From user stories to models: A machine learning empowered automation - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

From user stories to models: A machine learning empowered automation

Résumé

In modern software development, manually deriving architecture models from software requirements expressed in natural language becomes a tedious and time-consuming task particularly for more complex systems. Moreover, the increase in size of the developed systems raises the need to decompose the software system into subsystems at early stages since such decomposition aids to better design the system architecture. In this paper, we propose a machine learning based approach to automatically breakdown the system into subsystems and generate preliminary architecture models from natural language user stories in the Scrum process. Our approach consists of three pillars. Firstly, we compute word level similarity of requirements using word2vec as a prediction model. Secondly, we extend it to the requirement level similarity computation, using a scoring formula. Thirdly, we employ the Hierarchical Agglomerative Clustering algorithm to group the semantically similar requirements and provide an early decomposition of the system. Finally, we implement a set of specific Natural Language Processing heuristics in order to extract relevant elements that are needed to build models from the identified clusters. Ultimately, we illustrate our approach by the generation of subsystems expressed as UML use-case models and demonstrate its applicability using three case studies.
Fichier principal
Vignette du fichier
101978.pdf (514.37 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

cea-04485122 , version 1 (01-03-2024)

Licence

Identifiants

Citer

Takwa Kochbati, Shuai Li, Sébastien Gérard, Chokri Mraidha. From user stories to models: A machine learning empowered automation. MODELSWARD 2022 - 9th International Conference on Model-Driven Engineering and Software Development, Feb 2021, Online Streaming, France. pp.28-40, ⟨10.5220/0010197800280040⟩. ⟨cea-04485122⟩
98 Consultations
78 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More