Extract fields using proposed Copilot fields
Use the procedure in this topic to add fields to your solution that are proposed by the Copilot engine.
This is useful if a document has many pieces of information that you want to extract. This saves you time and effort by adding each field manually. If however, there are only a few fields that you want to extract, consider manually adding Copilot fields.
Before adding proposed fields using Copilot Auto Extract, verify the following steps are complete.
-
Add at least one configurable document type
-
Enable field extraction
-
If the field extraction screen is not already displayed, select
Fields
.
The first document type in your solution is displayed in two parts. The document types and their fields appear on the left and the document image for the currently selected document is on the right.
-
Optional. Select
Hide suggested fields.
This option is useful if the list of suggested fields interferes with readability.
You can select Show suggested fields at any time to view or add suggested fields.
-
Select
Add Copilot Auto Extract fields.
The Add Copilot Auto Extract fields window is displayed.
You can move or resize this window so you can better view the document image.
-
In the
Add Copilot Auto Extract fields window select the drop-down list arrow to the right of
Propose Copilot fields.
The Select page range setting is displayed.
-
Select a value for the
Select page range setting.
Choose from:
- Current page:
-
When the current training document is sent to the Copilot engine, only the current page is searched for proposed fields.
- Custom range:
-
When selected, enter the page range from the current training document that is sent to the Copilot engine to search for proposed fields.
By default, the range is set to 1 to 10 pages. If a document has fewer than 10 pages, the maximum page range matches the document page count. If a document has more than 10 pages, only the first ten pages are sent to the Copilot engine.
When you have selected the page range, select Apply.
-
The selected training document is sent to the Copilot engine to search for proposed fields. This can take a few
moments.
A list of fields is displayed, including a Name, Description, Type, and whether or not the field is located In table.
- For each field that you want to include in the extraction results, ensure is selected. Clear this check box if you want to exclude a field from the extraction results.
-
Select
Save.
Your new Copilot Auto Extract fields are added to the Fields tab for the selected document type. When a value is found, it is highlighted on the document, and the training circle indicates the field confidence. If the training circle icon is orange, add this field to additional documents.
The highlight might not match the actual content if the information is inferred.
- Repeat steps 3 to 8 to add proposed Copilot Auto Extract fields to other document types in your solution.
-
Optional. Add suggested fields or lasso fields.
-
Optional. Edit field properties for your extraction fields.
-
Configure your import channels.