Retrieving information from a directory


Retrieve invoice information to rebuild a customer database

Following a computer problem, a company needs to recover the data of its customers starting from its paper invoices. They are scanned beforehand.

The objective is twofold:
- reconstitute the customer database from this information and regroup them in a CSV file.
- extract billing information on pdf and link them to the customer account.

The output file diagram is special because it must correspond to the import logic of the cash register software used.



Extraction of invoice information after OCR (text recognition)


Automated processing in our Smart My PDF solution.


Retrieval of all information sorted and stored in a CSV document.

Scenario used


OCR Worker

Recovers text from a scanned image


ETL Worker

Cleanses and formats data


CSV Worker

Categorizes texts


Database Worker

Save to database

Return on investment

Retrieval of important data, customer contact details and accounting.

Cleaning, standardization, control and consolidation of information.

The file can be directly integrated into the customer's cash register software

500 hours of data entry by operators saved for the entire project.