File classification method and device, computing equipment and computer storage medium

Abstract

The invention discloses a file classification method and device, computing equipment and a computer storage medium. The method is performed based on the trained feature extraction network and the trained file classification model. The method comprises the steps that files to be classified are acquired; the files to be classified are inputted to the feature extraction network so as to obtain the file features of the preset dimension corresponding to the files to be classified; and classification prediction is performed based on the file features of the preset dimension by using the file classification model so as to obtain the corresponding classification result of the files. The file features of the files to be classified are extracted by using the trained feature extraction network basedon the scheme so that the time can be greatly saved, the efficiency and the accuracy of feature extraction can be enhanced, the influence of false video meta information can be avoided, classificationprediction is performed on the files to be classified by using the trained file classification model, automatic classification of the files can be realized, the problem of inaccuracy of the classification result caused by manual intervention can be avoided and the labor cost can also be reduced.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a file classification method, device, computing equipment and computer storage medium. Background technique [0002] With the rapid development of network technology, various files exist on the Internet. In order to help users effectively retrieve relevant files or quickly obtain files that users are interested in, some classification tools are needed to effectively classify a large number of files. Taking fans of a certain star as an example, fans only pay attention to the files of this star. Being able to classify the files and determine whether the files contain the stars followed by the fans can save the time of the fans, and it is not necessary for the fans to read all the files to determine whether the files contain the corresponding stars. [0003] In the prior art, the method of manually classifying files is adopted, which requires a lot of manpower, increases the c...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the method of manually classifying files is adopted, which requires a lot of manpower, increases the cost of classification, and the classification efficiency is low; although there are some methods for classifying file meta-information, but due to many There are false elements in the meta information of the file, resulting in low classification accuracy

Images