User commodity information pushing method and equipment based on image attribute extraction

A product information and attribute extraction technology, applied in the computer field, can solve the problem of insufficient vertical accuracy of user product recommendation, and achieve the effect of avoiding single push content, comfortable shopping experience, and accurate recommendation.

Inactive Publication Date: 2018-02-23
广州唯品会研究院有限公司
View PDF10 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of insufficient vertical accuracy in user commodity recommendation in the prior art, the embodiment of the present invention provides a method and device for pushing user commodity information based on image attribute extraction

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
  • User commodity information pushing method and equipment based on image attribute extraction
  • User commodity information pushing method and equipment based on image attribute extraction
  • User commodity information pushing method and equipment based on image attribute extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] An embodiment of the present invention provides a method for pushing user commodity information based on image attribute extraction, such as figure 1 As shown, the method includes:

[0066] S101: Obtain an instruction that triggers recommendation;

[0067] The instructions can be passive triggers based on the system or active triggers based on the user. Compared with simply typing text and searching in the database, the above instructions can provide richer information, such as pictures, the combination of pictures and text information, etc., to avoid The existing technology simply considers the limitations of commodity text description information, uses image information as the information source of search, avoids ignoring other characteristics of commodities, and realizes more comprehensive and accurate recommendations;

[0068] S201: extracting product attributes according to the above instructions, and searching for target products including the above product attri...

Embodiment 2

[0077] The present invention provides a method for pushing user product information based on image attribute extraction, such as figure 1 As shown, the method includes:

[0078] S101: Obtain an instruction that triggers recommendation;

[0079] Wherein, the instruction to trigger the recommendation in S101 includes a system-based or merchant-based passive trigger instruction S101a and a user-based active trigger instruction S101b;

[0080] Specifically, the passive trigger instructions include weather, seasons, birthdays, festivals or system-defined special dates;

[0081] The active trigger instruction S101b also includes:

[0082] S102: The user inputs preset scene information on the e-commerce platform, and the preset scene information is a picture, text or a combination of picture and text information.

[0083] S201: extracting product attributes according to the above instructions, and searching for a target product including the above product attributes from the creat...

Embodiment 3

[0115] An embodiment of the present invention provides a device for pushing user commodity information based on image attribute extraction, such as Figure 4 shown, including:

[0116] The scene identification module 41 is used to identify the preset scene information input by the user on the e-commerce platform, and the preset scene information includes a picture, text or a combination of picture and text information;

[0117] The obtaining module 42 is used to obtain the text information and picture information of the products that the user is interested in in the information database of the e-commerce platform, and obtain the user / commodity basic information table;

[0118] Image feature extraction module 43, for utilizing pre-trained neural network to extract the image feature of commodity; Described image feature extraction module comprises image color extraction unit, image shape extraction unit, image texture extraction unit;

[0119] The commodity attribute definition...

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 user commodity information pushing method based on image attribute extraction. The user commodity information pushing method is characterized by comprising the steps of: acquiring an instruction for triggering a recommendation; extracting commodity attributes according to the instruction, and searching target commodities comprising the commodity attributes in a user interest library; and forming a recommended commodity list and pushing commodity information to a user. The invention further discloses user commodity information pushing equipment using the user commodityinformation pushing method. The user commodity information pushing method is simple and convenient, the user commodity information pushing equipment is compact in structure, a relatively perfect userpersonalized database is established by combining picture attributes of the commodities with a knowledge graph, and precise pushing of similar commodities is realized by adopting collaborative filtering based on the user and the commodities, thereby bringing the fresh and comfortable shopping experience to the user.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for pushing user commodity information based on image attribute extraction. Background technique [0002] In recent years, e-commerce has entered a high-speed stage of vigorous development. While some large-scale B2Cs are flocking to the capital market, some shopping guide platforms focusing on B2Cs are also emerging. The early stage of the development of the e-commerce shopping guide platform is mainly to simply provide users with traffic guidance and product recommendations, and there are many female groups in the focused market, so it cannot fully meet the shopping needs of users. In the later period, we have been working hard to be more vertical and precise in positioning, in order to recommend products with strong needs specifically for users, so that the recommended products fully meet the needs of users, thus making them more accurate and 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 Applications(China)
IPC IPC(8): G06Q30/06G06F17/30
CPCG06Q30/0631G06F16/5838G06F16/9535
Inventor 董亚楠崔燕红刘宇黄惠燕
Owner 广州唯品会研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap