Buffering method and device during paper classification, equipment and storage medium

Abstract

The embodiment of the invention discloses a buffering method and device during paper classification, equipment and a storage medium, and belongs to the technical field of text information processing.The method comprises the steps of acquiring a to-be-classified text set and a classification target set; obtaining a classification label tree of the classification target set and a classification label set of each to-be-classified text; taking label elements in the classification label set as query conditions, and obtaining an auxiliary label set from the classification label tree; based on the label elements in the auxiliary label set and a preset screening condition, screening out a historical classification model meeting the preset condition from historical classification models of a classification target set; and selecting a final classification model from an initial test classification model set or newly establishing a final classification model, and classifying the to-be-classifiedtexts in the classification text set based on the final classification model. According to the method, the text classification efficiency of a user is improved, the availability of the historical classification model is maintained, and a better classification service is provided for the user.

Description

technical field [0001] The present application relates to the technical field of text processing, in particular to a buffering method, device, equipment and storage medium for classifying papers. Background technique [0002] Paper text classification is an important topic in the research of scientific and technological articles. When a new paper is published or announced, the most important function is to classify the text. A scientific paper is a theoretical article that expresses scientific research results after researching an academic issue in a certain scientific field. It has the characteristics of scientific, creative, theoretical, accessible, professional, and practical. In order to effectively organize and manage massive academic resources on the Internet, academic resources are usually classified according to a subject category level or a large-scale concept, so as to better access and search these academic resources. [0003] At present, in most classification m...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiment of the present application is to propose a buffer method, device, equipment and storage medium for paper classification, so as to solve the problem of excessive classification time consumption and untimely update of historical classification models in the prior art when users classify papers The problem of low applicability

Images