Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for recommending product pictures

A product recommendation and recommendation method technology, applied in business, data processing applications, sales/lease transactions, etc., can solve problems such as poor accuracy and inability to effectively recommend products required by users, and achieve the effect of improving accuracy

Active Publication Date: 2022-04-12
唯品会(海南)电子商务有限公司
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, products are generally recommended to users based on the user’s browsing and purchase of products in the purchase behavior, but the products recommended by these recommendation methods are not accurate enough to effectively recommend products that meet user needs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for recommending product pictures
  • Method and device for recommending product pictures
  • Method and device for recommending product pictures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] The embodiment of the present invention provides a method for recommending commodity pictures, which is applied to an e-commerce platform. Refer to figure 1 As shown, the method includes:

[0061] 101. Extract a plurality of tags from the product information input by the user that includes at least a product image.

[0062] Specifically, the product information only includes product pictures, and multiple tags are extracted from the product information including product pictures input by the user. The process may include:

[0063] Extract multiple image features in product images;

[0064] Get multiple labels corresponding to multiple image features.

[0065]Product information includes product pictures and text description information. Multiple tags are extracted from product information that includes at least product pictures entered by users. The process may include:

[0066] Extracting multiple image features in product images; and

[0067] Extract multiple keyw...

Embodiment 2

[0083] The embodiment of the present invention provides a method for recommending commodity pictures, which is applied to an e-commerce platform. Refer to figure 2 As shown, the method includes:

[0084] 201. When the commodity information input by the user only includes commodity pictures, multiple image features in the commodity pictures are extracted.

[0085] Wherein, the product picture may be obtained by the user by uploading a picture, taking a picture, or clicking on a picture.

[0086] Specifically, the process may include:

[0087] Preprocessing product images;

[0088] Extract multiple image features from the preprocessed product images.

[0089] In the embodiment of the present invention, the irrelevant information in the product picture is eliminated by preprocessing the product picture, such as filtering out interference, noise, and restoring useful real information, thereby ensuring the reliability of extracting image features in the product picture .

[0...

Embodiment 3

[0139] The embodiment of the present invention provides a method for recommending commodity pictures, which is applied to an e-commerce platform. Refer to Figure 4 As shown, the method includes:

[0140] 401. When the product information input by the user includes a product image and text description information, extract multiple image features in the product image and extract multiple keywords in the text description information.

[0141] Wherein, the product picture may be obtained by the user by uploading a picture, taking a picture, or clicking on a picture.

[0142] The text description information includes at least one of title information of the commodity, web page information of the commodity, or comment information of the commodity.

[0143] Specifically, extracting multiple image features in the product picture may include:

[0144] The product image is preprocessed, and multiple image features in the preprocessed product image are extracted.

[0145] The embodim...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method and device for recommending commodity pictures, belonging to the technical field of electronic commerce. The method includes extracting a plurality of tags from the product information input by the user, which at least includes a product picture; determining the tags associated with the user among the tags; obtaining a plurality of products to be recommended corresponding to the associated tags; Recommended products are recommended to users. The embodiments of the present invention can improve the accuracy of product recommendation, so that the products recommended to users are more in line with user needs.

Description

technical field [0001] The invention relates to the technical field of e-commerce, in particular to a method and device for recommending product pictures. Background technique [0002] With the popularization of the Internet and the maturity of e-commerce, people are increasingly using e-commerce platforms to obtain commodity information and purchase commodities. People hope that when purchasing commodities, the e-commerce platform can recommend various commodity information to users, such as recommending commodities that users may be interested in. Through product recommendation, the path for users to find the products they need can be shortened and the user experience can be improved. [0003] In the prior art, products are generally recommended to users based on the user's browsing and purchasing of products in the purchase behavior. However, the products recommended by these recommendation methods are not accurate enough to effectively recommend products that meet user ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q30/06
CPCG06Q30/0631
Inventor 崔燕红刘宇董亚楠黄惠燕
Owner 唯品会(海南)电子商务有限公司