• axiomatic relation
• design parameter
• functional requirement
• named entity recognition
• natural language processing

Engineering design is a knowledge-intensive process that aims to develop effective solutions to meet specific needs or solve technical problems. Designers must identify, extract, and structure requirements from texts and drawings of archived documents to understand the past and create innovations. This process is not trivial as technical knowledge is not structured and uniformed. This thesis aims to optimize this process using Axiomatic Design methodology with Natural Language Processing techniques applied on patents. Specifically, the objective of this thesis is two-fold: 1) extracting functional requirements and design parameters in a structured way, 2) analysing axiomatic relation, that is the relationship between functional requirements and design parameters. The approach used in this thesis shows a precision of 60% on the first task and 30-50% on the second. Moreover, a case study is presented to demonstrate the applicability of this approach to support the work of designers. The present thesis contributes to understanding how design information can be written into patent texts and serves as a knowledge base for future research endeavors.