Learning and reviewing problem bank recommendation method based on collaborative filtering
A collaborative filtering and recommendation method technology, applied in the field of modern learning platforms, can solve the problems of users wanting to change questions and low efficiency in the recommendation of answer types, and achieve the effect of improving learning and use efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] The technical solution of this patent will be further described in detail below in conjunction with specific embodiments.
[0037] A method for recommending learning review question banks based on collaborative filtering, comprising the following steps:
[0038] 1. Establish a user-mathematics question answering matrix, according to the popularity h of the mathematical question p p The calculation formula calculates the popularity of math problems for each math problem.
[0039] 2. For the current user to be recommended, if the number of math questions answered by the user is greater than 20, the similarity between the user and the current user is calculated according to the optimized Pearson correlation coefficient calculation formula, and the Top-N method is used to obtain the number of N users A preliminary set of similar neighbors formed. If the number of math questions answered by the current user is less than 20, in order to improve the recommendation quality, d...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


