Dynamic Roaming Criteria Tuning via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network connection management in electronic devices is static and fails to account for individual user patterns and dynamic access point characteristics, leading to a subpar user experience when roaming between different network access points.
Innovation Solution
Incorporating a machine learning engine that adjusts scan and transfer criteria based on connection attributes, access point attributes, and user patterns to optimize network scanning and handoff processes, ensuring a consistent and high-quality user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If static logic is used for network scanning and handoff decisions, then device complexity is reduced and ease of operation is improved, but adaptability to different user patterns and dynamic access point characteristics deteriorates
Solution Approach 1:
The patent applies dynamics by transitioning from static handoff logic to dynamic machine learning-based decision-making. The system continuously learns from user behavior patterns and access point characteristics, adapting scan thresholds and handoff criteria in real-time to optimize network connectivity for each user's unique usage patterns and environmental conditions.
Solution Approach 2:
The patent changes parameters by using machine learning models to dynamically adjust scan thresholds, connection quality metrics, and handoff criteria based on learned user preferences and observed network conditions. These parameter changes enable the system to adapt to different users, devices, and environments while maintaining ease of operation through automated decision-making.
2Adaptability or versatility
If machine learning is implemented to dynamically adjust scan and transfer criteria, then adaptability to user patterns and access point characteristics is improved, but device complexity increases
Solution Approach 1:
The patent applies self-service by implementing machine learning models that automatically learn and adapt to user behavior patterns and network conditions without requiring manual configuration. The system autonomously adjusts scan criteria, evaluates connection quality, and makes handoff decisions based on learned patterns, eliminating the need for user intervention while managing the complexity internally.
Solution Approach 2:
The patent uses feedback mechanisms where the machine learning model continuously receives data from network scans, connection quality measurements, and user behavior observations. This feedback loop enables the system to refine its predictions and adjust its behavior over time, improving adaptability while the automated nature of the feedback processing manages the complexity burden on the user.
3Reliability
If frequent scanning for alternative access points is performed, then connection quality and throughput are improved, but energy consumption and device complexity increase
Solution Approach 1:
The patent applies partial action by performing scanning at optimized intervals rather than continuously, using machine learning predictions to determine when scanning is most beneficial. The system scans for alternative access points selectively based on predicted user behavior and current network conditions, achieving sufficient connection quality while reducing unnecessary energy consumption from excessive scanning.
Solution Approach 2:
The patent uses dynamics to adjust scan frequency adaptively based on learned user patterns and current network conditions. The machine learning model dynamically determines optimal scan intervals, increasing scanning activity when connection quality is at risk and reducing it when the current connection is stable, thereby balancing reliability with energy efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The electronic devices described herein are configured to enhance user experience associated with a network connection when transitioning the network connection between access points. Determinations to scan for available access points and transfer the network connection to an alternative access point are based on connection attributes and/or access point attributes that are compared to scan criteria and transfer criteria. Further, the scan criteria and transfer criteria are updated, or adjusted, according to machine learning techniques such that the determinations to scan for access points and transfer between access points are tuned on a per-device and/or per-user level to fit patterns of use of a particular device and/or user. Over time, the updates to the scan criteria and transfer criteria based on machine learning provide an increasingly consistent, high quality user experience while roaming efficiently between access points.