Error is ‘Keyword Based Classifier: Unexpected character encountered while parsing value: %. Path ‘’, line 0, position 0."’

[Ioana_Gligan]

Hello @Ramyaraju and @Paresh - please see the link below for a sample workflow that contains the keyword based classifier configured, and also uses the Machine Learning Extractor for both invoices and receipts.

Please keep in mind that the attached flow also uses Abbyy FlexiCapture - so if you have it installed and licensed, it should work out of the box - otherwise please edit the flow, delete the FlexiCapture Extractor from the Data Extraction Scope, enter the “Configure Extraction” link, check the configuration, then click Save. The flow should then work without requiring FlexiCapture existence.

As you will see, the document processing framework is fully flexible and offers you an open framework where specific algorithms for classification and extraction can be combined, ordered, or easily changed.

Please let me know if this works:

How to use Intelligent OCR activities guide and example

Hello @Jeven_Delacruz Here is a sample workflow using the IntelligentOCR 2.2.0 package. It is using multiple extractors, and the keyword based classifier. It is configured to use Abbyy AND the Machine Learning Extractor for retrieving data from invoices and receipts. Please have a look at the taxonomy manager, and at the configuration wizards for the document processing scope activities (classify document scope, data extraction scope etc). Do let me know if it works Ioana I…

As a note, if you want to start using the Keyword Based Classifier from scratch, please just create an EMPTY file on disk initially as the learning resource. The extractor will create its own required content.