Neural Network Positioning for UE Clock Drift and Delay Uncertainty

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing wireless communication systems face challenges in accurately determining the location of user equipment (UE) due to variations in clock drift, hardware group delay, and other factors, which affect the precision of positioning measurements.

Innovation Solution

Implementing neural network functions that are dynamically generated based on machine-learning associated with historical measurement procedures to derive the likelihood of positioning measurement features, using UE-feature and BS-feature processing neural networks to enhance positioning estimates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional positioning measurement methods are used, then the positioning process is simple, but the positioning accuracy deteriorates due to clock drift and hardware group delay variations

Engineering Contradiction:
Improvepositioning accuracyVSAvoidpositioning system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transforms the positioning approach by changing from direct measurement to probability derivation. Neural network functions process historical measurement data to derive likelihoods of positioning features, fundamentally altering the measurement parameters from deterministic values to probabilistic assessments that account for clock drift and hardware variations

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary actions by collecting and processing historical measurement data before actual positioning occurs. Neural network functions are trained in advance on historical data to learn patterns and uncertainties, enabling more accurate real-time positioning without requiring complex real-time corrections for clock drift and hardware delays

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If neural network functions with historical measurement data are implemented, then positioning accuracy improves, but the processing complexity increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoidneural network processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the positioning problem into distinct neural network functions, each responsible for specific aspects such as clock drift compensation, hardware group delay correction, and final position estimation. This modular approach manages complexity by dividing the overall processing task into specialized, manageable components

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The neural network functions serve as intermediaries between raw measurement data and final positioning results. These intermediary processing layers transform and interpret historical measurement data, deriving meaningful positioning information while filtering out noise and systematic errors from clock drift and hardware variations

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4193163B1Neural network functions for positioning of a user equipment
Publication Date: 2026.04.08 QUALCOMM INC
  • EP4193163B1 patent drawingFigure 1
  • EP4193163B1 patent drawingFigure 2A
  • EP4193163B1 patent drawingFigure 2B

AI summary

In an aspect, a BS obtains at least one neural network function configured to facilitate a UE to derive a likelihood of at least one set of positioning measurement features being present at a candidate set of positioning estimates for the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures. The BS transmits the at least one neural network function to the UE. In another aspect, the UE obtains positioning measurement data associated with a location of the UE (e.g., locally the UE, or remotely from the BS). The UE determines a positioning estimate for the UE based at least in part upon the positioning measurement data and the at least one neural network function.