Supercharge Your Innovation With Domain-Expert AI Agents!

Auto-encoder and clustering-based hybrid recommendation method

A technology of mixed recommendation and recommendation method, applied in the direction of neural learning method, computer parts, character and pattern recognition, etc., can solve problems such as not considered, and achieve the effect of improving accuracy

Active Publication Date: 2018-09-04
HUAIYIN INSTITUTE OF TECHNOLOGY
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not take into account the differences between user clusters after clustering

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
  • Auto-encoder and clustering-based hybrid recommendation method
  • Auto-encoder and clustering-based hybrid recommendation method
  • Auto-encoder and clustering-based hybrid recommendation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0063] like Figure 1-5 Show, the present invention comprises the steps:

[0064] (1) Combining user rating matrix with user demographic characteristics;

[0065] (2) Use an autoencoder to learn user features, and use the obtained user features to cluster users;

[0066] (3) Use MAE to calculate the most suitable recommendation method for each category of users, and combine the recommendation methods to obtain a hybrid recommendation model;

[0067] (4) Calculate the target user category, and use the hybrid recommendation model to get the recommendation result.

[0068] In step (1), the specific steps of combining the user rating matrix and user demographic characteristics are as follows:

[0069] (1.1) Let the user data set U={U1, U2,...,Un}, the project data set I={I1,I2,...,Im}, and the user's rating range for the project is [0,5];

[0...

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 an auto-encoder and clustering-based hybrid recommendation method. The method comprises the following steps of: combining score data and population statistical data of users tocarry out normalization, extracting feature data of the users by utilizing an auto-encoder, and clustering users by using a K-means++ clustering method; when the user have recommendation demands, combining the score data and the population statistical data of to-be-recommended users to carry out normalization, extracting features of the to-be-recommended users by utilizing the auto-encoder, classifying the to-be-recommended users by using the K-means++ clustering method, and finally recommending the users by using a recommendation method most suitable for the category. The method is capable of making up the condition that existing recommendation methods are poor in performance on sparse matrixes, and effectively improving the recommendation correctness.

Description

technical field [0001] The invention belongs to the technical field of feature extraction and recommendation methods, in particular to a hybrid recommendation method based on autoencoder and clustering. Background technique [0002] With the continuous development of information technology, the information on the Internet has grown exponentially, and users cannot quickly find the information they want on the Internet. This is the problem of "information overload". Both academia and industry are constantly exploring ways to improve the quality of information services and solve the problem of "information overload", thus giving birth to personalized recommendation technology. In recent years, according to the needs of different recommendation systems, researchers have proposed corresponding personalized recommendation schemes, such as content-based recommendation, collaborative filtering, association rules, utility recommendation, combination recommendation, etc. [0003] The...

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): G06F17/30G06K9/62G06N3/04G06N3/08
CPCG06N3/088G06N3/045G06F18/23213
Inventor 朱全银赵阳胡荣林李翔严云洋冯万利周泓王啸瞿学新潘舒新
Owner HUAIYIN INSTITUTE OF TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com