Method and device for establishing user interest base based on picture attribute extraction

A technology for extracting user interests and attributes, applied in the computer field, can solve problems such as the improvement and difficulty of accurately retrieving interested products, achieve novel and comfortable shopping experience, and achieve the effect of fast, convenient and accurate finding

Inactive Publication Date: 2018-03-30
广州唯品会研究院有限公司
View PDF7 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Moreover, existing e-commerce shopping guides generally use user search or classification queries to find target products, but it is not easy t

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 establishing user interest base based on picture attribute extraction
  • Method and device for establishing user interest base based on picture attribute extraction
  • Method and device for establishing user interest base based on picture attribute extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Embodiments of the present invention provide a method for building a user interest library based on image attribute extraction, such as figure 1 As shown, the method includes:

[0053] Obtain the commodity information of the commodity that the user is interested in in the information database of the e-commerce platform, and prepare the user / commodity basic information table. The user's buying habits and preferences; using product pictures as the basis for obtaining product information can be more intuitive, comprehensive and accurate.

[0054] Use the pre-trained neural network to extract the image features of the product in the user / product basic information table, obtain the semantic features corresponding to the above image features, and define the semantic features as product attributes;

[0055] The application of artificial intelligence in the field of image recognition provides a technical basis and an information basis for image recognition, image feature extra...

Embodiment 2

[0063] Embodiments of the present invention provide a method for building a user interest library based on image attribute extraction, such as figure 1 As shown, the method includes:

[0064] S1: Obtain the product information of the user's interested product in the e-commerce platform information database, and generate the user / product basic information table;

[0065] Among them, the specific method of obtaining the product information of the user's interested product in the e-commerce platform information database includes obtaining the product information of the user's interested product in the e-commerce platform information database according to the user's historical record on the e-commerce platform, and the generation of the historical record includes: But not limited to behaviors such as image search, browsing, purchase, and collection; further, the way to obtain product information of products of interest to users in the information database of the e-commerce platfor...

Embodiment 3

[0107] The invention also discloses a device for establishing a user interest library based on image attribute extraction, such as image 3 As shown, the equipment includes:

[0108] Obtaining module 31, is used for obtaining the text information and the picture information of the product that the user is interested in in the information database of the electric business platform, and makes the user / commodity basic information table; The specific steps include, according to the image search, browsing, purchase and collection records of the user on the e-commerce platform, obtaining the product information of the product of interest to the user in the information database of the e-commerce platform;

[0109] Wherein, the product information includes at least a product picture; in a specific embodiment, the user can obtain the product picture alone, or obtain a combination of the picture and the text.

[0110] The user / product basic information table can obtain the user's purch...

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 for establishing user interest base based on picture attribute extraction. The method comprises a step of acquiring commodity information of an interested commodity ofa user in an e-commerce platform information database, a step of extracting a picture feature of the commodity by using a pre-trained neural network, obtaining a semantic feature corresponding to theabove image feature, and defining the semantic feature as a commodity attribute, and a step of creating a user interest library with the commodity attribute as a basic knowledge unit and a relation between a commodity category and a commodity attribute type as a frame. The invention also discloses a device using the above method. The method of the invention is simple and easy to implement, the device structure is compact, through image object recognition and the combination of a knowledge map corresponding to an image, the description and search for a commodity which is difficult to describein a language are realized, and a novel and comfortable shopping experience is brought to the user.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for establishing a user interest library based on image attribute extraction. Background technique [0002] 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-friendly. [0003] Moreover, existing e-commerce shopping guides generally use user search or classification queries to find target products, but it is not easy to describe the styles of products such as the style of cl...

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
IPC IPC(8): G06Q30/06G06F17/30
CPCG06Q30/0631G06F16/35G06F16/367G06F16/583
Inventor 刘宇崔燕红董亚楠黄惠燕
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