Presentation | 2014-03-14 Mining normal log sequential patterns for failure analysis of enterprise system Ryosuke TOGAWA, Shinjiro YAGI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Log messages of information systems have specific patterns. They are important for failure analysis to detect error messages. On the other hand, log messages are complicated because of natures of log, such as parallel processes, similar processes, an explosion of a process and a change of order of messages in the pattern. In this paper we propose novel method to extract correct patterns from complicated logs. We introduced constrained conditions based on the natures into pattern extraction. With the experimental result, we showed the proposed method improves the accuracy of pattern extraction. We'll verify the effect on failure analysis with actual data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Log / Log messages / Failure Analysis / Patterns |
Paper # | ICM2013-62 |
Date of Issue |
Conference Information | |
Committee | ICM |
---|---|
Conference Date | 2014/3/6(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Information and Communication Management(ICM) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Mining normal log sequential patterns for failure analysis of enterprise system |
Sub Title (in English) | |
Keyword(1) | Log |
Keyword(2) | Log messages |
Keyword(3) | Failure Analysis |
Keyword(4) | Patterns |
1st Author's Name | Ryosuke TOGAWA |
1st Author's Affiliation | NEC Knowledge Discovery Research Laboratories() |
2nd Author's Name | Shinjiro YAGI |
2nd Author's Affiliation | NEC Knowledge Discovery Research Laboratories |
Date | 2014-03-14 |
Paper # | ICM2013-62 |
Volume (vol) | vol.113 |
Number (no) | 492 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |