Enhancing Welfare Services for Suwon City Residents

Overview

Previously, welfare information for Suwon City was fragmented across multiple systems, making it difficult for citizens to find necessary information quickly. This project was initiated to improve welfare-related civil services by consolidating them into a single, integrated service platform.

Project description

The project established a system capable of sentence-based searches by integrating information on welfare policies, services, and regulations provided by both the central and local governments. Raw welfare policy data was reorganized, and sentence-based search functions were strengthened by analyzing user intent. Additionally, a specialized welfare task support service for government officials was developed to facilitate inter-departmental collaboration and allow for easy verification of legal information.

Key technological features

• RAG Architecture: Constructed a Retrieval-Augmented Generation (RAG) architecture utilizing an Embedding Model to enhance response accuracy
• Hybrid Search & Re-ranking: Implemented advanced document retrieval and re-ranking through a combination of Dense and Sparse Embedding vectors

Expected outcomes

By increasing accessibility to welfare services, the project will enhance citizen satisfaction and improve the operational efficiency of government officials, enabling the delivery of rapid welfare administrative services.

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.2, https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=29182&parentSeq=29203