Unlock instant, AI-driven research and patent intelligence for your innovation.

Personalized recommendation algorithm based on clustering algorithm with adaptive growth of number of clusters

A clustering algorithm and self-adaptive technology, applied in computing, computer parts, instruments, etc., can solve the problem of determining the optimal number of clusters in a lot of time, and the number needs to be manually specified in advance, to achieve high accuracy and reduce time.

Inactive Publication Date: 2017-08-25
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The MGSoC algorithm completes the self-adaptive growth of the number of clusters, which to a certain extent solves the problem that the number of clusters in the prior art needs to be manually specified in advance, and it takes a lot of time to determine the optimal number of clusters

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 algorithm based on clustering algorithm with adaptive growth of number of clusters
  • Personalized recommendation algorithm based on clustering algorithm with adaptive growth of number of clusters
  • Personalized recommendation algorithm based on clustering algorithm with adaptive growth of number of clusters

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The personalized recommendation algorithm of the clustering algorithm based on the self-adaptive growth of the number of clusters disclosed by the present invention includes two stages of clustering-based incremental learning and recommendation.

[0043] The overall flowchart of the personalized recommendation algorithm is as follows: figure 1 shown.

[0044] The specific implementation manner of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0045] 1. Initialization

[0046] This part corresponds to figure 1 In S1, see the detailed flow chart figure 2 .

[0047] S1: Initialization

[0048] S1.1: Initialize parameter set

[0049] 1) Assign values ​​to the number of users n and the number of items p according to the actual situation;

[0050] 2) The user of the algorithm specifies the initial number of clusters K, learning rate η, convergence threshold α, error threshold β, length d of the interval after l...

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 personalized recommendation algorithm based on a clustering algorithm with adaptive growth of the number of clusters. The algorithm includes two stages of cluster-based incremental learning and recommendation. The cluster-based incremental learning stage includes three parts: 1) clustering using an MWOSK-means algorithm provided by the invention; 2) realizing adaptive growth of the number of clusters using an MGSoC algorithm provided by the invention; and 3) performing incremental update. The recommendation stage is based on the result in the previous stage, and personalized recommendation is carried out using the collaborative filtering recommendation algorithm fused with a user weight. Compared with an existing recommendation algorithm in which clustering comes before collaborative filtering, the recommendation algorithm provided by the invention has the advantages of being high in accuracy, capable of adaptively determining the number of clusters, applicable to incremental learning, and so forth.

Description

technical field [0001] The invention relates to the problem of personalized recommendation in data mining, in particular to the field of cluster-based personalized recommendation in data mining. Background technique [0002] Personalized recommendation is to recommend information and products that the user is interested in based on the user's interest characteristics and purchase behavior. Collaborative filtering algorithm is a commonly used algorithm in personalized recommendation. Clustering before collaborative filtering recommendation is beneficial to solve the problems of large search space, low accuracy and sensitivity to sparse data. [0003] Clustering is the process of gathering objects with high similarity into clusters. In personalized recommendation, clustering technology can be used to cluster objects with high similarity, and then the cluster information can be used in the recommendation algorithm. However, most of the current personalized recommendation alg...

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): G06K9/62
CPCG06F18/23211
Inventor 杨波袁磊
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA