Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Personalized recommendation method based on labels and time information

A technology of time information and recommendation methods, which is applied in the direction of digital data information retrieval, special data processing applications, instruments, etc., can solve the problems of decreased recommendation accuracy and weakness, so as to improve recommendation accuracy, solve over-fitting problems, and improve user satisfaction degree of effect

Inactive Publication Date: 2019-08-30
ZHEJIANG GONGSHANG UNIVERSITY
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing recommendation techniques are weak in dealing with the sparsity of rating data, which is unique to most recommender systems, resulting in a decrease in recommendation accuracy. Therefore, how to train an effective recommender system model in the case of highly sparse data is still a major issue. challenge

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
  • Personalized recommendation method based on labels and time information
  • Personalized recommendation method based on labels and time information
  • Personalized recommendation method based on labels and time information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The above and other technical features and advantages of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them.

[0023] refer to Figure 1-8 As shown, a personalized recommendation method based on tags and time information, including the following steps:

[0024] Step 1: When the user enters the system platform, the system platform will automatically collect the user's historical behavior data, and collect, store and classify the data. The specific method is as follows: Figure 8 shown;

[0025] Step 2: The system records the collected historical behavior data as user tags and generates data for analyzing user preferences;

[0026] Step 3: The system rates user tags according to the preset rating criteria, and then generates tag novelty by recording tag generation frequency, and then generates 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 provides a personalized recommendation method based on labels and time information. The method comprises the following steps of 1, collecting the user history behavior data, obtaining the label preferences of the user according to the historical behavior of the user according to the rating, the label and the time information, then estimating the correlation between the label and theproject based on the frequency and the time effect of the label, and finally performing prediction rating on the preference model data by utilizing a matrix factor decomposition algorithm, and performing personalized recommendation on the user. According to the method, the problem of over-fitting caused by the sparse rating data can be effectively solved by adopting a cofactor decomposition methodcombining the time information and the label data, and the effectiveness of the recommendation result and the user satisfaction can be effectively improved.

Description

technical field [0001] The invention belongs to the field of information recommendation, and in particular relates to a personalized recommendation method. More specifically, a personalized recommendation method based on tags and time information is proposed. Background technique [0002] With the development of social networks and e-commerce platforms, it has led to the phenomenon of information overload, making it difficult for users to obtain information, products and services that meet user needs. In addition, user experience and purchase conversion rates drop significantly when users are faced with too many irrelevant choices. In this context, as a personalized information filtering tool, the recommendation system plays an increasingly important guiding role in solving information overload and helping users find the information they really need. Nowadays, in order to improve service quality, recommender systems have been applied to various fields of the Internet, such ...

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): G06F16/9535G06F16/9536
CPCG06F16/9535G06F16/9536
Inventor 陈佳佳刘东升郑一明陈鸿斌陈向楠刘彦妮陈亚辉
Owner ZHEJIANG GONGSHANG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com