Information processing systems, information processing methods, and programs

Abstract

We provide technologies related to information processing systems that generate job-related information. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, the first receiving step of receiving input of reference personnel information, the reference personnel information being information of a reference person for generating job-related information, and including at least one of profile information of a specific person and persona information of an ideal person, the generation step of generating job-related information based on the reference personnel information and first reference information, the job-related information including a job posting, job seeker search conditions and a scouting document, the first reference information including at least the correlation between the reference personnel information and the job-related information, and the output step of outputting the generated job posting, job seeker search conditions and scouting document.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] Patent Document 1 discloses a technology related to an employment activity support system.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is room for improvement in the technology related to an information processing system for supporting employment activities.

[0005] Therefore, in view of the above circumstances, the present invention aims to provide a technology related to an information processing system for generating job - related information and the like.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program: in a first reception step, the system receives input of reference personnel information, the reference personnel information being information of a personnel that serves as a standard for generating job-related information, and including at least one of profile information of a specific personnel and persona information of an ideal personnel; in a generation step, the system generates job-related information based on the reference personnel information and first reference information, the job-related information including a job posting, job seeker search conditions and a scouting document, the first reference information including at least the correlation between the reference personnel information and the job-related information; and in an output step, the system outputs the generated job posting, job seeker search conditions and scouting document.

[0007] This configuration makes it possible to provide technologies related to information processing systems that support improved recruitment activities. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] Block diagram showing the hardware configuration of Server 2. [Figure 3] This is a block diagram showing the hardware configuration of applicant terminal 3. [Figure 4] This block diagram shows the functions implemented by Server 2 (Control Unit 23) and Job Seeker Terminal 3 (Control Unit 33). [Figure 5] This figure shows screen G1, an example of a screen that presents the generated job posting JP to the employer U1. [Figure 6] This figure shows screen G2, an example of a screen that presents the generated search criteria CQ to the job seeker U1. [Figure 7] This figure shows screen G3, an example of a screen that presents the generated scout document SM to the recruiter U1. [Figure 8] This diagram shows an overview of the processes performed by Information Processing System 1. [Figure 9] This is an activity diagram showing an example of the information processing flow of the first embodiment, which is performed by the information processing system 1. [Figure 10] This figure shows screen G4, which is an example of a screen that accepts input of standard personnel information. [Figure 11] This figure shows screen G5, an example of a screen that accepts input regarding the acceptance or rejection of feature information or its priority. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0010] Incidentally, the program for implementing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or it may be provided as a downloadable medium from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as "reference information") is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a trained model that has been pre-trained to learn the correlation between input and output, or a generative AI such as a large-scale language model that can output a desired result by inputting a prompt (these models include parameters that construct the correlation relationship between input and output) or a visual language model.

[0012] Furthermore, in one embodiment, "part" may include, for example, hardware resources implemented by a circuit in a broad sense, and the information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various types of information are handled, and this information can be represented, for example, by the physical values ​​of signal values ​​representing voltage and current, the high or low values ​​of signal values ​​as a set of binary bits composed of 0s or 1s, or by quantum superposition (so-called qubits), and communication and calculations can be performed on a circuit in a broad sense.

[0013] Furthermore, a circuit in a broad sense is a circuit realized by combining at least a suitable combination of circuits, circuits, processors, and memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, it includes application-specific integrated circuits (ASICs), programmable logic devices (for example, simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

[0014] 1. Hardware Configuration This section describes the hardware configuration.

[0015] <Information Processing System 1> FIG. 1 is a block diagram showing an information processing system 1. The information processing system 1 includes a server 2 and a job seeker terminal 3. The server 2 and the job seeker terminal 3 are configured to be communicable through a telecommunication line (network). In an exemplary embodiment, the job seeker terminal 3 can function as a terminal of the job seeker U1. Here, the system exemplified in the information processing system 1 is composed of one or more devices or components. Therefore, it should be noted that even the server 2 alone, or the server 2 and the job seeker terminal 3, may be included in the information processing system 1. More specifically, the information processing system 1 may include an element selected from the group consisting of the server 2 and the job seeker terminal 3. Even if the unselected element is not included in the information processing system 1, it may be electrically connected to the selected element as an external element. Hereinafter, these components will be described.

[0016] The information processing system 1 is composed of one or more elements selected from the group consisting of the server 2 and the job seeker terminal 3, and these are configured to be mutually communicable via a network. This system constitutes, for example, at least a part of a job posting and job seeking system. The information processing system 1 performs, for example, posting of job offers by job seekers, searching for job applicants by job seekers, searching for job offers by job applicants, mediation of communication between job seekers and job applicants (transmission and reception of scout messages), etc. In addition, the information processing system 1 provides and manages, for example, a human resource matching platform and a human resource matching service used by job seekers and job applicants. Here, the information processing system 1 enables generation of a job offer document JP, a job applicant search condition CQ, and a scout document SM based on reference human resource information and reference information.

[0017] <Server 2> FIG. 2 is a block diagram showing the hardware configuration of the server 2. The server 2 includes a communication unit 21, a storage unit 22, and a control unit 23, and these components are electrically connected via a communication bus 20 inside the server 2. Each component will be further described.

[0018] The communication unit 21 is comprised of a communication module. The communication module may be a wireless communication module compliant with standards such as IEEE 802.11a / b / g / n / ac / ax, LTE, 5G, 6G, or a wired communication module compliant with standards such as IEEE 802.3. The communication unit 21 is configured to transmit various electrical signals from the server 2 to external components. The communication unit 21 is also configured to receive various electrical signals from external components to the server 2. More preferably, the communication unit 21 may have a network communication function, thereby enabling the communication of various information between the server 2 and external devices via a network.

[0019] The memory unit 22 stores various types of information as defined above. This can be done, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the server 2 executed by the control unit 23, or as memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The memory unit 22 stores various programs and variables related to the server 2 executed by the control unit 23.

[0020] The control unit 23 performs processing and control of the overall operation related to the server 2. The control unit 23 is, for example, a central processing unit (CPU) not shown. The control unit 23 realizes various functions related to the server 2 by reading predetermined programs stored in the memory unit 22. That is, information processing by software stored in the memory unit 22 is concretely realized by the control unit 23, which is an example of hardware, so that each step related to each function described later can be executed. These will be described in more detail in the next section. Note that the control unit 23 is not limited to being a single unit, and may be implemented with multiple control units 23 for each function, or a combination thereof.

[0021] <Job seeker terminal 3> The recruiter terminal 3 is an information processing device used by recruiter U1. "Recruiter" refers to a person who seeks labor and recruits personnel, and includes organizations or their personnel, such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.). Here, the person in charge may also be called a recruitment officer, and may include personnel in the human resources department of an organization or personnel in the department that intends to recruit personnel. Furthermore, recruiters also include recruitment agencies and personnel placement agencies that act as intermediaries between job seekers and recruiters. Recruitment agencies and personnel placement agencies may also be called headhunters, agents, etc. In this specification, "recruiter" also includes agents who perform recruitment work on behalf of the recruiter (RPO (Recruitment Process Outsourcing) operators, outsourcing partners, etc.). The reception unit 231 treats input by the recruiter themselves and input by agents equally, and in either case processes them as setting of standard personnel information and recruitment-related information.

[0022] Figure 3 is a block diagram showing the hardware configuration of the recruiter terminal 3. The recruiter terminal 3 comprises a communication unit 31, a storage unit 32, a control unit 33, a display unit 34, and an input unit 35, and these components are electrically connected within the recruiter terminal 3 via a communication bus 30. Each component will be described further. The descriptions of the communication unit 31, storage unit 32, and control unit 33 are the same as the descriptions of each part in server 2, so they will be omitted.

[0023] The display unit 34 may be included in the housing of the job seeker terminal 3, or it may be an external component. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. Preferably, this is done by using a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display, depending on the type of job seeker terminal 3.

[0024] The display unit 34 displays the screen indicated by the screen data transmitted from the server 2. The display unit 34 displays the system screen related to the information processing system 1 indicated by the screen data transmitted from the server 2.

[0025] The input unit 35 may be included in the housing of the job seeker terminal 3, or it may be an external component. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. If it is a touch panel, the user can input tap operations, swipe operations, etc. Of course, a switch button, mouse, QWERTY keyboard, etc. may be used instead of a touch panel. In other words, the input unit 35 receives operation input made by the user. This input is transmitted as a command signal to the control unit 33 via the communication bus 30, and the control unit 33 can perform predetermined controls and calculations as needed.

[0026] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory unit 22 is specifically realized by the control unit 23, which is an example of hardware, and can be executed as each functional unit included in the control unit 23 (at least one processor provided by the information processing system 1).

[0027] Figure 4 is a block diagram showing the functions realized by Server 2 (control unit 23) and Job Seeker Terminal 3 (control unit 33).

[0028] Figure 4A is a block diagram showing the functions implemented by the control unit 23. As shown in Figure 4A, the control unit 23 includes a reception unit 231, a generation unit 232, an output unit 233, an extraction unit 234, an aggregation unit 235, an acquisition unit 236, a specific unit 237, a presentation unit 238, an execution unit 239, a detection unit 240, a modification unit 241, and an artificial intelligence unit 242.

[0029] As shown in Figure 4B, the job seeker terminal 3 (control unit 33) includes a display unit 331 and an operation acquisition unit 332.

[0030] <Reception Desk 231> The reception unit 231 is configured to receive information from the job seeker terminal 3 or other information processing terminals. The reception unit 231 is also configured to receive various types of information by reading various types of information stored in the storage area, which is at least a part of the memory unit 22, and writing the read information to the work area, which is at least a part of the memory unit 22. The storage area is, for example, the area of ​​the memory unit 22 that is implemented as a storage device such as an SSD. The work area is, for example, the area that is implemented as memory such as RAM.

[0031] (First registration step) The reception unit 231 accepts input of standard personnel information as the first reception step. Standard personnel information is information about a person that serves as a standard for generating job-related information, and includes, for example, at least one of the profile information of a specific person and the persona information of an ideal person. Profile information includes information such as the attributes of a real person that serves as the standard, gender, age, year of joining the company, department, employment type, length of service, work location, job type, position, career history, grade, affiliation history, transfer history, skills, qualifications, role, expected results, years of experience, industries experienced, job types experienced, performance evaluation, behavioral characteristics / competencies, personality, etc. Profile information may also be the work history information of a specific job seeker or the personnel information of a specific employee. Persona information is information about the ideal person as envisioned by the employer U1. The reception unit 231 can accept one (one person) or multiple (multiple people) of standard personnel information.

[0032] The reception unit 231 may, as a first reception step, receive job seeker identification information that uniquely identifies a specific job seeker as profile information. "Job seeker" includes various persons who wish to find employment or work, such as job seekers, recent graduates (job seekers), and may also include persons who are currently engaged in job-seeking activities or are interested in job-seeking activities. Job seeker identification information is, for example, key information for uniquely referencing a job seeker's registration information in the job seeker database, and may include a system internal ID, membership number, job seeker ID, resume ID, external service linkage ID, email address, or resume URI. The reception unit 231 causes the acquisition unit 236 to acquire the job seeker's registration information corresponding to the job seeker identification information, and to acquire said registration information as profile information. Here, the reception unit 231 may, in particular, cause the acquisition unit 236 to acquire work history information included in the job seeker's registration information, and to acquire said work history information as profile information.

[0033] In this specification, "job seeker database" means a database in which registration information about job seekers is recorded. Here, "registration information" may include the job seeker's resume, work history, other profile information, the conditions such as the industry or occupation the job seeker desires, and related information, and may also include information about their work history (work history information).

[0034] The reception unit 231 may, as a first reception step, receive employee identification information as profile information, which uniquely identifies a specific employee belonging to the same organization as the recruiter. Here, a certain group of companies (groups) consisting of subsidiaries, affiliates, group companies, etc., may also be included as an example of an "organization" in this embodiment. "Employee" refers to a person who engages in the business of the organization, regardless of employment type (employee, contract worker, dispatched worker, officer, on-site employee, etc.). Employee identification information is, for example, key information for uniquely referencing employee registration information in the employee database, and may include employee number, personnel ID, email address, company directory ID, etc. The reception unit 231 causes the acquisition unit 236 to acquire the employee's personnel information corresponding to the employee identification information, and to acquire the employee's personnel information as profile information. Here, the reception unit 231 may, in particular, cause the acquisition unit 236 to acquire the work history information included in the employee's personnel information, and to acquire the work history information as profile information.

[0035] In this specification, "employee database" refers to a general term for databases that hold employee personnel and job information. When the reception unit 231 receives employee identification information, it retrieves at least a portion of the personnel information from the employee database via the acquisition unit 236 and accepts the said personnel information as standard personnel information.

[0036] "Personnel information" may include information about an employee's attributes, such as name, gender, age, years of service, year of joining the company, employee code, contact information, department, employment type, length of service, work location, job title, position history, grade, department history, transfer history, skills, qualifications, goals and evaluations, recruitment information (resume, offered position, annual salary, recruitment evaluation, aptitude test results, reference check information, etc.), post-employment information (condition, engagement indicators, aptitude, personality, interview history, attendance information, etc.), and other similar information, and may also include information about work history (work history information). Employee identification information is independent of job seeker identification information, but a correspondence between the two (e.g., a linked table) for the same person may be maintained.

[0037] As a first reception step, the reception unit 231 may receive registration information or personnel information as profile information for one or more job seekers or employees selected by the employer U1 as personnel of interest (e.g., personnel of interest) from among the job seekers or employees searched or viewed on the screen. For example, employer U1 can register job seekers or employees of interest as candidates or as "favorites," thereby specifying the information of the registered job seekers or employees as profile information. The reception unit 231 may also receive evaluations from employer U1 (e.g., evaluation categories A, B, C) for each job seeker or employee registered as a candidate. In this case, the acquisition unit 236 can extract registration information or personnel information for job seekers or employees corresponding to a predetermined evaluation (e.g., evaluation A), and acquire standard personnel information based on the extracted registration information or personnel information. This allows employer U1 to easily set standard personnel information based on personnel of interest or personnel of high value.

[0038] The reception unit 231, as the first reception step, receives input of a persona profile from the employer. Persona information is, for example, information about the ideal person the employer is looking for. Persona information may include keywords or sentences that represent the ideal person, and may be written in natural language. Persona information is, for example, information about the ideal person as envisioned by employer U1, and for example, information about the type of person employer U1 wants to hire. The persona profile may include information about the attributes of the person, and may include at least some of the following: gender, age, year of joining the company, department, employment type, length of service, work location, job type, position, career history, grade, affiliation history, transfer history, skills, qualifications, role, expected results, years of experience, industries experienced, job types experienced, performance evaluation, behavioral characteristics / competencies, personality, etc.

[0039] (Second registration step) The reception unit 231, as the second reception step, presents the extracted characteristic information to the job seeker and receives input from the job seeker regarding acceptance / rejection or priority of the characteristic information. Here, "characteristic information" refers to elements such as personality, attributes, skills, industry, job type, role, years of experience, degree, qualifications, and performance indicators extracted from one or more standard personnel information. "Acceptance / rejection" refers to inputting whether or not to use each characteristic information for generating job-related information, and "priority" refers to inputting a level (e.g., high, medium, low) or numerical value (0 to 1, etc.) that represents the weight given to each characteristic information when using it for generating job-related information. The reception unit 231 passes the acceptance / rejection and priority input results to the aggregation unit 235.

[0040] (Third registration step) The reception unit 231 accepts existing job postings and / or existing scouting documents as the third reception step. Here, "existing job postings" refers to job postings that have been created, published, or stored in the past. The reception unit 231 may accept existing job postings and / or existing scouting documents in various ways, such as files, HTML, or template IDs. "Existing scouting documents" refers, for example, to scouting documents that have been created, published, or stored in the past, or templates such as subject, body, resend subject, and resend body saved for sending scouting messages.

[0041] (Fourth registration step) As a fourth reception step, the reception unit 231 receives input from the employer indicating whether or not the generated job-related information should be used. The input indicating whether or not to use the information includes at least "use" and "do not use". If the reception unit 231 receives "use", it issues a trigger to the execution unit 239 that enables it to execute at least one of the following: publishing the job posting, using or sending a scouting document, or searching for job seekers based on the job seeker search criteria.

[0042] <Generation unit 232> The generation unit 232 generates job-related information based on standard personnel information and first reference information. The generation unit 232 can generate job-related information using registration information and personnel information corresponding to the standard personnel information. The job-related information includes job posting JP, job seeker search conditions CQ, and scout document SM. This allows the job posting JP, job seeker search conditions CQ, and scout document SM to be generated together based on information such as the type of personnel the employer wants.

[0043] A Job Posting JP is a document that shows the details of a job posting presented to job seekers. Figure 5 shows Screen G1, which is an example of a screen that presents the generated Job Posting JP to the employer U1. Screen G1 includes multiple areas G11 to G15 that display the contents of the job posting, and buttons G16 to G18. The following describes an example of the configuration of each area. Note that the configuration of Screen G1 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate depending on the specifications of the system or service that posts the job, the specifications of the job posting, or the template of the job posting.

[0044] Area G11 is the area that displays the job title, which will be the heading of the job posting JP. Area G12 is the area that displays the company profile. Area G12 displays the company name, industry, capital, establishment date, number of employees, location, business description, etc. Area G13 is the area that displays the job details. Area G13 displays the job title, employment type, job description, required experience / skills, number of hires, position, etc. Area G14 is the area that displays the terms and conditions of employment. Area G14 displays the salary type, salary amount, various allowances, insurance coverage, working hours, overtime, holidays, leave, work location, nearest station, etc. Area G15 is the area that displays the estimated annual salary. Area G15 displays the estimated annual salary range or upper / lower limit, etc. Button G16 is a button that instructs the regeneration of the job posting JP based on the standard personnel information and reference information. When pressed, a revised proposal based on the results of the previous generation may be made. Button G17 is a button that instructs the user to switch to edit mode, which allows the job seeker U1 to manually modify the displayed items. Button G18 is a button that instructs the user to confirm the job posting JP and make it available for use.

[0045] Figure 6 shows Screen G2, an example of a screen that presents the generated search conditions CQ to the employer U1. Screen G2 includes multiple areas G21 to G24 that display the content of the search conditions, and buttons G25 to G27. The following describes an example of the configuration of each area. Note that the configuration of Screen G2 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate depending on the specifications of the system or service used to search for job seekers, the specifications of the search conditions in the job seeker database, or the item structure of the job seeker database.

[0046] Area G21 is the area that displays a heading indicating that this screen is a screen for presenting job seeker search criteria. Area G22 is the area that displays the search criteria corresponding to "Item: 'Job Title'". Examples of job title categories that can be displayed in Area G22 include "Management, Accounting, Human Resources > Human Resources > Human Resources Development, Training, and Development", "Management, Accounting, Human Resources > Human Resources > Recruitment", and "Management, Accounting, Human Resources > Human Resources > Labor and Payroll". Area G23 is the heading area that displays the search criteria corresponding to "Item: 'Industry'". Area G24 is the area that displays specific search criteria related to industry, such as "Manufacturers, Trading Companies > Manufacturers > Electrical and Electronics", and "Manufacturers, Trading Companies > Manufacturers > Automobiles and Auto Parts". Button G25 is a button that instructs the regeneration of search criteria CQ based on standard personnel information and reference information. Button G26 is a button that instructs the user to switch to edit mode, which allows the employer U1 to manually modify each displayed item. Button G27 is a button that instructs the user to confirm the use of the search condition CQ.

[0047] In this specification, "search condition CQ" refers to a set of conditions (including a single condition or a combination of conditions) consisting of one or more search items (age, work location, skills, etc.) used to search for and extract job seekers registered in a job seeker database, and may also be called a search query. A search condition CQ is expressed in a normalized form, for example, in the item specifications (field definitions) and operator specifications (comparison, logical, range, set operations, etc.) of a job seeker database, and may include field names, operators, values, logical connectives (AND / OR / NOT), sorting order, and control parameters such as the number of results to retrieve.

[0048] The items that make up the search condition CQ include, for example, job title, industry, skills, qualifications, years of experience, position, educational background, work location, annual income, keywords, etc. The generation unit 232 generates the job seeker search condition CQ as a query normalized from the standard personnel information to the items and operator specifications of the job seeker database, etc. The generation unit 232 may, for example, perform processing such as (i) term normalization (integration of variations in notation and synonyms), (ii) category estimation (hierarchical assignment of job titles and industries), (iii) extraction of numerical values ​​and ranges (years of experience, annual income, etc.), (iv) negation / priority determination (exclusion conditions and mandatory conditions), and (v) mapping to the search condition specifications of the job seeker database, etc. (formatting of field names, operators, and values) to generate the search condition CQ as a query normalized to the items and operator specifications of the job seeker database, etc., based on the standard personnel information, vocabulary dictionary, category / tag mapping, media item and operator specifications, templates, etc. This allows for the automatic generation of search criteria (CQs) that are consistent with job-related information, thereby improving the efficiency and accuracy of job seeker searches.

[0049] Figure 7 shows screen G3, an example of a screen that presents the generated scout document SM to the recruiter U1. Screen G3 includes multiple areas G31 to G34 that display the contents of the scout document, and buttons G35 to G37. The following describes an example of the configuration of each area. Note that the configuration of screen G3 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate depending on the specifications of the system or service that creates or sends the scout document, the specifications of the scout document, or the scout sending template.

[0050] Area G31 displays the subject line of the recruitment letter used when sending it to a job seeker for the first time (initial transmission). Area G32 displays the body of the recruitment letter used for the initial transmission. Area G33 displays the subject line of the recruitment letter used when resending it to a job seeker if no reply is received (resending). Area G34 displays the body of the recruitment letter used for resending. By displaying the subject line and body for the initial transmission and the resend separately, and creating or editing them individually, it becomes easier to optimize the wording to increase open rates and reply rates.

[0051] Button G35 is a button that instructs the system to regenerate the scout document SM based on the standard personnel information and reference information. When the reception unit 231 receives a press of button G35, the generation unit 232 regenerates the scout document SM. After the press of button G35, the reception unit 231 may receive feedback from the recruiter U1 regarding the displayed scout document SM and any points to be corrected during regeneration. In that case, the generation unit 232 may generate a scout document SM that reflects the received feedback and points to be corrected. Button G36 is a button that instructs the system to transition to an edit mode in which the recruiter U1 can manually correct each item currently displayed. Button G37 is a button that instructs the system to confirm the scout document SM to make it usable. After confirmation, it is stored as a template for the scout message and may be recalled and used when creating and sending scout documents to job seekers.

[0052] In this specification, "Scout Document SM" refers to the data of a scout message sent by employer U1 to a job seeker. A Scout Document SM consists of at least a subject and a body. The generation unit 232 generates the subject and body of the Scout Document SM to be used for the initial transmission, and the subject and body of the Scout Document SM to be used for resending. The generation unit 232 generates the content of the subject and body for the initial transmission and resending based, for example, on standard personnel information, job posting JP, vocabulary dictionary, template, specifications for the scout document, tone instructions, etc. The generation unit 232 may also generate a Scout Document SM by modifying part or all of an existing Scout Document received from employer U1. The Scout Document SM may also be generated according to predetermined rules such as character count and prohibited words. By automatically generating scouting documents (SM), this improves consistency with job-related information and contributes to increased efficiency and improved quality in creating and sending scouting messages by recruiters (U1).

[0053] The generation unit 232 generates job-related information based on standard personnel information and first reference information. The first reference information includes at least the correlation between the standard personnel information and the job-related information. The first reference information is stored, for example, in the storage unit 22. The first reference information may include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the standard personnel information and the job-related information. The correlation included in the first reference information can be constructed by analyzing data including standard personnel information and the corresponding job-related information using statistical methods or machine learning methods.

[0054] The first reference information may include a set of parameters for generating job-related information from standard personnel information. For example, the first reference information may be various pre-trained models. The first reference information may include various pre-trained models (hereinafter referred to as job-related information generation models) that have been machine-trained to take standard personnel information as input and output job-related information. In this case, the generation unit 232 inputs the standard personnel information into the job-related information generation model and causes the job-related information generation model to output job-related information.

[0055] The job-related information generation model is included in the artificial intelligence unit 242. If the job-related information generation model is a dedicated learning model, it may be constructed by, for example, learning using standard personnel information data and corresponding job-related information data as training data. In such a job-related information generation model, parameters calculated or tuned through learning establish a correlation between standard personnel information and job-related information. The dedicated learning model may include a generative AI capable of generating job-related information not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0056] If the job-related information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the job-related information generation model that includes reference personnel information and instructions to output job-related information corresponding to the reference personnel information, causing the job-related information generation model to output job-related information. The generation unit 232 may also generate a prompt that includes instructions to create job-related information and input this prompt to the job-related information generation model. In addition to instructions to create and output reference personnel information and job-related information, the generation unit 232 may also input a prompt to the job-related information generation model that includes, for example, one or more samples of reference personnel information and one or more samples of corresponding job-related information as examples or samples of input and output pairs, or, for example, one or more samples of reference personnel information and one or more samples of corresponding job-related information as training data. In this case, a correlation between reference personnel information and job-related information is constructed by the parameters constituting the job-related information generation model and the prompt that includes instructions to output job-related information corresponding to the reference personnel information. Furthermore, a general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. The generative AI in a general-purpose learning model is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0057] The generation unit 232 may generate job-related information based on the extracted feature information and the first reference information. In this case, the first reference information may be configured to take the feature information as input and output the item values ​​of the job posting JP, the search expression for the job seeker search condition CQ, and the descriptive elements of the scout document SM.

[0058] The generation unit 232 may input standard personnel information and existing job postings and / or existing scout documents into the first reference information to generate job-related information. This makes it possible to generate job-related information that takes into account the content and writing style of existing job postings and / or existing scout documents. Existing job postings and existing scout documents may include, for example, text, templates, terminology preferences, tone and manner, etc., that the recruiter has created, used, or saved in the past. The resulting job-related information may be a job posting JP and / or scout document SM that are all or part of the existing job posting and / or existing scout document modified. The first reference information may include differential generation and rewriting rules (prohibited words, recommended words, fixed expressions) for text, etc., that have been created, used, or saved in the past, as well as generation based on existing text (terminology dictionary, paraphrase dictionary, section template). When using a generation AI, the generation unit 232 may assign previously created, used, or saved texts as prompt examples or system constraints, and optimize the text while maintaining its conformance to the standard personnel information.

[0059] The generation unit 232 generates a job posting JP based on the standard personnel information and the second reference information. The second reference information includes at least the correlation between the standard personnel information and the job posting JP. The second reference information is stored, for example, in the storage unit 22. The second reference information may include, for example, a table, a function, a simple algorithm, etc., that shows the correlation between the standard personnel information and the job posting. The correlation included in the second reference information can be constructed, for example, by statistically analyzing data that records the standard personnel information and the corresponding job posting.

[0060] The second reference information may include a set of parameters for generating job postings from standard personnel information. For example, the second reference information may be various pre-trained models. For example, the second reference information may include a job posting generation model which is a dedicated training model or a general-purpose training model that has been machine-trained to take standard personnel information as input and output job postings. In this case, the generation unit 232 inputs the standard personnel information into the job posting generation model and causes the job posting generation model to output job postings.

[0061] The job posting generation model is included in the artificial intelligence unit 242. The job posting generation model, which is a dedicated learning model, may be constructed, for example, by training with standard personnel information data and corresponding job posting data as training data. In such a job posting generation model, parameters calculated and tuned through learning construct a correlation between standard personnel information and job postings. The dedicated learning model may include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0062] If the job posting generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 inputs a prompt to the job posting generation model that includes reference personnel information and an instruction to output a job posting corresponding to the reference personnel information, causing the job posting generation model to output a job posting. The generation unit 232 may also generate a prompt that gives the job posting generation model an instruction to create a job posting and input this prompt to the job posting generation model. In addition to the reference personnel information and the job posting creation / output instruction, the generation unit 232 may also input a prompt to the job posting generation model that includes, for example, one or more samples of reference personnel information and one or more samples of corresponding job postings as examples, samples, or training data of input and output pairs. Here, the parameters that construct the job posting generation model and the prompt that includes an instruction to output a job posting corresponding to the reference personnel information construct a correlation between the reference personnel information and the job posting. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. Generative AI for general-purpose learning models is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0063] The generation unit 232 generates job seeker search conditions CQ and scout document SM based on the standard personnel information, the generated job posting JP, and the third reference information. By generating job-related information in this stepwise manner, the job seeker search conditions CQ and scout document SM can be generated based on the content of the generated job posting JP, thereby improving the consistency of this job-related information. The third reference information includes at least the correlation between the standard personnel information and the job posting JP and the job seeker search conditions CQ and scout document SM. The generation unit 232 may also present the job posting JP to the employer, receive a judgment input from the employer indicating that it is usable, and then generate the job seeker search conditions CQ and scout document SM based on the standard personnel information, the job posting JP, and the third reference information.

[0064] The third reference information is information regarding the correlation between standard personnel information and generated job postings, and job seeker search conditions and scouting documents. The third reference information is stored, for example, in the memory unit 22. The third reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between standard personnel information and generated job postings and job seeker search conditions and scouting documents. The correlations included in the third reference information can be constructed, for example, by statistically analyzing data that records standard personnel information and generated job postings and the corresponding job seeker search conditions and scouting documents.

[0065] The third reference information may include a set of parameters for generating job seeker search conditions and scouting documents from standard personnel information and generated job postings. For example, the third reference information may be various pre-trained models. For example, the third reference information may include a job seeker search condition generation model, which is either a dedicated learning model or a general-purpose learning model, that has been machine-trained to take standard personnel information and generated job postings as input and output job seeker search conditions and scouting documents. In this case, the generation unit 232 inputs the standard personnel information and generated job postings into the job seeker search condition generation model and causes the job seeker search condition generation model to output job seeker search conditions and scouting documents.

[0066] The job seeker search condition generation model is included in the artificial intelligence unit 242. The job seeker search condition generation model, which is a dedicated learning model, may be constructed by training using, for example, data of standard personnel information and generated job postings, and data of corresponding job seeker search conditions and scout documents as training data. In such a job seeker search condition generation model, parameters calculated and tuned through learning construct a correlation between the standard personnel information and generated job postings and the job seeker search conditions and scout documents. The dedicated learning model may include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0067] If the job seeker search condition generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 inputs a prompt to the job seeker search condition generation model that includes standard personnel information and a generated job posting, and an instruction to output job seeker search conditions and a scout document corresponding to the standard personnel information and the generated job posting, causing the job seeker search condition generation model to output the job seeker search conditions and the scout document. The generation unit 232 may also generate a prompt that gives an instruction to the job seeker search condition generation model to create job seeker search conditions and a scout document, and input this prompt to the job seeker search condition generation model. Furthermore, in addition to the instructions for creating and outputting standard personnel information, generated job postings, job seeker search conditions, and scout documents, the generation unit 232 may also input prompts to the job seeker search condition generation model that include, for example, one or more samples of standard personnel information and generated job postings, and one or more samples of corresponding job seeker search conditions and scout documents, as examples, samples, or training data of input and output pairs. Here, the parameters for constructing the job seeker search condition generation model and prompts that include instructions to output job seeker search conditions and scout documents corresponding to the standard personnel information and generated job postings establish a correlation between the standard personnel information and generated job postings and the job seeker search conditions and scout documents. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input of instructions such as the content of the output information to be generated and the content of the task to be performed.

[0068] The generation unit 232 may first generate a job posting JP (based on the second reference information), present the job posting JP to the employer, and after receiving input indicating whether it is usable, generate job seeker search conditions CQ and scout documents SM based on the standard personnel information, the job posting JP, and the third reference information. When using a generation AI, the generation unit 232 may add operator specifications, prohibited words, vocabulary dictionaries, and templates of the services used and the job seeker database as constraints to the prompt, and control it to obtain output that conforms to a predetermined format and item system.

[0069] <Output section 233> The output unit 233 outputs the generated job posting JP, job seeker search conditions CQ, and scout document SM. The output unit 233 presents the job posting JP as screen G1, the job seeker search conditions CQ as screen G2, and the scout document SM as screen G3 to the employer's terminal. This allows the employer to view the generated results and perform operations such as regeneration, editing, and confirmation.

[0070] <Extraction part 234> The extraction unit 234 extracts characteristic information from the one or more standard personnel information received. "Characteristic information" is information extracted based on attributes, gender, age, year of joining the company, department, employment type, length of service, work location, job type, position, career history, grade, affiliation history, transfer history, skills, qualifications, role, expected results, years of experience, industries experienced, job types experienced, performance evaluation, behavioral characteristics / competencies, personality, etc., included in the standard personnel information, in order to contribute to the generation of job-related information.

[0071] The extraction unit 234 extracts information common to multiple standard personnel information and / or information contained in any of them as feature information. Specifically, the extraction unit 234 extracts information common to multiple standard personnel information as feature information. The extraction unit 234 may also extract job titles, industries, skills, etc. that appear in common to multiple standard personnel information. In addition, the extraction unit 234 may extract information contained in any of the multiple standard personnel information as feature information. Furthermore, the extraction unit 234 may perform duplicate removal, synonym consolidation, hierarchical relationship resolution, etc., on each extracted piece of information. In addition, the extraction unit 234 may combine information common to multiple standard personnel information and information contained in only one of them to extract feature information.

[0072] The extraction unit 234 may extract feature information using reference information, which may include, for example, tables, functions, simple algorithms, etc., that show the correlation between standard personnel information and feature information. The reference information may also include a set of parameters for generating feature information from standard personnel information, which may be, for example, various pre-trained models. For example, the reference information may include a feature information extraction model that is a dedicated learning model or a general-purpose learning model that has been machine-trained to take multiple standard personnel information as input and output feature information. In this case, the extraction unit 234 inputs multiple standard personnel information into the pre-trained model and outputs feature information. For example, pre-trained language models, named entity recognition models, text classification models, etc., can be applied to extract feature information such as skills from the description text of registration information, estimate the role of work content, and cluster competency. The extraction unit 234 may perform rule-based post-processing (prohibited word removal, acceptance word list fitting, threshold determination) on the output of the model to create a final feature information list.

[0073] The feature information extraction model is included in the artificial intelligence unit 242. The feature information extraction model, which is a dedicated learning model, may be constructed, for example, by training with multiple reference personnel information and corresponding feature information data as training data. In such a feature information extraction model, parameters calculated and tuned through learning construct a correlation between multiple reference personnel information and feature information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0074] If the feature information extraction model is a general-purpose learning model (for example, a language model such as a large-scale language model), the extraction unit 234 inputs a prompt to the feature information extraction model that includes multiple reference personnel information and an instruction to output feature information using the multiple reference personnel information as input, causing the feature information extraction model to output feature information. The extraction unit 234 may also generate a prompt that gives an instruction to the feature information extraction model to extract feature information and input this prompt to the feature information extraction model. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input of instructions such as the content of the output information to be generated and the content of the task to be executed.

[0075] The extraction unit 234 may store the extraction results in the storage unit 22 as a record including the item name, value, confidence level, and source (which part of which standard personnel information the results were extracted from). The extraction unit 234 may also pass the extraction results to the reception unit 231 for the employer to input their decision to accept or reject or their priority in the second reception step.

[0076] <Aggregation section 235> The aggregation unit 235 aggregates the characteristic information according to the input of acceptance / rejection or priority. In the aggregation unit 235, "aggregation" refers to the process of reflecting the acceptance / rejection input of job seekers (e.g., accepted / not accepted / held) and priority input (e.g., required / recommended / reference, or numerical weight) for each characteristic information received by the reception unit 231, and organizing it into a format usable by the generation unit 232. The process of organizing into a usable format may include aggregation processing that includes at least one of the following: (i) selection of characteristic information based on acceptance / rejection, (ii) assignment of weights based on priority, (iii) logical classification of common (AND) / inclusion (OR) / exclusion (NOT), (iv) integration of duplicates and synonyms, and (v) assignment of sources and evidence.

[0077] <Acquisition part 236> The acquisition unit 236 is configured to acquire information from the job seeker terminal 3 or other devices. Furthermore, the acquisition unit 236 is configured to acquire various types of information by reading various types of information stored in the storage area, which is at least a part of the memory unit 22, and writing the read information to the work area, which is at least a part of the memory unit 22. The storage area is, for example, the area of ​​the memory unit 22 that functions as a storage device such as an SSD. The work area is, for example, the area that functions as memory such as RAM. The acquisition unit 236 connects to various external and internal information sources to acquire profile information, receive document files, and acquire data via APIs.

[0078] The acquisition unit 236 acquires the job history information of job seekers registered in the job seeker database using the job seeker identification information. The job seeker identification information is associated with the job seeker's job history information, and the reception unit 231 can acquire the job seeker's job history information based on the job seeker identification information by accepting the input of the job seeker identification information. The acquisition unit 236 searches and acquires the job history information corresponding to the job seeker identification information from the job seeker database using the job seeker identification information (system internal ID, external service linkage ID, etc.) as the primary key or alternate key. In addition, when the reception unit 231 accepts the input of job seeker identification information, it may have the acquisition unit 236 acquire the registration information of the job seeker corresponding to the job seeker identification information from the job seeker database and acquire said registration information as standard personnel information. Here, the acquisition unit 236 may, in particular, acquire the job history information included in said registration information as the job seeker's job history information and acquire said job history information as part of the standard personnel information.

[0079] In this specification, “Work History Information” means information representing the past work history of a job seeker or employee. Here, Work History Information may include information representing the content of the duties performed, the position held, the organization or department in which the employee was employed, the period of employment, the projects the employee was assigned to, the qualifications obtained, the skills held, performance indicators, and other information representing work-related experience, and may be obtained based on information recorded in a resume, work history document, or employee database in a human resources management system.

[0080] The acquisition unit 236 acquires personnel information of a specific employee registered in the employee database using employee identification information. The acquisition unit 236 acquires personnel information from the employee database using employee identification information as a key. If the same person exists in both the job seeker database and the employee database, the acquisition unit 236 may associate them using a link table or matching rules (name, date of birth, email hash, etc.). The reception unit 231 accepts the acquired personnel information as standard personnel information and passes it on to the extraction unit 234 and the aggregation unit 235.

[0081] <Specific part 237> The identification unit 237 is configured to identify job seekers or employees similar to the input personnel profile. The identification unit 237 identifies specific employees belonging to the same organization as job seekers or employers similar to the input personnel profile from the job seeker database or employee database. The identification unit 237 may identify multiple job seekers from the job seeker database or employee database. The identification unit 237 normalizes the free description of the input personnel profile and generates search conditions that map it to attributes such as job type, industry, skills, years of experience, and work location. The identification unit 237 may then perform at least one of (i) a conditional search based on attribute matching and (ii) a similarity search based on document vectors or embedding representations using the generated search conditions, and integrate the results to obtain a candidate set. The identification unit 237 may perform duplicate mergers, filtering based on business constraints such as employment type and work location, and exclusion of unreliable records on the acquired candidate set, and then rank the top multiple candidates based on relevance indicators (similarity score, number of attribute matches, etc.) to extract them as identification results.

[0082] <Presentation part 238> The display unit 238 is configured to display various information to the job seeker terminal 3 or other devices.

[0083] (First presentation step) As a first presentation step, the presentation unit 238 presents information on multiple identified job seekers or employees to the employer in a selectable format. The presentation unit 238 displays the information on job seekers or employees in a list format, either as cards or tables. The presentation unit 238 may also visually present the information on job seekers or employees, including identification information, a summary of their work history, skills, location, desired conditions (if any), suitability indicators such as similarity scores, and the basis for identification (such as highlighting corresponding characteristic information). The presentation unit 238 presents information on two or more job seekers or employees in a selectable format. The presentation unit 238 records the result of the employer's selection operation (selected, not selected, or held) and passes the registration information (or work history information) or personnel information of the selected job seekers or employees to the generation unit 232 as standard personnel information.

[0084] (Second presentation step) The presentation unit 238, as a second presentation step, presents the generated job-related information to the employer. The presentation unit 238 may display the job-related information in three tabs or sections: Job Posting JP, Job Seeker Search Criteria CQ, and Scout Document SM. The presentation unit 238 visually displays each item of the Job Posting JP, the query of the Job Seeker Search Criteria CQ, and the subject and body (first / re-send) of the Scout Document SM.

[0085] <Execution Section 239> The execution unit 239, upon receiving confirmation from the employer that the generated job-related information is usable, enables the execution of one of the following: publishing the job posting JP to job seekers, sending the scout document SM to job seekers, or searching for job seekers using the job seeker search criteria CQ.

[0086] "Disclosure of Job Postings JP to Job Seekers" refers to the act of posting and distributing Job Postings JP to designated media so that job seekers can view them. Specific examples may include: (i) posting on the company's website (e.g., recruitment website), (ii) posting on job posting / recruitment systems, job posting media, ATS (Applicant Tracking System), employee management systems with job posting functions, etc., via API integration, (iii) posting on the company's internal portal referral (e.g., internal job posting), and (iv) generating and sharing a public URL.

[0087] "Sending a recruitment letter SM to a job seeker" refers to the act of delivering a recruitment letter SM (including the subject and body for the initial transmission and the subject and body for subsequent transmissions) to a designated job seeker via electronic means. Specific examples may include (i) sending an email, (ii) sending via the messaging function of an external service, and (iii) sending an in-app notification.

[0088] "Searching for job seekers using job seeker search criteria CQ" refers to the act of normalizing the job seeker search criteria CQ according to the specifications of the system service used for the search, the items and operator specifications of the job seeker database, etc., and then performing a search to extract a set of job seekers that meet the criteria.

[0089] <Detection unit 240> The detection unit 240 inputs the generated job posting JP, job seeker search conditions CQ, and scout document SM into the fourth reference information, and uses the fourth reference information to detect inconsistencies or contradictions between the job posting JP, job seeker search conditions CQ, and scout document SM. The fourth reference information includes a machine learning model or generating AI that is capable of taking the job posting JP, job seeker search conditions CQ, and scout document SM as input and outputting detection results.

[0090] The fourth reference information includes the correlation between the job posting JP, the job seeker search criteria CQ, and the scout document SM, and the consistency (or inconsistency) between the three. The fourth reference information is information regarding the correlation between the job posting, the job seeker search criteria, and the scout document, and the information regarding the consistency between these three. The fourth reference information is stored, for example, in the memory unit 22. The fourth reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between the job posting, the job seeker search criteria, and the scout document, and the information regarding the consistency between these three. The correlations included in the fourth reference information can be constructed, for example, by statistically analyzing data that records the information regarding the consistency between the job posting, the job seeker search criteria, and the scout document.

[0091] The fourth reference information may include a set of parameters for generating information regarding the consistency between the three elements from the job posting, the job seeker search criteria, and the scouting document. For example, the fourth reference information may be various pre-trained models. For example, the fourth reference information may include a mismatch detection model, which is either a dedicated learning model or a general-purpose learning model that has been machine-trained to take the job posting, the job seeker search criteria, and the scouting document as input and output information regarding the consistency between the three elements. In this case, the detection unit 240 inputs the job posting, the job seeker search criteria, and the scouting document into the mismatch detection model and causes the mismatch detection model to output information regarding the consistency between the three elements.

[0092] The inconsistency detection model is included in the artificial intelligence unit 242. The inconsistency detection model, which is a dedicated learning model, may be constructed by training using, for example, data of job postings, job seeker search conditions, and scouting documents, and data of information regarding the consistency between these three, as training data. In such an inconsistency detection model, parameters calculated and tuned through training construct a correlation between job postings, job seeker search conditions, and scouting documents, and the consistency between these three. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0093] If the inconsistency detection model is a general-purpose learning model (for example, a language model such as a large-scale language model), the detection unit 240 inputs a prompt to the inconsistency detection model that includes a job posting, job seeker search conditions and a scouting document, and an instruction to output information regarding the consistency between these three, taking the job posting, job seeker search conditions and the scouting document as input, causing the inconsistency detection model to output information regarding the consistency between these three. The detection unit 240 may also generate a prompt that gives the inconsistency detection model an instruction to create information regarding the consistency between the job posting, job seeker search conditions and the scouting document, and input this prompt to the inconsistency detection model. In addition, the detection unit 240 may input a prompt to the inconsistency detection model that includes, in addition to the job posting, job seeker search conditions and the scouting document and the instruction to create and output information regarding the consistency between these three, an example of one or more samples of job postings, job seeker search conditions and scouting documents and one or more samples of information regarding the consistency between these three, as examples, samples or training data of input and output pairs. Here, parameters for constructing a discrepancy detection model and prompts containing instructions to output information about the consistency between the three elements corresponding to the job posting, job seeker search criteria, and scouting document, establish a correlation between the job posting, job seeker search criteria, and scouting document and the consistency between these three elements. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0094] Correlations related to inconsistencies include, for example, the correspondence between items in the job posting JP (e.g., job title, required skills, work location, salary range, etc.), the search parameters of the job seeker search conditions CQ (e.g., Boolean join, range, geographical conditions, etc.), and the contents of the scout document SM (e.g., subject, recruitment requirements in the body, expressions of compensation, etc.), inconsistency patterns, mandatory matching rules, and constraints based on the specifications of each piece of job-related information. The fourth reference information may be stored in the memory unit 22, for example. The fourth reference information may include a table showing the correspondence between the three, a rule base (constraints, prohibited words, synonym dictionary, item mapping table), a scoring function, or a simple algorithm, etc. The correlations included in the fourth reference information can be constructed, for example, by preparing sets of job postings JP, job seeker search conditions CQ, and scout document SM that have been generated, approved, and distributed in the past, and statistically analyzing the data with notes indicating the agreement / disagreement of the three.

[0095] The fourth reference information may include a machine learning model or a generative AI-based inconsistency detection model that takes the job posting JP, job seeker search conditions CQ, and scout document SM as input and outputs detection results including the presence, type, and severity of inconsistencies. In this case, the detection unit 240 inputs the job posting JP, job seeker search conditions CQ, and scout document SM into the inconsistency detection model and causes the inconsistency detection model to output detection results. In the inconsistency detection model, parameters calculated or tuned through learning (weights, vocabulary embeddings, prompt tuning components, etc.) constitute the correlation of the fourth reference information.

[0096] The inconsistency detection model is trained using, for example, a tripartite set of a job posting (JP), a job seeker search condition (CQ), and a scout document (SM), along with corresponding consistency labels (e.g., consistency, caution, contradiction) or inconsistency type labels (e.g., requirement contradiction, condition contradiction, terminology mismatch, tone mismatch, etc.) as training data. The training data may be created based on actual operation logs, annotations by supervisors, or the results of rule-based automatic labeling. The inconsistency detection model may also be trained using multi-class classification, multi-label classification, or extraction and summarization (extraction of evidence).

[0097] If the inconsistency detection model is a generative AI that includes a general-purpose natural language model (a so-called large-scale language model), the detection unit 240 takes the job posting JP, the job seeker search conditions CQ, and the scout document SM as inputs, and prompts the model to evaluate the consistency of the three and output the detection results in a predetermined output format (e.g., a schema with elements of inconsistency type, severity, justification location, and recommended correction policy), causing the model to output the detection results. In addition to the detection instructions, the detection unit 240 may also provide a few-example prompt including examples of input-output pairs (good examples and inconsistent examples), constraint information such as specifications, prohibited words, and mandatory matching rules for each piece of job-related information, and excerpts from item mapping tables and synonym dictionaries. Furthermore, the detection unit 240 performs schema verification and lexical normalization on the output of the generative AI, formats it into a predetermined format, and outputs it as the detection result of the detection unit 240. This enables a wide range of inconsistency detection methods, including those using general-purpose models, without being limited to machine learning models.

[0098] <Correction part 241> The modification unit 241 generates proposed revisions to the job posting JP, job seeker search conditions CQ, and scout document SM based on the detection results. The modification unit 241 receives the type, severity, basis, and recommended revision policy of the inconsistencies included in the detection results, and identifies the target for revision (at least one of the job posting JP, job seeker search conditions CQ, and scout document SM) according to the recommended revision policy. After identifying the target for revision, the modification unit 241 generates specific revision content for the target and outputs it as a proposed revision. The correction unit 241 maintains as rules the priority candidates for correction (job posting JP / job seeker search conditions CQ / scout document SM) for each type of inconsistency that includes at least one of the following: (i) requirement inconsistencies (e.g., required skills, work style, employment conditions), (ii) condition inconsistencies (e.g., salary range, work location, working hours), (iii) terminology inconsistencies (e.g., variations in the spelling of job titles and skill names), and (iv) tone and expression inconsistencies (e.g., differences in tone between the job posting JP and the scout document SM). It determines the target for correction according to the severity of the detection result and the specifications of each piece of job-related information, and generates a proposed correction. In this manner, discrepancies between job postings, job seeker search conditions, and scout documents can be reduced, and inconsistencies between the information presented to job seekers and the targets actually searched for and scouted can be suppressed.

[0099] The modification unit 241 generates proposed revisions to the job posting JP, job seeker search conditions CQ, and scout document SM based on the detection results and the fifth reference information. The fifth reference information includes at least the correlation between the job posting JP, job seeker search conditions CQ, and scout document SM, the detection results, and the proposed revisions.

[0100] The fifth reference information (reference information for generating revised proposals) includes the job posting JP, job seeker search conditions CQ, and scout document SM, the detection results regarding inconsistencies between them, and the correlation between these and the revised proposals to be generated. The fifth reference information may be stored in a memory unit, for example. The fifth reference information may include, for example, tables, functions, simple algorithms, and rule sets (which may include constraints such as specifications, item systems, operator specifications, vocabulary dictionaries, and forbidden word dictionaries for each piece of job-related information) that show the correspondence between the job posting JP, job seeker search conditions CQ, scout document SM and their corresponding detection results, and their corresponding revised proposals. The correlations included in the fifth reference information can be constructed, for example, by statistically analyzing revision history data that has been confirmed and adopted in the past (pairs of original text and revised proposals, acceptance / rejection results, A / B test results, results of resolving compliance issues, etc.).

[0101] The fifth reference information may include a machine learning model or a generation AI that is capable of outputting a revised proposal, which takes the job posting JP, job seeker search conditions CQ, scout document SM, and detection results as input. In this case, the revision unit 241 inputs the job posting JP, job seeker search conditions CQ, scout document SM, and detection results into the revised proposal generation model, and causes the revised proposal generation model to output a revised proposal (either full text replacement, differential patch, or item-level revision candidate). In the revised proposal generation model, the parameters calculated or tuned through learning constitute the correlation in the fifth reference information.

[0102] The revision proposal generation model may be included in the artificial intelligence section. The revision proposal generation model is trained using, for example, (a) data from job postings JP, job seeker search conditions CQ, and scout documents SM, (b) detection results for these (type of inconsistency, relevant location, expected consistency conditions, etc.), and (c) revision proposals corresponding to the combination (the final version adopted or the editor's final draft) as training data. This enables the model to output revision proposals that resolve the detection results while conforming to the specifications, item structure, operator specifications, and vocabulary constraints of each piece of job-related information.

[0103] If the revision proposal generation model is a generative AI that includes a general-purpose natural language model (large-scale language model), the revision unit 241 takes the job posting JP, job seeker search conditions CQ, scout document SM, and detection results as input, inputs a prompt to the revision proposal generation model instructing it to output a revision proposal that resolves the inconsistency, and causes it to output a revision proposal. The revision unit 241 generates a prompt that includes revision instructions (e.g., "Comply with the specifications, item system, and operator specifications of the scout document and revise the main text in three sentences or less", "Match the job title code in the search conditions with the position in the job posting JP", "Reflect the work location and expected annual salary upper limit of the job posting JP in the scout subject", etc.), and may also input examples of input / output pairs (a few examples of original text → revised text), constraint information such as style, prohibitions, vocabulary dictionary, and template identifiers as needed. Furthermore, the modification unit 241 may include an evaluation process that generates multiple options from the model output, calculates a consistency score for each option or a compliance score for each specification of the job-related information, and selects the top option as the modified option.

[0104] <Artificial Intelligence Department 242> The artificial intelligence unit 242 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server 2 in each functional unit may be common to all units, or it may be individually prepared for each functional unit. The artificial intelligence unit 242 functions as a core module that supports the artificial intelligence processing in each of these functional units.

[0105] The artificial intelligence unit 242 may be an AI (Artificial Intelligence) equipped with pre-trained models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNNs). The artificial intelligence unit 242 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include specific models such as OpenAI's GPT, Google's Gemini, and models provided through services and platforms such as Microsoft's Azure AI Studio. Generative AI may be, for example, text generation AI, image generation AI, or multimodal generation AI. The pre-trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 242 can include any pre-trained model.

[0106] Specific machine learning algorithms used to build trained models include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 242 can apply these algorithms as appropriate.

[0107] The artificial intelligence unit 242 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. Furthermore, the trained model may not only be one trained for a specific task, but also a general-purpose learning model that can be used universally for a wide range of tasks.

[0108] The artificial intelligence unit 242 may include a natural language model as its artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large-scale data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by One-shot Learning or Few-shot Learning. Furthermore, the general-purpose learning model may also be configured to handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 23 may be a separate pre-trained model, or it may be a common general-purpose pre-trained model. In addition, the artificial intelligence unit 242 may include a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model as a pre-trained model. Small-scale and medium-scale language models are natural language processing models that are trained on less data (and constructed with fewer parameters) compared to large-scale language models.

[0109] The pre-trained models included in the artificial intelligence unit 242 (pre-trained models used in each functional unit) can undergo additional training using methods such as transfer learning and fine-tuning. For example, whenever new data is registered, the artificial intelligence unit 242 may perform additional training and fine-tuning using this new data as training data. This improves the accuracy of the information output from the pre-trained models.

[0110] The trained model included in the artificial intelligence unit 242 may be a trained model (distilled model) obtained by knowledge distillation using the original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as the teacher model, and the student model is trained by adjusting the parameters of the student model so that the loss of the student model's output (soft target loss) relative to the teacher model's output (soft target) is small, and that student model becomes the distilled model. Alternatively, the student model may be trained so that the loss of the student model's output (hard target loss) relative to the correct labels (hard target) of the teacher data (combination of input data and output data of the trained model) is small. Compared to the original trained model (teacher model), the distilled model has performance close to that of the trained model, but with fewer parameters and a lower processing load. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0111] For example, the trained model used in each functional unit may be a distilled model trained using combinations of input and output data from a large-scale language model as training data. Alternatively, when the information processing system 1 is introduced, a large-scale language model may be used as the trained model in each functional unit, and once training data from the large-scale language model has been accumulated, the distilled model obtained by knowledge distillation using that training data may be used as the trained model in each functional unit.

[0112] An AI agent (also called an autonomous agent) is a model that, upon input of a goal (objective, purpose, etc.) such as "Teach me about XX" or a task such as "Output XX," breaks down the processes necessary to reach the goal or accomplish the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, outputs information according to the goal, and does not require user intervention (operation input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously learn in order to aim for goal achievement. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.).

[0113] <Display section> The display unit 331 of the job seeker terminal 3 controls the display unit 34 to display the screen indicated by the screen data transmitted from the server 2.

[0114] <Operation acquisition part> The operation acquisition unit 332 of the recruiter terminal 3 receives operations from recruiter U1 using the recruiter terminal 3.

[0115] 3. Information Processing Flow This section describes the flow of the information processing method executed by the information processing system 1. As shown below, the information processing method comprises each step executed by the information processing system. The program of this embodiment causes the computer to execute each step of the information processing system. The order of processing can be changed as appropriate, multiple processes may be executed simultaneously, and some processes may be omitted.

[0116] 3.1 Overview Figure 8 shows an overview of the processing performed by the information processing system 1. In this processing, first, the reception unit 231 receives input of standard personnel information as the first reception step (step S001). Standard personnel information is information about personnel that serves as a standard for generating job-related information, and includes at least one of the profile information of a specific person and the persona information of an ideal person. Next, the generation unit 232 generates job-related information based on the standard personnel information and the first reference information (step S002). The job-related information includes the job posting JP, the job seeker search conditions CQ, and the scout document SM. The first reference information includes at least the correlation between the standard personnel information and the job-related information. Next, the output unit 233 outputs the generated job posting JP, the job seeker search conditions CQ, and the scout document SM (step S003).

[0117] In summary, according to one embodiment, the information processing system comprises at least one processor. The processor comprises the following parts by reading a program. The reception unit 231 receives input of reference personnel information as the first reception step. The reference personnel information is information about personnel that serves as a standard for generating job-related information, and includes at least one of the profile information of a specific person and the persona information of an ideal person. The generation unit 232 generates job-related information based on the reference personnel information and the first reference information. The job-related information includes a job posting JP, a job seeker search condition CQ, and a scout document SM. The first reference information includes at least the correlation between the reference personnel information and the job-related information. The output unit 233 outputs the generated job posting JP, job seeker search condition CQ, and scout document SM. According to this embodiment, it is possible to provide technology related to an information processing system that generates a job posting JP, a job seeker search condition CQ, and a scout document SM based on reference personnel information.

[0118] 3.2 Specific Examples The following describes an example of the processing flow performed by the information processing system 1, using Figures 9 to 11. This example of the flow may be included within the scope defined in the overview described above. Note that this information processing may include any exception handling not shown. Exception handling includes interrupting the information processing or omitting each process. The selection or input performed in this information processing may be based on user operation or may be performed automatically without user operation.

[0119] <First Embodiment> The first embodiment shows an example of the information processing flow when the information processing system 1 receives profile information of a specific employee as standard personnel information and performs a series of processes to generate job-related information.

[0120] Figure 9 is an activity diagram showing an example of the information processing flow of the first embodiment performed by the information processing system 1. The following explanation will follow each activity in this activity diagram.

[0121] First, the reception unit 231 accepts input of standard personnel information as the first reception step (Activity A101). Standard personnel information is information about personnel that serves as the basis for generating job-related information, and includes, for example, profile information of a specific person.

[0122] Figure 10 shows screen G4, which is an example of a screen for receiving input of standard personnel information. Screen G4 includes areas G41 to G43 and a button G44. The following describes an example of the configuration of each area. Note that the configuration of screen G4 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate according to the specifications of the information processing system 1 and the input template.

[0123] Area G41 is the area that displays the heading "Desired Personnel Information" to indicate that this screen is the input screen for standard personnel information. Area G42 is the area for entering the profile information of the desired personnel. The recruiter U1 (or proxy user) may enter free-form text, a summary of the resume / CV, bullet points of skills, experience, roles, achievements, etc., or pasted text from an existing resume. One entry or multiple entries are permitted.

[0124] Area G43 is the area for entering identification information of the desired personnel. Identification information includes job seeker identification information and employee identification information. Job seeker identification information includes system internal ID, resume ID, external service linkage ID, etc. Employee identification information includes employee number, personnel ID, company directory ID, etc. You may enter an identifier for one person, or you may enter multiple identifiers separated by line breaks / delimiters. If identification information is entered, the reception unit 231 may instruct the acquisition unit 236 to retrieve work history information or personnel information from the relevant database based on the entered identification information and accept it as standard personnel information. Profile information (G42) and identification information (G43) may be entered individually or in combination.

[0125] Button G44 is a button that instructs the user to confirm and submit the standard personnel information entered on this screen.

[0126] For example, employer U1 may select a specific employee A from among the employees within the same organization and input the profile information of employee A as the reference candidate. Alternatively, employer U1 may input the profile information of multiple employees A and B within the organization as reference candidates, and the reception unit 231 may accept multiple reference candidate information as reference candidate information.

[0127] Profile information may also be employee identification information of an employee. Employee identification information may include, for example, personnel information and work history information managed within the organization. Personnel information and work history information within the organization may also be information managed in an employee database, and the record numbers of employee A and employee B in the employee database may be accepted as employee identification information. In other words, as the first acceptance step, the reception unit 231 may accept, as profile information, employee identification information that uniquely identifies a specific employee belonging to the same organization as the recruiter.

[0128] Next, the acquisition unit 236 retrieves personnel information of a specific employee registered in the employee database using employee identification information (Activity A102). For example, the acquisition unit 236 retrieves personnel information for employee A and employee B.

[0129] Next, the extraction unit 234 extracts characteristic information from the received employee information (an example of standard personnel information) (Activity A103). When the extraction unit 234 extracts characteristic information from multiple employee information, the extraction unit 234 extracts information that is common to the multiple standard personnel information or information that is included in either of them as characteristic information. That is, information common to employee A and employee B may be extracted as characteristic information, or information included in either employee A or employee B may be extracted as characteristic information.

[0130] Next, the presentation unit 238 presents the extracted feature information to the job seeker U1 (Activity A104).

[0131] Next, the reception unit 231, as the second reception step, presents the extracted characteristic information to the job seeker and receives input from the job seeker regarding acceptance or rejection of the characteristic information or its priority (Activity A105).

[0132] Figure 11 shows screen G5, which is an example of a screen that accepts input regarding the acceptance or rejection or priority of feature information. Screen G5 includes area G51, areas G521 to G524, area G53, area G54, and buttons G55 to G57. An example of each configuration is described below. Note that the configuration of screen G5 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate depending on the specifications of the information processing system 1 and the extraction results.

[0133] Area G51 displays a heading indicating that the screen is for "Confirming Feature Information" and an explanatory text showing the operating procedure. The explanatory text includes a list of feature information extracted from the profile information by the extraction unit, and states that the recruiter U1 can select the features to adopt and specify the priority between the adopted features. Areas G521 to G524 are list areas that display each extracted feature information (e.g., "Feature Information A", "Feature Information B", "Feature Information C", "Feature Information D") on a row. Each row includes the content of the feature (keywords, description, source, etc.) along with areas G53 and G54. Area G53 is the area where the user selects whether to adopt or reject the feature information. Area G53 may include, for example, a "Adopt / Reject" toggle, radio buttons, or checkboxes. Area G54 is the area where the user selects the priority. Area G54 may be configured to allow selection using, for example, three levels such as "High / Medium / Low" or a numerical slider. If the acceptance / rejection status for area G53 is set to "Rejected," the priority selector for that row may be disabled (grayed out). The initial value may be an automatically suggested value based on the extraction score (e.g., Accepted = Recommended, Priority = Medium). The number of displayed rows is variable depending on the extraction results, and scrolling and paging may be supported.

[0134] Button G55 is a button that instructs the user to return to the previous screen. Button G56 is a button that instructs the user to transition to an editing screen where, in addition to making selections in the list, the user can modify, add, or delete the text of the feature information. Button G57 is a button that instructs the user to confirm the acceptance / rejection and priority specified on the current screen. When an operation is performed on button G57, the user proceeds to activity A106.

[0135] Next, the aggregation unit 235 aggregates the characteristic information according to the input of acceptance / rejection or priority (Activity A106).

[0136] Next, reception unit 231 accepts existing job postings and / or existing recruitment documents as the third reception step (Activity A107).

[0137] The generation unit 232 inputs standard personnel information and existing job postings and / or existing scout documents into the first reference information to generate job-related information. The generation unit 232 generates job postings JP, search conditions CQ, and scout documents SM as job-related information. If existing job postings JP and scout documents SM have been received in advance, the generation unit 232 generates job postings JP and scout documents SM in which the existing job postings JP and parts of the existing scout documents SM have been replaced. In other words, job postings JP and scout documents SM are job postings JP and / or scout documents SM in which all or part of the existing job postings and / or existing scout documents have been modified.

[0138] The generation unit 232 may generate the job posting JP, search criteria CQ, and scout document SM all at once, but below we will explain the process in which the generation unit 232 first generates the job posting JP, receives confirmation from the employer U1 regarding the job posting JP, and then generates the search criteria CQ and scout document SM.

[0139] The generation unit 232 generates a job posting JP based on the standard personnel information and the second reference information (Activity A108). The second reference information includes at least the correlation between the standard personnel information and the job posting JP.

[0140] Next, the presentation unit 238 presents the generated job posting JP to the employer (Activity A109).

[0141] Next, the reception unit 231 receives input from job seekers regarding their decision on whether or not the job is usable (Activity A110).

[0142] After receiving a decision input from the employer indicating whether the information is usable, the generation unit 232 generates job seeker search conditions CQ and scout document SM based on the standard personnel information, the job posting JP, and the third reference information (Activity A111). The third reference information includes at least the correlation between the standard personnel information and the job posting JP and the job seeker search conditions CQ and scout document SM. Here, the generation unit 232 generates the job seeker search conditions CQ as a query normalized to the items and operator specifications of the job seeker database. The generation unit 232 generates the subject and body of the scout document SM to be used when sending for the first time, and the subject and body of the scout document SM to be used when resending.

[0143] Next, the detection unit 240 inputs the generated job posting JP, job seeker search conditions CQ, and scout document SM into the fourth reference information, and uses the fourth reference information to detect inconsistencies between the job posting JP, job seeker search conditions CQ, and scout document SM (Activity A112). The fourth reference information includes a machine learning model or generating AI that is capable of taking the job posting JP, job seeker search conditions CQ, and scout document SM as input and outputting detection results.

[0144] Next, the modification unit 241 generates proposed revisions to the job posting JP, the scout document SM, the job seeker search conditions CQ, and the scout document SM based on the detection results (Activity A113).

[0145] Next, the presentation unit 238, as a second presentation step, presents the generated scout document SM and search conditions CQ to the recruiter U1 (Activity A114).

[0146] Next, the reception unit 231, as the fourth reception step, receives input from the job seeker regarding whether or not they can use the search criteria CQ and the scout document SM (Activity A115).

[0147] Finally, if the execution unit 239 receives a determination that it is usable, it enables the execution of one of the following: publishing the job posting JP to job seekers, sending the scout document SM to job seekers, or searching for job seekers using the job seeker search criteria CQ (Activity A116).

[0148] With the above steps completed, the processing from activity A101 to activity A116 is finished, and the series of processing flows according to this embodiment is terminated.

[0149] <Second Embodiment> The second embodiment shows an example of the information processing flow when the information processing system 1 receives persona information of an ideal candidate as standard personnel information and performs a series of processes to generate job-related information.

[0150] First, the reception desk 231, as the first reception step, accepts input of the ideal candidate profile sought by the employer as persona information (Activity A117).

[0151] Next, the identification unit 237 identifies specific employees belonging to the same organization as the job seeker or employer who are similar to the entered personnel profile, from the job seeker database or employee database (Activity A118). The identification unit 237 may identify multiple job seekers or multiple employees from the job seeker database or employee database.

[0152] Next, the presentation unit 238, as the first presentation step, presents information on multiple identified job seekers or employees to the employer in a selectable manner (Activity A119).

[0153] Next, reception desk 231 accepts the selection of job seekers or employees from employers (Activity A120).

[0154] Next, the extraction unit 234 uses the work history information or personnel information of the selected job seeker or employee as reference personnel information to extract characteristic information (Activity A121).

[0155] Next, the control unit 23 proceeds to activity A104. The flow from activity A104 onward is the same as in Embodiment 1 and is therefore omitted. With this, the processing from activity A117 to activity A121 and from activity A104 to activity A116 is completed, and the series of processing flows according to this embodiment is finished.

[0156] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0157] In this configuration, it is possible to provide technology related to an information processing system that generates job postings JP, job seeker search conditions CQ, and scout documents SM based on standard personnel information. Even if the employer U1 does not have sufficient specialized knowledge regarding the creation of job postings, the design of search conditions, or the creation of scout documents, consistent job-related information can be generated simply by inputting standard personnel information.

[0158] For example, even if an employer is unable to articulate the content or appeal of their job opening, has not properly set the recruitment requirements, or lacks the time or expertise to create or refine job postings, recruitment messages, or job seeker search criteria, the system can still generate job-related information starting from the type of talent the employer wants. Therefore, even HR departments lacking specialized knowledge about job duties or recruitment departments lacking knowledge about recruitment can create appropriate job-related information.

[0159] 4. Others In the embodiments described above, Embodiment 1 describes a case where profile information of a specific employee is received as standard personnel information, and Embodiment 2 describes a case where persona information of an ideal candidate is received as standard personnel information. However, the employer U1 may search the job seeker database in advance, extract a specific job seeker from the job seeker database, and input job seeker identification information that uniquely identifies the job seeker in the job seeker database as profile information. That is, as the first reception step, the reception unit 231 receives job seeker identification information that uniquely identifies a specific job seeker as profile information. Furthermore, the acquisition unit 236 acquires the job history information of the job seeker registered in the job seeker database using the job seeker identification information. The generation unit 232 generates job-related information using the job history information as standard personnel information.

[0160] In the above embodiment, in Activity A101, in addition to identification information, information indicating which aspects of the person are desirable (or to be excluded) may be accepted as profile information. In screen G4 shown in Figure 10, the profile information may be a composite specification that instructs the addition or exclusion of specific characteristic information to the standard person information, such as "Employee A's information + [Management experience of 3 years or more, English B2 or higher]" or "Employee B's information - [New sales ratio exceeding 70%]". Furthermore, for multiple people, the specification may involve logical combinations (AND / OR), such as "Only the common characteristics of Employee C and Employee D" or "Characteristics of either Employee E or Employee F", and each characteristic may be entered with a weight or priority.

[0161] In the above embodiment, Server 2 performed various storage and control functions, but instead of Server 2, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 242 may be an external configuration of Server 2. In that case, the external artificial intelligence unit 242 may be provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of Server 2, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to Server 2. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using a large-scale language model. The artificial intelligence service server receives prompt input in the form of text, images, audio, etc., and generates and responds with answers to the prompts.

[0162] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. The information processing method comprises each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0163] The product may be provided in any of the following embodiments.

[0164] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, wherein in a first reception step, the system receives input of reference personnel information, where the reference personnel information is information of a personnel that serves as a standard for generating job-related information, and includes at least one of profile information of a specific personnel and persona information of an ideal personnel; in a generation step, the system generates the job-related information based on the reference personnel information and first reference information, where the job-related information includes a job posting, job seeker search conditions and a scouting document, where the first reference information includes at least the correlation between the reference personnel information and the job-related information; and in an output step, the system outputs the generated job posting, job seeker search conditions and scouting document.

[0165] In this configuration, it is possible to provide information processing systems that generate job postings, job seeker search criteria, and recruitment documents based on standard personnel information.

[0166] (2) An information processing system as described in (1) above, wherein the first reference information includes a machine learning model or a generative AI that is capable of taking the standard personnel information as input and outputting the job-related information.

[0167] (3) An information processing system according to (1) or (2) above, wherein in the first reception step, a plurality of standard personnel information is received as standard personnel information; further, in the extraction step, characteristic information is extracted from the received plurality of standard personnel information; and in the generation step, the recruitment-related information is generated based on the extracted characteristic information and the first reference information.

[0168] (4) An information processing system as described in (3) above, wherein in the extraction step, information common to the plurality of standard personnel information and / or information contained in any of them is extracted as characteristic information.

[0169] (5) An information processing system as described in (4) above, wherein in the second reception step, the extracted characteristic information is presented to the job seeker, and the job seeker inputs whether to accept or reject the characteristic information or the priority, and further in the aggregation step, the characteristic information is aggregated according to the input of acceptance or rejection or the priority.

[0170] (6) An information processing system described in any one of (1) to (5) above, wherein in the third reception step, an existing job posting and / or existing scout document is received, and in the generation step, the standard personnel information and the existing job posting and / or existing scout document are input into the first reference information to generate the job-related information, wherein the job-related information is a job posting and / or scout document that is a modified version of all or part of the existing job posting and / or existing scout document.

[0171] (7) An information processing system according to any one of (1) to (6) above, wherein the generation step generates the job posting based on the standard personnel information and the second reference information, wherein the second reference information includes at least the correlation between the standard personnel information and the job posting, and generates the job seeker search conditions and the scout document based on the standard personnel information, the generated job posting and the third reference information, wherein the third reference information includes at least the correlation between the standard personnel information and the job posting and the job seeker search conditions and the scout document.

[0172] (8) An information processing system as described in (7) above, wherein in the generation step, the system presents the job posting to the employer, receives an input from the employer indicating that it is usable, and then generates the job seeker search conditions and the scout document based on the standard personnel information, the job posting, and the third reference information.

[0173] (9) An information processing system according to any one of (1) to (8) above, wherein the generation step generates the job seeker search conditions as a query normalized to the items and operator specifications of the job seeker database.

[0174] (10) An information processing system according to any one of (1) to (9) above, wherein the generation step generates the subject and body of the scout document to be used when the scout document is first sent, and the subject and body of the scout document to be used when the scout document is resent.

[0175] (11) An information processing system according to any one of (1) to (10) above, wherein in the first reception step, job seeker identification information that uniquely identifies a specific job seeker is received as profile information; further, in the acquisition step, work history information of the job seeker registered in the job seeker database is acquired using the job seeker identification information; and in the generation step, the job posting related information is generated using the work history information as standard personnel information.

[0176] (12) An information processing system according to any one of (1) to (11) above, wherein in the first reception step, employee identification information that uniquely indicates a specific employee belonging to the same organization as the recruiter is received as profile information, further in the acquisition step, personnel information of the specific employee registered in the employee database is obtained using the employee identification information, and in the generation step, the recruitment-related information is generated using the personnel information as standard personnel information.

[0177] (13) An information processing system according to any one of (1) to (12) above, wherein in the first reception step, the system receives input of the persona profile sought by the employer as persona information; further, in the identification step, the system identifies job seekers or specific employees belonging to the same organization as the employer who are similar to the input persona profile from the job seeker database or employee database; and in the generation step, the system generates the job-related information using the work history information or personnel information of the identified job seeker or employee as the standard personnel information.

[0178] (14) An information processing system as described in (13) above, wherein in the identification step, a plurality of job seekers are identified; further, in the first presentation step, information of the identified plurality of job seekers or employees is presented to the employer in a selectable manner; and in the generation step, the job history information or personnel information of the selected job seekers or employees is used as the standard personnel information to generate the job-related information.

[0179] (15) An information processing system as described in any one of (1) to (14) above, wherein in a second presentation step, the generated job-related information is presented to the employer; in a fourth reception step, the employer inputs a decision on whether or not it can be used; and in an execution step, if the decision that it can be used is received, the system enables the execution of one of the following: publishing the job posting to job seekers, sending the scout document to the job seekers, or searching for job seekers based on the job seeker search criteria.

[0180] (16) An information processing system according to any one of (1) to (15) above, wherein in the detection step, the generated job posting, the job seeker search conditions and the scout document are input into a fourth reference information, and the fourth reference information is used to detect a result regarding inconsistencies between the job posting, the job seeker search conditions and the scout document, wherein the fourth reference information includes a machine learning model or a generation AI that is capable of taking the job posting, the job seeker search conditions and the scout document as input and outputting the detection result, and further, in the correction step, the information processing system generates a proposed correction of the job posting, the job seeker search conditions and the scout document based on the job posting, the job seeker search conditions and the scout document and the detection result.

[0181] (17) An information processing system according to any one of (1) to (16) above, comprising a server having the processor and a terminal that can access the server.

[0182] (18) An information processing method comprising each step performed by the information processing system described in any one of (1) to (16) above.

[0183] (19) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (16) above. Of course, this is not always the case.

[0184] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0185] 1: Information Processing System 2: Server 20: Communications bus 21: Communications Department 22: Storage section 23: Control Unit 231: Reception Department 232 :Generation part 233: Output section 234:Extraction part 235: Aggregation Department 236: Acquisition Department 237: Specific part 238:Presentation part 239: Execution Department 240: Detection unit 241: Correction section 242: Artificial Intelligence Department 3: Job seeker terminal 30: Communications bus 31: Communications Department 32: Storage section 33: Control Unit 331: Display section 332: Operation acquisition section 34:Display section 35: Input section CQ: Job seeker search criteria G1: Screen G11 :Area G12 :Area G13 :Area G14 :Area G15 :Area G16: Button G17: Button G18: Button G2: Screen G21 :Area G22 :Area G23 :Area G24 :Area G25: Button G26: Button G27: Button G3: Screen G31 :Area G32 :Area G33 :Area G34 :Area G35: Button G36: Button G37: Button G4: Screen G41 :Area G42 :Area G43 :Area G44: Button G5: Screen G51 :Area G521 :Area G522 :Area G523 :Area G524 :Area G53 :Area G54 :Area G55: Button G56: Button G57: Button JP:Recruitment form

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the first reception step, the input of standard personnel information is accepted, where the standard personnel information is information about a person that serves as the basis for generating job postings, job seeker search criteria, and scouting documents, and includes at least one of the profile information of a specific person and the persona information of an ideal person. In the generation step, Based on the aforementioned standard personnel information and second reference information, the job posting is generated, wherein the second reference information includes a machine learning model or generation AI that is capable of taking the aforementioned standard personnel information as input and outputting the job posting. The job posting is presented to the employer, and after receiving a decision from the employer that it is usable, the job seeker search conditions and the scout document are generated based on the standard personnel information, the job posting, and the third reference information, wherein the third reference information includes a machine learning model or generation AI that is capable of taking the standard personnel information and the job posting as input and outputting the job seeker search conditions and the scout document. An information processing system that outputs the generated job posting, the job seeker search criteria, and the scouting document in the output step.

2. In the information processing system described in claim 1, In the first reception step described above, multiple pieces of reference personnel information are received as the reference personnel information. Furthermore, in the extraction step, from the information contained in the multiple reference personnel information received, information relating to at least one of the following is extracted as characteristic information: job title, industry, skills, qualifications, role, expected results, years of experience, industries experienced, job titles experienced, performance evaluation, behavioral characteristics / competencies, and personality. An information processing system that generates the job posting based on the extracted feature information and the second reference information in the generation step.

3. In the information processing system described in claim 2, Furthermore, in the second reception step, the extracted characteristic information is presented to the job seeker, and the job seeker is asked to indicate whether to accept or reject the characteristic information or to prioritize it. Furthermore, in the aggregation step, the information processing system aggregates the feature information by selecting the feature information based on the input of acceptance or rejection, and / or assigning weights to the feature information based on the input of priority.

4. In the information processing system described in claim 1, In the third application step, existing job postings and / or existing recruitment documents are accepted. In the above generation step, The standard personnel information and the existing job posting are input into the second reference information to generate the job posting, wherein the generated job posting is a job posting that is a modified version of all or part of the existing job posting. An information processing system that inputs the aforementioned standard personnel information, the job posting, and the existing scout document into the third reference information to generate the scout document, wherein the generated scout document is a scout document that modifies all or part of the existing scout document.

5. In the information processing system described in claim 1, The information processing system generates the job seeker search conditions as a query normalized to the items and operator specifications of the job seeker database in the generation step.

6. In the information processing system described in claim 1, The generation step involves an information processing system that generates the subject and body of the scout document to be used when the scout document is first sent, and the subject and body of the scout document to be used when the scout document is resent.

7. In the information processing system described in claim 1, In the first reception step described above, the profile information received is job seeker identification information that uniquely identifies a specific job seeker. Furthermore, in the acquisition step, the job seeker identification information is used to acquire the job seeker's work history information registered in the job seeker database. In the generation step, the information processing system generates the job posting, the job seeker search criteria, and the scouting document using the work history information as the standard personnel information.

8. In the information processing system described in claim 1, In the first reception step described above, the profile information received is employee identification information that uniquely identifies a specific employee belonging to the same organization as the recruiter. Furthermore, in the acquisition step, the employee identification information is used to acquire the personnel information of the specific employee registered in the employee database. In the generation step, the information processing system generates the job posting, the job seeker search criteria, and the scouting document using the personnel information as the standard personnel information.

9. In the information processing system described in claim 1, In the first registration step, the applicant enters the persona information, which is the profile of the candidate the employer is looking for. Furthermore, in a specific step, the system identifies specific employees belonging to the same organization as the job seeker or employer who are similar to the entered candidate profile, from the job seeker database or employee database. An information processing system that, in the generation step, uses the identified job seeker or employee's work history information or personnel information as the standard personnel information to generate the job posting, the job seeker search criteria, and the scouting document.

10. In the information processing system described in claim 9, In the aforementioned identification step, multiple job seekers are identified, Furthermore, in the first presentation step, information on multiple identified job seekers or employees is presented to the employer in a selectable manner. An information processing system that, in the generation step, uses the selected job seeker or employee's work history information or personnel information as the standard personnel information to generate the job posting, the job seeker search criteria, and the scouting document.

11. In the information processing system described in claim 1, Furthermore, in the second presentation step, the generated job posting, the job seeker search criteria, and the scouting document are presented to the employer. In the fourth application step, the applicant submits an input indicating whether or not the applicant is eligible to use the service. An information processing system that, in the execution step, if it receives a determination that it is usable, enables the execution of one of the following: publishing the job posting to job seekers, sending the scouting document to the job seekers, or searching for the job seekers based on the job seeker search criteria.

12. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the first registration step, the input of standard personnel information is accepted, where the standard personnel information is information about a person that serves as a standard for generating job-related information, and includes at least one of the profile information of a specific person and the persona information of an ideal person. In the generation step, the job-related information is generated based on the standard personnel information and the first reference information, and here, The aforementioned job-related information includes job postings, job seeker search criteria, and recruitment documents. The first reference information includes a machine learning model or generative AI that is capable of taking the standard personnel information as input and outputting the job-related information. In the output step, the generated job posting, the job seeker search criteria, and the scouting document are output. In the detection step, the generated job posting, the job seeker search criteria, and the scout document are input into the fourth reference information, and the fourth reference information is used to detect inconsistencies between the three parties: the job posting, the job seeker search criteria, and the scout document. Here, the fourth reference information includes a machine learning model or generative AI that is capable of taking the job posting, the job seeker search criteria, and the scout document as input and outputting information regarding inconsistencies between the three parties. Furthermore, in the revision step, an information processing system generates proposed revisions to the job posting, the job seeker search criteria, and the scouting document based on the job posting, the job seeker search criteria, the scouting document, and the detection results.

13. In the information processing system according to any one of claims 1 to 12, A server having the aforementioned processor, A system comprising a terminal capable of accessing the aforementioned server.

14. Information processing method, An information processing method comprising each step performed by the information processing system according to any one of claims 1 to 12.

15. It is a program, A program for causing a computer to perform each step of the information processing system described in any one of claims 1 to 12.

Images