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

Hybrid recommendation system and method based on multi-objective optimization

A multi-objective optimization and hybrid recommendation technology, applied in the field of multi-objective optimization, can solve problems such as single recommendation type and single interest circle of users, and achieve the effect of improving the solution effect.

Pending Publication Date: 2022-05-24
GUILIN UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A single different recommendation algorithm has shown good performance in different applications. Traditional recommendation algorithms only use the accuracy of the recommendation as the only measure of the recommendation results when making recommendations to users, although this recommendation method can accurately match The user's interest needs, but the type of recommendation is relatively single, and it is easy for users to fall into a single interest circle

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
  • Hybrid recommendation system and method based on multi-objective optimization
  • Hybrid recommendation system and method based on multi-objective optimization
  • Hybrid recommendation system and method based on multi-objective optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] The present invention provides the following technical solutions: a hybrid recommendation system based on multi-objective optimization and a method thereof, comprising the following steps:

[0043] S1: Hybrid recommendation model construction;

[0044] S2: Optimization target selection;

[0045] S3: Multi-objective optimization model construction;

[0046] S4: Use the weight to sort the results;

[0047] The step S1 specifically includes the following steps:

[0048] S1.1: Collect the data set to be analyzed, and construct the user item scoring matrix through the data set;

[0049] S1.2: respectively adopt the content-based recommendation algorithm and the collaborative filtering-based recommendation algorithm for recommendation, and generate an initial candidate list;

[0050] S1.3: weighted summation of the form items obtained by each recommendation algorithm to generate a corresponding candidate set of hybrid recommendation algorithms;

[0051] The objectives op...

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 mixed recommendation system and method based on multi-objective optimization. The method comprises the following steps: acquiring data required by a recommendation system and establishing a corresponding data set; generating a mixed recommendation algorithm candidate set according to a plurality of indexes such as accuracy, novelty, diversity and recall rate of recommendation by using a mixed recommendation method; modeling the plurality of evaluation indexes into a multi-objective optimization problem, and converting a recommendation problem of the plurality of evaluation indexes into a high-dimensional multi-objective optimization problem; and improving a multi-objective optimization method, and selecting a recommendation set which most meets user requirements from the plurality of mixed recommendation algorithm candidate sets. According to the invention, the multi-objective optimization mixed recommendation method is applied to the recommendation system, so that a plurality of recommendation results can be recommended to the user more accurately, and the demand of the recommendation results of the user is better met.

Description

technical field [0001] The invention relates to the field of multi-objective optimization, in particular to a multi-objective optimization-based hybrid recommendation system and a method thereof. Background technique [0002] With the rapid development of Internet technology, the scale of network information has grown exponentially. The vast and complex network information allows us to obtain more diverse information, but how to allow users to accurately obtain the information they want from the massive information has become a difficult problem. From the perspective of information providers, how to accurately availability to users who are interested in them is also a challenge. In this case, recommender systems come into being. [0003] The recommender system does not require users to express their needs clearly, but presents some information that users may be interested in by analyzing users' historical behaviors. In recent years, recommendation systems have shown good ...

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): G06F16/9535G06F16/958G06F30/27G06N3/00G06F111/06
CPCG06F16/9535G06F16/958G06F30/27G06N3/006G06F2111/06
Inventor 陈基漓徐荣安谢晓兰王丽
Owner GUILIN UNIVERSITY OF TECHNOLOGY
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