메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(청운대학교)
저널정보
국제인공지능학회 The International Journal of Internet, Broadcasting and Communication The International Journal of Internet, Broadcasting and Communication Vol.17 No.1
오류 신고하기

피인용 0

검색

    초록·키워드

    In this paper, a Q&A chatbot using LLM, knowledge graph, Retrieval Augmented Generation(RAG), and AI agents is developed. To this end, we constructed a knowledge graph database using academic information data from University C. After constructing the knowledge graph, LLM is used to generate a Cypher query, and through this, we search for the desired information in the knowledge graph and inferred the answer using LLM. AI agent was constructed by defining function call and tool, and was implemented to enable stable answers to questions that were difficult to search using the previous method, through dynamic query generation and full-text index. Neo4j used in this paper uses the full-text search function of Apache Lucene. The AI agent determines which function should be used with appropriate arguments extracted from the user's question and acts as an executor that performs various processing. Simulation results show that developed Q&A chatbot generates correct answers for the user questions.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-25-02-093520587