KR101884167B1 - Artificial intelligence based job and institution matching system - Google Patents

Abstract

The present invention relates to an artificial intelligence-based job and education institution matching system which matches a job seeker to a job offer company or provides job education information. The artificial intelligence-based job and education institution matching system comprises: a personal information inputting module which receives input of user′s personal information; a career gene generating module which generates a first career gene based on the user′s personal information input into the personal information inputting module; a target career gene generating module which additionally receives user′s personal information and generates a second career gene or a third career gene based on the first career gene and career big-data; a job matching module which matches the second career gene to a job; and an education institution matching module which matches the third career gene to the education institution. The target career gene generating module checks whether the first career gene satisfies predetermined qualifications based on the career big-data. When the first career gene satisfies the qualifications, the target career gene generating module generates the second career gene, which is generated by adding job preference score information to the first career gene. When the first career gene does not satisfy the qualifications, the target career gene generating module generates the third career gene, which is generated by adding needed education information to the first career gene.

Description

ARTIFICIAL INTELLIGENCE BASED JOB AND INSTITUTION MATCHING SYSTEM.

The present invention relates to artificial intelligence based jobs and educational institution matching systems.

Job matching is becoming an increasingly important social problem in all countries by assigning the right job seekers to the right companies.

If such job matching is done by an employment counselor who can not review all profiles of the job seeker and the company profile, it may lead to miss-matching that assigns the wrong candidate to the wrong company.

In the case of job matching using statistical methods such as conventional least squares, Pearson correlation, and Manhattan distance, about 30% of mismatching is still occurring.

Job seekers, on the other hand, will be required to have various qualifications, career, academic background and foreign language requirements of the applicant institution. In particular, jobseekers may not have accurate information about employment requirements of job hunting organizations or survive in job competition, and may have career experiences that go beyond the requirements of job seeking organizations that they want to hire. This phenomenon eventually leads to an increase in social costs.

However, there is no system that accurately suggests job seekers 'job requirements to job seekers based on the system that accurately matches job seekers to the company they are seeking, or personal information such as job seekers' gender, academic background, and career .

On the other hand, the technology as a background of the present invention is disclosed in Korean Patent Registration No. 10-1781783.

The present invention provides an artificial intelligence based job and educational institution matching system that accurately matches a job seeker to a job offer company or suggests education information so that a job seeker can get a job at a job offer company.

---수학식 1

는 선호 주제 매칭 점수이고,

는 구인기관의 선호 주제에 관한 선호 점수이고,

는 구직자의 선호 주제에 관한 선호 점수이고,

는 구직자와 구인기관의 외부인자 점수이고,

는 취업일까지 기다리는 시간 점수이고,

는 구인기관 까지의 이동거리 점수를 의미하며,

는 연봉/복지 점수이고,

는 구직자의 패널티 점수이고,

는 구직자의 적성검사 점수이고,

는 구직자의 이직 이력 점수이고,

구직자의 회사 직무관련 이직 이력 점수이고, 상기 교육기관 매칭 모듈은, 하기의 수학식 2에 의해 산정된 선호 점수에 따라, 매칭된 교육기관의 순위를 산출하는 것을 특징으로 하며,

---수학식 2
여기서,

교과목 매칭 점수를 의미하고,

는 교육기관의 교과목에 대한 점수를 의미이고,

는 수강생의 교과목에 대한 점수이고,

은 수강생과 교육기관의 외부인자 점수이고,

는 교육시작일까지 기다리는 시간 점수이고,

는 교육기관 까지의 이동거리 점수이고,

은 수강생의 패널티 점수이고,

는 수강생의 적성검사 점수이고,

는 수강생의 교육 중도 포기 이력 점수이고,

는 교육기관의 교과목 수강생의 중도 포기 이력 점수이고, 상기 커리어 진 생성모듈에서 생성된 상기 제1커리어 유전자에 관한 정보는 복수의 서버에 분산되어 저장되는 것을 특징으로 한다.The artificial intelligence-based job and educational institution matching system of the present invention comprises: a personal information input module for inputting personal information of a user; A career generation module for generating a first career gene based on personal information of a user input to the personal information input module; A target career generation module for receiving a user's personal information additionally to generate a second career gene or generating a third career gene; A job matching module for matching the second career gene with a job; And an educational institution matching module for matching the third career gene with an educational institution, wherein the target career generation module checks whether the first career gene satisfies predetermined qualification requirements based on the career big data Generating the second career gene to which job preference score information is added to the first career gene when the first career gene satisfies the qualification requirement, and when the first career gene is not satisfied with the eligibility requirement And generating the third career gene to which the necessary education information is added to the first career gene, wherein the job matching module is configured to generate the third career gene by adding the necessary career information to the first career gene according to the preference score calculated by the following equation And an organ rank is calculated,

(1)

Is a preference topic matching score,

Is the preference score on the preferred subject of the job placement institution,

Is a preference score on a subject of preference of a job seeker,

Is the external factor score of job seekers and job seekers,

Is the number of hours waiting for work,

Means the moving distance score to the job agency,

Is the salary / welfare score,

Is the penalty score of the job seeker,

Is the aptitude test score of the job seeker,

Is the turnover history score of the job seeker,

The educational institution matching module calculates a ranking of matching educational institutions according to a preference score calculated by the following equation (2)

- (2)
here,

This means that,

Means the score for the curriculum of the educational institution,

Is the score for the student's course,

Is the external factor score of the learner and the institution,

Is the number of hours waiting until the training start date,

Is the moving distance score to the educational institution,

Is the penalty score of the student,

Is the aptitude test score of the learner,

Is the score of the students' abandonment history of education,

And the information on the first career gene generated by the career generation module is distributed and stored in a plurality of servers.

delete

delete

delete

delete

delete

delete

delete

delete

delete

The artificial intelligence based job and educational institution matching system may further include an information providing module for providing the user with information on the matching institution of the job matched in the job matching module and the educational institution matched in the education institution matching module have.

The present invention enables an artificial intelligence based job and educational institution matching system to accurately match a job seeker to a job offerer without mismatching.

In addition, the artificial intelligence-based job and educational institution matching system of the present invention can present educational information so that a job seeker can get a job at a job offer company.

1 is a block diagram of an artificial intelligence-based job and educational institution matching system according to an embodiment of the present invention,
Fig. 2 is a diagram for explaining the first career gene,
3 is a diagram for explaining the second career gene,
4 is a diagram for explaining the third career gene,
FIG. 5 is a diagram for explaining a career generation module and a target career generation module of the artificial intelligence based job and educational institution matching system of FIG. 1. FIG.

Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that, in adding reference numerals to the constituent elements of the drawings, the same constituent elements are denoted by the same reference symbols as possible even if they are shown in different drawings.

In the following description of the embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the understanding why the present invention is not intended to be a complete disclosure.

In describing the components of the embodiment of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are intended to distinguish the constituent elements from other constituent elements, and the terms do not limit the nature, order or order of the constituent elements.

Hereinafter, an artificial intelligence based job and educational institution matching system according to an embodiment of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram of an artificial intelligence-based job and educational institution matching system according to an embodiment of the present invention, FIG. 2 is a diagram for explaining a first career gene, FIG. 3 is a diagram for explaining a second career gene FIG. 4 is a diagram for explaining a third career gene, and FIG. 5 is a diagram for explaining a career creation module and a target career creation module in the artificial intelligence based job and educational institution matching system of FIG.

1 to 5, an artificial intelligence based job and educational institution matching system 100 according to an exemplary embodiment of the present invention includes a personal information input module 110, a career creation module 120, A module 130, and a job matching module 140, and an institution matching module 150.

The personal information (PD) of the user can be inputted through the personal information input module 110. Here, the user can be a job seeker for a job, a student who needs a job to get a job, a job seeker, or a student.

The personal information PD may include first personal information PD1, second personal information PD2, and third personal information PD3.

For example, the first personal information PD1 may include age information, gender information, address information, contact information, personality information, and aptitude check information. The second personal information PD2 may include education information, career information, language information, and certification information. The third personal information PD3 may be the desired job information, the desired job information, the position information of the desired job, and the desired salary information.

The first personal information PD1 to the third personal information PD3 may be sequentially input by the job seeker into the personal information input module 110. [

The career generation module 120 generates the first career gene CG1 based on the personal information PD input from the personal information input module 110. [

For example, the career generation module 120 may generate the first career gene CG1 (CG1), which sequentially connects the first personal information PD1, the second personal information PD2 and the third personal information PD3, Can be generated.

The target career generation module 130 generates the personal information PD for generating the second career gene CG2 based on the first career gene CG1, the career big data, and the educational institution big data Or generate a third career gene (CG3).

The career big data and educational institution big data refer to job related big data stored in an external server. For example, the career big data and educational institution big data may be data of the Korean National Statistical Office, SNS data, educational institution data, and the like.

Meanwhile, the first personal information PD1 to the third personal information PD3 included in the first career gene CG1 may be dispersed in a plurality of servers 21, 22, and 23, respectively.

That is, the career generation module 120 generates the first career gene CG1 and then transmits the first personal information PD1 to the third personal information PD3 to the plurality of servers 21, 22, and 23, respectively.

For example, the first personal information PD1 to the third personal information PD3 are distributed and stored in the first server 21, the second server 22, and the third server 23, It is possible to prevent personal information PD from being leaked.

More specifically, the first server 21 to the third server 23 include a first storage table t1 in which the first personal information PD1 to the third personal information PD3 can be stored, , A second storage table (t2), and a third storage table (t3), respectively.

The first personal information PD1 is stored in the first storage table t1 of the first server 21 and the second personal information PD1 is stored in the second storage table t2 of the second server 22. [ And the third personal information PD3 may be stored in the third storage table t3 of the third server 23. [

The IP address of the second server 22 is stored in the second storage table t2 of the first server 21 in the third storage table t3 of the first server 21, The IP address of the first server 21 is stored in the first storage table t1 of the second server 22 and the IP address of the second server 22 is stored in the third storage table t3 of the second server 22. [ The IP address of the third server 23 is stored in the first storage table t1 of the third server 23 and the IP address of the first server 21 is stored in the first storage table t1 of the third server 23. [ The IP address of the third server 23 may be stored in the second storage table t2.

The target career generation module 130 accesses the first server 21 to acquire the first personal information PD1 and the IP addresses of the second server 22 and the third server 23 , The second server 22 and the third server 23 should be accessed to acquire the second personal information PD2 and the third personal information PD3.

And generate the second career gene CG2 and the third career gene CG3.

That is, in the present invention, even if the first server 21 obtains the first personal information PD1, in order to acquire the second personal information PD2 and the third personal information PD3, The IP address of the second server 22 stored in the first server 21 and the IP address of the third server 23 should be also accessible.

The target career generation module 130 determines whether the first career gene CG1 satisfies a predetermined qualification requirement based on the career big data and if the first career gene CG1 satisfies the qualification requirement It is possible to generate the second career gene CG2 to which the job preference score information PD4 is added to the first career gene CG1.

The occupational preference score information PD4 may include job preference score information, straightwork preference score information, local preference score information, and salary preference score information input by a job seeker.

If the first career gene CG1 is not satisfied with the eligibility requirement, the target career generation module 130 generates the target education information PD5 to which the necessary education information PD5 is added to the first career gene CG1. 3 < / RTI > carrier gene (CG3).

Herein, the necessary education information (PD5) is information about education and training required for a job seeker.

The job matching module 140 may match the second career gene CG2 with a job.

The job matching module 140 matches the job based on the job seeker personal information extracted from the second career gene CG2 and the professionalism and eligibility information of the job extracted from the career big data and the education institution big data .

In more detail, the job matching module 140 may calculate a candidate job ranking of a matched job according to a preference score calculated by the following equation (1).

는 선호 주제 매칭 점수를 의미하고,

는 구인기관의 선호 주제에 관한 선호 점수를 의미하고,

는 구직자의 선호 주제에 관한 선호 점수를 의미한다.Here, C denotes the number of job centers, S denotes the number of job seekers,

Is a preference topic matching score,

Means the preference score on the preferred subject of the applicant institution,

Means the preference score on the subject of preference of the job seeker.

는 구직자와 구인기관의 외부인자 점수를 의미하고,

는 취업일까지 기다리는 시간 점수를 의미하고,

는 구인기관 까지의 이동거리 점수를 의미하며,

는 연봉/복지 점수를 의미한다.

The mean score of job seekers and job seekers is the external factor,

Means the number of hours spent waiting for work,

Means the moving distance score to the job agency,

Means salary / welfare score.

는 구직자의 패널티 점수를 의미하고,

는 구직자의 적성검사 점수,

는 구직자의 이직 이력 점수,

구직자의 회사 직무관련 이직 이력 점수를 의미한다.

Means the job seeker's penalty score,

The job seeker's aptitude test scores,

The results of this study are as follows.

Job history of the job seeker.

는 구직자의 패널티 점수 반영하여 구직자가 구인기관에 취업한 후 이직하는 비율을 낮출 수 있다.In the present invention,

May reduce the percentage of jobseekers leaving the job center after they are employed by reflecting the penalty score of the jobseeker.

의 수치가 낮을 수록, 완벽한 매칭(perfect matching)에 가까워지는 구인기관을 의미한다. 따라서 본 발명에서는 완벽한 매칭(perfect matching)에 해당하는 복수의 구인기관이 발견될 경우, 구직자에게 최적의 구인기관을 할당해 줄 수 있있다.And,

The lower the value of the term, the closer to perfect matching. Therefore, in the present invention, when a plurality of job search engines corresponding to perfect matching are found, it is possible to assign an optimum job search organization to a job seeker.

The educational institution matching module 150 may match the third career gene CG3 with an educational institution.

The educational institution matching module 150 may be configured to determine the educational institution based on the personal information of the applicant extracted from the second career gene CG2, the location of the educational institution extracted from the career big data and the educational institution big data, And matching educational institutions.

In more detail, the educational institution matching module 150 may calculate the ranking of the educational institutions of the matched jobs according to the preference score calculated by the following equation (2).

교과목 매칭 점수를 의미하고,

는 교육기관의 교과목에 대한 점수를 의미하고,

는 수강생의 교과목에 대한 점수를 의미한다.Here, e represents the number of educational institutions, k represents the number of students,

This means that,

Is the score for the curriculum of the educational institution,

Means the score for the course of the student.

은 수강생과 교육기관의 외부인자 점수를 의미하고,

는 교육시작일까지 기다리는 시간 점수를 의미하고,

는 교육기관 까지의 이동거리 점수를 의미한다.

Means the external factor scores of the learner and the institution,

Means the number of hours waiting until the training start date,

Means the distance traveled to the educational institution.

의 수강생과 교육기관의 외부인자 점수가 반영되기 때문에 수강생이 최소시간에 구인기관의 자격요건을 갖출 수 있다.In the present invention,

And the external factor scores of the institution are reflected, so that the learner can achieve the qualification of the applicant institution at the minimum time.

은 수강생의 패널티 점수를 의미하고,

는 수강생의 적성검사 점수이고,

는 수강생의 교육 중도 포기 이력 점수이며,

는 교육기관의 교과목 수강생의 중도 포기 이력 점수이다.

Means the penalty score of the learner,

Is the aptitude test score of the learner,

Is the score of abandonment history of the students,

Is the score of midterm abandonment of the students of the curriculum of the educational institution.

의 수강생의 패널티 점수 반영하여 수강생이 교육기관의 교육 과정을 중도 포기하는 비율을 낮출 수 있다.In the present invention,

The penalty score of the student can be lowered to the degree that the student abandons the curriculum of the institution.

는 수치가 낮을 수록, 완벽한 매칭(perfect matching)가까워지는 것을 의미한다.And

The lower the value, the closer to perfect matching.

The second career gene CG2 and the second career gene CG3 generated by the target career generation module 130 are also dispersed in the plurality of servers 21, 22 and 23 .

The artificial intelligence based job and educational institution matching system 100 may further include an information providing module 160.

The information providing module 160 provides information to the job seeker about information on a matching institution of a job matched in the job matching module 140 and information on an educational institution matched by the matching module 150.

The artificial intelligence based job and educational institution matching system 100 may further include a life cycle career management module 170.

The job seeker can continuously manage his / her personal information (PD) through the life cycle career management module 170. [

Hereinafter, perfect matching and mismatching are compared between the conventional Least Squares, Inverse Pearson Correlation, and the job matching using the artificial intelligence based job and educational institution matching system 100 of the present invention.

Experimental Example _ Analysis Conditions

84 applicants, and 54 recruitment agencies, respectively. The preference score for the preferred subject of 84 job seekers and 54 job applicants was 0 to 9 as shown in the following equation (3).

는 구인기관의 선호 주제에 관한 선호 점수를 의미하고, 는

는 구직자의 선호 주제에 관한 선호 점수를 의미한다. 여기서 c는 구인기관을 의미하고, s는 구직자를 의미하며, k는 선호 주제를 의미한다.

Means the preference score on the preferred subject of the applicant institution, and

Means the preference score on the subject of preference of the job seeker. Where c stands for job agency, s stands for job seeker, and k stands for preferred subject.

The preferred subject (k) is shown in Table 1 below.

 turn Preferred topic (K) One Inventory and Material Management (IM) 2 Process Management (PM) 3 Quality Management (QM) 4 Human Resource Management (HR) 5 Ergonomics (Er) 6 Financial / Investment Analysis (FI) 7 Supply Chain Management / Customer Relationship Management (SCRM) 8 Knowledge Management (K) 9 Strategic Management (S)

Comparative Example 1_ Least Squares

We matched the applicant and the job seeker using Equation 4 below regarding the least squares method.

Table 2 below shows the result of matching job seekers with job seekers using the least squares method. Perfect match

The perfect matching, which means perfect matching, is indicated by (P) in each locomotive, the second perfect matching, which means lane matching, is indicated by (S) in each locomotive, and the miss- (M), and 17 cases were found for the miss-matching by the least squares method and 3 cases were found for the second perfect matching.

C_ID C1 (P) C2 (P) C3 (P) C4 (P) C5 (P) C6 (P) C7 (P) C8 (M) C9 (P) S_ID 76 One 41 3 4 12 27 25 2 C_ID C10 (P) C11 (P) C12 (P) C1 (P) C14 (M) C15 (M) C16 (M) C17 (P) C18 (M) S_ID 6 11 21 38 22 69 7 71 18 C_ID C19 (P) C20 (P) C21 (M) C22 (P) C23 (P) C24 (P) C25 (P) C26 (M) C27 (P) S_ID 45 43 24 34 60 5 13 17 8 C_ID C28 (P) C29 (M) C30 (P) C31 (P) C32 (P) C33 (P) C34 (P) C35 (P) C36 (M) S_ID 28 26 31 68 14 36 37 15 63 C_ID C37 (P) C38 (M) C39 (P) C40 (P) C41 (S) C42 (P) C43 (M) C44 (M) C45 (S) S_ID 20 70 53 35 40 73 30 33 46 C_ID C46 (M) C47 (P) C48 (M) C49 (M) C50 (M) C51 (M) C52 (P) C53 (P) C54 (S) S_ID 23 29 55 32 42 81 39 59 44

Comparative Example 2_ Inverse Pearson Correlation [

We matched the applicant and the applicant using the following equation (5) regarding the Pearson correlation method.

Table 3 below shows the result of matching job applicants with job applicants using Pearson correlation method. Perfect perfect matching, which means perfect matching, is indicated by (P) in each job seeking institution. Second perfect matching, which means lane matching, is indicated by (S) in each job agency, and miss- (M) for each locomotive, 24 miss-matching by Pearson's correlation method, and 10 second perfect matching.

C_ID C1 (P) C2 (M) C3 (P) C4 (M) C5 (P) C6 (P) C7 (M) C8 (S) C9 (P) S_ID 76 60 41 55 3 13 46 42 One C_ID C10 (M) C11 (M) C12 (P) C13 (S) C14 (M) C15 (M) C16 (P) C17 (P) C18 (P) S_ID 20 39 21 47 38 7 69 71 4 C_ID C19 (P) C20 (M) C21 (S) C22 (M) C23 (M) C24 (P) C25 (P) C26 (S) C27 (P) S_ID 45 14 36 8 59 2 12 70 5 C_ID C28 (P) C29 (S) C30 (M) C31 (M) C32 (P) C33 (P) C34 (P) C35 (S) C36 (M) S_ID 28 53 34 54 15 37 73 6 23 C_ID C37 (P) C38 (M) C39 (M) C40 (M) C41 (S) C42 (M) C43 (M) C44 (S) C45 (S) S_ID 11 25 78 17 40 24 26 57 49 C_ID C46 (P) C47 (P) C48 (M) C49 (M) C50 (M) C51 (M) C52 (M) C53 (M) C54 (S) S_ID 35 29 77 18 48 81 50 27 31

Example 1

Using the above-described Equation (1) of the present invention, the job institution and the job seeker were matched.

Table 4 shows the result of matching the job seeker using the present invention including Equation (1).

와,

인자에 기인한 것이다.No miss-matching was found to indicate false matching, and five perfect matches were found, and all of the others were found to be perfect matching. In this case,

Wow,

It is due to the factor.

C_ID C1 (P) C2 (P) C3 (P) C4 (P) C5 (P) C6 (P) C7 (P) C8 (P) C9 (P) S_ID 76 One 41 3 4 13 27 8 2 C_ID C10 (P) C11 (P) C12 (P) C13 (P) C14 (P) C15 (P) C16 (P) C17 (P) C18 (P) S_ID 6 11 21 38 46 28 69 71 81 C_ID C19 (P) C20 (P) C21 (P) C22 (P) C23 (P) C24 (P) C25 (P) C26 (P) C27 (P) S_ID 45 22 18 25 14 5 12 17 9 C_ID C28 (P) C29 (P) C30 (P) C31 (P) C32 (P) C33 (P) C34 (P) C35 (P) C36 (P) S_ID 20 54 15 43 36 37 73 60 10 C_ID C37 (P) C38 (P) C39 (P) C40 (P) C41 (P) C42 (P) C43 (P) C44 (P) C45 (S) S_ID 24 16 53 7 40 19 47 49 51 C_ID C46 (P) C47 (P) C48 (S) C49 (S) C50 (S) C51 (P) C52 (P) C53 (P) C54 (S) S_ID 35 29 30 75 57 31 33 39 32

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them.

Furthermore, the terms "comprises", "comprising", or "having" described above mean that a component can be implanted unless otherwise specifically stated, But should be construed as including other elements. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used terms, such as predefined terms, should be interpreted to be consistent with the contextual meanings of the related art, and are not to be construed as ideal or overly formal, unless expressly defined to the contrary.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or essential characteristics thereof. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

100: Artificial intelligence based job and institution matching system
110: personal information input module
120: Career Generation Module
130: target career generation module
140: Job Matching Module
150: Institution matching module

Claims (7)

A personal information input module for inputting personal information of a user;
A career generation module for generating a first career gene based on personal information of a user input to the personal information input module;
A target career generation module for receiving a user's personal information additionally to generate a second career gene or generating a third career gene;
A job matching module for matching the second career gene with a job; And
And an educational institution matching module for matching the third career gene with an educational institution,
Wherein the target career generation module determines whether the first career gene satisfies predetermined qualification requirements based on the career big data and determines whether the first career gene satisfies the qualification requirement, Generates the second career gene to which the occupation preference score information is added, and generates the third career gene to which necessary education information is added to the first career gene if the first career gene is not satisfied with the eligibility requirement .
Wherein the job matching module comprises:
The job position ranking of the matched job is calculated according to the preference score calculated by the following equation (1)

(1)

Is a preference topic matching score,

Is the preference score on the preferred subject of the job placement institution,

Is a preference score on a subject of preference of a job seeker,

Is the external factor score of job seekers and job seekers,

Is the number of hours waiting for work,

Means the moving distance score to the job agency,

Is the salary / welfare score,

Is the penalty score of the job seeker,

Is the aptitude test score of the job seeker,

Is the turnover history score of the job seeker,

Job history of the job seeker,
The educational institution matching module comprises:
The ranking of matching educational institutions is calculated according to the preference score calculated by the following equation (2)

- (2)
here,

This means that,

Means the score for the curriculum of the educational institution,

Is the score for the student's course,

Is the external factor score of the learner and the institution,

Is the number of hours waiting until the training start date,

Is the moving distance score to the educational institution,

Is the penalty score of the student,

Is the aptitude test score of the learner,

Is the score of the students' abandonment history of education,

Is the score of midterm abandonment of the students of the curriculum of the educational institution,
Wherein the information on the first career gene generated by the career generation module is distributed and stored in a plurality of servers. delete delete delete delete delete The method according to claim 1,
And an information providing module for providing the user with information on a matching institution of the job matched in the job matching module and an educational institution matched in the matching module of the education institution.

Images