Communication methods, devices, system, and storage medium

By transmitting the AI ​​model's training dataset through multiple RRC messages, the storage and latency issues between the terminal and network devices were resolved, achieving efficient and accurate data transmission, adapting to terminal capabilities, and ensuring dataset integrity.

WO2026148554A1PCT designated stage Publication Date: 2026-07-16BEIJING XIAOMI MOBILE SOFTWARE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
BEIJING XIAOMI MOBILE SOFTWARE CO LTD
Filing Date
2025-01-09
Publication Date
2026-07-16

AI Technical Summary

Technical Problem

In existing technologies, when transmitting training datasets for AI models between terminals and network devices, there are problems of large storage requirements and high processing latency. In particular, when using RRC messages, the large amount of data leads to low storage and processing efficiency.

Method used

The training dataset of the AI ​​model is transmitted using multiple RRC messages. Each message contains a portion of the training data, and the integrity of the dataset is ensured by an identifier. The receiving side can start processing after receiving each message, and transmission is carried out using a dedicated signaling bearer.

Benefits of technology

It reduces storage requirements and processing latency, improves the transmission efficiency and accuracy of AI model training datasets, adapts to terminal capabilities, and ensures the complete transmission of datasets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025071627_16072026_PF_FP_ABST
    Figure CN2025071627_16072026_PF_FP_ABST
Patent Text Reader

Abstract

Embodiments of the present disclosure disclose communication methods, an apparatus, and a computer-readable storage medium, and relate to the technical field of communications. A communication method comprises: sending at least two first messages to a second device, the at least two first messages comprising at least part of a training data set, and the training data set corresponding to an artificial intelligence (AI) model. In the embodiments of the present disclosure, sending the training data set corresponding to the AI model by means of the at least two first messages can improve the transmission efficiency of the training data set of the AI model.
Need to check novelty before this filing date? Find Prior Art