17457718. BEAM-BASED MACHINE LEARNING-ENABLED RFFP POSITIONING simplified abstract (QUALCOMM Incorporated)

From WikiPatents
Jump to navigation Jump to search

BEAM-BASED MACHINE LEARNING-ENABLED RFFP POSITIONING

Organization Name

QUALCOMM Incorporated

Inventor(s)

Mohammed Ali Mohammed Hirzallah of San Diego CA (US)

Srinivas Yerramalli of San Diego CA (US)

Taesang Yoo of San Diego CA (US)

Rajat Prakash of San Diego CA (US)

Xiaoxia Zhang of San Diego CA (US)

BEAM-BASED MACHINE LEARNING-ENABLED RFFP POSITIONING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17457718 titled 'BEAM-BASED MACHINE LEARNING-ENABLED RFFP POSITIONING

Simplified Explanation

The patent application describes a method to improve the uniqueness of RF fingerprints by associating them with beam directions and features. This allows for more accurate positioning of wireless devices.

  • The ML module associates RF fingerprints with beam directions and features to enhance their uniqueness.
  • The network entity receives a plurality of first RF fingerprints associated with directional features and locations from wireless devices.
  • The network entity also receives a request to determine the position of a UE based on second RF fingerprints associated with the UE.
  • The position of the UE is estimated by matching the second RF fingerprints to the first RF fingerprints.

Potential Applications

  • Improved positioning accuracy for wireless devices.
  • Enhanced location-based services.
  • Better network optimization and management.

Problems Solved

  • Uniqueness of RF fingerprints is improved, reducing the chances of false matches.
  • Accurate positioning of wireless devices is achieved, enabling various applications and services.

Benefits

  • Increased accuracy in determining the position of wireless devices.
  • Improved efficiency in network optimization and management.
  • Enhanced user experience with location-based services.


Original Abstract Submitted

Aspects presented herein may enable an ML module to associate RF fingerprints with beam directions and/or beam features to improve the uniqueness of RF fingerprints. In one aspect, network entity may receive, from one or more wireless devices, a plurality of first RF fingerprints, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location. The network entity may receive a request to determine a position of a UE based on at least one second RF fingerprint associated with the UE or captured by the UE. The network entity may estimate the position of the UE based at least in part on matching the at least one second RF fingerprint to at least one of the plurality of first RF fingerprints.

Retrieved from "http://wikipatents.org/index.php?title=17457718._BEAM-BASED_MACHINE_LEARNING-ENABLED_RFFP_POSITIONING_simplified_abstract_(QUALCOMM_Incorporated)&oldid=25903"