Contextual user interactions with devices and applications today are largely confined to context from location or on-screen context, and to the device at hand. This disclosure describes a context framework that, with user permission, integrates wearable and stationary sensor inputs and traditional digital context into a larger computing ecosystem to deliver content across a range of proactive ambient computing use cases. Devices and apps register their sensors with a context engine and send periodic data updates to the engine. Using machine learning models, the context engine updates the user context based on sensor and external data, and provides the user context to registered devices and apps, which modify their behavior or surface content based on the user’s context.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.