Document Understanding - Processing resumes

Hello,

I am new to document understanding. figuring out how to do it. Here is my situation . I have various resumes in the format pdf, doc, docx and rtfs. I need to do the foll:

  1. Based on set of keywords (skills) i need to search in the doc and match it with the relevant resumes.
  2. Need to extract no of years of work ex, and email address of the candidate(in the resume)
    Please note that each resume can be in any format …there is NO standard format.

Please guide me how to go about it.

Thank you !

Hi @Purnima_Sambasivan

May @Parth_Doshi help you in this

Also have a look to his youtube channel :-

Happy Automation :raised_hands:

Best Regards
Er Pratik Wavhal :robot::man_technologist:t4: :computer:

1 Like

Hey Purnima,
you will have to define a taxonomy for each of your document types or else you can create an ML Model in AI Fabric and use that.

Hello Parth,

Thank you so much, Do you have any videos or link for reference? have not used AI fabric so far and in ML Model https://docs.uipath.com/automation-cloud/docs/about-licensing#section-document-understanding-endpoints, i am seeing structures only for invoices , receipts and purchase orders. I am looking to extract from resumes name, email, phone number and most importantly skills sets based on a set of keywords from an excel. FYI - I am using community edition of UiPath

Thank you so much

Hi @Purnima_Sambasivan
I am Also facing same issue. If you find any solution about data extraction(Candidate name and skills) from resume. please tell me.

We implemented the solution on this by using the keywords and identifying how many times the keyword will result. Considering if the person is really experienced in that skill, his/her cv should be flooded with that skill.

This validation is done only to sieve the initial candidates based on the pre-defined number of times the keyword is appearing. This should not be used to select the candidate.