Abstract: The subject technology provides a framework for generating personalized and relevant content suggestions for a user of an electronic device. The system collects data from various sources, including location, motion sensors, routine places, contacts, calls, and proximity to people and devices. The collected data is analyzed using inference technology to identify patterns and anomalies. The system can detect routine activities and identify anomalies based on the duration and frequency of activities, social interactions, and changes in user behavior. The system includes modules for grouping related activities and summarizing individual events and coarse-grained activities. The system also includes a ranking algorithm that generates recommendations based on various factors such as recency, distinctiveness, media richness, and user engagement. The system further includes a method of adjusting recommendation ranking based on prior analytics and user preferences.

Abstract: Embodiments are disclosed for estimating heart rate recovery (HRR) after maximum or high-exertion activity based on sensor observations. In some embodiments, a method comprises: obtaining, with at least one processor, sensor data from a wearable device worn on a wrist of a user; obtaining, with the at least one processor, a heart rate (HR) of the user; identifying, with the at least one processor, an observation window of the sensor data and HR; estimating, with the at least one processor during the observation window, input features for estimating maximum or near maximum exertion HRR of the user based on the sensor data and HR; and estimating, with the at least one processor during the observation window, the maximum or near maximum exertion HRR of the user based on a machine learning model and the input features.