Automatic file classification system

Abstract

The present invention relates to an automatic file classification system, which belongs to the field of data mining. The automatic file classification system provided by the invention comprises an input module, an information extraction module, a text preprocessing module, an image preprocessing module, a video preprocessing module, an audio preprocessing module, a text classification module, an image classification module, a video classification module, an audio classification module, a fusion module and an output module. In the system, text information, image information, video information and audio information in a file are extracted through the information extraction module, preprocessed by the text preprocessing module, the image preprocessing module, the video preprocessing module and the audio preprocessing module respectively and classified by the text classification module, the image classification module, the video classification module and the audio classification module respectively and classification results are comprehensively processed by the fusion module, so that a final classification result is obtained. A text classification result with higher accuracy can be obtained by the method.

Description

technical field [0001] The invention relates to an automatic file classification system, which belongs to the field of data mining and is suitable for automatic resource classification, network content supervision, spam filtering, digital libraries and the like. Background technique [0002] File automatic classification is a relatively hot research issue in the field of data mining. Its purpose is to train a classification function or classifier, which can map the files to be divided into the given corresponding categories. The goal is to find faster and more accurate ways of managing textual information. [0003] At present, a large number of researches focus on the research of text file classification. For example, Zhang Xiaodan et al. disclosed a decision-level text automatic classification method in the document "A Decision-Level Text Automatic Classification Fusion Method" (national patent, patent application number: 2009100878443). Fusion method, whose classificatio...

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the shortcomings of low accuracy existing in the existing automatic text classification system, and proposes a method based on multiple media (image, audio, video and text information) on the basis of the existing decision-level text automatic classification fusion model. The automatic classification system of documents can obtain classification results with higher accuracy

Images