24-05-19 03:09 AM
Hello Everyone,
I am trying to solve a business problem where we currently receive 10-15K emails a month from our customers with work requests. The details of the work that needs to be completed is typically described in the body of the email and many times the data is unstructured (Please see attached)
Once the email is received, we have human workforce which then manually reads the email and looks for key words to determine the type of request then create a saleforce ticket for the support team to work on.
As you can see the process is very manual with intense volume and more than often we end up missing our sla's as sometimes it can take days before a human can get to the email and pass if along to the support team.
Has anyone tried to solve similar problem? If so, did you use any ocr technology? or just in-built blue prism functionality? Any guidance and assistance would be truly appreciated.
Thanks,
Rahul Surana
24-05-19 07:19 AM
24-05-19 02:46 PM
24-05-19 04:13 PM
This e-mail you've attached actually looks fairly structured. Are you saying that the other e-mails you receive aren't in this format?
It looks like you've got some fairly standard field names. You can use a multi-calc stage to figure out what each field is. For example, InStr() for "Dealership Name: ", then use a Mid() to go from the start of the value for that field up to the next InStr() position of a newline character. It's messy to code, but BP can run a single multi-calc stage to figure all of these out fairly quickly.
If, for example, the format changes based on the client, you could have e-mail rules to sort them into different inbox folders ahead of time. Otherwise, you can also use a choice stage with various InStr checks to see which client is being specified in the message.
Ultimately though, and this is the kicker, if you need to determine a type of request for each ticket based on free-form text fields, you'll have to either rely on key words or train/leverage an AI to figure it out. It looks like this would be in the "Description of the Request: " section.