Method and system for excavation of high-order attributes of test questions

Abstract

The invention discloses a method and system for excavation of high-order attributes of test questions. The method comprises the steps that low-order attributes of the test questions and a student's historical answering information are acquired, wherein the low-order attributes include knowledge points or skills of the test questions; the different low-order attributes are combined, and estimated high-order attributes are formed; based on the low-order attributes and the student's historical answering information, the student's ability is determined; according to the student's ability and the student's historical answering information, a weight of the student's ability in each test question based on each estimated high-order attribute is determined; the quantity of the estimated high-order attributes corresponding to the student's ability of which the weights are lower than a set threshold is counted; and if the quantity is larger than a set value, the corresponding estimated high-order attributes are taken as the high-order attributes of the test questions. With the method and system disclosed by the invention, the high-order attributes of the test questions are determined efficiently and accurately.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a method and system for mining high-order attributes of test questions. Background technique [0002] In recent years, with the continuous advancement and development of computer technology and educational informatization, computer and artificial intelligence technology has been gradually applied to daily educational and teaching activities. The high-level attributes of the test questions are supplementary and superordinate to the low-order attributes of the test questions (mainly referring to knowledge points, such as trigonometric functions, quadratic equations, etc.), and play an important role in the construction of question banks, student ability assessment, and personalized learning. . [0003] Most of the existing test item attribute information is based on the low-level attributes marked by human experts, that is, the artificial experts in the field of the test question formul...

AI Technical Summary

Problems solved by technology

The existing manual expert labeling method has the following disadvantages: high requirements for labeling personnel, experts in related fields are needed, and a reasonable labeling system needs to be defined in advance before labeling; in addition, the cost of this manual labeling method is relatively high, And affected by subjective factors, it is prone to inconsistent standards of different experts

Images