Inferred User State Detection via Application Usage Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately detecting and managing user states, particularly mental states, which are crucial for optimizing device functionality and enhancing user experience, as users may be unwilling or unable to self-report their states.
Innovation Solution
A computer-implemented method that processes application-usage and session data to infer user states by generating embedded representations of application usage, clustering sessions, and determining device operations based on aggregated metrics and cluster assignments, allowing for passive monitoring and automatic adjustment of device functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users self-report their states, then accuracy of state detection is improved, but user willingness and ability to accurately identify state deteriorates
Solution Approach 1:
The system performs state detection automatically without requiring user participation or self-reporting. The device monitors application usage patterns and generates state inferences autonomously, allowing the system to serve itself rather than relying on user input for state detection.
Solution Approach 2:
The patent replaces the manual self-reporting mechanism with an automated computational system. Instead of relying on users to subjectively report their states, the system uses objective application usage data processed through algorithms to infer states automatically.
2Adaptability or versatility
If automated state inference is implemented, then user experience enhancement is improved, but device complexity increases
Solution Approach 1:
The state inference system is divided into distinct modular components: data collection module (application usage tracking), processing module (aggregated metrics calculation), inference module (state determination), and action module (device operation execution). This segmentation allows each component to be developed, tested, and maintained independently.
Solution Approach 2:
The system uses a unified approach where application usage data serves multiple purposes: tracking user behavior patterns, inferring cognitive states, determining mood, and triggering appropriate device responses. This multi-functional use of a single data source reduces the need for separate complex systems.
3Measurement precision
If continuous monitoring of application usage is performed, then state inference accuracy is improved, but energy consumption increases
Solution Approach 1:
Instead of continuous real-time monitoring, the system performs monitoring at discrete time points when application execution is detected. The aggregation of metrics occurs periodically based on detected execution events, reducing computational frequency while maintaining inference accuracy.
Solution Approach 2:
The system monitors only the necessary application execution events rather than all possible device operations. By focusing monitoring on application usage patterns specifically, the system achieves sufficient state inference accuracy without the energy cost of comprehensive continuous monitoring of all device activities.
Data Source
AI summary
Techniques are disclosed for controlling a device's operation based on an inferred state. More specifically, at each of a set of time points, execution of an application at an electronic device is detected. For each detected execution, an application-usage variable is determined. One or more aggregated metrics are generated based on aggregation of at least some of the application-usage variables. Based on the one or more aggregated metrics, a state identifier is identified that corresponds to an inferred state of a user of the electronic device. A device-operation identifier is retrieved that is associated with the state identifier. A device operation is performed associated with the device-operation identifier.