As a user and provider of document management over the last decade, nothing has intrigued me more than indexing – the process of tagging a document (or content) so that it can be retrieved quickly at a later date. From its early days, virtually everyone bought into the idea of a paperless office and scanning documents. However, when you then had to tackle indexing a document, it seemed like progress came to a halt. It didn’t matter that we had to write on manila folders, get those labels to stick on the documents, and then file them in a filing cabinet – manual paper processing somehow seemed easier than indexing. When we started scanning, we expected more from technology. We expected it to simply intelligently index our documents.
Through the years, document management vendors have made some significant strides in automating indexing for the small- to medium-sized business (SMB). The large corporations had the deep pockets and budgets to invest in sophisticated capture technologies that somehow magically took scanned documents and organized them where they needed to go. Those technologies worked well, but were out of reach for the majority of businesses who were then stuck doing indexing the old fashioned way or deciding not to scan at all.
When OCR was introduced, it had a profound impact on document management for the SMB. It immediately allowed the system to index every word in the document so that it could be found through a Boolean search. Documents still had to be indexed in most cases but it allowed for broader search capabilities. Document management vendors took it a step further by introducing zone OCR. An offshoot of the original OCR concept, zone OCR streamlined the indexing process further by quickly indexing standardized forms. Zone OCR initially required extensive IT support to setup the indexing templates and also required ongoing maintenance for new forms and as old forms changed. The process is clumsier than advertised and relies on clean scanned images with clear zones. While Zone OCR improved the indexing process, it still left much to be desired, including the ability to manage multiple, sometimes hundreds, of templates.
The launch of DocuWare 6 revolutionized indexing for the SMB through its new Intelligent Indexing Service. It uses simple point and click technology to build templates and learns independently when each document is stored, using this knowledge to automate future indexing. This cloud based technology is also crowd learning – it learns not only from your documents but also from anyone else using the service. If an invoice or form template already exists for the document you scanned, it intelligently applies the correct indexing template. This process of indexing and learning relieves a heavy burden from IT departments and key users.
Intelligent Indexing is a significant leap in indexing technology and allows the SMB to fully realize the potential of document management in their business. The automated indexing tool that was out of reach for many is now available for the majority of businesses. It comes just in time as content is transitioning from paper to digital and yet is more numerous than ever and has to managed effectively.