Anzeige
Erschienen in:
2019 | OriginalPaper | Buchkapitel
Automated Smartphone Keyboard Error Corrections
verfasst von : Vered Aharonson, Rotem Rousseau, Eran Aharonson
Erschienen in: Advances in Usability, User Experience and Assistive Technology
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
The usability of smartphone’s touch keyboard is often hampered by typing mistakes resulting from the small size of the virtual keys relatively to the user’s finger size. Although this problem has been addressed in various methods, an optimal solution in terms of both accuracy and user experience, however, has not been achieved. We developed an algorithm that predicts users typing intentions based on a statistical geometrical modeling of the touch points area. The algorithm builds a user-adaptive virtual location of the key based on deviations probability computation. An uncertainly measure activates a language statistics engine to enhance the prediction. The algorithm was integrated into the default Android® keyboard and was tested on users. Typing error rate using the implemented algorithms was reduced by 23.1% on average. The proposed method can enhance typing accuracy and user experience and may facilitate and improve the design of smaller and cheaper touch based smartphones.