Diversified exercise recommendation method, system and equipment combining difficulty and weak knowledge points

• Main Authors: MIAO QIGUANG, HUANG SHUXUE, KWON EUI-YOUNG, RAO YU, SUN PENGGANG, SONG JIANFENG
• Format: Patent
• Language: Chinese; English
• Published: 30.05.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a diversified exercise recommendation method, system and device combining difficulty and weak knowledge points, and the method comprises the steps: firstly coding a historical answer sequence of a student, and obtaining model input data in a standard format; modeling exercises by using an e-DKT model to obtain the correct answer probability of the exercises of the students, and modeling knowledge points by using a k-DKT model to obtain the mastering degree of the knowledge points of the students; on the basis of the correct answer probability and the knowledge point mastering degree, the exercise individual difficulty and student weak knowledge points are calculated, and a filtering module is utilized to select exercises which are moderate in difficulty and contain the weak knowledge points from the exercise set to construct candidate subsets; selecting exercises with the maximum spatial distance from the candidate subsets by using a simulated annealing algorithm, and generating a reco