How to use pxRunTimeAnalyzer for Entity extraction manually from the flow.

User Experience
, , , , , , , ,
1

Hi,

We have a requirement to Analyze the text from PDF or any other file and extract the entities out of it?

We are planning to use pxRunTextAnalyzer activity to do the same, but not sure how to use it to fulfill the above requirement.

2

@CharithaR To analyze text from a PDF or other file and extract entities using the pxRunTextAnalyzer activity, you first need to convert the content of the file into a text format that Pega can process. Once you have the text, you can call the pxRunTextAnalyzer activity. This activity requires two parameters: the Text Analyzer rule name and the Applies-To class of the Text Analyzer rule. The text to be analyzed should be passed as an input parameter. The activity will then analyze the text and extract the entities based on the configuration of the Text Analyzer rule. Remember to ensure that your Text Analyzer rule is properly configured for entity extraction

This is a GenAI-powered answer. All generated answers require validation against the provided references.

Creating entity extraction rules for text analytics

Building text analyzers

Intelligent interaction in text analytics

How to call text extraction model in activity?

3

@MarijeSchillern Hi ,

Could anyone help me how we can convert the content of the file into a text format that Pega can process.

And is there any Pega OOTB functionality to achieve this.

Thank you

4

@CharithaR I will let other users comment further as this requires customization.

Pega does not provide an Out-Of-The-Box feature to convert the content of a PDF file into a text format. However, you can use custom Java code with external libraries such as Apache PDFBox to extract text from a PDF file. Please note that this might require significant custom coding and testing.

Read PDF Data

Map eForm rules