KR20200023259A - Method, apparatus and program for providing specialist matching service using artificial intelligence model - Google Patents

Abstract

In a method performed by a computer, disclosed is a method for providing a specialist matching service. The method for providing a specialist matching service comprises the steps of: collecting job seeker information (S100); verifying the job seeker information (S200); storing the verified job seeker information in a database (S300); obtaining job offer information from a company (S400); matching job seekers corresponding to the job offer information among the job seekers stored in the database (S500); and providing the matched job seeker information to the company (S600).

Description

Method, apparatus and program for providing expert matching service using AI model {METHOD, APPARATUS AND PROGRAM FOR PROVIDING SPECIALIST MATCHING SERVICE USING ARTIFICIAL INTELLIGENCE MODEL}

The present invention relates to a method, apparatus and program for providing expert matching service using an artificial intelligence model.

Existing job search and job services were provided by collecting and distributing job postings, and assisting job seekers to search for job postings and apply for desired job postings. In the case of a service that searches for and provides job seekers according to job postings, it is generally provided through a headhunting company, and a headhunting company often recruits job seekers by posting job advertisements again.

However, unlike in the past, workers often turn away, and this tendency becomes stronger in the case of professionals with expertise in specific fields. In addition, there is a growing need for companies to directly contact and search for professions with specific areas of expertise.

In addition, professional workers often take non-fixed forms of work such as temporary workers, part-time jobs, and freelancers, and therefore, there is a demand for developing job searcher matching platforms that can reflect this tendency.

Publication No. 10-2010-0026834, published March 10, 2010

The problem to be solved by the present invention is to provide a method, apparatus and program for providing an expert matching service using an artificial intelligence model.

Problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

Expert matching service providing method according to an aspect of the present invention for solving the above problems, the step of collecting the job seeker information (S100), the step of verifying the job seeker information (S200), the verified job seeker information to the database Storing (S300), obtaining job information from a company (S400), matching job seekers corresponding to the job information among job seekers stored in the database (S500), and providing the matched job seeker information to the company. It includes the step (S600).

In addition, the step (S100) includes a step (S110) of collecting background information and career information of job seekers, the step (S200), the step of verifying the collected background information and career information (S210) and And evaluating the specialty of the job seeker based on the result verified in the step S210, in step S500, matching the one or more job seekers having a specialty corresponding to the job information. Step S510 may be included.

In addition, the step (S210), while obtaining evidence corresponding to the collected background information and career information, the evidence is based on the data obtained from the job seeker and the keywords included in the collected background information and career information It may include a step (S212), including the searched data based on the basis and the step (S214) of verifying the background information and career information of the job seeker based on the evidence.

In addition, the step (S220), the step of evaluating the relationship between the collected background information and career information and the professional field of the job seeker (S222), the step of evaluating the score of each of the collected background information and career information (S224) ), Based on the evaluated association, applying a weight to each of the evaluated scores (S226) and evaluating the job seeker's expertise in the professional field of the job seeker based on the weighted scores. It may include (S228).

In addition, the step (S222), the step of obtaining the professional evaluation data of the job seekers performed (S710), the step of extracting the keywords included in the acquired professional evaluation data (S720), corresponding to the extracted keywords Acquiring a professional evaluation result (S730); generating learning data including the extracted keywords and the professional evaluation result (S740); and using the learning data, evaluating a correlation between a keyword and a specialty. Training the artificial intelligence model (S750), extracting one or more keywords from the background information and career information of the job applicant collected in the operation (S110) (S760) and using the artificial intelligence model, the step The method may further include a step (S770) of evaluating an association between the one or more keywords extracted in step S760 and the professional field of the job seeker, and the step (S224) may include: The method may further include obtaining a participation rate of the job seeker for each career information (S780) and adjusting the evaluated score based on the participation rate (S790).

In addition, the step (S400) includes the step of obtaining job information for finding a freelancer (S410), the step (S500), the step of extracting a freelance job candidate matching the job information among job seekers stored in the database (S510), obtaining a job performance history and a job schedule of the freelance job seeker (S520), comparing the information obtained in the step (S520) with the request schedule included in the job offer information, and an expected job of the freelance job seeker Acquiring a schedule (S530), estimating a work process completion degree of the freelance job seeker according to the expected work schedule (S540) based on the work performance history, and a freelance job seeker having a work process completion degree equal to or more than a preset reference value; Matching the job information may be included (S550).

In addition, the step (S600), the step of obtaining a resume included in the matched job seeker information (S810), the step of extracting the part associated with the job information from the obtained resume (S820), the obtained resume Extracting different portions from other resumes stored in the database (S830), extracting one or more keywords from each of the portions extracted in the steps (S820) and (S830), and the extracting The method may further include generating a summary of the resume (S850) and providing the generated summary to the company (S860) based on the generated keyword.

In addition, the step (S400), the step of obtaining project information from the company (S910), the step of obtaining information on one or more work areas included in the project information (S920), performing the one or more work areas Determining a specialty for the further step (S930) and determining the required personnel of the one or more work areas (S940), the step (S500), the job seeker information corresponding to the determined specialty to obtain And extracting job candidates corresponding to the determined required personnel (S960) from the job applicant information obtained in the step S950 and the step S950, and the step S600 is performed to the extracted job candidates. The method may further include providing information on the company (S970).

According to an aspect of the present invention for solving the above problems includes a memory for storing one or more instructions and a processor for executing the one or more instructions stored in the memory, the processor by executing the one or more instructions, job seekers Collecting information (S100), verifying the job applicant information (S200), storing the verified job candidate information in a database (S300), obtaining job information from a company (S400), and in the database. An apparatus is provided for performing matching (S500) of job candidates corresponding to the job listings among stored job candidates and providing the matched job candidate information to the company (S600).

In accordance with an aspect of the present invention for solving the above problems is provided a computer program stored in a computer-readable recording medium that can be combined with a computer that is hardware, to perform the expert matching service providing method according to the disclosed embodiment.

Other specific details of the invention are included in the detailed description and drawings.

According to the disclosed embodiments, there is an advantage that allows a company to search for a desired expert by providing a job seeker information-oriented platform.

In addition, by managing and providing information of job seekers having a variety of professionalism and work forms, there is an advantage that the job seekers' professionalism can be easily recognized, and the job seeker can freely select a work form.

Effects of the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a diagram illustrating a system according to an exemplary embodiment.
2 is a flowchart illustrating a method for providing a job seeker matching service according to an exemplary embodiment.
3 is a flowchart illustrating a job seeker matching method according to an exemplary embodiment.
4 is a flowchart illustrating a verification method according to an exemplary embodiment.
5 is a flowchart illustrating a professional evaluation method according to an exemplary embodiment.
6 is a flowchart illustrating a method of evaluating job applicants, according to an exemplary embodiment.
7 is a flowchart illustrating a work schedule based matching method according to an exemplary embodiment.
8 is a flowchart illustrating a method of providing resume summary information according to an exemplary embodiment.
9 is a flowchart illustrating a project-based matching method according to an embodiment.
10 is a block diagram of an apparatus according to an embodiment.

Advantages and features of the present invention, and methods for achieving them will be apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be embodied in various different forms, only the present embodiments are intended to complete the disclosure of the present invention, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the invention, which is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and / or “comprising” does not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like elements throughout, and "and / or" includes each and all combinations of one or more of the mentioned components. Although "first", "second", etc. are used to describe various components, these components are of course not limited by these terms. These terms are only used to distinguish one component from another. Therefore, of course, the first component mentioned below may be the second component within the technical spirit of the present invention.

Unless otherwise defined, all terms used in the present specification (including technical and scientific terms) may be used in a sense that can be commonly understood by those skilled in the art. In addition, terms that are defined in a commonly used dictionary are not ideally or excessively interpreted unless they are specifically defined clearly.

The term "part" or "module" as used herein refers to a hardware component such as software, FPGA or ASIC, and the "part" or "module" plays certain roles. However, "part" or "module" is not meant to be limited to software or hardware. The “unit” or “module” may be configured to be in an addressable storage medium or may be configured to play one or more processors. Thus, as an example, a "part" or "module" may include components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. Functions provided within components and "parts" or "modules" may be combined into smaller numbers of components and "parts" or "modules" or into additional components and "parts" or "modules". Can be further separated.

The spatially relative terms " below ", " beneath ", " lower ", " above ", " upper " It can be used to easily describe a component and its correlation with other components. Spatially relative terms are to be understood as including terms in different directions of components in use or operation in addition to the directions shown in the figures. For example, when flipping a component shown in the drawing, a component described as "below" or "beneath" of another component may be placed "above" the other component. Can be. Thus, the exemplary term "below" can encompass both an orientation of above and below. Components may be oriented in other directions as well, so spatially relative terms may be interpreted according to orientation.

In the present specification, a computer refers to any kind of hardware device including at least one processor, and according to an embodiment, it may be understood as a meaning encompassing a software configuration that operates on the hardware device. For example, a computer may be understood as including, but not limited to, a smartphone, a tablet PC, a desktop, a notebook, and a user client and an application running on each device.

Hereinafter, with reference to the accompanying drawings will be described an embodiment of the present invention;

1 is a diagram illustrating a system according to an exemplary embodiment.

Referring to FIG. 1, a job seeker matching service providing system according to an exemplary embodiment includes an enterprise terminal 10, a job seeker terminal 20, and a server 100.

In one embodiment, the corporate terminal 10, the job seeker terminal 20 and the server 100 is a kind of the above-described computer, the server 100 may be a cloud server according to the embodiment, but is not limited thereto.

Each step described herein is described as being performed by a computer, but the subject of each step is not limited thereto, and at least some of the steps may be performed in different devices according to embodiments. For example, each of the steps described herein may be performed by the server 100, but is not limited thereto.

For example, the corporate terminal 10 may be a computer used by a human resources representative of the enterprise, but is not limited thereto.

In the present specification, an enterprise may be understood to encompass not only a business such as a sole proprietor or a corporation, but also a general individual, and does not limit a specific object. Likewise, an enterprise may mean an institution, a municipality, an association, or an organization.

For example, the job seeker terminal 20 may be a computer used by a job seeker, but is not limited thereto.

The job seeker terminal 20 uploads job seeker information to the server 100, and the enterprise terminal 10 requests and receives job seeker information corresponding to the job offer information from the server 100. The corporate terminal 10 may perform a contract by communicating with the matching job seekers and the server 100.

The contract information is stored in the server 100, and the result of performing the work according to the contract (eg, working period, salary, performance, employee evaluation, corporate evaluation, etc.) may also be stored in the server 100.

In some embodiments, at least some of the information stored in the server 100 may be stored and managed in the blockchain. For example, at least some of company information, job seekers information, contract information, and business performance results according to the contract may be stored in the blockchain, thereby preventing forgery and increasing the reliability of the service provided by the server 100. That is, the server 100 may verify company information and job seeker information based on the information stored in the blockchain, and perform matching based on the verified information.

2 is a flowchart illustrating a method for providing a job seeker matching service according to an exemplary embodiment.

In step S100, the computer collects job seeker information.

In step S200, the computer verifies the job seeker information.

In step S300, the computer stores the verified job seeker information in a database.

In step S400, the computer obtains job offer information from the company.

In step S500, the computer matches job seekers corresponding to the job information among job seekers stored in the database.

In step S600, the computer provides the matched job seeker information to the enterprise.

In this specification, a job seeker may mean a jobless or a prospective employee who wants to find a job, but may also mean a freelancer who seeks a part-time job or an outsourcing job. In addition, in a preferred embodiment according to the present invention may look for a job seeker having expertise in a particular field. However, the type of job seekers is not limited thereto, and may be understood as a meaning including general office workers, part-timers, and daily workers.

Similarly, in this specification, an expert means a person who has a professional ability to perform a specific field of work, but is not limited to a specific criterion for judging an expert, but in a broad sense, it encompasses all kinds of job seekers. It can also be understood.

In addition, job seekers encompass all job seekers seeking full-time work, job seekers seeking contract work, job seekers seeking part-time work, job seekers seeking part-time work, and job seekers seeking outsourcing. It is understood, but not limited to this.

In the present specification, the job information may be obtained as a job posting form for finding an employee who will be in charge of a specific job of a specific company, but is not limited thereto, and may include content of finding an expert who will be in charge of a specific job of a specific project. According to an embodiment, the job information may refer to search information or filter information input by a company to search for a specific job applicant.

That is, the computer may extract one or more keywords from job postings uploaded by the company or analyze the contents by using natural language processing (NLP), and provide job seekers corresponding to job postings. Job seekers may be searched and filtered based on the input search information or filter information.

In one embodiment, the computer may provide job seekers information to the enterprise via web pages or applications. Computers can provide information about job seekers who have been searched and organized based on information input from the company, but the information of job seekers who are recommended or registered in real time through web pages or application main pages or pop-up pages can be selected. It can also be provided to companies.

3 is a flowchart illustrating a job seeker matching method according to an exemplary embodiment.

In the above-described step (S100), the computer may perform the step (S110) of collecting background information and career information of the job seeker.

In step S200, the computer may perform step S210 of verifying the collected background information and career information.

In addition, the computer may perform the step (S220) of evaluating the professional field of the job seeker based on the result verified in the step (S210).

In operation S500, the computer may perform operation S510 of matching one or more job applicants having a specialty corresponding to the job information.

For example, the computer may obtain background information and career information uploaded by the job seeker, and may verify the authenticity of each information.

In one embodiment, the background information of the job seeker may include information related to the job seeker's specifications, such as, but not limited to, the job applicant's education, qualifications, language score.

In addition, the career information of the job seeker may include information about a job where the job seeker worked, information about a project performed by the job seeker, information about a task performed by the job seeker, but is not limited thereto.

The computer may evaluate each job seeker's area of expertise based on the job seeker's information. In one embodiment, the computer may obtain information about the specialty directly from the job seeker. In this case, the computer may evaluate the job seeker's expertise in the professional field based on the job seeker's background information and career information.

In another embodiment, the computer may select the professional field of the job seeker based on the background information and the career information of the job seeker. According to an embodiment, the computer may select one or more specializations for each job seeker. The computer can evaluate the expertise of each of the one or more specializations, and can determine the priority of each job seeker's specialization according to the evaluated expertise.

In one embodiment, the job seeker may have a plurality of specialties. Similarly, the job listings of a company may include information for finding job seekers having a plurality of specialties. Accordingly, the computer may select a plurality of specialties for job seekers, provide professional information on each specialty, and perform matching based on the job seekers.

Accordingly, the computer may select one or more other specialty areas of the job seeker based on the background information and the career information of the job seeker even if the job candidate directly inputs the specialty field. According to an embodiment, the computer may request a job seeker for confirmation for the selected specialty. For example, if a job seeker does not have expertise in the field, the job seeker may request the deletion of the area of expertise. In addition, if a job seeker does not want to work in the field, he or she may request the deletion of the area of expertise.

For example, certain job seekers may be rated as having expertise in both development and design. However, job seekers may want to focus on design work, not development work. In this case, the job seeker may request that the development work be deleted from his or her specialty, or may select only the design work as a specialty.

In one embodiment, the computer selects one or more specializations of each job seeker, including information about the areas of expertise and areas of interest not only available from each job seeker, but also information on areas of interest and areas of interest. May be obtained.

For example, a specific job seeker may or may not have a specialty in any specialty, but may want to experience work in that field. In this case, the computer may perform job information matching based on a specialized field desired by the job seeker.

In one embodiment, each job seeker's ability may be assessed as a numerical value. However, each job seeker's ability can be adjusted according to the individual's choice. For example, a specific job seeker may have a development ability of 50, a design ability of 40, and a planning ability of 30. This may result in an average of 40 job seekers.

The computer may perform job matching based on job applicants' overall stats and detailed stats, and may match job applicants with a specific statistic according to the contents of job candidates, and job applicants with a good balance of overall stats or stats. May match.

According to an embodiment, a specific ability value may be deleted (or set to 0) or blinded according to a job seeker's request. In this case, job information requiring the corresponding capability may be excluded from the matching object.

In another example, a job seeker may want to perform a development job, even though his design ability is 70 but his development ability is 10. In this case, if the design ability for the job candidate is blinded, the total ability of the job candidate may be evaluated as 10. However, instead of completely blinding other abilities, job seekers can determine the level of disclosure of those abilities. For example, job seekers can increase their value by assisting with design rather than allowing them to perform development tasks even if they lack the ability to develop. For example, by setting the disclosure level of the design capability to 50%, the design capability is 35 and the development capability is 10, so that a matching request may be made.

The capability setting and the matching method based thereon are not limited thereto, and various search methods, capability setting methods, and search result filtering methods may be applied according to embodiments.

4 is a flowchart illustrating a verification method according to an exemplary embodiment.

In the above-mentioned step (S210), the computer obtains evidence corresponding to the collected background information and career information, wherein the evidence is a keyword included in the data obtained from the job applicant and the collected background information and career information. Step S212 may be performed, including the retrieved material based on the information.

In addition, the computer may perform the step S214 of verifying the background information and the career information of the job applicant based on the evidence.

In one embodiment, the computer may collect evidence directly from the job seeker, and the evidence may include a document or a link. For example, it may include a certificate proving specific background information or career information, or a link for confirming the proof fact through the web.

In addition, the computer may search for information to verify this, based on the background information and career information. For example, the computer may verify the education or career of each job seeker by obtaining a list of graduates of the university, a list of successful candidates, a list of employees of a company, and the like.

In addition, the computer stores the results of matching, contracts and performance performed in accordance with the disclosed embodiments, some of which may be stored in the blockchain.

The computer can verify the authenticity of the background information and the career information uploaded by each job applicant based on the stored information.

5 is a flowchart illustrating a professional evaluation method according to an exemplary embodiment.

In the above-described step (S220), the computer may perform the step (S222) of evaluating the association between the collected background information and career information and the professional field of the job seeker.

In addition, the computer may perform a step (S224) of evaluating the score of each of the collected background information and career information.

In addition, the computer may perform a step S226 of applying a weight to each of the evaluated scores based on the evaluated correlation.

In addition, the computer may perform an operation (S228) of evaluating the job seeker's expertise in the job seeker's specialty based on the weighted score.

According to an embodiment, after verifying the authenticity of the information uploaded by each job seeker, each job seeker may be evaluated based on the content of each information. For example, there is a need for a system for evaluating each job seeker for a particular field of expertise, and if so, the level of expertise.

In one embodiment, the computer may evaluate the association between the job seeker information collected and each job seeker's specialty. For example, based on information on the job where each job seeker worked, departments in each job, their duties, and other work experiences, and the tasks or projects performed by each job searcher, and the job of each job seeker in the assignment and project. Each job seeker can then be assessed for association with one or more specializations.

In addition, the computer may evaluate the score of each job seeker information. For example, when evaluating whether each job seeker is an expert in a particular field, the score may be evaluated differently depending on the length of work, duties, and departments, even if each job seeker works for a company performing a job in that field. .

In addition, even if each job seeker participated in a specific task, the score may be given differentially according to the participation rate.

In addition, the score may be differentially given according to the evaluation result of the job search performed by the job seeker in each job or assignment.

In addition, the computer may weight the scores evaluated according to the association between each job seeker information and a specific specialty. For example, even if the score assigned for a specific career information is 100 points, if the association between the career information and a specific specialty is 70%, the score may be evaluated as 70 points.

The computer may add the score evaluation result and the weighted value to each evaluation score to evaluate each job seeker's expertise in a particular specialty.

In an embodiment, the association between each job seeker information and each specialty may be performed based on a preset database, and the database may include information previously input by experts in each field.

For example, a computer can evaluate professionalism by gathering information from experts in each field that evaluate their association with the field of expertise, and comparing the information with each job seeker. Such a task may be performed by a simple search and comparison according to keyword extraction, or may be performed through learning based on an artificial intelligence model.

6 is a flowchart illustrating a method of evaluating job applicants, according to an exemplary embodiment.

In the above-described step (S222), the computer may perform a step (S710) of obtaining the professional evaluation data of job seekers previously performed.

In addition, the computer may perform the step (S720) of extracting keywords included in the acquired professional evaluation data.

In addition, the computer may perform an operation (S730) of obtaining a professional evaluation result corresponding to the extracted keywords.

In operation S740, the computer may generate training data including the extracted keywords and the expertise evaluation result.

In addition, the computer may perform an operation (S750) of training an artificial intelligence model for evaluating a correlation between a keyword and a specialized field using the training data.

In addition, the computer may perform the step (S760) of extracting one or more keywords from the background information and the career information of the job seeker collected in the step (S110).

In addition, the computer may perform an operation (S770) of evaluating an association between the one or more keywords extracted in the operation S760 and the professional field of the job seeker using the artificial intelligence model.

In the above-described step (S224), the computer may perform the step (S780) of obtaining the participation rate of the job seeker for each of the collected career information.

In addition, the computer may perform the step S790 of adjusting the evaluated score based on the participation rate.

As described above, the computer may acquire data evaluating the expertise of job seekers who have been previously performed. For example, the computer may obtain information about each job seeker and information about each job seeker's association with a specific specialty.

The computer stores the obtained information in a database and can extract keywords from the stored information. For example, the computer extracts one or more keywords from each job seeker's information and obtains information about the association of each job seeker with each specialty, thereby obtaining information on the association between each keyword and each specialty. can do.

In one embodiment, the computer may obtain information through simple comparison between a keyword and a specialized field, or may acquire information through learning based on an artificial intelligence model.

In one embodiment, the computer may select extracted keywords. For example, the computer may exclude keywords that are common to other job seekers' information as general keywords, and may determine keywords that may be differentiated from other job seekers' information as key keywords of the job seekers' information.

In addition, the computer may generate the training data based on the collected information. In the learning data generation process, key keywords of job seekers information may be selected, and this operation may be performed through classification based on natural language processing (NLP), keyword comparison, clustering, etc., but is not limited thereto.

The acquired learning data may include information about the association between the specialty and the keywords. For example, the information may include information for classifying each specialty category and keywords that are related to or above a reference value, and may include information obtained by evaluating the correlation between each keyword and each specialty by a quantitative value such as a percentage.

The computer can train the AI model based on the training data.

The computer may extract keywords from the obtained job seeker information, and may evaluate an association between each extracted keyword and each specialty using an artificial intelligence model.

In addition, the computer may obtain the participation rate of each job seeker for each career information, and adjust the evaluation score based on this. For example, if the job seeker participates in a specific task, but the participation rate is 10%, only 10% of the evaluation score for the career information may be reflected to the job seeker.

7 is a flowchart illustrating a work schedule based matching method according to an exemplary embodiment.

In the above-described step (S400), the computer may perform a step (S410) of obtaining job information for finding a freelancer.

In the above-described step (S500), the computer may perform a step (S510) of extracting a freelance job applicant matching the job information among job seekers stored in the database.

In addition, the computer may perform a step (S520) of acquiring a work performance history and a work schedule of the freelance job seeker.

In addition, the computer may compare the information obtained in the step (S520) and the request schedule included in the job listing information, and may perform the step (S530) of obtaining the expected work schedule of the freelance job applicant.

In addition, the computer may perform an operation (S540) of estimating the completion of work processing of the freelance job applicant according to the expected work schedule based on the work performance history.

In addition, the computer may perform a step (S550) of matching the freelance job applicant with the job information with the degree of completion of the business process to a preset reference value.

For example, the job seeker matching method according to the disclosed embodiment may be used to provide a freelance job seeker with a service for matching and entrusting outsourcing.

Freelance job seekers are entrusted with outsourcing work in the form of assignments, and work on the commissioned scope within the period of delivery. In this case, the number of tasks that each freelance job applicant can take is not limited, and the task may be taken and processed at the discretion of the individual.

However, this may lead to a task exceeding an individual's ability, which may lead to a loss of quality of work or lack of time.

Therefore, the computer may determine the job processing speed of the job seeker based on an existing job performance history of the freelance job seeker, obtain a current job schedule, and determine the current work amount.

The computer can generate a work schedule expected when the work is entrusted to the freelance job seeker based on the type and amount of work to be entrusted to the freelance job seeker, and estimate the completion of work processing of the freelance job seeker based on the job schedule. have. For example, if the expected job schedule determines that the freelance job seeker cannot handle the work within the normal working hours, it may be predicted that the degree of completion will decrease.

According to an embodiment, the freelance job seeker normally works 8 hours a day, but when there is a lot of work, he may work 10 hours a day. The computer can also obtain information on whether the freelance job seeker does not lose his or her completeness, based on his / her work history.

In addition, each freelance job seeker can pre-populate a range of hours per day that can be performed. For example, there may be a person who wants to perform only 6 hours or less of work per day, and if there is a lot of work, there may be a person who can perform more than 10 hours of work a day. Thus, the computer can generate and evaluate the expected work schedule based on a range of work hours previously input by the freelance job seeker.

In addition, the computer may obtain information about how many hours each day job seeker can work for, without sacrificing the completion of the task, depending on the degree of completion of the task performed based on this.

Based on the information obtained, the computer judges whether or not each job seeker can perform the work within the maximum working time per day without sacrificing the completion of the work, and judges whether the work can be completed within the period based on the expected work schedule. Results Freelance job seekers who can perform their jobs can be matched with job listings.

According to an embodiment, the computer may acquire a personal schedule of a freelance job seeker, and may obtain information about a time at which a task can be performed substantially based on the personal schedule. For example, if the job seeker has a personal schedule, he or she will not be able to work at that time, so that the job seeker can obtain the actual work schedule for the job seeker, and create an expected job schedule based on the job seeker. Assess the feasibility of doing business

8 is a flowchart illustrating a method of providing resume summary information according to an exemplary embodiment.

In operation S600, the computer may perform an operation S810 of obtaining a resume included in the matched job candidate information.

In addition, the computer may perform a step (S820) of extracting a part associated with the job offer information from the obtained resume.

In addition, the computer may perform a step S830 of extracting a part different from other resumes stored in the database from the obtained resume.

In addition, the computer may perform step S840 of extracting one or more keywords from each of the portions extracted in the above-described step S820 and step S830.

In addition, the computer may perform a step S850 of generating a summary of the resume, based on the extracted keyword.

In addition, the computer may perform the step (S860) of providing the generated summary to the company.

In one embodiment, each company may want to save time spent looking for resumes uploaded by job seekers, and may want to obtain information that is missing in the process of reviewing resumes in a short time.

In this specification, a resume does not mean a specific form, but is understood as a meaning encompassing all forms of job seeker information according to the disclosed embodiments.

The computer may extract the resume from job applicant information and extract portions associated with each job listing. That is, unlike a case where a job seeker submits a resume to a company, since a company searches for a job seeker, the computer may extract a part associated with job information of each company from job seeker information (resume) of each job seeker.

For example, the associated part may mean, but is not limited to, background information and career information that can prove the specialized field of each job offer.

The computer can also extract the characteristic parts of the resume. For example, the computer may extract different parts by comparing the resume included in the job seeker information with the resumes of other job seekers stored in the database. Common parts of the resume may be general descriptions or difficult-to-characterize job seekers. Thus, the computer may extract content that is different from other resumes or that is included in other resumes with low probability or rate.

The computer can generate a summary of the resume based on the extracted content, highlight the full text of the summary, and highlight key keywords in the summary.

The computer can arrange the generated summary and provide it to the company, and the company has the advantage of selecting the information on the desired job candidate and specifically reviewing the summary while checking the summary.

9 is a flowchart illustrating a project-based matching method according to an embodiment.

In step S400, the computer may perform step S910 of obtaining project information from the company.

In addition, the computer may perform an operation (S920) of acquiring information on one or more work areas included in the project information.

In addition, the computer may perform a step S930 of determining a specialty for performing the one or more business fields.

In addition, the computer may perform the step S940 of determining the required personnel of the one or more business areas.

In operation S500, the computer may perform an operation S950 of obtaining job applicant information corresponding to the determined specialty.

In addition, the computer may perform the step S960 of extracting job seekers corresponding to the determined required personnel from the job seeker information obtained in the aforementioned step S950.

In the above-described step (S600), the computer may perform the step (S970) of providing the extracted information about the job seeker to the company.

In one embodiment, the project may mean a task force (TF) or a task that is performed for a specific period of time, but is not limited thereto, and may also mean a task of a general company or a specific department.

The computer may obtain from the project information information about one or more areas of work required to carry out the project. This may mean information about the division of work of a company.

The computer can determine one or more specializations to handle each business area, and determine the type and number of personnel required in that field. For example, specializations may include, but are not limited to, development, design, planning, accounting, language, and the like.

In addition, the computer can determine the type and number of manpower required in each specialty (for example, two employees, two representatives, or one more than five years of experience).

The computer may extract job candidate information based on the determined type and number of required personnel and provide the extracted information to the enterprise.

That is, the computer can acquire only project information, and design and recommend a manpower required to operate the project.

In one embodiment, the computer may generate various TF team configurations based on the project information, and generate a plurality of combinations including different job seekers for each configuration.

For example, a computer can create multiple configurations of the type and number of people required for each specialization and provide them to the enterprise to select the desired configuration, along with quantitative evaluation results for each configuration. Can be.

In addition, the computer may generate a plurality of combinations that include different job seekers for the determined configuration, and provide each combination to the enterprise. For example, different job seekers may be matched to respective positions constituting the TF team, and quantitative evaluation information of each TF team based on the matching result may be provided to the company. The enterprise may select at least one team from the examples presented. According to an embodiment, an enterprise may request to create a new combination using different job seekers included in the plurality of combinations presented, and request to match each job seeker based on the generated combination.

In addition, the computer can perform the work of the personnel department of the company, for example, it is possible to determine the type and number of personnel required of each team based on the business content of the company.

Computers can also place employees who are already working in the company at each location needed for projects or tasks. The computer acquires a pool of employees that can be assigned to a project or task and fills in the pool first. If there is a shortage of workers, the computer can search and extract job seekers for that workforce and provide that information to the enterprise.

10 is a block diagram of an apparatus according to an embodiment.

The processor 102 may include a connection passage (eg, a bus, etc.) that transmits and receives signals with one or more cores (not shown) and graphics processing unit (not shown) and / or other components. .

The processor 102 according to one embodiment executes one or more instructions stored in the memory 104 to perform the method described in connection with FIGS. 1-9.

For example, the processor 102 collects job seeker information, verifies the job seeker information, stores the verified job seeker information in a database, obtains job information from a company, and the job search information among job seekers stored in the database. Matching job seekers corresponding to the job information and providing the matched job candidate information to the company.

Meanwhile, the processor 102 may include random access memory (RAM) and read-only memory (ROM) for temporarily and / or permanently storing a signal (or data) processed in the processor 102. , Not shown) may be further included. In addition, the processor 102 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processor, a RAM, and a ROM.

The memory 104 may store programs (one or more instructions) for processing and controlling the processor 102. Programs stored in the memory 104 may be divided into a plurality of modules according to functions.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, in a software module executed by hardware, or by a combination thereof. The software module may be a random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art.

The components of the present invention may be implemented in a program (or an application) and stored in a medium to be executed in combination with a computer which is hardware. The components of the present invention may be implemented in software programming or software elements, and similarly, embodiments include C, C ++, including various algorithms implemented in combinations of data structures, processes, routines, or other programming constructs. It may be implemented in a programming or scripting language such as Java, assembler, or the like. Functional aspects may be implemented in algorithms running on one or more processors.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains may realize the present invention in other specific forms without changing the technical spirit or essential features thereof. I can understand that. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive.

10: enterprise terminal
20: Job Seeker Terminal
100: server

Claims (1)

In a method performed by a computer,
Collecting expert information (S100);
Verifying the expert information (S200);
Storing the verified expert information in a database (S300);
Acquiring job information from the company (S400);
Matching an expert corresponding to the job offer information among experts stored in the database (S500); And
Providing the matched expert information to the company (S600); Including,
The step (S100),
Collects career information, including background information about the professional's work, information on the project undertaken by the expert, and assignments undertaken by the expert. Step S110; Including,
The step (S200),
Verifying the collected background information and career information (S210); And
Evaluating an expert's specialty based on the result verified in the step S210; Including,
The step (S210),
Acquiring evidence corresponding to the collected background information and career information, wherein the evidence includes data retrieved based on data obtained from the expert and keywords included in the collected background information and career information. (S212); And
Verifying the background information and the career information of the expert based on the documentary evidence (S214); Including,
The step (S214),
Receiving documentary evidence from the expert; And
Verifying the background information and the career information by searching the background information and the information for verifying the career information; Including,
The step (S220),
Evaluating an association between the collected background information and career information with a professional field of the expert (S222);
Evaluating scores of the collected background information and career information (S224);
Based on the evaluated association, applying a weight of each of the evaluated scores for the expert's specialty (S226); And
Based on the weighted scores, evaluating the expert's expertise in the expert's field of expertise (S228); Including,
The step (S222),
Expertise of the experts already carried out on the basis of information on the workplace in which the specialist worked, the department in each workplace, his or her work, other work experience, the tasks carried out by the specialist, the project and the tasks and tasks performed by each specialist in the project. Acquiring evaluation data (S710);
Extracting keywords included in the acquired professional evaluation data (S720);
Obtaining a professional evaluation result corresponding to the extracted keywords (S730);
Generating training data including the extracted keywords and the expertise evaluation result (S740);
Training an artificial intelligence model for evaluating a correlation between a keyword and a specialized field using the training data (S750);
Extracting one or more keywords from the background information and the career information of the expert collected in the step S110 (S760); And
Evaluating (S770) an association between the one or more keywords extracted in the step S760 and the expert's specialty using the artificial intelligence model; More,
The step (S224),
Obtaining a participation rate of the expert for each of the collected career information (S780); And
Adjusting the evaluated score based on the participation rate (S790); More,
The step (S400),
Acquiring job information for finding a freelance expert (S410); Including,
The step (S500),
Extracting a freelance expert matching the job information from the experts stored in the database (S510);
Acquiring a work performance history, a personal schedule, and a work schedule of the freelance expert (S520);
Comparing the request schedule included in the job information with the information obtained in the step S520, and obtaining an expected work schedule of the freelance expert (S530);
Estimating a work process completion degree of the freelance expert according to the expected work schedule based on the work performance history (S540); And
Matching the freelance expert whose job process completion degree is equal to or greater than a predetermined reference value with the job information (S550); Including,
The step (S530),
Obtaining a work performance possible time for a time at which work can be performed based on the personal schedule;
Determining a current amount of work of the freelance expert based on the work schedule; And
Obtaining an expected work schedule of the freelance expert by comparing the work execution time and the current work quantity with a request schedule included in the job offer information; Including,
The step (S600),
Obtaining a resume included in the matched expert information (S810);
Extracting a part associated with the job offer information from the obtained resume (S820);
Extracting, from the obtained resume, a portion different from other resumes stored in the database (S830);
Extracting one or more keywords from each of the portions extracted in the step S820 and the step S830 (S840);
Generating a summary of the resume based on the extracted keyword (S850); And
Providing the generated summary to the company (S860); More,
The step (S400),
Obtaining project information from the company (S910);
Acquiring information on one or more work areas included in the project information (S920);
Determining a specialty for performing the one or more business fields (S930); And
Determining required personnel of the one or more business areas (S940); More,
The step (S500),
Acquiring expert information corresponding to the determined specialty (S950); And
Extracting an expert corresponding to the determined necessary manpower from the expert information obtained in the step S950 (S960); More,
The step (S600),
Providing information on the extracted expert to the company (S970); Including,
The step (S100),
Selecting one or more specialty fields for the expert based on the background information and the career information;
Evaluating expertise in each of the one or more specialties; And
Determining a priority of the one or more specialties based on the evaluated expertise; Including,
The step (S500),
When the delete command for the at least one specialty of the one or more specialties is received, deleting the at least one specialty corresponding to the delete command from the specialty of the expert; And
Matching an expert corresponding to the job offer information on the basis of the expertise of each of the one or more specialty areas not deleted; Including,
The step (S770),
Obtaining a core keyword among one or more keywords extracted in the step S760 by using at least one method of natural language processing (NLP), keyword comparison, and clustering, and selecting the acquired core keyword as learning data;
Training the artificial intelligence model based on the selected training data; And
And using the learned artificial intelligence model to evaluate the association between the key keyword and the expert's specialty.
The learning data may include a category of a specialty category, information that classifies keywords having a predetermined level or more associated with the specialty category, and information quantitatively evaluating the relation between each keyword and each specialty field. How to provide expert matching service.

Images