Network public opinion alarm storm suppression method

Abstract

The invention provides a network public opinion alarm storm suppression method. The method comprises the following steps: step 1, receiving an original alarm data stream generated by a traditional keyword alarm trigger mechanism; step 2, dividing the original alarm data stream into a plurality of event alarm data substreams; 3, the event alarm data substream is pushed to an alarm storm suppression layer, interception or merging is carried out through suppression rules in the alarm storm suppression layer, and alarm noise is reduced; and step 4, outputting the suppressed alarm information, sending the alarm information to the user, and simultaneously prompting an alarm reason. The scheme provided by the invention is compatible with the existing public opinion alarm mechanism, adopts a plug-and-play dynamic suppression layer mechanism, only generates key alarm points such as rapid change of popularity and important media mention, conforms to the attention law of people, and effectively suppresses the generation of alarm storm; and a feedback optimization mechanism is provided, and the current suppression rule is adjusted through alarm feedback information submitted by the user, so that the alarm suppression accuracy is further improved.

Description

technical field [0001] The invention relates to the field of cognitive domain network security, in particular to a method for suppressing network public opinion alarm storms. Background technique [0002] With the popularization of mobile smart devices and the Internet, a large number of Internet users share what is happening around them through forums, social media and other Internet applications and post their own comments on events in the network. Due to the all-weather, sudden and rapid Internet communication characteristics, a small local event can easily evolve into a national public opinion event with greater influence, and even some lawbreakers will use the Internet to distort the truth and spread rumors. The credibility of the company has a huge negative impact. Therefore, for management agencies such as the Cyberspace Administration of China and the Public Security Bureau, how to accurately and real-time obtain hot events or topics that the public cares about and ...

AI Technical Summary

Problems solved by technology

[0006]Aiming at the problems existing in the existing public opinion warning methods, such as excessive and frequent warning information, unknown root cause of the warning, and no feedback improvement mechanism, a network public opinion warning is proposed. Storm suppression method, which can be applied to various public opinion monitoring systems, pre-positions the existing alarm identification mechanism, only as a pre-judgment link, and introduces a multi-level alarm storm suppression method to filter and reduce the frequency of non-important alarms

Images