关键词: 知识图谱, 多任务模型, 意图分类, 命名实体识别, 大语言模型

Abstract: The “14th Five-Year Plan” encourages universities to participate in scenario innovation and promote intelligent construction with artificial intelligence technology. Among these initiatives, scientific research management is a crucial aspect of university management. However, existing scientific research management systems cannot meet the individual needs of users. To address this issue, this article focuses on transforming university scientific research management towards intelligence as the demand orientation, and combines knowledge graph, traditional model and large language models to jointly build a new generation of university scientific research management question answering system. First, it collected scientific research knowledge to build a scientific research knowledge graph. Then, it used a multi-task model for semantic parsing, simultaneously performing intent classification and entity extraction. Finally, it used the parsing results to generate query statements to retrieve information from the knowledge graph and answer general questions. Additionally, it combined large language models with knowledge graph to assist in processing open problems. Experimental results on datasets with associated intents and entities show that the F1 values of the adopted multi-task model in intent classification and entity recognition tasks are 0.958 and 0.937, respectively, surpassing other comparison models and single-task models. The Cypher generation test demonstrates the effectiveness of the custom Prompt in stimulating the emergent abilities of large language models. The accuracy of text-generated Cyphers using large language models reaches 85.8%, effectively handling open questions based on knowledge graph. Additionally, the accuracy of the question answering system built with knowledge graph, traditional model and large language models is 0.935, which well meets the needs of intelligent question and answer.

Key words: knowledge graph, multi-task model, intent classification, named entity recognition, large language models