Method and system for predicting the popularity of questions in question-and-answer communities based on deep learning models

A question and answer community, deep learning technology, applied in the computer field, can solve the problems of complex communication methods, cumbersome and efficient artificial feature extraction technology, difficult modeling, etc., to achieve the effect of satisfying the prediction results, and the prediction results are credible and accurate.

Active Publication Date: 2022-05-03
SUN YAT SEN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This is mainly due to the fact that the propagation of the problem is very complicated, and the heat of the problem is affected by many factors. However, the artificial feature extraction technology used in the existing technology is cumbersome and inefficient, and it is difficult to effectively model it. simple qualitative analysis

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 system for predicting the popularity of questions in question-and-answer communities based on deep learning models
  • Method and system for predicting the popularity of questions in question-and-answer communities based on deep learning models
  • Method and system for predicting the popularity of questions in question-and-answer communities based on deep learning models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, a method for predicting the popularity of questions in question-and-answer communities based on deep learning models includes the following steps:

[0055] S1. Obtain the historical information in the question-and-answer community, and after preprocessing the data, use the data to train the neural network model for predicting the popularity of questions. The prediction model for question popularity uses deep neural network technology and point process mathematical models, and includes a The layer posterior attention mechanism is used to model the characteristics of the question-and-answer community; after the training is stable, a prediction model with optimal parameters can be obtained;

[0056] S2. Obtain the existing information of the question to be predicted, including the text information of the question and the observed answer, time information, and the number of followers of the answer writer. These information will be input into the m...

Embodiment 2

[0087] Such as figure 2 As shown, a system for predicting the popularity of questions in the question-and-answer community based on a deep learning model. The system includes: a preprocessing module, an encoding module, a decoding module, an attention module, and a popularity prediction module. Combine below figure 2 Each module in will further illustrate the prediction method of the present invention.

[0088] Step A: Train the model, obtain the historical information in the question-and-answer community, preprocess the data, and use the data to train the neural network model for predicting the popularity of questions. The prediction model for question popularity uses deep neural network technology and point process mathematical models , and includes a layer of posterior attention mechanism to model the characteristics of question answering communities. After the training is stable, a prediction model with optimal parameters can be obtained.

[0089] Specifically, the fo...

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 present invention relates to a method and system for predicting the popularity of questions in a question-and-answer community based on a deep learning model. Including: S1. Obtain historical information in the question-and-answer community, preprocess the data, and use the data to train the neural network model for question popularity prediction. The question popularity prediction model uses deep neural network technology and point process mathematical models, including a layer of posterior attention The characteristics of the question-and-answer community are modeled by the force mechanism; after the training is stable, a prediction model with optimal parameters can be obtained; S2. Obtain the existing information of the question to be predicted, including the text information and time of the question and the observed answer information, the number of followers of the author of the answer, these information will be input into the model after a certain preprocessing, and the popularity prediction result will be obtained. The invention makes full use of the historical data of the question-and-answer community to meet the needs of the demand side for more detailed and accurate prediction results, so that the demand side can adopt corresponding coping strategies in advance according to the predicted hotness of the questions.

Description

technical field [0001] The invention belongs to the field of computer technology, and more specifically relates to a method and system for predicting the popularity of questions in question-and-answer communities based on deep learning models. Background technique [0002] Online Q&A communities, such as Zhihu, Quora, StackOverflow, etc., provide a convenient platform for users to ask their questions and share their answers anytime and anywhere. In recent years, the Q&A community has shown explosive growth and has become an important online platform for users to exchange and find information. How to effectively use the existing data in the question answering community to learn and predict the popularity of a question becomes a challenging research topic. [0003] In the process of realizing the present invention, the inventor found that the heat prediction of questions is very important to the operation and development of community Q&A, which can help the operators of Q&A c...

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 Patents(China)
IPC IPC(8): G06F16/9536G06F16/958G06N3/04G06N3/08
CPCG06F16/9536G06F16/958G06N3/08G06N3/044G06N3/045
Inventor 温志伟梁上松蒙在桥
Owner SUN YAT SEN 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