A cognitive system for business and technical support: A case study

摘要

Business and technical support has traditionally been labor based. In this paper, we introduce a cognitive system for business and technical support. This cognitive system is aimed at answering, for example, “how to” and “how do I fix” questions that represent more than half of support help-desk queries. The standard method to build cognitive systems involves collecting the user questions, collecting and curating the domain knowledge, creating ground truth for learning, training, and testing, and continuous learning from user interactions and feedback. However, the lack of actual user questions, quality, and coverage of available enterprise knowledge, ambiguity in user communication, and user expectations on coverage and accuracy pose a challenge in applying the standard method to the domain of technical support. We address this by extracting and modeling users’ support intents and questions from sources, such as help-desk tickets, discussion forums, and enterprise knowledge—extracting and using a domain knowledge graph to allow the cognitive system to have intent-disambiguating conversations with the user, and including a pool of human experts as a fall-back option to increase the effectiveness and acceptance of the solution (and as a source of learning). Users who participated in initial technology pilots found the system useful.