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

System and method for recommending waste industries on basis of diversified mixed modes

A recommendation method and recommendation system technology, applied in the field of waste industry recommendation system, can solve the problems of insufficient accuracy and diversity of recommendation results, and achieve the effects of improving order conversion rate, improving accuracy, and increasing diversity

Inactive Publication Date: 2017-06-13
河北中废通网络技术有限公司 +1
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, simply using a certain recommendation algorithm has deficiencies in the accuracy and diversity of the recommendation results. In view of the existing problems, the present invention proposes a waste industry recommendation system and its method based on mixing multiple modes, which can make the recommendation results more accurate. , to better meet the needs of users

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
  • System and method for recommending waste industries on basis of diversified mixed modes
  • System and method for recommending waste industries on basis of diversified mixed modes
  • System and method for recommending waste industries on basis of diversified mixed modes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The personalized recommendation method mixing multiple modes of the present invention will be further described in detail below with reference to the accompanying drawings and the embodiments of the present invention.

[0041] The association recommendation in module A of the system mainly adopts the method of clustering and calculating similar products, which mainly includes the following processes:

[0042] 1) Create an entity class SimilarityData, set three fields row (row), column (column), similarityValue (similarity), wherein the main function of the entity class SimilarityData is a triplet, a certain element in the matrix, use To save the sparse matrix; the similarity described in it is more appropriate to set the minimum similarity to 0.8 through the training set test before performing the clustering calculation;

[0043] 2) Create an instance SimilarityData[][] allSimilarityData, which is used to save all similar data;

[0044] 3) Create an array int[] countAr...

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 system and a method for recommending waste industries on the basis of diversified mixed modes. The system mainly comprises modules A, modules B and modules C. Effects of three mixed recommending modes of correlation recommending, hotspot recommending and TopN recommending mode mainly can be realized by the modules A; effects of initializing recommendation results mainly can be realized by the modules B; effects of filtering, result sorting, recommending explaining and ultimate recommendation results mainly can be realized by the modules C. High weights are set for the correlation recommending and the TopN recommending for common users of websites, and secondary weights are set for the hotspot recommending for the common users of the websites; the high weights are set for the hotspot recommending for users without optional records, and adaptive population to which the users belong is analyzed, so that corresponding weights can be set for the correlation recommending. The system and the method in an embodiment of the invention have the advantages that recommendation results can be accurate, the purchase rates of recommended commodities can be increased, and accordingly the conversion rates of order forms of commodities can be increased.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a waste industry recommendation system based on mixing multiple modes and a method thereof. Background technique [0002] At present, with the explosive increase of network information, consumers are often at a loss when faced with numerous choices, unknown fields, and overloaded information; however, at the same time, product merchants are also struggling to find suitable users and the most convenient channels, and the best tool to solve these two types of contradictions is the recommendation system. [0003] Data is the foundation of all recommendation systems. Accurate data has a good recommendation effect, just like the title of an article does to the content of the article. Model-based collaborative filtering recommendation, based on sample user preference information, trains a recommendation model, and then predicts and calculates recommendations based on re...

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): G06F17/30G06Q30/06
Inventor 王清霞刘宁周国辉姜林
Owner 河北中废通网络技术有限公司
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