Mobile Device Management with ML-Based Display Rate Personalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods of controlling mobile devices do not account for individual user behavior and usage patterns, resulting in suboptimal power, performance, and thermal management, which can degrade user experience.
Innovation Solution
A machine learning (ML) algorithm is trained to determine relationships between display frame and refresh rates and user behavior, enabling personalized power, performance, and thermal (PPT) management by adjusting these parameters based on historic and current usage patterns, including location, charging state, network state, and application usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If default temperature threshold is used to control mobile device performance, then thermal management is simplified, but user experience deteriorates due to lack of personalization
Solution Approach 1:
The system transitions from static default thresholds to dynamic personalized thresholds by continuously learning user behavior patterns and device usage contexts. The temperature threshold and performance attenuation strategies are dynamically adjusted based on individual user preferences, usage scenarios, and device state, resolving the contradiction between simplicity and adaptability.
Solution Approach 2:
The mobile device autonomously learns and adapts to user behavior patterns without requiring manual configuration. The system automatically collects usage data, trains personalized models, and adjusts thermal management parameters independently, maintaining operational simplicity while achieving personalization through self-service learning.
2Duration of action of stationary object
If performance attenuation is applied below charge level threshold, then battery life is extended, but user experience deteriorates due to suboptimal power management
Solution Approach 1:
The system changes the parameter of performance attenuation strategy based on multiple factors including charge level, usage pattern, and device state. Instead of a fixed threshold approach, the system dynamically adjusts power management parameters to balance battery life extension with optimized performance, resolving the contradiction between duration and operational quality.
Solution Approach 2:
The system implements feedback loops that monitor user interactions, usage patterns, and device performance in real-time. This feedback enables the system to learn from actual usage scenarios and refine power management strategies, ensuring that battery life extension does not compromise user experience through suboptimal performance.
3Device complexity
If conventional PPT management is used, then system complexity is reduced, but user experience deteriorates due to lack of personalization
Solution Approach 1:
The system performs preliminary learning and model training during idle periods or initial setup, collecting and processing usage data in advance. This preliminary action prepares personalized PPT management strategies before they are needed, allowing the system to maintain simplicity during operation while achieving personalization through pre-computed adaptive parameters.
Solution Approach 2:
The complex PPT management system is segmented into independent modules: data collection, usage pattern analysis, personalized model training, and real-time control execution. This segmentation allows each module to be optimized independently, managing overall system complexity while enabling sophisticated personalized control through coordinated module operation.
Data Source
AI summary
A method of for providing personalized management system, the method comprising: obtaining training data comprising respective sets of parameters of the mobile device, including at least one of a frame rate of the display and a refresh rate of the display, and corresponding usage of the mobile device; training the ML algorithm using the provided training data comprising determining relationships between the respective sets of parameters of the mobile device and the corresponding usage of the mobile device; and controlling the mobile device by managing parameters of the mobile device, including at least one of a frame rate of the display and a refresh rate of the display, responsive to the corresponding usage of the mobile device.