The Classify Document
action groups the input documents based on the first page of
each document, using the selected model file that is created with the Train
Advanced Classifier
action.
Prerequisites
- If not done already, use the Train Advanced Classifier action
to create a model file.
- Ensure the input files are in required format.
Build a bot with the Classify Document action within a
Loop action to iteratively classify each file in the selected
folder.
Procedure
-
In the Actions palette, double-click or drag
the Classify Document action from the Advanced
Classifier package.
-
In the Input file field,
provide the default filepath for incoming files for classification:
- Control Room file
- Desktop file
- Variable
-
In the Classifier field, provide the
filepath of the model file. You can either select the .zip
folder or extract the .clsproj3 file from this folder and select
it.
- Control Room file
- Desktop file
- Variable
-
Use the Output folder path
option to save the classification output documents. The pages from the output
document are saved in the respective subfolders based on the categories created in
the model file.
-
In the License field,
provide a license credential.
-
If you select Credential
option, click Pick to get a license from the
license locker.
-
Optional: Configure the Confidence threshold
(%). If the confidence value of the category prediction of a document is less than
the confidence threshold, the document is moved to the
Unclassified folder.
-
Select or create a list variable to hold the output. The
classification results as a list with the following keys:
- fileName: Name of file that you want to process
- category: The category to which the file belongs to
after classification. For example, all HR related documents will be placed in
one category.
- confidence: The threshold percentage value that shows
classification such as, which file belongs to which category based on training
data.