Garment matching method and system based on attention knowledge extraction as well as storage medium

Abstract

The invention discloses a garment matching method and system based on attention knowledge extraction as well as a storage medium. The method comprises the following steps: acquiring garment matching data of a fashion community website, and extracting a garment matching rule; constructing a student network: acquiring jacket visual features, jacket text features, pants visual features and pants textfeatures; modeling semantic relationships of different modes by using a multi-layer perception machine based on the acquired features; calculating the compatibility between each jacket and pants according to modeling results; building a student network based on the obtained compatibility by using a Bayesian personalized sorting algorithm; building a teacher network: building a constraint functionof the garment matching rule according to the compatibility between each jacket and pants; realizing confidence allocation of different garment matching rules by using an attention mechanism; building the teacher network according to the constraint function and the confidence of the garment matching rule; and training the student network by the teacher network, and performing garment matching byusing the trained student network.

Description

technical field [0001] The invention relates to a clothing collocation method, system and storage medium based on attention knowledge extraction. Background technique [0002] With the vigorous development of the fashion industry, how to match a suitable suit from a wide range of clothing has gradually become a headache for everyone. Fortunately, many fashion community websites such as Polyvore have emerged, where fashion lovers can share their clothing matching results, which provides researchers with a large amount of real data. In recent years, there have been many research works around clothing matching and recommendation. Existing techniques mainly apply deep learning to extract features from clothing images or texts, and then model the compatibility between complementary clothing. However, the field of clothing collocation has accumulated a wealth of domain knowledge, but the existing technology mainly uses data-driven deep learning methods, which rely on a large amo...

AI Technical Summary

Problems solved by technology

However, the field of clothing collocation has accumulated a wealth of domain knowledge, but the existing technology mainly uses data-driven deep learning methods, which rely on a large amount of label data, and do not make full use of the domain knowledge or collocation rules of clothing collocation, which makes the model less interpretable

Images