摘要
传统语音质量优化依赖于现场测试、案例积累和专家经验,以人工试验的方式分析问题,成本高昂且效率低下。通过应用数据挖掘、决策树机器学习算法以及地理可视化等多种技术,开发了基于大数据分析的语音体验优化可视化平台,可有效识别语音大数据中的规律,实现用户语音体验指标与无线网络性能指标关联分析、劣化门限智能识别以及质差区域画像分析等功能,有利于降低网络工程师技能门槛、提升网络优化工作效率、节省网络运维成本,为行业提供精准有效的语音体验提升解决方案。
Traditional voice quality optimization relies on field test,case accumulation and expert experience.It is costly and inefficient to analyze problems by manual test.Through the application of data mining,decision tree machine learning algorithm,geographic visualization and other technologies,a voice experience optimization visualization platform based on big data analysis was developed,which could effectively identify the laws in voice big data,and realize the functions of correlation analysis between user voice experience index and wireless network performance index,intelligent recognition of degradation threshold and image analysis of poor quality areas.It is conducive to reduce the skill threshold of network engineers,improve the work efficiency of network optimization,save network operation and maintenance costs,and provide accurate and effective voice experience improvement solutions for the industry.
作者
胡坚
孙磊
尹以雁
杨晓康
白金贵
张叶江
HU Jian;SUN Lei;YIN Yiyan;YANG Xiaokang;BAI Jingui;ZHANG Yejiang(China Mobile Group Yunnan Co.,Ltd.,Kunming 650041,China;Nokia Shanghai Bell Co.,Ltd.,Shanghai 201206,China)
出处
《电信科学》
2022年第10期131-139,共9页
Telecommunications Science
关键词
数据挖掘
地理可视化
决策树
语音体验
皮尔森相关系数
data mining
geographic visualization
decision tree
voice experience
Pearson correlation coefficient
