JP7701586B2 - Recruitment support device, recruitment support system, and recruitment support method - Google Patents

Description

This disclosure relates to a recruitment support device, a recruitment support system, and a recruitment support method.

In recent years, many recruitment platforms have been operating via the Internet. These recruitment platforms include services for so-called new graduate recruitment, targeted at students, and services for so-called job-change recruitment, targeted at mid-career hires such as working adults. Companies looking to hire provide job information to these recruitment platforms. Job seekers use these services to obtain job information.

For example, Patent Document 1 describes technology related to a recruitment service that provides job seekers with appropriate job search information based on information provided by both the job seeker and the employer.

JP 2013-246453 A

However, employers are required to interview as many candidates as possible in small groups and select candidates accordingly, so it is difficult to carry out efficient recruitment activities simply by matching appropriate job information.

Therefore, this disclosure has been made in consideration of the above problems, and its purpose is to support employers in their efficient recruitment activities.

According to the present disclosure, there is provided a recruiting support device that supports recruiters' recruiting activities, characterized in that the recruiting support device includes a key phrase selection unit that selects key phrases expressing characteristics of a job seeker from text information included in job seeker information related to the job seeker, and a message proposal generation unit that generates message proposals addressed to the job seeker based on the key phrases and presents the message proposals to the recruiter.

This disclosure allows employers to conduct efficient recruitment activities.

1 is a diagram illustrating an example of the overall configuration of a recruitment support system according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer that realizes the server device 1 according to the embodiment. FIG. 2 is a diagram illustrating an example of a software configuration of the server device 1 according to the embodiment. 11 is a diagram showing an example of the configuration of information stored in a recruiter information storage unit 131 according to the embodiment. FIG. 11 is a diagram showing an example of the configuration of information stored in a job seeker information storage unit 132 according to the embodiment. FIG. FIG. 4 is a flowchart illustrating a series of controls in the server device 1 according to the embodiment.

The contents of the embodiment of the present invention will be listed and described below. One embodiment of the present invention has the following configuration.
[Item 1]
A recruitment support device that supports recruiters' recruitment activities,
a key phrase selection unit that selects a key phrase that represents a characteristic of the job seeker from text information included in job seeker information related to the job seeker;
a message proposal generating unit that generates a message proposal for the job seeker based on the key phrase and presents the message proposal to the employer;
A recruitment support device comprising:
[Item 2]
The message proposal generator acquires edits input by the recruiter;
The recruitment support device according to claim 1 .
[Item 3]
an analysis unit that assigns a correct answer tag to the proposed message when the job seeker and the employer are successfully matched based on the proposed message;
a model generation unit that uses the proposed message assigned with the correct tag, the job seeker information, and recruiter information related to the recruiter as training data, and generates a message generation model by a statistical method, in which the job seeker information and the recruiter information are used as inputs and the proposed message is used as an output;
The recruitment support device according to claim 1 or 2, further comprising:
[Item 4]
the key phrase selection unit selects the key phrase representing a characteristic of the recruiting party from the recruiting party information related to the recruiting party;
a recommendation unit that compares the key phrases related to the job seeker and the job recruiter and presents the job seeker having a high degree of match or relevance to the job recruiter;
The recruitment support device according to claim 1 , further comprising:
[Item 5]
the message draft generator presents a sentence including the key phrase among text information to a party sending a message in a manner different from other text;
5. The recruitment support device according to claim 1,
[Item 6]
A recruitment support system that supports recruitment activities of recruiters,
a key phrase selection function that selects a key phrase that represents a characteristic of the job seeker from text information included in the job seeker information related to the job seeker;
a message draft generation function for generating a message draft addressed to the job seeker based on the key phrase and presenting the message draft to the employer;
A recruitment support system comprising:
[Item 7]
A recruitment support method for supporting recruitment activities of a recruiter, comprising:
a key phrase selection step of selecting a key phrase representing a characteristic of the job seeker from text information included in the job seeker information related to the job seeker;
a message draft generation step of generating a message draft addressed to the job seeker based on the key phrase and presenting the message draft to the employer;
A recruitment support method comprising:

A preferred embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components having substantially the same functional configuration are designated by the same reference numerals to avoid redundant description.

The server device 1 of this embodiment generates messages for smooth communication between job seekers and employers. The messages are not limited to those sent at the time of first contact, but may also include messages sent to arrange interview dates and to inform the job seeker of the possibility of being hired or employed.

==Overview==
Fig. 1 is a diagram showing the overall configuration of a server device 1 (recruitment support device). As shown in Fig. 1, the recruitment support system includes the server device 1, a recruiter terminal 3, and a job seeker terminal 4. The server device 1 is connected to the recruiter terminal 3 and the job seeker terminal 4 via a network 2. Although only one recruiter terminal 3 and one job seeker terminal 4 are shown, it goes without saying that there may be more than one. Furthermore, the specific devices of the recruiter terminal 3 and the job seeker terminal 4 are not limited to mobile terminals and personal computers, and may be, for example, a smartphone, a tablet computer, a wearable terminal, or other electronic devices.

==Recruiter Terminal 3==
The recruiter terminal 3 is a computer operated by a person in charge (recruiter) of an organization such as a company that desires to hire. The recruiter terminal 3 is, for example, a smartphone, a tablet computer, a personal computer, etc. The recruiter can access the server device 1 by, for example, an application or a web browser executed on the recruiter terminal 3.

==Job Seeker Terminal 4==
The job seeker terminal 4 is a computer operated by a human resource (job seeker) who wishes to work. The employer terminal 3 is, for example, a smartphone, a tablet computer, a personal computer, etc. The job seeker can access the server device 1 by, for example, an application or a web browser executed on the job seeker terminal 4.

The configuration of the server device 1 is described below.

2 is a diagram showing an example of the hardware configuration of the server device 1 of this embodiment. The server device 1 includes a processor 101, a memory 102, a storage device 103, a communication interface 104, an input device 105, and an output device 106. The processor 101 is a computing device that controls the operation of the entire server device 1, controls the transmission and reception of data between each element, and performs information processing necessary for application execution and authentication processing. For example, the processor 101 is a processor such as a CPU (Central Processing Unit), and executes each information processing by executing a program stored in the storage device 103 and deployed in the memory 102. The memory 102 includes a main memory configured with a volatile storage device such as a DRAM (Dynamic Random Access Memory), and an auxiliary memory configured with a non-volatile storage device such as a flash memory or a HDD (Hard Disc Drive). The memory 102 is used as a work area for the processor 101, and stores the BIOS (Basic Input/Output System) executed when the server device 1 is started, and various setting information. The storage device 103 stores various data and programs, and is, for example, a hard disk drive, a solid state drive, or a flash memory. The communication interface 104 is an interface for connecting to the network 2, and is, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone line network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc. The input device 105 is a device that accepts data input through, for example, a keyboard, a mouse, a touch panel, a button, a microphone, etc. The output device 106 is equipped with, for example, a display, a printer, a speaker, etc., for outputting data.

FIG. 3 is a block diagram showing the functional configuration of the server device 1. As shown in FIG. 3, the server device 1 includes functional units, namely, an employer information acquisition unit 111, a job seeker information acquisition unit 112, a key phrase selection unit 113, a recommendation unit 114, a message proposal generation unit 115, a message transmission/reception unit 116, an analysis unit 117, and a model generation unit 118, as well as an employer information storage unit 131, a job seeker information storage unit 132, a message information storage unit 133, and a template information storage unit 134.

The above-mentioned functional units are realized by the processor 101 of the server device 1 reading out a program stored in the storage device 103 into the memory 102 and executing it, and the above-mentioned storage units are realized as part of the storage area provided by the memory 102 and storage device 103 of the server device 1.

Here, in this embodiment, the data configuration of each storage unit, the employer information storage unit 131, the job seeker information storage unit 132, the message information storage unit 133, and the template information storage unit 134, is shown.

The recruiter information storage unit 131 stores the recruiter information received by the recruiter information acquisition unit 111, an example of which is shown in FIG. 4. As shown in FIG. 4, the recruiter information includes, but is not limited to, basic information such as the company name and date of establishment, recruitment information related to recruitment such as application requirements including the application industry and conditions, and selection information including the job seeker who sent the message. The basic information includes, for example, information such as the company name, representative name, date of establishment, history, address, contact information, and business details linked to the recruiter ID. The recruitment information includes, for example, information such as the job type, number of applicants, application requirements, desired skills and mindset, and messages from the recruiter. The selection information includes information such as the job seeker who sent the message, the job seeker who received a job offer, and the job seeker who was hired. Note that, as text processing information, information such as words, keywords, and key phrases processed and selected by the key phrase selection unit 113 is also stored.

The job seeker information storage unit 132 stores the job seeker information received by the job seeker information acquisition unit 112, an example of which is shown in FIG. 5. As shown in FIG. 5, the job seeker information includes, but is not limited to, personal information consisting of basic information such as the job seeker's name, employment information such as work history to date, selection results, and desired job type, and selection information such as the employer who received the message. The personal information, for example, is linked to the job seeker ID and consists of information such as name, age, address, contact information, academic history (including but not limited to university/graduate school name, faculty, department, research department, laboratory name, etc.), self-introduction (including but not limited to text, audio, video, etc.), research content, programming skills, papers/academic conference presentation record, and awards. The selection information is also composed of information such as current status (seeking a job, currently employed, etc.), work history (including but not limited to company name, business department, section, division, group, etc.), desired job type, and desired conditions. The selection information is composed of information such as a selection history (which employers received the message, which employers offered the employee a job offer, whether the employee joined the company or declined, and which companies rejected the employee). In addition, the text processing information also includes information on words, keywords, key phrases, etc. that are processed and selected by the key phrase selection unit 113.

The message information storage unit 133 stores the message information sent or received by the message sending/receiving unit 116. Furthermore, the message information storage unit 133 stores the message that the analysis unit 117 determines to be effective by assigning a correct answer label to the message.

The template information storage unit 134 stores a template that the message proposal generation unit 115 uses when generating a message. The template includes, but is not limited to, a section for inserting a key phrase selected by the key phrase selection unit 113 and a section for affirming the key phrase or asking a question about the key phrase.

This concludes the explanation of the data configuration of server device 1.

Here, in this embodiment, the functions of each of the functional units, namely, the employer information acquisition unit 111, the job seeker information acquisition unit 112, the key phrase selection unit 113, the recommendation unit 114, the message proposal generation unit 115, the message transmission/reception unit 116, the analysis unit 117, and the model generation unit 118, are described.

The employer information acquisition unit 111 acquires information about employers from the employer terminal 3 via the network 2. The communication in the transmission and reception may be either wired or wireless, and any communication protocol may be used as long as the communication between the two is possible. The employer information may be collected by a business using the server device 1 through interviews or questionnaires with the employer, and the information may be input from a terminal used by the business via the network 2, or may be input directly to the server device 1. When the employer information acquisition unit 111 acquires an electronic file containing voice, it may convert the voice into text using voice recognition technology. The voice recognition technology used in this case may be implemented in a commonly used manner, and a detailed explanation will be omitted here. Therefore, the information acquired by the employer information acquisition unit 111 can be treated as text information.

The job seeker information acquisition unit 112 acquires information about job seekers from the job seeker terminal 4 via the network 2. The communication in the transmission and reception may be either wired or wireless, and any communication protocol may be used as long as the communication between the two is possible. The job seeker information may be collected by a business using the server device 1 through interviews or questionnaires with the job seekers, and the information may be input from a terminal used by the business via the network 2, or may be input directly to the server device 1. When the job seeker information acquisition unit 112 acquires an electronic file containing voice, it may convert the voice into text using voice recognition technology. The voice recognition technology used in this case may be implemented in a commonly used manner, and a detailed description will be omitted here. Therefore, the information acquired by the job seeker information acquisition unit 112 can be treated as text information.

The key phrase selection unit 113 selects characteristic key phrases that represent the characteristics and priorities of employers and job seekers from the text information stored in the employer information storage unit and the job seeker information storage unit, and stores them in each storage unit.

The key phrase selection unit 113 can select key phrases using a method such as text analysis as described below. However, the method is not limited to the method described below, and key phrases may be selected by using any text analysis method as appropriate.

First, the key phrase selection unit 113 reads out text information stored, for example, in the employer information storage unit 131 and the job seeker information storage unit 132, and extracts phrases that are candidates for key phrases from the text information. For example, the key phrase selection unit 113 writes a specific pattern based on parts of speech, such as "adjective + noun," as a rule, and adopts and extracts phrases that match this as candidates (hereinafter, candidate phrases).

Next, the key phrase selection unit 113 calculates sentence embedding for the candidate phrases and the text information, and calculates an embedding vector. Since sentence embedding only requires that a vector with some fixed dimension is output from the input sentence, it may be performed using, for example, doc2vec, sent2vec, infersent, or other similar methods.

Next, the key phrase selection unit 113 extracts the embedding vectors of the candidate phrases that are close to the vector of the text information based on the similarity, and determines the key phrases. After that, the key phrase selection unit 113 obtains the top five of these (the number of phrases obtained can be changed) and sets them as key phrases for the text information.

Note that, since similar key phrases may be obtained in duplicate when extracted using the above-mentioned method, the key phrase selection unit 113 may compare the embedding vectors of key phrases with each other in order to provide diversity. In this case, the key phrase selection unit 113 may select as a key phrase a key phrase whose embedding vector has a high similarity to the vector of the text information, and whose embedding vector is far away from the key phrase and has a low similarity.

Furthermore, the key phrase selection unit 113 may select and rank the key phrases for each topic category. The key phrase selection unit 113 may refer to a database of frequently occurring keywords and key phrases included in pre-set categories, such as student life, research content, and extracurricular activities, and may allocate the selected key phrases to each category, and then rank them for each category. Furthermore, if a certain number of key phrases have not been selected for each pre-set category, the key phrase selection unit 113 may move up a key phrase that was ranked lower and select it as the key phrase for that category.

Furthermore, the key phrase selection unit 113 may divide the text information into words by morphological analysis, score the importance of the words based on the frequency of appearance, etc., and select the words with the highest importance as keywords. In this way, the key phrase selection unit 113 generates and selects text processing information (the key phrases, the words, the keywords) based on the text information. The key phrase selection unit 113 may determine that the key phrases or keywords are points that employers consider important when hiring (employer points) and points that job seekers consider important when selecting a place of employment (job seeker points).

The recommendation unit 114 selects suitable job seeker candidates for the employer and suitable job seeker candidates for the job seeker based on the employment wishes of the employer and the employment wishes of the job seeker, and presents them to the other party.

For example, the recommendation unit 114 compares the text information or text processing information included in the employer information with the text information or text processing information included in the job seeker information. As a result of the comparison, the recommendation unit 114 determines the degree of relevance between the text information or text processing information on the job seeker's side and the text information or text processing information on the employer's side, in addition to the degree of match between them. The degree of relevance is the degree of relevance between the text information or text processing information on the job seeker's side and the text information or text processing information on the employer's side, and represents the degree to which the job seeker is desired by the employer, or the degree to which the job seeker is desired by the employer. The degree of relevance may be calculated by cluster analysis or by comparing embedded vectors in the same manner as the key phrase selection unit 113.

The recommendation unit 114 determines that the degree of match is high when the other party contains text information that matches text information such as the skills and qualifications that the employer requires from the job seeker, for example, when the job seeker information contains text information that matches text information such as the employment conditions that the job seeker requires from the employer, such as specific employee benefits, or when the other party contains text information that matches text information such as the conditions that the job seeker requires from the employer. In addition, the recommendation unit 114 may determine that the degree of match is higher depending on the number of items with a degree of match higher than a predetermined standard.

In addition, for example, when an employer specifies a specific specialty as a skill required of a job seeker, the recommendation unit 114 determines that the relevance is high when the job seeker information contains text information related to the text information of the conditions required of the other party, such as whether or not text information related to the specialty is included in the job seeker information or the degree to which it is included. Furthermore, the recommendation unit 114 may determine that the relevance is even higher when there are many types of related text information or when a large amount of the information is included.

Furthermore, the recommendation unit 114 may determine the degree of match or relevance by comparing the employer points with the job seeker points.

Furthermore, the recommendation unit 114 may present to the other party employers and job seekers that are determined to have a high degree of match or relevance as described above. As a method of presenting to the other party, for example, the employers and job seekers may be presented in order of the degree of match or relevance, or the degree of match or relevance may be expressed as a numerical value or as a level within a scale.

The message proposal generation unit 115 generates a message to be sent to the other party, presents it to the sending party, and obtains edits from that party.

The message draft generation unit 115 calls up a template from the template information storage unit 134 that includes the key phrase selected by the key phrase selection unit 113 and has a context that shows interest in the other person, such as an affirmation of the key phrase or a question about the key phrase, and generates a message. For example, if the job seeker information includes text information such as "I have been doing research since joining a research lab at graduate school, and in some years I have given three academic presentations a year," and the key phrase selection unit 113 selects "three academic presentations a year" as a key phrase, the message draft generation unit 115 applies the template "(key phrase) is a great achievement," from the template information storage unit 134, and generates a message such as "Three academic presentations a year is a great achievement." Note that when applying a key phrase to a template, the message draft generation unit 115 may not only apply the key phrase to the template, but may also change the conjunctions and other words included in the key phrase and template so that they are correct Japanese.

If the message proposal generation unit 115 generates a message proposal intended for a job seeker, it presents the message proposal to the employer; if the message proposal generation unit 115 generates a message proposal intended for a job seeker, it presents the message proposal to the job seeker. The message proposal presented by the message proposal generation unit 115 is presented so that it can be edited by the party sending the message, and edits made to the message proposal by that party are obtained.

The message proposal generating unit 115 may select a sentence including a key phrase selected by the key phrase selecting unit 113 and present the sentence to the employer or job seeker. The method of presentation may be a method of presenting only the sentence, or a method of presenting the sentence in a different form from the other text, such as highlighting the sentence. The method of presentation may also be a method of presenting the entire text with the relevant sentence in a different form from the other text. The message proposal generating unit 115 may present the sentence and then present a message creation form to the employer or job seeker. In this case, the message proposal generating unit 115 may also present information to guide message creation, such as commenting on student life, commenting on research content, or commenting on previous jobs.

Furthermore, the message proposal generation unit 115 may generate a message based on a message generation model generated by the model generation unit 118 described below.

The message sending/receiving unit 116 provides a function that enables messages to be sent and received between the employer terminal 3 and the job seeker terminal 4. The message sending/receiving unit 116 obtains the sending intention of the party by clicking or tapping the send button, etc., of the message obtained by obtaining the editing of the message proposal generated by the message proposal generation unit 115 by the sending party, and transmits the message to the other party. Note that the generated message proposal may be sent as is as a message. The message sending/receiving unit 116 also receives the sent message. Note that the message sending/receiving unit 116 is an example of a message sending unit.

The message sending/receiving unit 116 stores, for example, the sent message, the message proposal generated by the message proposal generating unit 115, and the accepted edit content in the message information storage unit 133, identifying the sender and recipient.

The analysis unit 117 analyzes the message proposals generated by the message proposal generation unit 115, the accepted edits, and the messages sent and received by the message transmission/reception unit 116.

For example, the analysis unit 117 determines that the generated message was effective when the amount of editing of the message obtained from the sending party based on the message proposal generated by the message proposal generation unit 115 is small. The analysis unit 117 may also determine that the sent message was effective when a reply was made after the message was received. Furthermore, the analysis unit 117 may obtain information that an interview was held or that the candidate was hired after the message was sent, and determine that the message was effective. In this case, the analysis unit 117 stores the message determined to be effective in the message information storage unit 133 with a correct answer label attached.

The model generation unit 118 generates a message generation model that generates an effective message for the other party. For example, based on the recruiter information, the job seeker information, and the message information, the model generation unit 118 generates a message generation model that generates an effective message for a group of job seekers with similar educational backgrounds, desired job types, or experiences (such as types of part-time work or research content) and/or a group of recruiters with similar business philosophies, applied job types, and desired mindsets, using a statistical method. The method for generating the message generation model used by the model generation unit 118 may include classification, regression, correlation analysis, feature importance calculation, clustering, etc., and these statistical models may be implemented in a manner generally used in statistics, so detailed explanations are omitted here. The input data for the message generation model generated by these methods is, for example, the text information, the key phrases, the keywords, and the message information, and the message information to which the analysis unit 117 has assigned a correct answer label may be the correct answer information.

A typical process flow of this embodiment will be described with reference to FIG. 8. First, the employer information acquisition unit 111 acquires employer information (1001). Next, the job seeker information acquisition unit 112 acquires job seeker information (1002). The key phrase selection unit 113 performs language processing on the text information contained in the employer information and the job seeker information to select a key phrase (1003). The message proposal generation unit 115 applies the key phrase to a template called up from the template information storage unit 134 to generate a message (1004). At this time, the message proposal generation unit 115 may obtain an edit of the generated message from the party sending the message. The message transmission/reception unit 116 receives instructions from the party and transmits the message to the other party (1005), and stores the message information in the message information storage unit 133. The analysis unit analyzes the interaction between the two parties after the message transmission and the relationship with the recruitment, and analyzes the effective message (1006). The model generation unit 118 generates a message generation model for generating messages using the effective messages as correct answer data (1007).

Although the preferred embodiments of the present disclosure have been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to the examples. It is clear that a person with ordinary knowledge in the technical field of the present disclosure can conceive of various modified or revised examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

The device described in this specification may be realized as a single device, or may be realized by multiple devices (e.g., cloud servers) some or all of which are connected via a network. For example, the processor 101 and the storage device 103 of the server device 1 may be realized by different servers connected to each other via a network.

The series of processes performed by the device described in this specification may be realized using software, hardware, or a combination of software and hardware. A computer program for realizing each function of the server device 1 according to this embodiment may be created and installed in a PC or the like. A computer-readable recording medium on which such a computer program is stored may also be provided. Examples of the recording medium include a magnetic disk, an optical disk, a magneto-optical disk, and a flash memory. The computer program may also be distributed, for example, via a network, without using a recording medium.

In addition, the processes described in this specification using flowchart diagrams do not necessarily have to be performed in the order shown. Some processing steps may be performed in parallel. In addition, additional processing steps may be employed, and some processing steps may be omitted.

Furthermore, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology disclosed herein may achieve other effects that are apparent to a person skilled in the art from the description in this specification, in addition to or in place of the above effects.

REFERENCE SIGNS LIST 1 Server device 2 Network 3 Recruiter terminal 4 Job seeker terminal 101 Processor 102 Memory 103 Storage device 104 Communication interface 105 Input device 106 Output device 111 Recruiter information acquisition unit 112 Job seeker information acquisition unit 113 Key phrase selection unit 114 Recommendation generation unit 115 Message proposal generation unit 116 Message transmission/reception unit 117 Analysis unit 118 Model generation unit 131 Recruiter information storage unit 132 Job seeker information storage unit 133 Message information storage unit 134 Template information storage unit

Claims (6)

A recruitment support device that supports recruiters' recruitment activities,
a key phrase selection unit that selects a key phrase that represents a characteristic of the job seeker from text information included in job seeker information related to the job seeker;
a message proposal generating unit that generates a message proposal for the job seeker based on the key phrase and presents the message proposal to the employer;
an analysis unit that assigns a correct answer tag to the proposed message when the job seeker and the employer are successfully matched based on the proposed message;
a model generation unit that uses the proposed message assigned with the correct tag, the job seeker information, and recruiter information related to the recruiter as training data, and generates a message generation model by a statistical method, in which the job seeker information and the recruiter information are used as inputs and the proposed message is used as an output;
A recruitment support device comprising: The message proposal generator acquires edits input by the recruiter;
The recruitment support device according to claim 1 . the key phrase selection unit selects the key phrase representing a characteristic of the recruiting party from the recruiting party information related to the recruiting party;
a recommendation unit that compares the key phrases related to the job seeker and the job recruiter and presents the job seeker having a high degree of match or relevance to the job recruiter;
The recruitment support device according to claim 1 or 2 , further comprising: the message draft generator presents a sentence including the key phrase among text information to a party sending a message in a manner different from other text;
4. The recruitment support device according to claim 1, A recruitment support program that supports recruiters' recruitment activities,
The processor:
a key phrase selection step of selecting a key phrase representing a characteristic of the job seeker from text information included in job seeker information related to the job seeker;
a message draft generation step of generating a message draft addressed to the job seeker based on the key phrase and presenting the message draft to the employer;
an analysis step of assigning a correct answer tag to the message proposal when the job seeker and the employer are successfully matched based on the message proposal;
a model generation step of using the message draft to which the correct tag has been assigned, the job seeker information, and job seeker information related to the job seeker as training data, and generating a message generation model by a statistical method, the message generation model having the job seeker information and the job seeker information as inputs and the message draft as an output;
This is a recruitment support program that helps implement these measures. A recruitment support method for supporting recruitment activities of a recruiter, comprising:
The processor:
a key phrase selection step of selecting a key phrase representing a characteristic of the job seeker from text information included in job seeker information related to the job seeker;
a message draft generation step of generating a message draft addressed to the job seeker based on the key phrase and presenting the message draft to the employer;
an analysis step of assigning a correct answer tag to the message proposal when the job seeker and the employer are successfully matched based on the message proposal;
a model generation step of using the message draft to which the correct tag has been assigned, the job seeker information, and job seeker information related to the job seeker as training data, and generating a message generation model by a statistical method, the message generation model having the job seeker information and the job seeker information as inputs and the message draft as an output;
A recruitment support method that implements the above.

Images