Intelligent model adaptation method and device based on cloud-edge collaboration

By adaptively selecting and compressing intelligent models in the cloud, the problem of insufficient real-time performance and accuracy of edge devices under dynamic resources is solved, enabling edge devices to operate efficiently in complex inference tasks.

CN122137862APending Publication Date: 2026-06-02INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
INST OF AUTOMATION CHINESE ACAD OF SCI
Filing Date
2026-03-30
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

In existing technologies, cloud-edge collaborative intelligent agent adaptation methods rely on fixed schemes set manually, which cannot simultaneously meet the requirements of real-time performance and accuracy under the dynamic fluctuations of computing power and storage resources of edge devices. This makes it difficult for edge devices to meet the computing power requirements of various inference tasks.

Method used

By receiving quantized vectors from edge devices, the optimal intelligent model is adaptively selected in the cloud using a multi-dimensional matching and weight scoring mechanism. The model is then compressed under the resource constraints of the edge devices and sent to the edge devices using a differential model transmission mechanism, thereby dynamically updating the training dataset and optimizing the model.

Benefits of technology

In environments where edge devices have limited resources and variable operating conditions, the adaptive determination of the optimal model overcomes the waste of computing power in traditional manual fixed deployment schemes and improves the real-time performance and accuracy of edge devices when performing complex inference tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122137862A_ABST
    Figure CN122137862A_ABST
Patent Text Reader

Abstract

This invention provides a cloud-edge collaborative intelligent model adaptation method and apparatus. The method, applied to a cloud server, includes: receiving a quantization vector sent by an edge device; determining the quantization vector based on target information of the edge device, including device status information, computing resources, application scenario information, and requirement indicators; performing multi-dimensional matching and weighted scoring between the quantization vector and feature vectors corresponding to multiple intelligent models, and determining a target intelligent model from the multiple intelligent models based on the scoring results; and sending the target intelligent model to the edge device. The method and apparatus of this invention overcome the computational waste caused by traditional manual fixed deployment schemes, automatically adapting intelligent models for edge devices, thereby improving the real-time performance and accuracy of edge devices when performing complex inference tasks.
Need to check novelty before this filing date? Find Prior Art