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

A Combined Coding-Based Collaborative Ranking Recommendation Method

A recommendation method and coding technology, which is applied in the fields of instrumentation, computing, and electrical digital data processing, etc., can solve problems such as inconsistency between optimization goals and recommendation goals, insufficient binary code expression ability, etc., and achieve slow convergence speed, improved performance, and fast convergence speed effect

Active Publication Date: 2022-03-18
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention solves the problem of insufficient expression ability of traditional binary codes and the inconsistency between the optimization target and the recommendation target of the existing method based on combined coding, and aims to improve the efficiency and accuracy of recommendation

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
  • A Combined Coding-Based Collaborative Ranking Recommendation Method
  • A Combined Coding-Based Collaborative Ranking Recommendation Method
  • A Combined Coding-Based Collaborative Ranking Recommendation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The purpose and effects of the present invention will become more apparent by describing the present invention in detail below in conjunction with the accompanying drawings.

[0045] The present invention provides a collaborative ranking recommendation method based on combined coding, which includes a training stage and an online recommendation stage.

[0046] The training process is as figure 1 As shown, the specific steps are as follows:

[0047] (1) if image 3 As shown, select the anchor point.

[0048] (1.1) m users and n items form a scoring matrix M∈R m×n , use A={(u,i)|M ui >0} to represent the set pair of users and items corresponding to each rating in M; among them, u=1~m, i=1~n, M ui Indicates user u's rating on item i;

[0049] (1.2) Use the collaborative filtering algorithm on M to get the user's initial real-valued feature vector u 0 and the initial real-valued eigenvector i of the item 0 ; Then use the k-means clustering algorithm to select G anchor...

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 present invention disclosed a synergistic sort recommendation method based on a combination coding, trying to make full use of the accuracy of the real -value vector and the efficiency of binary vectors without affecting the performance of the model.The accuracy and efficiency of the method.In order to obtain the final goal of the recommended result of the recommended system, the CCCR uses a pair of sorting loss functions to make the method better perform on the sorting indicators.In order to obtain faster convergence and better convergence results than the traditional discrete coordinate decline method, CCCR uses a new and efficient optimization method, and uses the overall update binary vector instead of renewal.Finally, the experimental results on the open dataset show that while maintaining the efficiency of retrieval and training, the CCCR significantly improves the accuracy of the results in the top -K recommendation task.

Description

technical field [0001] The invention belongs to the field of discrete recommendation, in particular to a collaborative sorting recommendation method based on combined coding. Background technique [0002] In recent years, recommendation systems have been widely used in many fields of the Internet, such as e-commerce, social media, news streaming platforms, etc. In these scenarios, the main role of recommendation systems is to dig out Items that users are potentially interested in are recommended to users, thereby improving user experience and platform traffic and advertising revenue. [0003] In order to improve the recommendation efficiency of algorithms in large-scale recommendation scenarios, a lot of research work has made a lot of efforts in this area in recent years. One of the research directions is the use of hashing methods. Different from the traditional use of real latent feature vectors to represent users and items, the hash method uses binary vectors to repres...

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 Patents(China)
IPC IPC(8): G06F16/9536G06K9/62
CPCG06F16/9536G06F18/23213
Inventor 卢涛刘成昊孙建伶
Owner ZHEJIANG UNIV
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