Recruitment support device and recruitment support method

Abstract

To provide a recruitment support device and recruitment support method capable of appropriately recruiting job seekers.SOLUTION: A recruitment support device includes a management part for managing profile information of job seekers, and a control part for generating a scout document reflecting word groups containing one or more words extracted from the profile information. The control part leans correlation between first parameters relating to recruitment of the job seekers and the word groups to generate a learning model and extracts the word groups based on the generated learning model.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a recruitment support device and a recruitment support method. [Background technology]

[0002] In recent years, there has been a growing interest in services that match job seekers with employers. In these matching services, job seekers register their profile information in a database, and employers send employment-related documents (hereinafter referred to as "scouting documents") to job seekers based on the job seeker's profile information.

[0003] Furthermore, since creating a scout document is cumbersome, a technique has been proposed that utilizes a template for the scout document (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-246453 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-mentioned scouting letter templates are commonplace to job seekers, which reduces their interest in the scouting letters, leading to a lower response rate and the inability to properly hire job seekers.

[0006] SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and has as its object to provide a hiring support device and a hiring support method that can appropriately hire job seekers. [Means for solving the problem]

[0007] One aspect of the disclosure is a recruitment support device that includes a management unit that manages profile information of job seekers and a control unit that generates a scouting document that reflects a word group that includes one or more words extracted from the profile information, wherein the control unit generates a learning model by learning the correlation between a first parameter related to the recruitment of the job seeker and the word group, and extracts the word group based on the generated learning model.

[0008] One aspect of the disclosure is a recruitment support method comprising: step A of managing profile information of job seekers; step B of generating a scouting document that reflects a group of words including one or more words extracted from the profile information; and step C of generating a learning model by learning the correlation between a first parameter related to the recruitment of the job seeker and the group of words, and extracting the group of words based on the generated learning model. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a hiring support device and a hiring support method that can appropriately hire job seekers. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing a recruitment support system 100 according to an embodiment. [Figure 2] FIG. 2 is a diagram showing a recruitment support device 30 according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of profile information according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a scout document according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating a learning method according to the embodiment. [Figure 6] FIG. 6 is a diagram showing a learning method according to the first modification. [Figure 7] FIG. 7 is a diagram showing a recruitment support system 100 according to the second modification. [Figure 8]FIG. 8 is a diagram showing an example of a scout document according to the second modification. [Figure 9] FIG. 9 is a diagram showing a learning method according to the second modification. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments will be described with reference to the drawings. In the following description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.

[0012] However, please note that the drawings are schematic and the ratios of the dimensions may differ from those of the actual product. Therefore, the specific dimensions should be determined by taking into consideration the following explanation. Furthermore, it goes without saying that the dimensional relationships or ratios may differ between the drawings.

[0013] [Disclosure Summary] The recruitment support device according to the disclosed summary includes a management unit that manages profile information of job seekers, and a control unit that generates a scouting document that reflects a word group that includes one or more words extracted from the profile information. The control unit generates a learning model by learning the correlation between a first parameter related to the recruitment of the job seeker and the word group, and extracts the word group based on the generated learning model.

[0014] The recruitment support method according to the disclosed overview includes step A of managing profile information of job seekers, step B of generating a scouting document that reflects a word group including one or more words extracted from the profile information, and step C of generating a learning model by learning the correlation between a first parameter related to the recruitment of the job seeker and the word group, and extracting the word group based on the generated learning model.

[0015] In the summary of the disclosure, the recruitment support device generates a learning model by learning the correlation between a first parameter related to the recruitment of a job seeker and a group of words, and generates a scouting document that reflects the group of words extracted based on the generated learning model. With this configuration, it is possible to extract an appropriate group of words from profile information, and the success rate of recruiting a job seeker using the scouting document can be increased.

[0016] Although not particularly limited, it can be thought that an improvement in the response rate to scouting documents will increase the success rate of hiring job seekers.

[0017] [Embodiment] (Recruitment support system) The following describes a recruitment support system according to an embodiment: Fig. 1 is a diagram showing a recruitment support system 100 according to an embodiment.

[0018] As shown in Fig. 1, the recruitment support system 100 includes a first terminal 10, a second terminal 20, and a recruitment support device 30. The first terminal 10, the second terminal 20, and the recruitment support device 30 are connected by a network 200. Although not particularly limited, the network 200 may be configured by the Internet. The network 200 may include a local area network, a mobile communication network, or a VPN (Virtual Private Network).

[0019] The first terminal 10 is a terminal used by a job seeker. For example, the first terminal 10 may be a personal computer, a smartphone, or a tablet terminal. Although not particularly limited, the job seeker may use the first terminal 10 to input his or her profile information.

[0020] The second terminal 20 is a terminal used by the employer. The second terminal 20 may be a personal computer, a smartphone, or a tablet terminal. Although not particularly limited, the employer may use the second terminal 20 to view the profile information of the job seeker.

[0021] The hiring support device 30 is a device that supports the hiring of human resources. The hiring support device 30 provides a matching service between job seekers and employers. In an embodiment, the hiring support device 30 generates a scouting document for the job seeker. Details of the hiring support device 30 will be described later.

[0022] (Recruitment support device) The following describes a recruitment support device according to an embodiment. Fig. 2 is a diagram showing a recruitment support device 30 according to an embodiment. As shown in Fig. 2, the recruitment support device 30 includes a communication unit 31, a management unit 32, and a control unit 33.

[0023] The communication unit 31 is configured by a communication module. The communication module may be a wireless communication module conforming to a standard such as IEEE802.11a / b / g / n / ac / ax, LTE, 5G, or 6G, or may be a wired communication module conforming to a standard such as IEEE802.3.

[0024] In an embodiment, the communication unit 31 may constitute a transmission unit that transmits a scout document. For example, the communication unit 31 may transmit the scout document to the first terminal 10. The communication unit 31 may transmit the scout document to the second terminal 20 for viewing by the recruit. The scout document may be transmitted to the second terminal 20 before being transmitted to the first terminal 10.

[0025] The communication unit 31 may receive the profile information of the job seeker from the first terminal 10. The communication unit 31 may transmit the profile information of the job seeker to the second terminal 20 for viewing by the employer.

[0026] The management unit 32 is configured by a storage medium such as an SSD (Solid State Drive) or an HDD (Hard Disk Drive), and stores various information.

[0027] In the embodiment, the management unit 32 configures a management unit that manages profile information of job seekers. As described above, the profile information may be input by the job seeker using the first terminal 10.

[0028] Although not particularly limited, the profile information may include the information shown in Fig. 3. As shown in Fig. 3, the profile information may include desired conditions, current industry, current occupation, career history, etc.

[0029] The desired conditions are information regarding the conditions desired by the job seeker. The desired conditions may include the region in which the job seeker wishes to work (e.g., Tokyo, Osaka, nationwide, overseas, etc.). The desired conditions may include the job seeker's desired annual salary (e.g., XX yen or more, XX yen to XX yen, etc.). The desired conditions may include the job seeker's desired industry (e.g., manufacturing, information and communications, finance, service, etc.). The desired conditions may include the job type the job seeker wishes to work in (e.g., sales, clerical work, sales, accounting, legal affairs, etc.). Although not particularly limited, the desired conditions may include items other than those described above. For example, the desired conditions may include the job position the job seeker wishes to work in (e.g., management, department manager, section manager, responsible position, etc.).

[0030] The current industry may be information about the industry of the work that the job seeker is currently engaged in. If the job seeker is currently unemployed, the current industry may be information about the industry of the most recent work that the job seeker is engaged in.

[0031] The current job type may be information about the job type related to the work that the job seeker is currently engaged in. If the job seeker is currently unemployed, the current job type may be information about the job type related to the most recent work that the job seeker is engaged in.

[0032] The career history is information about the job seeker's career. The career history may include information about the job seeker's educational background. The career history may include information about the job seeker's work history. The career history may include information about the job seeker's qualifications. The career history may include information about the job seeker's skills. Although not particularly limited, the career history may include items other than those described above. For example, the career history may include information about the job seeker's selling points (e.g., achievements of work awards, personality, etc.).

[0033] The control unit 33 may include at least one processor. The at least one processor may be configured by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), one or more integrated circuits, one or more discrete circuits, or a combination thereof.

[0034] In an embodiment, the control unit 33 is configured to generate a scouting document that reflects a word group including one or more words extracted from the profile information. Here, the word group may mean a phrase including one or more extracted words, or a sentence including one or more extracted words. The phrase and sentence may be excerpted from the profile information, or may be automatically generated based on the extracted one or more words.

[0035] Although not particularly limited, the scout document may include the information shown in Fig. 4. As shown in Fig. 4, the scout document may include an introduction, points of interest / evaluation, a company introduction, job details, a summary, etc.

[0036] The first part is information about fixed phrases such as greetings, etc. The first part does not necessarily reflect the group of words extracted from the profile information.

[0037] The attention / evaluation points are information about points of interest to the job seeker and points for evaluating the job seeker. The attention / evaluation points may reflect a group of words extracted from profile information. For example, a group of words related to the abilities required of the job seeker may be reflected in the attention / evaluation points. The group of words related to the abilities may include one or more words extracted from the current industry, current job type, and career history. The attention / evaluation points may reflect a group of words related to the achievements required of the job seeker. The group of words related to the achievements may include one or more words extracted from the current industry, current job type, and career history.

[0038] For example, the attention / evaluation points may include a sentence such as, "After reading your resume, I contacted you because I thought you might be skilled not only in YYYY but also in ZZZZ." In such a case, YYYY and ZZZZ may be examples of a group of words extracted from the profile information. Alternatively, the above sentence itself may be automatically generated based on one or more words extracted from the profile information. XXX is the name of the job seeker.

[0039] The company introduction is information about the company. The company introduction may include content related to the company's business and the circumstances surrounding the company's business. Although not particularly limited, the company introduction may be input by the second terminal 20.

[0040] The job description is information about the job to be hired in the scouting document. The job description may include details of the job, the skills expected for the job, and issues related to the job. Although not particularly limited, the company introduction may be input via the second terminal 20.

[0041] The summary may be points of interest / evaluation based on the company introduction and job content. The summary may reflect a group of words extracted from profile information. For example, a group of words related to abilities required of a job seeker based on the company introduction and job content may be reflected in the points of interest / evaluation. The group of words related to abilities may include a group of words extracted from the current industry, current job type, and career history. A group of words related to achievements required of a job seeker based on the company introduction and job content may be reflected in the points of interest / evaluation. The group of words related to achievements may include a group of words extracted from the current industry, current job type, and career history.

[0042] For example, the focus / evaluation points may include a sentence such as, "We are looking to expand our organization in the future, and are looking for someone like Mr. / Ms. XXX who has experience with ZZZZ. We believe this is a phase where Mr. / Ms. XXX's strengths can be fully utilized." In such a case, ZZZZ may be an example of a group of words extracted from the profile information. Alternatively, the above sentence itself may be automatically generated based on one or more words extracted from the profile information. Note that XXX is the name of the job seeker.

[0043] Under these assumptions, in the embodiment, the control unit 33 generates a learning model by learning the correlation between a first parameter related to the hiring of a job seeker and a group of words. That is, the control unit 33 generates the learning model with the aim of improving the extraction accuracy of words (or groups of words) such as the above-mentioned YYYY and ZZZZ.

[0044] Specifically, the control unit 33 acquires scouting documents that have been sent in the past. The scouting documents are documents that reflect a group of words extracted from the profile information. The control unit 33 generates a learning model by learning the correlation between the group of words and the first parameter. When generating a new scouting document, the learning model is a model that inputs a group of words extracted from the profile information and outputs a group of words that had a positive impact on the hiring of the job seeker.

[0045] Here, the first parameter is a parameter corresponding to a scouting document that has been sent in the past, and is a parameter for determining whether the group of words had a positive impact on the hiring of the job seeker. The following parameters can be used as the first parameter:

[0046] First, the first parameter may be a parameter relating to the presence or absence of a reply to the scouting document. Specifically, the control unit 33 generates a learning model by learning the correlation between the word group and the presence or absence of a reply to the scouting document. In other words, the control unit 33 may generate a learning model such that the weighting of the word group included in the scouting document to which the job seeker replied is relatively high, and the weighting of the word group included in the scouting document to which the job seeker did not reply is relatively low. Alternatively, the control unit 33 may use the word group included in the scouting document to which the job seeker replied as the learning parameter, rather than the word group included in the scouting document to which the job seeker did not reply as the learning parameter. The fact that a reply was received to the scouting document means that the word group had a positive impact on the hiring of the job seeker.

[0047] The first parameter may include a parameter related to the time from the transmission of a scouting document to the receipt of a reply to the scouting document (hereinafter, referred to as lead time). Specifically, the control unit 33 generates a learning model by learning the correlation between word groups and lead times. For example, the control unit 33 may generate a learning model such that a word group included in a scouting document that has received a reply with a relatively short lead time is relatively weighted, and a word group included in a scouting document that has received a reply with a relatively long lead time is relatively weighted. Alternatively, the control unit 33 may use a word group included in a scouting document that has received a reply with a lead time shorter than a threshold as a learning parameter, rather than using a word group included in a scouting document that has received a reply with a lead time longer than a threshold as a learning parameter. A shorter lead time may indicate that the word group had a more positive impact on the hiring of the job seeker.

[0048] Second, the first parameter may be a parameter related to whether or not a job seeker is hired. Specifically, the control unit 33 generates a learning model by learning the correlation between the word group and whether or not a job seeker is hired. In other words, the control unit 33 generates a learning model such that the weighting of the word group included in the scouting document used in the case where the job seeker was hired is relatively high, and the weighting of the word group included in the scouting document used in the case where the job seeker was not hired is relatively low. Alternatively, the control unit 33 may use the word group included in the scouting document used in the case where the job seeker was hired as the learning parameter, rather than the word group included in the scouting document used in the case where the job seeker was not hired. The fact that the job seeker was hired means that the word group had a positive impact on the hiring of the job seeker.

[0049] Third, the first parameter may include parameters relating to both whether or not a reply has been made to the scouting document and whether or not the job seeker has been hired.

[0050] When a new scout document is to be sent, the control unit 33 extracts a group of words based on the generated learning model, and generates a scout document that reflects the extracted group of words.

[0051] (Learning method) The learning method according to the embodiment will be described below. It should be noted that the learning is performed before sending a new scout document.

[0052] 5, in step S10, the recruitment support device 30 acquires a group of words. The group of words is a group of words reflected in scouting documents that have been sent in the past, and is a group of words extracted from profile information.

[0053] In step S12, the hiring support device 30 acquires first parameters corresponding to previously sent scouting documents. The first parameters may include a parameter relating to at least one of whether or not a reply to the scouting document has been received and whether or not the job seeker has been hired.

[0054] In step S14, the recruitment support device 30 generates a learning model by learning the correlation between the word group and the first parameter. When generating a new scouting document, the learning model inputs a word group extracted from the profile information and outputs a word group that has had a positive impact on the recruitment of the job seeker.

[0055] (Action and effect) In an embodiment, the recruitment support device 30 generates a learning model by learning the correlation between a first parameter related to the recruitment of a job seeker and a group of words, and generates a scouting document that reflects the group of words extracted based on the generated learning model. This configuration makes it possible to extract appropriate groups of words from profile information, thereby increasing the success rate of recruiting a job seeker using a scouting document.

[0056] [Change Example 1] Modification 1 of the embodiment will be described below, focusing mainly on the differences from the first embodiment.

[0057] In the first modification, the learning model is generated using second parameters related to the attributes of the job seeker. The second parameters include one or more attributes selected from the desired conditions of the job seeker, the current industry of the job seeker, the current occupation of the job seeker, the career history of the job seeker, and the behavior of the job seeker.

[0058] The desired conditions of a job seeker can be identified from profile information. For example, it is possible that a group of words that has a positive effect on a job seeker with a relatively high desired annual salary will be different from a group of words that has a positive effect on a job seeker with a relatively low desired annual salary.

[0059] The current industry of a job seeker can be identified from profile information. For example, it is possible that values ​​differ depending on the current industry, and the set of words that have a positive impact on a job seeker differs depending on the industry.

[0060] The current occupation of a job seeker can be identified from the profile information. For example, it is possible that values ​​differ depending on the current occupation, and the set of words that have a positive impact on a job seeker differs depending on the occupation.

[0061] The job seeker's background can be identified from the profile information. For example, it is possible that a group of words that have a positive impact on a job seeker with managerial experience may differ from a group of words that have a positive impact on a job seeker without managerial experience.

[0062] The behavior of a job seeker includes the status of browsing job postings, the status of applications for job postings, the status of replies to scouting messages, etc. This information may be managed by the management unit 32 of the recruitment support device 30. For example, the behavior of a job seeker can be used as material for determining whether or not the job seeker is currently considering changing jobs. For example, it is conceivable that a group of words that has a positive effect on a job seeker who is currently considering changing jobs will be different from a group of words that has a positive effect on a job seeker who is not currently considering changing jobs.

[0063] Under these assumptions, the recruitment support device 30 generates a learning model using second parameters related to the attributes of job seekers.

[0064] For example, the second parameter may be input to the learning model as a learning parameter. That is, the recruitment support device 30 may generate the learning model by learning the correlation between the word group, the first parameter, and the second parameter.

[0065] Alternatively, the recruitment support device 30 may classify job seekers into two or more categories based on the second parameter. The recruitment support device 30 may generate a learning model for each category.

[0066] (Learning method) The following describes a learning method according to Modification 1. It should be noted that learning is performed before a new scout document is sent.

[0067] 6, in step S20, the recruitment support device 30 acquires a group of words. The group of words is a group of words reflected in previously sent scouting documents and is a group of words extracted from profile information.

[0068] In step S22, the hiring support device 30 acquires first parameters corresponding to previously sent scouting documents. The first parameters may include a parameter relating to at least one of whether a reply to the scouting document has been received and whether the job seeker has been hired.

[0069] In step S24, the recruitment support device 30 acquires a second parameter related to the attributes of the job seeker.

[0070] In step S26, the recruitment support device 30 generates a learning model by learning the correlation between the word group and the first parameter. In the first modification, the recruitment support device 30 generates a learning model using the second parameter.

[0071] (Action and effect) In Modification 1, the hiring support device 30 generates a learning model using second parameters related to the attributes of the job seeker. This configuration makes it possible to appropriately generate a learning model even in cases where the group of words that have a positive impact on the job seeker differs depending on the job seeker's attributes. This in turn makes it possible to extract appropriate group of words from the profile information, thereby increasing the success rate of hiring a job seeker using a scouting document.

[0072] [Change Example 2] The second modification of the embodiment will be described below, focusing mainly on the differences from the first embodiment.

[0073] In Modification Example 2, as shown in FIG. 7, a case where a third party 40 is involved is considered. For example, the third party 40 may be a headhunter. The third party 40 may have the authority to use at least some of the functions of the recruitment support device 30. In Modification Example 2, a case is assumed in which a job seeker receives a scouting document from the third party 40.

[0074] In the second modification, the learning model is generated using third-party information about the third party 40. The third-party information includes one or more attributes selected from the industry of the job openings handled by the third party 40, the job type of the job openings handled by the third party 40, and the job opening documents handled by the third party 40.

[0075] The industry of the job vacancies handled by the third party 40 may be managed by the management unit 32 of the recruitment support device 30, or may be identified from the job vacancy documents handled by the third party 40. The industry of the job vacancies handled by the third party 40 may be used to generate a learning model in the same way as the second parameter described above. That is, the industry of the job vacancies handled by the third party 40 may be used as a learning parameter of the learning model, or may be used to identify a category corresponding to the learning model.

[0076] The job types of the job postings handled by the third party 40 may be managed by the management unit 32 of the recruitment support device 30, or may be identified from the job posting documents handled by the third party 40. The job types of the job postings handled by the third party 40 may be used to generate a learning model in the same way as the second parameter described above. That is, the industry of the job postings handled by the third party 40 may be used as a learning parameter of the learning model, or may be used to identify a category corresponding to the learning model.

[0077] The job offer documents handled by the third party 40 may include documents sent by the third party 40 to job seekers. For example, the job offer documents handled by the third party 40 are documents used in headhunting. The job offer documents handled by the third party 40 may be used to generate a learning model in the same way as the scouting documents described in the embodiment. That is, a group of words to be used as learning parameters for the learning model may be extracted from the job offer documents handled by the third party 40. Furthermore, first parameters (whether or not a reply to the document is received and whether or not the job seeker is hired) corresponding to the job offer documents handled by the third party 40 may be managed by the management unit 32.

[0078] Although not particularly limited, the scout document of third party 40 may include the information shown in Fig. 8. As shown in Fig. 8, the scout document may include an introduction, points of interest / evaluation, a self-introduction, job details, a summary, etc. In other words, the scout document of third party 40 includes a self-introduction instead of the company introduction and job details of the scout document shown in Fig. 4.

[0079] The self-introduction is information related to the introduction of third party 40. The self-introduction may be input by third party 40. The self-introduction may include information related to the job opening that third party 40 is currently in charge of, may include information related to the past achievements of third party 40, and may include the area of ​​expertise of third party 40 (industry, occupation, etc.).

[0080] Under such a premise, the recruitment support device 30 generates a learning model using third-party information about the third party 40.

[0081] For example, the industries of the job openings handled by the third party 40, the job types of the job openings handled by the third party 40, and the job documents handled by the third party 40 may be used as learning parameters of the learning model. The industries of the job openings handled by the third party 40 and the job types of the job openings handled by the third party 40 may be used to identify categories corresponding to the learning model.

[0082] (Learning method) The following describes a learning method according to Modification 2. It should be noted that learning is performed before a new scout document is sent.

[0083] 9, in step S30, the recruitment support device 30 acquires a group of words. The group of words is a group of words reflected in scouting documents that have been sent in the past, and is a group of words extracted from profile information.

[0084] In step S32, the hiring support device 30 acquires first parameters corresponding to previously sent scouting documents. The first parameters may include a parameter relating to at least one of whether a reply to the scouting document has been received and whether the job seeker has been hired.

[0085] In step S34, the recruitment support device 30 acquires third party information related to the third party 40.

[0086] In step S36, the recruitment support device 30 generates a learning model by learning the correlation between the word group and the first parameter. In the second modification, the recruitment support device 30 generates a learning model using third-party information.

[0087] (Action and effect) In Modification 2, the recruitment support device 30 generates a learning model using third-party information about a third party 40. This configuration allows the population of information used to generate the learning model to be expanded, enabling the learning model to be generated appropriately. This in turn makes it possible to extract appropriate word groups from profile information, thereby increasing the success rate of recruiting job seekers using scout documents.

[0088] [Other embodiments] Although the present invention has been described by the above-mentioned embodiments, the descriptions and drawings that form part of this disclosure should not be understood to limit the present invention. From this disclosure, various alternative embodiments, examples, and operating techniques will become apparent to those skilled in the art.

[0089] Although not specifically mentioned in the above disclosure, Modification Example 1 and Modification Example 2 may be combined. That is, the recruitment support device 30 may generate a learning model using the second parameter and third-party information.

[0090] Although not specifically mentioned in the above disclosure, the learning may be machine learning or deep learning represented by AI (Artificial Intelligence).

[0091] Although not specifically mentioned in the above disclosure, the recruitment support device 30 may automatically generate a scouting document itself after extracting one or more groups of words extracted from the profile information based on a learning model. The scouting document may be generated by an existing writing tool. The writing tool may be a tool using AI.

[0092] In the above disclosure, the management unit 32 is provided in the hiring support device 30. However, the above disclosure is not limited to this. The management unit 32 may be included in the same external server as the hiring support device 30, as a separate entity, or may be included in a separate external server that can communicate with the hiring support device 30.

[0093] The above disclosure has mainly described a case in which the recruitment support device 30 transmits scout documents. However, the above disclosure is not limited to this. For example, the recruitment support device 30 may provide only the function of managing (storing) scout documents. In such a case, the recruitment support device 30 may generate a learning model and extract a word group using the learning model. This configuration can help improve the success rate of hiring job seekers using scout documents by providing a word group to be included in the scout document.

[0094] Although not specifically mentioned in the above disclosure, a program may be provided that causes a computer to execute each process performed by the recruitment support device 30. The program may also be recorded on a computer-readable medium. Using the computer-readable medium, the program can be installed on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a recording medium such as a CD-ROM or a DVD-ROM.

[0095] Alternatively, a chip may be provided that is configured by a memory that stores programs for executing the processes performed by the recruitment support device 30 and a processor that executes the programs stored in the memory. [Explanation of symbols]

[0096] 10...first terminal, 20...second terminal, 30...recruitment support device, 31...communication unit, 32...management unit, 33...control unit, 40...third party, 100...recruitment support system, 200...network

Claims

1. an administration department for managing profile information of job seekers; A control unit that generates a scout document using a learning model that extracts a word group including one or more words included in the profile information, A recruitment support device, wherein the scout document includes at least one of points focusing on the job seeker including a group of words extracted by the learning model or points for evaluating the job seeker including a group of words extracted by the learning model.

2. Step A of managing profile information of job seekers; and a step B of generating a scout document using a learning model that extracts a word group including one or more words included in the profile information, A recruitment support method, wherein the scout document includes at least one of points focusing on the job seeker including a group of words extracted by the learning model or points for evaluating the job seeker including a group of words extracted by the learning model.

Images