arrow
返回

Improving the system log analysis with language model and semi-supervised classifier

delete2019-03-23
delete1
PRE
AI
G
Guofu Li
P
Pengjia Zhu
N
Ning Cao *
M
Mei Wu
Z
Zhiyi Chen
G
Guangsheng Cao
李洪均 封面图
李洪均 (Hongjun Li)
C
Chenjing Gong
DOI:10.1007/s11042-018-7020-3delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Mining the vast amount of server-side logging data is an essential step to boost the business intelligence, as well as to facilitate the system maintenance for multimedia or IoT oriented services. Considering the vast volume of the data repository, designers of these logging-data analysis systems need to carefully balance the speed of the processing and the accuracy of the message classification. Conventional keyword-based log data monitoring and classification is sufficiently fast, but does not scale well in complex systems, especially when the target system is contributed by a large group of developers, each may differ in the way to encode the logging messages, and often carrying misleading labels. Conversely, many of the sophisticated approaches may suffer from their considerable time consumption, such that delayed processing jobs may begin to accumulate, and can hardly support the timely decision requirements. Meanwhile, we also suggest that the design of a large scale online log analysis should follow a principle that requires the least prior knowledge, in which unsupervised or semi-supervised solution is preferred. In this paper, we propose a two-stage machine learning based method, in which the system logs are regarded as the output of a quasi-natural language, pre-filtered by a perplexity score threshold, and then undergo a fine-grained classification procedure. Empirical studies on our web-services show that our method has obvious advantage in terms of processing speed and classification accuracy.
Keyword:
Log analysis
Language model
Machine learning
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Multimedia Tools and Applications 封面图
Multimedia Tools and Applications
IF:
3
论文数:
2.0W
被引数:
3.2W

机构

Q
Qingdao Binhai University
学者数:
246
论文数: 173
被引数: 566
Sanming University 封面图
Sanming University
学者数:
704
论文数: 492
被引数: 476
W
wuhan institute of technology
学者数:
1.0W
论文数: 6.6K
被引数: 11
学者 查看更多机构
引用论文

引用论文

Electric-field dependence of absorption spectra of polymer ion-hemicyanine dye complexes
err1990-12-01
err0
PREAI
errS. Nomura; T. Kobayashi; H. Matsuda; S. Okada; H. Nakanishi; H. Tomiyama
err分享
err收藏
Dependable Structural Health Monitoring Using Wireless Sensor Networks
err2017-07-01
err187
errOAAI
errBhuiyan, Md Zakirul Alam; Wang, Guojun; Wu, Jie; Cao, Jiannong; Liu, Xuefeng; Wang, Tian
err分享
err收藏
Bridging the gap: effect of text query reformulation in multimodal retrieval
err2017-01-03
err2
PREAI
errDatta, Deepanwita; Singh, Sanjay K.; Chowdary, C. Ravindranath
err分享
err收藏
Finger vein secure biometric template generation based on deep learning
err2017-01-21
err74
PREAI
errLiu, Yi; Ling, Jie; Liu, Zhusong; Shen, Jian; Gao, Chongzhi
err分享
err收藏
Towards Privacy-Preserving Content-Based Image Retrieval in Cloud Computing
err2018-01-01
err132
PREAI
errXia, Zhihua; Zhu, Yi; Sun, Xingming; Qin, Zhan; Ren, Kui
err分享
err收藏
Analysis of YouTube's traffic adaptation to dynamic environments
err2017-04-27
err7
PREAI
errAnorga, Javier; Arrizabalaga, Saioa; Sedano, Beatriz; Goya, Jon; Alonso-Arce, Maykel; Mendizabal, Jaizki
err分享
err收藏
err分享
err收藏
Entity linking across vision and language
err2017-05-09
err10
PREAI
errVenkitasubramanian, Aparna Nurani; Tuytelaars, Tinne; Moens, Marie-Francine
err分享
err收藏
学者 查看更多内容