Supercharge Your Innovation With Domain-Expert AI Agents!

Mobile application recommendation method based on downloading behavior data and vector representation learning

A recommendation method and mobile application technology, applied in data processing applications, special data processing applications, electrical digital data processing, etc., can solve problems such as complexity, poor results, and large data volumes, and achieve low complexity and training speed. Fast and accurate results

Inactive Publication Date: 2018-04-27
SUN YAT SEN UNIV
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires a large amount of data, and it takes a long time to train a variety of data; if only a single type of data is trained, the results are often poor
Moreover, since this type of method is often complex, it is difficult to avoid the phenomenon of overfitting

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 application recommendation method based on downloading behavior data and vector representation learning
  • Mobile application recommendation method based on downloading behavior data and vector representation learning
  • Mobile application recommendation method based on downloading behavior data and vector representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be further described below in conjunction with specific embodiment:

[0053] See attached figure 1 As shown, the mobile application recommendation method based on download behavior data and vector representation learning described in this embodiment includes the following steps:

[0054] S1. Extract each user's downloaded App sequence {x from the user downloaded App record data 1 ,x 2 ,...,x k};

[0055] S2. Input the download sequence into the word2vec model to obtain the representation vector of each App, {a 1 ,a 2 ,...a N}, assuming that a is a T-dimensional vector, then it is normalized to obtain A=Norm(a);

[0056] The normalization steps are as follows:

[0057] Suppose n-dimensional vector a={a 1 ,a 2 ,...,a n}, the modulus of this vector is Then the normalized vector Norm(a)=a / |a|;

[0058] S3, each user's download sequence {x 1 ,x 2 ,...,x k The App in} corresponds to the corresponding vector, and the T*K matrix is ​​...

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 relates to a mobile application recommendation method based on downloading behavior data and vector representation learning. The method includes the steps that user downloading sequencesare extracted, then an App representation vector A is trained and obtained, and a representation vector R of user downloading behaviors is calculated; the representation result is obtained in the twomodes of A representation and R representation or R representation. According to the mobile application recommendation method based on downloading behavior data and vector representation learning, sequential data of user downloading App is used, information of App and feedback information of users are not required, and obtaining of data sources is relatively easy; meanwhile, the complexity of a model is low, the over-fitting phenomenon can be avoided, the accuracy is high, and the training speed is high.

Description

technical field [0001] The invention relates to the technical field of application recommendation, in particular to a mobile application recommendation method based on download behavior data and vector representation learning. Background technique [0002] Mobile applications (app for short) refer to applications designed to run on smartphones, tablet computers and other mobile devices. Today, smart mobile phones have become an indispensable part of modern life. With the rapid development of the mobile Internet, mobile phones have even surpassed computers to become the most important terminal for our daily access to the Internet. And using a phone is actually using a different mobile application. Different applications can help us achieve different needs. For example, payment apps can allow us to pay more conveniently; social apps can make it easier for us to communicate with friends; game apps can allow us to have good entertainment and so on. [0003] Mobile applicatio...

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
CPCG06Q30/0255G06Q30/0277G06F16/9535
Inventor 郑子彬叶泳坚周晓聪
Owner SUN YAT SEN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com