Real-time life insurance claims digitization
%201.svg)
About
Hanwha Life
Problem
The company had accumulated ten years of medical data in unstructured document formats, with an additional inflow of hundreds of thousands of documents each day. Without digitization, this data remained unsuitable for analysis, limiting valuable insights. Digitizing this vast dataset was crucial to enable meaningful data analytics.
Technical challenges
- Real-time processing: Meeting the demand for real-time customer requests posed a significant challenge, with hundreds of thousands of documents needing processing daily.
- Extracting thousands of key-value pairs: Classifying millions of unstructured documents and extracting numerous key-value pairs was a difficult problem. Existing OCR solutions often lacked the accuracy needed to process such documents effectively.
Solution
Upstage installed document classification and key information extraction models for five main insurance claim documents onto the Hanwha Life on-premises infrastructure.
Results
Business impact
- Enterprise-grade accuracy: Achieved over 97% accuracy in document classification and 96% accuracy in key-value extraction for primary document types.
- Digitized 240,000+ documents per day: Including ten years of historical medical billing data, paving the way for enhanced data analytics.
- Reduced FTE by ~70%: Decreased full-time equivalents (FTE) needed for digitizing claims documents by approximately 70%, allowing resources to be reallocated to strategic initiatives.
- Supported new insurance product development: Leveraged insights from digitized data to drive innovation in insurance offerings. (Related article in Korean)
Why Upstage
About
Hanwha Life
Problem
The company had accumulated ten years of medical data in unstructured document formats, with an additional inflow of hundreds of thousands of documents each day. Without digitization, this data remained unsuitable for analysis, limiting valuable insights. Digitizing this vast dataset was crucial to enable meaningful data analytics.
Technical challenges
- Real-time processing: Meeting the demand for real-time customer requests posed a significant challenge, with hundreds of thousands of documents needing processing daily.
- Extracting thousands of key-value pairs: Classifying millions of unstructured documents and extracting numerous key-value pairs was a difficult problem. Existing OCR solutions often lacked the accuracy needed to process such documents effectively.
Solution
Upstage installed document classification and key information extraction models for five main insurance claim documents onto the Hanwha Life on-premises infrastructure.
Results
Business impact
- Enterprise-grade accuracy: Achieved over 97% accuracy in document classification and 96% accuracy in key-value extraction for primary document types.
- Digitized 240,000+ documents per day: Including ten years of historical medical billing data, paving the way for enhanced data analytics.
- Reduced FTE by ~70%: Decreased full-time equivalents (FTE) needed for digitizing claims documents by approximately 70%, allowing resources to be reallocated to strategic initiatives.
- Supported new insurance product development: Leveraged insights from digitized data to drive innovation in insurance offerings. (Related article in Korean)
Why Upstage
Explore more success stories
Explore how industry leaders have achieved success and transformed their workflows with Upstage.
Real-time life insurance claims digitization
Automating product price comparisons with a purpose-trained LLM
Upstage collaborated with ConnectWave to develop a domain-specific large language model (LLM) tailored for e-commerce tasks, addressing inefficiencies in manual product data extraction and organization. The customized LLM, built using Upstage’s advanced mixture-of-experts architecture, automated the extraction of attribute-value pairs and streamlined product catalog management. By significantly reducing manual workloads and improving data accuracy, the solution enhanced operational efficiency and user experience. Outperforming general-purpose LLMs like GPT-3.5, Upstage’s tailored model demonstrated the transformative potential of private LLMs in revolutionizing e-commerce operations.
Transforming news search with RAG
Upstage partnered with the Korea Press Foundation to create BIG KINDS AI, a Retrieval-Augmented Generation (RAG) system that transformed news search. Addressing limitations of keyword-based searches and challenges like hallucination, the system offered real-time updates and natural language query handling. Built on 82 million articles and powered by AWS, it delivered accurate, efficient results, achieving a quality score of 86 and client satisfaction of 92.2, setting a new standard for AI-driven search.
Building tomorrow’s solutions today
Talk to AI expert to find the best solution for your business.
