Test question duplicate removal method and test question duplicate removal system

Abstract

The invention relates to the technical field of education, and discloses a test question duplicate removal method and system, which can reduce the calculated amount of the system and improve the testquestion duplicate removal efficiency. The method comprises the steps of obtaining a target test question; determining a question type of the target test question and an involved knowledge point set;generating a feature code of the target test question according to the question type and the knowledge point set and a preset coding rule, and obtaining each test question with the feature code from atest question resource library, if the content similarity between the target test question and any test question in the test questions is greater than a preset threshold, judging that the target testquestion is a repeated test question and deleting the target test question, and otherwise, storing the target test question and the feature code of the target test question into the test question resource library.

Description

technical field [0001] This application relates to the field of educational technology, in particular to the technique of deduplication of test questions. Background technique [0002] With the development of Internet information technology, a large number of test question resources can be obtained on the Internet platform, and there are a large number of duplicate resources in these test question resources. Therefore, in the process of building the test question resource library, the primary problem to be solved is the identification and de-duplication storage of repeated test question resources. [0003] One method of deduplication of test questions is to calculate the content similarity between the test questions and all the test questions in the test question resource library before entering the database, and judge whether the test questions to be stored in the database are repeated according to the calculation results of the content similarity, so as to achieve the purp...

AI Technical Summary

Problems solved by technology

[0003] One method of deduplication of test questions is to calculate the content similarity between the test questions and all the test questions in the test question resource library before entering the database, and judge whether the test questions to be stored in the database are repeated according to the calculation results of the content similarity, so as to achieve the purpose of deduplication. This method of deduplication of test questions has a large amount of calculation and low efficiency

Images