A learning resource recommendation method based on a CBOW model

A learning resource and recommendation method technology, applied in the field of online learning resource recommendation, can solve the problems of data sparseness, no consideration of upper and lower sequence relations, etc., and achieve the effect of high accuracy

Pending Publication Date: 2019-06-18
XINJIANG UNIVERSITY
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, none of the above algorithms consider the upper-lower order relationship in knowledge learning, and there is a problem of data sparsity.

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 learning resource recommendation method based on a CBOW model
  • A learning resource recommendation method based on a CBOW model
  • A learning resource recommendation method based on a CBOW model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The application of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0029] A method for recommending learning resources based on the CBOW model, comprising the following processes:

[0030] First, establish a CBOW learning resource recommendation model. see figure 1 .

[0031] The invention integrates the knowledge sequence of the learning content and the learning intention of the learner into the CBOW model, intending to establish a new learning resource recommendation model under the background of electronic learning. The establishment process of the model is divided into the training process and the recommendation process, in which the training process is to arrange the known learning resources according to the learning order of the learners, and use the arranged learning resource sequence as the input of the CBOW model, and the output of the CBOW model is The similarity between learning resources, through th...

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 the field of online learning resource recommendation, in particular to a learning resource recommendation method based on a CBOW model. The method comprises the steps of 1, collecting historical learning behaviors of learners, and adding all the learning behaviors into a blank dictionary to establish a learning behavior dictionary; 2, training a CBOW model through the learning behavior dictionary to obtain similarity among learning behaviors; 3, predicting the future behavior of the learner according to a training completion result to obtain a candidate list 1; 4, predicting by adopting a collaborative filtering algorithm in a traditional recommendation algorithm based on the score of the learner on the learning resource to obtain a candidate list 2; And 5, combining the two candidate lists according to the same learner to obtain a final project recommendation list. According to the method, the CBOW is used for representing the knowledge sequence of the learning content in the learning historical behavior, and the characteristics are used for calculating the similarity among the projects, so that the problem that the resource sequence relationship in a traditional recommendation system is ignored is solved.

Description

technical field [0001] The invention relates to the field of online learning resource recommendation, in particular to a learning resource recommendation method based on a CBOW model. Background technique [0002] The online learning system has been committed to the research of learner interest prediction and learning resource recommendation, aiming at accurately grasping learner's learning intention, predicting and recommending accurate learning resources for them. In terms of recommendation algorithms, there have been very rich researches. According to different recommendation strategies, recommendation algorithms are generally divided into content-based filtering algorithms, collaborative filtering algorithms and hybrid recommendation algorithms. [0003] Content-based recommendation algorithms identify items that users are particularly interested in by analyzing item descriptions, thereby recommending similar items that a given user likes. Current research on content-b...

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): G06F16/9535
Inventor 秦继伟蒋云鹏汪烈军
Owner XINJIANG UNIVERSITY
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