AI-Based Positioning in Wireless Networks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current communication technologies lack efficient methods for enhancing positioning accuracy using artificial intelligence and machine learning models within the 3GPP framework, particularly in radio access technologies, leading to suboptimal location determination in wireless networks.

Innovation Solution

Implement AI-based positioning methods by activating an AI-based positioning model at terminal devices, access network devices, or core network devices, involving the exchange of AI capabilities and trained models through LPP and NRPPa protocols to improve positioning accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If AI-based positioning methods are implemented, then positioning accuracy is improved, but device complexity increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the positioning system into multiple components: terminal devices that collect measurement data, access network devices that process data and host AI models, and core network devices that coordinate operations. This segmentation allows AI-based positioning accuracy improvement while distributing computational complexity across different devices rather than concentrating it in one device.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces access network devices as intermediaries between terminal devices and core network devices. The access network device receives measurement data from terminals, processes it using AI models, and communicates results to the core network. This intermediary role reduces the complexity burden on individual devices by distributing processing functions.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If AI models are deployed at terminal devices, then positioning accuracy is enhanced, but energy consumption increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoidenergy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

Instead of deploying AI models at terminal devices (which would consume terminal energy), the patent inverts the approach by deploying AI models at access network devices. Terminal devices only perform lightweight measurement and data collection, while the energy-intensive AI processing occurs at the network side, thereby reducing terminal energy consumption while maintaining positioning accuracy enhancement.

Inventive Principle:
Principle #13The other way round (Inversion)

Solution Approach 2:

The access network device performs self-service by hosting and executing AI positioning models locally, eliminating the need for terminal devices to consume energy for complex AI computations. The network infrastructure serves itself by providing the computational resources needed for accurate positioning without burdening the terminal devices.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If AI-based positioning is activated, then positioning accuracy is improved, but protocol complexity increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoidprotocol complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent enhances existing positioning protocols (LPP and NRPPa) to serve multiple functions: traditional positioning operations and AI model coordination. By making these protocols multi-functional, the patent avoids creating entirely new complex protocols and instead extends existing ones to handle AI-based positioning, thereby reducing overall protocol complexity while achieving improved positioning accuracy.

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

Data Source

PatentUS20250212160A1Methods, devices, and medium for communication
Publication Date: 2025.06.26 NEC CORP
  • US20250212160A1 patent drawing
  • US20250212160A1 patent drawing
  • US20250212160A1 patent drawing

AI summary

Example embodiments of the present disclosure relate to methods, devices, and medium for communication. A terminal device receives, from a core network device, an LPP message informing the terminal device to activate an AI-based positioning for determining location related information based on an output of the positioning model; and transmitting the location related information to the core network device. In additional, an interaction between an access network device and a core network device via NRPPa is triggered to activate an AI-based positioning for determining location related information based on the output of a positioning model, and transmitting the location related information to the core network device. In this way, a procedure between the terminal device and the core network device is defined and thus the positioning accuracy may be improved.