基于HMM-Viterbi的通信网络资源数据处理方法及应用  

HMM-Viterbi Based Network Resource Data Processing Method and Its Application

作　　者：吴茜 李尧辉[1] 朱青仑 WU Qian;LI Yaohui;ZHU Qinglun(China Mobile Guangdong Co.Ltd.,Guangzhou 510623,China)

机构地区：[1]中国移动通信集团广东有限公司,广东广州510623

出　　处：《移动通信》2022年第2期89-94,共6页Mobile Communications

摘　　要：移动通信网络庞大复杂,不同专业或业务的海量网络资源数据由不同的单位使用不同的方法进行录入和维护,因此存在资源数据难以实现端到端关联的痛点问题。针对该问题,提出了一种基于HMM-Viterbi算法的通信网络资源数据处理方法,用以解决现有技术中由于网络资源数据的数量大、种类多,导致人工录入等因素造成的各种数据不准确、不规范问题。经过对中国移动网络资源数据的处理,验证了基于HMM-Viterbi的通信网络资源数据处理的有效性。结果表明:对广东移动全省城域网共10391条传输电路资源数据进行处理,成功定位并实现智能纠错的数据达2250条,占比达21.65%;并且,处理后广州、深圳、东莞、佛山四个业务量最大地市的城域网与传输的平均跨专业告警关联成功率从23.5%提升至59.8%,增幅显著。The mobile communication network is huge and complex,and the massive network resource data of different professions or services are recorded and maintained by different organizations using different methods.Therefore,there is a pain point that it is difficult to realize end-to-end association of resource data.To tackle this issue,this paper proposes a network resource data processing method based on HMM (hidden Markov model)-Viterbi to solve various data inaccuracy and non-standard problems of manual records caused by the large amount and variety of network resource data in existing technologies.Through the processing of China Mobile network resource data,the effectiveness of the network resource data processing based on HMM-Viterbi is verified.The results show that:the processing on the 10391 transmission circuits resource data of Guangdong Mobile’s metropolitan area network successfully locates and realizes intelligent error corrections of 2250 circuits,accounting for 21.65%.Moreover,the success rate of inter professions alarm association of Guangzhou,Shenzhen,Dongguan and Foshan,the metropolitan area network cities with the largest traffic volume,on average is increased significantly from 23.5% to 59.8%.

关 键 词：隐马尔可夫模型 维特比算法 网络通信技术 网络资源数据 

分 类 号：TN912.34[电子电信—通信与信息系统]