Methods for artificial intelligence-based positioning in wireless systems

EP4759015A1Pending Publication Date: 2026-06-17INTERDIGITAL PATENT HOLDINGS INC

Patent Information

Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
INTERDIGITAL PATENT HOLDINGS INC
Filing Date
2024-08-08
Publication Date
2026-06-17

AI Technical Summary

Technical Problem

Existing wireless standards, such as 3GPP, face challenges in efficiently utilizing AI/ML capabilities for enhanced positioning accuracy, as the current LMF-centric model may not be the most efficient approach with the introduction of advanced AI-based location technologies.

Method used

A method where a network function determines whether to perform an AI/ML-based positioning procedure based on entity capabilities, KPI requirements, or network policies, selecting appropriate AI/ML models and entities involved, and transmitting measurements to these models for improved positioning results.

Benefits of technology

This approach enables more accurate and efficient AI/ML-based positioning by leveraging the capabilities of various entities within the wireless system, such as WTRU, RAN, LMF, and NWDAF, thereby enhancing positioning accuracy and meeting specific KPI requirements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2024041398_13022025_PF_FP_ABST
    Figure US2024041398_13022025_PF_FP_ABST
Patent Text Reader

Abstract

A method performed by a NF may comprise: receiving, from a WTRU, a positioning request; determining to whether to perform an AI / ML-based positioning procedure; on a condition that the NF determines to perform an AI / ML-based positioning procedure: selecting an AI / ML-based positioning procedure; determining one or more entities that are involved in the AI / ML-based positioning procedure; receiving measurements from at least one of the WTRU or a RAN; and transmitting the received measurements to an AI / ML model.
Need to check novelty before this filing date? Find Prior Art