employs semantic networks for language processing in engineering design (what and how semantic networks are used as knowledge bases to provide computational design aids).…”