User Interface Layout Recommendation Based on Pairing Model

Abstract

In order to facilitate the generation of user interfaces from mockups, an approach was proposed to recommend User Interface (UI) layout based on Pairing Model. The absolute layout data of interfaces, including types, text, positions and sizes of components, are input into the model to generate layout. Paring Model is trained by machine-learning algorithms with features extracted from UI galleries. On the levels of functional and spatial relationship, the model decides pairing of input components and recommends a suitable layout. With use of component features, by machine-learning algorithms, the types of components are identified, which are the leaf nodes of the output layout hierarchy. The experiments on 3362 interface instances from 800 open source apps proved that the accuracy of the proposed approach, on average, exceeds 90%.