Question-answering system based on domain knowledge graph and construction method thereof

Abstract

The invention discloses a question-answering system based on a domain knowledge graph and a construction method thereof, which comprises the steps of crawling information of a given domain from the Internet, extracting triples in the information, and inserting the triples into a graph database for storage; carrying out word segmentation and syntactic analysis on a question input by a user to obtain a dependency relationship table among words in the question, the dependency relationship being a dependency relationship among the words in one sentence; generating a query semantic graph by traversing the dependency relationship table, and converting the query semantic graph into a query statement of a graph database; and finally, querying the graph database by using the query statement to obtain an answer. The invention further provides a question-answering system by adopting the method. The question-answering system comprises a knowledge graph construction module, a question-answering module, a background processing module and a front-end display module. The invention is oriented to a given field, effective information in the internet is crawled, triples are extracted to create a knowledge graph database, and a question-answering system returns accurate and concise answers by querying the knowledge graph database.

Description

technical field [0001] The invention relates to the research field of knowledge graph and automatic question answering system, in particular to a question answering system based on domain knowledge graph and its construction method. Background technique [0002] With the advent of the era of big data, information on the Internet is growing explosively. The traditional World Wide Web, which only contains links between web pages, can no longer meet people's needs for quickly obtaining information. People hope to organize information on the Internet in a smarter way. resources in order to quickly and accurately obtain the information you need. There are many types of question answering systems, such as: community question answering system, question answering system based on reading comprehension, question answering system based on knowledge graph, etc., involving technologies such as knowledge source search and construction, question analysis and answer acquisition. The tradit...

AI Technical Summary

Problems solved by technology

For the search of specific professional knowledge, these general knowledge graphs have huge information, and the answers to questions obtained by searching the knowledge graph database usually contain too much irrelevant information, making the precision rate low

[0010] Second, the existing question answering system does not understand the questions in a specific field accurately enough, and does not use effective tools and algorithms to analyze the grammatical structure and semantics of the questions, which makes the matching between the question and the knowledge graph database fail, and the correct answer cannot be found.

Images