Recruitment support system, recruitment support method and program

Abstract

To provide a recruitment support system, etc., capable of efficiently creating a scout document matching content of a job posting.SOLUTION: There is provided a recruitment support system. The recruitment support system includes a processor. The processor is configured to execute the following steps: an acquisition step of acquiring a job posting; and a scout document creation step of inputting the job posting to a first processing model, the learning model, causing the first processing model to output a plurality of document components respectively corresponding to a plurality of items included in the job posting, further inputting the plurality of document components to a second processing model, the learning model, and causing the second processing model to output a first scout document corresponding to the job posting.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a recruitment support system, a recruitment support method, and a program.

Background Art

[0002] As disclosed in Patent Document 1, there is known a technique for automatically selecting a scout document from a template according to the response of a job seeker (recruitment candidate).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The scout document preferably has content that conforms to each job offer.

[0005] In view of the above circumstances, the present invention aims to provide a recruitment support system and the like that can efficiently create a scout document that conforms to the content of a job offer.

Means for Solving the Problems

[0006] According to one aspect of the present invention, a recruitment support system is provided. This recruitment support system includes a processor. The processor is configured to execute the following steps. In the acquisition step, a job offer is acquired. In the scout document creation step, the job offer is input into a first processing model that is a learning model, and the first processing model is caused to output a plurality of document components respectively corresponding to a plurality of items included in the job offer. The plurality of document components are further input into a second processing model that is a learning model, and the second processing model is caused to output a first scout document corresponding to the job offer.

[0007] According to such an aspect, a scout document including document components corresponding to the items of the job offer form can be created. Further, by sequentially performing the step of generating document components for each item and the step of generating a scout document using the document components, a scout document that appropriately reflects the content of the job offer form can be efficiently created.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic matters shown in the following embodiments can be combined with each other.

[0010] By the way, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable medium that can be read by a computer, may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its function is realized on a client terminal (so-called cloud computing).

[0011] In addition, in this embodiment, the “section” may include, for example, a combination of hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in this embodiment, various types of information are handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0012] In addition, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, etc. That is, it includes an application specific integrated circuit (ASIC), programmable logic devices (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0013] 1. Hardware Configuration In this section, the hardware configuration will be described.

[0014] <Employment Support System 1> FIG. 1 is a configuration diagram showing Employment Support System 1. Employment Support System 1 includes a communication line 2, a server device 10, a plurality of applicant terminals 20, and a plurality of job seeker terminals 30. The server device 10, the applicant terminals 20, and the job seeker terminals 30 are configured to be communicable through the communication line 2. The connections of the server device 10, the applicant terminals 20, and the job seeker terminals 30 may be wired or wireless.

[0015] Employment Support System 1 constitutes a part of a recruitment and job seeking system used by a plurality of applicants (First Applicant U1 and Second Applicant U2) and a plurality of job seekers (First Job Seeker U3 and Third Job Seeker U4). Employment Support System 1 mainly creates and transmits scout documents based on recruitment forms. In one embodiment, Employment Support System 1 consists of one or more devices or components. Hereinafter, these components will be described.

[0016] <Server Device 10> FIG. 2 is a block diagram showing the hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected via the communication bus 14 inside the server device 10.

[0017] <Control Unit 11> The control unit 11 performs processing and control of the overall operations related to the server device 10. The control unit 11 is, for example, a Central Processing Unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading a predetermined program stored in the storage unit 12. That is, the information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and may be implemented to have a plurality of control units 11 for each function, or a combination thereof may also be possible.

[0018] <Storage Unit 12> The storage unit 12 stores various information defined by the foregoing description. This can be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the calculation of the program. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11. Also, the storage unit 12 may be an external storage device connected to the server device 10.

[0019] <Communication Unit 13> Although the communication unit 13 preferably uses wired communication means such as USB, IEEE 1394, Thunderbolt (registered trademark), and wired LAN network communication, it may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, and BLUETOOTH (registered trademark) communication as required. That is, it is more preferably implemented as a set of these multiple communication means. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0020] The server device 10 may be in an on-premises form or a cloud form. As a cloud-form server device 10, for example, it may provide the above-described functions and processes in the form of SaaS (Software as a Service) or cloud computing. Further, the server device 10 may be a multi-computer including a plurality of computers, or may be a virtual machine virtually constructed by software.

[0021] <Recruiter Terminal 20> FIG. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. As shown in FIG. 3A, the recruiter terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the storage unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected inside the recruiter terminal 20 via the communication bus 26. The descriptions of the control unit 21, the storage unit 22, and the communication unit 23 are omitted because they are the same as the descriptions of the respective units in the server device 10. Note that the recruiter terminal 20 may be a terminal operated by a staffing agency that communicates with job seekers on behalf of the recruiter.

[0022] <Input Unit 24> The input unit 24 receives operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 can execute predetermined control and calculations as necessary based on the transferred command signals. The input unit 24 may be included in the housing of the job seeker terminal 20 or may be externally attached. For example, the input unit 24 may be integrated with the output unit 25 and implemented as a touch panel. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 24. As the input unit 24, instead of a touch panel, a switch button, a mouse, a track pad, a QWERTY keyboard, etc. can be adopted.

[0023] <Output unit 25> The output unit 25 displays a screen of a graphical user interface (GUI) operable by the user. The output unit 25 may be included in the housing of the job seeker terminal 20 or may be externally attached. Specifically, the output unit 25 can be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. These display devices are preferably implemented selectively according to the type of the job seeker terminal 20.

[0024] <Job seeker terminal 30> As shown in FIG. 3B, the job seeker terminal 30 includes a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the storage unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected via the communication bus 36 inside the job seeker terminal 30. The descriptions of the control unit 31, the storage unit 32, the communication unit 33, the input unit 34, and the output unit 35 are omitted because they are the same as the descriptions of the respective units in the job offerer terminal 20.

[0025] 2. Functional configuration In this section, the functional configuration of this embodiment will be described. The information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (the processor included in the employment support system 1).

[0026] FIG. 4 is a block diagram showing the functions realized by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job applicant terminal 30 (control unit 31).

[0027] As shown in FIG. 4A, the server device 10 (control unit 11) includes a basic display control unit 111, a reception unit 112, a job offer creation unit 113, an acquisition unit 114, a job offer correction unit 115, a scout document creation unit 116, a correction presentation unit 117, and an artificial intelligence unit 120. As shown in FIG. 4B, the job seeker terminal 20 (control unit 21) includes a display unit 211 and an operation reception unit 212. As shown in FIG. 4C, the job applicant terminal 30 (control unit 31) includes a display unit 311 and an operation reception unit 312.

[0028] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the job seeker terminal 20 and the job applicant terminal 30. For example, the basic display control unit 111 displays the resume and work history created by the job applicant, the job offer and scout document created by the job seeker, etc. on the display unit 211 of the job seeker terminal 20 or the display unit 311 of the job applicant terminal 30.

[0029] Job seekers include organizations such as for-profit corporations (e.g., companies, etc.), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local public bodies, etc.). Also, job seekers include personnel intermediaries who mediate between job applicants and organizations as agents of the organization. Personnel intermediaries are also called headhunters, agents, etc.

[0030] <Reception unit 112> The reception unit 112 is configured to receive an input of initial conditions for creating a job offer form. The initial conditions are information that defines the profile of the person sought by the employer. The initial conditions include, for example, at least one of the title of the job offer form, the position name, the job content, the profile of the person sought by the employer, and the recruitment background. A persona is the profile of the person (the type of talent to be recruited) sought by the employer, and may be paraphrased as the desired talent profile, and may include, for example, job information. The recruitment background is the reason for the need for the talent or position to be recruited, and includes the organization's goals, issues, business situation (e.g., the start of a new project), etc. Further, the initial conditions may be the job category, position, skills, handled products, etc.

[0031] <Job offer form creation unit 113> The job offer form creation unit 113 is configured to create a job offer form from the initial conditions received by the reception unit 112. Specifically, the job offer form creation unit 113 creates a job offer form including a plurality of reference items based on the initial conditions. The reference items are items (i.e., items necessary for creating a scout document) that are referred to when creating a scout document in the scout document creation unit 116. The job offer form created by the job offer form creation unit 113 is added to the database stored in the storage unit 12.

[0032] FIG. 5 is a diagram showing an example of an initial condition input screen ID. As shown in FIG. 5A, the initial condition input screen ID includes an initial condition input field PF and a first button B1. The initial condition input field PF accepts input of initial conditions from the user (for example, text indicating the desired human resource image, position name, or title content). When the user inputs all or part of the initial conditions, as shown in FIG. 5B, a list of human resource images, position names, or titles related to the input initial conditions is displayed from among the pre-prepared human resource images, position names, or titles. When the user selects the displayed human resource image, position name, or title, the selected human resource image, position name, or title is input into the initial condition input field PF. When the first button B1 is input (pressed) with a human resource image, position name, or title input into the initial condition input field PF, the reception unit 112 accepts the human resource image, position name, or title input into the initial condition input field PF as an initial condition. The initial conditions may be input by the user selecting from a list of pre-prepared text options without directly inputting them. Also, as options for the initial conditions, those related to the user's registration information (for example, industry type, organization scale, etc.) pre-registered by the user may be extracted from the text indicating the content of the pre-prepared initial conditions and displayed on the initial condition input screen ID.

[0033] FIG. 6 is a diagram showing an example of an initial condition input screen ID in which a recruitment background selection area BF1 is displayed. On the initial condition input screen ID, when the first button B1 shown in FIGS. 5A and 5B is input, the recruitment background selection area BF1 shown in FIG. 6, the recruitment background display area BF2, and the second button B2 are displayed. In the recruitment background selection area BF1, options for the recruitment background related to the input talent image, position name, or title are displayed. Note that not limited to the input talent image, position name, or title, options for the recruitment background related to the user's registration information or other information input by the user may be displayed. In the recruitment background display area BF2, the recruitment background selected by the user from the options is displayed. When the second button B2 is input in a state where at least one recruitment background is selected, a recruitment ticket is created by the first recruitment ticket creation model of the artificial intelligence unit 120. Note that all or part of the text indicating the content of the recruitment background by the user may be received as input, and options for the recruitment background related to the input text may be displayed as selections from the pre-prepared recruitment backgrounds.

[0034] Here, in FIG. 6, the information selected by the user from the options displayed based on the initial conditions and the user's registration information is not limited to the recruitment background as long as it is related information that has not been input as an initial condition. The related information is information related to the recruitment ticket. For example, in addition to the recruitment background, it includes work content, required skills, etc. When related information other than the recruitment background is displayed and selected as an option, the recruitment background selection area BF1 is read as the related information selection area BF1, and the recruitment background display area BF2 is read as the related information display area BF2. In the related information selection area BF1, options for information related to the input talent image, position name, or title are displayed. In the related information display area BF2, the related information selected by the user from the options is displayed. When the second button B2 is input in a state where at least one related information is selected, a recruitment ticket is created by the first recruitment ticket creation model of the artificial intelligence unit 120. Note that the related information is part of the initial conditions.

[0035] Options for related information including the recruitment background are created, for example, by the related information creation model of the artificial intelligence unit 120. The related information creation model is a learning model that is trained to take as input a part of the initial conditions (e.g., a talent profile, a position name or title) and output related information that is another part of the initial conditions. That is, the related information creation model is a learning model that has learned, using as teacher data a part of the initial conditions and the corresponding related information data. Also, the related information creation model may be generative AI including a large language model. In this case, the job offer creation unit 113 inputs a part of the initial conditions and a prompt including an instruction to create and output related information to the related information creation model, and causes the related information creation model to output the related information. Also, in addition to the instruction to create and output related information and a part of the initial conditions, the job offer creation unit 113 may input to the related information creation model a prompt in which, as samples of input and output, for example, one or more samples of a part of the initial conditions and one or more samples of the corresponding related information are inserted.

[0036] The job offer creation unit 113 inputs the initial conditions to the first job offer creation model of the artificial intelligence unit 120 and causes the first job offer creation model to output a job offer. The first job offer creation model is a learning model that is trained to take the initial conditions as input and output a job offer. That is, the first job offer creation model is a learning model that has learned, using as teacher data the initial condition data and the corresponding job offer data. Also, the first job offer creation model may be generative AI including a large language model. In this case, the job offer creation unit 113 inputs the initial conditions and a prompt including an instruction to create and output a job offer to the first job offer creation model, and causes the first job offer creation model to output the job offer. Also, in addition to the instruction to create and output a job offer and the initial conditions, the job offer creation unit 113 may input to the first job offer creation model a prompt in which, as samples of input and output, for example, one or more samples of the initial conditions and one or more samples of the corresponding job offers are inserted.

[0037] FIG. 7 is a diagram showing an example of a job offer ticket JP. The job offer ticket JP includes a plurality of item columns such as the name of the position to be recruited, job content and working conditions, application qualifications, and appeal points. The job offer ticket JP may include other item columns other than these. The first job offer ticket creation model generates the text of these item columns based on the initial conditions. The first job offer ticket creation model may create a job offer ticket JP in which each of the plurality of reference items extracted by the first processing model described later is included in any one of the item columns. For example, the job offer ticket creation unit 113 may input a prompt in which samples of the plurality of reference items are inserted into the first processing model.

[0038] In addition, the job offer ticket creation unit 113 may create each of the plurality of reference items one by one using the second job offer ticket creation model of the artificial intelligence unit 120. The second job offer ticket creation model is a learning model that is trained to take the initial conditions as input and output the reference items. That is, the second job offer ticket creation model is a learning model that is trained using the initial condition data and the corresponding reference item data as teacher data. Also, the second job offer ticket creation model may be a generative AI including a large language model. In this case, the job offer ticket creation unit 113 inputs a prompt including an instruction to input the initial conditions and create and output the reference items into the second job offer ticket creation model, and causes the second job offer ticket creation model to output the reference items. That is, the job offer ticket creation unit 113 creates a prompt for each of the plurality of reference items one by one and inputs this prompt into the second job offer ticket creation model one by one. In this case, the job offer ticket creation unit 113 may use a plurality of second job offer ticket creation models trained for each reference item. Further, in addition to the creation / output instruction of the reference item and the initial conditions, the job offer ticket creation unit 113 may input a prompt in which, as samples of the input and output, for example, one or more samples of the initial conditions and one or more samples of the corresponding reference items are inserted into the second job offer ticket creation model.

[0039] The job offer form creation unit 113 may create a job offer form by further inputting the plurality of reference items output by the second job offer form creation model into the third job offer form creation model of the artificial intelligence unit 120. The third job offer form creation model is a learning model that is learned to take a plurality of reference items as input and output a job offer form. That is, the third job offer form creation model is a learning model that is learned using the data of a plurality of reference items and the data of the corresponding job offer form as teacher data. Also, the third job offer form creation model may be a generative AI including a large language model. In this case, the job offer form creation unit 113 inputs a prompt including an instruction to create and output a job offer form with a plurality of reference items as input into the third job offer form creation model, and causes the third job offer form creation model to output a job offer form. Further, in addition to the instruction to create and output a job offer form and the initial conditions, the job offer form creation unit 113 may input into the third job offer form creation model a prompt in which samples of one or more reference items and samples of one or more corresponding job offer forms are inserted as samples of input and output.

[0040] <Acquisition unit 114> The acquisition unit 114 is configured to acquire a job offer form for which a scout document is to be created. The acquisition unit 114, for example, receives an input of a job offer form for which a scout document is to be created from the applicant terminal 20 and acquires the data of the job offer form. The job offer form acquired by the acquisition unit 114 may be one created by the job offer form creation unit 113, or may be one created outside the recruitment support system 1 and imported into the recruitment support system 1.

[0041] When the job offer form created by the job offer form creation unit 113 by the applicant terminal 20 is selected, the acquisition unit 114 acquires the job offer form created based on the initial conditions as described above. The job offer form created by the job offer form creation unit 113 has a high extraction accuracy of a plurality of reference items by the first processing model described later. Therefore, the content of the job offer form is likely to be appropriately reflected in the scout document.

[0042] The acquisition unit 114 acquires website access information for accessing the recruitment ticket reference website, and based on the website access information, acquires a plurality of recruitment ticket access information from the recruitment ticket reference website through web scraping processing, and may further acquire a plurality of recruitment tickets from the plurality of recruitment ticket access information. The recruitment ticket reference website is a website including a plurality of recruitment ticket access information for accessing each of the plurality of recruitment tickets. FIG. 8 is a diagram showing an example of the recruitment ticket reference website RS. A plurality of recruitment ticket links JL (recruitment ticket access information) are posted on the recruitment ticket reference website RS. On the recruitment ticket reference website RS, individual recruitment tickets can be accessed by selecting the recruitment ticket link JL. Examples of the recruitment ticket reference website RS include a recruitment ticket list page (website) in which a recruitment list prepared for each organization provided by a recruitment management system (ATS: Applicant Tracking System) used by the organization is posted together with the recruitment ticket link JL of each recruitment ticket.

[0043] FIG. 9 is a diagram showing an example of the information acquisition screen AD for acquiring recruitment ticket access information. As shown in FIG. 9A, the information acquisition screen AD includes an access information input field AF. The URL (website access information) of the recruitment ticket reference website RS is input into the access information input field AF. The URL of the recruitment ticket reference website RS may be directly input by the user from the applicant terminal 20, or may be acquired and displayed by the acquisition unit 114 from the recruitment ticket reference website RS browsed (accessed) by the user. The acquisition unit 114 acquires the URL input into the access information input field AF as the website access information.

[0044] After acquiring the website access information, the acquisition unit 114 acquires a plurality of job offer links JL included in the job offer reference website RS using the website access information. As shown in FIG. 9B, the acquisition unit 114 displays a list of the job offer links JL (URLs of job offers) acquired on the information acquisition screen AD. The user selects a job offer link JL for which a job offer is to be acquired (i.e., a target for creating a scouting document, modifying a job offer, etc.), for example, by checking a checkbox. Also, as shown in FIG. 9B, the acquisition unit 114 may group a plurality of job offer links JL. The group of job offer links JL (URL group) is classified according to conditions such as job type, industry type, annual income, etc. By selecting a URL group, the user can select a plurality of job offer links JL included in the URL group all at once. When the third button B3 is input (pressed) with one or more job offer links JL selected, the acquisition unit 114 executes a web scraping process on the selected job offer links JL and acquires job offers from the respective URLs.

[0045] <Job offer modification unit 115> The job offer modification unit 115 is configured to modify the job offers acquired by the acquisition unit 114. Specifically, the job offer modification unit 115 creates a modified job offer obtained by modifying the job offer based on at least one of the title, job content, the profile of the person sought by the employer, and the recruitment background, which are extracted from the job offer acquired by the acquisition unit 114.

[0046] For example, the job offer modification unit 115 inputs the job offer into the initial condition estimation model of the artificial intelligence unit 120 and causes the initial condition estimation model to estimate an initial condition corresponding to the job offer (i.e., at least one of the title, position name, job content, the profile of the talent sought by the employer, and the recruitment background). Then, the job offer modification unit 115 inputs the estimated initial condition into the first job offer creation model described above, or a combination of the second job offer creation model and the third job offer creation model, and causes these models to output the job offer. The job offer modification unit 115 sets the job offer output from the model as the modified job offer to be the target for creating a scouting document.

[0047] The job offer form correction unit 115 may be configured to output a corrected job offer form including a plurality of reference items. For example, similar to the job offer form creation unit 113, the job offer form correction unit 115 may create one prompt for each of the plurality of reference items and input each of these prompts into the second job offer form creation model one by one to create the plurality of reference items one by one. Alternatively, the job offer form correction unit 115 may use a plurality of second job offer form creation models learned for each reference item.

[0048] The initial condition estimation model is a learning model trained to take a job offer form as input and output initial conditions. That is, the initial condition estimation model is a learning model trained using the data of the job offer form and the data of the corresponding initial conditions as teacher data. Further, the initial condition estimation model may be a generative AI including a large language model. In this case, the job offer form creation unit 113 inputs a prompt including an instruction to extract and output initial conditions with the job offer form as input to the initial condition estimation model, and causes the initial condition estimation model to output the initial conditions. Further, in addition to the extraction / output instruction of the initial conditions and the job offer form, the job offer form creation unit 113 may input a prompt in which, as samples of input and output, for example, one or more samples of job offer forms and one or more samples of corresponding initial conditions are inserted, into the initial condition estimation model.

[0049] In the acquisition unit 114, for example, when a plurality of job offer forms are acquired from a job offer form reference website or the like, the job offer form correction unit 115 creates a plurality of corrected job offer forms corresponding to the plurality of job offer forms respectively. That is, the job offer form correction unit 115 inputs the plurality of job offer forms into the initial condition estimation model one by one to extract the initial conditions. Further, the job offer form correction unit 115 inputs each of the extracted initial conditions of the plurality of job offer forms into the first job offer form creation model, or a combination of the second job offer form creation model and the third job offer form creation model one by one, and causes these models to output the corrected job offer forms.

[0050] <Scout document creation unit 116> The scout document creation unit 116 is configured to create a scout document corresponding to the job offer ticket acquired by the acquisition unit 114. The creation of the scout document by the scout document creation unit 116 is performed at an arbitrary timing. The creation of the scout document by the scout document creation unit 116 may be automatically executed, for example, after the creation or modification of the job offer ticket, or may be executed in response to an instruction from the user to create a scout document.

[0051] Specifically, the scout document creation unit 116 inputs the job offer ticket acquired by the acquisition unit 114 into the first processing model which is a learning model, causes the first processing model to output a plurality of document components respectively corresponding to a plurality of reference items included in the job offer ticket, inputs the plurality of document components into the second processing model which is a learning model, and causes the second processing model to output a first scout document corresponding to the job offer ticket.

[0052] Examples of the reference items include, but are not limited to, "reason for recruitment" (recruitment background), "hiring target", "future prospects", "attractiveness of the organization or position", "competitive advantage of the organization or position", etc. Any item related to the content of the scout document may be used. At least one document component of these reference items may be output. That is, the scout document creation unit 116 inputs into the first processing model a document component derived from the "reason for recruitment" described in the job offer ticket (i.e., a sentence for conveying to the job seeker "why are you recruiting?"), a document component derived from the "hiring target" described in the job offer ticket (i.e., a sentence for conveying to the job seeker "what kind of people are you recruiting?"), a document component derived from the "future prospects" described in the job offer ticket (i.e., a sentence for conveying to the job seeker "what kind of future prospects are there?"), a document component derived from the "attractiveness of the organization or position" described in the job offer ticket (i.e., a sentence for conveying to the job seeker "what kind of attractiveness is there for employees?"), and a document component derived from the "competitive advantage of the organization or position" described in the job offer ticket (i.e., a sentence for conveying to the job seeker "what kind of advantages does the organization or position have over competing organizations?"), and may output them.

[0053] <First processing model> The first processing model is a learning model trained to take a job offer ticket as input and output a plurality of document components. That is, the first processing model is a learning model that learns using the data of the job offer ticket and the data of the corresponding document components as teacher data. Also, the first processing model may be a generative AI including a large language model. In this case, the scout document creation unit 116 inputs a prompt including an instruction to create and output a plurality of document components with the job offer ticket as input to the first processing model, and causes the first processing model to output a plurality of document components. Further, in addition to the instruction to create and output a plurality of document components and the job offer ticket, the scout document creation unit 116 may input to the first processing model a prompt in which, as samples of input and output, for example, samples of one or more job offer tickets and samples of one or more corresponding document components are inserted. Here, the first processing model may extract and output a plurality of document components from the sentences included in the input job offer ticket data, or may create and output based on the sentences included in the input job offer ticket data. The plurality of document components created and output by the first processing model may be created so as to necessarily include at least a part of the sentences included in the job offer ticket data. These output results may be instructed by the prompt input to the first processing model.

[0054] The reference items to be extracted by the first processing model are incorporated as learning result parameters into the first processing model or inserted into the prompt input to the first processing model.

[0055] Furthermore, the scout document creation unit 116 may input samples of document components prepared for each attribute of job seekers who are the targets of scout document transmission, together with the job offer form, into the first processing model, and cause the first processing model to output document components according to the attributes of the job seekers. As a result, it is possible to create first scout documents with different layouts according to the target from one job offer form. The attributes of job seekers are information about job seekers. Specific examples of the attributes of job seekers include the industries, organizations, job types, skills, qualifications, annual income, age, etc. that the job seekers have experienced. The scout document creation unit 116 inputs, for example, a sample for the same industry (i.e., a job seeker whose experienced industry is the same as the industry of the job offer form) and a sample for a different industry (i.e., a job seeker whose experienced industry is different from the industry of the job offer form) into the first processing model, so as to output document components for the same industry and document components for a different industry from the input of one job offer form. That is, based on one job offer form, a plurality of document components with different contents can be output.

[0056] The scout document creation unit 116 may use samples of text components prepared for each recruitment category of the job offer form. The recruitment category is, for example, the job type, industry, etc. of the job offer form. Further, the scout document creation unit 116 may use a first processing model learned for each attribute of the job seeker or each recruitment category of the job offer form. For example, when the target of scout document transmission is a job seeker in the same industry, the scout document creation unit 116 may input the job offer form into a first processing model that outputs text components corresponding to the same industry.

[0057] Furthermore, the scout document creation unit 116 may change the prompt input to the first processing model according to the attributes of the job seeker or the recruitment category of the job offer form. For example, when the target of scout document transmission is a job seeker in the same industry, the scout document creation unit 116 may insert an instruction to output text components corresponding to the same industry into the prompt to the first processing model.

[0058] The scout document creation unit 116 may input an instruction to the first processing model to use, as an error message specific to the document components corresponding to the reference items not included in the job offer ticket among a plurality of reference items, along with the job offer ticket. Specifically, the scout document creation unit 116 inserts, into the prompt input to the first processing model, an output instruction for an error message such as, for example, "Please describe 'I don't know' if information is insufficient (the corresponding reference item does not exist in the job offer ticket)". As a result, the error message is output as the document component corresponding to the non-existent reference item. Further, when there is a reference item not included in the job offer ticket, the scout document creation unit 116 may cause the job seeker terminal 20 or the like to display that fact (error display).

[0059] The scout document creation unit 116 may input an instruction to the first processing model not to create the document components corresponding to the reference items not included in the job offer ticket among a plurality of reference items, along with the job offer ticket. In this case, the first processing model outputs only the document components corresponding to the reference items included in the job offer ticket.

[0060] <Second processing model> The second processing model is a learning model trained to take a plurality of document components (for example, document components corresponding to each of "recruitment reasons", "hiring targets", "future prospects", "organization or position", "competitive advantages of the organization or position", etc.) as input and output a first scout document. That is, the second processing model is a learning model trained using data on a plurality of document components and data on corresponding job application forms as teacher data. Also, the second processing model may be a generative AI including a large language model. In this case, the scout document creation unit 116 inputs a prompt including an instruction to create and output a first scout document with a plurality of document components as input to the second processing model, and causes the second processing model to output the first scout document. Further, in addition to the instruction to create and output the first scout document and the plurality of document components, the scout document creation unit 116 may input to the second processing model a prompt in which samples of one or more document components and samples of one or more first scout documents corresponding thereto are inserted as input and output samples.

[0061] Furthermore, the scout document creation unit 116 may input to the second processing model samples of the first scout document prepared for each attribute of the job seeker to whom the scout document is to be sent, together with the plurality of document components, and cause the second processing model to output the first scout document according to the attribute. Thereby, different versions of the first scout document can be created according to the target from one job application form. The scout document creation unit 116 inputs, for example, a sample for the same industry and a sample for a different industry to the second processing model, and outputs a first scout document for the same industry and a first scout document for a different industry from the input of a plurality of document components based on one job application form.

[0062] Note that, as described above, when inputting samples of document components prepared for each job seeker attribute into the first processing model and causing the first processing model to output document components corresponding to the job seeker attributes, it is not always necessary to input samples of the first scout documents prepared for each job seeker attribute into the second processing model. That is, the scout document creation unit 116 may cause the second processing model to output a first scout document for the same industry by inputting the document components output for those in the same industry into the second processing model, and may cause the second processing model to output a first scout document for those in different industries by inputting the document components output for those in different industries into the second processing model.

[0063] The scout document creation unit 116 may use samples of the first scout documents prepared for each recruitment category of the job offer form. Further, the scout document creation unit 116 may use a second processing model learned for each job seeker attribute or recruitment category of the job offer form. For example, when the recipients of the scout documents are job seekers in the same industry, the scout document creation unit 116 may input a plurality of document components into the second processing model that outputs a first scout document corresponding to the same industry.

[0064] Furthermore, the scout document creation unit 116 may change the prompt to be input into the second processing model according to the job seeker attribute or the recruitment category of the job offer form. For example, when the recipients of the scout documents are job seekers in the same industry, the scout document creation unit 116 may insert an instruction to output a first scout document corresponding to the same industry into the prompt to the second processing model.

[0065] In addition, the scout document creation unit 116 inputs document components other than error sentences among the plurality of document components into the second processing model. That is, the scout document creation unit 116 does not input document components whose content is an error sentence (for example, "I don't understand") into the second processing model. The second processing model creates the first scout document using only the input document components. As a result, halation in the first scout document is suppressed. That is, when the description corresponding to the reference item is not included in the job application form, it is suppressed that the document component for this reference item is generated by the second processing model from the information not included in the job application form.

[0066] In addition, the scout document creation unit 116 may input document components whose content is an error sentence into the second processing model, and may also input an instruction not to insert a sentence based on the error sentence into the first scout document into the second request processing model. For example, the scout document creation unit 116 may insert an instruction not to reflect the reference item (error sentence) in the first scout document when the reference item is an error sentence in the prompt input to the second processing model.

[0067] In addition, the scout document creation unit 116 does not necessarily have to input all of the plurality of sentence components output by the first processing model into the second processing model. For example, the scout document creation unit 116 may input only pre-specified sentence components among the plurality of sentence components output by the first processing model into the second processing model. The sentence components not input into the second processing model are used, for example, for creating a resend scout document by the fifth processing model described later.

[0068] The scout document creation unit 116 may input an instruction to limit the number of characters in the first scout document and an instruction to use a specific label name for the candidate name (the name of the job seeker who is the recipient of the scout document) into the second processing model. Specifically, the scout document creation unit 116 inserts output instructions such as "the number of characters in the generated text is within XX characters" and "the candidate name is not changed from {candidate name}" into the prompt input to the second processing model. As a result, a first scout document with an appropriate text length and suppression of hyphenation in the candidate name is output.

[0069] When the job offer amendment unit 115 creates an amended job offer for the job offer obtained by the acquisition unit 114, the scout document creation unit 116 inputs the amended job offer into the first processing model, causes the first processing model to output a plurality of document components respectively corresponding to a plurality of items included in the amended job offer, further inputs the plurality of document components into the second processing model, and causes the second processing model to output a first scout document corresponding to the amended job offer. As a result, while amending the job offer so that it is easier to employ the job seeker sought by the employer, a first scout document based on the amended job offer can be created. Therefore, a scout document that makes it easier to employ a job seeker can be efficiently created.

[0070] The first scout document output by the second processing model is composed of a group of texts in which the expressions, contexts, etc. of a plurality of document components are adjusted. The first scout document may also include sentences and words assigned by the second processing model. FIG. 10 is a diagram showing an example of the scout document SD created by the scout document creation unit 116. The scout document SD in FIG. 10 includes a main text MB created by the second processing model, a beginning SH and an end SF created by a third processing model described later. In the example of FIG. 10, the main text MB includes a first sentence S1, a second sentence S2, a third sentence S3, a fourth sentence S4, and a fifth sentence S5.

[0071] In the example of FIG. 10, the first sentence S1 is a sentence that explains "what kind of organization / business it is". The first sentence S1 is generated based on, for example, the sentence components corresponding to "reason for recruitment". The second sentence S2 is a sentence that explains "what kind of environment it is". The second sentence S2 is generated based on, for example, the sentence components corresponding to "reason for recruitment". The third sentence S3 is a sentence that explains "what kind of person it matches". The third sentence S3 is generated based on, for example, the sentence components corresponding to "target for employment". The fourth sentence S4 is a sentence that shows "what kind of attractions / future prospects there are". The fourth sentence S4 is generated based on, for example, the sentence components corresponding to "future prospects" and the sentence components corresponding to "attractions of the organization or position". The fifth sentence S5 is a sentence that shows "what kind of competitive advantages there are". The fifth sentence S5 is generated based on, for example, the sentence components corresponding to "competitive advantages of the organization or position".

[0072] The first scout document output by the second processing model may be directly sent to the job seeker as a scout document by the user, or may be used as a template for the scout document on the premise of the user's modification and addition.

[0073] The scout document creation unit 116 may adjust or modify the content and style of the first scout document. That is, the scout document creation unit 116 may further input the first scout document into the third processing model which is a learning model, and cause the third processing model to output a second scout document with the format of the first scout document adjusted. Thereby, while adjusting the entire scout document, the style as a scout document can be arranged.

[0074] <The third processing model> The third processing model is a learning model trained to take the first scout document as input and output the second scout document. That is, the third processing model is a learning model trained using the data of the first scout document and the corresponding data of the second scout document as teacher data. Also, the third processing model may be generative AI including a large language model. In this case, the scout document creation unit 116 inputs a prompt including an instruction to take the first scout document as input and create and output the second scout document to the third processing model, and causes the third processing model to output the second scout document. Further, in addition to the instruction to create and output the second scout document and the first scout document, the scout document creation unit 116 may input to the third processing model a prompt in which, as samples of input and output, for example, one or more samples of the first scout document and one or more corresponding samples of the second scout document are inserted.

[0075] The scout document creation unit 116 may input to the third processing model an instruction to make the text of the first scout document easier to understand and an instruction to insert a beginning and an end into the first scout document. Specifically, the scout document creation unit 116 inserts, into the prompt input to the third processing model, output instructions such as, for example, "Please make the first scout document easier to understand for the hiring staff who will send the scout document" and "Please output the second scout document in an output format including the beginning text and the end text". Thereby, a second scout document having a text surface such as that created by the hiring staff and including the beginning SH and the end SF shown in FIG. 10 is output. Note that the scout document creation unit 116 may input to the third processing model an instruction (prompt) to insert only one of the beginning and the end. Also, the scout document creation unit 116 may input to the third processing model an instruction (prompt) to insert a fixed text (beginning, end, or other text) independent of the content of the first scout document.

[0076] The second scout document output by the third processing model may be directly sent to the job seeker as a scout document by the user, or may be used as a template for a scout document assuming user correction and addition.

[0077] The scout document creation unit 116 may assign a title (subject line) to the second scout document. That is, the scout document creation unit 116 may further input the second scout document into a fourth processing model which is a learning model, and cause the fourth processing model to output the title of the second scout document. Thereby, a title that can enhance the interest of job seekers can be assigned to the scout document. Also, the labor of the user considering the title of the scout document is reduced.

[0078] Furthermore, the scout document creation unit 116 may assign a title (subject line) to the first scout document. That is, the scout document creation unit 116 may further input the first scout document into a fourth processing model which is a learning model, and cause the fourth processing model to output the title of the first scout document. That is, the scout document creation unit 116 may input the first scout document output by the second processing model into the fourth processing model without inputting it into the third processing model. Also by this, a title that can enhance the interest of job seekers can be assigned to the scout document.

[0079] <Fourth Processing Model> The fourth processing model is a learning model that is learned to take a scout document (the first scout document or the second scout document) as an input and output the title of the scout document. That is, the fourth processing model is a learning model that is learned using the data of the scout document and the data of the corresponding title as teacher data. Also, the fourth processing model may be a generative AI including a large language model. In this case, the scout document creation unit 116 inputs a prompt including an instruction to create and output a title, with the scout document as an input, to the fourth processing model, and causes the fourth processing model to output the title of the scout document. Also, in addition to the instruction to create / output the title and the scout document, the scout document creation unit 116 may input to the fourth processing model a prompt in which, as samples of the input and output, for example, samples of one or more scout documents and samples of one or more corresponding titles are inserted.

[0080] The fourth processing model may be a learning model that learns only the data of the title of the scout document as teacher data. Also, when the fourth processing model is a generative AI, in addition to the title creation / output instruction and the scout document, the scout document creation unit 116 may input a prompt to the fourth processing model without inserting an input sample but inserting a plurality of title samples as output samples.

[0081] After sending the scout document to the job seeker, the scout document creation unit 116 may create a resend scout document for resending to the same job seeker based on the same job posting. That is, the scout document creation unit 116 may input the second scout document into a fifth processing model that is a learning model and cause the fifth processing model to output a resend scout document. Thereby, while maintaining the content of the second scout document, a resend scout document with a different text format from the second scout document can be efficiently created.

[0082] Furthermore, instead of the second scout document, the scout document creation unit 116 may input the first scout document into a fifth processing model that is a learning model and cause the fifth processing model to output a resend scout document. That is, the scout document creation unit 116 may input the first scout document output by the second processing model into the fifth processing model without inputting it into the third processing model. Thereby, while maintaining the content of the first scout document, a resend scout document with a different text format from the first scout document can be efficiently created.

[0083] <The fifth processing model> The fifth processing model is a learning model trained to take a scout document (the first scout document or the second scout document) as input and output a resending scout document. That is, the fifth processing model is a learning model that learns using the data of the scout document and the data of the corresponding resending scout document as teacher data. Also, the fifth processing model may be generative AI including a large language model. In this case, the scout document creation unit 116 inputs a prompt including an instruction to create and output a resending scout document with the scout document as input to the fifth processing model, and causes the fifth processing model to output the resending scout document. Further, in addition to the instruction to create and output the resending scout document and the scout document, the scout document creation unit 116 may input to the fifth processing model a prompt in which, as samples of input and output, for example, one or more samples of scout documents and one or more samples of corresponding resending scout documents are inserted.

[0084] The resending scout document output by the fifth processing model is composed of a group of sentences included in the first scout document or the second scout document (or an arrangement of the group of sentences) and additional sentences added to prompt a reply. The additional sentences include, for example, a first sentence newly created based on the sentence components output by the first processing model and a general-purpose second sentence (for example, "Have you checked the scout sent the other day?") including words to prompt a reply. The first sentence may be called a variable sentence that varies depending on the content of the scout document, and the second sentence may be called a fixed sentence that does not vary depending on the content of the scout document.

[0085] The scout document creation unit 116 inputs, for example, among the plurality of sentence components output by the first processing model, the sentence components that were not input to the second processing model (that is, not reflected in the first scout document) into the fifth processing model together with the first scout document or the second scout document, and causes the fifth processing model to output a resending scout document in which a first sentence based on the sentence component is added. In this case, the scout document creation unit 116 inserts an output instruction such as "Please organize and insert the 'particularly attractive points' of the position" into the prompt input to the fifth processing model. Thereby, a resending scout document with additional sentences not included in the initial scout document (the first scout document or the second scout document) is obtained.

[0086] Further, the scout document creation unit 116 may extract a specific sentence (for example, a sentence related to "attractive points") from the sentence components reflected in the first scout document and the content of the first scout document, and insert a sentence emphasizing the sentence (for example, a sentence emphasizing "attractive points") into the resending scout document.

[0087] The resending scout document output by the fifth processing model may be directly transmitted to the job seeker as a scout document by the user, or may be used as a template for a scout document assuming user modification and addition. Also, the resending scout document may be automatically created when creating the first scout document or the second scout document, or may be created in response to a user's instruction to resend the scout document.

[0088] When the job offer ticket correction unit 115 creates a plurality of corrected job offer tickets, the scout document creation unit 116 creates a plurality of first scout documents corresponding to each of the plurality of corrected job offer tickets. As a result, for a plurality of job offer tickets accessible from the above-described job offer ticket reference website, scout documents corresponding to each job offer ticket can be created collectively. Further, the scout document creation unit 116 may create a plurality of second scout documents, the titles of each of the plurality of first scout documents, or a plurality of resend scout documents based on the plurality of first scout documents. Similarly, the scout document creation unit 116 may create the titles of each of the plurality of second scout documents or a plurality of resend scout documents based on the plurality of second scout documents.

[0089] <Correction prompt unit 117> The correction prompt unit 117 is configured to present the correction content in the corrected job offer ticket created by the job offer ticket correction unit 115. For example, the correction prompt unit 117 compares the job offer ticket before correction with the job offer ticket after correction and displays them on the applicant terminal 20. FIG. 11 is an example of a correction content display screen MD. On the correction content display screen MD, a correction outline MS, a job offer ticket JP1 before correction, and a job offer ticket JP2 after correction are displayed. The job offer ticket JP1 before correction and the job offer ticket JP2 after correction are displayed side by side on the left and right.

[0090] The correction prompt unit 117 may emphasize the display so that it can be visually distinguished from other parts, such as highlighting the difference between the job offer ticket JP1 before correction and the job offer ticket JP2 after correction (the corrected part in the job offer ticket JP2 after correction). Further, the correction prompt unit 117 may present only the corrected part.

[0091] The correction prompt section 117 receives an approval input for the correction of the job offer ticket presented from the job seeker terminal 20 (that is, the overwrite update of the job offer ticket with the corrected job offer ticket). The corrected job offer ticket is stored in the database. The scout document creation section 116 may create a scout document for the corrected job offer ticket upon receiving approval from the user for the correction of the job offer ticket. In other words, when the correction of the job offer ticket by the user is not approved, the scout document creation section 116 may be configured not to execute the creation of the scout document for the corrected job offer ticket. However, the scout document creation section 116 may be configured to create a scout document corresponding to the corrected job offer ticket as a template regardless of whether the correction is approved or not.

[0092] The correction prompt section 117 may receive a direct correction input (editing input) for the description items of the job offer ticket from the job seeker terminal 20. In this case, a scout document is created by the scout document creation section 116 for the job offer ticket corrected by the correction input.

[0093] <Artificial intelligence section 120> The artificial intelligence section 120 is configured to receive inputs from each functional section and return the instructed output. Note that the artificial intelligence used by the server device 10 in each functional section may be common or may be prepared individually for each functional section.

[0094] The artificial intelligence section 120 is an AI (Artificial Intelligence) equipped with a language model such as a Transformer (including GPT (Generative Pretrained Transformer, GPT-1, GPT-2, GPT-3), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), etc.) or a Recurrent Neural Network (RNN), and may include a generative AI.

[0095] A language model is an example of a learning model by a machine learning algorithm. Specific algorithms for machine learning include the nearest neighbor method, the naive Bayes method, decision trees, support vector machines, deep learning (deep neural networks) using neural networks, and the like. The artificial intelligence unit 120 can appropriately apply the above algorithms.

[0096] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or semi-supervised learning. In supervised learning, machine learning is performed using teacher data (learning data). The teacher data is composed of a pair of input data for learning and output data (correct data). Also, the language model may be a general-purpose model that is not only trained for a specific task but can be generally used for a wide range of tasks.

[0097] The artificial intelligence unit 120 may be a general-purpose natural language processing learning model such as a large language model (LLM) that has learned a vast amount of data as artificial intelligence. Such a general-purpose learning model includes language models that can handle various tasks without fine-tuning by One-shot Learning, Few-shot Learning, etc. Also, the general-purpose learning model may be configured to be able to handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be separate learning models or a common general-purpose learning model.

[0098] The learning model (the learning model used in each functional unit such as the first processing model) included in the artificial intelligence unit 120 can perform additional learning. For example, each time a new job application form is registered and a scout document is created, the artificial intelligence unit 120 may use these as new teacher data to perform additional learning and be fine-tuned. Thereby, the accuracy of the expected value information output from the learning model is improved.

[0099] <Display unit> The display units 211 of the employer terminal 20 and 311 of the job seeker terminal 30 each display the screen indicated by the screen data transmitted from the server device 10.

[0100] <Operation reception unit> The operation reception unit 212 of the employer terminal 20 receives operations by the user (employer) using the employer terminal 20. The operation reception unit 312 of the job seeker terminal 30 receives operations by the user (job seeker) using the job seeker terminal 30.

[0101] 3. Information processing method In this section, an information processing method of the server device 10 will be described. In this information processing method, each part of the server device 10 is executed by a computer as each step.

[0102] This information processing method includes a first embodiment and a second embodiment. The information processing method of the first embodiment includes a reception step of receiving an input of initial conditions for creating a job offer, a job offer creation step of creating a job offer including a plurality of items based on the initial conditions, an acquisition step of acquiring the job offer created based on the initial conditions, inputting the job offer into a first processing model which is a learning model, outputting a plurality of document components respectively corresponding to the plurality of items included in the job offer by the first processing model, inputting the plurality of document components into a second processing model which is a learning model, outputting a first scout document corresponding to the job offer by the second processing model, inputting the first scout document into a third processing model which is a learning model, outputting a second scout document with the format of the first scout document adjusted by the third processing model, inputting the second scout document into a fourth processing model which is a learning model, outputting the title of the second scout document by the fourth processing model, inputting the second scout document into a fifth processing model which is a learning model, and a scout document creation step of outputting a resend scout document by the fifth processing model.

[0103] FIG. 12 is an activity diagram showing the flow of information processing (recruitment document creation process from job offer creation) of the first embodiment executed by the adoption support system 1. Hereinafter, the information processing will be described along each activity of this activity diagram.

[0104] The creation process of the recruitment document in the first embodiment starts with the creation of a job offer by the job seeker. The job seeker inputs initial conditions for creating a job offer on the job seeker terminal 20 (activity A101). The server device 10 receives the input of the initial conditions from the job seeker terminal 20 (activity A102). The server device 10 creates a job offer based on the received initial conditions (activity A103). Subsequently, the server device 10 inputs the created job offer into the first processing model (activity A104). As a result, document components are output from the first processing model. Next, the server device 10 inputs the document components into the second processing model (activity A105). As a result, the first recruitment document is output from the second processing model.

[0105] Furthermore, the server device 10 inputs the first recruitment document into the third processing model (activity A106). As a result, the second recruitment document is output from the third processing model. Subsequently, the server device 10 inputs the second recruitment document into the fourth processing model and the fifth processing model (activity A107). As a result, a title is output from the fourth processing model, and a resend recruitment document is output from the fifth processing model. The server device 10 outputs the second recruitment document and the resend recruitment document to the job seeker terminal 20 (activity A108). As a result, the second recruitment document and the resend recruitment document are displayed on the job seeker terminal 20 (activity A109).

[0106] The information processing method of the second embodiment includes an acquisition step of acquiring a job offer ticket, a job offer ticket correction step of creating a corrected job offer ticket by correcting the job offer ticket based on at least one of the title, job content, candidate profile required by the employer, and recruitment background extracted from the job offer ticket, an input step of inputting the corrected job offer ticket into a first processing model to output a plurality of document components corresponding to the plurality of items included in the corrected job offer ticket in the first processing model, an input step of further inputting the plurality of document components into a second processing model to output a first scout document corresponding to the corrected job offer ticket in the second processing model, an input step of further inputting the first scout document into a third processing model which is a learning model to output a second scout document with the format of the first scout document adjusted in the third processing model, an input step of further inputting the second scout document into a fourth processing model which is a learning model to output the title of the second scout document in the fourth processing model, and a scout document creation step of further inputting the second scout document into a fifth processing model which is a learning model to output a resend scout document in the fifth processing model.

[0107] FIG. 13 is an activity diagram showing the flow of information processing (creation process of scout document from correction of job offer ticket) of the second embodiment executed by the employment support system 1. Hereinafter, the information processing will be described along each activity of this activity diagram.

[0108] The creation process of the scout document in the second embodiment starts from the modification of the job offer form selected by the job seeker. The job seeker inputs the selection of the job offer form to be modified on the job seeker terminal 20 (Activity A201). The server device 10 extracts modification conditions including at least one of the title, job content, the profile of the person sought by the job seeker, and the recruitment background from the selected job offer form (Activity A202). The server device 10 creates a modified job offer form based on the extracted modification conditions (Activity A203). Subsequently, the server device 10 inputs the created modified job offer form into the first processing model (Activity A204). As a result, document components are output from the first processing model. Next, the server device 10 inputs the document components into the second processing model (Activity A205). As a result, the first scout document is output from the second processing model. Activities A206 to A209 are the same as activities A106 to A109 in the first embodiment.

[0109] 4. Operation Summarizing the operation of this embodiment, it is as follows. That is, a scout document including document components corresponding to the items of the job offer form can be created. Also, by performing stepwise the step of generating document components for each item and the step of generating a scout document using the document components, a scout document that appropriately reflects the content of the job offer form can be efficiently created.

[0110] As described above, the embodiments of the present invention have been explained, but the present invention is not limited thereto and can be appropriately changed without departing from the technical idea of the invention.

[0111] 5. Others In the above-described embodiment, the server device 10 performs various storage and control operations. However, instead of the server device 10, a plurality of external devices may be used. That is, various information and programs may be distributed and stored in a plurality of external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 120, which is an external configuration, is configured to receive an input from each functional unit of the server device 10 and return an instructed output to the server device 10.

[0112] The aspect of this embodiment is not limited to the employment support system 1, and may be an information processing method or a program. The employment support method includes each step executed by the employment support system 1. The program causes a computer to execute each step of the employment support system 1.

[0113] The control unit 11 of the employment support system 1 does not necessarily have to include the job offer creation unit 113. That is, the control unit 11 may create a scouting document only for existing job offers. Also, the control unit 11 does not necessarily have to include the job offer correction unit 115.

[0114] It may also be provided in each of the aspects described below.

[0115] (1) An employment support system comprising a processor, the processor being configured to execute the following steps: In an acquisition step, a job offer is acquired. In a scouting document creation step, the job offer is input into a first processing model that is a learning model, and the first processing model is caused to output a plurality of document components respectively corresponding to a plurality of items included in the job offer. The plurality of document components are further input into a second processing model that is a learning model, and the second processing model is caused to output a first scouting document corresponding to the job offer.

[0116] (2) In the recruitment support system described in (1) above, in the scout document creation step, the first scout document is further input into a third processing model which is a learning model, and the third processing model outputs a second scout document with the format of the first scout document adjusted. A recruitment support system.

[0117] (3) In the recruitment support system described in (2) above, in the scout document creation step, the second scout document is further input into a fourth processing model which is a learning model, and the fourth processing model outputs the title of the second scout document. A recruitment support system.

[0118] (4) In the recruitment support system described in (2) or (3) above, in the scout document creation step, the second scout document is further input into a fifth processing model which is a learning model, and the fifth processing model outputs a scout document for resending. A recruitment support system.

[0119] (5) In the recruitment support system described in (1) above, in the scout document creation step, the first scout document is further input into a fourth processing model which is a learning model, and the fourth processing model outputs the title of the first scout document. A recruitment support system.

[0120] (6) In the recruitment support system described in (1) or (5) above, in the scout document creation step, the first scout document is further input into a fifth processing model which is a learning model, and the fifth processing model outputs a scout document for resending. A recruitment support system.

[0121] (7) In the recruitment support system described in any one of (1) to (6) above, in the scout document creation step, together with the job application form, an instruction to set the document components corresponding to the items not included in the job application form among the plurality of items as specific error messages is input into the first processing model, and among the plurality of document components, the document components other than the error messages are input into the second processing model. A recruitment support system.

[0122] (8) In the employment support system according to any one of (1) to (7) above, in the scout document creation step, together with the job offer form, samples of the document components prepared for each attribute of the job seekers who are the transmission targets of the scout document are input into the first processing model, and the first processing model is caused to output the document components corresponding to the attributes. An employment support system.

[0123] (9) In the employment support system according to any one of (1) to (8) above, in the scout document creation step, together with a plurality of the document components, samples of the first scout document prepared for each attribute of the job seekers who are the transmission targets of the scout document are input into the second processing model, and the second processing model is caused to output the first scout document corresponding to the attributes. An employment support system.

[0124] (10) In the employment support system according to any one of (1) to (9) above, the processor is further configured to execute the following steps. In the reception step, an input of initial conditions for creating the job offer form is received. In the job offer form creation step, the job offer form including a plurality of the items is created based on the initial conditions. In the acquisition step, the job offer form created based on the initial conditions is acquired. An employment support system.

[0125] (11) In the employment support system according to any one of (1) to (9) above, the processor is further configured to execute the following steps. In the job offer form correction step, a corrected job offer form is created by correcting the job offer form based on at least one of the title, job content, the image of the person sought by the employer, and the recruitment background extracted from the job offer form. In the scout document creation step, the corrected job offer form is input into the first processing model, and the first processing model is caused to output a plurality of the document components respectively corresponding to the plurality of items included in the corrected job offer form. The plurality of document components are further input into the second processing model, and the second processing model is caused to output the first scout document corresponding to the corrected job offer form. An employment support system.

[0126] (12) In the employment support system described in (11) above, the processor is further configured to execute the following steps. In the correction presentation step, the correction content in the corrected job offer is presented. An employment support system.

[0127] (13) In the employment support system described in (11) or (12) above, in the acquisition step, website access information for accessing a job offer reference website including a plurality of job offer access information for accessing each of the plurality of job offers is acquired. Based on the website access information, a plurality of the job offer access information is acquired from the job offer reference website by web scraping processing, and further a plurality of the job offers are acquired from the plurality of the job offer access information. In the job offer correction step, a plurality of corrected job offers corresponding to each of the plurality of job offers are created. In the scout document creation step, a plurality of the first scout documents corresponding to each of the plurality of corrected job offers are created. An employment support system.

[0128] (14) In the employment support system described in (1) above, in the scout document creation step, an instruction to generate a plurality of the text components based on the job offer is input to the first processing model, and an instruction to generate the first scout document based on the plurality of the text components is input to the second processing model. An employment support system.

[0129] (15) In the employment support system described in (2) above, in the scout document creation step, an instruction to generate the second scout document based on the first scout document is input to the third processing model. An employment support system.

[0130] (16) In the employment support system described in (3) above, in the scout document creation step, an instruction to generate the title based on the second scout document is input to the fourth processing model. An employment support system.

[0131] (17) In the employment support system according to (4) above, in the scout document creation step, an instruction to generate the resending scout document based on the second scout document is input to the fifth processing model. An employment support system.

[0132] (18) In the employment support system according to (5) above, in the scout document creation step, an instruction to generate the title based on the first scout document is input to the fourth processing model. An employment support system.

[0133] (19) In the employment support system according to (6) above, in the scout document creation step, an instruction to generate the resending scout document based on the first scout document is input to the fifth processing model. An employment support system.

[0134] (20) An employment support method comprising each step executed by the employment support system according to any one of (1) to (19) above.

[0135] (21) A program that causes a computer to execute each step of the employment support system according to any one of (1) to (19) above. Of course, this is not all.

[0136] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The embodiments and their modifications are included in the scope and gist of the invention and are included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0137] 1: Employment support system 2: Communication line 10: Server device 11: Control Unit 12: Memory Unit 13: Communication Unit 14: Communication Bus 20: Employer Terminal 21: Control Unit 22: Memory Unit 23: Communication Unit 24: Input Unit 25: Output Unit 26: Communication Bus 30: Job Seeker Terminal 31: Control Unit 32: Memory Unit 33: Communication Unit 34: Input Unit 35: Output Unit 36: Communication Bus 111: Basic Display Control Unit 112: Reception Unit 113: Job Offer Document Creation Unit 114: Acquisition Unit 115: Job Offer Document Revision Unit 116: Scout Document Creation Unit 117: Revision Prompting Unit 120: Artificial Intelligence Unit 211: Display Unit 212: Operation Reception Unit 311: Display Unit 312: Operation Reception Unit

Claims

1. A recruitment support system, A processor is provided. The processor is configured to perform the steps of: In the acquisition step, the job posting is acquired, In the scouting document creation step, the recruitment support system inputs the job posting into a first processing model which is a learning model, causes the first processing model to output a plurality of document components which respectively correspond to a plurality of items contained in the job posting, and further inputs the plurality of document components into a second processing model which is a learning model, causes the second processing model to output a first scouting document corresponding to the job posting.

2. The recruitment support system according to claim 1, In the scout document creation step, the first scout document is further input into a third processing model, which is a learning model, and the third processing model is caused to output a second scout document in which the format of the first scout document has been adjusted, in a recruitment support system.

3. The recruitment support system according to claim 2, In the scout document creation step, the second scout document is further input to a fourth processing model which is a learning model, and the fourth processing model is caused to output a title of the second scout document, in this recruitment support system.

4. The recruitment support system according to claim 2, In the scout document creation step, the second scout document is further input to a fifth processing model which is a learning model, and a resend scout document is output from the fifth processing model, in the recruitment support system.

5. The recruitment support system according to claim 1, In the scout document creation step, the first scout document is further input to a fourth processing model which is a learning model, and the fourth processing model is caused to output a title of the first scout document, in this recruitment support system.

6. The recruitment support system according to claim 1, In the scout document creation step, the first scout document is further input to a fifth processing model which is a learning model, and a resend scout document is output from the fifth processing model, in the recruitment support system.

7. The recruitment support system according to claim 1, In the scout document creation step, an instruction to set the document components corresponding to items among the plurality of items that are not included in the job listing as specific error sentences is input into the first processing model along with the job listing, and the document components among the plurality of document components other than the error sentences are input into the second processing model, in a recruitment support system.

8. The recruitment support system according to claim 1, In the scout document creation step, samples of the document components prepared for each attribute of the job seeker to whom the scout document is to be sent are input into the first processing model along with the job posting, and the first processing model is caused to output the document components according to the attributes, in a recruitment support system.

9. The recruitment support system according to claim 1, In the scout document creation step, a sample of the first scout document prepared for each attribute of a job seeker to whom the scout document is to be sent, along with a plurality of the document components, is input into the second processing model, and the second processing model is caused to output the first scout document according to the attributes.

10. The recruitment support system according to claim 1, The processor is further configured to perform the steps of: In the reception step, input of initial conditions for creating the job posting is received, In the job posting creation step, the job posting including the plurality of items is created based on the initial conditions; In the acquisition step, the recruitment support system acquires the job advertisement created based on the initial conditions.

11. The recruitment support system according to claim 1, The processor is further configured to perform the steps of: In the job posting correction step, a corrected job posting is created by correcting the job posting based on at least one of the title, the job content, the person profile desired by the employer, and the recruitment background extracted from the job posting; In the scout document creation step, the revised job posting is input into the first processing model, the first processing model is caused to output a plurality of document components corresponding to each of the items included in the revised job posting, the plurality of document components are further input into the second processing model, and the second processing model is caused to output the first scout document corresponding to the revised job posting, in a recruitment support system.

12. The recruitment support system according to claim 11, The processor is further configured to perform the steps of: In the correction suggestion step, the recruitment support system suggests corrections to the corrected job posting.

13. The recruitment support system according to claim 11, In the acquisition step, website access information for accessing a job posting reference website is acquired, the website access information includes a plurality of job posting access information for accessing each of the plurality of job postings, and the plurality of job posting access information is acquired from the job posting reference website by a web scraping process based on the website access information, and the plurality of job postings are further acquired from the plurality of job posting access information; In the job posting correction step, a plurality of corrected job postings corresponding to the plurality of job postings are created, In the scout document creation step, a recruitment support system creates a plurality of first scout documents corresponding to the plurality of revised job advertisements, respectively.

14. The recruitment support system according to claim 1, In the scout document creation step, instructions for generating a plurality of the sentence components based on the job posting are input to the first processing model, and instructions for generating the first scout document based on the plurality of the sentence components are input to the second processing model, in a recruitment support system.

15. The recruitment support system according to claim 2, In the scout document creation step, an instruction to generate the second scout document based on the first scout document is input to the third processing model, in the recruitment support system.

16. The recruitment support system according to claim 3, In the scout document creation step, an instruction to generate the title based on the second scout document is input to the fourth processing model, in the recruitment support system.

17. The recruitment support system according to claim 4, In the scout document creation step, an instruction to generate the resent scout document based on the second scout document is input to the fifth processing model, in the recruitment support system.

18. 6. The recruitment support system according to claim 5, In the scout document creation step, an instruction to generate the title based on the first scout document is input to the fourth processing model, in the recruitment support system.

19. 7. The recruitment support system according to claim 6, In the scout document creation step, an instruction to generate the resent scout document based on the first scout document is input to the fifth processing model, in the recruitment support system.

20. A recruitment support method, comprising: A recruitment support method comprising the steps executed by the recruitment support system according to any one of claims 1 to 19.

21. A program, A program causing a computer to execute each step of the recruitment support system according to any one of claims 1 to 19.

Images