Research and implementation of a financial question answering system for universities based on LangChain and ChatGLM
The research begins by collecting,organizing,and processing documents from university financial websites,result-ing in the establishment of a local knowledge base.This knowledge base is then utilized to construct a question-answering system for university finance,which is based on LangChain and ChatGLM.To evaluate the system's performance,a panel consisting of uni-versity financial staff,teachers,and student volunteers has conducted detailed testing,assessment,and analysis of the system.The test results demonstrate that the question-answering system excels in terms of accuracy,interpretability,and response speed,espe-cially in the areas of research funding management,student services,and payroll services,where it has reached near-practical lev-els of functionality.However,the system still has deficiencies in knowledge base completeness,retrieval of relevant knowledge for questions,and generation of effective answers based on knowledge,which are the focus of future research.The research efforts pro-vide a novel solution for enhancing the service capabilities and levels of university financial departments and also offer valuable in-sights for the research and application of large language models in the development of digital campuses.
LangChainChatGLMLLMlarge language modelfinancial question answeringknowledge base question an-sweringquestion answering systemdialogue system
万方数据
维普
