Retrieval method and device based on domain knowledge graph and search engine

Abstract

The invention discloses a retrieval method and device based on a domain knowledge graph and a search engine, and the method comprises the steps: building a relation graph based on the domain knowledge graph after obtaining the input of a user and collecting a first search intention of the user, and confirming and recognizing a second search intention of the user according to the interaction operation of the user and the relation graph. Therefore, the more accurate collection and understanding of the user intention are achieved, and a search engine can more accurately search required data conveniently; and due to the fact that the constructed and displayed relational graph not only covers the intention represented by the original input of the user, but also comprises automatically-expanded information associated with the intention represented by the original input of the user, so a knowledge exploration and extension space capable of being visually looked up and operated is provided for a user to confirm the search intention of the user, and the requirement for professional knowledge of the user is lowered; on the premise of low specialty requirements, the information retrieval problem in a data association relationship scene with knowledge complexity, specialty and certain breadth / depth can be solved with high accuracy, high efficiency and low time consumption.

Description

technical field [0001] The present application belongs to the technical field of information retrieval, and in particular relates to a retrieval method, device and search engine based on a domain knowledge graph. Background technique [0002] Information retrieval is a method / means of finding information, and is an important way for users to obtain information. Traditional technologies use keyword retrieval (such as keyword retrieval based on full-text retrieval related technologies) to find the required information from information collections. That is, the user inputs keywords to the search engine, and the search engine determines relevant information items from the information collection through full-text keyword matching of information items, and feeds back to the user. [0003] The applicant found that the retrieval scheme of the traditional technology has at least the following technical defects: [0004] 1) Construct search conditions only based on the keyword inform...

AI Technical Summary

Problems solved by technology

[0004]1) Construct search conditions only based on the keyword information input by the user, the information is single, and it is difficult for the search engine to accurately identify the user's search intention, which leads to the fact that users often need to For the results returned by the search engine, only by constantly modifying and trying the search keywords can a satisfactory search result be obtained. Even after multiple attempts, the desired result cannot be obtained, and the efficiency of information retrieval is low and time-consuming;

[0005]2) For specific industrial fields (such as biomedicine, optoelectronics / light guides, space technology, etc.) Traditional search engines require users to have certain professional knowledge in order to carry out retrieval tasks well. The professional level and knowledge limitations of users have become an important factor affecting the search accuracy of traditional search technologies. In the knowledge structure of users Incomplete, when it is impossible to find suitable keywords for data retrieval, it is difficult to give high-accuracy retrieval results that meet the user's intentions, resulting in low accuracy of retrieval results

Images