LEKG: A System for Constructing Knowledge Graphs from Log Extraction

Fangrong Wang; Alan Bundy; Xue Li; Ruiqi Zhu; Kwabena Nuamah; Lei Xu; Stefano Mauceri; Jeff Z. Pan

doi:10.1145/3502223.3502250

LEKG: A System for Constructing Knowledge Graphs from Log Extraction

Fangrong Wang, Alan Bundy, Xue Li, Ruiqi Zhu, Kwabena Nuamah, Lei Xu, Stefano Mauceri, Jeff Z. Pan^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Logs record system events and status, which help developers and system administrators diagnose run time errors, monitor running status and mine operation patterns [13, 23]. However, logs are complex and weakly linked, making it difficult to diagnose the causes of failures. While recent studies on log knowledge extraction focus on lifting entities from log messages for enriching a background knowledge graph (BKG), they do not involve knowledge reasoning for inferring implicit relations nor guarantee that the knowledge learned from log streams is consistent with the background knowledge. In this preliminary research paper, we present a log extraction approach to log knowledge graph (KG) construction. It includes a novel strategy that utilizes inference rules from a background knowledge graph to learn new triples and validate triples. Also, it implements a local to global strategy to perform reasoning on temporary log instance graphs (LIGs) then on the extended BKG, which significantly reduces query space. Finally we demonstrate the applicability of this approach by a use case in the context of root cause analysis.

Original language	English
Title of host publication	Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021
Editors	Oscar Corcho, Thepchai Supnithi, Xiaoyan Zhu, Aidan Hogan, Thanaruk Theeramunkong, Haofen Wang
Publisher	Association for Computing Machinery, Inc
Pages	181-185
Number of pages	5
ISBN (Electronic)	9781450395656
DOIs	https://doi.org/10.1145/3502223.3502250
Publication status	Published - 6 Dec 2021
Event	10th International Joint Conference on Knowledge Graphs, IJCKG 2021 - Virtual, Online, Thailand Duration: 6 Dec 2021 → 8 Dec 2021

Conference

Conference	10th International Joint Conference on Knowledge Graphs, IJCKG 2021
Country/Territory	Thailand
City	Virtual, Online
Period	6/12/21 → 8/12/21

Keywords / Materials (for Non-textual outputs)

knowledge graph
log analysis
relation linking
root cause analysis

Access to Document

10.1145/3502223.3502250Licence: All Rights Reserved

https://dl.acm.org/doi/abs/10.1145/3502223.3502250Licence: All Rights Reserved

Cite this

Wang, F., Bundy, A., Li, X., Zhu, R., Nuamah, K., Xu, L., Mauceri, S., & Pan, J. Z. (2021). LEKG: A System for Constructing Knowledge Graphs from Log Extraction. In O. Corcho, T. Supnithi, X. Zhu, A. Hogan, T. Theeramunkong, & H. Wang (Eds.), Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021 (pp. 181-185). Association for Computing Machinery, Inc. https://doi.org/10.1145/3502223.3502250

Wang, Fangrong ; Bundy, Alan ; Li, Xue et al. / LEKG: A System for Constructing Knowledge Graphs from Log Extraction. Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021. editor / Oscar Corcho ; Thepchai Supnithi ; Xiaoyan Zhu ; Aidan Hogan ; Thanaruk Theeramunkong ; Haofen Wang. Association for Computing Machinery, Inc, 2021. pp. 181-185

@inproceedings{d14d86c09ead471b8e2deea04333d816,

title = "LEKG: A System for Constructing Knowledge Graphs from Log Extraction",

abstract = "Logs record system events and status, which help developers and system administrators diagnose run time errors, monitor running status and mine operation patterns [13, 23]. However, logs are complex and weakly linked, making it difficult to diagnose the causes of failures. While recent studies on log knowledge extraction focus on lifting entities from log messages for enriching a background knowledge graph (BKG), they do not involve knowledge reasoning for inferring implicit relations nor guarantee that the knowledge learned from log streams is consistent with the background knowledge. In this preliminary research paper, we present a log extraction approach to log knowledge graph (KG) construction. It includes a novel strategy that utilizes inference rules from a background knowledge graph to learn new triples and validate triples. Also, it implements a local to global strategy to perform reasoning on temporary log instance graphs (LIGs) then on the extended BKG, which significantly reduces query space. Finally we demonstrate the applicability of this approach by a use case in the context of root cause analysis.",

keywords = "knowledge graph, log analysis, relation linking, root cause analysis",

author = "Fangrong Wang and Alan Bundy and Xue Li and Ruiqi Zhu and Kwabena Nuamah and Lei Xu and Stefano Mauceri and Pan, {Jeff Z.}",

note = "Funding Information: The authors would like to thank Huawei for supporting the research on which this paper was based under grant CIENG4721/LSC. Publisher Copyright: {\textcopyright} 2021 ACM.; 10th International Joint Conference on Knowledge Graphs, IJCKG 2021 ; Conference date: 06-12-2021 Through 08-12-2021",

year = "2021",

month = dec,

day = "6",

doi = "10.1145/3502223.3502250",

language = "English",

pages = "181--185",

editor = "Oscar Corcho and Thepchai Supnithi and Xiaoyan Zhu and Aidan Hogan and Thanaruk Theeramunkong and Haofen Wang",

booktitle = "Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021",

publisher = "Association for Computing Machinery, Inc",

}

Wang, F, Bundy, A , Li, X, Zhu, R, Nuamah, K, Xu, L, Mauceri, S & Pan, JZ 2021, LEKG: A System for Constructing Knowledge Graphs from Log Extraction. in O Corcho, T Supnithi, X Zhu, A Hogan, T Theeramunkong & H Wang (eds), Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021. Association for Computing Machinery, Inc, pp. 181-185, 10th International Joint Conference on Knowledge Graphs, IJCKG 2021, Virtual, Online, Thailand, 6/12/21. https://doi.org/10.1145/3502223.3502250

LEKG: A System for Constructing Knowledge Graphs from Log Extraction. / Wang, Fangrong; Bundy, Alan ; Li, Xue et al.
Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021. ed. / Oscar Corcho; Thepchai Supnithi; Xiaoyan Zhu; Aidan Hogan; Thanaruk Theeramunkong; Haofen Wang. Association for Computing Machinery, Inc, 2021. p. 181-185.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - LEKG: A System for Constructing Knowledge Graphs from Log Extraction

AU - Wang, Fangrong

AU - Bundy, Alan

AU - Li, Xue

AU - Zhu, Ruiqi

AU - Nuamah, Kwabena

AU - Xu, Lei

AU - Mauceri, Stefano

AU - Pan, Jeff Z.

PY - 2021/12/6

Y1 - 2021/12/6

N2 - Logs record system events and status, which help developers and system administrators diagnose run time errors, monitor running status and mine operation patterns [13, 23]. However, logs are complex and weakly linked, making it difficult to diagnose the causes of failures. While recent studies on log knowledge extraction focus on lifting entities from log messages for enriching a background knowledge graph (BKG), they do not involve knowledge reasoning for inferring implicit relations nor guarantee that the knowledge learned from log streams is consistent with the background knowledge. In this preliminary research paper, we present a log extraction approach to log knowledge graph (KG) construction. It includes a novel strategy that utilizes inference rules from a background knowledge graph to learn new triples and validate triples. Also, it implements a local to global strategy to perform reasoning on temporary log instance graphs (LIGs) then on the extended BKG, which significantly reduces query space. Finally we demonstrate the applicability of this approach by a use case in the context of root cause analysis.

AB - Logs record system events and status, which help developers and system administrators diagnose run time errors, monitor running status and mine operation patterns [13, 23]. However, logs are complex and weakly linked, making it difficult to diagnose the causes of failures. While recent studies on log knowledge extraction focus on lifting entities from log messages for enriching a background knowledge graph (BKG), they do not involve knowledge reasoning for inferring implicit relations nor guarantee that the knowledge learned from log streams is consistent with the background knowledge. In this preliminary research paper, we present a log extraction approach to log knowledge graph (KG) construction. It includes a novel strategy that utilizes inference rules from a background knowledge graph to learn new triples and validate triples. Also, it implements a local to global strategy to perform reasoning on temporary log instance graphs (LIGs) then on the extended BKG, which significantly reduces query space. Finally we demonstrate the applicability of this approach by a use case in the context of root cause analysis.

KW - knowledge graph

KW - log analysis

KW - relation linking

KW - root cause analysis

UR - http://www.scopus.com/inward/record.url?scp=85124009389&partnerID=8YFLogxK

U2 - 10.1145/3502223.3502250

DO - 10.1145/3502223.3502250

M3 - Conference contribution

AN - SCOPUS:85124009389

SP - 181

EP - 185

BT - Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021

A2 - Corcho, Oscar

A2 - Supnithi, Thepchai

A2 - Zhu, Xiaoyan

A2 - Hogan, Aidan

A2 - Theeramunkong, Thanaruk

A2 - Wang, Haofen

PB - Association for Computing Machinery, Inc

T2 - 10th International Joint Conference on Knowledge Graphs, IJCKG 2021

Y2 - 6 December 2021 through 8 December 2021

ER -

Wang F, Bundy A , Li X, Zhu R, Nuamah K, Xu L et al. LEKG: A System for Constructing Knowledge Graphs from Log Extraction. In Corcho O, Supnithi T, Zhu X, Hogan A, Theeramunkong T, Wang H, editors, Proceedings of the 10th International Joint Conference on Knowledge Graphs, IJCKG 2021. Association for Computing Machinery, Inc. 2021. p. 181-185 doi: 10.1145/3502223.3502250

LEKG: A System for Constructing Knowledge Graphs from Log Extraction

Abstract / Description of output

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Multi-source Knowledge Reasoning for Completeness and Continuous Enrichment Project

Cite this

LEKG: A System for Constructing Knowledge Graphs from Log Extraction

Abstract / Description of output

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Projects

Multi-source Knowledge Reasoning for Completeness and Continuous Enrichment Project

Cite this