User interest portrait construction method and device, storage medium and computer device

Abstract

The invention discloses a user interest portrait construction method and device, a storage medium and a computer device. The method comprises: acquiring text information browsed by a user on a webpagecorresponding to a preset website; constructing a text feature word vector set by utilizing the text feature word vectors extracted from the text information; according to the text feature word vector set and a preset interest word vector, calculating interest similarity between the preset interest word vector and the text feature word vector set; and according to the interest similarity, constructing an interest portrait of the user. Compared with an existing user interest portrait construction mode, the method has the advantages that the user portrait category does not need to be preset, the feature data standard does not need to be formulated, the similarity between the preset interest word vector and the text feature word vector set can be calculated to determine the user portrait only by presetting specific interest words, and the construction efficiency of the user portrait is improved.

Description

technical field [0001] The present application relates to the technical field of data analysis, and in particular to a method and device, a storage medium, and a computer device for constructing a user interest profile. Background technique [0002] With the rapid development of network technology, the Internet has become a common information acquisition platform for users. For merchants, it is an important means to improve service quality by using users' online information to understand users and provide users with more suitable services or products. At present, user information is often learned by constructing user portraits. Among them, the user portrait is a virtual representative of a real user, which can display the attribute information of the user. [0003] The existing user portrait construction methods mostly use supervised classification methods, which need to preset the categories of user portraits, and give the corresponding standard feature data of each categ...

AI Technical Summary

Problems solved by technology

[0003] The existing user portrait construction methods mostly use supervised classification methods, which need to preset the categories of user portraits, and give the corresponding standard feature data of each category of user portraits, so as to compare the actual feature data of the target user with the standard feature data. relationship to determine the portrait of the target user. However, in practical applications, the standard feature data is extremely difficult to determine, and the efficiency and accuracy of user portrait construction are low.

Images