Automobile accessory searching method based on semantic knowledge

An automobile accessory searching method based on semantic knowledge comprises the steps that on the basis that an accessory database is established, historical manual decoding data labeling is conducted, and model training data is made; a knowledge graph and a matching model are constructed by using the cleaned samples as training data; according to keywords input by a user, corresponding aliasesare associated through matching of the knowledge graph, matching is conducted from the vehicle model accessory full table through the expanded alias list, and accessories with the highest correlationare discharged; and finally, outputting the names of the parts and other related information in the database. According to the invention, spoken and diversified user input of accessories is learned through the knowledge graph and the matching model, the intervention of manual decoding can be reduced, the efficiency is improved, the cost is saved, and the user experience of a transaction platformis optimized. 一种基于语义知识的汽配件搜