Trajectory Prediction Forking With Confidence Thresholds for UE Handover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing trajectory prediction methods in wireless communication networks struggle to accurately predict multiple likely trajectories of user equipment, leading to inefficient resource allocation and increased interruption times due to incorrect predictions.
Innovation Solution
A confidence-based approach is introduced, where the model predicts a set of possible future trajectories by creating 'forks' when multiple paths have high confidence, using forking criteria to ensure adequate prediction confidence and iteratively determining next locations, allowing for better resource allocation and reduced interruption times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single trajectory prediction method is used, then the prediction process is simple, but the prediction accuracy is insufficient and resource allocation is inefficient
Solution Approach 1:
The patent segments the trajectory prediction by creating multiple forks representing different possible paths. Each fork is evaluated independently with confidence scoring, allowing the system to handle multiple predictions systematically rather than as a single complex prediction, thereby improving accuracy without overwhelming complexity
Solution Approach 2:
The patent introduces confidence thresholds as a parameter to control the forking process. By adjusting this threshold, the system can dynamically control the number of forks created, balancing between prediction accuracy (more forks) and process complexity (fewer forks), thus resolving the contradiction through parameter optimization
2Reliability
If multiple trajectory forks are created, then the prediction accuracy improves, but the computational complexity and resource consumption increase
Solution Approach 1:
The patent performs preliminary confidence evaluation for each potential fork before fully processing it. This preliminary action filters out low-confidence predictions early, reducing the number of forks that require full computational processing, thus maintaining reliability while reducing computational complexity
Solution Approach 2:
The patent applies partial processing to forks based on their confidence levels. High-confidence forks receive full processing attention, while lower-confidence forks receive reduced processing or are discarded, implementing a partial action strategy that maintains overall prediction reliability while managing computational resources efficiently
3Reliability
If confidence threshold is set high, then the prediction reliability is high, but the number of predicted trajectories is reduced
Solution Approach 1:
The patent makes the confidence threshold dynamic rather than fixed. The threshold can be adjusted based on network conditions, UE behavior patterns, and prediction context, allowing the system to adapt between high reliability (higher threshold) and high versatility (lower threshold) modes as needed, resolving the contradiction through dynamic parameter adjustment
Data Source
AI summary
An apparatus includes at least one processor; and at least one memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: receive as input to a machine learning model a sequence of past serving locations of a user equipment; determine, using the machine learning model, a vector of confidences for predicted next locations of the user equipment; create at least one fork for at least one predicted next location of the predicted next locations having a confidence that exceeds a forking threshold; and determine iteratively a plurality of next locations of the user equipment, using as input the at least one predicted next location having the confidence that exceeds the forking threshold.