Personalized learning resource recommendation method based on learner preference modeling

A technology of learning resources and recommendation methods, applied in the field of learner portrait construction for learning resource recommendation, can solve the problem that learner preferences cannot be reasonably expanded, and the different effects of target courses are not considered, so as to achieve rationalization of correlation results and ensure comprehensive Performance and accuracy, the effect of simplifying storage
CN111460249AActive Publication Date: 2020-07-28GUILIN UNIV OF ELECTRONIC TECH
11 Cites 17 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
GUILIN UNIV OF ELECTRONIC TECH
Publication Date
2020-07-28

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a personalized learning resource recommendation method based on learner preference modeling. The method is characterized in that related learning log files of learners are obtained from an online learning platform; data such as historical course registration records, corresponding course scores and course related attributes of learners are taken as input data; historical course preferences of learners can be better obtained by embedding an attention mechanism; the coding input is used as the coding input of an automatic coder neural network, then a course knowledge graphis established to obtain a course pre-determined knowledge relationship, decoding is performed according to the correlation between courses, the probability of learning a target course by a learner is finally calculated, and a target recommendation list of the learner is generated according to the probability from large to small, so the individuation and accuracy of a recommendation result is improved.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] (1) Technical field

[0002] The invention relates to technical fields such as machine learning, recommendation systems, and data mining, and in particular to a method for constructing learner portraits for learning resource recommendation.

[0003] (2) Background technology

[0004] With the in-depth development of education informatization, the number of online educational resources is showing an exponential growth trend. How to help learners obtain the learning resources they want from massive amounts of data is crucial for online learning platforms. Therefore, how to construct the learner's preference feature according to the learner's historical registration course is the key to the personalized learning resource recommendation system. Most of the previous learner preference modeling methods are based on the course records of the user's historical registration, and characterize the learner's preference characteristics by generating course feature vectors, and then g...

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