Question answering method and device based on knowledge graph

Abstract

The invention provides a question answering method and device based on a knowledge graph, and the method comprises the steps: obtaining a question statement, carrying out the matching of the question statement with a plurality of question types corresponding to at least one knowledge field, and carrying out the secondary matching of the question statement with the knowledge graph of the corresponding field; determining a question type corresponding to the question statement and a target knowledge field to which the question type belongs based on a preset condition; and constructing a target query statement according to a question and answer template corresponding to the question type and the question statement, querying in a knowledge graph corresponding to the target knowledge field through the target query statement, and returning an answer.

Description

technical field [0001] The present application relates to the technical field of information data processing, and in particular, to a question answering method and apparatus based on knowledge graphs, a computing device, and a computer-readable storage medium. Background technique [0002] In the existing independent software and the Internet, the search engine services it can provide are usually retrieval tools or simple questions and answers about a single item of literary knowledge (such as idioms, ancient poems or golden sentences). In a certain scenario, users need to acquire and use various types of literary knowledge in their writing. For example, to ask questions such as "descriptive idioms", "look up at the next sentence of the bright moon", "Lu Xun's famous sayings", etc. Switch to a different third-party search or dictionary and other tools. These tools currently mainly support returning relevant knowledge for the keywords input by the user, but if the input infor...

AI Technical Summary

Problems solved by technology

In a certain scenario, users need to obtain and use various types of literary knowledge in writing. For example, when asking questions such as "idioms describing hard work", "the next sentence of looking up at the bright moon", "Lu Xun's famous quotes", etc., you must ask more questions. Switch to different third-party search tools or dictionaries. These tools currently mainly support the return of relevant knowledge for keywords in user input. If the input information is complex or does not exist in the knowledge base of the tool, it cannot provide all information. As a result, users have to spend a lot of time selecting different types of retrieval tools, and screening, screening and comprehensive processing of the literary knowledge returned by the retrieval tools, thus greatly destroying the continuity and user experience of users in terms of document writing ideas

Images