Press Release
Korea Deep Learning develops an automated insurance claim system with Boum Inc.
Korea Deep LearningPublished

In October 2022, Korea Deep Learning formed a consortium with Boum Inc., a company specializing in insurance claim solutions, and set out to develop an automated insurance claim system. The goal is to make filing an individual insurance claim simple by having artificial intelligence read medical charts. The two companies were jointly selected for the 2022 Data Voucher Program and are developing medical chart image data processing and an AI OCR model.
AI takes over the work of transcribing hospital documents
Until now, people had to read and transcribe the documents they received from hospitals. Korea Deep Learning replaces this process with document recognition based on DEEP OCR, its core technology, reducing the time a claim takes and the items that get left out.
The Data Voucher Program is a government-supported system that lets client companies receive the data and technology they need from supplier companies in the form of vouchers. In this project, Korea Deep Learning is responsible for processing medical chart image data and developing the AI OCR model, while Boum Inc. contributes on the insurance claim solution side.
A kiosk that connects users to an agent by video
The finished solution will take the form of a kiosk. When a user connects to an agent by video at the kiosk, the AI automatically prepares the claim documents that match the conversation. After the first claim, a claim can be completed in about 10 seconds. Noting that middle-aged and older people use existing insurance claim solutions less, Boum Inc. plans to create a claim environment that people of every generation can use easily, through a human-connected kiosk where users can talk with an agent.
Medical records in every format: bringing unstructured document recognition to insurance
Medical record documents are a typical example of unstructured documents, with formats that vary from one to the next. Kim Ji-hyun, CEO of Korea Deep Learning, explained that DEEP OCR can recognize unstructured documents such as online store product pages as well as high-volume documents such as logistics documents, and said the company would satisfy customers, insurers and medical institutions alike.
Korea Deep Learning has built experience in recognizing unstructured documents with DEEP OCR: in April 2022, it was selected for the AI Voucher Program with a project to digitize handwritten waybills for Sunghwa Corporate Express, and in the same month it received the Korea Economic Daily President's Award at the 2022 Korea Impactech Awards. This is a case of the experience it built in finance, the public sector and logistics expanding into insurance.
Twenty-two Data Voucher projects and the KB Unicorn Club
In 2022, Korea Deep Learning was selected for 22 projects in the Data Voucher Program. It is also receiving support from a tailored accelerating program as a company selected for the 2022 KB Unicorn Club, run jointly by KB Kookmin Bank and the Gyeonggi Center for Creative Economy and Innovation.
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.







