Mail Room Automation with NLP Classification

Mail Room Automation with NLP Classification

Use Case Description

These are the high level steps for this automation:

-Login to the Mail Portal
-Search for and open eligible packets containing certain parameters.
-Define business logic to identify the eligible packets
-Reassign those eligible packets to a separate mail queue.
-Download the documents within the packets for further review
-Extract the data on the documents via Optical Character Recognition (OCR)
-Enter packet notes regarding the success or failure of a packet
-Submit the packet for upload to a Enterprise test environment
-Perform Natural Language Processing classification on extracted data and provide back to dashboard/business intelligence engine.

There are certain advanced concepts involved in this use case like data extraction, NLP classification etc. Feel free to comment \ ask questions. I would be happy to help answer any queries or have further discussion on the implementation.

AS-IS WORKFLOW, TO-BE WORKFLOW

Other information about the use case

Industry categories for this use case: Customer Service, Information Technology and Services, Operations

Skill level required: Advanced

UiPath Products that were used: UiPath Studio, UiPath Assistant, UiPath Document Understanding, UiPath Orchestrator

Other applications that were used: HyperScience NLP Engine \ AI Center, Tableau \ Kibana

Other resources: Mailroom Automation: Increase Mailroom Organization and Efficiency | Ephesoft
Mailroom Automation Software | Digital Mailroom Solutions

What is the top ROI driver for this use case?: Accelerate growth and operational efficiency

3 Likes

Hi Pradeep, this is an interesting use case… which classification model did you use… did you use a standard BERT model or this was a business specific one… would love to learn more.

Hi Deepak - it’s a clinical BERT model pretrained with clinical notes \ EHR for this specific use case. I can share a recorded demo if that could help you understand the solution.

1 Like

Thanks Pradeep… looking forward to it. :+1: :+1: