Search across all content
projectKey services include accurately searching for relevant statutes and precedents through natural language queries, automatically organizing and providing factual circumstances, grounds for disposition, and legal reasoning bases, and responding with precedents and relevant statutory content appropriate to the query's intent.
Previously, searching for precedents and regulations related to customs disputes was keyword- centric, consuming significant time for tasks. To perform swift customs administration, there was a need to quickly and accurately verify the legal basis for judgments, leading to the development of an AI chatbot service capable of natural language-based search.
To train the AI model, data corresponding to Articles 31 to 35 of the Customs Act, necessary for customs investigations, was secured. This included case law and related legal statutes. Additional data was collected and utilized from external legal sites such as the National Law Information Center and Casenote. The training data was vectorized, loaded into a database for preprocessing, and then trained using RAG.
Key services include accurately searching for relevant statutes and precedents through natural language queries, automatically organizing and providing factual circumstances, grounds for disposition, and legal reasoning bases, and responding with precedents and relevant statutory content appropriate to the query's intent.
The introduction of natural language-based search reduced the time required to search existing precedents and statutes. The repetitive, manual task of selecting precedents was automated, enhancing operational efficiency. Starting with this internal innovation in customs administration, it is expected to enable reliable and prompt administrative support for citizens.
The project was planned to continuously strive to secure internal IT budgets and actively participate in external support projects, such as government ministry support project competitions, to pursue the formal development of AI models. Through this, the project aims to achieve digital innovation.
Launch year: 2024
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=29025
In partnership with
National Information Society Agency (NIA)
In partnership with
National Information Society Agency (NIA)
Connect with 500,000+ public servants solving your hardest challenges.
Connect with 500,000+ public servants solving your hardest challenges.
Help public servants worldwide learn from your work, what worked, what flopped and what you'd do differently
Share your project
Log in or sign up to continue the conversation