Workflow

The common workflow of using Textweiser for document classification is:

• create a database
• add categories
  The categories are added as suitable for each case and can be structured flat or mono-hierarchical (taxonomies).
• train categories
  The document classification can start as soon as the classifier has been trained once. Training may be done with a rather small amount of documents.
• classify documents

In the beginning you usually add a set of categories and train each category. However, it is possible to change the structure during operation. Textweiser allows to add new categories or rename and delete existing ones.

Besides that, some administrative tasks are recommended to be executed periodically. The data can be optimized, which increases accuracy and performance of the document classification.

Additionally there are functions to backup and restore the data. A migration from a Textweiser backup to a different database or operating system is possible.