FEATURE AI & VR
Automated capture of customs- clearance data
The regulations and laws governing cross-border trade have changed, presenting huge challenges to anyone involved in export and e-commerce. It is therefore essential that postal and parcel companies, carriers and e-commerce retailers adapt their processes to remain compliant. By Hans Jongebloed, Consultant, Prime Vision OCR Team
A
new rule comes into force on 1st July this year that requires VAT to be calculated on all parcels entering Europe. Conservative
estimates indicate this will result in a fi fty-fold increase in the number of parcels for which the postal service must process VAT as part of customs data. Before packages can leave the international hub, postal operators must submit customs data. If the data is incomplete, the customs department will reject the item which would then be returned or stored until the required data is supplied. This will undoubtedly result in postal operators being on the receiving end of many complaints from users, even though the fault lies fi rmly with the shipping company itself. Furthermore, if the data is incorrect it may lead to inaccurate VAT invoices and potentially more costly complaints and/or return of items.
Long-standing problems
This issue is in addition to a variety of other problems postal operators already need to address when a substantial proportion of these parcels go through the automated sorting process. Firstly, many packages are erratic in size, shape and weight which can cause multiple problems when trying to present the label in the correct position to a scanner. The predefi ned customs labels and barcode system also often suff er from poor printing, with crucial information missing or the ink being smudged.
12 April 2021 | Automation
Lastly, even when a parcel is a standard shape, fl atly presented to the scanner, with precise, clear customs labels, the lack of standardisation in senders’ address label formatting makes a near-impossible read for the more common scanners. Add to this the fact the remaining 19% of the 560 million parcels have no standardised formatting at all and it becomes a daunting prospect for any modern European sorting hub.
The lack of optimised automation optical
code reading (OCR) available on the market with the capability to handle this complicated import stream means that vast resources are immobilised while a high proportion of parcels are manually sorted. With the potential of customs changes compounding the problem, manual processing and the considerable associated costs will spiral ever higher, potentially introducing signifi cant delays in parcel delivery. To avoid this additional workload, postal operators must ensure that e-commerce companies provide customs data in advance so that processing and delivery of parcels are not compromised. Furthermore, this new VAT rule may cause consumers to reject packages when they realise additional charges must be paid on their order.
Based on AI and Deep Learning Computer vision expert, Prime Vision, off ers AI-enabled solutions that address the new regulatory landscape. The company’s International Label Reader automates the processing of international packets and
parcels bearing customs labels CN22 and CN23, allowing the easy acquisition of all required customs data for postal items not pre-declared digitally.
The International Label Reader is based on Prime Vision’s award-winning OCR technology; however, new innovations like state-of-the-art neural networks based on AI and Deep Learning techniques have taken this system to the next level. By presenting thousands of previously unfathomable addresses from individual countries to the International Label Reader its neural network makes connections and learns what is the normal format for each market.
The system manages the semi-automated coding process that is required to obtain all the data needed to clear a postal item through customs. The automated element comprises the Prime Vision Mail Match central workfl ow system for identifi cation of sender, receiver and custom fi elds optical character recognition for clearance purposes, a web- based data entry video coding platform and a manual image lift station for image acquisition and barcode reading. Increased automation rates in automatic sorting, coupled with less manual sorting, a reduction in video coding costs and effi cient customs declaration are clear benefi ts. The system can be integrated or standalone.
CONTACT:
Prime Vision
www.primevision.com
automationmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46
