Pattern-based auto-completion of UML modeling activities

Abstract

Auto-completion of textual inputs when using IDEs benefits software development experts and novices. Researchers demonstrated that auto-completion is beneficial for graphical modeling tasks as well. However, supporting software development by auto-completing UML modeling activities remains largely unexplored by research and unsupported by modeling tools. By matching editing operations to activity patterns, partly performed modeling activities can be recognized and automatically completed. This paper proposes an approach that computes auto-completions for partly performed modeling activities while a developer is creating or evolving UML models. Selected auto-completions can be previewed and adjusted before being executed. We claim, that this approach can improve developers' modeling efficiency. Therefore, we assessed our approach based on a catalog of common modeling activities for structural UML models and found that effort for conducting defined modeling activities can be reduced significantly.

Towards an assessment grid for intelligent modeling assistance

“…Focusing on the field of software and system modeling, existing assistants together support all key aspects of the system life-cycle of increasingly complex systems. Large efforts have gone into supporting common modeling languages like UML, e.g., to support a particular modeling process [37], and to help build diagrams from natural language [21] or through recommendations from similarities [16] or established patterns [25]. However, it is very time-consuming to build similar IMAs for the diverse set of other domain-specific abstractions that are tailored to heterogeneous stakeholders.…”

“…All existing IMAs focus only on syntactic model quality (Level 1 of Quality of IMA Regarding Model), i.e., they do not consider semantic or pragmatic quality, except for one case of semantic quality ( [8]). The majority of existing IMAs remains at low levels of autonomy (Level 0 or 1), but there are four cases with higher autonomy ( [8,12,16,25]). None of the existing IMAs report on relevance (Level 0) or confidence (Level 0), or provide information about trust (Level 0), except for one case with high relevance ( [12]).…”

“…All but one existing IMA provide a safe lookup (Level 2 of Quality Degree), i.e., none of them reaches the level for trade-off analysis. Most existing IMAs provide recommendations regularly upon request and are able to do so quickly, i.e., at most minutes (Level 2 of Timeliness), except for three cases that offer more immediate and/or autonomous recommendations ( [12,25,31,32]). In terms of external sources, existing IMAs predominantly use a mix of public and private data (Level A1 or A2) that is well curated (Level C2) and periodically updated (Level U3).…”

Data Model Development for Process Modeling Recommender Systems

“…Although it has been demonstrated that assistance functions are beneficial in these domains [5] [6], assistance functions are not considered in commercial BPM tools. However, since recommender systems "generate meaningful recommendations to a collection of users" [7], development activities towards such systems should be given a priority in order to offer assistance functions in process modeling tools too.…”

A definition-by-example approach and visual language for activity patterns in engineering disciplines

“…In previous work, we used complex patterns of editing events to update traceability information automatically upon recognizing users' modeling activities [7] and successfully brought a visual language approach to traceability analysis [8][9][10]. In a succeeding project, we studied how software modeling activities can be recommended while a developer is editing UML models [11] and how such recommended activities can then be auto-completed [12][13][14]. Both proposed approaches build upon activity definitions captured as event-processing rules.…”