Method and apparatus for filtering rubbish contents

Abstract

The invention discloses a content spam filtering method and adopts a technical proposal as follows: judgment is carried out to posted content according to preset semantic analysis conditions; the content meeting the preset semantic analysis conditions in the posted content is taken as content spam and shielded; and the posted content after shielding treatment is published on a network after reviewing. The invention also discloses a content spam filtering device. The technical proposal can effectively realize the shielding of the content spam of communities, save the input capital of labor and material resources and improve working efficiency.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method and device for filtering junk content. Background technique [0002] At present, traditional filtering methods are generally adopted in Internet technologies for filtering community spam content. combine figure 1 As shown, before the content posted by the user is published on the Internet, it must first pass through the first-level dirty word filtering, and the words in the post that match the first-level dirty word will be blocked as spam words; The second-level dirty word filtering in the manual review stage will be performed on the content after the manual review, and the words that match the second-level dirty word in the post will be blocked again as spam words; the content after the second-level dirty word filtering will be successfully published to On the Internet; for the spam content that is not filtered out in the first-level or second-level dirty word f...

AI Technical Summary

Problems solved by technology

Therefore, in the prior art, this method of relying on dirty word filtering to filter spam content is passive and leads to limitations in filtering coverage;

[0006] (2) There is also a certain degree of passivity in the later inspection process of the post content that has been published on the Internet. The management server should actively browse and inspect the posts published on the Internet, and delete the spam words found one by one, so Increased labor input and capital for machine maintenance

Images