Method and device for detecting abnormal messages based on account number attributes

Abstract

Disclosed is a method for detecting an abnormal message, comprising: dividing a text of a detected message into a plurality of text segments; obtaining one or more account attributes of each text segment, and determining a publication proportion parameter corresponding to the account attributes of each text segment; determining a first factor corresponding to the account attributes of each text segment according to the publication proportion parameter; determining a second factor of the detected message according to the first factor corresponding to the account attributes of each text segment; and determining according to the second factor of the detected message whether the detected message is an abnormal message. Through the combination of publication account attributes of messages with undifferentiated text segmentation and the use of Bayesian algorithm, batches of junk messages of a microblog account are effectively limited, and the flexibility of junk message processing is improved.

Description

technical field [0001] The invention relates to the field of computer networks, in particular to a method and system for detecting abnormal messages based on account attributes. Background technique [0002] Network Instant Messenger (IM, Instant Massager) tool has been developed to today, has been accepted by most of the network users, and has become one of the indispensable software tools for network users, not only used in leisure and entertainment at ordinary times, but also in the user's It is also widely used at work. In the IM software, the main realization is the one-on-one friend chat alone and the one-on-N group or discussion group message chat mode. With the continuous development of Internet applications, microblogging applications similar to Twitter (twitter) are also developing and growing. [0003] Weibo is the abbreviation of micro blog, which has high efficiency of information transmission and low threshold. Through Weibo, users can disseminate and transm...

AI Technical Summary

Problems solved by technology

[0006] (1) It is difficult to accurately obtain the spam sample library:

[0007] Generally, the spam sample library can only be discovered manually or by some other behavior detection algorithms. The discovery time is often delayed by several hours, and there are cases of misjudgment.

This has a great impact on the integrity and accuracy of the sample, which directly leads to a great deviation between the spam probability of each word and the real value

[0008] (2) Existing spam messages or advertisements do circumvention processing for word segmentation, resulting in the inability to correctly segment words:

As a result, the message becomes isolated words after word segmentation, which cannot be accurately matched with the words in the sample library

Images