User Equipment Neural Network Positioning for Indoor Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining the position of user equipment, such as using satellite signals or wireless network signals, struggle to accurately locate devices indoors.

Innovation Solution

User equipment equipped with a neural network model processes wireless signals to generate indicators, determining its position based on these indicators and a trained neural network, allowing for precise positioning even indoors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If satellite signals are used for positioning, then positioning accuracy is improved outdoors, but positioning accuracy deteriorates indoors

Engineering Contradiction:
Improvepositioning accuracyVSAvoidindoor positioning capability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent applies universality by making the user equipment capable of performing multiple positioning functions - both outdoor satellite-based positioning and indoor neural network-based positioning. The device selectively activates the appropriate positioning method based on the environment, achieving both outdoor accuracy and indoor capability through a single multi-functional system.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces wireless network signals as an intermediary for indoor positioning when satellite signals are unavailable. The neural network processes these intermediate wireless signals to derive position information, creating a mediator system that bridges the gap between satellite-based outdoor positioning and indoor positioning requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If wireless network signals are used for positioning, then positioning function is provided indoors, but positioning accuracy deteriorates

Engineering Contradiction:
Improveindoor positioning capabilityVSAvoidpositioning accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional signal-based positioning mechanics with a neural network-based system. Instead of relying on complex signal propagation models and time difference calculations that limit accuracy, the neural network learns complex patterns from wireless signals and directly predicts position, achieving higher accuracy through intelligent processing rather than mechanical measurement methods.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the processing parameters by using a neural network to analyze multiple wireless signal parameters simultaneously. The neural network processes signal strength, signal quality, and other wireless signal characteristics as input parameters to determine position, transforming the approach from single-parameter measurement to multi-parameter intelligent analysis.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If neural network model is used for positioning, then positioning accuracy is improved indoors, but device complexity increases

Engineering Contradiction:
Improveindoor positioning accuracyVSAvoidneural network processing capability
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-training the neural network model with positioning data before deployment. The neural network is trained offline with labeled position and wireless signal data, so that during actual operation, it only needs to perform inference rather than learning from scratch. This preliminary training phase separates the complex learning process from the operational phase, reducing real-time processing complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements self-service by enabling the user equipment to autonomously perform positioning using its own neural network model and locally processed wireless signals. The device independently determines its position without requiring complex centralized processing or extensive external infrastructure, making the system self-sufficient and reducing overall system complexity.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20250220624A1User equipment supporting neural network-based positioning function and operating method of the same
Publication Date: 2025.07.03 SAMSUNG ELECTRONICS CO LTD
  • US20250220624A1 patent drawing
  • US20250220624A1 patent drawing
  • US20250220624A1 patent drawing

AI summary

A user equipment supporting a first positioning function may include a transceiver configured to receive first wireless signals from a base station at a first position of the user equipment, and a first processor configured to control the transceiver, wherein the first processor is configured to, based on the first wireless signals, generate first values of a plurality of first indicators, and perform an operation according to the first positioning function of determining based on the first values whether the first position corresponds to a first specific position.