Unlock instant, AI-driven research and patent intelligence for your innovation.

A digital education resource recommendation method and system

A technology for educational resources and recommendation methods, applied in the field of digital educational resource recommendation methods and systems, can solve the problems of difficult to obtain features, a large number of manual participation, etc., and achieve the effects of wide application, overcoming cold start, and high user satisfaction

Active Publication Date: 2017-04-12
HUAZHONG NORMAL UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This recommendation strategy first extracts the content characteristics of the recommended objects, and matches them with the user’s interests and preferences in the user model. The recommended objects with a high degree of matching can be recommended to users as recommendation results. However, building the content characteristics of resources often requires a lot of manual participation. , and it is difficult to obtain suitable features

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 digital education resource recommendation method and system
  • A digital education resource recommendation method and system
  • A digital education resource recommendation method and system

Examples

Experimental program
Comparison scheme
Effect test

example

[0062] The process of calculating student A’s interest in the learning resource "Introduction to Data Mining" is as follows: first obtain the text information of "Introduction to Data Mining", convert it into digital information, and obtain the text information M of "Introduction to Data Mining", Taking M as the input of the trained convolutional neural network, the predicted feature vector N of "Introduction to Data Mining" is obtained through the forward broadcast of the convolutional neural network, and then the feature vector S of student A is taken out from the student feature library, and the The vector N is multiplied by S to obtain the estimated value a of the student A's interest in the learning resource "Introduction to Data Mining". If a is greater than the threshold value preset by the system, it will be recommended, otherwise it will not be recommended.

[0063] In the example, the user-resource matrix is ​​shown in Table 1

[0064]

[0065] Among them, the vac...

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 method for recommending digital educational resources, which is characterized in that it comprises the following steps: (1) extracting the text information of the educational resources; (2) digitizing the text information to obtain a matrix of text numbers; (3) extracting the text information of the text numbers The matrix inputs the resource feature recognizer obtained by pre-training, and the resource feature recognizer outputs the educational resource feature vector; (4) Multiply the educational resource feature vector and the user feature vector to obtain the student's interest in educational resources. The present invention extracts educational resource features from resource text information, and combines student features to determine students' interest in resources. This method can be applied to any resource that has a partial text description, and has a wide range of applications and high recommendation satisfaction.

Description

technical field [0001] The invention relates to the field of educational informatization, in particular to a method and system for recommending digital educational resources. Background technique [0002] In the past decade, the rapid growth of Internet size and coverage has brought about the problem of information overload, to solve this problem recommendation system has become popular. Recommender systems are used in many scenarios, such as: movies, music, news, research papers, etc. In the field of online education based on the education cloud, a recommendation system is also adopted to enable students to improve learning efficiency and experience, and to provide students with personalized learning services. [0003] At present, there are many methods for implementing recommendation systems, and these methods can be mainly divided into two categories: collaborative filtering methods and content-based recommendation methods. The basic idea of ​​collaborative filtering is...

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): G06F17/30G06K9/62
CPCG06F16/9535G06F18/22
Inventor 刘海杨宗凯刘三女牙张昭理舒江波
Owner HUAZHONG NORMAL UNIV