Invention Grant
- Patent Title: Qualifying machine learning-based CSI prediction
-
Application No.: US16888593Application Date: 2020-05-29
-
Publication No.: US11483042B2Publication Date: 2022-10-25
- Inventor: Yisheng Xue , Weiliang Zeng , Xiaoxia Zhang , Yongbin Wei
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Agent Yanling Yang
- Main IPC: H04B7/06
- IPC: H04B7/06 ; G06N20/00 ; H04L1/18 ; H04L41/16

Abstract:
Certain aspects of the present disclosure provide techniques for qualifying machine learning model-based channel state information (CSI) predictions. An example method generally includes receiving, from a network entity, a channel state information (CSI) prediction model for quantized CSI, calculating CSI based on downlink reference signal measurements, generating a quantized CSI difference value based a quantization of a difference between the calculated CSI and CSI predicted based on a CSI prediction model, and reporting, to the network entity, the calculated CSI and the quantized CSI difference value.
Public/Granted literature
- US20210376895A1 QUALIFYING MACHINE LEARNING-BASED CSI PREDICTION Public/Granted day:2021-12-02
Information query