AI Chatbot Service Based on Child Health Policies

Overview

The annual unmet medical care rate in Gimhae City, with a population of 560,000, stands at 12.7%, which is significantly higher than the national average of 5.3%.

This rate is particularly high among people in their 20s to 40s, who represent the primary child- rearing generation. Limited access to pregnancy, childbirth, and pediatric healthcare services can adversely affect children's overall health management.

To address this issue, the project aims to develop a practical mobile application that provides child health management information using hyper-scale AI technologies, enabling all caregivers to conveniently access essential healthcare guidance anytime, anywhere.

Project description

A 240MB PDF document containing 33 child health and welfare policy items was processed through text and image analysis as well as OCR technology, and subsequently trained using the Hyper CLOVA-X AI model. This allowed the development of a child health policy chatbot capable of handling natural—language Q&A related to child healthcare and welfare services. The system employs CLOVA Studio’s RAG technology to search for documents similar to user queries in real time, enabling the AI to generate contextually accurate responses based on relevant reference materials.

Key technological features

• Implemented with advanced Q&A capabilities using a CLOVA X LLM-based model grounded in natural language understanding (NLU) technology
• Enhanced information retrieval accuracy by configuring an independent RAG (Retrieval- Augmented Generation) module.
• Integrated real-time data retrieval with generative AI responses for improved user experience.

The Chatbot offers personalized, AI-based consultation on child health policies, enabling citizens to access real-time information on support programs, vaccination schedules, and application procedures at any time.

Expected outcomes

The service is expected to bridge information gaps among parents’ and improve access to healthcare services. By automating health and welfare policy guidance through AI, the system will reduce administrative workload, enhance response accuracy, and increase overall service efficiency.

Launch year: 2024

Attribution

Case study courtesy of the National Information Society Agency, Republic of Korea, Apolitical's Content Partner. Sourced from Use Cases of Public AI Service, Vol.1,  https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=28997&parentSeq=28999