Communication method and apparatus
By negotiating the use of the same AI model between terminal devices and network devices, and by utilizing the uplink high-channel estimation algorithm to assist downlink performance monitoring, the problem of low AI model monitoring accuracy is solved, thereby improving the stability of the communication system and the efficiency of the equipment.
WO2026144663A1PCT 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
- 2025-11-25
- Publication Date
- 2026-07-09
AI Technical Summary
Technical Problem
In existing technologies, the accuracy of AI models in communication systems is low, leading to instability in the operation of communication systems.
Method used
By negotiating the use of the same AI model between terminal devices and network devices, and performing performance monitoring in the uplink direction, the high channel estimation algorithm accuracy of network devices is used to assist in the performance monitoring in the downlink direction, and the configuration of multiple reference signals is combined to improve monitoring accuracy.
Benefits of technology
It improves the accuracy of AI model performance monitoring, reduces meaningless performance monitoring, and lowers device power consumption and performance consumption.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN2025137456_09072026_PF_FP_ABST
Abstract
A communication method and apparatus, for use in improving the accuracy of model monitoring. The method comprises: a first device receives first information, wherein the first information is used for adjusting information related to performance monitoring for a first AI model, and the first AI model is used by the first device to perform channel estimation on a channel between the first device and a second device; and on the basis of the first information, the first device determines a performance monitoring result for the first AI model, or stops monitoring the performance of the first AI model. It can be understood that in addition to information required by the first device to perform performance monitoring on the first AI model in the related art, the first information for assisting in performance monitoring is additionally provided to the first device, so that the first device can implement more accurate performance monitoring for the first AI model on the basis of the additionally provided first information.
Need to check novelty before this filing date? Find Prior Art