go to top
Obsidian Business Service Intelligence

Automatic interpretation of service management indicators

Presentation at GigaTIC2017 on artificial intelligence techniques for the automatic interpretation of service management indicators

Presentation at GigaTIC2017, an event organized by iTSMF and ISACA, of research on the automatic interpretation of service management indicators implemented in Obsidian. Carried out by Alberto Bugarín, professor of artificial intelligence, and the director of Obsidian, Diego Berea.

The video currently has 37075 views on YouTube and 358 likes.

If you are interested in receiving information of new videos posted by Obsidian, subscribe to the channel and YouTube will periodically send you notifications when new videos are posted. The Obsidian YouTube channel currently has 1902 subscribers. 

Data2text implementation on Obsidian

Several disciplines of artificial intelligence, are related to natural language processing (NLP). Of these, one subset concerns techniques for the automatic generation of natural language (NLG).

Intense research has been going on for several years in this area. As a result, different researchers have developed and deployed different software, which has been tested in real environments, with satisfactory results.

Particularly relevant is that considering predictions for 2018; NLG is going to be present on a large percentage of BI market tools.

In this scenario, the management of ITSM services offers a very rich context for the application of NLG techniques. It has multiple actors (technicians, managers, directors), each with different information needs. These may be technical specifications, service performance values or simply knowing whether the service level agreed with the customer has been accomplished or not. Such information can be extracted from the corporate tools of service desk and monitoring. NLG techniques attempt to help the user by processing data and displaying a written interpretation of these data according to the user’s role.

Initially, this presentation shows the most common methodologies for the implementation of an NLG system of a data2text type. At the end, multiple examples of practical applications to the automatic interpretation of service management indicators are shown. The examples are based on the data2text implementation performed in Obsidian. This implementation includes both service desk metrics and availability, capacity or service level indicators, which are already working in real environments. With data2text implementation, it is now possible to generate automatic written reports using data obtained from these tools. This is one of the main advantages of these types of systems: reducing the analytical effort which the user must make.

More information on the data2text functionalities of Obsidian.