17932174. SIMILARITY LEARNING FOR CROWD-SOURCED POSITIONING simplified abstract (QUALCOMM Incorporated)

SIMILARITY LEARNING FOR CROWD-SOURCED POSITIONING

Organization Name

QUALCOMM Incorporated

Inventor(s)

Sooryanarayanan Gopalakrishnan of San Diego CA (US)

Jay Kumar Sundararajan of San Diego CA (US)

Taesang Yoo of San Diego CA (US)

Naga Bhushan of San Diego CA (US)

Guttorm Ringstad Opshaug of Redwood City CA (US)

Grant Marshall of Campbell CA (US)

Chandrakant Mehta of Cupertino CA (US)

Zongjun Qi of Saratoga CA (US)

SIMILARITY LEARNING FOR CROWD-SOURCED POSITIONING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17932174 titled 'SIMILARITY LEARNING FOR CROWD-SOURCED POSITIONING

Simplified Explanation

The patent application focuses on enhancing the accuracy and latency of User Equipment (UE) positioning through crowd-sourcing. A network entity computes a position estimate of a UE using neighbor-cell scan data from the UE and reference UEs.

• Network entity receives measurements from a UE for at least one cell.
• Position estimation of the UE is performed using measurements from the UE, measurements from reference UEs, or locations of reference UEs through an ML model.
• UE and reference UEs share at least one common cell for positioning.

Potential Applications

• Enhanced location-based services
• Improved emergency response systems
• Optimized network planning and optimization

Problems Solved

• Inaccurate UE positioning
• High latency in determining UE location
• Limited availability of reference points for positioning

Benefits

• Increased accuracy in UE positioning
• Reduced latency in determining UE location
• Enhanced overall network performance

Original Abstract Submitted

Aspects presented herein may enhance the accuracy and/or latency of UE positioning based on crowd-sourcing, where a network entity may compute a position estimate of a UE based on neighbor-cell scan data from the UE and one or more reference UEs. In one aspect, a network entity receives a first set of measurements associated with at least one cell from a UE. The network entity performs a position estimation of the UE based on at least one of the first set of measurements associated with the at least one cell, a second set of measurements for each of a set of reference UEs, or a location of each of the set of reference UEs via an ML model, where the UE and the set of reference UEs include at least one common cell.