A requirement mining framework to support complex sub-systems suppliers

Abstract

The design of engineered socio-technical systems relies on a value chain within which suppliers must cope with larger and larger sets of requirements. Although 70 % of the total life cycle cost is committed during the concept phase and most industrial projects originally fail due to poor requirements engineering [1], very few methods and tools exist to support suppliers. In this paper, we propose to methodologically integrate data science techniques into a collaborative requirement mining framework so as to enable suppliers to gain insight and discover opportunities in a massive set of requirements. The proposed workflow is a five-phase process including: (1) the extraction of requirements from documents and (2) the analysis of their quality by using natural language processing techniques; (3) the segmentation of requirements into communities using text mining and graph theory; (4) the collaborative and multidisciplinary estimation of decision making criteria; and (5) the reporting of estimations via an analytical dashboard of statistical indicators. We conclude that the methodological integration of data science techniques is an effective way to gain insight from hundreds or thousands of requirements before making informed decisions early on. The software prototype that supports our workflow is a JAVA web application developed on top of a graph-oriented data model implemented with the NoSQL NEO4J graph database. As a future work, the semi-structured as-required baseline could be a sound input to feed a formal approach, such as model- and simulation-based systems engineering.