KR102466112B1 - System for providing recommendation service for majors suitable for the job - Google Patents

Abstract

The present invention relates to a system for providing a major recommendation service suitable for a job, and more specifically, to a system implementing a service providing a user with information on a major suitable for a job desired by the user, wherein the job information the user wishes to engage in in the future A user terminal for transmitting the following server unit through wired/wireless communication; and a server unit that calculates a degree of similarity between the job information of the user received from the user terminal and the major information, and transmits the major information, which is listed in order of similarity to the user terminal, to the user terminal. a job data storage unit configured to store job information including detailed knowledge required to perform the job for each job; a major data storage unit configured to store major information including information about various majors and detailed subjects constituting a curriculum of the corresponding major for each major; a natural language processing unit that performs natural language processing on the job information of the job data storage unit and the major information of the major data storage unit, and stores vectorized job information and vectorized major information; a similarity calculation unit that calculates a similarity value between the vectorized job information stored in the natural language processing unit and the vectorized major information using a Jaccard coefficient; and a result processing unit which extracts major information corresponding to job information of the user received from the user terminal from the major data storage unit in order of similarity values calculated by the similarity calculation unit and transmits the extracted major information to the user terminal. It is characterized by doing. According to the system for providing a major recommendation service suitable for a job according to the present invention, in recommending a major suitable for a job, natural language processing and Jaccard coefficient are used to determine the similarity between detailed knowledge constituting the job and detailed subjects constituting the major. After calculating the similarity between the relevant detailed knowledge and the major based on this calculation, the similarity between the job and the major is finally calculated and majors are recommended in order of high similarity, so that the major information suitable for the job desired by the user is conveniently However, it can be provided quickly and with high reliability, and accordingly, there is an effect of effectively helping the user to decide on a future career.

Description

System for providing recommendation service for majors suitable for the job {System for providing recommendation service for majors suitable for the job}

The present invention relates to a system implementing a service providing a user with major information suitable for a job desired by the user.

A job is a job in which a person is responsible and in charge of a position or occupation, and to perform such a job, detailed knowledge of one or more jobs is required. For example, in order to perform the job of 'database developer', specific job knowledge such as 'computer and electronic engineering', 'communication', 'arithmetic and mathematics', and 'English' is required.

For high school students who are about to go to college, the type of job or job they will have when they enter society is often determined by which college major they choose, so if you have a specific job or job in mind It can be seen that it is more important than anything else to preemptively select a major that is helpful in performing these jobs or duties.

Until now, as a method of recommending a major suitable for the job, a questionnaire to evaluate the job aptitude is presented to the student, and a method in which an expert recommends an appropriate major based on the result of the job aptitude test has been used. However, this method has the inconvenience of having to carry out a cumbersome job aptitude test for students, and it takes some time for the job aptitude test result to come out, so there are limitations in quickly recommending majors, and furthermore, the professionalism of consulting experts There is a problem that the suitability or accuracy of the major recommended according to the competency varies greatly.

1. Korea Patent No. 10-0856705 (2008. 09. 04.) 2. Korean Patent Publication No. 2016-0135451 (2016. 11. 28.)

The present invention has been derived to solve the above problems, and recommends a major that can quickly, conveniently and highly reliably provide major information suitable for a job desired by a user without going through a procedure such as a separate job aptitude test. Its purpose is to provide a service providing system.

The problem to be solved by the present invention is not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by those skilled in the art from the following description. will be.

The present invention, derived to solve the above problems, relates to a system for providing a major recommendation service suitable for a job, and more specifically, in a system implementing a service that provides a user with major information suitable for a job desired by a user, a user terminal that transmits job information that the user wishes to engage in in the future to the following server through wired/wireless communication; and a server unit that calculates a degree of similarity between the job information of the user received from the user terminal and the major information, and transmits the major information, which is listed in order of similarity to the user terminal, to the user terminal. a job data storage unit configured to store job information including detailed knowledge required to perform the job for each job; a major data storage unit configured to store major information including information about various majors and detailed subjects constituting a curriculum of the corresponding major for each major; a natural language processing unit that performs natural language processing on the job information of the job data storage unit and the major information of the major data storage unit, and stores vectorized job information and vectorized major information; a similarity calculation unit that calculates a similarity value between the vectorized job information stored in the natural language processing unit and the vectorized major information using a Jaccard coefficient; and a result processing unit which extracts major information corresponding to job information of the user received from the user terminal from the major data storage unit in order of similarity values calculated by the similarity calculation unit and transmits the extracted major information to the user terminal. It is characterized by doing.

According to the system for providing a major recommendation service suitable for a job according to the present invention, in recommending a major suitable for a job, natural language processing and Jaccard coefficient are used to determine the similarity between detailed knowledge constituting the job and detailed subjects constituting the major. After calculating the similarity between the relevant detailed knowledge and the major based on this calculation, the similarity between the job and the major is finally calculated and majors are recommended in order of high similarity, so that the major information suitable for the job desired by the user is conveniently However, it can be provided quickly and with high reliability, and accordingly, there is an effect of effectively helping the user to decide on a future career.

1 conceptually illustrates a major recommendation service providing system suitable for a job according to the present invention.
FIG. 2 shows an example in which major information suitable for a user's desired job is provided in order of high similarity in the system for providing a major recommendation service suitable for a job according to the present invention.
3 illustrates an example of job information stored in a job data storage unit in the system for providing a major recommendation service suitable for a job according to the present invention.
4 illustrates an example of major information stored in a major data storage unit in a major recommendation service providing system suitable for a job according to the present invention.
5 schematically illustrates the concept of a method for calculating the total similarity between a job and a major in a major recommendation service providing system suitable for a job according to the present invention.
6 illustrates an example of a process of calculating a degree of similarity through natural language processing in a major recommendation service providing system suitable for a job according to the present invention.
7 illustrates an example of a process of calculating a similarity value between detailed knowledge constituting a job and detailed subjects constituting a major in a similarity calculating unit of a major recommendation service providing system suitable for a job according to the present invention.
8 illustrates an example of a process of calculating a similarity value between detailed knowledge constituting a job and a major in a similarity calculation unit of a major recommendation service providing system suitable for a job according to the present invention.
9 illustrates an example of a process of calculating a total similarity value between a job and a major in a similarity calculating unit of a major recommendation service providing system suitable for a job according to the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, it should be understood that this is not intended to limit the present invention to specific embodiments, and includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

The present invention relates to a system for providing a major recommendation service suitable for a job, and more specifically, to a system implementing a service providing a user with information on a major suitable for a job desired by the user, wherein the job information the user wishes to engage in in the future A user terminal for transmitting the following server unit through wired/wireless communication; and a server unit that calculates a degree of similarity between the job information of the user received from the user terminal and the major information, and transmits the major information, which is listed in order of similarity to the user terminal, to the user terminal. a job data storage unit configured to store job information including detailed knowledge required to perform the job for each job; a major data storage unit configured to store major information including information about various majors and detailed subjects constituting a curriculum of the corresponding major for each major; a natural language processing unit that performs natural language processing on the job information of the job data storage unit and the major information of the major data storage unit, and stores vectorized job information and vectorized major information; a similarity calculation unit that calculates a similarity value between the vectorized job information stored in the natural language processing unit and the vectorized major information using a Jaccard coefficient; and a result processing unit which extracts major information corresponding to job information of the user received from the user terminal from the major data storage unit in order of similarity values calculated by the similarity calculation unit and transmits the extracted major information to the user terminal. It is characterized by doing.

Hereinafter, to aid understanding of the present invention, it will be described in detail through embodiments shown in the drawings. The embodiments shown in the drawings are only examples for explaining the present invention, and the scope of the present invention is not limited thereby.

In the present invention, the user terminal transmits job information that the user wishes to engage in in the future to the server unit through wired/wireless communication, and the user terminal responds by allowing the user to access the server unit through login. Any type of device can be used, and for example, it can be a smart phone, tablet PC, desktop PC, etc. used by the user.

In the present invention, the server unit calculates the degree of similarity between job information and major information of the user received from the user terminal as shown in the example shown in FIG. 2 and transmits major information listed in order of high similarity to the user terminal, As shown in FIG. 1 , the server unit includes a job data storage unit, a major data storage unit, a natural language processing unit, a similarity calculation unit, and a result processing unit.

In the present invention, the job data storage unit stores job information composed of information on various jobs and detailed knowledge required to perform the job for each job, and the job information is stored in text form. In addition, the job information preferably includes knowledge importance information for assigning a weight to each detailed knowledge in order to reflect the importance or proportion of detailed knowledge required for job performance. In the present invention, the accuracy and reliability of the recommended major information can be further increased by reflecting the knowledge importance information in calculating the similarity between jobs and majors. 3 shows an example of job information stored in the job data storage unit, and detailed knowledge corresponding to the job of 'big data analyst' includes 'arithmetic and mathematics' and 'computer and electronic engineering', and each detailed knowledge A numerical value for knowledge importance is given for each knowledge. A method for calculating the knowledge importance is not particularly limited, and various reasonable methods may be applied. In the example of FIG. 3 , the importance of knowledge is calculated by applying a method of surveying the importance of detailed knowledge necessary for practice targeting 30 incumbents for each job.

In the present invention, the major data storage unit stores major information including information about various majors and detailed subjects constituting the curriculum of the corresponding major for each major, and the major information is stored in text form. 4 shows an example of major information stored in the major data storage unit, and sub-subjects corresponding to the major of 'Computer Engineering' include 'discrete mathematics', 'electrical and electronic circuits', and 'computer structure'. A method of specifying information about the detailed subject among the major information is not particularly limited, and various reasonable methods may be applied. For example, in the example of FIG. 4 , common subjects among the required major subjects of 'Department of Computer Engineering' of the three major engineering colleges are selected and specified as detailed subjects.

A system for providing a major recommendation service suitable for a job according to the present invention calculates a similarity between a job and a major based on the data of the job data storage unit and the major data storage unit, and recommends a major suitable for the corresponding job in order of high similarity. In particular, as shown in the example of FIG. 5, the similarity between the sub-knowledge constituting the job and the sub-subject constituting the subject is calculated individually, and then the similarity values are combined to calculate the overall similarity between the job and the major. .

In the present invention, the natural language processing unit performs natural language processing on the job information of the job data storage unit and the major information of the major data storage unit to store vectorized job information and vectorized major information, and the natural language processing is typically Word2Vec. Word embedding models such as , FastText, Doc2Vec, and GloVe are being used, and when words, sentences, paragraphs, etc. are input, these word embedding models convert words into vectors of a specific dimension to measure similarity between vectors. According to the similarity of words, similarity between documents may be measured through word similarity measurement. In the present invention, the natural language processing unit can load various types of word embedding models, but unlike other word embedding models, it is preferable to load FastText as a word embedding model, which can vectorize new words that do not exist in training data. In the example shown in FIG. 6 , a process of vectorizing natural language words 'mathematics' and 'science' using a word embedding model can be confirmed.

In the present invention, the similarity calculation unit calculates a similarity value between the vectorized job information stored in the natural language processing unit and the vectorized major information using a Jaccard coefficient, wherein the Jaccard coefficient is a method for measuring similarity between two words. As , the similarity between the two words w1 and w2 (hereinafter referred to as 'S(w1, w2)') is expressed by the term [Equation 1] when using the Jacquard coefficient.

[Equation 1]

In the example shown in FIG. 6 , a process of calculating the similarity between the two words 'mathematics' and 'science' using the Jacquard coefficient can be confirmed, and the similarity between the two words 'mathematics' and 'science' is 0.6.

The method of calculating the similarity value between the vectorized job information and the vectorized major information in the similarity calculation unit using the Jaccard coefficient is more specifically a) between the detailed knowledge constituting the job and the detailed subject constituting the major. Calculating a similarity value using [Equation 2] below; b) calculating a similarity value between the detailed knowledge constituting the job and the major based on the similarity value calculated in step a) using the following [Equation 3]; and c) calculating the overall similarity value between the job and the entire space based on the similarity value calculated in step b) using the following [Equation 4]. After calculating the similarity between the detailed knowledge constituting the job and the detailed subjects constituting the major, based on this, the similarity between the specific knowledge and the major is calculated, and finally, the similarity between the corresponding job and the major is calculated. It is possible to provide more accurate and highly reliable major information in the order of high similarity.

[Equation 2]

here,

Job knowledge: detailed knowledge that constitutes a job

Major subjects: Detailed subjects that make up the major

[Equation 3]

[Equation 4]

In particular, in the case of [Equation 4] used in step c), knowledge importance information for each detailed job knowledge included in the job information is used to further increase the reliability and accuracy of the similarity value between the job and major calculated. It is characterized by being reflected as a weight.

7 shows an example of a process for calculating a similarity value between detailed knowledge constituting the job corresponding to step a) and detailed subjects constituting the major, and detailed knowledge constituting the job (database developer) 'computer' and 'Electronic Engineering' and 'Discrete Mathematics', a detailed subject composing the major (Department of Computer Engineering). In FIG. 7, detailed knowledge constituting job duties and detailed subjects constituting majors are displayed in text form, but in reality, all are vectorized.

8 shows an example of a process for calculating a similarity value between the detailed knowledge constituting the job corresponding to step b) and the major, and 'computer and electronic engineering', the detailed knowledge constituting the job (database developer) It shows the process of calculating the degree of similarity between majors 'Computer Engineering'. In FIG. 8, detailed knowledge constituting job duties and detailed subjects constituting majors are displayed in text form, but in reality, all are vectorized.

9 shows an example of the process of calculating the similarity value between the job corresponding to step c) and the major, and the process of finally calculating the similarity between the job 'Database Developer' and the major 'Computer Engineering' indicates In FIG. 9, detailed knowledge constituting job duties and detailed subjects constituting majors are displayed in text form, but in reality, all are vectorized.

In the present invention, the result processing unit extracts major information corresponding to the job information of the user received from the user terminal from the major data storage unit in the order of the similarity value calculated by the similarity calculation unit and transmits it to the user terminal. As such, the result processing unit may transmit up to the major information having the highest N-th highest similarity value to the terminal of the user (N: natural number).

According to the system for providing a major recommendation service suitable for a job according to the present invention, in recommending a major suitable for a job, natural language processing and Jaccard coefficient are used to determine the similarity between detailed knowledge constituting the job and detailed subjects constituting the major. After calculating the similarity between the relevant detailed knowledge and the major based on this calculation, the similarity between the job and the major is finally calculated and majors are recommended in order of high similarity, so that the major information suitable for the job desired by the user is conveniently However, it can be provided quickly and with high reliability, and thus has the advantage of effectively helping the user to decide on his or her future career.

As described above, those skilled in the art to which the present invention pertains will be able to understand that the present invention can be embodied in other specific forms without changing its technical spirit or essential features. The scope of the present invention is indicated by the claims to be described later rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts are interpreted to be included in the scope of the present invention. It should be.

Claims (4)

In a system implementing a service that provides a user with major information suitable for a job desired by the user,
a user terminal that transmits job information that the user wishes to engage in in the future to the following server through wired/wireless communication; and a server unit configured to calculate a degree of similarity between job information and major information of the user received from the user terminal and transmit major information, which is listed in order of similarity to the user terminal, to the user terminal,
The server unit includes a job data storage unit configured to store job information including information on various jobs and detailed knowledge required to perform the job for each job; a major data storage unit configured to store major information including information about various majors and detailed subjects constituting a curriculum of the corresponding major for each major; a natural language processing unit that performs natural language processing on the job information of the job data storage unit and the major information of the major data storage unit and stores vectorized job information and vectorized major information; a similarity calculation unit that calculates a similarity value between the vectorized job information stored in the natural language processing unit and the vectorized major information using a Jaccard coefficient; and a result processing unit which extracts major information corresponding to job information of the user received from the user terminal from the major data storage unit in order of similarity values calculated by the similarity calculation unit and transmits the extracted major information to the user terminal. do,
The job information includes knowledge importance information that assigns weight to each detailed knowledge necessary for job performance,
The method of calculating the similarity value between the vectorized job information and the vectorized major information in the similarity calculation unit using a Jaccard coefficient,
a) Calculating the similarity value between the detailed knowledge constituting the job and the detailed subject constituting the major using the following [Equation 2];
b) calculating a similarity value between the detailed knowledge constituting the job and the major based on the similarity value calculated in step a) using the following [Equation 3]; and
c) calculating a similarity value between the job and the entire space based on the similarity value calculated in step b) using [Equation 4] below;
[Equation 2]

here,
Job knowledge: detailed knowledge that constitutes a job
Major subjects: Detailed subjects that make up the major

[Equation 3]

[Equation 4]

delete According to claim 1,
The system for providing a major recommendation service suitable for a job, characterized in that the natural language processing unit is loaded with FastText as a word embedding model for natural language processing.
delete

Images