Adaptive Notification Output for User Engagement and Distraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated assistant applications face challenges in reducing user distraction and conserving computational resources due to the need for multiple interactions and notifications, especially when users are engaged in activities like driving, leading to potential safety hazards and inefficiencies in resource usage.
Innovation Solution
The automated assistant dynamically determines when and how to present notifications based on predicted levels of user engagement, using sensor data and notification properties to suppress, condense, or delay notifications, allowing for automatic responses and reducing the burden on computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If notifications are provided immediately upon receipt, then user awareness of important information is improved, but user distraction and safety risks increase
Solution Approach 1:
The system performs preliminary analysis of user engagement level before providing notifications. It predicts whether the user is engaged in a distracting activity (like driving) and delays notification provision until a safer time, thus preventing distraction while ensuring information is eventually delivered
Solution Approach 2:
The notification provision is made dynamic by continuously monitoring user engagement levels and adapting the timing and method of notification delivery. The system can switch between immediate provision, delayed provision, suppression, or automatic response based on real-time engagement assessment
2Reliability
If multiple interactions are required to complete a task, then user control and confirmation are improved, but computational resources and network resources are wasted
Solution Approach 1:
The automated assistant performs self-service by automatically responding to notifications without requiring user intervention. It uses available data (location, calendar, contacts) to generate and send responses autonomously, eliminating the need for multiple user interactions while conserving computational resources
Solution Approach 2:
The system prepares and sends automatic responses in advance based on predicted user engagement levels. By anticipating when the user will be unavailable, it proactively handles notifications before they would require user attention, reducing the need for repeated interactions
3Object-affected harmful factors
If notifications are suppressed during high engagement periods, then user safety is improved, but information delivery is delayed
Solution Approach 1:
The system performs preliminary actions by automatically responding to notifications during high engagement periods without user awareness. It handles the notification in the background and only informs the user after completion, eliminating delay while maintaining safety
Solution Approach 2:
The automated assistant acts as an intermediary between the notification system and the user. It receives notifications, processes them automatically using available data, and delivers responses without requiring user presence, thus bridging the gap between safety and timely information delivery
Data Source
AI summary
Dynamically adapting provision of notification output to reduce distractions and/or to mitigate usage of computational resources. In some implementations, an automated assistant application predicts a level of engagement for a user and determines, based on the predicted level of engagement (and optionally future predicted level(s) of engagement), provisioning (e.g., whether, when, and/or how) of output that is based on a received notification. For example, the automated assistant application can, based on predicted level(s) of engagement, determine whether to provide any output based on a received notification, determine whether to suppress provision of output that is based on the received notification (e.g., until a later time with a decreased predicted level of engagement), determine whether to provide output that is a condensed version of the received notification, determine whether to automatically respond to the notification, and/or select an output modality for providing output that is based on the received notification.