Hardcore: PDF document automation
Channel 3: Fully automated document flow with PDF documents
DIG.easyconnect, as a channel, offers exactly what the name promises: incredibly easy access to full EDI convenience via the DIG Portal, so that even these incoming documents never have to be entered by hand again!
For this purpose, data from PDF documents is converted accordingly using OCR or Deep OCR (both technical solutions are available), depending on the specific requirements of the customer, and is checked, prepared and transferred to the target system in the desired format fully automatically at the DIG Portal.
What is OCR?
OCR stands for Optical Character Recognition, also commonly referred to as text recognition. Technically, success rates of up to 99 percent are possible after appropriate training phases, so that manual and repetitive tasks relating to document capture and invoice recognition can be largely automated. In addition to "normal" OCR, DIG also offers Deep OCR, in which artificial intelligence eliminates the need for training phases.
Automated processing of PDF documents
In order to be able to automatically process incoming PDF documents such as order confirmations, invoices, delivery bills and incoming customer orders, they are first converted into machine-readable text using OCR. The PDF documents are analyzed by special software and the results checked for validity or read rate. The success rate depends on the class, quality, structure and formatting of the original document.
The read-out data is structured via a conversion into an XML file, with which all the advantages of an EDI document flow can be used.
- Order confirmations
- Delivery bills
- incoming customer orders
DIG training support for standard OCR
DIG supports OCR training for recognizing data from PDF invoices and other documents by checking the individual PDF documents that do not produce satisfactory results. In the first step, optimization possibilities through system settings are checked and discussed before implementation. If required, the recognition rate can also be maximized with individual programming to such an extent that, as a rule, only individual cases need to be validated in the company.
Delivery note recognition in practice
Whether on construction sites or in different warehouses: delivery bills often go through a lot before they are scanned! Also, at item level, the supplier's item numbers do not match your own. DIG therefore enables an automated assignment of the delivery bill to the order in the ERP (by means of an order number recognized by OCR). This not only facilitates control, but also enables a learning system that derives from the manual assignment of the individual items the ability to automatically check these items the next time despite different item numbers!
Try the magic of reading your PDF documents!
See for yourself how OCR and Deep-OCR bring dream results and full EDI convenience with your exact documents, not only saving time but also avoiding transmission errors! We will be happy to tell you more.
How OCR learns to read PDF documents correctly
With the standard OCR, the recognition reliability of the fields and reading of the values is marked with a point value. This is necessary because documents from different senders are formatted differently, i.e. individual fields and items may contain completely different data. A threshold value can be defined, from which a manual validation is to take place. The responsible employee checks the contents in a web interface and makes corrections if necessary. In this way, the system continuously learns by marking and saving unrecognized fields in the graphical interface. As a cloud solution, the software learns from the input of all users and thus offers everyone faster learning progress.
DIG opens up an even faster and successful path with the integration of Deep-OCR: This innovative type of document analysis uses AI (artificial intelligence) to train the correct capture of data in documents with different layouts. For example, item data from incoming invoices is transferred directly to the accounting software so that posting records can be created directly.