Chinese tag recommendation correction method based on synonym and antonym

A technology of synonyms and antonyms, applied in the field of computer network recommendation system, can solve the problems of unresearched processing, semantic conflict, redundant repetition of label semantics, etc., to achieve the effect of wide label coverage and accurate label recommendation.

Inactive Publication Date: 2018-02-16
HOHAI UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Whether it is based on content or user behavior data, the existing Chinese and foreign tag recommendation methods are to recommend a set of tags, but the relationship between tags in the tag group recommended to users has not been studied and

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
  • Chinese tag recommendation correction method based on synonym and antonym

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] like figure 1 As shown, a Chinese label recommendation correction method based on synonyms and antonyms includes the following steps:

[0034] Step 1: Obtain the Chinese data set of users, resources, and tags, and use the method of tensor decomposition to calculate the tags that users put on resources, and sort these tags in descending order of probability to obtain an ordered list of recommended tags.

[0035] The specific steps of step 1 are as follows:

[0036]Step 1.1: Represent the data of the Chinese dataset of users, resources, and tags in the form of a triple set {u, i, t}, where u represents the user user, and i represents the item to be marked, which is called a resource , t represents the label tag, and then presents the triplet set {u,i,t} with the tensor as the model, that is, the initial tensor A is constructed with the triplet set {u,i,t}, and t...

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 Chinese tag recommendation correction method based on a synonym and an antonym. The method comprises the following steps that: before tags in a tag recommendation list obtained on the basis of a tensor decomposition method are recommended to a user, carrying out synonym and antonym discriminant check; arranging the tag which ranks behind in synonym word pair and an antonym word pair at the last of a candidate tag list; and recommending the first N pieces of tags to the user so as to eliminate tag semantic redundancy and semantic conflicts in a recommend tag group or lower the recommended sorting of the tag semantic redundancy and semantic conflicts. By use of the Chinese tag recommendation correction method based on the synonym and the antonym, the tag semantic redundancy and semantic conflicts in a recommend tag group can be eliminated, or the recommended sorting of the tag semantic redundancy and semantic conflicts in the recommend tag group can be lowred.

Description

technical field [0001] The invention relates to a method for recommending and correcting Chinese tags based on synonyms and antonyms, and belongs to the technical field of computer network recommendation systems. Background technique [0002] With the rapid development of social networks, it has become more and more popular for users to freely add tags to content they are interested in, including web pages, pictures, videos, music, and the like. Labels are social to a certain extent, and there are situations such as synonyms, ambiguous words, and wrong spellings, which lead to a large number of repetitive, irregular, and invalid labels in the labeling system, which is not conducive to the virtuous circle of the labeling system. Tag recommendation means that when a user tags a resource, the system automatically recommends appropriate tags for the user to choose based on the user's hobbies or the content of the resource itself, thereby saving the user's time and energy, improv...

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): G06F17/30
CPCG06F16/3334G06F16/3344G06F16/335
Inventor 刘元珍韩立新杨忆勾智楠
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap