Enhancing KBQA Performance in Large-Scale Chinese Knowledge Graphs Using Apache Spark

Knowledge graph (KG) is a kind of fundamental technologies in the development of knowledge base question answering (KBQA) systems, primarily designed to assist in rapidly retrieving accurate information from massive knowledge repositories. Due to the content of knowledge bases continues to expand, the search performance of KBQA systems has become a crucial research topic. This study focuses on enhancing the query efficiency of KBQA systems by increasing the throughput of system queries through a distributed computing framework based on Apache Spark. The main research achievements of this study include optimizing the performance of Chinese KBQA systems using Apache Spark's distributed computing architecture, improving the efficiency of question-answering services, enhancing the accuracy of semantic similarity models to gain a deeper understanding of natural language semantics, and increasing the accuracy and reliability of similarity matching. Under the evaluation method of exact matching, the accuracy of knowledge base queries can reach 90.5%.