Knowledge retrieval method and device, storage medium, server

Abstract

The invention discloses a knowledge retrieval method and device, a storage medium and a server. The knowledge retrieval method comprises the steps: receiving input information of a user; recognizing the retrieval intention of the user according to the input information to obtain retrieval intention points, wherein the retrieval intention points are determined according to knowledge in a knowledgebase; recombining and fusing all the retrieval intention points of the user to obtain a retrieval intention point combination conforming to the retrieval intention of the user; and performing retrieval according to the retrieval intention point combination, and outputting a retrieval result. By means of the technical scheme, an ideal retrieval result can be provided in a small corpus scene.

Description

technical field [0001] The present invention relates to the field of big data technology, in particular to a knowledge retrieval method and device, a storage medium, and a server. Background technique [0002] Text knowledge retrieval is usually divided into two scenarios: large corpus retrieval and small corpus retrieval. In various professional fields, there is a large amount of text knowledge, many of which are relatively professional, and corpus retrieval scenarios with a small amount of knowledge. At present, knowledge retrieval in this type of scenario is still dominated by traditional retrieval technologies such as distributed search (Elastic Search, referred to as ES) and full-text retrieval (SOLR, read as SOLAR), which cannot identify user intentions and can only provide keywords. search, and the search quality is limited. [0003] Existing intelligent retrieval systems are mainly used in large corpus scenarios. Using neural network algorithms, a large amount of c...

AI Technical Summary

Problems solved by technology

At present, knowledge retrieval in this type of scenario is still dominated by traditional retrieval technologies such as distributed search (Elastic Search, referred to as ES) and full-text retrieval (SOLR, read as SOLAR), which cannot identify user intentions and can only provide keywords. of searches, and the search quality is limited

[0003] Existing intelligent retrieval systems are mainly used in large corpus scenarios. Using neural network algorithms, a large amount of corpus is required for training to obtain a high-quality retrieval model, so it cannot be applied to small corpus (such as within 1 million knowledge points) text retrieval scenarios for

The retrieval effect of existing retrieval tools for small corpus scenarios is not ideal

Images