Adaptive Notification Provisioning for Low-Distraction Assistant Output
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated assistant applications often distract users by requiring multiple interactions to accomplish tasks, especially in situations like driving, leading to safety concerns and inefficient use of computational resources.
Innovation Solution
An automated assistant application dynamically determines when and how to present notifications to users, adapting based on predicted levels of engagement, notification properties, and sensor data to minimize distractions and conserve resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If multiple interactions are required to accomplish tasks with automated assistant, then task completion accuracy is improved, but user distraction and safety risks increase
Solution Approach 1:
The system performs preliminary actions by predicting future user engagement levels and proactively scheduling notification deliveries for optimal times. Instead of requiring multiple interactions during high-engagement periods, the system anticipates better moments to deliver information, reducing the need for repeated user engagements during critical driving periods.
Solution Approach 2:
The system dynamically adapts notification delivery based on real-time assessment of user engagement levels derived from sensor data, route characteristics, and contextual information. This dynamic approach allows the system to adjust between immediate delivery and delayed delivery, optimizing between task completion efficiency and user safety based on current conditions.
2Speed
If notifications are provided immediately upon receipt, then information delivery timeliness is improved, but user distraction increases
Solution Approach 1:
The system performs preliminary analysis of user engagement levels and route characteristics before delivering notifications. By predicting future engagement levels, the system can proactively schedule notifications for optimal delivery times, ensuring timely information delivery without causing distraction during high-engagement driving periods.
Solution Approach 2:
The system continuously monitors sensor data, user behavior patterns, and route characteristics to provide feedback on optimal notification timing. This feedback loop enables the system to adjust notification delivery timing dynamically, balancing information timeliness with user safety by delaying notifications when distraction risk is high.
3Object-affected harmful factors
If notifications are delayed until user engagement is low, then user distraction is reduced, but information delivery timeliness deteriorates
Solution Approach 1:
The system performs preliminary prediction of user engagement levels to identify optimal notification delivery windows. By anticipating periods of lower engagement based on route characteristics and historical patterns, the system can schedule notifications in advance for these optimal times, maintaining timeliness while reducing distraction.
Solution Approach 2:
The system dynamically balances notification timing based on real-time engagement assessment. Rather than applying fixed delay rules, the system adapts delivery timing continuously based on sensor data and contextual factors, optimizing the balance between timeliness and distraction reduction for each specific situation.
4Manufacturing precision
If multiple interactions are required for task completion, then task accuracy is improved, but computational resource consumption increases
Solution Approach 1:
The system performs preliminary processing of notifications and predictions of optimal delivery timing, consolidating multiple potential interactions into a single strategically timed delivery. This preliminary action reduces the need for multiple back-and-forth interactions, thereby decreasing computational resource consumption while maintaining task completion accuracy.
Solution Approach 2:
The system uses sensor data and contextual information already being collected for other purposes to predict optimal notification timing, rather than requiring additional user inputs or interactions. This self-service approach leverages existing data streams to optimize notification delivery, reducing computational overhead while maintaining accuracy.
5Loss of information
If notifications are re-provided after being ignored, then information delivery completeness is improved, but computational resource consumption increases
Solution Approach 1:
The system performs preliminary assessment of user engagement and notification importance to determine optimal delivery timing before the user might ignore it. By predicting the best moment for delivery based on engagement levels and route characteristics, the system ensures information is delivered when the user is most likely to process it, eliminating the need for re-provisioning and conserving computational resources.
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.