Method and device for identifying spam

Abstract

The invention discloses an identification method and device for junk information, and relates to the technical field of information. The method comprises the following steps that: inputting an object to be identified into an information classifier to carry out primary identification; obtaining first junk information contained in a primary identification result; inputting contents except the first junk information in the object to be identified into a preset neural network model to be subjected to secondary identification; obtaining second junk information contained in a second identification result; and according to the first junk information and / or the second junk information, correcting the preset neural network model. Therefore, through at least two times of screening and the neural network model, the junk information in the object to be identified is identified, identification accuracy and intelligence can be greatly improved, and the junk information can be prevented from hurting users as much as possible.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a garbage information identification method and device. Background technique [0002] With the continuous development of the Internet, self-media and social media products are developing rapidly, the amount of information on the Internet is increasing day by day, and the openness of the Internet also leads to the existence of a lot of bad information on the Internet. In order to provide users with a better network environment, and to prevent users from being harmed or lost by bad information, monitoring and filtering information has become a common demand. [0003] Application of content filtering technology can realize the filtering of bad information on the Internet, so as to ensure the security of the network environment. There are many forms of information on the Internet, among which text form is the most common one. Text filtering refers to the process of fin...

AI Technical Summary

Problems solved by technology

[0004] However, in the process of implementing the present invention, the inventor found that there are at least the following problems in the prior art: the existing keyword matching technology only filters spam information by directly including specific keywords, while Chinese is extensive and profound, and the same word It may express completely opposite meanings under different semantics. Therefore, this method is likely to cause non-spam information containing keywords to be misidentified, hindering the dissemination of normal information; moreover, the identification and filtering effects of keyword matching technology are affected. The limit on the number of preset keywords makes it impossible to learn independently and expand the scope of recognition

It can be seen that the existing keyword matching technology has the problems of low accuracy and limited filtering ability.

Images