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

Interaction method aimed at explanation of recommendation system

A recommendation system and interaction method technology, applied in marketing and other directions, can solve problems such as unreasonable explanations, lack of explanations, and inability to obtain additional information of recommendation results, so as to reduce computational burden, reduce time overhead, and achieve accurate recommendation results. Effect

Inactive Publication Date: 2015-11-18
HEFEI UNIV OF TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most users cannot understand the recommendation principle of the recommendation system, and have no way to obtain additional information about the recommendation results
From the user's point of view, a recommendation system that lacks proper explanations or unreasonable explanations cannot gain users' trust

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
  • Interaction method aimed at explanation of recommendation system
  • Interaction method aimed at explanation of recommendation system
  • Interaction method aimed at explanation of recommendation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] An interactive method for explaining the recommendation system. In the explanation of the recommendation results of the recommendation system, the process of user intervention is added. In the module for explaining the recommendation results, the user intervention process adopts text input or label selection, which is convenient for the background to understand Classify the browsing or purchase records with the user-item as the data structure, so that the recommendation results of the recommendation system under different classifications can obtain higher conversion rates.

[0021] The specific steps of the text input or label selection adopted in the user intervention process are as follows:

[0022] (1) The system provides users with basic scene classification through label selection, and also provides users with text input windows;

[0023] (2) The established tags are sorted by the system according to the popularity of users for users to choose;

[0024] (3) Proces...

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 interaction method aimed at explanation of a recommendation system. In the explanation aimed at recommendation result of the recommendation system, a user intervention process is added, in a module for explaining the recommendation result, a text input mode or a label selection mode is used for the user intervention process, and thus, a background is helped to classify browsing or purchase records with a data structure of user-article, and conversion rate of the recommendation results of the recommendation system in different classifications can be higher. According to the invention, disadvantages of the prior explanation mechanism of the recommendation system are improved, consequently, internal logic of the recommendation system is more transparent and is not considered as a 'black box' by the users any more, and the recommendation results have a basis; meanwhile, by interaction between the recommendation system and the users, an aim of data cleaning can be realized, calculation load of the system can be reduced, the recommendation results are more accurate, and thus, trust of the users on the system is increased, the recommendation system is facilitated to quickly and accurately capture interest features of the users, and time overhead for the users to look up information is reduced.

Description

technical field [0001] The invention relates to the technical field of recommendation systems, in particular to an interactive method for explanation of recommendation systems. Background technique [0002] The emergence and promotion of the Internet has brought a large amount of information to users, satisfying users' needs for information in the information age. However, with the rapid development of the Internet, the amount of information on the Internet has increased significantly, making it impossible for users to obtain the part of information that is really useful to them when faced with a large amount of information, and the efficiency of using information is reduced instead. This is the so-called problem of information overload. [0003] The recommendation system is a very potential way to solve the problem of information overload, especially in the large-scale application of e-commerce, it recommends the information and products that the user is interested in to t...

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): G06Q30/02
Inventor 汤临春刘征宇史鹏健田昶宋亮陆国生
Owner HEFEI UNIV OF TECH
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