Special network incident detection method based on flow graph model

Abstract

The invention provides a special network incident detection method based on a flow graph module. The method comprises the following steps that each data text is sequentially subjected to segmentation processing to obtain keywords in each data text as nodes, and the co-occurrence relation between the keywords is used as the an edge keyword co-occurrence graph; the edge frequency of each edge is determined according to the occurring times of each coming moment of each edge in the key graph co-occurrence graph when the current detection moment is reached and the corresponding attenuation corresponding to each coming moment of each edge; the node moving frequency of each node is determined according to the edge frequency of edges between all adjacent nodes; the moving frequency change degree of each node is determined, sudden hot word nodes are determined according to the moving frequency change degree, and a sudden hot word co-occurrence graph is obtained; the preset graph clustering algorithm processing is carried out according to the sudden hot word co-occurrence graph, and each incident is obtained. The sudden hot word detection is carried out on the basis of the flow graph keyword co-occurrence graph, further, the incidents are detected, and the accuracy and the real-time performance of the incident detection results are ensured.

Description

technical field [0001] The invention belongs to the technical field of big data processing, and in particular relates to a method for detecting social network emergencies based on a stream graph model. Background technique [0002] Social networks are playing an increasingly important role in people's lives, such as Weibo. The two largest microblog platforms in China, Sina and Tencent, have registered more than 500 million people. CNNIC’s 33rd China Internet Development Survey Statistical Report As of December 2013, the number of microblog users in my country was 281 million, and the utilization rate of microblog among netizens was 45.5%. [0003] For emergencies or hot events, Weibo's scale of influence and speed of transmission surpass ordinary blogs and traditional news media. On May 12, 2008, a major earthquake occurred in Wenchuan, Sichuan, China. Twitter disclosed the first news at about 14:35:33. Including the Linwu melon farming incident, the school bus overloading...

AI Technical Summary

Problems solved by technology

Currently, clustering-based methods and topic model methods are mostly used to detect emergencies from a large number of microblogs. However, the existing cluster-based methods and topic model methods need to specify the number of events in advance, and There is no good way to estimate this value, and it can only be designed through experience, which makes the detection results of emergencies in Weibo poor

Images