Towards Intelligent Process Support for Customer Service Desks: Extracting Problem Descriptions from Noisy and Multi-lingual Texts
Customer service is a differentiating capability for companies, but it faces significant challenges due to the growing individualization and connectivity of products, the increasing complexity of knowledge that service employees need to deal with, and steady cost pressure. Artificial intelligence (AI) can support service processes in a variety of ways, however, many projects simply propose replacing employees with chat bots. In contrast to pure automation focusing on customer self-service, we introduce three intelligent assistants that support service employees in their complex tasks: the scribe, the skill manager, and the background knowledge worker.
In this paper, we discuss the technology and architecture underlying the skill manager in more detail. We present the results from an evaluation of commercial cognitive services from IBM and Microsoft on comprehensive real-world data that comprises over 80,000 tickets from a major IT service provider, where problem reports often comprise an email-based conversation in multiple languages. We demonstrate how today’s commercially available cognitive services struggle to correctly analyze this data unless they use background ontological knowledge. We further discuss a pattern- and machine-learning based approach that we developed to extract problem descriptions from multi-lingual ticket texts, which is key to the successful application of AI-based services.
- 1.Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)
- 2.Caruana, R., Karampatziakis, N., Yessenalina, A.: An empirical evaluation of supervised learning in high dimensions. In: 25th International Conference on Machine Learning, pp. 96–103. ACM (2008)Google Scholar
- 4.de Carvalho, V.R., Cohen, W.W.: Learning to extract signature and reply lines from email. In: 1st Conference on Email and Anti-Spam (CEAS) (2004)Google Scholar
- 6.Dredze, M., et al.: Intelligent email: aiding users with AI. In: 23rd AAAI Conference, pp. 1524–1527. AAAI Press (2008)Google Scholar
- 8.Goel, A., et al.: Using Watson for constructing cognitive assistants. Adv. Cognit. Syst. 4, 1–16 (2016)Google Scholar
- 9.Gownder, J.P.: The future of jobs, 2025: working side by side with robots. Research report, Forrester (2015)Google Scholar
- 12.IBM: Natural language understanding cognitive service (2017). IBM Bluemix, https://console.ng.bluemix.net/catalog/services/natural-language-understanding
- 13.Lampert, A., Dale, R., Paris, C.: Segmenting email message text into zones. In: Conference on Empirical Methods in Natural Language Processing, pp. 919–928. Association for Computational Linguistics (2009)Google Scholar
- 15.Microsoft: Text analytics cognitive service (2017). https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/
- 16.Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. arXiv preprint arXiv:1610.08401 (2016)
- 17.Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015)Google Scholar
- 19.Wipro: Wipro to transform customer service desk at Nexenta using its artificial intelligence (AI) platform HOLMES (2016). http://www.wipro.com/newsroom/press-releases/Wipro-to-transform-customer-service-desk-at-Nexenta-using-its-artificial-intelligence-platform-HOLMES/. 15 Dec 2016