Communication method and apparatus

By establishing associated AI models in wireless communication systems and ensuring that the models meet the same criteria, the problem of high overhead in feedback channel state information from terminal devices is solved, thereby improving the performance of AI models and the efficiency of communication systems.

WO2026145103A1PCT designated stage Publication Date: 2026-07-09HUAWEI TECH CO LTD

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
HUAWEI TECH CO LTD
Filing Date
2025-12-22
Publication Date
2026-07-09

AI Technical Summary

Technical Problem

In wireless communication systems, when using massive MIMO technology, the overhead of terminal devices feeding back channel state information is too high, and the design of existing AI models cannot effectively improve performance.

Method used

By establishing associated AI models between network devices and terminal devices, it is ensured that the models meet the same criteria, thereby improving the matching degree between models and reducing the feedback overhead of channel state information.

Benefits of technology

It improves the performance of AI models, reduces the feedback overhead of channel state information, and enhances the efficiency of communication systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025144298_09072026_PF_FP_ABST
    Figure CN2025144298_09072026_PF_FP_ABST
Patent Text Reader

Abstract

The present application provides a communication method and apparatus, which are applied to the technical field of communications. The method comprises: a first apparatus determines a first model on the basis of a first criterion; the first apparatus sends first information, and correspondingly, a second apparatus receives the first information; and the second apparatus determines a second model on the basis of the first information, wherein the second model satisfies the first criterion, and the first model is associated with the second model. By using the method, the first model can be generated on the basis of the first criterion, and by means of the first information, both the second model and the first model satisfy the first criterion, thereby improving the degree of matching between the first model and the second model and enhancing the model performance of the first model and the second model.
Need to check novelty before this filing date? Find Prior Art