Document Indexing to facilitate Intelligent Search

Document Indexing to facilitate Intelligent Search

Use Case Description

Problem Statement:
There are several commercial or government agencies out there with volumes of paper record that they keep for years for record keeping and for historical purposes to search & compare data. The biggest challenge is finding the required information in a timely manner. Even if these agencies could digitize all their paper records, locating crucial information is still a huge challenge.
Locating key information can be only done through proper indexing. Benefits of proper Indexing approach is not just limited to quick retrieval of the document but also:
1- Improved organization of the digital files.
2- Improved efficiency since the information is now available in a timely manner.
3- Saves time & money

Solution:
To overcome this challenge, RPA \ Document Understanding with OCR is the best fit solution.
• Once the scanned document is available to the UiPath bot, it gets loaded in the processing loop.
• The bot will scan the available file using Document Understanding to identify the pre-defined key words.
• The list of key words needs to be defined to be used for indexing parameters.
• Once the keywords are extracted, update the same index parameters to the Content Management System.
• Now the CMS has the document & relative key words to setup the indexing.

The above approach works perfectly if all the documents scanned have a standard template, in other cases, it may be better to first define what could be the best keywords to use for the business. In that case we can go for either “Full text indexing” or “Metadata indexing” approach.

Next Steps:
This use case is relevant to the data heavy organizations lie Land registry, wildlife historical data, driver licensing etc. Even though there are few commercial tools out there, UiPath RPA is still the most efficient approach for OCR & indexing.

AS-IS WORKFLOW, TO-BE WORKFLOW

Other information about the use case

Industry categories for this use case: Compliance, Customer Service, Universities Academy

Skill level required: Intermediate

UiPath Products that were used: UiPath Studio, UiPath Action Center, UiPath Document Understanding, UiPath Orchestrator

Other applications that were used: Content Management Systems

Other resources: Challenges - The British Library

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