Picture recommendation method and device of social network

Abstract

The invention provides a picture recommendation method and device of a social network. The method comprises the following steps of: acquiring an uploaded picture; judging whether the uploaded picture is a figure picture or not; if the uploaded picture is the figure picture, selecting a figure picture from a picture database of the social network to serve as a contrast picture; if the uploaded picture is a non-figure picture, selecting a non-figure picture from the picture database to serve as a contrast picture; extracting a color feature value of the picture pixel of the uploaded picture; calculating a color feature distance between the uploaded picture and the contrast picture selected from the picture database; and recommending a relative picture to a user according to the magnitude of the color feature distance. According to the method, the operational complexity can be lowered for the user; the experience of the user to use the social network is improved; and the accuracy of the social network to recommend the picture is improved.

Description

technical field [0001] The invention belongs to the field of social networks, and in particular relates to a method and device for recommending pictures in a social network. Background technique [0002] At present, in some social networks (such as Pinterest, O2, Huapetal.com, Heidang.com, etc.), after a user shares his own picture on the website, the website can recommend to the user related to the picture or the Other pictures that users may be interested in and the owners of these pictures, so as to link users with similar tastes and preferences for pictures to form a network circle. [0003] figure 1 An existing picture recommendation method in a social network is shown. Such as figure 1 As shown, the social network includes a picture database 10, and the picture database 10 stores pictures such as a picture 11 and a picture label 11a, a picture 12 and a picture label 12a, a picture 13 and a picture label 13a and other pictures and their labels. The picture label is ...

AI Technical Summary

Problems solved by technology

[0004] The disadvantages of the existing picture recommendation methods in the above social networks are: ① When users share pictures, they need to manually mark the pictures, which increases the complexity of user operations and affects the user experience of using social networks; ② Because different users have different observations and understandings of the same picture, the picture annotations provided by each user are inevitably subjective, which will cause the non-objectiveness of the picture annotations and cause the pictures obtained by matching the image annotations to be inconsistent with the user's expectations. expectations, thus affecting the accuracy of website recommendations

Images