Efficient initial acquisition with gain state prediction using machine learning

US12316398B2 · kind B2 · utility

Assignee

• QUALCOMM Incorporated · US

Inventors

• Khyati Bhupendrabhai Mardia · San Diego, US
• Yue Hong · San Diego, US
• Sandeep Ramannavar · San Diego, US
• Rohit Bhasi Thazhath · San Diego, US
• Shraddha Ramachandra Phadnis · San Diego, US
• Madhup Chandra · San Diego, US
• Arvind Vardarajan Santhanam · San Diego, US
• Shanshan Wang · San Diego, US
• Yongle Wu · San Diego, US
• Tom Chin · San Diego, US
• Scott Hoover · Goshen, US

Key dates

• Filing date: Mar 30, 2023
• Grant date: May 27, 2025
• Expiry date: Mar 30, 2043

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04W88/06
• WIPO field: Digital communication
• WIPO sector: Electrical engineering

Abstract

Methods, systems, and devices for wireless communications are described. For example, the described techniques provide for a user equipment (UE) to predict a gain state for an initial acquisition procedure. For example, the UE may use a machine learning (ML) model to predict an initial gain state which is likely to result in a successful initial acquisition procedure (e.g., without adjusting the gain state and reattempting the initial acquisition procedure). The UE may input UE history data or crowdsourced data (e.g., from a local network or a cloud-based server) into the ML model to generate a predicted gain state which may be more likely to result in a successful initial acquisition (e.g., without reattempting the initial acquisition procedure). The UE may use the initial gain state generated by the ML model to attempt an initial acquisition procedure with a network entity.