Classification

InputManagement uses Artificial Intelligence and Machine Learning to classify documents. Currently, two classifiers are supported: optical and textual.

To classify documents, make sure that the classes exist and are correctly configured.

Training

The classification needs to be trained. Training takes place in the context of a pipeline. Pipelines can be configured in the administration area. Each pipeline has several class definitions. A class definition is a reference to a class with a collection of sample documents. These samples can be uploaded directly into the class definition. The better the samples for each class, the better the subsequent classification will be.

A good training set has the following characteristics:

• no attachments (for example, from claims and account statements)
• only the first 1-5 pages of longer documents
• no extra-large documents
• no handwritten documents
• good scan quality (300 dpi)
• only PDFs
• 80 documents per class