Message identification method and device, equipment and storage medium

Abstract

The invention provides a message identification method and device, equipment and a storage medium, and belongs to the technical field of Internet. The method comprises the following steps of: for a message generated based on a template, obtaining a fingerprint sample of the template, namely a plurality of reference character strings capable of representing edited text contents in the message, and matching the fingerprint sample with corresponding character strings in the message so as to determine whether the message belongs to a target type or not. According to the method, the calculation amount of data processing in the message recognition process is reduced by adopting matching between the character strings representing the editing text content, a large amount of model calculation is not needed, the maintenance cost of the fingerprint sample is low, and in the mode, the characteristics of similar or same grammar structures of the messages generated based on the message template are fully utilized, so that the message recognition efficiency is improved. The matching accuracy is high, and the accuracy and efficiency of message identification are improved.

Description

technical field [0001] The present application relates to the technical field of the Internet, and in particular to a message identification method, device, equipment and storage medium. Background technique [0002] With the development of computer technology and the diversification of terminal functions, social applications provide a social platform that facilitates communication among users, and the purpose of communication can be achieved through message interaction on the social platform. For example, the social platform provides a template-based message interaction method. Users can call the fixed template provided by the social platform, and based on the typesetting and information types specified by the fixed template, edit it on the basis of the fixed template in order to generate The message to be pushed. Some malicious users will use this type of information to carry out some malicious actions, such as advertising, fraud, etc., causing unnecessary harassment to u...

AI Technical Summary

Problems solved by technology

[0004] In the above process, due to the large order of magnitude of the messages to be recognized, the server has a large amount of calculation in the process of recognition, which requires a large amount of data processing resources. Moreover, since the complete text of the message is recognized, there will be a lot of redundant information in it. Remaining information, such as format information, leads to low recognition accuracy and efficiency

Images