Text classification method and device

Abstract

The invention relates to the technical field of computers and provides a text classification method and device. The method comprises the steps of S1, determining a feature word set of each target textby utilizing a key word bank expansion-based feature selection rule; S2, by utilizing an intra-feature word class uniformity and inter-feature word class discrimination degree-based weight calculation formula, calculating a weight of each feature word in the feature word set; S3, by utilizing a maximum weight fusion algorithm, performing weight fusion calculation on the weights of the feature words of the same target text in different text categories to construct target text eigenvectors; and S4, based on the target text eigenvectors, classifying target texts by utilizing a multi-mark classification model. According to the text classification method and device provided by the invention, the accuracy of text information expression can be effectively improved; the efficiency of model building can be improved; and the text information is ensured to be subjected to multi-mark classification accurately and efficiently.

Description

technical field [0001] The present invention relates to the field of computer technology, and more specifically, to a text classification method and equipment. Background technique [0002] China is a large agricultural country based on agriculture. There are many people engaged in the agricultural industry. The achievements in agricultural scientific research are outstanding, and some farmers have very rich production experience. However, the speed of agricultural development still needs to be improved. It is mainly due to the lack of mutual learning of agricultural information and the timely application of agricultural scientific research results to actual production. The reason is that a large number of information resources in the agricultural industry have not been effectively managed, and it is difficult for those who need relevant information to quickly obtain the corresponding information. Effective classification of agricultural information is the key to agricultur...

AI Technical Summary

Problems solved by technology

However, agricultural information resources have the characteristics of massive quantity, diversified carriers, multi-source channels, and heterogeneous storage. If the existing multi-label classification method is directly applied to agricultural texts, there will be inaccurate expression of text information and poor classification effect. Good and other questions

Images