/Patent Tracker
GooglePatent applicationNetworks & wirelessInterest 4/10

Google patents method to shrink wireless data using machine learning

Google describes a way for phones to send less data back to cell towers while still describing the quality of the connection. The phone uses a machine learning model to compress the information about the signal path into a smaller report.

Why it mattersThis could help mobile networks handle more traffic efficiently by reducing the amount of data phones need to send to towers.

In the filing’s own words

This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for low-complexity ML-based CSI compression ( 270 a). A UE ( 102) receives ( 240), from a network entity ( 104), a CSI-RS for a channel estimation ( 250). The UE ( 102) sends ( 285), to the network entity ( 104), a CSI report including a first PMI and a second PMI. The first PMI indicates a wideband preceder ( 355) associated with the channel estimation ( 250) and the second PMI indicates a compressed subband eigenvecter associated with the wideband preceder ( 355).

What exactly they claim (claim 1)

1 - 18. (canceled)

Facts

Company
Google (Google LLC)
Official title
LOW COMPLEXITY MACHINE LEARNING-BASED CHANNEL STATE INFORMATION COMPRESSION
Publication number
US20260261305A1
Application number
18994553
Filed
May 25, 2023
Published
Sep 3, 2026
Inventors
2
Claims
21

Classified under

H04B 7/0626 Electricity & electronicsH04B 7/0456 Electricity & electronicsH04W 72/21 Electricity & electronics
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in Networks & wireless

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.