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

A QA community label recommendation method based on convolution neural network

A convolutional neural network and question-and-answer community technology, applied in the field of question-and-answer community label recommendation, can solve problems such as unscalable, unsatisfactory recall rate and precision indicators, and inability to handle continuous update of the question-and-answer community, achieving good migration and accuracy matching effect

Active Publication Date: 2019-02-01
WUHAN UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (1) They apply constraints to relatively small datasets;
[0008] (2) They are not scalable and cannot handle continuous updates in Q&A communities;
[0009] (3) Their recall and precision metrics are not ideal

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
  • A QA community label recommendation method based on convolution neural network
  • A QA community label recommendation method based on convolution neural network
  • A QA community label recommendation method based on convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0051] 1) Given a software object o i , let x i ∈ R k is the k-dimensional vector corresponding to the i-th word described. The description of length n is expressed as:

[0052]

[0053] where ⊕ is the stitching operator, x i:i+j refers to the word x i splicing. x i ,x i+1 ,...,x i+j . it can be used figure 1 The n*k matrix-vector representation in . These word vectors are trained by the Mikolov method.

[0054] 2) The convolution operation involves a filter f∈R hk , which is applied to a window of h words to produce a new feature. For example, feature c i by the word x i:j+h-1 by c i =tanh(f·x i:i+h-1 +b) generation, where b∈R is a bias term and tanh is a non-linear hyperbolic tangent function. This filter is applied to describe {x 1:h ; x 2:h+1 ;…;x n-h+1:h} to generate feature maps

[0055] c={c 1 ; c 2 ;…;c n-h+1};

[005...

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 question answering community label recommendation method based on a convolution neural network, specifically, it involves the data preprocessing of the question data set inthe question answering community, and then the matrix is established by word embedding, The Mikilovo method is used to change the matrix of training set into three-dimensional matrix, then the convolution neural network model is used to train the three-dimensional matrix, and finally the new questions in the question-answering community are tagged by the trained model, which is a tagging recommendation method based on the convolution neural network in question-answering community. It has the following outstanding characteristics and advantages: First, the convolution layer can be introduced toextract features accurately and match them more precisely; Secondly, the ability of convolution neural network to deal with large images makes it possible to deal with large data sets. Thirdly, convolution neural network has good migration in image processing, which makes it have good migration in label recommendation.

Description

technical field [0001] The invention relates to a method for recommending tags in a question-and-answer community based on a convolutional neural network. Background technique [0002] With the rapid development of the Internet, more and more IT enthusiasts seek help, share experience, and learn new technology knowledge on the Internet, thus various developer question-and-answer communities, software information sites such as StackOverflow and Freeecode have emerged It can provide information sharing and communication for developers all over the world. [0003] To facilitate proper categorization and efficient searching, developers need to provide tags for their publications. However, tagging is an inherently uncoordinated process that depends not only on a developer's understanding of their own posts, but also on other factors, including the developer's English language skills and knowledge of existing posts. [0004] As a result, developers keep creating new tags even wh...

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): G06F16/383G06F17/27
CPCG06F40/205G06F40/242
Inventor 刘进周平义储玮崔晓晖李兵陈旭施泽洋彭新宇赵发凯
Owner WUHAN UNIV
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