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

Mobile APP recommendation method based on weighted mixing

An APP recommendation and APP labeling technology, applied in the information field, can solve the problems of ignoring user behavior, unable to characterize user preferences, and excessive characterization of model validity problems, and achieve the effect of improving accuracy and diversity.

Active Publication Date: 2016-08-24
NANTONG UNIVERSITY
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a mobile APP recommendation method based on weighted mixing to solve the current content-based recommendation algorithm that only considers the similarity between information

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
  • Mobile APP recommendation method based on weighted mixing
  • Mobile APP recommendation method based on weighted mixing
  • Mobile APP recommendation method based on weighted mixing

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0043] The present invention will be further described in detail below in conjunction with the drawings.

[0044] Such as figure 1 As shown, the method of the present invention first analyzes user behavior for the processed mobile APP profile data and user APP download list data, and weights and quantifies the label data set downloaded by the user according to the analysis result, and then establishes a personalized label model , Use the personalized tag model to traverse all the candidate mobile APPs, calculate the user's prediction scores for the candidate mobile APPs, and finally get the recommendation list.

[0045] (1) User behavior analysis

[0046] The mobile APP downloaded by the user is classified according to the download source in the user's mobile APP download list data, and then the label data of the mobile APP downloaded by the user is weighted and quantified according to the classification result. First, analyze the user's behavior by analyzing the user's download sou...

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 mobile APP recommendation method based on weighted mixing, which comprises the following steps of: grabbing mobile APP label data and mobile APP brief introduction data, and carrying out data pre-processing together with user mobile APP download data; building an individualized label model aiming at the pre-processed mobile APP label data and user mobile APP download data, calculating forecast score by utilizing the model and obtaining a first recommendation list; building an LDA user model aiming at the processed mobile APP brief introduction data and user mobile APP download data, obtaining probability distribution of users in a theme by utilizing the model, calculating the similarity between the users by utilizing KL divergence and forming a second recommendation list; carrying out weighted mixing on the two recommendation lists to finally form a recommendation list. According to the method, two mutually independently methods are used for forming corresponding recommendation results, and the two recommendation results are finally subjected to weighted mixing; the advantages of the two methods are combined by a parallel weighted mixing manner, so that the accuracy and diversity of the recommendation result are improved.

Description

technical field [0001] The invention relates to the field of information technology, in particular to a mobile APP recommendation method based on weighted mixing for research on mobile APP personalized recommendation. Background technique [0002] With the rapid development of information technology and the Internet, mobile smart terminals have rapidly become popular as carriers of information services in recent years. The popularization of mobile smart terminals has brought about the rapid growth of the mobile APP market, and the installation of applications in several major application markets has also become more and more popular. The main application markets include: APP Store, Android Market and Windows Store, and have more users The number of mobile APPs in the APP Store and Android Market has exceeded one million. [0003] The rapid development of mobile APP has brought rich and varied choices to users, but it takes a lot of time for users to choose from a large numb...

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): G06F17/30G06Q30/02
Inventor 施佺肖瑶丁卫平陈建平杨晨晨
Owner NANTONG UNIVERSITY
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