Input selection aware monitoring for enhanced machine learning based positioning
By assessing and monitoring input matching between training and inference phases, the method ensures consistent input selection for machine learning-based positioning, improving accuracy in dynamic TRP environments.
Patent Information
- Application Number
- PCT/FI2025/050060
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-05-10
- Filing Date
- 2025-02-12
- Publication Date
- 2025-11-13
AI Technical Summary
Existing communication systems face challenges in ensuring consistent input matching between training and inference phases in machine learning-based positioning, leading to varying positioning accuracy due to differences in transmission-reception-point (TRP) selection and order, particularly in non-line-of-sight scenarios.
Implementing a method to assess and monitor the matching of inputs used during training and inference phases, using threshold matching factors and channel characteristics to adjust machine learning model switching, ensuring consistent input selection for improved positioning accuracy.
Enhances positioning accuracy by ensuring consistent input selection, thereby meeting quality of service requirements in dynamic TRP environments.