Advances in both computing and algorithms have allowed for machines to and humans to understand and engage with eachother with less friction given the advent of Natural Language Processing and Understanding Technology. For ITSM, a few use cases immediately come to mind:

  • Customer Service Chatbot: We deal with a number of customer issues regarding our SaaS offering, and offer a 24×7 phone as well as online self service channels for issue submission. A chatbot would facilitate deflection of issues and offer a cheaper issue creation channel than phone.
  • Sentiment detection: As issues come in from many channels such as portals, emails, and chat, paying attention to user sentiment is key to quickly escalating and resolving the most urgent customer issues first.
  • Technical/Support Documentation: Technical documentation is written for all new features and functions developed in a software release of our SaaS platform. NLG can assist in taking the structured app data and auto generate a baseline set of documentation.
  • Customer Call Summarization: Sales and support personnel are frequently on the phone with customers, and must manually enter a summary of the conversation into the appropriate lead or incident record in our system. A speech to text and auto summarization would automate this process and help surface topic trends during conversations.
  • Issue Summarization: When incidents are resolved after dialogue between a technician and the customer, the resolution details are captured to generate knowledge that a future technician could leverage. Auto summarizing the resolution details would facilitate the process.

NLP is much closer tied to understanding a user, and facilitating the generation or transfer of knowledge. Since most activities surrounding NLP can be directly accomplished by a human, although at a slower rate, the primary strategies NLP will affect are cost leadership and differentiation.

Cost leadership is clear as operational expenses are minimalized in a support context as chatbot replace tier 1 labor and allow existing labor to focus on higher complexity, higher value add opportunities. In addition, they are available 24×7, and can potentially support multiple languages offering native scalability. These savings in labor to due automation go beyond support – and have implications for sales representatives and documentation writers as well. For sales, it is a tool to increase productivity by documenting calls. On the other hand for documentation writers, it helps generate an output that they are directly responsible for.

The auto generation of summarized text based on voice conversations held by support and sales staff over the phone or in a incident (case ticket) will significantly proliferate the amount of information available to analyze, and to re-use in future interactions. This, alongside automated sentiment analysis help offer a differentiation point of more effective customer service.

The technology will have the ability to transform the way we engage, and consume data and information with IT. When it comes to virtual agents and chatbots, understanding use cases is the first exercise to understanding what issues the technology can help deflect. To help you understand this, Pericror has developed a topic analysis tool that can help you identify top issues in a ServiceNow instance.