AI classification

This section describes the automatic detection of data in documents. Here you will find information about data categories and editing marked fields.

Document classification

After a document is added, the system automatically starts its classification.

The classifier uses data search and recognition algorithms developed by BTC as well as artificial intelligence-based mechanisms. It analyzes the document's content and structure, then marks the recognized elements directly on its pages.

After classification is complete, the user should review the detected fields. They can remove incorrect markings and change their position and size before proceeding to anonymization.

Classification supports finding data, but does not replace the user's final verification. Information about how the model works and document processing can be found in the section AI model security.

Tip: Classification time depends on the document size and the number of areas containing data that needs to be recognized. The analysis progress is visible on the loading bar. For documents containing up to about 1000 such fields, classification usually takes no longer than 30 seconds.