Complex question multi-hop intelligent question answering method based on knowledge graph representation learning

• Main Authors: ZHANG YUANMING, LU JIAWEI, JI QI, XIAO GANG, XU XUESONG, WANG QIBING, CHENG ZHENBO
• Format: Patent
• Language: Chinese; English
• Published: 07.03.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a multi-hop intelligent question answering method for complex questions based on knowledge graph representation learning, which comprises the following steps of: 1) learning vector representation of entities and relationships through a knowledge graph representation learning algorithm, and mapping semantic vectors of the questions to the same vector space; 2) searching reachable entities of question subject entities, screening part of the reachable entities as candidate answers according to a scoring function, and establishing reasoning paths of the candidate answers; 3) inputting the reasoning path into an encoder, and combining an attention mechanism to obtain a fusion vector of all paths; and 4) calculating the similarity between the fusion vector of the path and the question vector as the score of the candidate answer, and selecting the entity with the highest score as the answer of the question. According to the method, the semantic relation between the question and the entity and