Open AccessStudy on the Adaptive Test Modelling Based on Knowledge Graph in the Domain of Substation
Author(s) -
WANG Weizhou,
ZHAO Xilan,
Qi Gao,
Lu Liu,
LIN Changnian
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2213/1/012017
Subject(s) - reachability , adjacency matrix , computer science , domain knowledge , graph , knowledge graph , test (biology) , domain (mathematical analysis) , artificial intelligence , machine learning , theoretical computer science , mathematics , paleontology , mathematical analysis , biology
Traditional tests in the substation training fail to fit the ability of the operation and maintenance personnel and precisely describe their weakness. In this paper, an adaptive test model based on the knowledge graph in the domain of substation is constructed. With the help of the knowledge point correlations in the knowledge graph, the model updates the knowledge level of the testee in real time according to the response of each question, and automatically selects the next question that fits the individual. In cases where the test question covers different knowledge amount, the model constructs the knowledge state space or the adjacency/reachability matrix to infer the knowledge mastery, which improves the test efficiency and quality by reasonably reducing the number of questions during the test. Calculation results demonstrate that the model can accurately capture the weakness the substation personnel and has broad application prospects on evaluations in the vocational education.