Keyword extraction method and system for professional knowledge graph, computer and storage medium

Abstract

The invention discloses a vocational knowledge graph keyword extraction method. The method comprises the steps of obtaining recruitment data and preprocessing the recruitment data; performing manual annotation on the preprocessed recruitment data to generate a text dictionary; inputting the text dictionary into a pre-constructed initial keyword extraction model to train the initial keyword extraction model so as to obtain a final keyword extraction model; inputting recruitment data of keywords to be extracted into the final keyword extraction model to extract initial keywords; and filtering the initial keyword to obtain a final keyword. The invention further discloses a vocational knowledge graph keyword extraction system, computer equipment and a readable storage medium. By adopting the method and the device, the keywords in the document can be directly extracted without depending on a word segmentation tool, and the extraction effect of the composite keywords can be greatly improved, so that a solid technical foundation is laid for construction and landing of the professional knowledge graph.

Description

technical field [0001] The present invention relates to the field of big data, in particular to a method, system, computer and storage medium for extracting keywords from an occupational knowledge map. Background technique [0002] With the vigorous development of the Internet, the amount of information on the network has begun to explode. How to quickly and accurately obtain knowledge from massive amounts of information has become the core and urgent need of people. The knowledge graph absorbs the concepts of semantic web and ontology in knowledge organization and expression, making knowledge easier to exchange, circulate and process between computers and between computers and people. In recent years, with the rapid development of artificial intelligence, the key issues involved in knowledge graphs, such as knowledge extraction, representation, fusion, reasoning, and question answering, have been solved and broken through to a certain extent. Widely concerned by scholars a...

AI Technical Summary

Problems solved by technology

The traditional keyword extraction method relying on lexical statistical information first needs to segment the document, so the accuracy of the word segmentation tool will greatly affect the final extraction effect, and it is based on the method of bagging, and the position information between words cannot be obtained. exploited, and therefore naturally present some defects

Keywords in the employment field are highly professional, with strong coherence between words and many compound keywords. The traditional word segmentation algorithm cannot cope with this special situation well and cannot meet the keyword extraction needs in the employment field.

Images