Extracting data from different format of PDF in Employee resume usecase

Learning Initatives Reboot Your Skills 2021
, ,
1

Hi Team,
i need a approach for coming senario, i have 50 resumes in different formats and have to read and extract specific fields like NAME,Designation,Skills,Experience,Linkedin and phone number.
i need to know whether this is possible with uipath ? if yes what will be approach!! if any one has model or POC kindly share it with me balasammy@live.com. kindly help as ua best.

Thanks to all.

2

Hi @balaji.S , reading PDFs is definitely possible with UiPath. You would need to first download the PDF Package by going to “Design” → “Manage Packages”. Then search for “UiPath.PDF.Activities” and download the package.
You can then use the following PDF activities, the one you’re looking for is “Read PDF Text”.

image
image383×680 95.6 KB

When reading the PDF, you can save the value of the PDF with “Save for Later Use”. Once you have the text saved, you can then use another activity to extract and filter the information you want, for example with the action “Modify Text”.

3

yes you are true but in my case has multiple resumes with different formats and i have to extract name,experience,Skills , mail and phone number …how can i achiv this

4

how many different PDF structures are there? If not a lot this could be done but if every PDF is different then it adds complexity.
Are you able to share the PDF? If not, maybe you can share the structure with some dummy data. Thank you!

5

i mean to say i have 10 different formats of pDF like general resume formats form google docs and other kind of resume formats !! is it doable ? if yes , kindly let me know the approach \

6

Hi,

Are there any ML skills available in UiPath to perform so?

Thanks

7

I was working on the same, so just wanted to know if you got the solution?