Each queue defines the structure of data fields that Rossum extracts. When editing this structure you have two options:
- Use pre-trained data fields – Rossum’s generic AI engine has been pre-trained to recognize specific data fields and enables you to start extracting data without any additional training for the AI.
- Define custom fields and train the dedicated AI engine to automatically extract them.
How to customize data extraction with pre-trained data fields
Using pre-trained data fields is simple. This function works out of the box and is easy to set up.
After you login to Rossum, go to the Settings screen by clicking the gear icon in the upper left corner.
- Click “Queues” in the sidebar, then select the queue you want to configure.
- This opens a queue settings screen where you can open the “Fields to capture” tab.
- In this tab, you can select and deselect fields according to their relevance to the documents you are processing.
- When you are done, click “Save” to store your settings.
Now, the updated data fields should be visible in the validation screen.
Customizing data extraction with custom fields
If you want to define custom data fields, you need to edit the extraction schema.
Note: Only Enterprise Edition users can train Rossum’s dedicated AI engine to automatically extract custom data fields. If you want to access the Enterprise Edition, please contact our automation experts.