New and advanced machine learning techniques that will help fleet management software to import document data “as accurate as a human and much faster” are being trialled by FleetCheck.  

Peter Golding, Fleetcheck managing director

The technique – which use data to improve how a system performs a repetitive task over time – is being applied to create new methods of easily importing information from paper and PDF documents and could be available to customers from later this year.

Peter Golding, managing director, said that research among its customer base had found that the ability to circumvent retyping details from paper or scanned such as invoices, fuel receipts and check sheets was the most common request for future product updates.   

He explained: “One of the major barriers which make it hard to fully digitalise company car, van and truck management processes is that many fleet suppliers still use paper-based systems or scanned PDF documents and images rather than easily imported, structured data.   

“Ideally, our users would like to be able to scan these pieces of paper or import these PDF files and the software then identify what the document represents before automatically importing the relevant information into the right field of their system.”  

Golding added that the company was not aware of any fleet software currently in the marketplace that can do this.  

“It is a really tough coding problem, meaning that the software would have to be able to identify an invoice, for example, and then draw the relevant figures in the right places.   

“There are difficult obstacles here. How does the system know which are the figures for the invoice subtotals and total and which are other numbers on the page that have no direct relevance, such as the postcode or the phone number?”  

He also said that trials by FleetCheck on a machine learning model for common documents were already reaping some success – and the company envisages its system will soon be “as accurate as a human entering data and much faster”. It’s currently tipped to arrive on the market later in 2022.  

Golding finished: “It’s a step change that will bring real benefits to our customers and represents a small revolution in terms of what fleet management software can do.”