Improving IT Support by Enhancing Incident Management Process with Multi-modal Analysis

Abstract

3 IT support services industry is going through a major transformation with AI becoming commonplace. There has been a lot of effort in the direction of automation at every human touchpoint in the IT support processes. Incident management is one such process which has been a beacon process for AI based automation. The vision is to automate the process from the time an incident/ticket arrives till it is resolved and closed. While text is the primary mode of communicating the incidents, there has been a growing trend of using alternate modalities like image to communicate the problem. A large fraction of IT support tickets today contain attached image data in the form of screenshots, log messages, invoices and so on. These attachments help in better explanation of the problem which aids in faster resolution. Anybody who aspires to provide AI based IT support, it is essential to build systems which can handle multi-modal content. In this paper we present how incident management in IT support domain can be made much more effective using multi-modal analysis. The information extracted from different modalities are correlated to enrich the information in the ticket and used for better ticket routing and resolution. We evaluate our system using about 25000 real tickets containing attachments from selected problem areas. Our results demonstrate significant improvements in both routing and resolution with the use of multi-modal ticket analysis compared to only text based analysis.

Machine Learning Supervised Analysis for Enhancing Incident Management Process

“…Its competitiveness in this area with suitable pre-processing compared with more advanced techniques such as support vector machines is remarkable. [3] In medical diagnosis automation, it is also highly applicable. [4] The formula is shown in Equation 3.…”

“…A process, therefore, of restricting the potential disruption initiated by such an occurrence, followed by a return to normal business operation, is Incident Management. Business functions, employees, IT systems [2], information security [3], clients [4], or several essential business operations can be disrupted by an incident without existing effective Incident management [5]. In a process enriched event log dataset for incident management, data is collected from the Service Now platform's event or instance audit system.…”

Improving Support Ticket Systems Using Machine Learning: A Literature Review

“…İşcen and Gürbüz [2] x Lo, Tiba [25] x x Mukunthan and Selvakumar [26] x Nayebi, Dicke [6] x x Mandal, Agarwal [11] x Misra and Podder [27] (x) x Palacios, Morillas [28] (x) x Shanmugalingam, Chandrasekara [29] x…”

“… Automate labeling of tickets, either for training or for easier ticket resolution by a support agent [34]  Chatbots [15,33,44]  Spam detection [3]  Performance optimization [24]  Automated analysis of pictures attached to a support ticket [11]  Business/process/text mining for better support system architecture [25,45]  AI explainability in support ticket automating [22]  Ticket resolution time prediction [10]  Automated STSs in context of Internet of Things (IoT) [28]  Using answering bot (Microsoft LUIS) for automated request responses [29] The findings and results in these topics were as diverse as the topics itself. Nevertheless, we were able to carve out some general findings:  As in nearly any research in the field of Machine Learning the accessibility and quality of training data importantly influences the outcome of the project [1,3,25]  The metrics precision and recall are by far the most-used metrics for evaluating ML ticket classification tools [5,6,18,36].…”

“…With Artificial Intelligence (AI) and Machine Learning (ML) algorithms becoming commonplace, the automating of STSs has become more interesting than ever before [11]. Technologies for automated ticket classification and automated ticket resolution using ML open the possibility of automating basic day-to-day IT tasks replacing the first level support staff members [4,8].…”