DOM Machine Learning

[Ritaman_Baral]

1 . None , Screen,Scan,Legacy explanation

2. In the checkbox do I need to enter unique ID ?

o
3.

Use of template manager

[Anil_G (Anil Gorthi)]

@Ritaman_Baral

1. The following explains

Choose a preprocessing profile for the specified image or UI element to achieve a better OCR read. The following options are available:

• None - does not apply a preprocessing profile;
• Screen - preprocessing suitable for remote desktop applications;
• Scan - preprocessing suitable for scanned files;
• Legacy - uses the engine’s default settings for preprocessing images, this is the default option.

https://docs.uipath.com/activities/other/latest/ui-automation/google-ocr

2. In the check box field you will map the internal taxonomy name to the given document type if applicable…for example if you are using machine learning classifier then it would by default have a classifier for recipt and in your taxonomy you might name receipt as bill…so you need to provide the name recipt in the field against the bill line item in the classifier…if the document type is already your own taxonomy document type…for example for a keyword based the document type would be same as what you provide then nothing to provide there can be left blank

https://docs.uipath.com/activities/other/latest/document-understanding/machine-learning-classifier

https://docs.uipath.com/activities/other/latest/document-understanding/classify-document-scope

3. It is to define the template structure and how and what fields would be present where…for more details exactly how to and all…see this detailed explanation

https://docs.uipath.com/activities/other/latest/document-understanding/form-extractor#the-template-manager-wizard

Hope this helps

Cheers