Recognition feature library acquisition method and device as well as short message identification method and device

Abstract

The invention provides a recognition feature library acquisition method and a device as well as a short message identification method and a device. The recognition feature library acquisition method comprises the following steps of: forming a sample seat by utilizing a plurality of short messages with predefined message types from a user; carrying out character string extraction on each short message in the sample set to obtain a first character string set, wherein character strings in the first character string set are different; counting the quantity of the short messages including the corresponding character string in the sample set according to each character string in the first character string set; calculating mutual information of each character string corresponding to each type of the short message according to a counting result; and according to the sequence of the mutual information from large to small, selecting part of or whole character strings in the first character string set to form a recognition feature library. The efficiency of recognition of the short messages is improved.

Description

technical field [0001] The invention relates to a short message recognition technology of a communication network, in particular to a method and a device for obtaining a recognition feature library, and a short message recognition method and device. Background technique [0002] The Ministry of Industry and Information Technology of the People's Republic of China has always paid close attention to the treatment of spam text messages, requiring all operators to carry out targeted self-inspection and self-correction nationwide, effectively standardize business behavior, and resolutely stop various violations of laws and regulations and violations of user rights and interests. For operators and management departments, in addition to strict management, technical means are also necessary to control spam messages. [0003] Regarding the definition of spam text messages, benevolent people have different opinions, and wise men see wisdom. Except that text messages that are anti-Part...

AI Technical Summary

Problems solved by technology

[0004] In the existing technology, the interception of spam text messages on the operator side can only intercept text messages that are anti-Party and anti-country in content, affect the stability and unity of the country and the people, pornographic text messages that hurt social morality, and spam that exceed the threshold in the traffic of the main sending number SMS interception

It is impossible to carry out from the perspective of individual mobile phone users, unique and personalized spam interception, and if a unified standard is used to deal with it, for some users, it may cause accidental deletion or the effect of no deletion , resulting in low processing efficiency, as illustrated below

[0005] Assume that for user A, he does not like a certain artist X extremely, and for user B, he likes X extremely, if there is a piece of news about X that needs to be pushed to the user in the form of a short message, in this case Next, if a unified criterion is set, or the news is judged as spam, the short message will not be sent, which will mistakenly delete the message that B wants, or the news will be sent to A and B, but in A’s view, this is spam Short message, both methods have the disadvantage of low efficiency

Images