Communication method and related device

By determining model suitability in wireless communication systems and using dataset similarity to assess model suitability, the problems of high model deployment latency and resource overhead in existing technologies are solved, achieving more efficient model deployment and higher accuracy.

WO2026007624A1PCT designated stage Publication Date: 2026-01-08HUAWEI TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2025/099834
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-07-01
Filing Date
2025-06-09
Publication Date
2026-01-08

Smart Images

  • Figure CN2025099834_08012026_PF_FP_ABST
    Figure CN2025099834_08012026_PF_FP_ABST
Patent Text Reader

Abstract

A communication method and a related device. The method comprises: generating or receiving first information, wherein the first information is used for indicating the similarity between a first data set and a second data set, the first data set is used for training a model, and the second data set consists of data acquired by a first communication device; and acquiring a determination result, wherein the determination result is determined on the basis of the first information, and the determination result is used for indicating whether the model is applicable to the first communication device. In this way, it is determined, on the basis of the similarity between the first data set and the second data set, whether the model is applicable to the first communication device, thereby preventing an inappropriate model from being sent to the first communication device, and also reducing the calculation overhead caused by model training.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Model similarity calculation method and model updating method

    CN116502095A

  • Information processor, method for processing information, computer program, and learning system

    JP2022064115A

  • Training transfer-focused models for deep learning

    US20200320379A1

  • Artificial intelligence optimization platform

    US20220230024A1

  • Context similarity detector for artificial intelligence

    US20230222360A1