KR20200129042A - Apparatus and method for recommending job - Google Patents

Abstract

The present invention relates to a method for recommending a customized job and method for recommending a job based on military service records and, more specifically, to a method for recommending a military position using a filter generated based on a dictionary including a plurality of job competency units or recommending a civilian job, certification, or training to a person with experience in a military service. According to an embodiment of the present invention, based on a filter provided with objective, reasonable, and consistent standards, a military position can be recommended to a target person or a suitable job can be recommended to a person with experience in a military service.

Description

Military service career-based job recommendation device and method, customized position recommendation device {APPARATUS AND METHOD FOR RECOMMENDING JOB}

The present invention relates to a customized position recommendation method and a military service career-based job recommendation method, and more particularly, to recommend a military position by using a filter created based on a dictionary including a plurality of job competency units, or to a military service experienced person It is about how to recommend a private job, certification, or training to a person.

Among the young soldiers who are discharged after completing their service, most of the discharged soldiers who do not return to college enter society without preparing for employment. According to the current situation, even if all military personnel acquire enough experience needed in society through military life, it is not just evaluated by the civil society, but also is not recognized as a career. Even though they studied the same major in college and worked as a military officer for many years as a military officer, personnel officers, and deputy officers, they are not recognized as the same professional activity in society, and are not accepted as social careers. Of course, it is the same that the details of the job performance of an enlisted soldier who has completed compulsory service are not evaluated as vocational activities in society.

Executives who have performed vocational activities as vocational soldiers in the military perform their duties for quite a long time based on their job abilities or special skills. Therefore, he has considerable expertise in his job field. Nevertheless, these capabilities are not in circulation with society. This is because the service experience in the military is not effectively recognized as a vocational activity related to social experience.

The present invention is to provide a job recommendation device, a job recommendation method, and a recording medium for recommending a civilian job to a person with experience in military service by using a filter generated based on a dictionary including a plurality of job competency units.

In addition, the present invention is to provide a job recommendation method capable of recommending a military position based on a filter prepared with an objective, rational and consistent standard, or recommending a suitable job to a person with experience in military service.

In addition, the present invention is to provide a job recommendation method capable of improving job competency even during military service life as it is possible to recommend customized positions from a subject's major, social experience, and qualifications before enlisting in the military.

The problem to be solved by the present invention is not limited to the problems mentioned above. Other technical problems that are not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

The present invention provides a job recommendation method. In one embodiment, the job recommendation method includes, by a job recommendation unit, recommending a job to the subject based on the subject’s competency-related data and a filter, and the filter is data related to the required competency according to the job It is generated based on a dictionary including a plurality of job competency units consisting of, and among the degrees of association between the job competency units and words extracted from the data constituting the job competency units and the association between the job competency units It includes at least one, wherein the job competency units include a plurality of military position units composed of data related to required competencies according to the military position, and the competency-related data of the subject includes the subject's military position.

In one embodiment, the filter is a word extracted from data constituting the job competency units in one of a first unit of a row unit and a column unit, and another second unit And a two-dimensional matrix in which they are arranged, and the two-dimensional matrix may have a degree of association between each job competency unit of the first unit and each word of the second unit as each component value.

In an embodiment, the filter includes a two-dimensional matrix in which job competency units are arranged in a first unit of a row unit and a column unit, and the job competency units are arranged in another second unit, and , The two-dimensional matrix has a degree of relationship between a first job competency unit associated with each job competency unit of the first unit and a second job competency unit associated with each job competency unit of the second unit as each component value. I can.

In an embodiment, the step of recommending the job may include extracting words related to the military position of the subject from the competency-related data; And determining one or more job competency units related to the subject from the extracted words. And determining the at least one job competency unit as a recommended job.

In an embodiment, the at least one job competency unit is used as a first job competency unit, and at least one second job among a plurality of job competency units is based on the similarity with the first job competency unit based on the filter. It may include the step of determining the competency unit as a recommended job.

The present invention includes a method for recommending military positions. In one embodiment, the method for recommending a military position includes, by a job recommendation unit, recommending a position to the subject based on the subject's competency-related data and a filter, and consists of data related to the required competencies according to the job. Generated based on a dictionary including a plurality of job competency units, at least one of a degree of association between the job competency units and words extracted from the data constituting the job competency units and a degree of correlation between the job competency units Including, wherein the job competency units include a plurality of military job units consisting of data related to required competencies according to the military job position, and the competency-related data of the subject is the subject's education information, possession certificate information, portfolio, resume, Self-introduction letter, SNS data, data collected by a chatbot that collects history information in the form of conversation with the subject, social relationship information of the subject, interests on the subject’s SNS, the subject’s content viewing record, the subject’s identification It contains at least one of the information retrieval history.

In one embodiment, the filter is a word extracted from data constituting the job competency units in one of a first unit of a row unit and a column unit, and another second unit And a two-dimensional matrix in which they are arranged, and the two-dimensional matrix may have a degree of association between each job competency unit of the first unit and each word of the second unit as each component value.

In an embodiment, the filter includes a two-dimensional matrix in which job competency units are arranged in a first unit of a row unit and a column unit, and the job competency units are arranged in another second unit, and , The two-dimensional matrix has a degree of relationship between a first job competency unit associated with each job competency unit of the first unit and a second job competency unit associated with each job competency unit of the second unit as each component value. I can.

In one embodiment, the step of recommending the job may include extracting words related to the job competency of the subject from the competency related data; And determining one or more group positions related to the subject from the extracted words. And determining the at least one military position unit as a recommended military position.

According to an embodiment of the present invention, a job recommendation method of recommending a military position or recommending a job to a person with experience in military service using a filter generated based on a dictionary including a plurality of job competency units is provided.

In addition, according to an embodiment of the present invention, it is possible to recommend a military position to a target person based on a filter prepared with objective, rational, and consistent criteria, or to recommend a suitable job to a person with experience in military service.

According to an exemplary embodiment of the present invention, it is possible to improve job competency even during military service life as it is possible to recommend customized positions based on a subject's major, social experience, and certification before enlisting in the military.

The effect of the present invention is not limited to the above-described effects. Effects not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings.

1 is a configuration diagram of a job recommendation device according to an embodiment of the present invention.
2 is a block diagram of a job recommendation server constituting a job recommendation device according to an embodiment of the present invention.
3 is a block diagram of a filter generator constituting a job recommendation device according to an embodiment of the present invention.
4 is a block diagram of a job recommendation unit constituting a job recommendation device according to an embodiment of the present invention.
5 is a configuration diagram of a first filter generating unit configuring a job recommendation device according to an embodiment of the present invention.
6A and 6B are diagrams illustrating a job competency unit document of a dictionary collection including a plurality of job competency units.
7 is an exemplary diagram of a first filter according to the first embodiment of the present invention.
8 is a configuration diagram of a first job recommendation unit constituting a job recommendation device according to an embodiment of the present invention.
9 is an exemplary diagram of a first filter according to a second embodiment of the present invention.
10 is a block diagram of a first job recommendation unit constituting a job recommendation device according to a second embodiment of the present invention.
11 is a block diagram of a first job recommendation unit constituting a job recommendation device according to another embodiment of the present invention.
12 is a block diagram of a second filter generating unit configuring a job recommendation device according to an embodiment of the present invention.
13 is an exemplary diagram of a second filter according to the first embodiment of the present invention.
14 is an exemplary diagram of a second filter according to a second embodiment of the present invention.
15 is a block diagram of a second job recommendation unit according to the first embodiment of the present invention, which constitutes a job recommendation device according to an embodiment of the present invention.
16 is a configuration diagram of a second position recommendation unit according to a second embodiment of the present invention.
17 is a configuration diagram of a second job recommendation unit constituting a job recommendation device according to another embodiment of the present invention.

Other advantages and features of the present invention, and a method of achieving them will become apparent with reference to embodiments to be described later in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and the present invention is only defined by the scope of the claims. Even if not defined, all terms (including technical or scientific terms) used herein have the same meaning as commonly accepted by universal technology in the prior art to which this invention belongs. General descriptions of known configurations may be omitted so as not to obscure the subject matter of the present invention. In the drawings of the present invention, the same reference numerals are used as much as possible for the same or corresponding configurations.

The terms used in the present 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 indicates otherwise. In the present application, terms such as "comprise", "have" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or a combination thereof described in the specification. It is to be understood that the possibility of the presence or addition of other features, numbers, steps, actions, components, parts, or combinations thereof, or any further features, is not excluded in advance.

The'~ unit' used throughout this specification is a unit that processes at least one function or operation, and may mean, for example, a hardware component such as software, FPGA, or ASIC. However,'~ part' is not limited to software or hardware. The'~ unit' may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. As an example,'~ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, and subs. Routines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The components and functions provided by the'~ unit' may be performed separately by a plurality of elements and the'~ units', or may be integrated with other additional elements.

In this specification, the term'job ability' is used. The term'job ability' as used herein refers to the knowledge, skills, and attitudes required for job performance in the industrial field. For example, it can be defined as a competency unit according to the concept systematized by the Korea Human Resources Development Service or the Korea Vocational Competency Development Institute as National Competency Standards (NCS). Specifically, information on NCS can be obtained from https://www.ncs.go.kr/, and the major classification (24) classified by referring to the Korean Employment Classification of Occupations (KECO), According to the sub-class (79), sub-class (253), and sub-class (1,001), knowledge, skills, and skills of the competency unit elements provided in the competency unit (report) included in each competency unit included in the competency units provided in each of the 1,001 subcategories It can be an attitude. However, the above-described example is only an example, and job capability should not be interpreted as a concept limited to the above-described capability unit or capability unit element. For example, job competency may mean all items to be described, such as the name, definition, basic job competency, evaluation items, performance standards for each competency unit element defined in the NCS. In addition, job competency may not be defined by NCS, but may be defined as job performance ability for a certain job. In addition, job competency includes knowledge, skills, attitudes, etc. required for job performance in an industrial site not described above, and may be a concept classified according to certain criteria.

The term used throughout this specification, the definition of a job competency unit (included in the dictionary collection and constituting the dictionary collection), does not simply mean job competency itself, but data related to the competency required by each job competency. It should be understood as a concept of a data set that includes, and is not simply defined as a word, but interpreted as a concept including a glossary of words or a job description defined as a sentence or a job description that includes a plurality of words for each job competency, and their index It should be.

Similar to the definition of the job competency unit, the term used throughout this specification, it does not simply mean the position itself, but the data set including the data related to the competence required by each position. It should be understood as a concept, and it should be interpreted as a concept including a vocabulary or sentence that includes a plurality of words for each job title, a description of a job title, a description of a job title, and their index.

1 is a configuration diagram of a job recommendation device according to an embodiment of the present invention. Referring to FIG. 1, a job recommendation device 10 according to an embodiment of the present invention may include a job recommendation server 30 and a database 40.

The job recommendation server 30 may collect competency-related data from the target terminal 20 and recommend a job suitable to the subject by using a filter generated based on a dictionary including a plurality of job competency units. In addition, it is possible to recommend related certifications that can be acquired and training necessary to improve job competency based on the recommended job.

A filter according to an exemplary embodiment of the present invention will be described in more detail later with reference to FIGS. 7, 9, 13, and 14.

The subject terminal 20 is a terminal used by the subject, and may be implemented as, for example, a smartphone, a tablet PC, a video phone, a desktop PC, a laptop PC, a netbook computer, a workstation, a PDA, a PMP, and a wearable device. It is not limited thereto.

The database 40 includes data related to competency of targets, data related to recruitment of recruiters such as companies and public institutions, and a dictionary including a plurality of job competency units (e.g., reports by competency unit according to NCS classification, NCS classification). It is possible to store information such as vocabulary extracted from the report for each competency unit) and filters.

The database 40 is not necessarily interpreted as being separated from the job recommendation server 30 and provided separately, and should be understood as a concept including a memory provided in the job recommendation server 30. The job recommendation server 30 may access the target terminal, the recruiter terminal, and the database 40 through various types of communication. Here, various types of communication may be implemented by a network interface capable of wired and/or wireless communication, for example, short-range communication (eg, Bluetooth, WiFi direct, or IrDA (infrared data association)) or long-distance communication (eg, cellular It may be a network, the Internet, or a computer network (eg, LAN or WAN), but is not limited thereto. Wired/wireless network interfaces communicate according to various communication standards such as IEEE, zigbee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), Long Term Evoloution (LTE), 5th Generation (5G), etc. It may be configured as a network interface that performs, but is not limited thereto.

2 is a block diagram of a job recommendation server constituting a job recommendation device according to an embodiment of the present invention. 1 and 2, the job recommendation server 30 may include a filter generation unit 100, a job classification filter 200, and a job recommendation unit 300.

The filter generator 100 may generate one or a plurality of different filters 200 based on a dictionary including a plurality of job competency units.

The dictionary collection (hereinafter referred to as the dictionary collection) that includes a plurality of job competency units includes job competency extracted from job-related specific data (e.g., job seeker's self-introduction, job description, classification data according to NCS, etc.) It refers to a set of data that is organized by classifying related data (eg, words, sentences, etc. related to job competency) according to each defined job competency unit. Each job competency unit may include an index representing job competency and data related to job competency.

The filter 200 derives an output value related to the input value when an input value is provided. For example, the input value may be a word related to job ability or job ability. For example, the output value may be a word related to job ability or job ability. In an embodiment, the filter 200 may be calculated based on a dictionary including a plurality of job competency units. The filter 200 generated by the filter generator 100 may be stored in the database 40. The job recommendation unit 300 may recommend a job suitable to the subject based on the subject-related data and the filter 200 generated by the filter generating unit 100.

In an embodiment, a dictionary containing a plurality of job competency units is a document related to competency units according to job classification defined according to the National Competency Standards (NCS) classification, and military positions (jobs) in a system similar to the NCS. A job description document for each military position that defines the classification of military positions established by defining the military position and the military position according to the military position created according to the military position classification (e.g., a job description defining the duties according to the military position) or the above documents It may include a word collection including words extracted from.

The classification of military positions defined in this specification is a standardization and systematization of job competencies required for each military position. The military position classification classifies responsibilities by position, and the required competencies are defined according to the responsibilities by position. Responsibilities and required competencies for each position are created as a dictionary that defines the duties for each military position. More specifically, the classification of military positions can be defined in a manner and system similar to that of the NCS classification. According to the classification of military positions, each classified military position may include a military position definition document that defines the military position. The military position definition document systematically includes the responsibilities and required competencies for each position. For example, a document defining a military position may include the contents of knowledge, skills, and abilities required to perform duties in the military, divided into'competency unit factors','performance criteria', and'knowledge, skills, attitudes', etc. . Military position definition documents may exist as data.

For example, classification of military positions may be collected and defined from data defined on the Korea Military Manpower Administration website (https://www.mma.go.kr/). For example, in defining military positions, the upper classification is divided into'Army','Navy','Marine Corps', and'Air Force', and'Army' is'Technical Administrator','Job Special Forces','Pay Support Soldiers' ','Professional Special Forces','Language Soldiers', and'KATUSA Soldiers'. Among them, for example,'Technical Administrators' are'K series tank control','Tank communication maintenance', and'K-21 infantry combat It can be classified into'Vehicle Control','Armored Vehicle Control','Valkan Maintenance','Field Construction','Survey','Crane Driving', and'Password Operation'. 'Special skill' as defined by the Military Manpower Administration of the Republic of Korea may be defined as a'military position unit' as defined in this specification. The Military Manpower Administration website provides information related to'jobs','missions', and'related fields' defined for each'specialty'. For example, information related to ‘K series tank control’ can be viewed at https://www.mma.go.kr/conscription/recruit_service/procedure/army/S_board_text.do?mc=mma0000388&gun_gbcd=1&mojip_gbcd=1. Information on'jobs','missions', and'related fields' for each'specialty' provided by the Military Manpower Administration can be defined as required competencies related to the relevant specialty. Alternatively, the data related to the required competencies according to the military job is defined in terms of the knowledge, skills, and competencies required to perform the job in the military for each defined'military position unit'. It can be subdivided into'knowledge, skill, attitude', etc. and defined and stored in the dictionary.

In an embodiment, the filter generating unit 100 is a dictionary collection of each job competency unit (hereinafter, when referred to as a'job competency unit' without special mention, the job competency unit is provided as a concept including a group position unit) Filter by extracting data according to each job competency unit in, extracting words from the extracted data according to each job competency unit, and calculating the degree of association between each job competency unit and words or between each job competency unit Can be created. For example, the data according to each job competency unit is'classification number','name','definition','evaluation guideline','basic job competency','evaluation item', job competency belonging to the job competency unit. It may be a data-formatted document including information such as'name','conformity','knowledge','technology', and'attitude' for each unit element.

3 is a block diagram of a filter generator constituting a job recommendation device according to an embodiment of the present invention. 4 is a block diagram of a job recommendation unit constituting a job recommendation device according to an embodiment of the present invention. 3 and 4, the filter generation unit 100 may include a first filter generation unit 120, a second filter generation unit 140, and a filter update unit 160. The filter 200 may include a first filter 220 and a second filter 240. The job recommendation unit 300 may include a first job recommendation unit 320 and a second job recommendation unit 340.

The first filter generator 120 may generate a first filter 220 of a two-dimensional matrix representing a relationship between each job competency unit and words extracted from data according to each job competency unit. The second filter generator 120 may generate a second filter 240 of a two-dimensional matrix indicating a degree of association between each job competency unit.

The first job recommendation unit 320 may recommend a job to a target person based on the first filter 220 generated by the first filter generation unit 120. The second job recommendation unit 340 may recommend a job to a target person based on the second filter 240 generated by the second filter generation unit 140. Hereinafter, the first filter 220 will be described first, and then the second filter 240 will be described.

5 is a configuration diagram of a first filter generating unit configuring a job recommendation device according to an embodiment of the present invention. 3 and 5, the first filter generation unit 120 includes a dictionary construction unit 122, a word extraction unit 126, a correlation analysis unit 130, and a normalization unit 132. Can include. The dictionary collection construction unit 122 may construct the dictionary collection 125 by dividing and extracting data according to the job competency unit from the job competency-related data 400 and integrating the extracted data according to the job competency unit. In one embodiment, the dictionary construction unit 122 may extract pdf documents defining job competency units for each of 24 NCS major categories. The number n of the job competency units 124 may be different, and in one embodiment, n represents the number of job competency units 124 belonging to the corresponding classification. PDF documents according to n number of job competency units 124 belonging to the same classification can be used to calculate the first filter 220 for the corresponding classification, and as many as the number of classifications (for example, the NCS classification system According to the large classification, 24) of first filters 220 may be calculated.

6A and 6B are diagrams illustrating documents defining job competency units 124 of NCS as an example of a dictionary including a plurality of job competency units. For each job competency unit,'classification number','name','level','definition','basic job competency','evaluation items','performance standards' for each job competency unit element, Data related to job competency units can be extracted from documents containing information such as'knowledge','skill', and'attitude'. The word extractor 126 may extract words 128 from all of the n job competency units. In an embodiment, the word extracting unit 126 may include a morpheme analyzer that divides sentences in a document defining the job competency units 124 into words in morpheme units and tagging parts of speech. In an embodiment, the word extracting unit 126 excludes stop words from sentences, and N-grams such as Uni-gram and/or bi-gram (N is an integer of 2 or more). ) To extract words.

The association analysis unit 130 may analyze a degree of association between the job competency units 124 defined in the dictionary 125 and the words 128 extracted from the job competency units 124. In an embodiment, the correlation analysis unit 130 includes n job competency units 124 and m words extracted from n job competency units 124 based on TF-IDF (Term Frequency Inverse Document Frequency). The degree of association between them can be analyzed. The degree of association between the job competency units 124 and the words 128 may be calculated according to Equations 1 to 3 below, or may be calculated according to Equations 1, 2, and 4 below.

[Equation 1]

[Equation 2]

[Equation 3]

[Equation 4]

In Equations 1 to 4,'tfidf(t,d,D)' is the word frequency inverse document frequency,'t' is a word,'d' is a document, D is a set of all documents, and tf(t,d) is a word Frequency, idf(t,D) is the inverse document frequency,'ft,d' is the frequency of the word t in the document d, and'df(t,d)' is the number of documents containing the word t among all documents Represents.

The relevance analysis unit 130 applies not only TF-IDF, but also non-negative matrix factorization (NMF) and word embedding technologies such as Word2Vec/Doc2Vec, and documents job competency units. And, it is also possible to analyze the degree of association between words extracted from job competency unit documents.

When the number of words 128 extracted from n job competency units 124 is m, the degrees of association between job competency units 124 and words 128 can be expressed as a matrix of size n×m. have. The normalization unit 132 may generate a normalized matrix by dividing each component of the n×m matrix by a set value so that the size of the matrix of size n×m is normalized to 1. The set value may be different depending on each component of the n×m matrix. Also, the set value may be different depending on the normalization method. On the other hand, in the present embodiment, the matrix is normalized to have a size of 1, but it may be modified to an appropriate size such as 10 or 100. Accordingly, a normalized first filter 220 may be generated for each major classification. By normalizing the first filter 220, it is possible to prevent the priorities of recommended jobs belonging to different major categories from being influenced by different matrix sizes between major categories, and recommended jobs as competency units within a specific major category (large category with a large matrix size) It is possible to prevent the concentration of people and recommend a job (competency unit) suitable for job seekers not only in the large category with a large matrix size, but also in the large category with a small matrix size.

7 is an exemplary diagram of a first filter according to the first embodiment of the present invention. Referring to FIGS. 5 and 7, the first filter 220 includes job competency units 124 (a1, a2, ..., an-1, an) in a row unit (first unit). Words (128) (v1, v2, ..., vm-1, vm) that are arranged and extracted from the job competency units 124 of the dictionary collection 125 in a column unit (second unit) This can be expressed as an arrayed two-dimensional matrix. Each component value of the 2D matrix of the first filter 220 may be a value obtained by dividing the TF-IDF value of a word by the matrix size and normalized. The first filter 220 may be referred to as a set of row vectors having a size of 1×m for each of the n job unit capabilities. The number m of words 128 may be approximately tens of thousands to hundreds of thousands of words.

In the above, for an embodiment of the first filter 220 in which job competency units are sequentially arranged in row units (first unit), and words extracted from job competency unit documents are sequentially arranged in column units (second unit). Although described, in the first filter 220, job competency units may be arranged in column units, and words extracted from job competency unit documents may be arranged in row units. In this case, each job competency unit vector may be provided as a column vector.

Referring again to FIG. 3, the filter update unit 160 collects update information of a dictionary including a plurality of job competency units through a periodic crawling technology, and a dictionary includes a plurality of job competency units. The filter can be updated based on the update information of. The dictionary collection including a plurality of job competency units can be changed or updated to reflect future social changes and the needs of industrial sites, and job competency units may be added or deleted if there is a new or disappearing job. In addition, words included in the job competency unit or required competencies may be changed or updated to include more specific terms. For example, if the word ��powerpoint��, which is a program name used in industrial sites, is collected from a self-introduction, which is an example of job competency-related data 400, powerpoint When the word is not included in the unit, the dictionary collection including the job competency unit may be updated to include it. The filter updater 160 may update a filter when a dictionary including a plurality of job competency units is updated.

For example, the filter update unit 160 finds a job competency unit with a new classification number or a new name in a dictionary including a plurality of job competency units collected by crawling, or finds the classification numbers of the existing job competency units or If there is a deleted classification number or name among the names, or by a crawling technique, the job competency unit's'vocational basic competency','evaluation items','performance criteria','knowledge' by job competency unit element When it is determined that information such as,'technology','attitude', etc. has been changed, it is determined that the dictionary including a plurality of job competency units has been changed or updated, and the filter may be updated.

8 is a configuration diagram of a first job recommendation unit constituting a job recommendation device according to a first embodiment of the present invention. 4, 7 and 8, the first job recommendation unit 320 may recommend one or more jobs to the subject based on the subject's competency-related data 500 and the first filter 220. In an embodiment, the competency-related data 500 includes military service experience. Military position career is the main specialty at the time of military service, a portfolio that includes data related to military duties, the duties performed at the time of military service, the name of the position, and specialty. It may include the military service period, the service period for each military position, the service period for each specialty, and so on. In addition, competency-related data 500 refers to data collected by a chatbot that collects education information, certificate information, portfolio, resume, self-introduction, SNS data, and history information in the form of conversations with the subject, collected through the subject's voice. It may include digitized personal information such as social relations information of the data subject, interests of SNS, content viewing records, and search information. The competency-related data 500 may be collected from the target person's terminal, or may be collected from the target person's SNS or email, a job search relay server, a school or a national administrative agency server that stores and manages information on the target person. The first job recommendation unit 320 may include a word extraction unit 322, a vectorization unit 324, a similarity calculation unit 326, and a recommended job determination unit 328.

The word extracting unit 322 may extract competency related words from the competency related data 500 of the subject. The word extracting unit 322 may include a morpheme analyzer for dividing sentences in the competency-related data 500 into words in morpheme units and tagging parts of speech. In an embodiment, the word extracting unit 322 extracts the noun tagging morpheme after morpheme analysis, removes stop words, and then applies N-grams such as bi-grams in the case of noun continuation. . The word extractor 322 may extract only words corresponding to the words 128 defined in the first filter 220 from among words of the competency-related data 500.

The vectorization unit 324 may vectorize words extracted from the capability-related data 500 by the word extraction unit 322 according to the arrangement order of the words 128 defined in the first filter 220. In the first filter 220, the words 128 are arranged in a column unit. The vectorization unit 324 includes k (k is an integer of 0 or more and m or less) extracted from the competency-related data 500 according to the arrangement order of the words 128 defined in the first filter 220 Can be converted to a 1×m row vector. In this case, in the row vector transformed from words extracted from the capability-related data 500, k components may have a size greater than 0, and the remaining (m-k) components may have a value of 0. The component value of each of the k words may be determined as a value corresponding to the Term Frequency (TF) of the word in the competency-related data 500, or a value irrespective of the frequency by applying a binary score. It may be decided. When a word frequency (TF) is used, a normalized term frequency can be used to calculate the similarity (eg, cosine similarity). In the case of using a binary score, it can be applied by taking the square and then dot product.

For example, assuming that the word'architectural design' is included twice in the competency-related data 500, and the word corresponding to'architectural design' in the first filter 220 is defined in the 12145th column, When the frequency is not considered, the 12145th component value of the primary vector generated by the vectorization unit 324 is determined as '1', and when the frequency of the word is considered, the primary vector generated by the vectorization unit 324 The 12145th component value of may be determined as '2'. Then, a normalized row vector (feature vector) can be generated by a vector normalization operation. The similarity calculation unit 326 is based on the row vector (feature vector) generated from the competency-related data 500 by the vectorization unit 324 and the similarity between the job seeker's feature vector and the competency units based on the first filter 220 Can be calculated. In an embodiment, the similarity calculation unit 326 may calculate a similarity (eg, cosine similarity) between a feature vector of a job seeker and a row vector (capability unit vector) of each of the competency units.

In an embodiment, the cosine similarity may be calculated as a value obtained by dividing the feature vector of the subject and the row vector of each of the m job competency units by the size of the feature vector and the row vector size of the job competency unit. When the feature vector is normalized, the operation of dividing by the size of the feature vector may be omitted. The similarity calculation unit 326 may calculate a similarity with a feature vector of a subject for each of n job competency units belonging to one major classification. The recommended job determination unit 328 determines the priority of the job competency units in the order of the highest similarity to the subject’s feature vector among n similarity values between the subject’s feature vector and the job competency units, and selects a recommended job to be recommended to the subject. You can decide. In addition, certification information required for the recommended job or training information necessary to improve competency can be provided.

In an embodiment, the recommended job determination unit 328 may determine a recommended job from one or a plurality of major categories in an order of high similarity between the target's feature vector and the job competency units for each major category. Alternatively, when the target person inputs selecting a specific major category using the target person interface, a job (job competency unit) belonging to the major category may be recommended based on a filter for only the selected major category. In the above, the case of recommending a job by creating various filters for each major category has been described as an example, and it is also possible to create a single filter for all job competency unit documents belonging to all major categories to recommend a job.

9 is an exemplary diagram of a first filter according to a second embodiment of the present invention. 5 and 9, the first filter 220 includes group-level units 1124 (b1, b2, ..., bn-1, bn) in a row unit (first unit). It is arranged and expressed in a two-dimensional matrix in which the group office unit and the previously extracted words 128 (v1, v2, ..., vm-1, vm) are arranged in a column unit (second unit). I can. Each component value of the 2D matrix of the first filter 220 may be a value obtained by dividing the TF-IDF value of a word by the matrix size and normalized. The first filter 220 may be referred to as a set of row vectors having a size of 1×m for each of the n job unit capabilities. The number m of words 128 may be approximately tens of thousands to hundreds of thousands of words.

In the above, for an embodiment of the first filter 220 in which the group positions are sequentially arranged in a row unit (first unit), and words extracted from the job competency unit documents are sequentially arranged in a column unit (second unit). Although described, in the first filter 220, the group positions are arranged in column units, and words extracted from the job competency unit documents may be arranged in rows. In this case, each group assignment unit vector may be provided as a column vector.

10 is a configuration diagram of a first job placement recommendation unit constituting the job placement recommendation device of the present invention. 4, 9, and 10, the first position recommendation unit 1320 may recommend one or more positions to the target person based on the competency-related data 500 and the first filter 220 of the target person. In an embodiment, the competency-related data 500 includes data collected by a chatbot that collects education information, possession certificate information, portfolio, resume, self-introduction, SNS data, and history information in a conversation with the subject, and the subject's voice. It may include digitized personal information such as data collected through data, social relationship information of the subject, interests of SNS, content viewing records, search information, and the like. The competency-related data 500 may be collected from the target person's terminal, or may be collected from the target person's SNS or email, a job search relay server, a school or a national administrative agency server that stores and manages information on the target person. The first position recommendation unit 1320 may include a word extraction unit 322, a vectorization unit 324, a similarity calculation unit 326, and a recommended position determination unit 1328.

The word extracting unit 322 may extract competency related words from the competency related data 500 of the subject. The word extracting unit 322 may include a morpheme analyzer for dividing sentences in the competency-related data 500 into words in morpheme units and tagging parts of speech. In an embodiment, the word extracting unit 322 extracts the noun tagging morpheme after morpheme analysis, removes stop words, and then applies N-grams such as bi-grams in the case of noun continuation. . The word extractor 322 may extract only words corresponding to the words 128 defined in the first filter 220 from among words of the competency-related data 500.

The vectorization unit 324 may vectorize words extracted from the capability-related data 500 by the word extraction unit 322 according to the arrangement order of the words 128 defined in the first filter 220. In the first filter 220, the words 128 are arranged in a column unit. The vectorization unit 324 includes k (k is an integer of 0 or more and m or less) extracted from the competency-related data 500 according to the arrangement order of the words 128 defined in the first filter 220 Can be converted to a 1×m row vector. In this case, in the row vector transformed from words extracted from the capability-related data 500, k components may have a size greater than 0, and the remaining (m-k) components may have a value of 0. The component value of each of the k words may be determined as a value corresponding to the Term Frequency (TF) of the word in the competency-related data 500, or a value irrespective of the frequency by applying a binary score. It may be decided. When a word frequency (TF) is used, a normalized term frequency can be used to calculate the similarity (eg, cosine similarity). In the case of using a binary score, it can be applied by taking the square and then dot product.

The similarity calculation unit 326 is based on the row vector (feature vector) generated from the capability-related data 500 by the vectorization unit 324 and the first filter 1220 between the feature vector of the subject and the group positions. Similarity can be calculated. In an embodiment, the similarity calculation unit 326 may calculate a similarity (eg, cosine similarity) between a feature vector of a subject and a row vector (job capability unit vector) of each of the group positions.

In an embodiment, the cosine similarity may be calculated as a value obtained by dividing the feature vector of the subject and the row vector of each of the m job competency units by the size of the feature vector and the row vector size of the job competency unit. When the feature vector is normalized, the operation of dividing by the size of the feature vector may be omitted. The similarity calculation unit 326 may calculate a similarity with a feature vector of a subject for each of n job competency units belonging to one major classification. The recommended job determination unit 328 determines the priority of the job competency units in the order of the highest similarity to the subject’s feature vector among n similarity values between the subject’s feature vector and the job competency units, and selects a recommended job to be recommended to the subject. You can decide.

In an embodiment, the recommended position determination unit 1328 may determine the recommended position in the order of a feature vector of a subject and a degree of similarity between the group positions.

According to an embodiment of the present invention, a filter is not created by learning using career (past job experience), such as a resume, portfolio, and self-introduction of the subject, but only a dictionary including a plurality of job competency units. By creating a filter based on the job or military position, it is possible to prevent the occurrence of error factors in the filter due to uncertain learning data, and it is suitable for the target subject based on a filter prepared with objective, reasonable, and consistent criteria. You can recommend a job or military position.

According to an exemplary embodiment of the present invention, it is possible to improve job competency even during military service life as it is possible to recommend customized positions based on a subject's major, social experience, and certification before enlisting in the military.

In the above, the job recommendation device and the job recommendation method according to an embodiment of the present invention have been described as an example of constructing job competency unit data by crawling documents defined by NCS as an example of defining a dictionary collection. The job recommendation device and job recommendation method according to the embodiment are not only NCS, but also NOS (National Occupational Standards), VAAS (Vocational Ability Assessment Standards), NSS (National Skill Standard), NQF (National Qualification Framework), KQF (Korean Qualifications Framework). ), KECO (Korean Employment Classification of Occupations), or other unlisted job competency standards can be crawled to construct job competency unit data in the dictionary. In addition, even if it is not defined as a standard, it can be applied to the case of defining knowledge, skills, attitudes, etc. for job competency.

11 is a block diagram of a first job recommendation unit constituting a job recommendation device according to another embodiment of the present invention. 7 and 10, the first job recommendation unit 320 classifies jobs related to recruitment based on the recruitment-related data 600 and the first filter 220 of the recruiter, and based on the job classification information of the recruiter. You can recommend one or more jobs to job seekers. In an embodiment, the recruitment-related data 600 may include recruitment information such as career, educational program, academic background, and job experience required by a recruiter such as a company or a public institution. The recruitment-related data 600 may be collected from a recruiter terminal, or may be collected from a recruiter's SNS or email, a job posting relay server, a school or a national administrative agency server that stores and manages information on the recruiter. In addition, the recruitment-related data 600 may be collected by a chatbot that collects information in the form of a conversation with the recruiter, or may be collected through voice analysis of the recruiter. The first job recommendation unit 320 may include a word extracting unit 330, a vectorization unit 332, a similarity calculation unit 334, and a job classification unit 336.

The word extractor 330 may extract employment-related words from the recruitment-related data 600 of the recruiter. The word extracting unit 330 may include a morpheme analyzer for dividing sentences in the recruitment-related data 600 into words in morpheme units and tagging parts of speech. In an embodiment, the word extraction unit 330 extracts noun tagging morphemes after morpheme analysis from sentences, removes stop words, and applies N-grams such as bi-grams in the case of noun continuation. can do. Excluding stop words, words can be extracted with N-grams (N is an integer of 2 or more) such as uni-gram and/or bi-gram. The word extractor 330 may extract only words corresponding to the words 128 defined in the first filter 220 from among words of the recruitment-related data 600.

The vectorization unit 332 may vectorize words extracted from the recruitment-related data 600 by the word extraction unit 330 according to the arrangement order of the words 128 defined in the first filter 220. The vectorization unit 332 includes p (p is an integer of 0 or more and m or less) extracted from the recruitment-related data 600 according to the arrangement order of the words 128 defined in the first filter 220 Can be converted to a 1×m row vector. In this case, in the row vector (feature vector) converted from words extracted from the recruitment-related data 600, p components among m components have a size greater than 0, and the remaining (mp) components have a value of 0. Can have The component value of each of the p words may be determined as a value corresponding to the Term Frequency (TF) of the word in the recruitment-related data 600, or a value of 1 regardless of the frequency based on the binary score. It may be decided. When a word frequency (TF) is used, a normalized term frequency can be used to calculate the similarity (eg, cosine similarity). In the case of using a binary score, it can be applied by taking the square and then dot product.

For example, assuming that the word'architectural design' is included 3 times in the recruitment-related data, and the word corresponding to'architectural design' in the first filter 220 is defined in the 12145th column, the frequency of the word is considered. If not, the value of the 12145th component of the first row vector (feature vector) generated by the vectorization unit 332 is determined as '1', and when the frequency of words is considered, the first row generated by the vectorization unit 332 The value of the 12145th component of the vector (feature vector) may be determined as '3'. Thereafter, a normalized row vector (feature vector) may be generated by vector normalization (when the frequency of a word is considered) or vector square and dot product (when a binary score is applied).

The similarity calculation unit 334 includes a row vector (feature vector) generated from the recruitment-related data 600 by the vectorization unit 332 and the feature vector of the recruiter and the job competency units based on the first filter 220. Similarity can be calculated. In an embodiment, the similarity calculation unit 334 may calculate a similarity (eg, cosine similarity) between a feature vector of the employer and a row vector of each of the job competency units. In an embodiment, the cosine similarity may be calculated as a value obtained by dividing the feature vector of the recruiter and the row vector of each of the m job competency units by the size of the recruiter's feature vector and the row vector size of the job competency unit. The similarity calculation unit 334 may calculate a cosine similarity with a feature vector of an adopter for each of n job competency units belonging to one major classification. The job classification unit 336 determines the priorities of the job competency units in the order of the highest cosine similarity with the employee's feature vector among n cosine similarity values between the recruiter's feature vector and the job competency units, Competency units) can be classified according to the standard classification of job competency.

In an embodiment, the job classification unit 336 may provide job classification results from one or a plurality of major categories in an order of high similarity between the recruiter's feature vectors and job competency units, for each major category. Alternatively, when the recruiter inputs a selection of a specific major category using the target person interface, jobs belonging to the major category may be classified based on a filter for only the selected major category. In the above, the case of classifying the job of the recruiter by creating various filters for each major category has been described as an example, and it is also possible to classify the job related to the recruiter by creating a single filter for all job competency unit documents belonging to all major categories.

When one or more job classification information related to the recruiter is determined, recruitment information is provided to the job seeker matching the job classification information of the corresponding recruiter, and job matching between the job seeker and the recruiter can be made based on the job competency unit. Therefore, job mismatch between the recruiter and the recruiter by providing recruiters with job aptitude that meets the job aptitude of companies and public institutions, and job seekers are provided with employment information that can perform the appropriate job based on the job competency unit. Can be prevented.

Hereinafter, an embodiment in which the second filter 240 is generated to recommend a job will be described. 12 is a block diagram of a second filter generating unit configuring a job recommendation device according to an embodiment of the present invention. 3 and 12, the second filter generator 140 is a second filter generating unit 140 of a two-dimensional matrix indicating the degree of association between the job competency units 124 extracted from the dictionary 125 including a plurality of job competency units. 2 Filter 240 can be created.

The second filter generation unit 140 may include a dictionary construction unit 122, a word extraction unit 146, and a relationship analysis unit 148 between classifications. The dictionary construction unit 122 may extract job competency units 124 from job competency-related data 400. In an embodiment, the dictionary construction unit 122 may extract job competency units 124 from job competency-related data. The number of extracted job competency units 124 may be n. The n job competency units 124 may be used to calculate the second filter.

The word extracting unit 146 may extract words from all of the n job competency units 124. The word extracting unit 146 may include a morpheme analyzer for dividing sentences in the job competency units 124 into words in morpheme units and tagging parts of speech. In an embodiment, the word extracting unit 146 may extract a noun tagging morpheme after morpheme analysis, remove stop words, and then apply an N-gram such as a bi-gram in the case of a noun continuation. .

The relationship between classifications analysis unit 148 may analyze the degree of correlation between the job competency units 124 based on the similarity of words extracted from the job competency units 124. In an embodiment, the relationship between classifications analysis unit 148 may analyze a degree of correlation between n job competency units 124 based on TF-IDF (Term Frequency Inverse Document Frequency).

In an embodiment, when m words are extracted from the entire job competency units 124 by the word extracting unit 146, the interclassification relationship analysis unit 148 maps the order of all words to the column order. You can create a row vector of size ×m. The relationship between classifications analysis unit 148 generates a row vector for each job competency unit 124 from a set of words extracted from each job competency unit 124, As many as n number of row vectors can be created. Thereafter, for all n×n combinations between the n job competency units 124, for example, the cosine similarity between the row vectors of the two job competency units 124 is calculated according to Equations 1 to 4 above. By calculating, the relationship between the job competency unit documents 124 can be analyzed. Relationship values between the job competency unit documents 124 may be represented by a two-dimensional matrix having a size of n×n, and the two-dimensional matrix may be stored by the second filter 240.

13 is an exemplary diagram of a second filter according to the first embodiment of the present invention. 12 and 13, the second filter 240 includes job competency units 124 (a1, a2, ..., an-1, an) in a row unit (first unit). It is arranged and may be expressed as a two-dimensional matrix in which job competency units 124 (a1, a2, ..., an-1, an) are arranged in a column unit (a second unit). The job competency units 124 (a1, a2, ..., an-1, an) may be defined in the same order as the row unit and the column unit. Each component value of the 2D matrix of the second filter 240 may be a similarity value between a plurality of row vectors generated from a plurality of word sets each extracted from a plurality of job competency units. Since the diagonal component of the second filter 240 is a similarity value between a plurality of identical row vectors extracted from the same job capability unit, the component value is 1. The second filter 240 may be regarded as a set of row vectors having a size of 1×n of each of the n job unit capability units. A large component value in the second filter 240 means that the similarity between the two corresponding job competency units is large, and in the opposite case, the similarity between the two job competency units is small.

14 is an exemplary diagram of a second filter according to a second embodiment of the present invention. 12 and 14, in the second filter 1240, job competency units a1, a2, ..., an-1, an are arranged in a row unit (first unit), It may be expressed as a two-dimensional matrix in which the group office units (b1, b2, ..., bm-1, bm) are arranged in a column unit (a second unit). Each component value of the 2D matrix of the second filter 1240 may be a similarity value between a plurality of row vectors generated from a plurality of word sets each extracted from job competency units and group job units. A large component value in the second filter 240 means that the similarity between the two corresponding job competency units is large, and in the opposite case, the similarity between the two job competency units is small.

15 is a block diagram of a second job recommendation unit according to the first embodiment of the present invention, which constitutes a job recommendation device according to an embodiment of the present invention. 4, 13, or 14 and 15, the second job recommendation unit 340 provides one or more jobs to the subject based on the subject’s competency-related data 500 and the second filters 240 and 1240. I can recommend it. The second job recommendation unit 340 may include a word extracting unit 342, a job capability analysis unit 344, and a recommended job determination unit 346.

The word extracting unit 342 may extract competency-related words from the competency-related data 500 of the subject. The word extracting unit 342 may include a morpheme analyzer for dividing sentences in the competency-related data 500 into words in morpheme units and tagging parts of speech. In an embodiment, the word extracting unit 342 extracts a noun tagging morpheme after morpheme analysis, removes stop words, and applies N-grams such as bi-grams in the case of noun continuation, and Words related to the unit of job competency can be extracted.

The job competency analysis unit 344 determines one or more first job competency units related to the subject from words extracted from the competency-related data 500, and determines the first job competency unit based on the second filters 240 and 1240. One or more second job competency units having a high similarity to and may be extracted. As another example, when the level score for the first job competency unit is input by the target person, or when completion information such as a career or education program related to the first job competency unit is input, the job competency analysis unit 344 may perform a second filter. Based on the similarity matrix relationship between the job competency units of (240, 1240), the level score or completion information for the first job competency unit may be reflected as the level score or completion information for the other job competency units.

For example, in the second filter 240 shown in FIG. 13, the relationship between the an-1th job competency unit (the first job competency unit) and the anth job competency unit (the second job competency unit) is 0.30. , If the subject's level score related to the an-1st job competency unit is input as 90 points, or measured/evaluated or analyzed, the subject's level score may be reflected as 27 points for the anth job competency unit as well. Accordingly, based on the second filter 240, the job search-related history of the subject's first job competency unit can be expanded to other job competency units, so that various job competency units suitable for the subject can be recommended to the subject. .

16 is a configuration diagram of a second position recommendation unit according to a second embodiment of the present invention. 4, 14, and 16, the second position recommendation unit 1340 may recommend one or more military positions to the target person based on the competency-related data 500 of the target person and the second filter 1240. . The second position recommendation unit 1340 may include a word extracting unit 342, a job capability analysis unit 344, and a recommended position determination unit 1346.

The word extracting unit 342 may extract competency-related words from the competency-related data 500 of the subject. The word extracting unit 342 may include a morpheme analyzer for dividing sentences in the competency-related data 500 into words in morpheme units and tagging parts of speech. In an embodiment, the word extracting unit 342 extracts a noun tagging morpheme after morpheme analysis, removes stop words, and applies N-grams such as bi-grams in the case of noun continuation, and Words related to the unit of job competency can be extracted.

The job competency analysis unit 344 determines one or more first job competency units related to the subject from the words extracted from the competency-related data 500, and determines the first job competency unit and the high level based on the second filter 1240. As one or more second job competency units having similarity, for example, a military job unit may be extracted.

The recommended position determination unit 1328 may determine the recommended position in the order of the feature vector of the target person and the degree of similarity between the military position units.

According to an embodiment of the present invention, a filter is not created by learning using career (past job experience), such as a target's resume, portfolio, and self-introduction, but based on a dictionary including a plurality of job competency units. As a filter is created to recommend a job or military position to the target person, it is possible to recommend a suitable job or military position to the target person based on a filter prepared with objective, reasonable and consistent criteria.

17 is a configuration diagram of a second job recommendation unit constituting a job recommendation device according to another embodiment of the present invention. 15 and 17, the second job recommendation unit 340 analyzes the job competency criteria related to recruitment based on the recruitment-related data 600 and the second filter 240, and provides one or more recruitment information to the target person. Can recommend. The second job recommendation unit 340 may include a word extracting unit 348 and a job capability criterion analysis unit 350.

The word extractor 348 may extract job-related words related to recruitment from the recruitment-related data 600 of the recruiter. The word extracting unit 348 may include a morpheme analyzer that divides sentences in the recruitment-related data 600 into words in morpheme units and tags parts of speech. In an embodiment, the word extractor 348 may extract a noun tagging morpheme after morpheme analysis, remove stop words, and then apply an N-gram such as a bi-gram in the case of noun continuation. . The word extracting unit 348 may extract words related to the job competency unit from among words of the recruitment-related data 600.

The job competency criteria analysis unit 350 determines one or more third job competency units related to the recruiter from the words extracted from the recruitment-related data 600, and determines the third job competency based on the second filters 240 and 1240. One or more fourth job competency units having a high degree of similarity to the unit can be extracted. As another example, when the level score required for the third job competency unit is entered by the recruiter, or when completion information such as military career or education program required in relation to the third job competency unit is input, the job competency criteria analysis unit ( 350) is the level score or completion information required for the third job competency unit based on the similarity matrix relationship between the job competency units of the second filter 240, and the level score or completion information required for the other job competency units. Can be reflected as Accordingly, based on the second filter (240, 1240), it is possible to expand the hiring-related history requested by the recruiter for the first job competency unit to the level required for other job competency units, Recruiters can be recommended to those who meet the level of demand for them.

When one or more job competency units related to the recruiter are determined, employment information is provided to the target person matching the job competency unit information of the corresponding employee, so that job matching between the target and the recruiter can be made based on the job competency unit. Therefore, job mismatch between the recruiter and the recruiter by providing recruiters with job aptitude that meets the job aptitude of companies and public institutions, and job seekers are provided with employment information that can perform the appropriate job based on the job competency unit. In addition, as military careers can be converted into civilian careers, the details of job performance performed in the military can be recognized as careers.

At least some of the job recommendation methods according to an embodiment of the present invention may be written in a program that can be executed on a computer, and may be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium. Computer-readable recording media include volatile memories such as SRAM (Static RAM), DRAM (Dynamic RAM), SDRAM (Synchronous DRAM), Read Only Memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Nonvolatile memory such as Electrically Erasable and Programmable ROM (EEPROM), flash memory device, phase-change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FRAM), floppy disk, hard disk, or The optical reading medium may be, for example, a storage medium in the form of a CD-ROM or a DVD, but is not limited thereto.

At least some of the job recommendation methods according to an embodiment of the present invention may be implemented by software (eg, a program) including instructions stored in a computer-readable storage medium. At least some of the job recommendation methods according to an embodiment of the present invention may be implemented by calling a stored command from a storage medium and executing a process according to the called command. Instructions may include code generated or executed by a compiler or interpreter. The storage medium may be provided in the form of a non-transitory storage medium. Here,'non-transient' means that the storage medium does not contain a signal and is tangible, but does not distinguish between semi-permanent or temporary storage of data in the storage medium.

It should be understood that the above embodiments have been presented to aid the understanding of the present invention, and do not limit the scope of the present invention, and various deformable embodiments are also within the scope of the present invention. The technical protection scope of the present invention should be determined by the technical spirit of the claims, and the technical protection scope of the present invention is not limited to the literal description of the claims per se, but the invention of the scope of which the technical value is substantially equal. It should be understood that it extends to.

10: job recommendation device
20: target terminal
30: job recommendation server
40: database
100: filter generator
120: first filter generation unit
140: second filter generation unit
160: filter update unit
200: filter
220, 1220: first filter
240, 1240: second filter
300: job recommendation department
320: 1st job recommendation section
340: second job recommendation unit
400: Job competency related data
500: competency-related data
600: hiring data

Claims (9)

Including, by the job recommendation unit, recommending a job to the subject based on the subject’s competency-related data and filters,
The filter is generated based on a dictionary including a plurality of job competency units composed of data related to required competence according to the job, and the degree of association between the job competency units and words extracted from the data constituting the job competency units And at least one of the degree of relationship between the job competency units,
The job competency units include a plurality of military positions consisting of data related to required competencies according to military positions,
The competency-related data of the subject includes a job recommendation method including the subject’s military position. The method of claim 1,
The filter is a two-dimensional matrix in which job competency units are arranged in a first unit of a row unit and a column unit, and words extracted from data constituting the job competency units are arranged in another second unit. Including,
The two-dimensional matrix, a job recommendation method having a degree of association between each job capability unit of the first unit and each word of the second unit as respective component values. The method of claim 1,
The filter includes a two-dimensional matrix in which job competency units are arranged in a first unit of a row unit and a column unit, and the job competency units are arranged in another second unit,
The two-dimensional matrix is a job having a degree of relationship between a first job competency unit associated with each job competency unit of the first unit and a second job competency unit associated with each job competency unit of the second unit as component values Recommended way. The method of claim 1,
The step of recommending the job,
Extracting words related to the military position of the subject from the competency-related data; And
Determining one or more job competency units related to the subject from the extracted words; And
Job recommendation method comprising the step of determining the at least one job competency unit as a recommended job. The method of claim 4,
The at least one job competency unit is the first job competency unit,
And determining at least one second job competency unit among a plurality of job competency units as a recommended job based on a similarity with the first job competency unit based on the filter. Including, by the job recommendation unit, recommending a position to the subject based on the subject’s competency-related data and filters,
It is generated based on a dictionary including a plurality of job competency units composed of data related to required competency according to job, and the degree of association between the job competency units and words extracted from the data constituting the job competency units and the job It includes at least one of the degree of relationship between the competency units, and
The job competency units include a plurality of military positions consisting of data related to required competencies according to military positions,
The subject's competency-related data includes the subject's education information, possession certificate information, portfolio, resume, self-introduction, SNS data, data collected by a chatbot that collects history information in a conversation with the subject, and the subject's social relationship. Information, the subject’s interest on the SNS, the subject’s content viewing record, the subject’s specific information search history, including at least one of. The method of claim 6,
The filter is a two-dimensional matrix in which job competency units are arranged in a first unit of a row unit and a column unit, and words extracted from data constituting the job competency units are arranged in another second unit. Including,
The two-dimensional matrix, a group position recommendation method having a degree of association between each job competency unit of the first unit and each word of the second unit as respective component values. The method of claim 6,
The filter includes a two-dimensional matrix in which job competency units are arranged in a first unit of a row unit and a column unit, and the job competency units are arranged in another second unit,
The two-dimensional matrix is a group having a degree of a relationship between a first job competency unit associated with each job competency unit of the first unit and a second job competency unit associated with each job competency unit of the second unit as component values How to recommend a position. The method of claim 1,
The step of recommending the job,
Extracting words related to the job competency of the subject from the competency related data; And
Determining one or more group positions related to the subject from the extracted words; And
And determining the at least one military position unit as a recommended military position.

Images