We are currently implementing Customer Service for Insurance and want to leverage the Pega Platform Email Triage capabilities to perform STP (straight through processing). Is it possible to integrate an interaction with the email triage case to allow use of text analysis, entity extraction, case suggestion and email conversation. We would like these types of cases to show up as interactions within our customer service portal.
Hi, what version of CS are you building this on ? STP support was added in CS 7.4. Before we get to the how, I would like to understand the STP use case. STP does not allow for any oversight of the case when it runs. It runs to completion based on the entities determined by the NLP, which tends to fail often.
Posted: 5 years ago
Posted: 14 Nov 2018 12:21 EST
Jarrod Bezzina (Jarrod)
Thanks for responding. We are using Customer Service 7.31 on Pega Platform 7.3.1.
Email triage will be used in a number of different methods, mostly using Robotics to extract PDF contents or NLP to extract entities on structured emails (i.e. emails that resemble forms with entities listed down a page). The reason for using NLP in that case is we could have numerous number of emails with entities in different order. I believe NLP is more reliable in these cases, do you agree?
One of our use cases in this respect is receiving an email with a number of entities which describes an insurance policy mutation. The email has no other content other that policy number, type of mutation and some other required attributes. The email is generated by an intermediator's website after a client requests a change of policy from their portal. We would like to extract these attributes and call an external systems API to update the policy then respond back to the client submitting the policy change to the portal when successful.
We would also like a interaction created to give CSR's visibility of the email if the client may call the insurance company with any inquiry.