Hi, How Can I Help You?: Automating Enterprise IT Support Help Desks

Authors

  • Senthil Mani IBM Research AI
  • Neelamadhav Gantayat IBM Research AI
  • Rahul Aralikatte IBM Research AI
  • Monika Gupta IBM Research AI
  • Sampath Dechu IBM Research AI
  • Anush Sankaran IBM Research AI
  • Shreya Khare IBM Research AI
  • Barry Mitchell IBM Global Business Services
  • Hemamalini Subramanian IBM Global Business Services
  • Hema Venkatarangan IBM Global Business Services

DOI:

https://doi.org/10.1609/aaai.v32i1.11386

Keywords:

Question Answering, Cognitive Ensemble, IT support, Machine Learning

Abstract

Question answering is one of the primary challenges of natural language understanding. In realizing such a system, providing complex long answers to questions is a challenging task as opposed to factoid answering as the former needs context disambiguation. The different methods explored in the literature can be broadly classified into three categories namely: 1) classification based, 2) knowledge graph based and 3) retrieval based. Individually, none of them address the need of an enterprise wide assistance system for an IT support and maintenance domain. In this domain, the variance of answers is large ranging from factoid to structured operating procedures; the knowledge is present across heterogeneous data sources like application specific documentation, ticket management systems and any single technique for a general purpose assistance is unable to scale for such a landscape. To address this, we have built a cognitive platform with capabilities adopted for this domain. Further, we have built a general purpose question answering system leveraging the platform that can be instantiated for multiple products, technologies in the support domain. The system uses a novel hybrid answering model that orchestrates across a deep learning classifier, a knowledge graph based context disambiguation module and a sophisticated bag-of-words search system. This orchestration performs context switching for a provided question and also does a smooth hand-off of the question to a human expert if none of the automated techniques can provide a confident answer. This system has been deployed across 675 internal enterprise IT support and maintenance projects.

Downloads

Published

2018-04-27

How to Cite

Mani, S., Gantayat, N., Aralikatte, R., Gupta, M., Dechu, S., Sankaran, A., Khare, S., Mitchell, B., Subramanian, H., & Venkatarangan, H. (2018). Hi, How Can I Help You?: Automating Enterprise IT Support Help Desks. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11386