Network policy optimization method and apparatus, computer readable storage medium
By acquiring parameters and business test metrics from competitor networks, a network policy classification model is trained, and the parameters of the network to be optimized are automatically optimized. This solves the problem of low network policy accuracy in existing technologies and achieves more efficient network optimization.
CN117081926BActive Publication Date: 2026-07-03CHINA MOBILE GRP FUJIAN CO LTD +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA MOBILE GRP FUJIAN CO LTD
- Filing Date
- 2022-05-07
- Publication Date
- 2026-07-03
AI Technical Summary
Technical Problem
Existing network optimization strategies rely on the experience of network optimization engineers and lack analysis of competitor networks, resulting in low accuracy and instability of the strategies.
Method used
By acquiring network parameters and business test metrics from competitor networks, a network strategy classification model is trained to automatically optimize the network parameters of the network to be optimized, and machine learning is used to analyze network strategies from multiple dimensions.
Benefits of technology
It significantly improves the accuracy and efficiency of network strategy optimization, and enhances the competitiveness of the network to be optimized.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117081926B_ABST
Abstract
This application discloses a network strategy optimization method and apparatus, and a computer-readable storage medium, comprising: acquiring network parameters and service test indicators of a first network and a second network of competitors within each competitor network region; determining the superiority index value of the first network based on the comparison results of the superiority and inferiority of the same type of service test indicators of the first network and the second network; determining network strategy classification samples and corresponding strategy superiority and inferiority labels based on the network parameters and service test indicators of the first network and the second network, as well as the superiority index value of the first network, and training a network strategy classification model for classifying the network strategy of the first network as superior or inferior; classifying the network strategy of the target network to be optimized within the target competitor network region based on the network strategy classification model; and optimizing the network parameters of the target network to be optimized based on the network parameters of the competitor networks within the target competitor network region when the network strategy classification result is inferior.
Need to check novelty before this filing date? Find Prior Art