KR20200114519A - method and system for predicting pass rate of making question - Google Patents

Abstract

The present invention relates to a method for exam pass rate prediction. The present invention is to stabilize the yearly pass rate of an exam in order to improve the public confidence in the given exam. The method includes: a first step of inputting and storing, in a database unit, past year-specific exam scoring data and past year-specific mock exam scoring data including past exam average score data and mock exam average score data, current-year mock exam scoring data, and past year-specific exam difficulty adjustment history data; a second step of calculating a past year-specific learning index by extracting and calculating, with a plan calculation unit, the past year-specific exam scoring data, the past year-specific and current-year mock exam scoring data, and the past year-specific exam difficulty adjustment history data stored in the database unit; a third step of calculating a current-year learning index through the plan calculation unit based on the past year-specific learning index and pre-stored past year-specific exam applicant count data; and a fourth step of calculating current-year predicted average score data for predicted pass rate determination and exam difficulty management by calculating, with the plan calculation unit, the current-year learning index, previous-year exam average score data, previous-year mock exam average score data, current-year mock exam average score data, and current-year exam difficulty adjustment history data.

Description

Method and system for predicting pass rate of making question}

The present invention relates to a test pass rate prediction method and system, and more particularly, to a test pass rate prediction method and system for stabilizing the pass rate by year of the test so that the public confidence of the exam to be questioned is improved.

The test is a system implemented to verify the candidate's learning ability or qualification, and its main purpose is to evaluate the candidate's accurate ability. In particular, it is important to maintain a stable pass rate so that the number of passers does not have a large variation in the number of passed tests for each test run in the qualification verification test, where qualifications are granted based on test scores.

Accordingly, the institution in charge of the test is trying to stabilize the pass rate by setting the question difficulty level based on the scoring results of the existing test, and writing questions for each questionnaire to suit the set difficulty level.

In addition, from the standpoint of the organization in charge of the test, it is important to manage to maintain a certain pass rate in each exam so that the public confidence and reliability of the exam are continuously maintained.

However, since the difficulty evaluation by the questionnaire varies greatly depending on the individual's knowledge, personality, and disposition, the possibility of inconsistency with the set difficulty level is high, and the degree of difficulty varies greatly for each test session. there was.

In particular, conventionally, there is a problem in that it is difficult to adjust the difficulty of each exam so that the difficulty of each exam is kept constant when questioning, since there is substantially insufficient research on a method of calculating and predicting the expected pass rate of the exam to be given in advance.

Korean Patent Application Publication No. 10-2002-0023519

In order to solve the above problems, the present invention has as a solution to provide a test pass rate prediction method and system for stabilizing the pass rate for each year of the test so that the public confidence of the test to be questioned is improved.

In order to solve the above problems, the present invention provides test scoring data for each past year and mock test scoring data for each past year, including average score data for each of the previously implemented tests and simulation tests, and the mock exam scoring data for the current year, and the past year. A first step of inputting and storing test difficulty adjustment detail data in a database unit; A second step of extracting and calculating the test scoring data for each past year, the mock test scoring data for each past year and the current year, and the test difficulty adjustment details data for each past year, stored in the database unit, by a plan calculation unit to calculate a learning index for each past year; A third step of calculating a learning index for the current year through the plan calculation unit based on the learning index for each past year and the previously stored data on the number of test takers for each past year; And the current year's learning index, the previous year's test average score data, the previous year's simulation test average score data, the current year's simulation test average score data, and the current year's test difficulty adjustment history data calculated through the plan calculation unit. It provides a test pass rate prediction method including a fourth step of calculating the expected average score data for the current year for determining the pass rate and managing test difficulty.

In addition, the present invention is a test scoring data for each past year including application rate data and average score data of the previously implemented test, mock test scoring data for each past year including the average score data of the previously implemented simulation test, and scoring for the current year. A database unit for inputting and storing data and test difficulty adjustment history data for each past year; By extracting the test scoring data for each past year, the simulation test scoring data for each past year, and the test difficulty adjustment data for each past year stored in the database unit, the learning index for each past year is calculated, and the learning index for each past year and the pre-stored current year test Calculate the learning index for the current year based on the number of test takers data, and the learning index for the current year, the average score data for the previous year's test, the average score data for the simulation test for the previous year, the average score data for the simulation test for the current year, and the adjustment history data for the current year test A plan calculation unit that calculates the predicted average score data for the current year by calculating; And it provides a test pass rate prediction system including a questionnaire management unit for automatically extracting the current year test difficulty adjustment history data for test difficulty through correction of the expected pass rate.

Through the above solution means, the present invention provides the following effects.

First, it is possible to determine the expected pass rate of the current year test through the predicted average score data calculated in advance based on the scoring data of the simulation test before the current year's test, so the difficulty of the test to be presented is adjusted before the test. As a result, the passing rate of each year of the exam is stabilized, so the public confidence of the exam can be remarkably improved.

Second, the expected average score data for the current year for test difficulty management is calculated based on the ratio between the average score data for the actual test and the simulation test, and the learning index for the current year, but as the test difficulty adjustment data for the current year are corrected, the expected average score Since the data is calculated, it is possible to judge the exact expected pass rate.

Third, since the median value of the correct answer rate for each different difficulty section corresponding to the difficulty of the exam to be adjusted is reflected in the current year's test difficulty adjustment history data, it is possible to accurately calculate the predicted average score data for the current year. The reliability of the pass rate can be remarkably improved.

Fourth, it is possible to objectively judge the learning level of test takers by past year through the past year's learning index reflecting the average score data of the mock exam conducted as a question asked by the questioning committee for the separately selected mock exam personnel. Since the learning index for the current year is calculated based on each learning index, the accuracy of the expected pass rate can be improved.

1 is a block diagram showing a test pass rate prediction system according to an embodiment of the present invention.
2 and 3 are flow charts showing a test pass rate prediction method according to an embodiment of the present invention.

Hereinafter, a method and system for predicting a test pass rate according to a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing a test pass rate prediction system according to an embodiment of the present invention.

As shown in FIG. 1, the test pass rate prediction system 100 according to an embodiment of the present invention preferably includes a database unit 10, a plan calculation unit 20, and a questionnaire management unit 30. The test pass rate prediction system 100 refers to a device capable of performing a test pass rate prediction method, such as a PC of a test questioning organization.

Meanwhile, the database unit 10 includes test scoring data for each past year including application rate data and average score data of the previously administered test, and mock test scoring data for each past year including average score data for the previously conducted simulation test, It is preferable to input and store the scoring data of the simulation test for the current year, including the average score data of the simulation test for the year, and the adjustment history data of the test difficulty for each year.

At this time, in one embodiment of the present invention, it is described that the test and mock test are presented by year, but in some cases, when the test and mock test are conducted several times a year, each scoring data may be input and stored for each round. .

In addition, it is desirable to understand that the previously conducted test refers to a test that is the same subject as the test subject to be tested, and has been conducted before the enforcement date of the test subject to the year to be tested and has been scored. In addition, the above mock test refers to a mock exam conducted by the questionnaire for the mock test personnel selected separately.

In addition, the mock exam for the current year refers to a mock exam conducted by the questionnaire for the mock test personnel in response to the exam for the current year scheduled for the current year.

In addition, each of the scoring data and each of the test difficulty adjustment history data may be provided in a spreadsheet data format. Here, the scoring data may include whether or not the correct answer for each question for all candidates of the corresponding test by year or by each round of the previously administered test.

At this time, each question is classified for each subject, and score data and average score data for each subject of each candidate may be calculated according to whether or not the question is answered correctly and the points are allocated for each question.

In addition, the pass/fail status may be calculated according to the pass criterion score, the error criterion score for each subject, and the like. Of course, each candidate's score for each subject, average score, pass/fail, etc. may be pre-calculated and provided in the scoring data.

In addition, the database unit 10 may input and store application rate data for each past year of the exam, data for an exam rate for elective courses for each past year, and data on the number of recipients for elective courses for the current year, respectively.

On the other hand, it is preferable that the plan calculation unit 20 extracts the test scoring data for each past year, the simulation test scoring data for each past year, and the adjustment history data for each past year, stored in the database unit, and calculates a learning index for each past year. .

In addition, it is preferable that the plan calculation unit 20 calculates the learning index for the current year based on the learning index for each previous year and the previously stored data on the number of test takers for the current year.

In addition, the plan calculation unit 20 calculates the current year's learning index, the previous year's test average score data, the previous year's simulation test average score data, the current year's simulation test average score data, and the current year test difficulty adjustment history data. It is desirable to calculate the expected average score data.

In this case, it is preferable to understand that the average score data for the previous year's test is included in the test scoring data for each past year, and the average score data for the simulation test for the previous year is included in the scoring data for the simulation test for each past year.

In addition, it is preferable to understand that the average score data for the simulation test for the current year is included in the score data for the simulation test for the current year.

In addition, it is preferable that the plan calculation unit 20 calculates the predicted application rate data for the current year through the average ratio of the number of applicants and the number of test takers for each previous year included in the data for the number of applicants for each year.

On the other hand, it is preferable that the question management unit 30 automatically extracts the test difficulty adjustment history data for the current year in order to manage the test difficulty through correcting the expected pass rate.

Here, the question management unit 30 automatically extracts the test difficulty adjustment details data for the current year and transmits the data to the plan calculation unit 20, and the plan calculation unit 20 is the first calculated average score data for the current year. It is desirable to calculate the final corrected estimated average score data for the current year by reflecting and calculating the test difficulty adjustment data for the current year.

Therefore, it is possible to determine the expected pass rate of the current year test through the predicted average score data calculated in advance based on the scoring data of the mock test before the current year test is conducted, and the difficulty of the test to be presented based on this can be adjusted before the test. As a result, the passing rate of each year of the exam is stabilized, so the public confidence of the exam can be remarkably improved.

2 and 3 are flowcharts illustrating a method of predicting a test pass rate according to an embodiment of the present invention. Hereinafter, a method for predicting a test pass rate according to an embodiment of the present invention will be described in detail.

As shown in FIGS. 2 to 3, the test pass rate prediction method according to an embodiment of the present invention includes input and storage of each data (s10), calculation of a learning index for each past year (s20), calculation of a learning index for the current year (s30), It is preferable to include a series of steps of calculating the predicted average score data for the current year (s40).

Here, there are three assumptions for performing the test pass rate prediction method according to an embodiment of the present invention, and the assumptions are as follows.

First, the distribution of the predicted scores for each subject and the average scores of examinees follows a normal distribution.

Second, the shape of the score distribution due to the difficulty adjustment does not change.

Third, there is only one subject for the missed person, and the other subjects except for this are above the passing average score. For example, if the passing criterion score is 60, it is assumed that only one subject has 25 points or more and less than 40 points, and 60 points or more for other subjects.

Accordingly, on the premise that the three assumptions described above are established, a series of steps of inputting and storing each data, calculating the learning index for each past year, calculating the learning index for the current year, and calculating the expected average score data for the current year are performed. It is predictable.

On the other hand, test scoring data for each past year and mock test scoring data for each past year, including average score data of the previously conducted test and simulation test, the current year mock test scoring data including the average score data for the current year, and the past year. The individual test difficulty adjustment history data is input and stored in the database unit 10 (s10).

At this time, it is most preferable that the input of each of the scoring data is performed together with the execution of each test and each simulation test.

And, each data input and storage step (s10), the step of inputting and storing the application rate data for each past year of the exam, the exam rate data for the past year, and the number of applicants for each selected subject in the current year, respectively, in the database unit 10 It may contain more.

In addition, each data input and storage step (s10) may further include a step of calculating the estimated test rate data for the current year through the average ratio of the number of applicants and the number of test takers for each previous year included in the data for the number of test takers for each previous year. I can. In other words, the estimated number of applicants and the expected number of applicants for the current year can be estimated through the average of the number of applicants and the number of applicants for each previous year included in the data on the number of candidates for the previous year.

On the other hand, an equation in which the test scoring data for each past year, the mock test scoring data for each past year, the mock exam scoring data for the current year, and the test difficulty adjustment history data for each past year are stored in the database unit 10 in advance. Based on the extraction and calculation by the plan calculation unit 20 provided to process the calculation performance, the learning index for each past year is calculated (s20).

Here, the learning index for each past year is calculated by Equation 1 below.

Here, S _t is the learning index for each year in t, A _t is the test average score data of examinees for each subject in t year, A _t-1 is the test average score data for each subject in t-1, B _t-1 is t -Average score data for mock exams by mock test personnel in year t for each subject in year 1, C _t is data on average score data for mock exams by mock test personnel in t year for each subject in t year, and D _t is data for adjustment of test difficulty for each subject in year t Means. In this case, it is preferable to understand that the above-described year t is the past year excluding the current year.

In detail, the learning index (S _t ) for each previous year in Equation 1 is the numerator value of the test average score data (A _t ) for the corresponding year, the test average score data (A _t-1 ) and the corresponding the simulation of the flue test average score data obtained by adding the multiplied test difficulty level adjustment history data (D _t) of the year, the value obtained by dividing the immediately preceding year simulated average score data (B _t-1) of the year in between (C _t) value It is preferable that the denominator is calculated individually for each year excluding the current year.

Through this, the learning level of test takers for each year can be objectively determined through the study index (S _t ) for each year, reflecting the average score data of the simulation test conducted by the questionnaire as a question set by the questionnaire. It is possible to judge. That is, as the ratio between the denominator value reflected by the average score data of the simulation test and the numerator value, which is the test average score data (A _t ) for the corresponding year, it is possible to derive an objective learning index for each past year.

In addition, it is preferable that the individually calculated learning index (S _t ) for each past year is input and stored in the database unit 10. Subsequently, the learning index (S _n ) for the current year is calculated through the plan calculation unit 20 based on the previous year-specific learning index (S _t ) and the previously stored data on the number of test takers for each previous year (s30).

Here, the learning index for the current year is calculated by Equation 2 below.

Here, S _n is the learning index for the current year for each subject, E _t is the data on the number of test takers for each year in t, and S _t is the learning index for each year in t.

In detail, the current year's learning index (S _n ) in Equation 2 is calculated through a numerator value, which is the sum of the value of multiplying the number of test takers for each past year by the learning index for each past year, and a denominator value that is the sum of the number of test takers for each past year. Can be. In addition, it is preferable that the calculated learning index (S _n ) for the current year is input and stored in the database unit 10.

Through this, the learning index for the current year (S _n ) is calculated based on the learning index for each past year (S _t ) and the previously stored data for the number of test takers for each past year, so it is possible to objectively judge the learning level of the test takers for the current year. . Therefore, since the current year's learning index (S _n ) is calculated based on the previous year's learning index (S _t ), the accuracy of the final derived expected pass rate can be improved.

On the other hand, in addition to the current year's learning index calculation step (s30), a step (s31) of determining whether the current year test performed through the plan calculation unit 20 is a single lesson may be performed.

Here, when the current year test to be implemented is a single class, a step (s32a) of estimating the current year test application rate for the single class may be performed through the plan calculation unit 20. On the other hand, when the current year test to be implemented is a plurality of lessons, a step (s32b) of estimating a current year test application rate for each period for the plurality of lessons may be performed through the plan calculation unit 20.

In this case, it is preferable that the plan calculation unit 20 calculates the expected application rate data for the current year through the average ratio of the number of applicants and the number of applicants for each past year. Through this, it is possible to accurately calculate the predicted average score data for the current year for each period of the current year test being conducted.

On the other hand, in addition to the calculation of the learning index for the current year (s30), a step (s33) of determining whether an optional subject exists in the exam for the current year performed through the plan calculation unit 20 may be performed.

Here, when there are no elective subjects in the current year test being conducted, a step (s34a) of inputting and storing data on the number of applicants for the current year in the database unit 10 may be performed. On the other hand, if there are elective subjects in the current year's test being implemented, the step of estimating the current year test application rate for each elective subject, and inputting and storing data on the number of applicants for the current year for each elective subject in the database unit 10 (s34b). Can be performed.

At this time, it is desirable to understand that estimating the test application rate is the same as calculating the expected application rate data for the current year, and it is understood that the expected application rate data for the current year for each elective subject is the same as the process of calculating the expected application rate data for the current year. This is desirable.

On the other hand, the learning index for the current year, the average score data for the previous year, the average score data for the simulation test for the previous year, the average score data for the simulation test for the current year, and the adjustment history data for the test difficulty for the current year are used by the plan calculation unit 20. It is calculated through the calculation to calculate the expected average score data for the current year for determining the expected pass rate and managing the difficulty of the test (s40).

Here, the expected average score data for the current year is calculated by Equation 3 below.

Here, A _n is the test expected average score data for each subject in the current year, A _n-1 is the test average score data for each subject in the n-1 year, and B _n-1 is the mock test for each subject in year n-1. The average score data of the simulation test of the agent, C _n is the average score data of the simulation test of the simulation test agent in the n year for each subject in the year _n , D _n is the data on the adjustment history of the test difficulty for each subject in the year _n , and S _n is the learning index for the current year for each subject. it means.

In detail, the current year's learning index (S _n ), the previous year's test average score data (A _n-1 ), the previous year's simulation test average score data (B _n-1 ), and the current year's simulation test average score data ( Based on C _n ) and test difficulty adjustment history data for the current year (D _n ), the predicted average score data for the current year (A _n ) may be calculated first.

That is, in Equation 3, the expected average score data (A _n ) is the average score of the simulation test in the previous year from the product of the test average score data (A _n-1 ) for the previous year and the simulation test average score data (C _n ) for the current year. A value obtained by dividing the data (B _n-1 ) and the test difficulty adjustment history data (D _n ) for the current year may be calculated first by multiplying the learning index (S _n ) for the current year.

In addition, it is preferable that the first calculated predicted average score data (A _n ) is input and stored in the database unit 10.

In addition, it is preferable to perform a step (s41) of determining by the questionnaire management unit 30 whether the expected average score data for the current year (A _n ) exceeds or falls short of a target average score preset for each subject for test difficulty management. .

Here, if the predicted average score data for the current year (A _n ) exceeds or falls short of the preset range based on the target average score for each subject, the difficulty of each subject, that is, the adjustment history data for the test difficulty for the current year (D _n ) It is preferable that the adjusting step (s42) is performed.

In detail, in the step of calculating the predicted average score data for the year (s40), the current year automatically extracted from the question management unit 30 provided for managing the difficulty of the test in the predicted average score data for the year (A _n ) calculated first. It is preferable to further include the step of calculating the final corrected estimated average score data (A _n ) for the current year by substituting and calculating the test difficulty adjustment details data (D _n ).

At this time, the current year test difficulty adjustment history data (D _n ) is calculated by any one of the equations disclosed in Equation 4 below.

Here, the number of adjusted questions means the number of questions adjusted for adjustment of the difficulty level during the exam in the current year, and the score corresponding to the perfect score for each subject and the number of questions for each subject are previously stored in the database unit 10, respectively. At this time, it is desirable to understand that the value obtained by dividing the number of questions for each subject from the score corresponding to the perfect score for each subject means the score for the test.

In addition, the current year test difficulty adjustment history data (D _n ) may be extracted by the questionnaire management unit 30 based on the median value in Table 1 below.

difficulty step Correct answer rate (%) Median Prize One 0-10 0.15 2 10-20 3 20~30 medium 4 30~40 0.45 5 40-50 6 50~60 Ha 7 60~70 0.8 8 70~80 9 80~90 10 90~100

In this case, as shown in Table 1, a difficulty level for each question may be set by dividing the correct answer rate of the test question for each preset section, and a preset intermediate value corresponding to the difficulty level for each question may be set. For example, by the questionnaire management unit 30, a section of 0 to 30% of correct answers is set to'high difficulty', a section of 30 to 60% of correct answers is set to'under difficulty', and a section of 60 to 100% of correct answers is set to'lower difficulty'. Can be set to'.

Accordingly, the median value of the correct answer rate for each difficulty level can be reflected in the current year's test difficulty adjustment history data (D _n ), and objective test difficulty can be derived based on the correct answer rate for each question of the test being conducted.

In detail, when the difficulty of the current year test is adjusted to medium or medium, in Equation 4 above

Equation of may be automatically extracted by the question management unit 30.

And, if the difficulty of the current year test is adjusted to medium or low, in Equation 4 above

Equation of may be automatically extracted by the question management unit 30.

In addition, if the difficulty level of the current year test is adjusted from top to bottom, or from bottom to top, in Equation 4 above

Equation of may be automatically extracted by the question management unit 30.

Through this, the median value of the correct answer rate for each different difficulty section corresponding to the difficulty of the test question to be adjusted is reflected in the current year's test difficulty adjustment history data (D _n ), so that the correct average score data for the current year (A _n ) Since calculation is possible, the reliability of the expected test pass rate derived therefrom can be significantly improved.

That is, it can be estimated that the final average score data (A _n) calculated as the year the test difficulty level adjustment history data (D _n) is corrected to the first said estimated mean score data (A _n) calculated difference. In addition, the final corrected predicted average score data A _n may be input and stored in the database unit 10.

Accordingly, the expected pass rate of the current year exam may be calculated based on the final corrected expected average score data A _n and the number of candidates for the current year test stored in the database unit 10. At this time, the expected pass rate is the ratio of the number of passers to the total number of test takers. Can be calculated.

In addition, a test question for the current year may be presented through the question management unit 30 based on the final corrected average score data A _n for the current year. Here, the questionnaire subject question may be extracted from the base question previously stored in the database unit 10 by the questionnaire management unit 30.

Therefore, it is possible to determine the expected pass rate of the current year test through the predicted average score data calculated in advance based on the scoring data of the mock test before the current year test is conducted, and the difficulty of the test to be presented based on this can be adjusted before the test. As a result, the passing rate of each year of the exam is stabilized, so the public confidence of the exam can be significantly improved.

In addition, the predicted average score data for the current year for test difficulty management is calculated based on the ratio between the average score data for the actual test and the simulation test, and the learning index for the current year, and as the test difficulty adjustment data for the current year are corrected, the expected average Since score data is calculated, it is possible to determine an accurate expected pass rate.

At this time, the terms such as "include", "comprise" or "have" described above mean that the corresponding component may be present unless otherwise stated, excluding other components. It should not be construed as being able to include other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art, unless otherwise defined. Terms generally used, such as terms defined in the dictionary, should be interpreted as being consistent with the meaning of the context of the related technology, and are not interpreted as ideal or excessively formal meanings unless explicitly defined in the present invention.

As described above, the present invention is not limited to each of the above-described embodiments, and it is possible to be modified and implemented by those of ordinary skill in the art without departing from the scope claimed in the claims of the present invention. And, these modifications are within the scope of the present invention.

100: test pass rate prediction system 10: database unit
20: Plan calculation department 30: Question management department

Claims (10)

Test scoring data for each past year, including average score data for each of the previously conducted tests and mock tests, and mock exam scoring data for each past year, mock exam scoring data for the current year, and test difficulty adjustment history data for each past year are entered into the database. A first step of being stored;
A second step of extracting and calculating the test scoring data for each past year, the mock test scoring data for each past year and the current year, and the test difficulty adjustment details data for each past year, stored in the database unit, by a plan calculation unit to calculate a learning index for each past year;
A third step of calculating a learning index for the current year through the plan calculation unit based on the learning index for each past year and the previously stored data on the number of test takers for each past year; And
The study index for the current year, the average score data for the previous year, the average score data for the simulation test for the previous year, the average score data for the simulation test for the current year, and the adjustment history data for the current year test difficulty are calculated through the plan calculation unit and the expected pass rate. A test pass rate prediction method including a fourth step of calculating the predicted average score data for the year for judgment and test difficulty management. The method of claim 1,
The fourth step,
The step of calculating the final corrected estimated average score data for the current year by substituting and calculating the test difficulty adjustment details data automatically extracted from the questionnaire management unit provided for test difficulty management to the first calculated average score data for the current year. Test pass rate prediction method, characterized in that it further includes. The method of claim 2,
In the fourth step, the expected average score data for the current year is

Calculated by, where A _n is the candidate's expected average score data for each subject in the current year, A _n-1 is the test average score data of the examinee for each subject in n-1, B _n-1 is the n-1 subject For each n-year mock test agent's average score data, C _n is the n-year mock exam average score data for each n-year subject, D _n is the test difficulty adjustment history data for each n-year subject, and S _n is for each subject. A test pass rate prediction method characterized by the learning index for the current year. The method of claim 2,
In the fourth step, the test difficulty adjustment history data for the current year is

Test pass rate prediction method, characterized in that calculated by any one of. The method of claim 1,
In the third step, the learning index for the current year is

It is calculated by, where S _n is the study index for the current year for each subject, E _t is the data on the number of test takers by the previous year in t, and S _t is the learning index for each year in t. The method of claim 1,
In the second step, the learning index for each past year is

Calculated by, where S _t is the study index for each year in t, A _t is the test average score data for each subject in t year, A _t-1 is the test average score data for each subject in t-1, B _{t -1} is the average score data of the mock test of the mock test personnel in the t year for each subject in the t-1 year, C _t is the average score data for the mock test of the mock test personnel in the t year for each subject in the t year, and D _t is the test by year for each subject in the t year. Test pass rate prediction method, characterized in that the difficulty adjustment history data. The method of claim 1,
The first step,
The step of calculating the expected application rate data for the current year through the average ratio of the number of applicants and the number of test takers for the last year included in the data for the number of applicants for the previous year;
And the step of inputting and storing data on the test application rate for each previous year of the test, data on the application rate for selected subjects for each year, and data for the number of applicants for each selected subject for the current year, respectively, in the database unit. Test scoring data for each past year, including the application rate data and average score data of the previously administered exam, and mock test scoring data for each past year, including the average score data for the previously administered mock exam, and the scoring data for the mock exam for the current year, and each year. A database unit for inputting and storing test difficulty adjustment history data;
By extracting the test scoring data for each past year, the simulation test scoring data for each past year, and the test difficulty adjustment data for each past year stored in the database unit, the learning index for each past year is calculated, and the learning index for each past year and the pre-stored current year test Calculate the learning index for the current year based on the number of test takers data, and the learning index for the current year, the average score data for the previous year's test, the average score data for the simulation test for the previous year, the average score data for the simulation test for the current year, and the adjustment history data for the current year test A plan calculation unit that calculates the predicted average score data for the current year by calculating; And
A test pass rate prediction system comprising a questionnaire management unit that automatically extracts the data on the test difficulty adjustment details for the current year for test difficulty management through correction of the expected pass rate. The method of claim 8,
The questionnaire management unit automatically extracts the test difficulty adjustment details data for the current year and transmits it to the plan calculation unit,
The plan calculation unit calculates the final corrected estimated average score data for the current year by reflecting and calculating the test difficulty adjustment details data for the current year to the estimated average score data for the current year, which was calculated first. The method of claim 8,
The plan calculation unit calculates the expected application rate data for the current year through the average ratio of the number of applicants and the number of applicants for the previous year, which are included in the data on the number of candidates for the previous year.
The test pass rate prediction system, characterized in that, in the database unit, test pass rate data by past year, elective subject test rate data by past year, and elective subject number data for the current year are input and stored, respectively.

Images