Taking advantage of AI capabilities can dramatically enhance the effort-to-value-ratio of sales order processing

Sales orders come in countless forms. Orders come through email and someone has to process them into the ERP system. It takes routine human effort to scan these orders and collect the essential information for further processing.

Sales orders can be processed in several different ways, but the most expensive one relies on human labor to extract data from sales orders and enter this data into an ERP system.

We can also automate this process

Traditional capture solutions can also be quite inefficient, however. This is due to a large number of unique customers sending in sales orders.

when combinating capture with AI

For a large international corporation, it is not unheard of to have well over 20,000 corporate customers, each with offices in multiple locations. In the worst-case scenario, there may be 400,000 unique sales order templates that someone has to implement using a capture solution. If each template takes a dozen hours, the total effort will be over half a million hours. And that obviously isn’t good for business.

You can handle these routine tasks using artificial intelligence. At the same time, you can save the human effort for more meaningful and creative tasks.

Enter ElinarAI

With our help, you can achieve efficient sales order processing by combining IBM Datacap Insight Edition with ElinarAI. The solution uses the powerful cognitive capabilities of Datacap to create a page layout and tokenize sales orders.

ElinarAI combines IBM Watson with Elinar’s AI for an advanced understanding of content-centric processes. This will take enterprise content management (ECM) to the next level by utilizing advanced artificial intelligence and machine learning methodologies.

Training artificial intelligence

Initially, we train AI to understand various sales orders. In order to do so, we give the AI a large number of order and invoice history documents. It takes several weeks of supercomputer capacity for AI to learn the differences between sales orders. To do this, we use the Power8 Minsky.

After it has been trained in different sales orders, the AI will learn to recognize them. If a company gets new partners – and thereby new sales orders forms – a few samples would initially be run through the AI to see if it performs correctly. If it does not, further training or data post-processing is required.

The model how Elinar's AI works

AI-enhanced sales order processing

When a new order comes in, it is scanned with Datacap optical character recognition. The trained AI model can then identify the correct information from the order.

Datacap is further used to validate and verify the information. After that, it extracts the correct information and enters it into the ERP or another system.

Advantages and disadvantages in a nutshell:
  • Routine work relating to traditional sales order processing takes up a huge amount of time.
  • Large international companies might have 20,000 different customers with various different sales order forms.
  • Using traditional capture solutions, it can take hundreds of thousands of hours of work to input all the sales order templates into the system.
  • When combining capture with artificial intelligence, a lot of work effort can be saved for more meaningful tasks.

Elinar's CTO Ari Juntunen, specialist in augment and automating with AI
Ari Juntunen, CTO
+358 40 524 4482