CURRENT STATE
So much for the paperless office. Paper is everywhere, and handling paper as part of any business process adds cost, increases error rates, and can dramatically reduce process velocity and efficiency.
And it’s not just paper. Although much of the physical paper received by organisations has been replaced by email and their attachments (Word documents, pdf’s, scanned images, spreadsheets etc.), the problem hasn’t gone away. The data is still trapped. Your staff must still manually process the documents – determining what they are and re-keying data from them into your own systems. Ironically, many email attachments are printed when they are received to make them easier for staff to process.
Typical examples are invoices, purchase orders, remittance advices, and all of the documents associated with any type of loan or customer onboarding process.
Wouldn’t life be better if a system could automatically digitize all inbound documents, irrespective of channel (paper, email, fax etc.), classify them by document type, extract any or all data from them, send that data to the appropriate backend system, and then export the digitized and indexed documents to a document repository for easy retrieval?
The good news is that this is very much a reality, and it can be implemented rapidly, with little if any change to existing systems.
FUTURE STATE
Advanced document capture platforms, such as Ephesoft Transact, make automatic document processing a reality.
There are multiple ways to capture data: including scanners, multi-function peripherals (MFPs), network folders, fax, email, content services or document repositories, and mobile devices.
Ingestion
Documents and images are normalized, cleaned up and rotated in preparation for classification. The system applies despeckle and deskew filters to improve image quality. The resulting document can then be identified and the data can be easily extracted.
Image Processing
Classification
This is where the system determines what type of document it ingested through Optical Character Recognition (OCR), Intelligent Character Recognition (ICR) and/or Optical Mark Recognition (OMR). This step will determine if a document is, for example, an invoice, purchase order, remittance advice or any of a large number of documents related to any process. An advanced document capture system only needs one or two samples so it can “learn” to classify the documents; Ephesoft accomplishes this via patented machine learning algorithms. The system uses a variety of techniques to classify the data: search content, images, bar codes and one document merging. If the system has low confidence in any document it attempts to classify, the process can call upon a human operator for confirmation.
Validation
If there are any documents that fall below pre-set tolerance levels, they are highlighted for human review. For example, this can happen when there are smudges, spills, blurry characters or possibly missing fields. The system alerts you to these documents for manual verification and correction.
Export and Deliver
Once all documents have been validated, the documents and data are moved to a repository or other line of business system. The exported documents and data can be stored on a local server or cloud based storage.
Extraction
This is the process of extracting data from the documents. Any data can be extracted, including data from within complex tables. The system is configured to extract the data using a variety of techniques. Extraction accuracy can be increased further by applying data validation rules and using database lookups and/or business rules.
BUSINESS BENEFITS
Thousands of organisations have successfully implemented an advanced document capture solution - because the business value and the business case are so compelling.
-
Substantial cost reductions as manual activities are automated
-
Imroved process efficiency and effectiveness
-
Reduced error rates
-
Faster processing times
-
Enhanced customer satisfaction - as processing times are reduced and customers can engage using their channel of choice (increasingly, documents are captured via the mobile channel
We implement advanced document capture solutions using Ephesoft Transact. We configure Transact to automate the capture and digitisation of documents received across all inbound channels, automatically classify each document, and extract data as needed. The extracted data populates any system, with little or no manual intervention. Clients achieve huge process efficiency and effectiveness benefits and the solution typically has a very rapid ROI.
