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

Method and device for user behavior prediction and corresponding information recommendation

A prediction method and user technology, applied in the information field, can solve problems such as impossibility, insufficient data, time-consuming machine resources, etc.

Active Publication Date: 2018-02-27
ALIBABA (CHINA) CO LTD
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above model training takes a lot of time and machine resources, and cannot be done in the case of insufficient data

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
  • Method and device for user behavior prediction and corresponding information recommendation
  • Method and device for user behavior prediction and corresponding information recommendation
  • Method and device for user behavior prediction and corresponding information recommendation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0029] As mentioned in the background technology section, in information applications, such as news and content aggregation APPs, it is often necessary to make personalized recommendations to users based on their behavior attribute information, so as to recommend information that matches their browsing behaviors to users, and improve user experience. satisfaction. At present, when using algorithms such as collaborative filtering, matrix dec...

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 method and device for user behavior prediction and corresponding information recommendation. The method comprises the steps that based on n original labels of various users in a benchmark user group, multiple layers of label pairs are generated for the users, and the users in the benchmark user group are divided into multiple layers of label pairs of the users, so that multiple layers of label pair groups are generated; based on user behaviors in the multiple layers of label pair groups corresponding to the multiple layers of labels of the target user, the user behaviors of the target user are predicted; according to a prediction result, corresponding information can be recommended to the user. Therefore, compared with a predictive algorithm in the prior art, theprediction scheme achieves layer-by-layer delivery of characteristics by simply introducing the multiple layers of labels, so that not only can a lot of model training and machine resources be saved,but also the prediction and recommendation effects of actual use are improved.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a method, device, computing device and storage medium for predicting user behavior and recommending corresponding information. Background technique [0002] In information applications, such as news and content aggregation apps, user behavior attributes need to be analyzed based on specific algorithms in order to recommend relevant information to users that matches their browsing behavior, that is, personalized recommendations for users. The core technology of personalized recommendation is the article click probability prediction algorithm. At present, the common practice is to use collaborative filtering, matrix decomposition, LR sorting algorithm, etc. These algorithms need to train models based on user behavior data. The above model training takes a lot of time and machine resources, and cannot be done in the case of insufficient data. [0003] In view of the a...

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): G06F17/30
CPCG06F16/9535G06F16/955
Inventor 潘岸腾
Owner ALIBABA (CHINA) CO LTD
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