Short message monitoring method ensuring identity of sender based social network mechanism

Abstract

The invention discloses a short message monitoring method that determines identity of senders based on social network mechanism. Short message is a shortcut method that applies wireless communication technology, which is not different from face to face communication, letter communication, voice conversation and Email communication in essence. The social network belongs to scale-free networks in complex network category. Clustering is a basic characteristic of the social network. The invention starting from clustering of the social network to implement short message preprocess and re-real time filtering based on communication historical records between short message senders and receivers and between receivers determines identity of the senders to block spam short messages. A short message monitoring centre is used in a hardware platform using symmetrical multi-process SMP technology. The monitoring centre is characterized in free maintenance, high blocking rate, low mis-judgment, which is not applicable for text short message filtering, but also effective to voice short message, multi-media short message in 3G generation.

Description

technical field [0001] The invention relates to short message monitoring technology in the field of short message technology, in particular to a short message monitoring method for confirming the sender's identity based on a social network mechanism. Background technique [0002] From 2000 to 2007, the SMS business volume in my country was 1 billion, 18.9 billion, 90 billion, 137.1 billion, 217.7 billion, 304.6 billion, 429.6 billion, and 592.1 billion. The volume is as high as 353.8 billion, an increase of 92.7% compared with 2006, accounting for 59.75% of the total number of short messages (Internet Society of China "2007 Mobile Phone Short Message Survey Report"). On July 23, 2008, the number of mobile phone users nationwide reached 601 million (statistical bulletin of the Ministry of Industry and Information Technology). Although most of the 100 million newly added users in 2008 are low-end users and have limited contribution to the ARPU of operators, cheap SMS is undoub...

AI Technical Summary

Problems solved by technology

[0014] The limited effectiveness of keyword and sending frequency filtering methods has been confirmed in ASA. One is easy to be avoided by spam messages, resulting in missed judgments; the other is that many words of keywords do not convey bad information. There is only a relatively high frequency of occurrence, so it is easy to cause misjudgment, and misjudgment will cause greater losses to users than omission

[0015] The text classification and filtering method based on SMS content has three major defects: first, the software and hardware resource overhead of the text classification and filtering method is too large, and the operators are overwhelmed with the average daily processing volume of 1.7 billion; second, the vector space model is used as a For example, text classification needs to go through six steps: word segmentation, feature selection, feature weight calculation, text vector ge...

Images