KR20240071694A - Job suitability personality system and method using big data - Google Patents

Abstract

The present invention relates to a job suitability aptitude test system and method using big data that can classify and respond to high performers and low performers and match job suitability. The aptitude test server loads the aptitude test database and scores the aptitude test. Saving the scoring results in a personality test database; The personality test database includes a first extraction step of extracting a high performer group consisting of people who are employed at a company and classified as high performers by the company from the information of people who solved the personality test problem performed by the personality test server; A step where the AI server extracts the problems of high performers from the personality test results corresponding to the high performers and forms a merit pattern; The personality test database includes a second extraction step of extracting a low performer group consisting of people who are employed at a company and classified as low performers by the company from the information of people who solved the personality test problem performed by the personality test server; A step where the AI server extracts the problems of low performers from the personality test results corresponding to the low performer group and forms a defective pattern; The AI server grants additional and subtracted points to personality test questions corresponding to the merit pattern and defective pattern, respectively; And the AI server is configured to include a calculation step of calculating the personality suitability by subtracting the deduction points from the addition points, which has the effect of matching the job suitability suitable for the job in addition to the personality test.

Description

Job suitability personality test system and method using big data {JOB SUITABILITY PERSONALITY SYSTEM AND METHOD USING BIG DATA}

The present invention relates to a job suitability aptitude test system and method using big data. More specifically, the present invention relates to a job suitability personality test system and method using big data. More specifically, it classifies high performers and low performers of a job from accumulated personality test data and uses the classified data to determine the propensity and low performance of high performers. This relates to a job suitability personality test system and method using big data that can match job suitability by classifying and responding to the performer's tendencies and continuously managing them.

The beginning of personality testing dates back to 1920. At that time, American Dr. Robert Woodworth developed the 'Woodworth Personal Data Sheet' to select soldiers to participate in World War I. Through the test, we wanted to identify young people who were unable to withstand trauma and were likely to develop delirium. In other words, it was developed as a test to filter out people who shoot comrades or harm themselves due to the stress of war.

In the future, the Woodworth Test is said to have become the framework for numerous personality tests such as the 'Myers Briggs Personality Inventory (MBTI)', the 'Minnesota Multiphasic Personality Inventory (MMPI)', and the 'NEO Personality Inventory (Revised NEO Personality Inventory)'. MBTI and MMPI are used in a variety of places, including schools, companies, hospitals, and researchers. In addition, there are numerous personality tests modified to suit each industry.

Unlike personality tests, aptitude tests are closer to the commonly known I.Q. tests, intelligence tests, and academic ability assessments. A representative aptitude test is the SAT, which is taken during college entrance exams in the United States. SAT is a test developed in the early 1900s to unify the entrance exams that were different for each university. SAT started in 1926. At the time, the SAT consisted of a variety of subjects, including English, French, Latin, history, math, chemistry, and physics. Afterwards, I started taking aptitude tests in college using the SAT to find the career aptitude that was right for me.

Companies have introduced aptitude tests to place employees in fields that suit their aptitude. It varies from company to company, but most assess the applicant's cognitive, logical, executive, and linguistic capabilities. In addition, there are places where common knowledge or history are evaluated.

In existing companies, tests such as general knowledge, language, professional knowledge, and thesis were mainly written academic ability evaluation tests. However, such tests may evaluate knowledge through study or some skills, but they do not test the test taker's personality. I began to realize that seeing was not enough.

Therefore, companies have realized that it is unreasonable to hire people based on the existing written test, and although the aptitude test is completely different from other test subjects, because it has the above-mentioned necessity, companies are conducting an additional subject called the aptitude test in addition to the written test. has increased.

As such personality tests have developed, each government department, government-invested institution, bank, financial institution, large company, etc. has adopted a method of hiring new employees or employees based on written scores and interviews. However, recently, personality tests are used rather than written tests when hiring. There is a trend of placing more importance on interviews.

Since many companies, including large corporations, can evaluate work adaptability through aptitude tests, they are placing more emphasis on aptitude tests that focus on personality and aptitude rather than written tests for the purpose of selecting excellent talent.

Since such personality tests are important from a company's perspective, each company is seeking the best method to rationalize personnel, selection, and placement and to scientifically manage management. As part of this, each company is increasing investment to change the job environment and placing emphasis on human resource training, thereby improving productivity.

However, the aptitude tests administered by each company are collected in the form of a question bank and a collection of questions is published, and there is a problem in that the accuracy of the aptitude test through such exposed question papers is gradually becoming unreliable.

Republic of Korea Patent Publication No. 10-2000-0063641 (November 6, 2000). ‘Advanced career guidance system based on personality and aptitude test’

The present invention was created to solve the above-mentioned problems. The purpose of the present invention is to classify the data into high performers and low performers from the company's accumulated personality test data and input the classified data to select high performers. The purpose is to provide a job suitability personality test system and method using big data that can accumulate personality test and aptitude test data of low performers and determine future job suitability from the accumulated data.

The problems to be solved by the present invention are not limited to those mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

The job connection system using the job suitability personality test of the present invention to achieve the above-mentioned purpose is,

When applying for a personality test online, personality test questions are provided at a designated location online or offline at the request of the applicant. When applying for a personality test offline, personality test questions are provided at a designated location offline and the provided personality test is provided. An aptitude test server that scores questions and provides aptitude test results when the grading is completed;

Among the result information of people who took the personality test performed by the personality test server, the test results of people who were employed at a company and classified as high performers by the company are stored as a high performer group, and the personality test questions and aptitude from the high performer group are stored. Classify it as a test problem and extract the propensity analysis problems of high performers, save the test results of people who are employed at a company and classified as low performers by the company as a low performer group, and classify the low performer group into personality test problems and aptitude test problems. a personality test database that extracts low-performing propensity analysis problems; and

From the propensity analysis problems of high performers extracted from the above personality test database, the average value, variance, and deviation of the percentage of correct answers answered by each high performer are calculated, arranged in the order of the highest absolute deviation, and a certain number of problems are selected in the order of the highest absolute deviation. After adoption, the pattern of answers adopted for each question is stored as a merit pattern, and the most frequently selected answer from the low performer extraction result extracted from the personality test database is stored as a merit pattern of the person who selected the corresponding answer from the sample of low performers. After calculating the average value, variance, and deviation, arranging the problems in the order of the highest absolute deviation, selecting a certain number of problems in the order of the highest absolute deviation, saving the selected problems as a defective pattern, and storing the merit pattern and the aptitude test test results. It is composed of an AI server that evaluates the similarity and determines job suitability by evaluating the similarity with the personality test results of the defective pattern.

The AI server is,

In determining job suitability, additional points are given by evaluating the similarity between the adopted merit pattern and the job suitability test results, and subtracted points are given by evaluating the similarity between the adopted defective pattern and the job suitability test results. Points are subtracted from the added points. It can be configured to calculate the personality suitability by subtracting the value.

The AI server is,

It can be configured to store high-performing groups and low-performing groups for each job, form merit patterns and defective patterns for each job, and calculate personality suitability for each job.

The AI server excludes the two problems with the lowest absolute deviation among the problems constituting the merit pattern at regular time intervals and replaces the two problems with other problems, and determines the deviation among the problems constituting the defective pattern. The two problems with the lowest scores are excluded and replaced with other problems. If there are overlapping problems among the above merit and disadvantage patterns, the overlapping problems are excluded and replaced with the problem with the next highest iron deviation value equal to the excluded problem. It can be configured as follows.

In extracting problems that constitute merit patterns and defective patterns, the AI server may be configured as a personality test problem, as a written test problem, or as a mixture of personality test problems and written test problems.

The job matching method using the job suitability personality test of the present invention to achieve the above-mentioned purpose is,

A personality test server loading the personality test database, scoring the personality test, and storing the scoring results in the personality test database;

The personality test database includes a first extraction step of extracting a high performer group consisting of people who are employed at a company and classified as high performers by the company from the information of people who solved the personality test problem performed by the personality test server;

A step where the AI server extracts the problems of high performers from the personality test results corresponding to the high performers and forms a merit pattern;

The personality test database includes a second extraction step of extracting a low performer group consisting of people who are employed at a company and classified as low performers by the company from the information of people who solved the personality test problem performed by the personality test server;

A step where the AI server extracts the problems of low performers from the personality test results corresponding to the low performer group and forms a defective pattern;

The AI server grants additional and subtracted points to personality test questions corresponding to the merit pattern and defective pattern, respectively; and

The AI server is configured to include a calculation step of calculating the personality suitability by subtracting the deduction points from the addition points.

The high-performing group and the low-performing group can be configured to store each job, form merit patterns and defective patterns for each job, and calculate personality suitability for each job.

The first extraction step is,

A step where the AI server calculates the average value, variance, and deviation of the correct response rate of high performers;

A step where the AI server obtains the average value, variance, and deviation of the percentage of correct answers from the group of high performers and places them in order of the problems with the highest absolute deviation; and

It may be configured to include a step where the AI server selects a certain number of problems in the order of highest absolute deviation among the problems of the sorted group of high performers and stores them as a merit pattern.

The second extraction step is,

A step where the AI server calculates the average value, variance, and deviation of the correct response rate of low performers;

The AI server calculates the average value, variance, and deviation of the percentage of correct answers from the low-performing group and arranges them in order of the problems with the highest absolute deviation; and

It may be configured to include a step where the AI server selects a certain number of problems in the order of highest absolute deviation among the problems of the sorted group of low performers and stores them as a defective pattern.

The calculation step is,

A step where the AI server calculates an additional value by weighting the number of correct answers to the merit pattern problem according to the section;

A step where the AI server calculates a subtraction value by weighting the number of correct answers to the problem of the defective pattern according to the section;

The AI server performs a judgment step to determine whether there are overlapping problems among the merit pattern and defect pattern problems;

A step where the AI server determines in the judgment stage that if there are overlapping problems among the merit pattern and defect pattern problems, the overlapping problems are excluded from the merit pattern and defective pattern, respectively; and

It may be configured to include a step where the AI server reorganizes the problems of the merit pattern and the defective pattern by supplementing the same number of problems as the number of overlapping problems among the problems of the merit pattern and the defective pattern.

The job suitability personality test system and method using big data according to the present invention classifies high performers and low performers of a job from accumulated personality test data, classifies the tendencies of high performers and low performers using the classified data, and By continuously managing this in response, there is an effect of matching the job suitability for the job in addition to the personality test.

Figure 1 is a block diagram showing the configuration of a job suitability personality test system using big data according to an embodiment of the present invention.
Figure 2 is a flow chart showing the process of job suitability personality testing using big data according to an embodiment of the present invention.
Figure 3 is a flowchart showing the process of configuring the merit pattern of Figure 2 according to an embodiment of the present invention.
Figure 4 is a flowchart showing the process of configuring the defective pattern of Figure 2 according to an embodiment of the present invention.
Figure 5 is a flowchart showing the process of calculating the addition and subtraction points of Figure 2 according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings.

Figure 1 is a block diagram showing the configuration of a job suitability personality test system according to an embodiment of the present invention.

Referring to Figure 1, the job connection system using the job suitability personality test of the present invention includes a wired and wireless communication network (10), a terminal (100), a personality test server (200), a personality test database (300), and an AI server (400). It can be configured to include.

First, the terminal 100 can use devices such as a personal computer (PC), smartphone, tablet PC, and personal digital assistant (PDA), and the terminal 100 can be connected to a personality test server ( 200).

First, the terminal 100 is a device that can communicate with the aptitude test server 200 and input text. The terminal 100 applies for an aptitude test to the aptitude test server 200 through the wired or wireless communication network 10. The aptitude test application can be done online or offline, and the aptitude test can be done online or offline. When the personality test is conducted online, the personality test paper is displayed through the terminal 100, and the personality test is performed by checking the relevant items on the displayed test paper. If the personality test is conducted offline, a group or people with the same purpose are convened at a predetermined time and place, the personality test is distributed, the personality test is performed, the test paper is collected, and the personality test results are scored. It can produce results. In the present invention, for convenience of explanation, a case where the test is performed online will be described.

If you take an online aptitude test, you can check the aptitude test results in real time, and if you take an offline aptitude test, you can check the test results after a certain period of time.

The personality test server 200 loads the personality test database 300 and scores the personality test. The personality test server 200 transmits the scoring results of the personality test to the terminal 100 through the terminal 100 and displays the personality test results on the terminal 100.

When applying for a personality test online, the personality test server 200 provides personality test questions at a designated location online or offline according to the request of the applicant. When applying for a personality test offline, the personality test server 200 provides a personality test at a designated location offline. When questions are provided and the provided personality test questions are received and grading is completed, they are scored and the personality test results are provided.

The aptitude test server 200 scores the aptitude test results by calculating the value input from the terminal 100 and determining trap problems. The personality test scored by the personality test server 200 is largely divided into a personality test and an aptitude test. In particular, in the case of personality tests, in order to prevent false writing, the same problems may be presented repeatedly or similar types of problems may be arranged to increase the reliability of writing. An example of such a trap problem is that similar but different problems are placed repeatedly, and if the results of the repeated similar problems do not match, it is judged that the trap problem has not been passed, and points may be deducted from the personality test results. there is.

The personality test database 300 stores a high performer group consisting of people who are employed at a company and classified as high performers by the company among the information on people who solved the personality test problems performed by the personality test server 200. The AI server 400 extracts the problems of high performers from the personality test results corresponding to the high performer group. The problems extracted at this time are extracted separately from personality test and aptitude test problems.

The personality test database 300 forms a low performer group consisting of people who are employed at a company and are classified as low performers by the company among the information on people who solved the personality test problems performed by the personality test server 200. The AI server 400 extracts the problems of low performers from the corresponding group of low performers. The problems extracted at this time are extracted separately from personality test and aptitude test problems.

In order to extract problems with a high percentage of correct answers answered by high performers from the group of high performers extracted from the personality test database 300, the AI server 400 calculates the average value, variance, and deviation of the percentage of correct answers answered by high performers, and solves problems with high absolute deviation. Arrange them in order. The AI server 400 selects a certain number of problems in the order of highest absolute deviation from the arranged problems and then stores the patterns of the adopted problems and their answers as a merit pattern. At this time, the number of problems extracted by the AI server 300 can be 10 to 30 problems, and preferably 20 problems.

In order to extract problems with a high percentage of correct answers answered by low performers from the group of low performers extracted from the personality test database 300, the AI server 400 calculates the average value, variance, and deviation of the percentage of correct answers answered by low performers, and determines the average value, variance, and deviation of the correct answers answered by low performers, and determines the problem with a high absolute deviation. After arranging the problems in order and selecting the problems of a certain description in the order of the highest absolute deviation, the patterns of the adopted problems and their answers are stored as a testive pattern. At this time, the number of problems extracted by the AI server 300 can be 10 to 30 problems, and preferably 20 problems.

Meanwhile, in selecting a merit pattern, the AI server 400 selects a certain number of problems in the order of the highest absolute deviation as described above, but can be selected from personality test problems, aptitude test problems, or Personality test questions and aptitude test questions can be used interchangeably. In case of mixed adoption, the same number of merit pattern problems and defective pattern problems can be adopted.

In addition, when determining job suitability, the AI server 400 evaluates the similarity between the adopted merit pattern and the personality test results to give additional points, and evaluates the similarity between the adopted defective pattern and the personality test results to give additional points. By subtracting from the score, a person with a high score is judged to have a high job suitability among the comparison group that took the relevant personality test. It is configured to do so.

For example, the AI server 400 selects 20 problems as merit patterns and detective patterns, and compares them with problems corresponding to the 20 merit patterns from the aptitude test results. If the correct answer is given to 15 merit pattern problems, An additional score of 15 points is given, and if you answer 10 correct answers to a defective pattern problem, 10 points can be deducted. In this case, the personality suitability can be set by adding the addition and subtraction points, and in this case, the personality suitability can be 5 points by adding the addition and subtraction points.

In addition, the AI server 400 is configured to give a higher score or subtract more points by assigning weight when giving additional points using a merit pattern or when giving subtractive points using a defective pattern. For example, from the aptitude test results, for merit pattern questions, if the correct answer is 0, you will get 0 points, if you have 1 correct answer, you will get 1 point, if you have 2 correct answers, you will get 2.5 points, if you have 3 correct answers, you will get 4 points, and if you have 3 correct answers, you will get 4 points. 5.5 points for individual answers, 7 points for 5 correct answers, 9 points for 6 correct answers, 11 points for 7 correct answers, 13 points for 8 correct answers, and 15 points for 9 correct answers. , 17 points for 10 correct answers, 19 points for 11 correct answers, 21 points for 12 correct answers, 23 points for 13 correct answers, 25 points for 14 correct answers, 15 correct answers 27 points for correct answers, 30 points for 16 correct answers, 33 points for 17 correct answers, 36 points for 18 correct answers, 42 points for 19 correct answers, and 50 points for 20 correct answers. Additional points may be awarded. Conversely, for defective patterns, the score can be subtracted by weighting each section in the same way as for merit patterns. In other words, to summarize, if you get 1 question right, you get 1 point, if you get 2 to 5 questions right, 1.5 points are added to the previous score, and if you get 6 to 15 questions right, you get 1 point. The score is calculated by adding 2 points to each previous score. If 16 to 18 questions are correct, 3 points are added to the previous score. If 19 questions are correct, 6 points are added to the previous score. It is calculated by adding , and if 20 questions are answered correctly, 8 points are added to the previous score. In the same way, the defective pattern can also be calculated by assigning weights. Here, the method of calculating each merit pattern and defective pattern by weighting each section according to the number of correct answers is explained as an example, and the weighted section can be easily changed.

If a problem that matches the selected merit pattern and defective pattern occurs, the AI server 400 excludes it from each merit pattern and defective pattern and replaces it with the same number of problems as the excluded problem.

In addition, the merit patterns and defective patterns derived by the AI server 400 can be subdivided and extracted for each job, and the personality suitability can be determined for each job accordingly. For example, merit patterns and defective patterns can be formed for each job, such as research institutes, design departments, human resources departments, etc., and personality suitability for each job can be calculated. For example, personality and sexual suitability can be calculated by determining the personality and sexual suitability for each job for employees selected as new employees. Decision makers within the company can determine the job of the new employee by referring to the personality suitability derived for each job. In other words, personality suitability can be used as an indicator to determine the employee's job after completing the personality test.

Figure 2 is a flow chart showing the process of job suitability personality testing using big data according to an embodiment of the present invention.

Referring to FIG. 2, first, in step S202, the aptitude test server 200 loads the aptitude test database 300, scores the aptitude test, and stores the scoring results in the aptitude test database 300.

In step S204, the personality test database 300 extracts a high performer group consisting of people who are employed at a company and classified as high performers by the company from the information on people who solved the personality test problems performed by the personality test server 200. . High performers can be extracted for each job.

In step S206, the AI server 400 extracts the problems of high performers from the personality test results corresponding to the high performer group and forms a merit pattern.

In step S208, the personality test database 300 extracts a low performer group consisting of people who are employed at a company and are classified as low performers by the company from the information on people who solved the personality test problem performed by the personality test server 200. . Low-performing groups can be extracted for each job.

In step S210, the AI server 400 extracts the problems of low performers from the personality test results corresponding to the low performer group and forms a defective pattern. In particular, the problems solved by the high-performing group and the low-performing group can be extracted by extracting only the personality test, only the aptitude test, or mixing the personality test and the aptitude test in equal proportions.

In step S212, the AI server 400 grants additional and subtracted points to personality test questions corresponding to the merit pattern and defective pattern, respectively. In the process of awarding additional and subtracted points, additional and subtracted points can be assigned by assigning weights according to the number of questions in each section that correspond to the merit pattern in the aptitude test results.

In step S214, the AI server 400 calculates the personality suitability by subtracting the subtracted points from the added points. Meanwhile, as described above, high-performing groups and low-performing groups can be extracted for each job, and merit patterns and defective patterns can be formed for each job correspondingly. In addition, personality suitability can be measured for each job group, and can be employed and applied to each job.

Figure 3 is a flowchart showing the process of configuring the merit pattern of Figure 2 according to an embodiment of the present invention.

Referring to FIG. 3, in step S302, the AI server 400 calculates the average value, variance, and deviation of the percentage of correct answers answered by high performers in order to extract questions with a high percentage of correct answers from the group of high performers extracted from the personality test database 300. .

In step S304, the average value, variance, and deviation of the percentage of correct answers from the high-performing group are obtained and the questions are arranged in order of highest absolute deviation.

In step S306, the AI server 400 selects a certain number of problems in the order of highest absolute deviation among the problems of the sorted group of high performers and stores them as a merit pattern. Here, the certain number of problems may preferably be 20 problems.

Figure 4 is a flowchart showing the process of configuring the defective pattern of Figure 2 according to an embodiment of the present invention.

Referring to FIG. 4, in step S402, the AI server 400 calculates the average value, variance, and deviation of the correct answer rates of low performers in order to extract questions with a high correct answer rate from the low performers extracted from the personality test database 300. .

In step S404, the average value, variance, and deviation of the percentage of correct answers from the low-performing group are obtained and the questions are arranged in order of highest absolute deviation.

In step S406, the AI server 400 selects a certain number of problems in the order of highest absolute deviation among the problems of the sorted group of low performers and stores them as a defective pattern.

Figure 5 is a flowchart showing the process of calculating the addition and subtraction points of Figure 2 according to an embodiment of the present invention.

Referring to FIG. 5, in step S502, the AI server 400 calculates an additional value by weighting the number of correct answers to the merit pattern problem according to the section. In particular, it can be configured to give a higher weight as more matches are made.

In step S504, the AI server 400 calculates a subtraction value by weighting the number of correct answers to the problem of the defective pattern according to the section. In particular, it can be configured to give a higher weight as more matches are made.

In step S506, the AI server 400 also determines whether there are overlapping problems among the merit pattern and defect pattern problems.

The AI server 400 determines in step S506 that, if there are overlapping problems among the merit pattern and defect pattern problems, it excludes the overlapping problems from the merit pattern and defective pattern, respectively (step S508).

In step S510, the AI server 400 forms the merit pattern and defective pattern problems by supplementing the same number of problems as the number of overlapping problems among the merit pattern and defective pattern problems. The problems supplemented here can be selected from the problems of the next highest order that were not selected among the problems arranged in order of problems with high absolute deviation in steps S302 and S404.

What has been described above is only an example for implementing the job suitability personality test system and method using big data according to the present invention, and the present invention is not limited to the above-described embodiment, but is as claimed in the patent claims below. Likewise, it will be said that the technical spirit of the present invention exists to the extent that anyone with ordinary knowledge in the field to which the present invention pertains can make various modifications without departing from the gist of the present invention.

10: wired and wireless communication network 100: terminal
200: Personality test server 300: Personality test database
400: AI server

Claims (10)

When applying for a personality test online, personality test questions are provided at a designated location online or offline at the request of the applicant. When applying for a personality test offline, personality test questions are provided at a designated location offline and the provided personality test is provided. An aptitude test server that scores questions and provides aptitude test results when grading is completed;
Among the result information of people who took the personality test performed by the personality test server, the test results of people who were employed at a company and classified as high performers by the company are stored as a high performer group, and the personality test questions and aptitude from the high performer group are stored. Classify it as a test problem and extract the propensity analysis problems of high performers, save the test results of people who are employed at a company and classified as low performers by the company as a low performer group, and classify the low performer group into personality test problems and aptitude test problems. a personality test database that extracts low-performing propensity analysis problems; and
From the propensity analysis problems of high performers extracted from the above personality test database, the average value, variance, and deviation of the percentage of correct answers answered by each high performer are calculated, arranged in the order of the highest absolute deviation, and a certain number of problems are selected in the order of the highest absolute deviation. After adoption, the pattern of answers adopted for each question is stored as a merit pattern, and the most frequently selected answer from the low performer extraction result extracted from the personality test database is stored as a merit pattern of the person who selected the corresponding answer from the sample of low performers. After calculating the average value, variance, and deviation, arranging the problems in the order of the highest absolute deviation, selecting a certain number of problems in the order of the highest absolute deviation, saving the selected problems as a defective pattern, and storing the merit pattern and the aptitude test test results. A job suitability personality test system using big data that includes an AI server that evaluates the similarity and determines job suitability by evaluating the similarity with the personality test test results of the defective pattern. The method of claim 1, wherein the AI server,
In determining job suitability, additional points are given by evaluating the similarity between the adopted merit pattern and the job suitability test results, and subtracted points are given by evaluating the similarity between the adopted defective pattern and the job suitability test results. Points are subtracted from the added points. A job suitability personality test system using big data that calculates the personality suitability by subtracting the value. The method of claim 2, wherein the AI server,
A job suitability personality test system using big data that stores high and low performers for each job, forms merit patterns and defective patterns for each job, and calculates personality suitability for each job. According to paragraph 3,
The AI server excludes the two problems with the lowest absolute deviation among the problems constituting the merit pattern at regular time intervals and replaces the two problems with other problems, and determines the deviation among the problems constituting the defective pattern. The two problems with the lowest scores are excluded and replaced with other problems. If there are overlapping problems among the above merit and disadvantage patterns, the overlapping problems are excluded and replaced with the problem with the next highest iron deviation value equal to the excluded problem. A job suitability personality test system using big data that consists of: According to paragraph 3,
In extracting problems that constitute merit patterns and defective patterns, the AI server performs tasks using big data that are composed of personality test problems, written test problems, or a mixture of personality test problems and written test problems. Suitability personality test system. A personality test server loading the personality test database, scoring the personality test, and storing the scoring results in the personality test database;
The personality test database includes a first extraction step of extracting a high performer group consisting of people who are employed at a company and classified as high performers by the company from the information of people who solved the personality test problem performed by the personality test server;
A step where the AI server extracts the problems of high performers from the personality test results corresponding to the high performers and forms a merit pattern;
The personality test database includes a second extraction step of extracting a low performer group consisting of people who are employed at a company and classified as low performers by the company from the information of people who solved the personality test problem performed by the personality test server;
A step where the AI server extracts the problems of low performers from the personality test results corresponding to the low performer group and forms a defective pattern;
The AI server grants additional and subtracted points to personality test questions corresponding to merit patterns and defective patterns, respectively; and
A job suitability personality test method using big data that includes a calculation step in which the AI server calculates the personality suitability by subtracting the deduction points from the addition points. According to clause 6,
The job suitability personality test method using big data is configured to store the high performer group and low performer group for each job, form merit patterns and defective patterns for each job, and calculate personality suitability for each job. The method of claim 7, wherein the first extraction step is,
A step where the AI server calculates the average value, variance, and deviation of the correct response rate of high performers;
A step where the AI server obtains the average value, variance, and deviation of the percentage of correct answers from the group of high performers and places them in order of the problems with the highest absolute deviation; and
A job suitability personality test method using big data that includes the step of the AI server selecting a certain number of problems in the order of highest absolute deviation among the problems of the sorted group of high performers and storing them as a merit pattern. The method of claim 7, wherein the second extraction step is,
A step where the AI server calculates the average value, variance, and deviation of the correct response rate of low performers;
The AI server calculates the average value, variance, and deviation of the percentage of correct answers from the low-performing group and arranges them in order of the problems with the highest absolute deviation;
A job suitability personality test method using big data that includes the step of selecting a certain number of problems in the order of highest absolute deviation among the problems of the low performers sorted by the AI server and storing them as a defective pattern. The method of claim 7, wherein the calculation step is,
A step where the AI server calculates an additional value by weighting the number of correct answers to the merit pattern problem according to the section;
A step where the AI server calculates a subtraction value by weighting the number of correct answers to the problem of the defective pattern according to the section;
The AI server performs a judgment step to determine whether there are overlapping problems among the merit pattern and defect pattern problems;
A step where the AI server determines in the judgment stage that if there are overlapping problems among the merit pattern and defect pattern problems, the overlapping problems are excluded from the merit pattern and defective pattern, respectively; and
A job suitability personality test method using big data that includes a step where the AI server reorganizes the problems of the merit pattern and defective pattern by supplementing the same number of problems as the number of overlapping problems among the problems of the merit pattern and defective pattern.