Skip to main content

Is it possible to extract data from multiple PDFs using Automation Anywhere
In which PDFs have
1. Different formats
2 .Unstructured data with different keywords .
3. We have around 1000 Pdf files 
4. May Include scanned PDFs

Hi @Harika 1170 ,

 

If you are not familiar, there is a feature called IQ BOT in AA which is developed specifically for document extraction whether it is structured or unstructured. 

 

It will automate document-centric business processes, end to end, a web-based, Cloud-native intelligent document processing solution that can read and process complex documents and email. This solution combines RPA with AI techniques to extract and classify semi-structured and unstructured data.

Automation 360 IQ Bot is a hybrid solution for On-Premises and Cloud deployments.

 

If you are using community edition, you can utilize IQ Bot but the document extraction is limited to 100 documents per learning instance.

 

If you are using an enterprise version and don’t have an IQ BOT license purchased yet, you can contact your PEM.

 

 

In addition to it, if you are having an enterprise client of version 25 and above, there is a new feature called Document Automation. You may refer here for further details on configuring and utilizing the same.


Thanks for the reply, We are not sure of what format the input document will be in future, it is difficult to train IQ bot for all types of formats, and also the keywords may be different. 

I have never heard of Document Automation, thanks for introducing this concept, will try it.

 


Thanks for the reply, We are not sure of what format the input document will be in future, it is difficult to train IQ bot for all types of formats, and also the keywords may be different. 

I have never heard of Document Automation, thanks for introducing this concept, will try it.

 

 

There is option to segregate the Documents based on its type (Invoice, Utility bill etc.). You can also customize the Form fields and Table fields based on your requirements. 


Hi @Harika 1170 ,

You can achieve that using IQ BOT, IQ BOT Classifier Package or Document Automation.

 

IQ BOT and IQ BOT Classifier Package 

IQ Bot Classifier package enables you to group or classify documents into appropriate learning instances for content extraction in Automation 360 IQ Bot.

 

https://docs.automationanywhere.com/bundle/enterprise-v2019/page/enterprise-cloud/topics/aae-client/bot-creator/commands/cloud-doc-classifier-package.html

 

Document Automation :

The Document Automation workflow enables users to scale their document processing operation. Users create learning instances that use Automation Anywhere or Google Document AI pre-trained models to process invoices, utility bills, and receipts. Once a learning instance is running in production, it automatically improves extraction accuracy based on feedback from manual validation.

https://docs.automationanywhere.com/bundle/enterprise-v2019/page/enterprise-cloud/topics/iq-bot/native/iq-bot-workflow.html

 

Thanks

 


Hi @Harika 1170 

Adding to the above, you cannot find the IQ BOT Classifier package by default in your CR, get in touch with your PEM or CSM For the package.

I’d recommend to try Document Automation for this use case.


Hi @Harika 1170, were you able to do this? if yes, could you please let me know the process. Thanks! 

@Tamil Arasu10 Hi, is this possible in the community edition? I am getting generic.server.exception error when i try to create a learning instance. 


Hi @swarajk,

Please check out the link

Document Automation Community Edition

 


Reply