A method and system for question answering in kitchen domain based on knowledge graph

Abstract

The invention discloses a method and system for questioning and answering in a kitchen field based on a knowledge graph. The method comprises the steps that a question sentence is acquired and treated by word segmentation, so a word segmentation result is obtained; entities and attributes of a word segmentation result are extracted according to context characteristics, and a semantic logic expression corresponding to the question sentence is generated; a SPARQL query statement is generated according to the semantic logic expression; and the knowledge graph of the kitchen field is inquired according to the SPARQL query statement and a result is obtained, and an answer corresponding to the question sentence is obtained according to the result. According to the invention, the questioning and answering system in the kitchen field is achieved, and accuracy and efficiency of the questioning and answering system in the kitchen field are increased.

Description

technical field [0001] The invention relates to a question answering system, in particular to a question answering method and system in the kitchen field. Background technique [0002] With the popularization of natural language understanding technology, many intelligent question-answering systems, intelligent examination systems, and intelligent questioning systems have emerged. It is contrasted with a knowledge base that should be trained on a large corpus to allow machines to understand natural language. However, the meanings and divisions of sentences and words are different in different fields, and most of the tokenizers on the market are universal, and the corpus will also have many division standards. At present, in the field of kitchens, recipes such as videos, pictures and texts are uploaded to the Internet for people to view, which will make many people query the corresponding recipes or dish names through the Internet, but there is no good reference The question...

AI Technical Summary

Problems solved by technology

At present, in the field of kitchens, recipes such as videos, pictures and texts are uploaded to the Internet for people to view, which will make many people query the corresponding recipes or dish names through the Internet, but there is no good reference The Q&A system in the kitchen field cannot provide people with fast and accurate search

Images