Information processing system, information processing method and program

Abstract

We provide information processing systems that can support matching between headhunters and job seekers. [Solution] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute the following steps by reading a program: in the information acquisition step, job seeker information indicating the attributes of the job seeker is acquired; in the headhunter extraction step, at least one recommended headhunter to be recommended to the job seeker is extracted from headhunters who act as agents of the employer and are registered in a database, based on the job seeker information and first reference information; and the first reference information includes a correlation between the job seeker information and the recommended headhunter.

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a technology for providing job information to headhunters. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-164745 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for technology that helps match headhunters with job seekers.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can support matching between headhunters and job seekers. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute the following steps by reading a program: in the information acquisition step, job seeker information indicating the attributes of the job seeker is acquired; in the headhunter extraction step, at least one recommended headhunter to be recommended to the job seeker is extracted from headhunters who act as agents of the employer and are registered in a database, based on the job seeker information and first reference information; and the first reference information includes a correlation between the job seeker information and the recommended headhunter.

[0007] According to this embodiment, matching between headhunters and job seekers can be supported. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] 2 is a block diagram showing the hardware configuration of the server device 10. FIG. [Figure 3] 2 is a block diagram showing the hardware configuration of a headhunter terminal 20 and a job seeker terminal 30. FIG. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (controller 11), a headhunter terminal 20 (controller 21), and a job seeker terminal 30 (controller 31). [Figure 5] 10 is a diagram showing an example of a scout document list screen LD displayed on the job seeker terminal 30. FIG. [Figure 6] FIG. 10 is a diagram showing an example of a message screen MD displayed on the job seeker terminal 30 to notify the job seeker of a scouting document sent by a recommended headhunter. [Figure 7] 10 is a diagram showing an example of a scout document display screen SD displayed on the job seeker terminal 30. FIG. [Figure 8] 1 is an activity diagram showing an example of the flow of information processing (recommended headhunter extraction processing) executed by the information processing system 1. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other.

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

[0011] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. 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 formula constructed using a statistical method), a trained model that has previously learned the correlation between input and output, or a generative AI such as a large-scale language model (these models include parameters that establish the correlation between input and output) or a visual language model that can output a desired result in response to a prompt.

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

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

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

[0015] <Information Processing System 1> 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes a communication line 2, a server device 10, a plurality of headhunter terminals 20, and a plurality of job seeker terminals 30. The server device 10, the headhunter terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the headhunter terminals 20, and the job seeker terminals 30 may be wired or wireless.

[0016] The information processing system 1 constitutes at least a part of a recruitment and job search system used by, for example, multiple headhunters (first headhunter U1 and second headhunter U2) and multiple job seekers (first job seeker U3 and second job seeker U4). The information processing system 1 mainly performs functions such as allowing headhunters or recruiters to search for job seekers, allowing job seekers to search for jobs, and mediating communication between headhunters or recruiters and job seekers. For example, the information processing system 1 provides and manages a talent matching platform and talent matching services used by headhunters, recruiters, and job seekers. In one embodiment, the information processing system 1 comprises one or more devices or components. These components are described below.

[0017] <Server device 10> Fig. 2 is a block diagram showing the hardware configuration of server device 10. As shown in Fig. 2, server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. Control unit 11, storage unit 12, and communication unit 13 are electrically connected within server device 10 via communication bus 14.

[0018] <Control unit 11> The control unit 11 processes and controls the overall operations related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out predetermined programs stored in the storage unit 12. In other words, information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being a single unit, and the server device 10 may have multiple control units 11 for each function. Furthermore, the server device 10 may be configured with a combination of these.

[0019] <Storage section 12> The memory unit 12 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The memory unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0020] <Communications Department 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), or wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as LTE / 5G, or BLUETOOTH (registered trademark) communication as needed. That is, it is more preferable to implement it as a collection of multiple communication means. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The server device 10 may be an on-premise server or a cloud server. The cloud server device 10 may provide the above-described functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] <Headhunter Terminal 20> FIG. 3 is a block diagram showing the hardware configuration of the headhunter terminal 20 and the job seeker terminal 30. The headhunter terminal 20 is an information processing terminal used by a headhunter. A headhunter is an organization or its personnel who acts as an agent of the recruiter to act as an intermediary between job seekers and the recruiter (organization). A headhunter is also called a recruitment agency, recruitment introduction agency, agent, etc.

[0023] "Recruiters" include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations), and public corporations (e.g., local governments) or their personnel. Personnel at recruiters may also be called hiring personnel, and may include personnel in the organization's human resources department or personnel in the department that hires personnel.

[0024] 3A, the headhunter terminal 20 includes a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected via the communication bus 26 inside the headhunter terminal 20. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is omitted because they are the same as the explanation of each unit in the server device 10.

[0025] <Input section 24> The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 can execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the headhunter terminal 20 or may be attached externally. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 24. Instead of a touch panel, a switch button, a mouse, a trackpad, a QWERTY keyboard, etc. can be used as the input unit 24.

[0026] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the headhunter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them depending on the type of headhunter terminal 20.

[0027] <Job Seeker Terminal 30> The job seeker terminal 30 is an information processing terminal used by a job seeker. "Job seekers" include, for example, employed people (people looking to change jobs), prospective new graduates (job seekers), students, etc., and also include people who are looking to change jobs or find employment, or people who are interested in changing jobs or finding employment.

[0028] 3B, the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected via the communication bus 36 inside the job seeker terminal 30. The explanation of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are the same as the explanation of each unit in the headhunter terminal 20.

[0029] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (at least one processor included in the information processing system 1).

[0030] FIG. 4 is a block diagram showing functions realized by the server device 10 (controller 11), headhunter terminal 20 (controller 21), and job seeker terminal 30 (controller 31).

[0031] As shown in FIG. 4A, the server device 10 (control unit 11) includes a basic display control unit 111, an information acquisition unit 112, an evaluation unit 113, a headhunter extraction unit 114, a job offer extraction unit 115, and an artificial intelligence unit 120.

[0032] 4B, the headhunter terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in FIG. 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0033] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the headhunter terminal 20 or the job seeker terminal 30. For example, the basic display control unit 111 displays information on job seekers or job offers registered in the database on the display unit 211 of the headhunter terminal 20 or the display unit 311 of the job seeker terminal 30 in response to a request from each user (headhunters U1, U2 or job seekers U3, U4).

[0034] <Information acquisition unit 112> The information acquisition unit 112 is configured to acquire information relating to job seekers, headhunters, job offers, etc. The information acquisition unit 112 acquires at least job seeker information indicating attributes of the job seeker who is the user.

[0035] "Job seeker information" is information registered in a database, including, for example, basic information about the job seeker (such as name, gender, age, and address) or work history. Job seeker information may also include, for example, a document called a resume, which is a document related to the job seeker's work history in which the job seeker conveys to the employer his or her work history, experience, skills, qualifications, etc. related to his or her previous work. A document related to the job seeker's work history (resume) may include the job seeker's resume, other profile information, and the job seeker's desired industry and job type, etc. A "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, work history, desired working conditions, etc. Job seeker information may also include information other than documents related to the job seeker's work history.

[0036] The information acquisition unit 112 may further acquire first history information indicating the job seeker's job search activity history. The "first history information" includes, for example, the login status to services provided by the information processing system 1 (for example, a job change / employment support service or a matching service (a service that manages registered information of job seekers)), the date and time of registration or update of registered information, the status of receiving scouting documents from headhunters or recruiters, the status of replies to scouting documents, and the history of actions taken regarding job offers. Here, the scouting document refers to an email, message, etc. sent by a recruiter or headhunter to a job seeker such as a job seeker or a new graduate student, encouraging the job seeker to apply for a selection process or suggesting an interview, and may also be called a scouting email.

[0037] The "login status to the service" includes, for example, the number of logins in a predetermined period, the number of days since the last login, etc. The first history information may also include the registration period for the service (the period of time that has elapsed since the registration information was registered).

[0038] "Scouting document reception status" includes, for example, the number of scouting documents received, the time of receipt of the scouting documents, information about the headhunter or recruiter who received the scouting documents (for example, the attributes of the headhunter described below, or the attributes of the recruiter such as organizational size and industry), and information about the job posting attached to the scouting document (for example, job attributes such as job type, duties, position, working conditions, etc.).

[0039] "Reply status to scouting documents" includes, for example, the number of replies to the scouting document, the time of reply to the scouting document, the number of days from receipt of the scouting document to reply, information about the headhunter or recruiter who sent the returned scouting document, and information about the job posting attached to the returned scouting document.

[0040] "History of job posting behavior" includes, for example, the number of times a job posting was viewed in a specified period, the number of applications for a job posting in a specified period, the number of jobs added to a bookmark list in a specified period, information about the jobs viewed (job attributes), information about the jobs applied for, and information about the jobs added to a bookmark list.

[0041] A bookmark list (also called a "favorite list" or "interest list") is a list prepared for each job seeker, in which the job seeker can register any job openings. By referring to the bookmark list, the job seeker can select a job opening from the registered bookmark list to view, apply for, or take other action on.

[0042] The first history information may include specific job information indicating attributes of a specific job for which the job seeker has taken an action. Examples of "specific job information" include job information viewed by the job seeker, job information applied for by the job seeker, job information added to the job seeker's bookmark list, job information described in or attached to a scouting document replied by the job seeker, job information introduced to the job seeker in an interview, job information that has passed screening (documentation or interview), etc. Examples of "specific job information" include the recruitment conditions for the specific job.

[0043] The information acquisition unit 112 may further acquire headhunter information indicating the attributes of headhunters registered in the database. "Headhunter information" is information registered in the database, including, for example, information about the headhunter himself / herself and the achievements of the headhunter. The headhunter information includes, for example, profile, self-promotion, department name, job title, work location (area of ​​responsibility), educational background, areas of expertise (industry, job type, annual income range, age range, etc.), expertise, years of experience, language ability, past intermediary achievements, etc.

[0044] The headhunter information may include first performance information indicating attributes of the involved job seekers in whose job search activities the headhunter has been involved. A "involved job seeker" is, for example, a job seeker with whom the headhunter has had contact regarding employment in the past. The "job search activities" in which the headhunter has been involved include, for example, sending scouting documents to the involved job seekers, receiving replies to the scouting documents from the involved job seekers, interviews with the involved job seekers, communication with the involved job seekers (phone calls, interviews, sending and receiving messages, etc.), introducing job openings to the involved job seekers, and supporting the involved job seekers until they are hired by the employer.

[0045] The information (items) about the participating job seekers included in the first performance information is the same as the job seeker information of the user job seeker, and is, for example, information registered in the database including the participating job seeker's basic information (name, gender, age, address, etc.) or work history.

[0046] The first performance information may indicate attributes of the job seekers involved in the hiring decision made by the headhunter. This allows the user job seeker to be matched with the headhunter by referring to the attributes of the job seekers involved in the hiring decision made by the headhunter. This encourages job seekers to reply to messages (scouting documents) from headhunters, increasing the response rate and increasing the hiring rate for job seekers through headhunters. This makes it possible to extract, for example, headhunters with a track record of hiring in industries, job types, ages, areas, etc. that are the same or similar to those of the job seeker, or messages from such headhunters. Here, "hiring" may also be referred to as "concluding a deal." Furthermore, "hiring" may include not only the job seeker's employment or job change confirmation with the employer, but also the employer's offer of employment to the job seeker, the job seeker's acceptance of the offer, the job seeker's joining the employer, etc.

[0047] The headhunter information may include second performance information indicating attributes of related job postings in which the headhunter was involved in the hiring decision. A "related job posting" is a job posting that was previously associated with a headhunter (a job posting that the headhunter represented) and for which the hiring of a related job seeker was decided through the intermediation activities of the headhunter.

[0048] The information (items) about the related job offer included in the second performance information is the same as the specific job offer information included in the first history information of the user job seeker, and includes, for example, recruitment conditions such as the industry, job type, job duties, position, required skills (required experience), annual salary, work location, and working style of the specific job offer.

[0049] The headhunter information may include basic information about the headhunter (such as name, gender, age, and address) or information about their expertise. This makes it possible to match the job seeker (user) with the headhunter based on the commonality of their basic information (such as address) or the headhunter's knowledge and experience regarding the industry, job type, etc. in which the job seeker is seeking employment. This makes it possible to extract recommended headhunters that are highly suitable for the job seeker's current situation, desired conditions, etc., and encourage the job seeker to reply to messages (scouting documents) from the headhunter, thereby increasing the response rate.

[0050] The headhunter information may include feedback information from job seekers involved in the job search activities of the headhunter. This allows recommended headhunters to be extracted by taking into account the evaluations of the job seekers involved, in addition to information about the headhunter themselves and their track record. This makes it possible to match individual job seekers with headhunters that are more suitable for them.

[0051] Feedback to the headhunter is obtained, for example, at a predetermined timing (for example, a certain time after receiving a scout, after an interview, after a deal is concluded, etc.) through a questionnaire presented to the job seeker terminal 30. The questionnaire may include, for example, a graded evaluation of the headhunter (for example, a 5-point evaluation), comments on good points, comments on bad points, etc.

[0052] Feedback to headhunters may be weighted depending on the time lapse from the predetermined timing to when the participating job seeker provided the feedback. For example, if feedback is provided sooner after an interview, the content of that feedback (evaluation results) will be weighted more heavily than other feedback. Note that this weighting is referenced when the headhunter extraction unit 114, which will be described later, extracts recommended headhunters.

[0053] The information acquisition unit 112 may further acquire second history information indicating the history of the headhunter's intermediary activities. The "second history information" is information used by the evaluation unit 113 (described later) to evaluate the headhunter, and includes the history of intermediation activities for multiple job seekers. The "intermediation activities" include, for example, a first activity and a second activity.

[0054] A "first activity" is, for example, an activity in the initial stage in which a headhunter understands a job seeker's career and job search intentions, and supports their preparation. Furthermore, "first activity" also includes, for example, activities to support a job seeker's self-analysis and confirm the job seeker's intentions regarding employment. A headhunter may, for example, conduct an interview with a job seeker (especially the first interview) or support the job seeker's self-reflection activities as a first activity. Furthermore, a headhunter may, for example, support the job seeker in creating a resume, curriculum vitae, etc., as a first activity. Supporting a job seeker's self-reflection activities involves helping the job seeker organize their purpose or reasons for seeking employment, their desired employment destination or conditions, etc., through communication via telephone, interview, email, etc. These first activities are carried out before a headhunter introduces information about a job seeker or recommends a job seeker to the employer (organization) that is their client.

[0055] "Secondary activities" include, for example, activities in which a headhunter supports communication between a job seeker and an employer during the recruitment process and facilitates the job seeker's employment. "Secondary activities" also include, for example, activities supporting communication between a job seeker and an employer. A headhunter's secondary activities include, for example, mediating a job seeker's application for a job, mediating the job seeker's contact with an employer, assisting the job seeker in setting up or preparing for an interview or meeting with an employer, and supporting the job seeker in finding employment with an employer. If a headhunter assists a job seeker in preparing a resume or curriculum vitae after introducing a job seeker to an employer, such assistance is included in the second activities. Furthermore, a headhunter may also engage in, for example, activities in which a job seeker confirms or negotiates working conditions such as contract length and wages after receiving a job offer from an employer, or mediates or supports the job seeker in contacting the employer to accept or decline the job offer.

[0056] Furthermore, if the job seeker is looking to change jobs, the headhunter may provide support activities for the job seeker to resign from their current organization as the second activity. Support activities for resignation include, for example, advice on when to submit resignation, assistance with writing a resignation letter, and assistance with negotiating resignation with superiors, the human resources department, etc. In this way, the second activity includes activities that occur after the headhunter introduces or recommends the job seeker to the employer. Furthermore, the second activity is a separate activity that does not overlap with the first activity, and may include only activities that occur after the headhunter introduces or recommends the job seeker to the employer.

[0057] The second history information may include information indicating the content of the first activity and / or the second activity (specific activity content, points according to the activity, etc.), and may also include information indicating the job seeker's evaluation of the first activity and / or the second activity (first evaluation information and / or second evaluation information). The job seeker's evaluation is collected, for example, by a questionnaire presented to the job seeker terminal 30. The job seeker's evaluation also includes, for example, a score indicating the degree of satisfaction.

[0058] The second history information may include information about the headhunter's record of successful deals. The information about successful deals may be referred to as recruitment support record, and may include, for example, the number of job offers made by the headhunter, the number of successful hires, the number of hires who joined the company, the offer rate, the hiring rate, the hiring rate, and the average annual salary of successful hires for the job offers. Furthermore, the second history information may include rule compliance information. The rule compliance information indicates the degree to which the headhunter complied with the rules established in the first activity or the second activity. The rules are established to ensure that the headhunter's activities are carried out at a certain level, such as a rule that "when supporting job seekers in their self-reflection activities, interviews should be conducted in person or over the phone."

[0059] The information acquisition unit 112 may further acquire available job information indicating attributes of the job offers stored in association with the headhunter. The available job information is referenced when the job offer extraction unit 115, which will be described later, extracts recommended job offers. "Job offers stored in association with the headhunter" are, for example, job offers that are represented (mediated) by the headhunter (job offers that can be introduced to employers or job offers that can be attached to scouting documents sent to employers).

[0060] <Evaluation Department 113> The evaluation unit 113 is configured to determine an evaluation of the headhunter based on the second history information (the history of the headhunter's intermediary activities). The evaluation unit 113 may determine the evaluation of the headhunter based on, for example, the first evaluation information and the second evaluation information included in the second history information. Furthermore, the evaluation unit 113 may determine the evaluation of the headhunter based on contract performance information and / or rule compliance information included in the second history information in addition to the first evaluation information and the second evaluation information.

[0061] Specifically, the evaluation unit 113 determines the evaluation of the headhunter based on the second history information (particularly the first evaluation information and the second evaluation information) and the evaluation reference information. The evaluation reference information includes a correlation between the second history information and the headhunter's evaluation. The evaluation reference information is stored, for example, in the storage unit 12. The evaluation reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates the correlation between the second history information and the headhunter's evaluation. The correlation included in the evaluation reference information can be constructed, for example, by statistically analyzing data recording the second history information and the corresponding headhunter's evaluation.

[0062] The evaluation reference information may include a headhunter evaluation model, which is a learning model trained by machine learning that is capable of inputting the second history information and outputting an evaluation of the headhunter, or a generative AI. In this case, the evaluation unit 113 inputs the second history information into the headhunter evaluation model and causes the headhunter evaluation model to output an evaluation of the headhunter. In the headhunter evaluation model, parameters calculated, tuned, etc. by learning constitute the correlation of the evaluation reference information.

[0063] The headhunter evaluation model is included in the artificial intelligence unit 120. The headhunter evaluation model, which is trained to be able to output evaluations of headhunters, is trained using, for example, data of the second history information and the corresponding evaluations of headhunters as training data.

[0064] When the headhunter evaluation model is a generative AI including a general-purpose natural language model (large-scale language model), the evaluation unit 113 inputs the second history information, inputs a prompt including an instruction to output a headhunter evaluation corresponding to the second history information to the headhunter evaluation model, and causes the headhunter evaluation to output the headhunter evaluation. The evaluation unit 113 may generate a prompt that instructs the headhunter evaluation model to create a headhunter evaluation, and input the prompt to the headhunter evaluation model. Furthermore, the evaluation unit 113 may input, in addition to the instruction to create and output the headhunter evaluation and the second history information, a prompt that inserts, for example, one or more samples of the second history information and one or more corresponding samples of headhunter evaluations as examples, samples, or training data of input and output pairs to the headhunter evaluation model.

[0065] The evaluation of a headhunter may be an absolute evaluation (for example, a score indicating the level of evaluation), a relative numerical value (for example, a ranking among the headhunters being evaluated), or information indicating a rank (level) (for example, a rank on several levels such as "S," "A," "B," "C," etc.). The evaluation of a headhunter may also include an item-by-item evaluation determined for each piece of evidence information such as the first evaluation information, second evaluation information, contract performance information, and rule compliance information.

[0066] The evaluation of the headhunter determined by the evaluation unit 113 is registered as information about the headhunter and is displayed, for example, on the job seeker terminal 30 when the job seeker refers to the information about the headhunter.

[0067] <Headhunter Extraction Section 114> The headhunter extraction unit 114 is configured to extract at least one recommended headhunter to recommend to the job seeker from among the headhunters registered in the database, based on the job seeker information acquired by the information acquisition unit 112 and the first reference information.

[0068] Examples of "recommended headhunters" include headhunters who handle job openings that match or are close to the job seeker's desired conditions (industry, job type, annual salary, work location, etc.), headhunters who specialize in industries, job types, annual salary, work location, etc. that match or are close to the job seeker's desired conditions (industry, job type, annual salary, work location, etc.), headhunters who have a track record of supporting the job search and hiring decisions of other job seekers with similar attributes to the job seeker, and headhunters who can provide support appropriate to the job seeker's activity status (for example, intention to change jobs or find employment, motivation for changing jobs or finding employment, desired timing for changing jobs or finding employment, etc.).

[0069] The first reference information includes a correlation between job seeker information and recommended headhunters. The first reference information is stored, for example, in the storage unit 12. The first reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates the correlation between job seeker information and recommended headhunters. The correlation included in the first reference information can be constructed, for example, by statistically analyzing data recording job seeker information and corresponding recommended headhunters.

[0070] The first reference information may include a recommended headhunter determination model, which is a machine-learned learning model or a generative AI that is capable of inputting job seeker information and outputting recommended headhunters. In this case, the headhunter extraction unit 114 inputs the job seeker information into the recommended headhunter determination model and causes the recommended headhunter determination model to output recommended headhunters. In the recommended headhunter determination model, parameters calculated, tuned, etc. through learning constitute the correlations of the first reference information.

[0071] The recommended headhunter determination model is included in the artificial intelligence unit 120. The recommended headhunter determination model, which has been trained to be able to output recommended headhunters, is trained using, for example, data on job seeker information and data on corresponding recommended headhunters as training data.

[0072] When the recommended headhunter determination model is a generative AI including a general-purpose natural language model (large-scale language model), the headhunter extraction unit 114 inputs job seeker information, inputs a prompt including an instruction to output recommended headhunters corresponding to the job seeker information to the recommended headhunter determination model, and causes the recommended headhunter to output the recommended headhunter. The headhunter extraction unit 114 may generate a prompt that gives the recommended headhunter determination model an instruction to determine recommended headhunters and input the prompt to the recommended headhunter determination model. Furthermore, the headhunter extraction unit 114 may input, in addition to the instruction to determine and output recommended headhunters and the job seeker information, a prompt that inserts, for example, one or more samples of job seeker information and one or more samples of recommended headhunters corresponding thereto as examples, samples, or training data of input and output pairs to the recommended headhunter determination model.

[0073] The first reference information may include information for determining (selecting or creating) a search formula for searching for recommended headhunters from among registered headhunters, based on the job seeker information and / or the first history information. For example, the first reference information may be a table, algorithm, or the like that defines the relationship between features (e.g., feature vectors) extracted from the job seeker information and the headhunter's search formula (e.g., conditions such as the specialty field, attributes of the job being represented, and the headhunter's track record). Furthermore, the headhunter extraction unit 114 may input an instruction to create a search formula or an instruction to search for recommended headhunters based on the job seeker information to a search formula creation model, which is a generation AI included in the first reference information, and cause the search formula or a search result using the search formula to be output to the search formula creation model.

[0074] The first reference information may be, for example, a search formula template or format that defines the headhunter's search items (e.g., job type, industry, annual salary, etc. in the track record) and information (variables) extracted from the job seeker information and / or the first history information for each search item. For example, the first reference information may be a search formula template or format such as "job type={job type of the user job seeker}, industry={industry of the user job seeker}, annual salary={annual salary of the user job seeker ±500,000 yen}", and the headhunter extraction unit 114 may create search conditions (search query) by inserting the job seeker information, the specific job information of the first history information, etc. into such first reference information.

[0075] The headhunter extraction unit 114 may extract recommended headhunters based on the job seeker information and headhunter information acquired by the information acquisition unit 112 and the first reference information. This allows matching between job seekers and headhunters by comparing the job seeker information with the headhunter information. As a result, job seekers benefit from reduced effort in finding a suitable headhunter and increased employment opportunities due to increased contact with headhunters. In particular, this system can help job seekers who receive many scouting documents from headhunters identify the scouting documents they want to view and reply to. Headhunters also benefit from efficient approaches to job seekers that match their strengths, gaining the trust of job seekers by being presented as recommended headhunters, improving the response rate to scouting documents sent to job seekers, and increasing the number of hiring decisions and closing rates due to increased opportunities for job seekers to receive support.

[0076] For example, the headhunter extraction unit 114 may extract recommended headhunters based on information such as the desired industry or desired occupation or current industry or current occupation included in the job seeker information, information on areas of expertise (areas of expertise, occupations of expertise, etc.) included in the headhunter information, and the first reference information. This makes it possible to extract headhunters and messages (scouting documents) from the headhunters based on the areas of expertise, encouraging job seekers to reply to messages from headhunters and increasing the reply rate, as well as the rate at which job seekers are hired through headhunters.

[0077] In this case, the first reference information includes correlations between the job seeker information, the headhunter information, and the recommended headhunters. The recommended headhunter determination model included in the first reference information receives the job seeker information and the headhunter information as input and outputs recommended headhunters. Therefore, the recommended headhunter determination model trained to be able to output recommended headhunters is trained, for example, using data on the job seeker information and the headhunter information and data on the corresponding recommended headhunters as training data. Furthermore, when the recommended headhunter determination model is a generative AI, the headhunter extraction unit 114 receives the job seeker information and the headhunter information as input, and inputs a prompt to the recommended headhunter determination model that includes an instruction to output recommended headhunters corresponding to the combination of the job seeker information and the headhunter information, causing the recommended headhunter to output the recommended headhunter.

[0078] When the headhunter information includes first performance information (attributes of job seekers involved in job-seeking activities), the headhunter extraction unit 114 may extract recommended headhunters based on the similarity between the attributes of job seekers indicated in the job seeker information and the attributes of job seekers indicated in the first performance information. This makes it possible to present, as recommended headhunters, headhunters who have a track record of supporting job seekers with attributes similar to those of the user job seeker. This makes it possible to match a headhunter that is suitable for the attributes of the user job seeker.

[0079] The similarity between job seekers is expressed by the difference in feature amounts (e.g., vector distance) of the job seeker information, and for example, job seekers whose difference in feature amounts is less than a threshold (e.g., cosine similarity is equal to or greater than a threshold) are determined to be similar to each other. The feature amounts of the job seeker information are quantified using known methods, such as natural language processing using morphological analysis or encoding. The feature amounts of the job seeker information may also be obtained by referencing a table that defines feature amounts for each keyword. The similarity between job seekers may also be determined by a learning model or generation AI that has been trained by machine learning to be able to calculate similarity.

[0080] The headhunter extraction unit 114 determines a recommended headhunter based on the calculated similarity between the attributes of the job seekers. For example, the headhunter extraction unit 114 may determine as a recommended headhunter a headhunter who has been involved in the job search of a job seeker whose similarity is equal to or greater than a predetermined threshold (or exceeds the threshold). Furthermore, the headhunter extraction unit 114 may determine as a recommended headhunter a headhunter who, among the job seekers in whose job search the headhunter has been involved, has a number of job seekers whose similarity to the user job seeker is equal to or greater than a predetermined threshold (or exceeds the threshold).

[0081] When extracting recommended headhunters using the similarity of job seekers in this manner, the first reference information may include information for calculating the similarity of job seekers (algorithms, tables, learning models, generation AI, etc.) and information for determining recommended headhunters based on the similarity (thresholds, conditional expressions, etc.).

[0082] It should be noted that the headhunter extraction unit 114 does not need to extract recommended headhunters based on the similarity of all items (items indicating attributes) included in the job seeker information with the corresponding items in the first performance information (information on other job seekers), and may extract recommended headhunters based on the similarity of some items (for example, industry) included in the job seeker information. For example, the headhunter extraction unit 114 may extract headhunters who specialize in a specific industry, headhunters who specialize in a specific occupation, headhunters who are skilled in a specific age group, etc.

[0083] When the headhunter information includes first performance information (attributes of job seekers involved in job search activities) and second performance information (attributes of job offers involved in hiring decisions), the headhunter extraction unit 114 may extract recommended headhunters based on the degree of compatibility between the job seeker attributes indicated in the job seeker information and the job offer attributes indicated in the second performance information, in addition to the similarity of the job seeker attributes. This makes it possible to present as recommended headhunters those headhunters who have a track record of supporting job seekers with attributes similar to those of the user job seeker and who have also had experience in hiring the user job seeker for a job offer that is suitable for the user job seeker. In other words, headhunters can be matched based on information on "which job seeker was hired for which job offer" and the user job seeker's profile, desired conditions, etc.

[0084] Here, "suitability" refers to the degree of suitability between an item referenced in the job seeker information (e.g., desired annual income) and an item referenced in the second performance information (e.g., expected annual income). Furthermore, the headhunter extraction unit 114 does not need to extract recommended headhunters based on the suitability of each of all items included in the job seeker information with the corresponding items in the second performance information, and may extract recommended headhunters based on the suitability of some items included in the job seeker information (e.g., annual income).

[0085] The headhunter extraction unit 114 may extract recommended headhunters based on the job seeker information, first history information (history of the job seeker's activities), and headhunter information acquired by the information acquisition unit 112, as well as the first reference information. This makes it possible to match job seekers with headhunters using the activity history, which is dynamic information, in addition to the attributes, which are static information of the job seeker, and therefore to present recommended headhunters that are suited to the circumstances of each individual job seeker.

[0086] In this case, the first reference information includes correlations between the job seeker information, the first history information, and the headhunter information and the recommended headhunters. The recommended headhunter determination model included in the first reference information receives the job seeker information, the first history information, and the headhunter information as input, and outputs recommended headhunters. Therefore, the recommended headhunter determination model trained to be able to output recommended headhunters is trained, for example, using the job seeker information, the first history information, and the headhunter information, and the corresponding data on recommended headhunters, as training data. Furthermore, when the recommended headhunter determination model is a generative AI, the headhunter extraction unit 114 receives the job seeker information, the first history information, and the headhunter information as input, and inputs a prompt to the recommended headhunter determination model that includes an instruction to output recommended headhunters corresponding to the combination of the job seeker information, the first history information, and the headhunter information, thereby causing the recommended headhunter to output the recommended headhunter.

[0087] If the first history information includes specific job information (attributes of the specific job for which the job seeker has taken action), the headhunter extraction unit 114 may extract recommended headhunters based on a comparison between the attributes of the specific job indicated by the specific job information and the attributes of the job seeker indicated by the job seeker information. This makes it possible to extract the job seeker's career change direction (e.g., increase in annual salary, career change, range of work locations, etc.) based on the differences (differences) between the specific job in which the user job seeker is interested and the job seeker's profile and desired conditions. Furthermore, by referring to such career change direction and the headhunter information, it is possible to match a headhunter that suits the user job seeker's intentions.

[0088] For example, the headhunter extraction unit 114 may obtain trend information indicating an annual income gap, i.e., "the annual income of the job offer is larger than the current annual income of the job seeker," by comparing the attributes of the specific job offer with the attributes of the user job seeker, and extract headhunters who have a track record (a wealth of experience) of providing recruitment support to increase annual income as recommended headhunters based on the trend information and the headhunter information.Furthermore, the headhunter extraction unit 114 may obtain trend information indicating an industry change, i.e., "the industry or job type of the job offer differs from the current industry or job type of the job seeker," by comparing the attributes of the specific job offer with the attributes of the user job seeker, and extract headhunters who have a track record (a wealth of experience) of providing recruitment support for industry or job type changes as recommended headhunters based on the trend information and the headhunter information.

[0089] In this manner, when recommended headhunters are extracted by comparing the attributes of a specific job offer with the attributes of a job seeker, the first reference information may include information (algorithms, tables, learning models, generation AI, etc.) for generating trend information for job seekers, and information (algorithms, tables, learning models, generation AI, etc.) for determining recommended headhunters based on the trend information and headhunter information.

[0090] The headhunter extraction unit 114 may extract recommended headhunters from among the headhunters registered in the database who have been evaluated by the evaluation unit 113 to be at least a predetermined level. This makes it possible to extract recommended headhunters from among headhunters who have a certain track record of intermediary activities or have received evaluations of their intermediary activities from job seekers, thereby improving the quality of headhunters matched with users who are job seekers. Furthermore, by extracting headhunters based on objective evaluations, headhunters and job seekers who are presented with scouting documents sent by the headhunters can feel at ease when considering actions such as replying to the scouting documents.

[0091] "Headhunters with a predetermined or higher evaluation" include, for example, headhunters whose evaluation score is equal to or higher than a predetermined threshold (or exceeds the threshold), headhunters whose evaluation ranking is equal to or higher than a predetermined threshold (or exceeds the threshold), headhunters whose evaluation rank is equal to or higher than a predetermined standard rank (e.g., "A rank"), etc. The headhunter extraction unit 114 may display the extracted recommended headhunters on the job seeker terminal 30 in descending order of evaluation (e.g., highest score).

[0092] The headhunter extraction unit 114 may extract recommended headhunters from among the headhunters from whom the user job seeker has received scouting documents (i.e., headhunters who have sent scouting documents to the user job seeker). The condition for headhunters to be extracted may be that "they have sent scouting documents to the job seeker, and the scouting documents are in an unread or unreply state."

[0093] The first reference information may include multiple pieces of supplementary reference information, each with a different weighting or type of items referenced in the job seeker information when extracting recommended headhunters. Examples of "items referenced" in the job seeker information include career history, skills, experience, age, address, current annual income, desired annual income, etc.

[0094] "Weighting" refers to the degree of importance in matching job seekers and headhunters. Items with a higher weighting are referenced preferentially over other items when extracting recommended headhunters. For example, if the "desired annual salary" item in the job seeker information is weighted higher than the "career history" item in the job seeker information, headhunters with a higher correlation between the desired annual salary in the job seeker information and the headhunter information (e.g., the annual salary of the related job offer) are extracted as recommended headhunters with a higher correlation between the career history in the job seeker information and the headhunter information (e.g., the career history of the related job seeker). Note that the weighting may be set to zero. Items with a weighting of zero are not referenced when extracting recommended headhunters.

[0095] In addition to the items in the job seeker information, the types of items referenced in the headhunter information when extracting recommended headhunters, or the weighting of each item, may differ for each piece of supplementary reference information. Examples of "items referenced" in the headhunter information include the headhunter's expertise, the headhunter's area of ​​responsibility, the attributes of the involved job seekers (e.g., career history, skills, experience, age, address, annual salary of the concluded job at the time of conclusion of the job offer (decision to hire), etc.), the attributes of the involved job offers (e.g., the job offer's industry, job type, duties, position, required skills, qualifications, or experience, welcomed skills, qualifications, or experience, annual salary, work location, work style, etc.), feedback from the involved job seekers, etc.

[0096] The supplementary reference information may include information for determining (selecting or creating) a search formula for searching for recommended headhunters from among registered headhunters, depending on the job seeker information and / or the first history information. For example, the first reference information may include supplementary reference information (search formula templates or formats) in which at least some of the search items used to search for headhunters are different from each other.

[0097] For example, the first reference information may include the following first auxiliary reference information, second auxiliary reference information, third auxiliary reference information, fourth auxiliary reference information, etc. The first auxiliary reference information creates a search formula using job seeker information related to job type or industry. The first auxiliary reference information is used, for example, for job seekers who tend to take more action on job offers that match their current job type or industry. The second auxiliary reference information creates a search formula using job seeker information related to current annual income (information such as current annual income + xx million yen) in addition to job type or industry. The second auxiliary reference information is used, for example, for job seekers who tend to take more action on job offers with annual income higher than their current annual income. The third auxiliary reference information creates a search formula using the current job type or industry in the job seeker information and the job type or industry included in the specific job information, and searches the job types of the headhunter's first performance information (involved job seekers) and the job types of the second performance information (involved job offers). The third auxiliary reference information is used, for example, for job seekers who tend to take many actions toward job openings in occupations different from their current occupation and are assumed to be considering a career change. The fourth auxiliary reference information creates a search formula for searching for headhunters who are skilled in specific support tasks, using the headhunter's own attributes (e.g., areas of expertise, etc.), the second history information (e.g., job seeker satisfaction, etc.). The fourth auxiliary reference information does not need to use job seeker information to create the search formula. Furthermore, the fourth auxiliary reference information may create a search formula using job seeker information related to occupation or industry in addition to the headhunter information described above. The fourth auxiliary reference information is used, for example, for job seekers who take few actions toward job openings and are assumed to have little desire to change jobs or are unsure about changing jobs.

[0098] The supplementary reference information is prepared, for example, for each proposal policy for a job seeker (points to be emphasized when matching with a headhunter). The "proposal policy" is determined based on the job seeker's attributes, activity trends, etc., based on the job seeker information and / or first history information, and is, for example, an appeal axis for the job seeker. For example, in supplementary reference information for a job seeker who wishes to increase his or her annual income, the job seeker's "desired annual income" and the "annual income of the relevant job offer" are weighted higher than other items. Also, for example, in supplementary reference information for a job seeker who wishes to start a new career based on his or her own experience, the job seeker's "career history" and the "expertise of the headhunter" are weighted higher than other items.

[0099] The headhunter extraction unit 114 may extract recommended headhunters based on the job seeker information and supplementary reference information selected according to the job search activity history indicated by the first history information. This makes it possible to select supplementary reference information to be used for extracting recommended headhunters according to the activity history of the job seeker who is the user, and to match a headhunter that meets the job seeker's preferences.

[0100] For example, when it is determined that the job seeker desires to increase their annual income based on the job listings and the like included in the job search history, the headhunter extraction unit 114 selects supplementary reference information with an increase in annual income as the proposal policy. Also, when it is determined that the job seeker does not desire to change jobs immediately based on the login status and the like included in the job search history, the headhunter extraction unit 114 selects supplementary reference information with an proposal policy of consultation that will lead to a job change.

[0101] The headhunter extraction unit 114 selects supplementary reference information based on, for example, the job search history and the selection reference information. The selection reference information includes a correlation between the job search history and the selected supplementary reference information. The selection reference information is stored, for example, in the storage unit 12. The selection reference information may include, for example, a table, a function, a simple algorithm, or the like, that indicates the correlation between the job search history and the supplementary reference information. The correlation included in the selection reference information can be constructed, for example, by statistically analyzing data recording the job search history and the corresponding supplementary reference information.

[0102] The reference information for selection may include a learning model that has been machine-learned to take the job search history as input and output supplementary reference information, or a reference information selection model that is a generative AI. In this case, the headhunter extraction unit 114 inputs the job search history into the reference information selection model and causes the reference information selection model to output supplementary reference information. In the reference information selection model, parameters calculated, tuned, etc. through learning constitute the correlation of the reference information for selection.

[0103] The reference information selection model is included in the artificial intelligence unit 120. The reference information selection model, which has been trained to be able to output supplementary reference information, is trained using, for example, data on the job search history and data on the corresponding supplementary reference information as training data.

[0104] When the reference information selection model is a generative AI including a general-purpose natural language model (large-scale language model), the headhunter extraction unit 114 inputs the job search history, inputs a prompt including an instruction to output auxiliary reference information corresponding to the job search history to the reference information selection model, and causes the reference information selection model to output the auxiliary reference information. The headhunter extraction unit 114 may generate a prompt that instructs the reference information selection model to select auxiliary reference information and input the prompt to the reference information selection model. Furthermore, the headhunter extraction unit 114 may input, in addition to the instruction to select and output the auxiliary reference information and the job search history, a prompt that inserts, for example, one or more samples of the job search history and one or more corresponding samples of auxiliary reference information as examples, samples, or training data of input and output pairs to the reference information selection model.

[0105] The headhunter extraction unit 114 may extract recommended headhunters based on the job seeker information, the headhunter information, and the selected supplementary reference information. The headhunter extraction unit 114 may also extract recommended headhunters based on the job seeker information, the headhunter information, the first history information, and the selected supplementary reference information.

[0106] The headhunter extraction unit 114, for example, displays information about the extracted recommended headhunters on the job seeker terminal 30. The "information about the recommended headhunters" includes, for example, information indicating the recommended headhunters, links to detailed information about the recommended headhunters, scouting documents sent by the recommended headhunters, links to the scouting documents, etc.

[0107] Information about recommended headhunters is displayed on the job seeker terminal 30, for example, when a job seeker logs in to the service provided by the information processing system 1, when a job seeker displays a list of in-service messages such as scout documents, when a job seeker clears the display of the list (removes from the list), when a scout document is received (specifically, at regular notification times such as daily or weekly), etc. Information about recommended headhunters is also displayed on the job seeker terminal 30 in the form of, for example, a widget, a pop-up, a modal, a dialog, a banner, a push notification, etc.

[0108] The headhunter extraction unit 114 may extract recommended headhunters from among the headhunters from which the user (job seeker) has received scouting documents, and display the scouting documents received from the extracted recommended headhunters or links to the scouting documents on the job seeker terminal 30. This indirectly presents the recommended headhunters to the job seeker by displaying the scouting documents or links to the scouting documents, and also encourages the job seeker to take action (such as replying to the scouting documents) to make contact with the recommended headhunters.

[0109] If the first reference information includes multiple pieces of supplementary reference information, the first reference information may further include multiple message templates associated with each piece of supplementary reference information. A "message template" is a template for an introduction message introducing a scouting letter from a recommended headhunter to a job seeker. The headhunter extraction unit 114 may also display on the job seeker terminal 30 a link to the scouting letter received from the recommended headhunter extracted based on the supplementary reference information, and an introduction message created based on the message template included in the supplementary reference information. This allows the job seeker to be presented with an introduction message that is in line with the proposal policy along with a link to the scouting letter, thereby lowering the psychological hurdle for the job seeker in replying to the scouting letter.

[0110] The message template is prepared in accordance with the proposal policy of the supplementary reference information. For example, if the proposal policy is to increase annual salary, a message template including a message informing the job seeker that the scout is for a job that will increase annual salary is associated with the supplementary reference information. The message template may include a message explaining the criteria or logic used to select recommended headhunters or scout documents, such as, for example, "From the scout documents you have received, we have selected scout documents from highly rated headhunters" or "From the scout documents you have received, we have selected scout documents from headhunters who have a track record of supporting job seekers with careers and experience similar to yours." The introduction message displayed on the job seeker terminal 30 may be the message template as is, or may be a message template with specific information (e.g., information about the headhunter or information about the scout document) inserted therein.

[0111] 5 is a diagram showing an example of a scout document list screen LD displayed on the job seeker terminal 30. The scout document list screen LD displays a list of scout documents that the job seeker has received from a recruiter or a headhunter. The scout document list screen LD is displayed in response to an instruction to display a list of scout documents on the job seeker terminal 30.

[0112] FIG. 6 is a diagram showing an example of a message screen MD displayed on the job seeker terminal 30 to notify the job seeker of a scouting document sent by a recommended headhunter. The message screen MD is displayed, for example, when a job seeker displays the scouting document list screen LD on the job seeker terminal 30 in a case where there is a scouting document sent by a recommended headhunter that the job seeker has not read or replied to. In the example of FIG. 6, the message screen MD is displayed as a pop-up so as to overlap the scouting document list screen LD. The message screen MD includes a message based on a message template and a link SL (message confirmation button) to the scouting document from the recommended headhunter. Note that the entire message screen MD (pop-up screen) may be a link to the scouting document.

[0113] Fig. 7 is a diagram showing an example of a scout document display screen SD displayed on the job seeker terminal 30. The scout document display screen SD displays detailed information (sender, scout content, attached job information (link), etc.) of the scout document selected on the scout document list screen LD, as well as an input field IF for accepting input of a reply to the scout document. Furthermore, when an input operation is performed on the link SL to the scout document on the message screen MD of Fig. 6, the screen displayed on the job seeker terminal 30 transitions to a scout document display screen SD which displays the content of the linked scout document.

[0114] The headhunter extraction unit 114 may extract and present recommended headhunters (displaying links to scouting documents) to job seekers who satisfy predetermined conditions. The "predetermined conditions" may be, for example, having received a scouting document within a predetermined period (e.g., within the past month), having never been hired in the past, being within a predetermined age range, being within a predetermined annual income range, etc. The headhunter extraction unit 114 may determine whether the job seeker information of the user satisfies predetermined conditions, and extract recommended headhunters, display scouting documents or links to scouting documents received from the extracted headhunters, etc., only for job seekers who satisfy the conditions.

[0115] Furthermore, the headhunter extraction unit 114 may extract recommended headhunters for job seekers registered in the database who have at least one of the following characteristics: the number of organizations they have worked for, their current annual salary, and the number of job openings they have come into contact with is below a predetermined value. This allows for priority matching with headhunters for job seekers in specific segments, such as young people and those with little job-changing experience, who are less likely to take action such as replying to scouting documents. As a result, the number of successful experiences of job seekers in specific segments increases across the entire service (matching platform) provided by the information processing system 1, and the support results of headhunters improve.

[0116] "Contact with a job offer" includes, for example, replying to a scouting letter, meeting with a recruiter or headhunter about a job offer, applying for a job, screening after applying for a job (documentation or interview), and hiring decision.

[0117] The headhunter extraction unit 114 may extract recommended headhunters to be recommended to a job seeker from among the headhunters who have sent scouting documents to the job seeker who is a user (who is a target for extraction of recommended headhunters) based on the evaluation value determined by the evaluation unit 113. In this case, the headhunter extraction unit 114 may not use job seeker information to extract recommended headhunters. Furthermore, the headhunter extraction unit 114 may display, on the job seeker terminal 30, scouting documents or links to the scouting documents received from the recommended headhunters extracted based on the evaluation value.

[0118] <Job extraction section 115> The job offer extraction unit 115 is configured to extract at least one recommended job offer to be recommended to a job seeker from among the job offers handled by the recommended headhunters extracted by the headhunter extraction unit 114, based on the job seeker information and handled job offer information acquired by the information acquisition unit 112 and the second reference information. This allows the recommended job offer to be presented to the job seeker together with or instead of the presentation of the recommended headhunter, thereby encouraging the job seeker to take action toward deciding on employment (for example, applying for a job offer).

[0119] The second reference information includes correlations between job seeker information, handled job information, and recommended job offers. The second reference information is stored, for example, in the storage unit 12. The second reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates the correlations between job seeker information, handled job information, and recommended job offers. The correlations included in the second reference information can be constructed, for example, by statistically analyzing data recording combinations of job seeker information and handled job information and corresponding recommended job offers.

[0120] The second reference information may include a recommended job offer determination model, which is a learning model trained by machine learning so that job seeker information and available job offer information can be input and recommended job offers can be output, or a generative AI. In this case, the job offer extraction unit 115 inputs the job seeker information and available job offer information into the recommended job offer determination model and causes the recommended job offer determination model to output recommended job offers. In the recommended job offer determination model, parameters calculated, tuned, etc. by learning constitute correlations in the second reference information.

[0121] The recommended job offer determination model is included in the artificial intelligence unit 120. The recommended job offer determination model, which has been trained to be able to output recommended job offers, is trained using, for example, job seeker information, data on handled job offers, and data on recommended job offers corresponding to these as training data.

[0122] When the recommended job offer determination model is a generation AI including a general-purpose natural language model (large-scale language model), the job offer extraction unit 115 inputs job seeker information and handled job offers, inputs a prompt including an instruction to output recommended job offers corresponding to the job seeker information and the handled job offers to the recommended job offer determination model, and causes the recommended job offers to be output. The job offer extraction unit 115 may generate a prompt that gives the recommended job offer determination model an instruction to determine recommended job offers and inputs the prompt to the recommended job offer determination model. Furthermore, the job offer extraction unit 115 may input, in addition to the instruction to determine and output recommended job offers and the job seeker information and handled job offers, a prompt that inserts, for example, one or more samples of job seeker information and handled job offers and one or more corresponding samples of recommended job offers as examples, samples, or training data of input and output pairs to the recommended job offer determination model.

[0123] The job offer extraction unit 115, for example, displays information about the extracted recommended job offers on the job seeker terminal 30. The "information about recommended job offers" includes, for example, information indicating the recommended job offers, a link to detailed information about the recommended job offers (job postings), etc. The information about recommended job offers may be displayed on the job seeker terminal 30 together with information about recommended headhunters, for example.

[0124] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0125] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with a learning model such as a language model, such as a Transformer (including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4)), a Bidirectional Encoder Representations from Transformers (BERT), a Bidirectional and Auto-regressive Transformer (BART), or a Recurrent Neural Network (RNN). The artificial intelligence unit 120 may be, for example, a generative AI or an AI agent including a large-scale language model. A large-scale language model is a type of generative AI and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. The artificial intelligence unit 120 may also include any machine learning model, deep learning model, artificial intelligence model, or the like.

[0126] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0127] The artificial intelligence unit 120 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). The training data consists of pairs of input data for learning and output data (correct answer data). Furthermore, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0128] The artificial intelligence unit 120 may include a natural language model as its artificial intelligence, or may be a general-purpose natural language processing trained model such as a large-scale language model (LLM). An LLM is a learning model that has previously trained a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). It can perform various language processing tasks when given a task, and can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, answering questions, and generating sentences, according to given prompts. Such a general-purpose learning model includes a language model that can handle various tasks without fine-tuning, using one-shot learning, few-shot learning, etc. Furthermore, a general-purpose learning model may also be configured to handle various tasks using zero-shot learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

[0129] The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as the recommended headhunter determination model) can undergo additional learning using techniques such as transfer learning and fine tuning. For example, each time new data is registered, the artificial intelligence unit 120 may perform additional learning and fine tuning using the new data as new training data. This improves the accuracy of the information output from the learning model.

[0130] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using an original learning model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby learning the student model, which becomes the distilled model. Alternatively, the student model may be learned to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model). Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the learning model. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0131] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the learning model used in each functional unit, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the learning model used in each functional unit.

[0132] An AI agent (which may also be called an autonomous agent) is a model that, when given a goal (purpose, objective, etc.) such as "teach me XX" or a task such as "output XX," breaks down the processing required to reach the goal or accomplish the task into subtasks, actions, etc., and performs the necessary data collection and analysis, program generation, and execution. The AI ​​agent targets information and instructions input by a user, autonomously selects and executes tasks and actions according to the goal, and outputs information according to the goal, without requiring user intervention (operational input). The AI ​​agent may also autonomously learn to achieve its goal by autonomously creating and executing plans and evaluating the execution results. For example, the AI ​​agent may be autonomously updated based on the results of subtask execution (e.g., collected information, information analysis results, etc.).

[0133] <Display section> The display unit 211 of the headhunter terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen (information) indicated by the data transmitted from the server device 10.

[0134] <Operation acquisition part> The operation acquisition unit 212 of the headhunter terminal 20 accepts operations by a headhunter using the headhunter terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by a job seeker using the job seeker terminal 30.

[0135] 3. Information Processing Method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

[0136] This information processing includes an information acquisition step and a headhunter extraction step. In the information acquisition step, job seeker information indicating attributes of the job seeker is acquired. In the headhunter extraction step, at least one recommended headhunter to be recommended to the job seeker is extracted from headhunters who act as agents of the employer and act as intermediaries between the job seeker and the employer, and are registered in the database, based on the job seeker information and the first reference information.

[0137] 8 is an activity diagram showing an example of the flow of information processing (recommended headhunter extraction processing) executed by the information processing system 1. Below, the information processing will be explained along with each activity in this activity diagram.

[0138] The recommended headhunter extraction process begins with the server device 10 acquiring information. The server device 10 acquires job seeker information, headhunter information, first history information, etc. from a database (activity A101). Next, the server device 10 extracts recommended headhunters based on the acquired job seeker information, etc. (activity A102). Furthermore, the server device 10 outputs information on the extracted recommended headhunters to the job seeker terminal 30 (activity A103). As a result, the information on the recommended headhunters is displayed on the job seeker terminal 30 (activity A104).

[0139] 4. Effect The operation of this embodiment can be summarized as follows: That is, it is possible to support matching between headhunters and job seekers.

[0140] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be modified as appropriate within the scope of the technical idea of ​​the invention.

[0141] 5.Other In the above embodiment, the server device 10 performs various storage and control functions. However, multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external component of the server device 10. In this case, the external artificial intelligence unit 120 may be provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. 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 LLM. The artificial intelligence service server receives inputs of prompts such as text, images, and voice, and generates and responds to the prompts.

[0142] At least one of the devices included in the information processing system 1 may be installed outside the country in which the functions of the information processing system 1 are performed.

[0143] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes steps executed by the information processing system 1. The program causes a computer to execute the steps of the information processing system 1.

[0144] The control unit 11 does not necessarily have to include the evaluation unit 113 and the job offer extraction unit 115. For example, the information processing system 1 does not necessarily have to have at least one of the function of evaluating headhunters and the function of extracting recommended jobs.

[0145] The information processing system of the present invention may also be configured as follows. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the information acquisition step, historical information showing the history of intermediary activities of the headhunter who acts as an agent of the employer between the job seeker and the employer is acquired, In the evaluation step, an evaluation of the headhunter is determined based on the history information; In the headhunter extraction step, from among the headhunters who have sent scouting documents to a specific job seeker, headhunters with a predetermined evaluation or higher are extracted as at least one recommended headhunter to be recommended to the specific job seeker, and the information processing system displays the scouting documents received by the specific job seeker from the recommended headhunters or links to the scouting documents.

[0146] It may be provided in the following manner.

[0147] (1) An information processing system comprising at least one processor, the processor being configured to execute the following steps by reading a program: in an information acquisition step, job seeker information indicating attributes of the job seeker is acquired; in a headhunter extraction step, at least one recommended headhunter to be recommended to the job seeker is extracted from headhunters who act as agents of employers and are registered in a database based on the job seeker information and first reference information; wherein the first reference information includes a correlation between the job seeker information and the recommended headhunter.

[0148] (2) In the information processing system described in (1) above, the information acquisition step further acquires headhunter information indicating the attributes of headhunters, and the headhunter extraction step extracts the recommended headhunters based on the job seeker information, the headhunter information, and the first reference information, wherein the first reference information includes a correlation between the job seeker information, the headhunter information, and the recommended headhunters.

[0149] (3) In the information processing system described in (2) above, the headhunter information includes first performance information indicating the attributes of job seekers in whose job search activities the headhunter has been involved, and in the headhunter extraction step, the recommended headhunters are extracted based on the similarity between the attributes of job seekers indicated in the job seeker information and the attributes of job seekers indicated in the first performance information.

[0150] (4) In the information processing system described in (3) above, the first performance information indicates attributes of job seekers in whose hiring decisions the headhunter was involved.

[0151] (5) In the information processing system described in (4) above, the headhunter information includes second performance information indicating attributes of job offers in which the headhunter was involved in hiring decisions, and in the headhunter extraction step, the recommended headhunters are extracted based on the degree of compatibility between the attributes of the job seeker indicated by the job seeker information and the attributes of the job offer indicated by the second performance information, in addition to the similarity.

[0152] (6) An information processing system according to any one of (2) to (5) above, wherein the headhunter information includes basic information or information about the expertise of the headhunter.

[0153] (7) In the information processing system described in any one of (2) to (6) above, the headhunter information includes feedback information to the headhunter from job seekers whose job search activities the headhunter has been involved in.

[0154] (8) In the information processing system described in any one of (2) to (7) above, the information acquisition step further acquires first history information indicating the job seeker's job search history, and the headhunter extraction step extracts the recommended headhunters based on the job seeker information, the first history information, the headhunter information, and the first reference information, wherein the first reference information includes correlations between the job seeker information, the first history information, and the headhunter information and the recommended headhunters.

[0155] (9) In the information processing system described in (8) above, the first history information includes specific job information indicating attributes of a specific job for which the job seeker has taken action, and in the headhunter extraction step, the recommended headhunter is extracted based on a comparison between the attributes of the specific job indicated in the specific job information and the attributes of the job seeker indicated in the job seeker information.

[0156] (10) In the information processing system described in any one of (1) to (9) above, in the information acquisition step, first history information indicating the job seeker's job search history is further acquired, and the first reference information includes a plurality of auxiliary reference information having different types of items referenced in the job seeker information when extracting the recommended headhunters, or different weightings for each item, and in the headhunter extraction step, the recommended headhunters are extracted based on the job seeker information and the auxiliary reference information selected according to the job search history indicated by the first history information.

[0157] (11) In the information processing system described in (10) above, the first reference information further includes a plurality of message templates each corresponding to a plurality of the supplementary reference information, wherein the message template is a template of an introduction message introducing a scouting document from the recommended headhunter to a job seeker, and the headhunter extraction step displays a link to the scouting document received from the recommended headhunter extracted based on the supplementary reference information, and the introduction message created based on the message template included in the supplementary reference information.

[0158] (12) In the information processing system described in any one of (1) to (11) above, in the headhunter extraction step, the recommended headhunters are extracted from the headhunters from whom the job seeker has received a scouting document, and the scouting document received from the extracted recommended headhunter or a link to the scouting document is displayed.

[0159] (13) In the information processing system described in any one of (1) to (12) above, the information acquisition step further acquires second history information indicating the history of the headhunter's intermediary activities, and the processor is configured to further execute the following steps: the evaluation step determines an evaluation of the headhunter based on the second history information, and the headhunter extraction step extracts the recommended headhunter from among headhunters whose evaluation is above a predetermined level.

[0160] (14) In the information processing system described in any one of (1) to (13) above, in the headhunter extraction step, the recommended headhunter is extracted for a job seeker for whom at least one of the number of organizations the job seeker has worked for, the current annual income, and the number of job openings the job seeker has come into contact with is equal to or less than a predetermined value.

[0161] (15) In the information processing system described in any one of (1) to (14) above, the information acquisition step further acquires job information handled that indicates attributes of job offers associated with the headhunter and stored, and the processor is configured to further perform the following steps: in the job offer extraction step, based on the job seeker information, the job information handled, and second reference information, extract at least one recommended job offer to be recommended to the job seeker from the job offers handled by the recommended headhunter, and the second reference information includes a correlation between the job seeker information, the job information handled, and the recommended job offer.

[0162] (16) An information processing method, comprising steps executed by the information processing system according to any one of (1) to (15) above.

[0163] (17) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (15) above. Of course, this is not the case.

[0164] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0165] 1: Information processing system 10: Server device 11: Control section 111: Basic display control section 112: Information acquisition department 113: Evaluation section 114: Headhunter Extraction Department 115: Job extraction department 120: Artificial Intelligence Department 12: Storage section 13: Communications Department 14: Communication bus 2: Communication line 20: Headhunter terminal 21: Control unit 211:Display section 212: Operation acquisition section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job seeker terminal 31: Control unit 311: Display section 312: Operation acquisition section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus LD: Scout document list screen MD: Message screen SD: Scout document display screen SL: Link

Claims

1. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the information acquisition step, job seeker information indicating attributes of job seekers and headhunter information indicating attributes of headhunters are acquired, wherein the headhunter information includes first performance information indicating attributes of job seekers in whose job search activities the headhunter has been involved; In the headhunter extraction step, based on the job seeker information, the headhunter information, and first reference information, at least one recommended headhunter to be recommended to the job seeker is extracted from among headhunters who are registered in a database and act as agents of employers and act as intermediaries between job seekers and employers, based on the similarity between at least one of the job seeker attributes indicated in the job seeker information, namely, career history, experience, skills, age, address, and annual income, and at least one of the job seeker attributes indicated in the first performance information, namely, career history, experience, skills, age, address, and annual income, wherein the first reference information includes a correlation between the job seeker information, the headhunter information, and the recommended headhunter.

2. 2. The information processing system according to claim 1, An information processing system, wherein the first performance information indicates attributes of job seekers whose hiring decisions the headhunter was involved in.

3. 3. The information processing system according to claim 2, the headhunter information includes second performance information indicating attributes of job offers in which the headhunter was involved in hiring decisions; In the headhunter extraction step, the recommended headhunters are extracted based on the similarity as well as the degree of compatibility between the attributes of the job seeker indicated by the job seeker information and the attributes of the job offer indicated by the second performance information.

4. 2. The information processing system according to claim 1, An information processing system in which the headhunter information includes basic information or information regarding the expertise of the headhunter.

5. 2. The information processing system according to claim 1, An information processing system in which the headhunter information includes feedback information to the headhunter from job seekers whose job-seeking activities the headhunter has been involved in.

6. 2. The information processing system according to claim 1, The information acquisition step further acquires first history information indicating a history of job search activities of the job seeker, In the headhunter extraction step, the recommended headhunters are extracted based on the job seeker information, the first history information, the headhunter information, and the first reference information, wherein the first reference information includes correlations between the job seeker information, the first history information, and the headhunter information, and the recommended headhunters.

7. 7. The information processing system according to claim 6, the first history information includes specific job offer information indicating attributes of a specific job offer for which the job seeker has taken an action; In the headhunter extraction step, the information processing system extracts the recommended headhunters based on a comparison between attributes of the specific job offer indicated by the specific job offer information and attributes of the job seeker indicated by the job seeker information.

8. 2. The information processing system according to claim 1, The information acquisition step further acquires first history information indicating a history of job search activities of the job seeker, the first reference information includes a plurality of auxiliary reference information items each having a different weighting for each of the items or types of items referenced in the job seeker information when extracting the recommended headhunters, In the headhunter extraction step, the recommended headhunters are extracted based on the job seeker information and the supplementary reference information selected according to the job search activity history indicated by the first history information.

9. 9. The information processing system according to claim 8, the first reference information further includes a plurality of message templates respectively associated with the plurality of supplementary reference information, wherein the message templates are templates of introduction messages for introducing scouting documents from the recommended headhunters to job seekers; In the headhunter extraction step, an information processing system displays a link to a scouting document received from the recommended headhunter extracted based on the supplementary reference information, and the introduction message created based on the message template included in the supplementary reference information.

10. 2. The information processing system according to claim 1, In the headhunter extraction step, the information processing system extracts the recommended headhunters from among the headhunters from whom the job seeker has received scout documents, and displays the scout documents received from the extracted recommended headhunters or links to the scout documents.

11. 2. The information processing system according to claim 1, The information acquisition step further acquires second history information indicating a history of intermediary activities of the headhunter; The processor is further configured to perform the steps of: In the evaluation step, an evaluation of the headhunter is determined based on the second history information; In the headhunter extraction step, the recommended headhunters are extracted from among headhunters whose evaluations are equal to or higher than a predetermined value.

12. 2. The information processing system according to claim 1, In the headhunter extraction step, the information processing system extracts the recommended headhunters for job seekers for whom at least one of the number of organizations they have worked for, their current annual income, and the number of job openings they have come into contact with is equal to or less than a predetermined value.

13. 2. The information processing system according to claim 1, In the information acquisition step, job information representing attributes of the job vacancies stored in association with the headhunter is further acquired, The processor is further configured to perform the steps of: In the job extraction step, at least one recommended job to be recommended to the job seeker is extracted from the job offers handled by the recommended headhunter based on the job seeker information, the handled job information, and second reference information, wherein the second reference information includes a correlation between the job seeker information, the handled job information, and the recommended job offer.

14. An information processing method, comprising: An information processing method comprising the steps executed by the information processing system according to any one of claims 1 to 13.

15. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 13.

Images