Method and apparatus for hybrid inference for beam management in an artificial intelligence / machine learning system

EP4758742A1Pending Publication Date: 2026-06-17INTERDIGITAL PATENT HOLDINGS INC
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
INTERDIGITAL PATENT HOLDINGS INC
Filing Date
2024-08-08
Publication Date
2026-06-17

AI Technical Summary

Technical Problem

Current beam management techniques in AI/ML systems for 5G NR air interfaces face challenges in reducing overhead and latency, improving beam selection accuracy, and efficiently predicting beams in the time and spatial domains.

Method used

A method and apparatus where a WTRU is configured with input and output beam patterns and AI/ML models with trained weights. The WTRU measures signal quality of a subset of input beams to identify the best input beam, predicts the best output beam using AI/ML models, and reports these predictions to the base station for hybrid inference in beam management.

Benefits of technology

This approach enhances beam prediction accuracy, reduces latency and overhead, and improves overall performance in beam management by leveraging AI/ML models for optimized beam selection and prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2024041518_13022025_PF_FP_ABST
    Figure US2024041518_13022025_PF_FP_ABST
Patent Text Reader

Abstract

A WTRU is configured with input and output beam patterns and AI / ML models with trained weights. Each input beam pattern includes beam indexes for a set of input beams, and each output beam pattern includes beam indexes for a set of output beams. Each AI / ML model corresponds to one output beam pattern. The WTRU measures signal quality of a subset of the set of input beams of each input beam pattern to identify a best input beam and reports that beam to a base station. The WTRU receives, from the base station, an indication of one of the input beam patterns and one of the output beam patterns for predicting a best output beam based on the report. The WTRU predicts the best output beam using the AI / ML model corresponding to the indicated output beam pattern and the trained weights and reports the predicted best beam to the base station.
Need to check novelty before this filing date? Find Prior Art