Research And Realization Of The Intelligent Examination System Based On The Network

A test is one of the main measures of the educational assessment. The traditional test, especially the large scale of traditional paper-and-pencil (P&P) test is time-consuming and energy-exhausting. Meanwhile there are some difficulties with the procedures of organization and management when the traditional tests are administered.Along with the rapid development of computer technology, the computer plays a more and more major role in the standard test. But most computerized testing are computer-based tests (CBT), they are the electronic form of P&P tests with no adaptive function.For the last two decades, the computerized adaptive testing (CAT), based on the Item Response Theory (IRT), is rapidly developed and applied in examination field The tenet of CAT is to construct an optimal test for each examinee, Unlike P&P tests; different examinees can receive different tests of differing length and contents.CAT has several advantages over P&P tests: Shorter tests, higher measurement precision, test on demand, and immediate test scoring as well as reporting ,these all make CAT more attractive.In this thesis the system design and realization of variable- length CAT is discussed and explored. In the adaptive testing, the following functions are included, they are estimating the examinee's ability, selecting the suitable item administered sequentially and terminating the test when the predetermined target is reached.The strategy of selecting the item is based on the maximum information method proposed by Lord. And the method of estimating the examinee's ability is the conditional maximum likelihood estimation. The rule of termination of the test is based on the test Fisher information.The grading function is an important of the exam systems, the current exam systems have settled the grading function to the objective problems(e.g multiple-choice test,estimation test),but they have not tested the grading function to the subjective problems very well,therefore,the common exam systems don't have the grading function. If there are only objective problems in one exam system,the exam system will not be a good system for only the type of the objective problems lacking the ability of testing the examinees'ability. Therefore,the perfect system should have subjective problems to different subject .To the subjective problems, there haven't been a exam system which can do the grading function automatically for the subjective problems. The automatic grading function of the subjective problems relates to all kinds of knowledge fields such as artificial intelligence,mode identification and natural language understanding,it needs many technical problems to be settled,which makes it a technical difficulty in the online exam system.This article emphasizes particularly on the grading of the subjective problems on the academic level ,those methods also have localizations .Backward-looking,viewing the future, the grading techniques will be researched by more fields, which makes the grading of subjective problem to be not so far away, with the development of the computer techniques, the grading techniques of the subjective problems can also obtain its own development.In this thesis some of the future possibilities of CAT are discussed.