The problem for many organisations, however, is that the data they receive is often semi-structured or unstructured, creating a real stumbling block for traditional DPA solutions. For example, when DPA software receives a document that does not conform to the pre-programmed rules, an exception is created. The software will then either need to be recoded to handle the new document template, or it will be passed to a human operator to manually process. At high volumes, this method of handling document exceptions becomes unmanageable and is costly both in resource and time to the organisation.
By applying IPA solutions to document processing, intelligent technologies such as Machine Learning, Natural Language Processing and Cognitive Automation are introduced, and exceptions can be handled within the end-to-end digital process. IPA platforms, such as Celaton’s inSTREAM™, apply Machine Learning algorithms, which have the ability to learn through the natural consequence of processing through the collaboration with operators who teach it about document exceptions in a process called ‘Human in the Loop’. This removes the need for recoding with every new document type received.
The main advantages of applying ‘Human in the Loop’ are: