Gaining Insight from Operational Data for Automated Responses
Facilitating autonomic behavior is largely achieved by automating routine maintenance procedures, including problem detection, determination and resolution. System monitoring provides effective means for problem detection. Coupled with automated ticket creation, it ensures that a degradation of the vital signs, defined by acceptable thresholds or known patterns, is flagged as a problem candidate. It is a known practice to define thresholds or conditions that are conservative in nature, thus erring on the side of caution. This practice leads to a large number of tickets that require no action (false positives). Elimination of false positive alerts is imperative for effective delivery of IT Services. It is also critical for the subsequent problem determination and resolution. All operational data, including events and problem records, will be used for automated resolution recommendation.
Automating resolution of complex events is exciting but unknown territory for Service provides. We are grateful to the technical teams and executive leadership of IBM technical services for their trust and on-going support to our road to AI driven automation.
Also this work was done in collaboration with Florida International University and St. Johns University, and we thank our collaborators: prof. Dr. Tao Li (deceased), prof. Dr. G. Ya. Grabarnik, Dr. Liang Tang, Dr. C. Zeng, Dr. Wubai Zhou, and Qing Wang.
- 2.Bird S (2006) NLTK: the natural language toolkit. In: Proceedings of the COLING/ACL on Interactive presentation sessions. Association for Computational Linguistics, pp 69–72Google Scholar
- 3.Srikant R, Agrawal R (1996) Mining quantitative association rules in large relational tables. In: Proceedings of ACM SIGMOD, pp 1–12Google Scholar
- 4.Yin X, Han J (2003) CPAR: classification based on predictive association rules. In: Proceedings of SDMGoogle Scholar
- 7.Chang S, Zhou J, Chubak P, Hu J, Huang TS (2015) A space alignment method for cold-start tv show recommendations. In: Proceedings of the 24th International Conference on Artificial Intelligence, pp 3373–3379Google Scholar
- 8.Li L, Chu W, Langford J, Schapire RE (2010) A contextual-bandit approach to personalized news article recommendation. In: WWW. ACM, pp 661–670Google Scholar
- 9.Schein AI, Popescul A, Ungar LH, Pennock DM (2002) Methods and metrics for cold-start recommendations. In: SIGIR. ACM, pp 253–260Google Scholar
- 10.Petrov S, Das D, McDonald R (2011) A universal part-of-speech tagset. arXiv preprint arXiv:1104.2086.Google Scholar
- 11.Potharaju R, Jain N, Nita-Rotaru C (2013) Juggling the Jigsaw: towards automated problem inference from network trouble tickets. In: NSDI, pp 127–141Google Scholar
- 12.Zeng C, Wang Q, Mokhtari S, Li T (2016) Online context-aware recommendation with time varying multi- armed bandit. In: SIGKDD, pp 2025–2034Google Scholar
- 14.Castillo LA, Mahaffey PD, Bascle JP (2008) Apparatus and method for monitoring objects in a network and automatically validating events relating to the objects. U.S. Patent, US 7,469,287 B1.Google Scholar