Method for recommending problem based on probability latent semantic analysis

A technology for semantic analysis and recommendation methods, applied in the field of social networking, which can solve the problems of time-consuming and underutilized user contacts, etc.

Inactive Publication Date: 2009-01-28
ZHEJIANG UNIV
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for users, it is time-consuming to find the problems they are interested in
Howeve...

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 for recommending problem based on probability latent semantic analysis
  • Method for recommending problem based on probability latent semantic analysis
  • Method for recommending problem based on probability latent semantic analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The implementation process of the present invention needs to be trained first, and then applied.

[0036] In the training step, all the question information raised and answered by the user is first extracted from the user interactive question answering system, where each question is represented by a text vector, including the question itself and its answer. Next, an expectation-maximization method is used to train a three-way state model, where the latent variables of the state model are vectors representing interests, whose initial values ​​are a set of random values. After the iterative process of expectation maximization, the interest vector will converge to the local optimal result. At this point, the training steps are completed.

[0037] During the application process, according to the trained interest vector, the joint probability of the question and the user is calculated and sorted, and the final ranked list of questions is recommended to the user.

[0038] 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 recommended method for analyzing the latent semantic problem based on the probability. The method describes the interest of a user through a state model in the latent semantic analysis on the probability and provides the compatible problem recommendation for the user interactive type question-answering system. The method adopts a ternary state model, has the advantages of two recommended ways based on the content and collaborative filtering, performs problem recommendation according to the personalized information of the user, and has high accuracy and good applicability in the user interactive type question-answering system.

Description

technical field [0001] The invention relates to a social network, a question answering system, and a recommendation system technology, in particular to a method for recommending questions based on probabilistic latent semantic analysis. Background technique [0002] In recent years, user-interactive question-answering systems, which aim to enhance mutual answers between users, have become a new research hotspot. In the past few years, there have been such websites as Sina Aiwen, Baidu Zhizhi, Yahoo! Answers and other user-interactive question-answering systems. Users are free to ask questions, browse questions, and answer questions. However, for users, it is time-consuming to find the questions they are interested in. Therefore, recommending questions to users who are interested or able to answer is an important supplement to user-interactive question-answering systems. [0003] A recommendation system is an information filtering technique designed to present items (such...

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): G06F17/30G06F17/27
Inventor 卜佳俊陈纯曲明成仇光吴昊
Owner ZHEJIANG 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