Method, device, electronic equipment and storage medium for determining a target label

Abstract

A method, device, electronic device, and storage medium for determining a target tag disclosed in an embodiment of the present application, the method includes acquiring an object set and an attack data set, and the objects in the object set and the attack data subsets in the attack data set are one by one Correspondence, and according to the attack data set, determine the associated data set corresponding to the object set. The objects in the object set correspond to the associated data subsets in the associated data set. The associated data subset includes the social account information and network information of each object. Browse the information, and then determine the target label information of each object in the object collection according to the attack data collection and the associated data collection. Based on the embodiment of the present application, by combining the attack data set, social account information and web browsing information to determine the target label of the object, not only can enrich the label information of the object, improve the user's portrait, but also improve the accuracy of determining the identity information of the object.

Description

technical field [0001] The invention relates to the field of computer networks, in particular to a method, device, electronic equipment and storage medium for determining a target label. Background technique [0002] In the era of big data, all the data of any system can be used as a resource to discover the correlation relationship between data. Nowadays, big data has been widely used in Internet advertising push, user personalized service, etc., providing powerful data support for Internet services. [0003] User portrait, also known as user role, is an important application of big data technology by establishing descriptive label attributes for users in multiple dimensions, and then using these label attributes to outline users' various personal characteristics. [0004] The existing methods for determining target tags mainly include two types. One is to profile users based on their basic information, consumption behavior, and network behavior. However, the user portrait...

AI Technical Summary

Problems solved by technology

[0004] The existing target label determination methods mainly include two types. One is to profile the user based on the user’s basic information, consumption behavior, network behavior, etc. However, the user portrait obtained based on this method is not complete

The other is to directly call the user portrait model as the portrait model corresponding to different users. This method is prone to situations where the user portrait cannot completely match the user, resulting in inaccurate inference of big data.

Images