Knowledge graph question-answering method and system based on graph neural network embedding matching

• Main Authors: LI MINJIA, LI KEQIN, TANG ZHUO, LI KENLI, LIU CHUBO, YANG WANGDONG, XIAO GUOQING, ZHOU XU
• Format: Patent
• Language: Chinese; English
• Published: 07.05.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a knowledge graph question-answering method based on graph neural network embedding matching, which comprises the following steps: acquiring a question from a user, processing the question by using a named entity recognition tool to obtain an entity in the question, and processing the question by using a syntactic analysis tool to obtain a query graph and a subject term corresponding to the question; performing entity linking processing on the obtained subject terms by utilizing an entity synonym dictionary to obtain subject terms in a knowledge graph, inputting the subject terms in the knowledge graph into the knowledge graph for retrieval to obtain a subject graph, inputting the obtained subject graph and an obtained query graph into a trained graph embedding matching model, and obtaining an answer of the question. According to the method and system, the technical problem that the template of the existing semantic analysis method cannot be completely suitable for all natural language