Back to the newsroom

Press Release

Korea Deep Learning and Sunghwa Corporate Express selected for a KRW 300 million AI Voucher to digitize handwritten waybills

Korea Deep LearningPublished

Korea Deep Learning and Sunghwa Corporate Express selected for a KRW 300 million AI Voucher to digitize handwritten waybills
In April 2022, Korea Deep Learning was selected to receive KRW 300 million in AI Voucher support for a project with Sunghwa Corporate Express to develop a system that reads handwritten waybills.

Korea Deep Learning has been selected for the 2022 AI Voucher Support Program of the National IT Industry Promotion Agency, which it entered jointly with Sunghwa Corporate Express. The selection was confirmed on April 4, 2022, and the two companies will receive KRW 300 million in development funding to build a "high-speed deep learning waybill recognition system for digitizing handwritten waybills." The goal is to read handwritten waybills, turn the delivery information into data, and automate parcel sorting.

Turning handwritten waybills into data

Many handwritten waybills still pass through parcel sorting sites. Because the handwriting and the way they are filled in vary widely, people often have to read and sort them by hand, which slows sorting and adds to the workload of delivery drivers.

The system the two companies are developing recognizes handwritten waybills, turns the delivery information into data, and uses that data to automate logistics sorting. Through the project, the two companies plan to shorten parcel sorting time, increase the economic benefits for the logistics industry, and ease the parcel industry's sorting problems.

Combining data from about 70 logistics networks with DEEP OCR

Sunghwa Corporate Express, the lead company, is a leader in business parcel delivery with about 70 logistics networks across the country. It holds more than 100,000 handwritten waybill records and has been steadily preparing to adopt handwriting OCR technology. As the supplier, Korea Deep Learning provides DEEP OCR, a character recognition solution based on its own deep learning engine. The structure brings field waybill data and OCR technology together within a single consortium.

Waybills are not new to Korea Deep Learning. In 2019, its first year, it built a deep learning waybill recognition system for Korea Post, and in April 2022 it received the President's Award of The Korea Economic Daily at the Korea Impactech Awards for a dual recognition system for shipping information that uses DEEP OCR.

"Through this consortium, which uses the lead company's waybill data and our DEEP OCR technology, we will work to achieve automated sorting through advances in technology that ease the fatigue of delivery drivers."

— Kim Ji-hyun, CEO, Korea Deep Learning

AI Vouchers that fund KRW 300 million in development

The AI Voucher Support Program, run by the National IT Industry Promotion Agency, funds development so that companies looking to adopt AI can form a consortium with a supplier and adopt the best AI for them in a short time. Each selected project receives KRW 300 million in development funding.

About DEEP OCR

Korea Deep Learning started out by reading documents. Built on KDL's own document-specialized VLM, DEEP OCR is Korea's first VLM-based OCR solution, reading not just the characters but the structure and meaning of a document together. It handles unstructured documents in every kind of layout without building separate training data, and extracts text and key-value data from visual elements such as seals, signatures, tables, numbers and symbols. From loan documents in finance to administrative documents in the public sector and handwritten waybills in logistics, documents people used to copy out by hand become business data through DEEP OCR. More information is available on the DEEP OCR page at koreadeep.com.

About Korea Deep Learning

Korea Deep Learning (KDL), founded in 2019, is an enterprise AI agent company. Built on KDL Frontier, its own vision-language model (VLM) specialized for documents, KDL makes AI agents that take on and complete the document work of businesses and public institutions. Its main products are DEEP OCR, DEEP Parser, DEEP Agent and DEEP Ops.

Source