Abstract
Current computing devices display static home screens. Also, application data is isolated within individual applications. This forces users to access different apps for information, creating a high cognitive load. This disclosure describes techniques that, with user permission, automatically generates and presents an adaptive, contextually appropriate user interface (e.g., home screen interface) on a computing device. The user interface provides seamless, proactive, personal assistance throughout the day and reduces the effort (and time) the user needs to spend to access desired information. With user permission, data from multiple sources is aggregated and an on-device machine-learned model is implemented to identify user goals based on this context. The output of the ML model is used to organize information into dynamic, visually distinct visual spaces. These spaces can include glanceable UI, actionable elements, app bundles, etc. The UI layout is modified dynamically to prioritize relevant visual spaces. High-priority content can be emphasized with larger display blocks. The described techniques proactively anticipate user needs based on the user’s context.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Brisendine, Stephanie; Karam, David; Johnston, Chorong; Oh, DJ; Kugler, Tyler; Raupach, Tim; Chandel, Alok; Dupin, Lucas; and Bowman, Hannah, "Context-Aware Personalized Modular User Interfaces Using Artificial Intelligence", Technical Disclosure Commons, (July 07, 2026)
https://www.tdcommons.org/dpubs_series/10828