Extracting Information from Word and PDF Documents

The Challenge

Most organisations have vital knowledge trapped in scanned documents. Extracting this information is expensive and time consuming

Many organisations have vast amounts of their knowledge trapped in scanned documents.

This may be entity information – names, business numbers, contract values, dates, $ amounts, etc.

Or it may be financial information sitting in columns in a report or P&L statement.

Extracting and applying information from these documents is extremely difficult:

  • Scanned documents are images and cannot be edited using text editing tools

     

  • Traditional OCR technology only delivers the content into textual format, with high error rates

     

  • Mapping of relationships between entities is a costly manual exercise

The Solution

1WordFlow Reveal

1WordFlow Reveal is:

An end to end service

Digitisation, extraction, standardised presentation (in web format) and reporting in a single solution

Simple to Use

Designed for the non-technical user. Reveal combines OCR with modern web tools for presentation and analysis

Cloud Based

Customers require no infrastructure. Users simply upload documents using a friendly web interface and Reveal transforms and extracts the information to a secure website

Scalable for Large Volumes of Content

Reveal works at scale, aggregating all documents into a single web location.

Case Study

Identifying Trust Deed Beneficiaries for AML Compliance

A major bank was faced with the challenge of identifying all overseas domiciled trust beneficiaries in order to ensure compliance with Anti Money Laundering (AML) legislation.

In addition to identifying the domicile, they needed to establish where the beneficiaries had related entities.

The bank held several thousand trust deed documents in scanned PDF format. The time frame for compliance was too short to allow this process to be completed manually.

The bank needed an automated solution that would extract the required information quickly and accurately.

How 1WordFlow Helped

  • Transformed the scanned trust deeds into digital websites
  • Extracted beneficiary and related information
  • Extracted beneficiary and related information
  • Enabled the Bank to meet regulatory deadlines

The Bank now has a repeatable, scalable process for ensuring ongoing compliance.

Find out how 1WordFlow can extract your vital information from scanned documents 

You can`t add more product in compare