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

Evaluation method and device for recommendation effects

Active Publication Date: 2017-11-24
TENCENT TECH (BEIJING) CO LTD
View PDF11 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, since different people have different understandings of the importance of certain indicators in different scenarios, it is difficult to use the same indicators to make direct horizontal comparisons
Therefore, it is impossible to draw comparable and consistent conclusions on the recommendation effect
In addition, for different algorithm strategies, various long-term indicators may also contradict each other
Therefore, it is difficult for current evaluation algorithms to effectively compare and evaluate different recommendation strategies.

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
  • Evaluation method and device for recommendation effects
  • Evaluation method and device for recommendation effects
  • Evaluation method and device for recommendation effects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and examples.

[0028] figure 1 It is a schematic diagram of the implementation environment involved in an embodiment of the present invention. see figure 1 , the recommendation effect evaluation system 100 includes: a client 110 - 1 . . . a client 110 -N and a server 120 . Wherein, the server 120 further includes a user database 121 , a recommendation effect evaluation sub-server 122 , an offline algorithm iteration sub-server 123 and a recommendation engine 124 .

[0029] In an embodiment of the present invention, the recommendation engine 124 in the server 120 determines the content recommended to the user and sends it to the clients 110-1...110-N. In a specific application, depending on whether the users are all users or a part of the user group, the recommended...

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 an evaluation method and device for recommendation effects. The method includes the steps of in the process of recommending content to multiple users on the basis of one recommendation policy, obtaining behavior data of each user, which is generated according to the recommended content, wherein the behavior data includes the values of multiple behavioral indicators during a waiting time quantum before evaluation; for each behavioral indicator, determining the ranking of one user in a to-be-estimated user group according to the value of each user in the behavioral indicator; according to the ranking and the weight of each behavioral indicator, figuring out the first health degree of each user in the to-be-estimated user group; according to the first heath degrees, figuring out a recommendation effect index corresponding to the recommendation policy. According to the evaluation method and device for the recommendation effects, one single recommendation effect index can be provided for evaluation of different recommendation policies, and therefore the resource utilization rate of a server can be improved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method and device for evaluating recommendation effects. Background technique [0002] In Internet applications, recommendation applications can recommend various types of content to users. For example, news applications push news content in various fields such as entertainment, sports, and finance to users every day. [0003] When evaluating the recommendation effect of recommended applications, it is usually based on multiple long-term indicators, such as user retention rate over a period of time, average daily / weekly active users, average refresh times, etc. When evaluating different recommendation strategies, the performance of each long-term indicator needs to be considered comprehensively. [0004] However, since different people have different understandings of the importance of some indicators in different scenarios, it is difficult to use the same indicators to ...

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
CPCG06F16/9535
Inventor 范欣李海青郑坚
Owner TENCENT TECH (BEIJING) 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