On-Device Hybrid ML for Predictive UE Call Quality Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing call quality optimization solutions are inefficient for known user equipment (UE) and do not consider real-time user activity or background noise, leading to unpredictable call quality degradation during long duration calls with known entities.
Innovation Solution
A hybrid machine learning model is used to identify patterns influencing call quality based on historical data and real-time context, allowing for resource adjustments in user equipment (UE) to improve call quality, such as adjusting resource allocation, network configuration, and providing user recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional holistic call quality solutions are applied, then call quality is addressed for all users, but the solutions are not practical and inefficient for known UE with specific call patterns
Solution Approach 1:
The patent applies local quality by transitioning from holistic call quality solutions to UE-specific optimizations. The system identifies known UE based on call patterns, locations, and entities, then applies tailored resource allocation and network configuration adjustments specific to each UE's historical performance and requirements, rather than applying uniform solutions to all users.
Solution Approach 2:
The patent implements preliminary action by analyzing historical call data and identifying patterns before actual calls occur. The system pre-determines optimal resource allocation, coding techniques, and network parameters based on historical performance of known UE, enabling proactive optimization before call quality degradation can occur.
2Reliability
If network-based solutions monitor network performance, then resource allocation is managed, but UE state tracking and real-time user activity consideration are insufficient
Solution Approach 1:
The patent applies self-service by enabling the UE to autonomously analyze its own call history, identify patterns, and determine optimal resource allocation. The UE independently tracks its own state, location, and call characteristics, reducing dependency on complex network-based tracking while maintaining reliable performance monitoring and adaptive optimization.
3Reliability
If real-time resource adjustment is made, then call quality issues are predicted and mitigated, but computational resources and processing complexity increase
Solution Approach 1:
The patent applies preliminary action by pre-analyzing historical call data to identify patterns and predict potential quality issues before they occur. The system performs computational analysis in advance, establishing prediction models and resource allocation strategies beforehand, which reduces the need for intensive real-time computation during actual calls.
Solution Approach 2:
The patent implements dynamics by adapting resource allocation and network parameters in real-time based on predicted call quality issues. The system dynamically adjusts coding techniques, bandwidth allocation, and network routing decisions according to the specific call context and predicted requirements, optimizing the balance between computational energy consumption and call quality consistency.
Data Source
AI summary
Embodiments of the present disclosure disclose method and apparatus optimizing call quality in a user equipment (UE). The method includes: identifying a mobile originated (MO) call or a mobile terminated (MT) call satisfying one or more criteria; capturing a plurality of parameters associated with the MO call or the MT call and the UE, based on the MO call or the MT call satisfying the one or more criteria and correlating the plurality of parameters with historical call data to identify one or more patterns influencing the call quality; analyzing, using a hybrid machine learning (ML) model, the one or more identified patterns and predicting call quality issues for the MO call or the MT call; and adjusting UE resources based on the predicted call quality issues and real time context data and adjusting includes providing recommendations for a user of the UE.