Notification Timing Prediction Using Historical Response Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in managing notifications on personal electronic devices, as existing methods like muting sound or using vibrate-only options do not effectively differentiate between notification types, particularly for urgent versus non-urgent messages, leading to distractions and potential missed emergency calls.
Innovation Solution
A method and apparatus that analyze historical user data to determine the optimal time and device for presenting notifications based on activity status, time of day, context, and notification type, using a database that stores information about user responses to previous notifications, to increase the likelihood of timely attention from the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If the user mutes sound to prevent distractions from notifications, then audible notifications are reduced, but incoming voice calls cannot be distinguished from other notifications
Solution Approach 1:
The notification system segments different types of notifications (voice calls, text messages, emails, social media posts) and assigns distinct vibration patterns to each type. This allows the user to mute audible notifications while still being able to distinguish between different notification categories through unique vibration signatures, thereby reducing distractions while maintaining the ability to detect emergency calls.
Solution Approach 2:
Different vibration characteristics are applied to different notification types. Voice calls receive a specific vibration pattern that differs from text messages, emails, and social media notifications. This local differentiation in vibration quality enables the user to identify the type of notification without audible alerts, resolving the contradiction between distraction reduction and emergency call detection.
2Object-affected harmful factors
If the user selects vibrate-only option for notifications, then audible distractions are eliminated, but all notification types receive the same vibration pattern making them indistinguishable
Solution Approach 1:
The vibration notification system is segmented into multiple distinct patterns, with each pattern assigned to a specific notification type. Voice calls, text messages, emails, and social media posts each have their own unique vibration signature. This segmentation maintains adaptability and versatility in notification differentiation while eliminating audible distractions.
Solution Approach 2:
Each notification type receives a customized vibration pattern tailored to its specific category. The vibration frequency, duration, and pattern vary locally for each notification type, enabling the user to distinguish between different notifications through tactile feedback alone, thus achieving both distraction elimination and notification versatility.
3Reliability
If the user attends to all notifications immediately, then no notifications are missed, but focus on personal interactions or problem analysis is disrupted
Solution Approach 1:
The system performs preliminary analysis of the notification type and the user's current activity state before determining the notification delivery strategy. By anticipating the user's focus needs and pre-classifying notifications, the system can defer non-urgent notifications or deliver them in a manner that minimizes disruption, while ensuring urgent notifications are communicated through distinctive vibration patterns that cannot be ignored.
Solution Approach 2:
The notification system incorporates feedback about the user's current activity state and response patterns. By monitoring whether the user is engaged in personal interactions or problem analysis, the system adjusts notification delivery timing and intensity, providing feedback loops that maintain notification response completeness while preserving user focus and productivity.
Data Source
AI summary
A database comprises historical information of a user's response to previous notifications. The database is accessed to determine a time at which to provide a (new) notification to the user, utilizing at least: a) current user activity status (e.g., determined from measurement information collected from one or more personal devices and/or user calendar events; b) time/day; and c) context information about the notification (e.g., geo-location, indoors/outdoors) including notification type (e.g., calendar entry, email, IM). The user gets the notification via a portable device at the determined time. A machine learning model can select the determined time by discriminating features of the previous notifications for which the user immediately attended versus those that were deferred and/or ignored. Content of the notification can also be altered in view of such discriminating features so as to increase a likelihood the user will immediately attend to the provided notification.