User personalized preference mining method based on text and image

A user and text technology, applied in the field of user personalized preference mining, can solve the problem of ignoring the limitation of user preference

Active Publication Date: 2021-06-08
HEFEI UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the existing technology ignores the limitation of user preferences. According to the attention theory, users cannot be interested in all pref

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 personalized preference mining method based on text and image
  • User personalized preference mining method based on text and image
  • User personalized preference mining method based on text and image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In this embodiment, as figure 1 As shown, a text- and image-based user personalized preference mining method is carried out as follows:

[0055] Step 1. Construct a user set U={1,2,…,u,…,|U|}, where u represents the uth user, and |U| represents the number of users;

[0056] Step 1.1. Obtain the product pictures and product text descriptions purchased by |U| users respectively, which constitute a user-purchased product information set D, where the product text description set is represented as D w , the product image collection is denoted as D v ;

[0057] Step 1.2, remove the product text description set D w All punctuation marks, stop words, and low-frequency words in the preprocessed product text description collection Among them, N u Indicates the number of all unique words in the purchase record of the uth user, W un Indicates the nth word in the uth user's purchase record; n=1,2,...,N u ;

[0058] Step 1.3, for product image collection D v All images in t...

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 personalized preference mining method based on texts and images, which comprises the following steps of: 1, constructing a user set and extracting product text description information and image information in product information purchased by users, 2, designing a parametric Bayesian model STILT (SparseTextand Image Link Topic) modeling preference content and user interest content, and 3, carrying out parameter inference by using a collapse type Gibbs sampling algorithm. According to the method, the personalized preference of the user can be effectively mined in combination with the multi-modal data of the pictures and the texts, and the user preference is focused in a certain range, so that the comprehensiveness, the accuracy and the rapidness of user personalized preference mining can be improved, accurate recommendation for the user is facilitated, and a personalized recommendation strategy is formulated.

Description

technical field [0001] The invention relates to the technical field of user personalized preference mining, in particular to a text and image-based user personalized preference mining method. Background technique [0002] User preference refers to the user's preference for a commodity or commodity combination, which reflects the user's personal needs and interests. Due to the lack of direct contact between users and products in online shopping, product descriptions and pictures have become the main way for users to understand products. This information directly affects user decision-making, so it is indispensable to combine text and images to mine users' personalized preferences. [0003] Pictures and texts have become the main sources of information for online users to purchase products. The product information that users browse and purchase provides rich resources for discovering users' personalized needs. However, in the current state of the art, when mining users' pers...

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): G06F16/9535G06Q30/06
CPCG06F16/9535G06Q30/0601G06Q30/0631Y02D10/00
Inventor 姜元春李怡钱洋刘业政孙见山柴一栋梁瑞成周永行贺菲菲刘心语
Owner HEFEI UNIV OF TECH
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