Automated Contract Support for Schools via Adaptive Learning

Overview

Public contracts for construction, services, and goods are essential for institutional operations. However, the methods and procedures are highly complex, and various laws, guidelines, and training materials are scattered, making them difficult to search and utilize effectively. To address this, the Seoul Metropolitan Office of Education (SMOE) aims to provide a Contract Administration Support Service. By automating the document drafting and information retrieval processes, the system will save faculty members' time and allow them to focus on more specialized tasks.

Project description

The AI chatbot service has been trained on a comprehensive collection of contract case studies to ensure high response accuracy. When a user queries the system regarding procurement or contracting procedures, the AI provides precise guidance based on verified precedents. Furthermore, the service provides direct download links to the original source documents, allowing faculty members to verify legal grounds and official forms immediately without secondary searches.

This dual-indexing approach—combining structured hierarchy with unstructured keyword extraction—ensures that even highly specific or nuanced contracting rules can be located quickly, regardless of how the user phrases their inquiry.

Key technological features

• Structured Data Indexing: Fast structural searching based on the table of contents and specific sections of manuals or guidelines
• Unstructured Data Indexing: Separate indexing of core phrases and critical keywords within the data to enhance retrieval precision

Expected outcomes

The implementation of this service creates an environment where faculty members can improve their processing speed and concentrate on higher-value professional duties. By standardizing the information retrieval process, the system strengthens the transparency and public accountability of contract administration.

Quantitatively, the SMOE expects a 30% reduction in the time required for contract-related tasks. This efficiency gain not only lowers the administrative burden but also minimizes the risk of legal errors or procedural omissions, leading to a more reliable and streamlined public procurement system.

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=29234