Proxemic PDF Notification Management for Privacy and Complexity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for managing device notifications are invasive of user privacy, require extensive use of external sensors, and are computationally complex, making them inefficient and costly.
Innovation Solution
The use of proxemic probability density functions (PDFs) to manage device notifications by sensing a user's immediate environment and computing the likelihood of interaction with other humans or devices, allowing for dynamic adjustment of notification settings based on the user's cognitive load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing solutions are used to manage device notifications, then notification management capability is provided, but user privacy is invaded
Solution Approach 1:
The system uses the device's own sensors (microphone, speaker, accelerometer) to autonomously detect user engagement state without requiring external monitoring devices or invasive data collection. The device serves itself by using its existing components to manage notifications based on detected user interaction patterns.
Solution Approach 2:
The system introduces an intermediary approach by using audio signal analysis and proxemic probability density functions as indirect indicators of user engagement, rather than directly monitoring private user behavior or installing external sensors. This intermediary layer enables notification management while preserving user privacy.
2Adaptability or versatility
If existing solutions are used to manage device notifications, then notification management capability is provided, but extensive external sensors are required
Solution Approach 1:
The system makes existing multi-functional components (microphone for audio recording, speaker for audio output, accelerometer for motion detection) serve the additional purpose of detecting user engagement state for notification management. This eliminates the need for dedicated external sensors while maintaining comprehensive notification management capability.
Solution Approach 2:
The device uses its own built-in sensors to perform engagement detection without requiring external sensor hardware. The microcontroller and existing sensors work together to autonomously determine when notifications should be suppressed, eliminating dependency on external sensing infrastructure.
3Adaptability or versatility
If existing solutions are used to manage device notifications, then notification management capability is provided, but computational complexity increases
Solution Approach 1:
The system applies partial action by using simplified audio feature extraction and threshold-based decision making rather than complex machine learning models. The proxemic probability density function uses basic mathematical operations (Gaussian calculations) rather than computationally intensive algorithms, achieving effective notification management with reduced computational overhead.
Solution Approach 2:
The system changes the computational approach by transforming raw audio and motion data into simplified probabilistic representations (proxemic probability density functions). This parameter transformation reduces computational complexity while maintaining the ability to accurately detect user engagement states for notification management.
Data Source
AI summary
Methods and devices for management of notifications at an electronic device are disclosed. Sensed data is obtained representing a sensed location of the user and at least one other human or device. A first proxemic probability density function (PDF) is defined using the sensed location of the user and at least one other proxemic PDF is defined using the sensed location of the at least one other human or device. An entropy metric is generated representing likelihood of interaction between the user and the at least one other human or device by computing an overlap between the first proxemic PDF and the other proxemic PDF. In response to the entropy metric exceeding a defined threshold, the electronic device transitions from a default mode to an engaged mode, wherein in the engaged mode the electronic device is controlled to provide at least one output differently than in the default mode.