Noisy Positioning Data Processing Using Network Assistance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing AI/ML-based positioning systems face challenges in processing noisy positioning data, which affects the accuracy of device positioning in communication networks.

Innovation Solution

The proposed solution involves an apparatus that obtains measurement data and noisy positioning data, generates denoised positioning data using network assistance information, and transmits both measurement and denoised positioning data. This process improves the accuracy of positioning data and enhances AI/ML-based positioning systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If AI/ML models use large datasets of training samples for positioning, then positioning accuracy is improved, but the accuracy of positioning data (labels) deteriorates due to noise

Engineering Contradiction:

Improvepositioning accuracyVSAvoidaccuracy of positioning data

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary denoising of positioning data before using it for AI/ML model training. A second apparatus receives noisy positioning data from a first apparatus, generates denoised positioning data using denoising rules, and transmits the cleaned data back for training purposes. This preliminary processing ensures that training datasets are free from noise while maintaining large dataset sizes for accurate positioning.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary denoising mechanism between data collection and model training. The second apparatus acts as a mediator that receives noisy positioning data, applies denoising rules to generate clean positioning data, and provides this processed data back to the first apparatus for AI/ML training. This intermediary layer separates the noise source from the training process while preserving data utility.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of manufacture

If noisy positioning data is used directly for training, then data collection is simplified, but positioning accuracy deteriorates

Engineering Contradiction:

Improvedata collection simplicityVSAvoidpositioning accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system implements self-service denoising where the second apparatus autonomously receives noisy positioning data, generates denoised positioning data using pre-configured denoising rules, and transmits the cleaned data back to the first apparatus. This self-service mechanism maintains data collection simplicity while automatically improving positioning accuracy through intelligent denoising processing.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20250048318A1Noisy positioning data processing

Publication Date: 2025.02.06 NOKIA TECHNOLOGIES OY

AI summary

Example embodiments of the present disclosure relate to methods, devices, apparatuses and computer readable storage medium of noisy positioning data processing. In a method, a first apparatus obtains measurement data and first positioning data associated with the measurement data. The first apparatus generates second positioning data from the first positioning data based on network assistance information. The first apparatus transmits at least the measurement data and the second positioning data. In this way, an accuracy of the positioning data can be improved.