Enhanced Maintenance Services with Automatic Structuring of IT Problem Ticket Data

We propose a novel technique to enhance the IT problem isolation and resolution Maintenance Services by automatically structuring problem tickets consisting of free form, heterogeneous textual data. The originality of our technique consists in applying the Conditional Random Fields (CRFs) supervised learning process to automatically identify individual units of information in the raw data. We apply our technique to identify structural patterns specific to the problem ticket data used in Call Centers since this data is not explicitly structured, is highly noisy, and very heterogeneous in content, making it hard to analyze and search by the remote technical support personnel. We present a study of the accuracy of our experiments.