Method and device for identifying styles of commodities

Abstract

The invention provides a method and a device for identifying styles of commodities. The method includes acquiring sample pictures of the commodities and processing the sample pictures according to preset modes to obtain sample training sets; initializing parameters of preset deep convolutional neural networks and training the sample pictures in the sample training sets in the deep convolutional neural networks with the initialized parameters to obtain picture style identification models; identifying pictures of the to-be-identified commodities by the aid of the picture style identification models to obtain probability vectors for indicating that the pictures of the to-be-identified commodities belong to different style types; identifying the style types of the to-be-identified commodities according to set commodity style judgment rules and the probability vectors. The sum of the probability vectors is 1. According to the technical scheme, the method and the device in an embodiment of the invention have the advantages that the style types of the commodities can be automatically and accurately identified, accordingly, the commodity style identification accuracy and efficiency can be improved, and the work intensity can be relieved for operation personnel.

Description

technical field [0001] The present application belongs to the technical field of image information processing, and in particular relates to a method and device for recognizing the style of commodities. Background technique [0002] With the development of the Internet consumption era, consumers can choose their favorite products online, which greatly facilitates users to shop. For example, consumers can choose their favorite product types through the product pictures displayed by online merchants. [0003] Generally, when consumers purchase goods online, they are often influenced by various conceptual factors, such as brand, price, color, style, etc. These conceptual factors can generally be manually set by the merchant on the service operation platform. Among the many conceptual factors, some factors such as clothing brand, price, color, etc. are usually easy to define, and generally have relatively clear and standardized boundaries for distinction. For some other commodi...

AI Technical Summary

Problems solved by technology

However, both merchants and consumers will often have large deviations due to subjective factors when judging the style type of the product to be filled in. Therefore, concepts such as product style type often cause confusion and ambiguity among merchants and consumers. Affect the style classification of merchant products or the selection of consumer product styles, reducing the effect of product marketing

This not only affects the transaction conversion rate, but also reduces the user experience

At the same time, due to the wide variety of online products, generally the amount of information involved in the processing of product styles is relatively large, which will also consume a lot of working time and labor of operators

[0004] In the prior art, the use of manual subjective judgment to identify product styles often leads to large differences in product style recognition results, making it difficult to perform accurate, reasonable and unified style recognition

At the same time, the judgment method of manual recognition has also increased the work intensity of the operator's commodity style recognition and reduced the efficiency of commodity style recognition

Images