Method for auditing safety of internet video

Abstract

The invention discloses a method for auditing the safety of an internet video by using a computer system. Digital genes are formed by extracting the characteristics of a sample image or video. Each gene represents all samples with similar characteristics so that the validity and the availability of the samples are improved through abstraction. In the process of detection comparison, a four-step detection method, i.e. slicing and screening, preliminary detection comparison of a maximum sample, a secondary detection comparison of a minimum sample, result feedback and alarming, is adopted, therefore, screening is carried out first, then a large-scope comparison is fast carried out so that the number of the video images to be detected is reduced, and then the detection with pertinence is carried out so as to greatly improve the audition efficiency and increases the accuracy, validity and completeness of the audition.

Description

technical field [0001] The invention relates to a method for using a computer system to conduct security inspection of Internet video. Background technique [0002] With the development of broadband technology, the user-generated content (UGC) model based on Web 2.0 technology has led to an explosive growth trend of Internet video, which has brought great challenges to the review of video content and Internet security. In the radio and television mode, all video content is produced by the TV station itself or in cooperation, and has been checked by editors and chief editors at various levels to ensure the safety and legality of the content. However, under the Web 2.0 mode, users (netizens) have their creative desires stimulated, and a large amount of video content is provided on Internet sites. But at the same time, there are also a small number of people who intentionally or unintentionally upload unsafe or illegal video content, including piracy, pornography, violence and...

AI Technical Summary

Problems solved by technology

Under the controllable situation of the old content production, the traditional review method is enough to cope with it, but in the field of Internet video review, this method has the following obvious problems: (1) The efficiency of manual operation is low; (2) The requirements for editing are high, and the work The pressure is high; (3) the accuracy rate is extremely low; (4) the scope of discovery and detection is very small

In addition, editors have limited knowledge and limited memory. Even if they see content with potential safety hazards, such as pirated versions, they cannot find them.

[0004] Nowadays, there is no effective method for the security review of Internet videos. We use the method of Internet virus detection (extracting virus and Trojan horse characteristics to establish a virus database, and using sample matching method for detection) to extract features from various bad videos and digitize them into digital genes. Establish a digital gene bank, and then use the method of digital gene matching to detect security issues in Internet videos

Images