Information processing systems, information processing methods, and programs

Abstract

We provide an information processing system, information processing method, and program that can support the matching of employers and job seekers. [Solution] In the information processing system, the server device acquires input information about the recruiter who sent the scouting document received by the job seeker, extracts recommended recruiters for each of the multiple evaluation indicators based on the input information about the recruiter and multiple different evaluation indicators, and generates proposal information corresponding to the recommended recruiters based on the input information about the recommended recruiters and reference information for generating proposal information. The reference information for generating proposal information includes at least the correlation between the input information about the recommended recruiters and the proposal information, and the proposal information includes at least the reasons for recommending the recommended recruiters. The server device further associates the generated proposal information with the scouting document from which the recommended recruiter corresponding to the proposal information originated or a link to said scouting document, and displays it on the job seeker's terminal.

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a technology for supporting matching between recruiters and job seekers. [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2013-246453 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] There is a need for a technology that supports matching between recruiters and job seekers.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that can support matching between recruiters and job seekers. [Means for Solving the Problem]

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program: an acquisition step in which input information relating to an employer who is the sender of a scout document received by a job seeker is acquired; an extraction step in which recommended employers to be recommended to the job seeker are extracted for each of the multiple evaluation indicators based on the input information relating to the employer and a plurality of mutually different evaluation indicators; a generation step in which proposal information corresponding to the recommended employer is generated based on input information relating to the recommended employer and reference information for generating proposal information, the reference information for generating proposal information at least includes the correlation between the input information relating to the recommended employer and the proposal information, the proposal information at least includes the reasons for recommending the recommended employer; and a display control step in which the generated proposal information is associated with a scout document from which the recommended employer corresponding to the proposal information is the sender or a link to said scout document, and displayed to the job seeker.

[0007] This approach can support the matching of employers and job seekers. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of server device 10. [Figure 3] This block diagram shows the hardware configuration of the job seeker terminal 20 and the job applicant terminal 30. [Figure 4] This is a block diagram showing the functions realized by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). [Figure 5] This figure shows an example of the proposal information display screen PD shown on the job seeker terminal 30. [Figure 6] This is an activity diagram showing an example of the flow of information processing (display processing of proposed information) performed by Information Processing System 1. [Modes for carrying out the invention]

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

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

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

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

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

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

[0015] <Information Processing System 1> Figure 1 is a configuration diagram representing information processing system 1. Information processing system 1 comprises a communication line 2, a server device 10, multiple recruiter terminals 20, and multiple job seeker terminals 30. The server device 10, recruiter terminals 20, and job seeker terminals 30 are configured to communicate with each other via the communication line 2. The connection between the server device 10, recruiter terminals 20, and job seeker terminals 30 may be wired or wireless. Furthermore, the server device 10, recruiter terminals 20, and job seeker terminals 30 are each examples of "information processing devices".

[0016] Information processing system 1 constitutes at least a part of a job posting and job search system used by multiple employers (first employer U1 and second employer U2) and multiple job seekers (first job seeker U3 and second job seeker U4). Information processing system 1 primarily performs tasks such as employers searching for job seekers, job seekers searching for job postings, and mediating communication between employers and job seekers. For example, information processing system 1 provides and manages a talent matching platform, talent matching services, and job change / employment support services used by employers and job seekers. In one embodiment, information processing system 1 consists of one or more devices or components. These components will be described below.

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

[0018] <Control Unit 11> The control unit 11 processes and controls overall operations related to the server device 10. The control unit 11 is, for example, a Central Processing Unit (CPU), which is an example of a processor. The control unit 11 implements various functions related to the server device 10 by reading a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 is specifically implemented by the control unit 11, which is an example of hardware, so that the control unit 11 can be executed as each functional unit included therein. These will be described in further detail in the next section. Note that the number of the control unit 11 is not limited to one, and the server device 10 may include a plurality of control units 11 for each function. Further, the server device 10 may be configured by a combination of these.

[0019] <Storage Unit 12> The storage unit 12 stores various types of information defined by the above description. The storage unit 12 can be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs related to the server device 10 executed by the control unit 11, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) for program operations. The storage unit 12 stores various programs, variables, and the like related to the server device 10 executed by the control unit 11.

[0020] <Communication Unit 13> Although wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), and wired LAN network communication are preferable for the communication unit 13, the communication unit 13 may also include wireless LAN network communication, mobile communication such as LTE / 5G, BLUETOOTH (registered trademark) communication, and the like as necessary. That is, the communication unit 13 may be implemented as a set of the plurality of communication means. Further, the server device 10 may communicate various types of information with the outside via the communication unit 13 and a network.

[0021] The server device 10 may be on-premises or in a cloud environment. A cloud-based server device 10 may provide the above-mentioned functions and processing in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] <Job seeker terminal 20> Figure 3 is a block diagram showing the hardware configuration of the employer terminal 20 and the job seeker terminal 30. The employer terminal 20 is an information processing terminal used by employers and can access the server device 10.

[0023] "Employers" include organizations that conduct recruitment activities or their personnel. Employers are, for example, those who intend to hire job seekers or those who conduct the selection process for job seekers. Personnel within employers may also be called recruitment officers, and these officers may include personnel in the organization's human resources department or personnel in the department responsible for hiring. Employers may also include headhunters. Headhunters are organizations or their personnel that act as agents for employers, mediating between job seekers and employers. Headhunters are also called recruitment agencies, hiring agents, etc.

[0024] Here, "hiring" may also be called "contracting." Furthermore, "hiring" may include not only the decision of the job seeker to find employment or change jobs, but also the offer of employment from the employer to the job seeker, the job seeker's acceptance of the offer, and the job seeker's joining the employer's company.

[0025] Furthermore, "organization" includes for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.). In addition, "organization" is not limited to a single legal entity, but may also include a group composed of multiple legal entities with capital relationships or partnerships (e.g., a group consisting of a parent company, subsidiaries, affiliated companies, etc.).

[0026] As shown in Figure 3A, the job seeker terminal 20 comprises a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, storage unit 22, communication unit 23, input unit 24, and output unit 25 are electrically connected within the job seeker terminal 20 via the communication bus 26. The descriptions of the control unit 21, storage unit 22, and communication unit 23 are the same as the descriptions of each part in the server device 10 and are therefore omitted.

[0027] <Input section 24> The input unit 24 receives operation inputs made by the user. The operation inputs are transmitted as command signals to the control unit 21 via the communication bus 26. The control unit 21 can perform predetermined controls or calculations based on the transmitted command signals as needed. The input unit 24 may be included in the housing of the job seeker terminal 20 or it may be an external component. 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, the input unit 24 can be a switch button, mouse, trackpad, QWERTY keyboard, etc.

[0028] <Output section 25> The output unit 25 displays a graphical user interface (GUI) screen that can be operated by the user. The output unit 25 may be included in the housing of the job seeker terminal 20 or it may be an external device. Specifically, the output unit 25 can be implemented as a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display. It is preferable that these display devices be used according to the type of job seeker terminal 20.

[0029] <Job seeker terminal 30> The job seeker terminal 30 is an information processing terminal used by job seekers and is accessible to the server device 10. "Job seekers" include various types of people seeking employment, such as those who are looking to change jobs or find employment (e.g., currently employed people (those seeking a job change), prospective graduates (job seekers), students, etc.), and those who are interested in changing jobs or finding employment. Job seekers are, for example, those who are interested in changing jobs or finding employment with an employer, those who wish to change jobs or find employment with an employer, and those who plan to change jobs or find employment with an employer.

[0030] As shown in Figure 3B, the job seeker terminal 30 comprises a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are electrically connected within the job seeker terminal 30 via the communication bus 36. The descriptions of the control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are the same as the descriptions of each part in the employer terminal 20 and are therefore omitted.

[0031] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory 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 provided by the information processing system 1).

[0032] Figure 4 is a block diagram showing the functions realized by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0033] As shown in Figure 4A, the server device 10 (control unit 11) comprises a basic display control unit 111, an information acquisition unit 112, a job applicant extraction unit 113, a proposed information generation unit 114, a display control unit 115, and an artificial intelligence unit 120.

[0034] As shown in Figure 4B, the job seeker terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212.

[0035] As shown in Figure 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0036] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the employer terminal 20 or the job seeker terminal 30. For example, the basic display control unit 111 displays input information about job seekers and registration information about employers registered in the database on the display unit 211 of the employer terminal 20 or the display unit 311 of the job seeker terminal 30, in response to requests from each user (employers U1, U2 or job seekers U3, U4). Input information about job seekers includes, for example, the job seeker's registration information and the job seeker's history information. Input information about employers includes, for example, the employer's registration information and the employer's history information.

[0037] <Information acquisition unit 112> The information acquisition unit 112 is configured to acquire information related to job seekers, employers, job postings, etc. The information acquisition unit 112 is configured to acquire input information about the employer who sent the recruitment letter received by the job seeker. The information acquisition unit 112 may also acquire input information about the job seeker and input information about the employer who sent the recruitment letter received by the job seeker.

[0038] "Job seeker registration information" includes, for example, the job seeker's basic information (name, age, gender, address, etc.), current employment information (organization, industry, department, job title, duties, job description, position, annual income, etc.), and past employment information.

[0039] The registration information of job seekers may include, for example, a resume, which is a document detailing the job seeker's work history, experience, skills, qualifications, etc., to employers. The work history document may include the job seeker's resume, other profile information, and conditions such as the type of industry or job the job seeker desires. A "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, work history, and desired working conditions. The work history document may be automatically generated by artificial intelligence such as generation AI, or it may be created by the job seeker themselves.

[0040] In this specification, "generation" may be used interchangeably with "creation," and encompasses all processing methods for obtaining an object as a result of processing. For example, this may include processing to construct an object from scratch, processing to reconstruct existing information by modifying or processing it, and processing to identify an object by extracting or selecting specific information from a predetermined data set such as a list.

[0041] The input information regarding job seekers may include first history information (job seeker history information) that shows the history of the job seeker's job-seeking activities. Here, the first history information (job seeker history information) may include at least one of the following: the status of receiving scout documents, the status of replies to scout documents, the history of actions taken regarding job postings, and the history of interactions with artificial intelligence. Furthermore, the first history information may include, for example, the login status to services provided by the information processing system 1, the date and time of registration or update of registration information, etc. Here, a scout document refers to an email, message, SNS (Social Networking Service) post, chat, notification, etc., sent by an employer or headhunter to a job seeker, such as a job seeker or a recent graduate, to encourage them to apply for selection or propose an interview, and may also be called a scout email.

[0042] "Receipt status of recruitment letters" includes, for example, the number of recruitment letters received, the date of receipt of the recruitment letters, information about the headhunter or recruiter who received the recruitment letter (for example, the attributes of the headhunter described below, or the attributes of the recruiter such as the size of the organization or the industry), and information about the job posting attached to the recruitment letter (for example, job attributes such as job title, duties, position, and working conditions).

[0043] "Status of responses to recruitment letters" includes, for example, the number of responses to recruitment letters, the timing of responses, the number of days from receiving the recruitment letter to responding, information about the headhunter or recruiter who sent the responded recruitment letter, and information about the job description attached to the responded recruitment letter.

[0044] "Job-related activity history" includes, for example, the number of times job postings were viewed during a specified period, the number of applications for jobs during a specified period, the number of job postings added to the bookmark list during a specified period, the job postings viewed (job attributes), the job postings applied for, and the job postings added to the bookmark list.

[0045] A bookmark list (also known as a "favorites list" or "interesting list") is a list prepared for each job seeker, where they can register any job postings they wish to work on. By referring to their bookmark list, job seekers can select from the registered job postings to take action on, such as viewing or applying for them.

[0046] The "history of interaction with artificial intelligence" includes, for example, a record of the content of interactions between job seekers and artificial intelligence. The history of interaction with artificial intelligence may include, for example, exchanges between job seekers and artificial intelligence regarding confirmation of the job seeker's desired conditions, consultation regarding career changes, adjustment of conditions for job searches, and exchange of feedback on suggested information (not limited to natural language dialogue, but also including the selection of options and predetermined input operations). The artificial intelligence that interacts with job seekers may be called an AI agent or AI concierge.

[0047] "Login status to the service" may include, for example, the number of logins during a specified period, the number of days elapsed since the last login, etc. Furthermore, the first history information may also include the registration period for the service (the period elapsed since registration of the registration information).

[0048] The first history information may include specific job information that indicates the attributes of a specific job posting in which the job seeker took action. "Specific job postings" include, for example, job postings viewed by the job seeker, job postings applied for by the job seeker, job postings added to the job seeker's bookmark list, job postings listed or attached to recruitment documents replied to by the job seeker, job postings introduced to the job seeker during interviews, etc., and job postings that passed the screening (document or interview). "Specific job information" includes, for example, the recruitment conditions of a specific job posting.

[0049] "Job seeker registration information" refers to information registered in a database, including, for example, information about the job seeker themselves. If the job seeker is a headhunter, the job seeker registration information may include, for example, a profile, self-introduction, department name, job title, work location (area of ​​responsibility), educational background, areas of expertise (industry, job type, annual salary, age, work location, etc.), specialization, years of experience, language skills, etc. Furthermore, the job seeker registration information may include, for example, information about the organization itself (if the job seeker is an organization), the organization to which the job seeker belongs (if the job seeker is a representative of the organization), or the organization on which the job seeker acts as an agent (if the job seeker is a headhunter), such as information indicating the business content, industry, organizational size, performance, products or services handled, financial status, and management plan. In addition, the job seeker registration information may include information about the entire organization (for example, the business content, industry, performance of the entire organization), or information about a part of the organization (for example, a business unit, department to which the job seeker belongs) (for example, the business content, industry, performance of a single business unit).

[0050] "Job postings" typically refer to job applications, but they do not necessarily need to be formatted like job applications. They can also be unstructured documents such as memos that at least list the requirements.

[0051] "Description of the organization or business" is a job description document that explains at least one of the following: the organization, industry, department, job type, duties, position, annual salary, and work style. For example, the job description document may include a description of the organization's history, business environment, characteristics, a specific description of the job type or duties, and a description of working conditions.

[0052] In addition to requirements, job postings may include descriptions of the ideal candidate, the organization, or the work itself. "Ideal candidate" refers to keywords or phrases that describe the attributes of the persona the employer is seeking. These attributes may include, for example, age, gender, job title, position, behavioral characteristics, interests, personality, values, and attitude.

[0053] The job seeker registration information may include headhunter information that indicates the attributes of the headhunter. Headhunter information may include, for example, basic information of the headhunter (e.g., name, gender, age, address, etc.), and information on their area of ​​expertise or specialization in at least one of the following: industry, job type, annual income, age, and work location. This makes it possible for the job seeker extraction unit 113, described later, to extract job seekers based on the commonality of basic information (e.g., address) between the user (job seeker) and the headhunter, or based on the headhunter's knowledge and experience regarding the industry, job type, etc., that the job seeker wishes to work in. As a result, it is possible to extract recommended job seekers (recommended headhunters) who are highly suitable for the job seeker's current situation and desired conditions, encouraging job seekers to respond to messages (scout documents) from headhunters and increasing the response rate.

[0054] The input information regarding the employer may include first-hand information indicating the attributes of the involved job seeker, who is a job seeker in whom the employer has been involved in the job search activities. "Job search activities" in which the employer has been involved include, for example, sending recruitment letters to involved job seekers, receiving replies to recruitment letters from involved job seekers, interviews or meetings with involved job seekers, other communication with involved job seekers (telephone calls, sending and receiving messages, etc.), introducing job openings to involved job seekers, and supporting involved job seekers until they are hired by the employer.

[0055] The information about the job seekers involved, included in the first performance information, consists of the same items as the job seeker's information, and includes, for example, the basic information of the involved job seeker (name, gender, age, address, etc.) or registration information including work history.

[0056] The first performance information may indicate the attributes of the job seekers involved in the hiring decision, among the job seekers involved. This allows the employer extraction unit 113, described later, to extract employers by referring to the attributes of the job seekers involved in the hiring decision, thereby matching job seekers (users) with employers. In particular, if the employer is a headhunter, for example, it can extract headhunters with hiring experience in the same or similar industries, occupations, ages, and areas as the job seeker, or messages from such headhunters. This allows for prompting job seekers to respond to messages (scout documents) from employers.

[0057] The job seeker's registration information may include second-tier performance information indicating the attributes of the job postings in which the headhunter was involved in the hiring decision. "Involved job postings" are job postings that were previously associated with a headhunter (for example, job postings that the headhunter acted as an agent for) in which the hiring of the involved job seeker was decided through the headhunter's activities.

[0058] The information about job postings included in the second performance information consists of the same items as the specific job posting information included in the first history information of the user (job seeker). For example, it includes the industry, job title, duties, position, required skills (required experience), annual salary, work location, and employment type of the specific job posting.

[0059] The input information regarding the employer may include second-tier history information (the employer's history information). Second-tier history information may include, for example, the contents of a recruitment letter sent by the employer to the job seeker (for example, job information written or attached to the recruitment letter).

[0060] The second set of historical information may also include information showing the headhunter's history of intermediary activities. "Second set of historical information" is information for evaluating the headhunter and includes the history of intermediary activities for multiple job seekers. "Intermediary activities" may include, for example, the first activity and the second activity.

[0061] "First activities" refer to the initial stages of a headhunter's work, such as understanding a job seeker's career and job-seeking intentions, and supporting their preparation. These "first activities" also include activities such as supporting the job seeker's self-analysis and confirming their employment intentions. For example, a headhunter might conduct interviews with the job seeker (especially the initial interview) and support the job seeker's self-reflection activities as first activities. A headhunter may also support the job seeker in creating their resume and work history as a first activity. Supporting the job seeker's self-reflection activities involves communication via telephone, interviews, email, etc., to help the job seeker clarify their purpose or reasons for seeking employment, their desired workplace, or conditions. These first activities take place before the headhunter introduces the job seeker's information to the client (organization) or recommends the job seeker.

[0062] "Second activity" refers to activities in which a headhunter supports communication between job seekers and employers during the recruitment process, thereby facilitating job placement. "Second activity" also includes activities that support communication between job seekers and employers. For example, a headhunter may perform the following as second activities: mediating job seekers' applications, mediating communication between job seekers and employers, assisting in setting up or preparing interviews or meetings between job seekers and employers, and assisting job seekers in securing employment. Furthermore, if a headhunter assists a job seeker in preparing their resume, work history, etc., after introducing a job seeker to an employer, this assistance is included in second activities. Additionally, a headhunter may perform the following as second activities after a job seeker has received a job offer: confirming or negotiating working conditions such as contract period and wages, and mediating or assisting the job seeker in accepting or declining the offer.

[0063] Furthermore, if the job seeker is seeking a new job, the headhunter may also provide support for the job seeker's resignation from their current organization as a second activity. Support for resignation includes, for example, advice on when to submit resignation, how to write a resignation letter, and how to negotiate with supervisors, HR departments, etc. Thus, the second activity includes activities after the headhunter has introduced or recommended a job seeker to an employer. Moreover, the second activity is a separate activity that does not overlap with the first activity, and may include only activities after the headhunter has introduced or recommended a job seeker to an employer.

[0064] The second history information may include information indicating the content of the first and / or second activities (specific activity details, points corresponding to the activities, etc.), and may also include information indicating the job seeker's evaluation of the headhunter for the first and / or second activities (first evaluation information and / or second evaluation information). The job seeker's evaluation is collected, for example, through a questionnaire presented on the job seeker terminal 30. The job seeker's evaluation of the headhunter may also include, for example, a score indicating satisfaction.

[0065] The second set of historical information may include information on the headhunter's hiring record. This hiring record information may also be called hiring support record information, and may include, for example, the number of job offers, the number of successful hires, the number of employees hired, the offer rate, the hiring rate, the employee hiring rate, and the average annual salary for the jobs filled by the headhunter. Furthermore, the second set of historical information may also include information on rule compliance. This rule compliance information indicates the degree to which the headhunter complied with the rules established in the first or second activity. These rules are established to ensure that the headhunter's activities are conducted at a certain level, and may include, for example, a rule that "when supporting job seekers' self-reflection activities, interviews should be conducted in person or by telephone."

[0066] The input information regarding job seekers may include handling job information that indicates the attributes of the job that has been linked to and stored by the headhunter. "Job that has been linked to and stored by the headhunter" refers to, for example, job that the headhunter is acting on behalf of (intermediating) (i.e., a job that can be introduced to the job seeker or a job description can be attached to a recruitment letter sent to the job seeker).

[0067] The information acquisition unit 112 may be configured to acquire feedback information from job seekers, including evaluations of employers. This allows for the extraction of recommended employers based on evaluations from job seekers (for example, job seekers involved in the job search activities of the employer). As a result, it becomes possible to match individual job seekers with more suitable employers.

[0068] Feedback information is obtained, for example, through questionnaires presented to the job seeker's terminal 30 at predetermined times (e.g., after a certain period of time has elapsed since receiving a scout offer, after an interview, after a job offer has been made, etc.). These questionnaires include, for example, an evaluation of the employer (e.g., a 5-point scale), comments on what was good, and comments on what was bad.

[0069] Feedback information may be weighted according to the time elapsed since the aforementioned predetermined timing when the participating job seeker provided feedback. For example, the shorter the time between receiving the questionnaire and responding to it, the greater the weight; the longer the time, the less weight it receives. Feedback information may also be weighted based on when the feedback was given. For example, the more recent the feedback (current or close to a predetermined reference time), the greater the weight; the further back in time the feedback was given, the less weight it receives.

[0070] The information acquisition unit 112 may be configured to acquire information regarding responses from job seekers to recruitment documents sent by recruiters. Information regarding responses may include, for example, the response rate from job seekers (e.g., involved job seekers) to recruitment documents sent by recruiters, and the speed of the recruiter's response to contact from job seekers (e.g., involved job seekers) (e.g., within ○ days of the recruiter sending the recruitment document).

[0071] <Recruiter extraction section 113> The job seeker extraction unit 113 is configured to extract recommended job seekers for each of the multiple evaluation indicators based on input information about job seekers and multiple evaluation indicators that are different from each other. The job seeker extraction unit 113 may also extract at least one recommended job seeker based on input information about job seekers and at least one evaluation indicator. In other words, a recommended job seeker is at least one job seeker that is extracted based on input information about job seekers and at least one evaluation indicator.

[0072] Recommended employers may be employers whose input information satisfies predetermined conditions. These predetermined conditions may include, for example, a minimum number of characters, a maximum number of characters, and a threshold for the occurrence of keywords identical or similar to a specific keyword. The employer extraction unit 113 may control which employers are included in the extraction of recommended employers based on the predetermined conditions. For example, the employer extraction unit 113 may control whether or not to include an employer in the extraction of recommended employers based on the amount of information provided in the employer's registration information (e.g., profile, self-introduction, etc.) (for example, employers who have provided 200 characters or more may be included in the extraction of recommended employers). The employer extraction unit 113 may also control whether or not to include an employer in the extraction of recommended employers based on, for example, the frequency or number of occurrences of keywords identical or similar to a specific keyword in the employer's registration information. For example, if a specific keyword is a general term (e.g., a term that frequently appears in profiles), the employer extraction unit 113 may control whether or not to exclude employers whose frequency or number of occurrences of the specific keyword exceeds a threshold from the extraction of recommended employers. This makes it possible to suppress the inclusion of job seekers whose profiles are formulaic and lack originality or expertise in the selection process, thus enabling the extraction of recommended job seekers without reducing convenience for job seekers. On the other hand, the job seeker extraction unit 113 may, for example, control the selection process to include job seekers whose frequency or occurrence rate of a particular keyword is above a threshold if that keyword is a highly specialized term, as recommended job seekers. This makes it possible to extract more highly specialized recommended job seekers.

[0073] The evaluation metrics are the first evaluation metric, the second evaluation metric, the third evaluation metric, the fourth evaluation metric, the fifth evaluation metric, or a combination thereof. Multiple evaluation metrics include at least one of the first, second, third, fourth, and fifth evaluation metrics and may be combined with any other evaluation metric. For example, multiple evaluation metrics may include at least one of the first and second evaluation metrics.

[0074] The job seeker extraction unit 113 may extract recommended job seekers for each of the multiple evaluation indicators based on the input information about the job seekers and the multiple evaluation indicators, which include at least one of the first evaluation indicator and the second evaluation indicator.

[0075] The first evaluation metric is an indicator that represents the similarity between the input information about job seekers and the input information about employers. If the employer is a headhunter, the first evaluation metric may be an indicator that represents the similarity between the job seeker's registration information and the headhunter's information.

[0076] The first evaluation indicator may be an indicator that represents the similarity (whether it is identical or close to the conditions) between the conditions desired by the job seeker (e.g., industry, job type, annual salary, work location, etc.) and the registered information of the employer (e.g., if the employer is a headhunter, this would be work location, educational background, areas of expertise, specialization, past placement record, etc.; if the employer is an organization, this would be the organization's business content, industry, performance, etc.). This indicator may be evaluated using, for example, cosine similarity, but is not limited to this. If the recommended employer extraction model described later is a general-purpose learning model (e.g., a language model such as a large-scale language model), the recommended employer extraction model may be input with input information about the employer and a prompt that includes instructions to extract recommended employers based on the first evaluation indicator, and the recommended employer extraction model may be output. By extracting recommended employers based on the first evaluation indicator, it becomes possible to propose employers that are a good fit for the job seeker.

[0077] The second evaluation indicator is, for example, an indicator that represents the specificity of the information entered regarding job applicants.

[0078] The second evaluation indicator may be, for example, an indicator that represents the specificity of the information contained in the applicant's registration information, such as their profile and self-introduction. For example, if the applicant is a headhunter, this indicator would represent whether the applicant's registration information includes specific details of their past support achievements (e.g., age, company, change in annual income, etc.), or if the applicant is an organization, it would represent whether the organization's registration information includes specific details of its business activities, industry, performance, etc. Alternatively, the second evaluation indicator may be, for example, an indicator that represents the level of attentiveness in the applicant's registration information. For example, if the applicant is a headhunter, this indicator would represent whether the applicant's registration information includes details of the applicant's own career, anecdotes, personality, hobbies, etc., or if the applicant is an organization, it would represent whether the applicant's registration information includes details of the organization's values, culture, etc. The second evaluation indicator may be, for example, a combination of an indicator that represents the specificity of the applicant's registration information and an indicator that represents the level of attentiveness in the applicant's registration information. Furthermore, the employer extraction unit 113 may extract recommended employers to job seekers for each of the multiple evaluation indicators, based on the input information about employers and multiple evaluation indicators, including at least an indicator representing the specificity of the employer's registration information and an indicator representing the level of attentiveness of the employer's registration information. If the recommended employer extraction model described later is a general-purpose learning model (for example, a language model such as a large-scale language model), the recommended employer extraction model may be input with the input information about employers and a prompt including an instruction to extract recommended employers based on the second evaluation indicator, and the recommended employer extraction model may be output. By extracting recommended employers based on the second evaluation indicator, it becomes possible to suggest employers that job seekers can trust more or employers with whom they can interact more attentively.

[0079] A third evaluation metric is, for example, an indicator representing the specificity of the recruiter's resume information (e.g., the content of the recruitment letter sent by the recruiter). The third evaluation metric may also be an indicator representing the specificity of the job information contained in the recruitment letter sent by the recruiter.

[0080] The third evaluation metric may be, for example, an indicator representing the specificity of the job information described or attached to the recruitment document sent by the recruiter. This indicator may include, for example, whether or not job information is described in the recruitment document, whether or not job information is attached to the recruitment document, the number and amount of job information described, etc. If the recommended recruiter extraction model described later is a general-purpose learning model (for example, a language model such as a large-scale language model), the recommended recruiter extraction model may be input with input information about the recruiter and a prompt that includes an instruction to extract recommended recruiters based on the third evaluation metric, and the recommended recruiter extraction model may be output. By extracting recommended recruiters based on the third evaluation metric, it becomes possible to suggest recruiters who have already proposed job information or who have provided specific job information in past communications with other job seekers to job seekers who want to advance their job search early.

[0081] The fourth evaluation metric is, for example, an indicator that shows the consistency between feedback information and the input information about job seekers.

[0082] The fourth evaluation metric may be, for example, an indicator that shows the consistency between the evaluation of an employer obtained from a job seeker and the input information about the employer. For example, if the employer is a headhunter, this metric may be the consistency (gap) between the description in the employer's registration information (for example, a description that they are available on weekday evenings and weekends) and the evaluation (for example, one of the negative points of the employer is that their schedule did not match on weekday evenings and weekends). Alternatively, the fourth evaluation metric may be, for example, an indicator that shows the consistency between the employer's registration information and the employer's history information. If the recommended employer extraction model described later is a general-purpose learning model (for example, a language model such as a large-scale language model), the recommended employer extraction model may be input with the input information about the employer and a prompt that includes an instruction to extract recommended employers based on the fourth evaluation metric, and the recommended employers may be output by the recommended employer extraction model. By extracting recommended employers based on the fourth evaluation indicator, it becomes possible to suggest employers to job seekers whose track record is guaranteed by their historical information and feedback information (evaluations from other job seekers), rather than suggesting employers based solely on the descriptive information in their registration details.

[0083] The fifth evaluation metric is, for example, an indicator that represents information about the responses from job seekers to recruitment letters sent by employers.

[0084] The fifth evaluation metric may be, for example, an indicator representing the response rate from job seekers (e.g., involved job seekers) to recruitment documents sent by employers. If the recommended employer extraction model described later is a general-purpose learning model (e.g., a language model such as a large-scale language model), the recommended employer extraction model may be input with input information about employers and a prompt containing instructions to extract recommended employers based on the fifth evaluation metric, and the recommended employers may be output by the recommended employer extraction model. By extracting recommended employers based on the fifth evaluation metric, it becomes possible to suggest employers who have received responses from a larger number of job seekers to job seekers.

[0085] Furthermore, if the recommended employer extraction model described later is a general-purpose learning model (for example, a language model such as a large-scale language model), the recommended employer extraction model may be input with input information about the employer and a prompt that includes instructions to extract at least one recommended employer based on multiple evaluation indicators, using the input information about the employer as input, and the recommended employer extraction model may be output. In this case, the multiple evaluation indicators may include, but are not limited to, at least one of the first, second, third, fourth, and fifth evaluation indicators. For example, employers may be extracted whose input information about the employer matches the conditions desired by the job seeker (e.g., industry, job type, annual salary, work location, etc.) (first evaluation indicator), and whose recruitment information is attached to the scout document (third evaluation indicator). This makes it possible to recommend employers that better meet the diverse needs of job seekers.

[0086] The evaluation metrics are not limited to numerical indicators, but may also include qualitative indicators that define the qualities of recommended job seekers, or instructions for identifying recommended job seekers.

[0087] The job seeker extraction unit 113 may be configured to extract recommended job seekers based on input information about job seekers, evaluation indicators, and extraction reference information. In this case, the extraction reference information includes at least the correlation between the input information about job seekers, evaluation indicators, and recommended job seekers.

[0088] The reference information for extraction includes information on the correlation between input information about job seekers, evaluation indicators, and recommended job seekers. This reference information is stored, for example, in the memory unit 12. The reference information may also include, for example, tables, functions, simple algorithms, etc., that show the correlation between input information about job seekers, evaluation indicators, and recommended job seekers. The correlations included in the reference information for extraction can be constructed, for example, by statistically analyzing data that records input information about job seekers, evaluation indicators, and corresponding recommended job seekers.

[0089] The extraction reference information may include a set of parameters for extracting recommended job seekers from input information about job seekers and evaluation indicators. For example, the extraction reference information may be various pre-trained models. For example, the extraction reference information may include a recommended job seeker extraction model, which is a dedicated learning model or a general-purpose learning model that has been machine-trained to be able to extract recommended job seekers using input information about job seekers and evaluation indicators as input. In this case, the job seeker extraction unit 113 inputs the input information about job seekers and evaluation indicators into the recommended job seeker extraction model and causes the recommended job seeker extraction model to extract recommended job seekers.

[0090] The recommended job seeker extraction model is included in the artificial intelligence unit 120. The recommended job seeker extraction model, which is a dedicated learning model, may be constructed by training using, for example, data of input information and evaluation indicators regarding job seekers, and corresponding data of recommended job seekers, as training data. In such a recommended job seeker extraction model, parameters calculated and tuned through training construct a correlation between the input information regarding job seekers, evaluation indicators, and recommended job seekers. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be generated or the content of the task to be executed.

[0091] If the recommended employer extraction model is a general-purpose learning model (for example, a language model such as a large-scale language model), the employer extraction unit 113 inputs a prompt to the recommended employer extraction model that includes an instruction to extract recommended employers corresponding to the input information and evaluation index of the said employer, taking the input information and evaluation index of the said employer as input, and causes the recommended employer extraction model to output recommended employers. The employer extraction unit 113 may also generate a prompt that gives an instruction to the recommended employer extraction model to extract recommended employers and input this prompt to the recommended employer extraction model. In addition, the employer extraction unit 113 may input a prompt to the recommended employer extraction model that includes, in addition to the input information and evaluation index of the employer and the instruction to output recommended employers, inserts, for example, one or more samples of input information and evaluation index of the employer and one or more samples of recommended employers corresponding to them, as examples, samples, or training data of input and output pairs. Here, parameters for constructing a recommended job seeker extraction model and prompts containing instructions for extracting recommended job seekers corresponding to input information and evaluation metrics about job seekers establish a correlation between the input information about job seekers, the evaluation metrics, and the recommended job seekers. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0092] The reference information for extraction may include a recommended job seeker extraction model, which is a machine learning model or generative AI, that is capable of extracting at least one recommended job seeker by taking input information about job seekers and several different evaluation metrics as inputs. In this case, the input information about job seekers and several different evaluation metrics are input to the recommended job seeker extraction model, and the recommended job seeker extraction model is made to extract at least one recommended job seeker.

[0093] The recruiter extraction unit 113 may be configured to extract recommended recruiters based on input information about job seekers, input information about recruiters, evaluation indicators, and reference information for extraction. In this case, the reference information for extraction includes at least the correlation between the input information about job seekers, input information about recruiters, evaluation indicators, and recommended recruiters.

[0094] The reference information for extraction includes information on the correlation between input information about job seekers, input information about employers, and evaluation indicators, and recommended employers. The reference information for extraction is stored, for example, in the memory unit 12. The reference information for extraction may also include, for example, tables, functions, simple algorithms, etc., that show the correlation between input information about job seekers, input information about employers, and evaluation indicators, and recommended employers. The correlations included in the reference information for extraction can be constructed, for example, by statistically analyzing data that records input information about job seekers, input information about employers, and evaluation indicators, and the corresponding recommended employers.

[0095] The extraction reference information may include a set of parameters for extracting recommended employers from input information about job seekers, input information about employers, and evaluation indicators. For example, the extraction reference information may be various pre-trained models. For example, the extraction reference information may include a recommended employer extraction model, which is a dedicated learning model or a general-purpose learning model that has been machine-trained to be able to extract recommended employers using input information about job seekers, input information about employers, and evaluation indicators as input. In this case, the employer extraction unit 113 inputs the input information about job seekers, input information about employers, and evaluation indicators into the recommended employer extraction model and causes the recommended employer extraction model to extract recommended employers.

[0096] A dedicated learning model, such as a recommended employer extraction model, may be constructed by training it using, for example, data on job seekers, employers, and evaluation metrics, along with corresponding recommended employer data, as training data. In such a recommended employer extraction model, parameters calculated and tuned through training establish a correlation between the input information on job seekers, employers, and evaluation metrics, and the recommended employers. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI in the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be generated or the content of the task to be executed.

[0097] If the recommended employer extraction model is a general-purpose learning model (for example, a language model such as a large-scale language model), the employer extraction unit 113 inputs the input information about job seekers, the input information about employers and evaluation indicators, and the recommended employer extraction model into the recommended employer extraction model, which takes the input information about job seekers, the input information about employers and evaluation indicators as input, and includes a prompt that includes an instruction to extract recommended employers corresponding to the input information about job seekers, the input information about employers and evaluation indicators, causing the recommended employer extraction model to output recommended employers. The employer extraction unit 113 may also generate a prompt that gives an instruction to the recommended employer extraction model to extract recommended employers and input the prompt into the recommended employer extraction model. Furthermore, the recruiter extraction unit 113 may input prompts to the recommended recruiter extraction model that include, for example, one or more samples of input and output pairs, such as input information about job seekers, input information about recruiters, and evaluation indicators, and one or more corresponding samples of recommended recruiters, as examples, samples, or training data of input and output pairs. Here, the parameters for constructing the recommended recruiter extraction model and the prompts that include instructions to extract recommended recruiters corresponding to the input information about job seekers, input information about recruiters, and evaluation indicators construct a correlation between the input information about job seekers, input information about recruiters, and evaluation indicators and the recommended recruiters. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input of instructions such as the content of the output information to be generated and the content of the task to be executed.

[0098] <Proposal information generation unit 114> The proposal information generation unit 114 is configured to generate proposal information corresponding to recommended job seekers based on input information about recommended job seekers and reference information for proposal information generation. In this case, the reference information for proposal information generation includes at least the correlation between the input information about recommended job seekers and the proposal information.

[0099] The input information for recommended job seekers is the input information about the job seekers extracted by the job seeker extraction unit 113.

[0100] The suggestion information includes at least the reasons for recommending the recommended job seeker. The reasons for recommending the recommended job seeker are, for example, natural language recommendation statements such as "Continuing a 0% turnover rate in the first year after changing jobs," "Consultant specializing in planning positions," "Proposals include job descriptions," and "Support from a partner with multiple job change experience." The suggestion information generation unit 114 may also generate suggestion information that includes tag words representing evaluation indicators. Here, the tag words are keywords that help job seekers make decisions when selecting a job seeker by representing the evaluation indicators used to extract recommended job seekers. For example, the first evaluation indicator may include "Specialized Match," the second evaluation indicator may include "Reliability" or "Attentiveness," and the third evaluation indicator may include "Job Openings." The suggestion information generation unit 114 may also generate suggestion information that includes job seeker introduction information. The job seeker introduction information includes words that indicate the attributes and characteristics of the job seeker. For example, catchphrases such as "Expert in the XX Industry" or "Supporter of Medium- to Long-Term Careers." Furthermore, the suggestion information may also include input information about the recommended job seeker.

[0101] The reference information for generating suggestion information is information regarding the correlation between input information about recommended job seekers and suggestion information. The reference information for generating suggestion information is stored, for example, in the memory unit 12. The reference information for generating suggestion information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between input information about recommended job seekers and suggestion information. The correlations included in the reference information for generating suggestion information can be constructed, for example, by statistically analyzing data that records input information about recommended job seekers and corresponding suggestion information.

[0102] The reference information for generating suggestion information may include a set of parameters for outputting suggestion information from input information about recommended job seekers. For example, the reference information for generating suggestion information may be various pre-trained models. For example, the reference information for generating suggestion information may include a suggestion information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take input information about recommended job seekers as input and output suggestion information. In this case, the suggestion information generation unit 114 inputs the input information about recommended job seekers into the suggestion information generation model and causes the suggestion information generation model to output suggestion information.

[0103] The proposal information generation model is included in the artificial intelligence unit 120. The proposal information generation model, which is a dedicated learning model, may be constructed by training using, for example, data of input information about recommended job seekers and data of corresponding proposal information as training data. In such a proposal information generation model, parameters calculated and tuned through training build a correlation between the input information about recommended job seekers and the proposal information. The dedicated learning model may include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be output or the content of the task to be executed.

[0104] If the suggestion information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the suggestion information generation unit 114 inputs input information about recommended job seekers and a prompt that includes an instruction to output suggestion information corresponding to the input information about recommended job seekers, causing the suggestion information generation unit to generate the suggestion information. The suggestion information generation unit 114 may also generate a prompt that gives the suggestion information generation model an instruction to output suggestion information and input this prompt to the suggestion information generation unit. In addition, the suggestion information generation unit 114 may input a prompt to the suggestion information generation unit that includes, in addition to the input information about recommended job seekers and the instruction to output suggestion information, an example of input and output pairs, such as one or more samples of input information about recommended job seekers and one or more samples of suggestion information corresponding to them, as example, sample, or training data. Here, the parameters that construct the suggestion information generation model and the prompt that includes an instruction to output suggestion information corresponding to the input information about recommended job seekers construct a correlation between the input information about recommended job seekers and the suggestion information. Furthermore, a general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. The generative AI in a general-purpose learning model is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0105] The reference information for generating suggestion information may include a suggestion information generation model, which is a machine learning model or a generation AI capable of taking input information about recommended job seekers as input and outputting suggestion information. In this case, the input information about recommended job seekers is input into the suggestion information generation model, and the suggestion information generation model is made to output suggestion information.

[0106] Furthermore, the proposal information generation unit 114 may be configured to generate proposal information corresponding to recommended employers based on input information about job seekers, input information about recommended employers, and reference information for proposal information generation. In this case, the reference information for proposal information generation includes at least the correlation between the input information about job seekers and the input information about recommended employers and the proposal information.

[0107] The reference information for generating suggestion information may include a set of parameters for outputting suggestion information from input information about job seekers and input information about recommended employers. For example, the reference information for generating suggestion information may be various pre-trained models. For example, the reference information for generating suggestion information may include a suggestion information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take input information about job seekers and input information about recommended employers as input and output suggestion information. In this case, the suggestion information generation unit 114 inputs the input information about job seekers and input information about recommended employers into the suggestion information generation model and causes the suggestion information generation model to output suggestion information.

[0108] A dedicated learning model, such as a suggestion information generation model, may be constructed by training it using, for example, data on job seekers and recommended employers, along with corresponding suggestion information data, as training data. In such a suggestion information generation model, parameters calculated and tuned through training establish a correlation between the input information on job seekers and recommended employers and the suggestion information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI in the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be output or the content of the task to be performed.

[0109] If the proposal information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the proposal information generation unit 114 inputs to the proposal information generation model an instruction to output proposal information corresponding to the input information about job seekers and the input information about recommended employers, taking the input information about job seekers and the input information about recommended employers as input, and causes the proposal information generation unit to generate proposal information. The proposal information generation unit 114 may also generate a prompt that gives the proposal information generation model an instruction to output proposal information and input this prompt to the proposal information generation unit. In addition, the proposal information generation unit 114 may input to the proposal information generation unit a prompt that includes, in addition to the input information about job seekers and the input information about recommended employers and the instruction to output proposal information, one or more samples of input information about job seekers and the input information about recommended employers and one or more samples of corresponding proposal information as examples, samples, or training data of input and output pairs. Here, parameters for constructing a proposal information generation model and prompts containing instructions to output proposal information corresponding to input information about job seekers and input information about recommended employers establish a correlation between the input information about job seekers and recommended employers and the proposal information. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0110] The reference information for generating suggestion information may include a suggestion information generation model, which is a machine learning model or generation AI, that is capable of outputting suggestion information by taking input information about job seekers and input information about recommended employers as input. In this case, the input information about job seekers and input information about recommended employers are input into the suggestion information generation model, and the suggestion information generation model is made to output suggestion information.

[0111] The proposal information generation unit 114 may output proposal information based on input information regarding recommended job seekers, at least one evaluation index used when extracting the recommended job seekers, and reference information for proposal information generation. In this case, the reference information for proposal information generation includes at least the correlation between the input information regarding recommended job seekers, at least one evaluation index used when extracting the recommended job seekers, and the proposal information.

[0112] The reference information for generating suggestion information may include a set of parameters for outputting suggestion information from input information about recommended job seekers and at least one evaluation metric used when extracting the recommended job seekers. For example, the reference information for generating suggestion information may be various pre-trained models. For example, the reference information for generating suggestion information may include a suggestion information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take input information about recommended job seekers and at least one evaluation metric used when extracting the recommended job seekers as input and output suggestion information. In this case, the suggestion information generation unit 114 inputs the input information about recommended job seekers and at least one evaluation metric used when extracting the recommended job seekers into the suggestion information generation model and causes the suggestion information generation model to output suggestion information.

[0113] A dedicated learning model, the suggestion information generation model, may be constructed by training it using, for example, input information about recommended job seekers and data of at least one evaluation metric used when extracting the recommended job seekers, along with corresponding suggestion information data, as training data. In such a suggestion information generation model, parameters calculated and tuned through training establish a correlation between the input information about recommended job seekers, at least one evaluation metric used when extracting the recommended job seekers, and the suggestion information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI in the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be output or the content of the task to be executed.

[0114] If the proposal information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the proposal information generation unit 114 inputs a prompt to the proposal information generation model that includes an instruction to output proposal information corresponding to the input information about the recommended job seeker and at least one evaluation index used when extracting the recommended job seeker, and causes the proposal information generation model to generate proposal information. The proposal information generation unit 114 may also generate a prompt that gives the proposal information generation model an instruction to output proposal information and input the prompt to the proposal information generation model. Furthermore, the proposal information generation unit 114 may input prompts to the proposal information generation model that include, for example, one or more samples of the input information about the recommended job seekers and at least one evaluation index used when extracting the recommended job seekers, as well as an instruction to output proposal information, as examples, samples, or training data of input and output pairs, such as one or more samples of the input information about the recommended job seekers and at least one evaluation index used when extracting the recommended job seekers, and one or more samples of proposal information corresponding to them. Here, the parameters for constructing the proposal information generation model and the prompts that include an instruction to output proposal information corresponding to the input information about the recommended job seekers and at least one evaluation index used when extracting the recommended job seekers establish a correlation between the input information about the recommended job seekers and at least one evaluation index used when extracting the recommended job seekers, and the proposal information. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input of instructions such as the content of the output information to be generated and the content of the task to be executed.

[0115] The reference information for generating suggestion information may include a suggestion information generation model, which is a machine learning model or generation AI, that is capable of outputting suggestion information by taking input information about recommended job seekers and at least one evaluation metric used when extracting recommended job seekers as input. In this case, the input information about recommended job seekers and at least one evaluation metric used when extracting recommended job seekers are input into the suggestion information generation model, and the suggestion information generation model is made to output suggestion information.

[0116] The proposal information generation unit 114 may output proposal information based on input information about job seekers, input information about recommended employers, at least one evaluation index used when extracting the recommended employers, and reference information for proposal information generation. In this case, the reference information for proposal information generation includes at least the correlation between the input information about job seekers, the input information about recommended employers, and at least one evaluation index used when extracting the recommended employers, and the proposal information.

[0117] The reference information for generating suggestion information may include a set of parameters for outputting suggestion information from input information about job seekers, input information about recommended employers, and at least one evaluation metric used when extracting the recommended employers. For example, the reference information for generating suggestion information may be various pre-trained models. For example, the reference information for generating suggestion information may include a suggestion information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take input information about job seekers, input information about recommended employers, and at least one evaluation metric used when extracting the recommended employers as input and output suggestion information. In this case, the suggestion information generation unit 114 inputs the input information about job seekers, input information about recommended employers, and at least one evaluation metric used when extracting the recommended employers into the suggestion information generation model and causes the suggestion information generation model to output suggestion information.

[0118] A dedicated learning model, the suggestion information generation model, may be constructed by training it using, for example, data on job seekers, recommended employers, and at least one evaluation metric used to extract the recommended employers, along with corresponding suggestion information data, as training data. In such a suggestion information generation model, parameters calculated and tuned through training establish a correlation between the input information on job seekers, the input information on recommended employers, at least one evaluation metric used to extract the recommended employers, and the suggestion information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI in the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be output or the content of the task to be performed.

[0119] If the proposal information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the proposal information generation unit 114 inputs a prompt to the proposal information generation model that includes an instruction to output proposal information corresponding to the input information about the job seeker, the input information about the recommended employer, and the at least one evaluation index used when extracting the recommended employer, taking the input information about the job seeker, the input information about the recommended employer, and the at least one evaluation index used when extracting the recommended employer as input, causing the proposal information generation model to generate proposal information. The proposal information generation unit 114 may also generate a prompt that gives an instruction to the proposal information generation model to output proposal information, and input the prompt to the proposal information generation model. Furthermore, the proposal information generation unit 114 may input prompts to the proposal information generation model that include, for example, one or more samples of input and output pairs, such as input information about job seekers, input information about recommended employers, and at least one evaluation index used when extracting the recommended employers, and an instruction to output proposal information, as well as one or more samples of corresponding proposal information, such as one or more samples of input information about job seekers, input information about recommended employers, and at least one evaluation index used when extracting the recommended employers, and one or more sample proposal information, as examples, samples, or training data of input and output pairs. Here, the input information about job seekers, input information about recommended employers, and at least one evaluation index used when extracting the recommended employers, and the prompts that include an instruction to output proposal information corresponding to the input information about job seekers, input information about recommended employers, and at least one evaluation index used when extracting the recommended employers, establish a correlation between the input information about job seekers, input information about recommended employers, and at least one evaluation index used when extracting the recommended employers, and the proposal information. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the input information. Generative AI for general-purpose learning models is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0120] The reference information for generating suggestion information may include a suggestion information generation model, which is a machine learning model or generation AI, that is capable of outputting suggestion information by taking input information about job seekers, input information about recommended employers, and at least one evaluation metric used when extracting the recommended employers as input. In this case, the input information about job seekers, input information about recommended employers, and at least one evaluation metric used when extracting the recommended employers are input into the suggestion information generation model, and the suggestion information generation model is made to output suggestion information.

[0121] <Display Control Unit 115> The display control unit 115 is configured to display to the job seeker the generated proposal information and the scout document sent by the recommended recruiter corresponding to the proposal information, or a link to said scout document. The display control unit 115 may also display to the job seeker the proposal information including tag words. The display control unit 115 may also display at least one of the generated proposal information, the scout document sent by the recommended recruiter corresponding to the proposal information, and a link to the scout document. Here, the display control unit 115 may control whether to display scout documents and / or links to scout documents that the job seeker has already replied to.

[0122] Figure 5 shows an example of a proposal information display screen PD displayed on the job seeker terminal 30. The proposal information display screen PD includes a recruiter display area ER, recruiter introduction information EI about recommended recruiters, a recommendation statement RM about recommended recruiters, a tag word TW representing the evaluation indicators used to select the recommended recruiters, and a link SL (message confirmation button) to the scout document received from the recommended recruiter. In Figure 5, the proposal information includes recruiter introduction information EI about recommended recruiters, a recommendation statement RM about recommended recruiters, and a tag word TW representing the evaluation indicators used to select the recommended recruiters. By selecting the link SL (message confirmation button), the job seeker transitions to the screen displaying the scout document received from the recommended recruiter. The link SL does not necessarily need to be displayed; the job seeker may also transition to the screen displaying the scout document received from the recommended recruiter by selecting the recruiter display area ER, recommendation statement RM, tag word TW, etc. In addition, although not shown in the figure, the proposal information display screen PD may display all or part of the scout document received from the recommended recruiter.

[0123] In Figure 5, the suggested information display screen PD includes multiple job seeker display areas ER. These multiple job seeker display areas ER display the corresponding recommendation text RM, tag words TW, and link SL for each recommended job seeker. By displaying recommended job seekers, extracted based on multiple different evaluation indicators, side-by-side for job seekers, job seekers can compare the factors they prioritize in job seekers. This configuration enables job seekers to find job seekers who are a better fit for them.

[0124] The proposal information display screen (PD) may be displayed as a pop-up, for example, on the job seeker's list of scout documents or on the screen immediately after logging into the service. This allows for the re-presentation of scout documents from recommended employers, carefully selected based on multiple evaluation indicators, from among previously received but unread or unreplied-to scout documents, along with generated proposal information (e.g., specific reasons why they match the job seeker's attributes and intentions). As a result, it not only prevents job seekers from overlooking scout documents, but also allows job seekers to intuitively understand the importance and suitability of the scout document through the proposal information, effectively encouraging proactive responses from job seekers. Furthermore, by generating proposal information using a proposal information generation model, the rationale for recommending an employer can be specifically articulated and presented for each employer through specific evaluation indicators. This has the effect of improving the sense of satisfaction and confidence in matching compared to conventional, standardized recommendation messages.

[0125] <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 each functional unit of the server device 10 may be common to all units, or it may be prepared individually for each functional unit.

[0126] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with trained models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNN). The artificial intelligence unit 120 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include specific models such as OpenAI's GPT (registered trademark), Google's Gemini (registered trademark), and models provided through services and platforms such as Microsoft's Azure (registered trademark) AI Studio. Generative AI may be, for example, text generation AI, image generation AI, multimodal generation AI, etc. The trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 120 can include any pre-trained model.

[0127] Specific machine learning algorithms used to build trained models include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply these algorithms as appropriate.

[0128] 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 consists of pairs of input data and output data (correct answer data) for training. Furthermore, the trained model may not only be one trained for a specific task, but also a general-purpose learning model that can be used universally for a wide range of tasks.

[0129] The artificial intelligence unit 120 may include a natural language model as artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by One-shot Learning or Few-shot Learning. Furthermore, the general-purpose learning model may also be configured to handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate pre-trained model, or it may be a common general-purpose pre-trained model. In addition, the artificial intelligence unit 120 may include a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model as a pre-trained model. Small-scale and medium-scale language models are natural language processing models that are trained on less data (and constructed with fewer parameters) compared to large-scale language models.

[0130] The pre-trained models included in the artificial intelligence unit 120 (pre-trained models used in each functional unit) can undergo additional training using methods such as transfer learning and fine-tuning. For example, whenever new data is registered, the artificial intelligence unit 120 may perform additional training and fine-tuning using this new data as training data. This improves the accuracy of the information output from the pre-trained models.

[0131] The trained model included in the artificial intelligence unit 120 may be a trained model (distilled model) obtained by knowledge distillation using the original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as the teacher model, and the student model is trained by adjusting the parameters of the student model so that the loss of the student model's output (soft target loss) relative to the teacher model's output (soft target) is small, and that student model becomes the distilled model. Alternatively, the student model may be trained so that the loss of the student model's output (hard target loss) relative to the correct labels (hard target) of the teacher data (combinations of input data and output data of the training model) is small. Compared to the original training model (teacher model), the distilled model has performance close to that of the trained model, but with fewer parameters and a lower processing load. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0132] For example, the trained model used in each functional unit may be a distilled model trained using combinations of input and output data from a large-scale language model as training data. Alternatively, when the information processing system 1 is introduced, a large-scale language model may be used as the trained model in each functional unit, and once training data from the large-scale language model has been accumulated, the distilled model obtained by knowledge distillation using that training data may be used as the trained model in each functional unit.

[0133] An AI agent (also called an autonomous agent) may, in response to a goal (objective, purpose, etc.) or task (output of XX) input by a user, break down the task into subtasks, actions, etc., in order to reach the goal or accomplish the task, and may perform at least one of the following actions: collecting and analyzing necessary data, using external tools, generating and executing programs, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks, actions, etc. according to the goal, and outputs information according to the goal, and does not require user intervention (operation input). However, the AI ​​agent may request confirmation or feedback from the user as needed. Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously perform learning (including in-context learning, etc.) to aim at achieving the goal or improving the accuracy of achievement. For example, the AI ​​agent may autonomously update based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.). Note that the AI ​​agent may be configured as a multi-agent system comprising multiple AI agents. In this case, multiple AI agents may have different roles, capabilities, or access privileges. Multiple AI agents may cooperate to solve tasks by communicating (dialogue) with each other using natural language or a predetermined protocol. The cooperation between each AI agent is not limited to a hierarchical structure (superior-subordinate relationship), and multiple AI agents may autonomously discuss and vote, and the final output may be decided by consensus.

[0134] <Display section> The display unit 211 of the job seeker terminal 20 shown in Figure 4B, and the display unit 311 of the job seeker terminal 30 shown in Figure 4C, respectively, display the screen (information) indicated by the data transmitted from the server device 10.

[0135] <Operation acquisition part> The operation acquisition unit 212 of the employer terminal 20 receives operations from the employer using the employer terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 receives operations from the job seeker using the job seeker terminal 30.

[0136] 3. Information Processing Methods This section describes the information processing method of the server device 10. In this information processing method, each part of the server device 10 is executed by a computer as a step.

[0137] The above-described information processing method comprises an acquisition step, an extraction step, a generation step, and a display control step. In the acquisition step, input information about the employer who sent the scout document received by the job seeker is acquired. In the extraction step, recommended employers to be recommended to the job seeker are extracted for each of the multiple evaluation indicators based on the input information about the employer and multiple different evaluation indicators. In the generation step, proposal information corresponding to the recommended employer is generated based on the input information about the recommended employer and reference information for generating proposal information, and includes at least the reasons for recommending the recommended employer. In the display control step, the generated proposal information is associated with the scout document from which the recommended employer corresponding to the proposal information originated, or a link to said scout document, and displayed to the job seeker.

[0138] Figure 6 is an activity diagram showing an example of the flow of information processing (display processing of proposed information) performed by the information processing system 1. Below, the information processing will be explained according to each activity in this activity diagram.

[0139] The process of displaying the proposed information begins with information acquisition by the server device 10. The server device 10 acquires input information, etc., regarding the employer who sent the scout document received by the job seeker (Activity A101). Next, the server device 10 extracts recommended employers based on the acquired information, etc. (Activity A102). Furthermore, the server device 10 generates proposed information based on the input information, etc., regarding the extracted recommended employers (Activity A103). After generating the proposed information, the server device 10 outputs the proposed information to the job seeker terminal 30 (Activity A104). As a result, the proposed information is displayed on the job seeker terminal 30 (Activity A105).

[0140] 4. Effect The function of this embodiment can be summarized as follows: It can support the matching of employers and job seekers. In particular, by extracting recommended employers based on at least one evaluation metric and displaying suggested information, it becomes possible to recommend suitable employers to job seekers.

[0141] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0142] 5. Others In the above embodiment, the server device 10 performed various storage and control functions, but instead of the server device 10, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the external artificial intelligence unit 120 may be provided by, for example, an artificial intelligence service server, and is configured to receive input 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. In this case, each functional unit of the server device 10 causes the artificial intelligence unit 120 to output recommended job seekers and proposal information. The artificial intelligence service server may be a server that provides services using a learning model, or a server that performs language processing tasks using a language model. In particular, the artificial intelligence service server may be constructed using an LLM. The artificial intelligence service server receives prompt input in the form of text, images, audio, etc., and generates and responds with answers to the prompts.

[0143] At least one of the devices included in the information processing system 1 may be located outside the country in which the functions of the information processing system 1 are performed.

[0144] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. In the information processing method, the information processing device executes each step of the information processing system 1. In the program, the computer causes the computer to execute each step of the information processing system 1.

[0145] The product may be provided in any of the following embodiments.

[0146] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, the acquisition step of acquiring input information relating to an employer who is the source of a scout document received by a job seeker, the extraction step of extracting recommended employers to recommend to the job seeker for each of the multiple evaluation indicators based on the input information relating to the employer and a plurality of mutually different evaluation indicators, the generation step of generating proposal information corresponding to the recommended employer based on input information relating to the recommended employer and reference information for generating proposal information, wherein the reference information for generating proposal information includes at least the correlation between the input information relating to the recommended employer and the proposal information, and the proposal information includes at least the reasons for recommending the recommended employer, and the display control step of displaying the generated proposal information to the job seeker in association with the scout document from which the recommended employer corresponding to the proposal information is the source or a link to the scout document.

[0147] (2) In the information processing system described in (1) above, the reference information for generating the proposed information includes a proposed information generation model which is a machine learning model or a generation AI that is capable of taking the input information relating to the recommended job seeker as input and outputting the proposed information, and in the generation step, the input information relating to the recommended job seeker is input to the proposed information generation model and the proposed information generation model is made to output the proposed information.

[0148] (3) In the information processing system described in (2) above, in the acquisition step, input information relating to the job seeker is further acquired, and in the extraction step, based on the input information relating to the employer and the plurality of evaluation indicators including at least one of the first evaluation indicator and the second evaluation indicator, recommended employers to be recommended to the job seeker are extracted for each of the plurality of evaluation indicators, where the first evaluation indicator is an indicator that represents the similarity between the input information relating to the job seeker and the input information relating to the employer, and the second evaluation indicator is an indicator that represents the specificity of the input information relating to the employer, and in the generation step, the job seeker An information processing system that generates proposal information corresponding to the recommended job seeker based on input information relating to the job seeker, input information relating to the recommended job seeker, and reference information for generating proposal information, wherein the reference information for generating proposal information includes a proposal information generation model which is a machine learning model or generation AI that is capable of taking the input information relating to the job seeker and the input information relating to the recommended job seeker as input and outputting the proposal information, and in the generation step, the input information relating to the job seeker and the input information relating to the recommended job seeker are input to the proposal information generation model and the proposal information generation model is made to output the proposal information.

[0149] (4) An information processing system as described in (3) above, wherein the input information relating to the recruiter further includes the recruiter's history information including the contents of the scout document sent by the recruiter, and the plurality of evaluation indicators further includes a third evaluation indicator, wherein the third evaluation indicator is an indicator representing the specificity of the job information contained in the contents of the scout document.

[0150] (5) An information processing system as described in (3) above, wherein the input information relating to the job seeker further includes the job seeker's history information, and the job seeker's history information includes at least one of the following: the status of receiving a scouting document, the status of replying to a scouting document, the history of actions taken in response to job postings, and the history of conversations with artificial intelligence.

[0151] (6) In the information processing system described in (1) above, the recommended job seeker is a job seeker whose input information satisfies predetermined conditions, and the predetermined conditions include at least one of a minimum number of characters, a maximum number of characters, and a threshold for the appearance of keywords identical or similar to a specific keyword.

[0152] (7) An information processing system as described in (1) above, wherein in the generation step, a tag word representing the evaluation index is generated as the proposed information, and in the display control step, the proposed information including the tag word is displayed to the job seeker.

[0153] (8) An information processing system as described in (3) above, wherein in the acquisition step, feedback information including an evaluation of the employer is acquired from the job seeker, the plurality of evaluation indicators further include a fourth evaluation indicator, the fourth evaluation indicator is an indicator representing the consistency between the feedback information and the input information concerning the employer.

[0154] (9) Information processing system as described in (3) above, wherein the acquisition step acquires information from job seekers regarding a scout document sent by the recruiter, and the plurality of evaluation indicators further include a fifth evaluation indicator, the fifth evaluation indicator being an indicator representing the information regarding the reply.

[0155] (10) Information processing system as described in (3) above, wherein the recruiter is a headhunter, the input information relating to the recruiter includes headhunter information indicating the attributes of the headhunter, the headhunter information includes at least one area of ​​expertise such as industry, occupation, annual income, age, and work location, and the plurality of evaluation indicators include at least the first evaluation indicator, the first evaluation indicator is an indicator representing the similarity between the registered information relating to the job seeker and the headhunter information.

[0156] (11) In the information processing system described in (1) above, in the extraction step, recommended job seekers are extracted based on the input information relating to the job seeker, the evaluation index, and the reference information for extraction, wherein the reference information for extraction includes at least the correlation between the input information relating to the job seeker, the evaluation index, and the recommended job seeker.

[0157] (12) The information processing system described in (1) above, comprising a server having the processor and a terminal that can access the server.

[0158] (13) An information processing method comprising each step performed by the information processing system described in any one of (1) to (11) above.

[0159] (14) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (11) above. Of course, this is not always the case.

[0160] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0161] 1: Information Processing System 2: Communication lines 10: Server device 11: Control Unit 111: Basic Display Control Unit 112: Information acquisition department 113: Recruiter extraction department 114: Proposal information generation section 115: Display Control Unit 120: Artificial Intelligence Department 12: Storage section 13: Communications Department 14: Communications bus 20: Job seeker terminal 21: Control Unit 211:Display section 212: Operation acquisition section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications 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: Communications bus PD: Proposal information display screen ER: Recruiter display area EI: Job Posting Information RM: Recommendation TW: Tag words SL: Link

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, the input information about the employer who sent the recruitment letter received by the job seeker is obtained. In the extraction step, based on the input information about the job seeker and a plurality of different evaluation indicators, recommended job seekers are extracted for each of the plurality of evaluation indicators. In the generation step, based on the input information regarding the recommended job seeker and the reference information for generating the proposal information, proposal information corresponding to the recommended job seeker is generated, and here, The aforementioned reference information for generating the proposed information includes at least the correlation between the input information regarding the recommended job seeker and the proposed information. The aforementioned proposed information includes at least the reasons for recommending the aforementioned recommended job seekers, An information processing system that, in the display control step, associates the generated proposal information with the scout document or a link to the scout document, which is sent by the recommended recruiter corresponding to the proposal information, and displays them to the job seeker.

2. In the information processing system described in claim 1, The aforementioned reference information for generating proposal information includes a machine learning model or a generation AI proposal information generation model that is capable of taking the input information regarding the recommended job seeker as input and outputting the proposal information. An information processing system that, in the generation step, inputs input information regarding the recommended job seekers into the proposal information generation model and causes the proposal information generation model to output the proposal information.

3. In the information processing system described in claim 2, In the aforementioned acquisition step, further input information about the job seeker is acquired, In the extraction step, based on the input information regarding the job seeker and the plurality of evaluation indicators, which include at least one of the first evaluation indicator and the second evaluation indicator, recommended job seekers to be recommended are extracted for each of the plurality of evaluation indicators, and here, The first evaluation index is an index that represents the degree of similarity between the input information concerning the job seeker and the input information concerning the employer. The second evaluation indicator is an indicator that represents the specificity of the input information regarding the job applicant, In the generation step described above, based on the input information regarding the job seeker, the input information regarding the recommended employer, and the reference information for generating the proposal information, proposal information corresponding to the recommended employer is generated, and here, The aforementioned reference information for generating proposal information includes a proposal information generation model, which is a machine learning model or generation AI, that is capable of taking the input information regarding the job seeker and the input information regarding the recommended employer as input and outputting the proposal information. An information processing system that, in the generation step, inputs input information regarding the job seeker and input information regarding the recommended employer into the proposal information generation model, and causes the proposal information generation model to output the proposal information.

4. In the information processing system described in claim 3, The input information relating to the said recruiter further includes the recruiter's history information, including the content of the scouting document sent by the recruiter. The aforementioned multiple evaluation indicators further include a third evaluation indicator, where, The third evaluation indicator is an information processing system that represents the specificity of the job information contained in the scout document.

5. In the information processing system described in claim 3, The input information relating to the job seeker further includes the job seeker's history information, An information processing system that includes, for the aforementioned job seeker's history information, at least one of the following: the status of receiving a recruitment letter, the status of responding to a recruitment letter, the history of actions taken regarding job postings, and the history of interactions with artificial intelligence.

6. In the information processing system described in claim 1, The aforementioned recommended employers are employers whose input information regarding them satisfies the specified conditions. An information processing system in which the predetermined conditions include at least one of the minimum number of characters, the maximum number of characters, and a threshold relating to the occurrence rate or frequency of keywords identical or similar to a specific keyword.

7. In the information processing system described in claim 1, In the generation step, tag words representing the evaluation indicators are generated as the proposed information. The information processing system, in the display control step, displays the proposed information, including the tag words, to the job seeker.

8. In the information processing system described in claim 3, In the acquisition step described above, feedback information, including an evaluation of the employer, is obtained from the job seeker. The aforementioned multiple evaluation indicators further include a fourth evaluation indicator, The fourth evaluation indicator is an information processing system that represents the consistency between the feedback information and the input information regarding the job applicant.

9. In the information processing system described in claim 3, In the acquisition step, the recruiter obtains information regarding the job seeker's response to the recruitment document that was sent by the recruiter. The aforementioned multiple evaluation indicators further include a fifth evaluation indicator, The fifth evaluation indicator is an information processing system, which is an indicator representing information related to the reply.

10. In the information processing system described in claim 3, The aforementioned recruiter is a headhunter, The input information relating to the job seeker includes headhunter information indicating the attributes of the headhunter, and the headhunter information includes at least one area of ​​expertise: industry, job type, annual salary, age, and work location. The aforementioned plurality of evaluation indicators include at least the first evaluation indicator, The first evaluation index is an index representing the degree of similarity between the registered information of the job seeker and the headhunter information, in an information processing system.

11. In the information processing system described in claim 1, In the extraction step, recommended job seekers are extracted based on the input information regarding the job seeker, the evaluation indicators, and the reference information for extraction, and here, The extraction reference information includes at least the correlation between the input information relating to the job seeker, the evaluation indicator, and the recommended job seeker in the information processing system.

12. In the information processing system described in claim 1, A server having the aforementioned processor, A system comprising a terminal capable of accessing the aforementioned server.

13. An information processing method, An information processing method comprising each step performed by the information processing system according to any one of claims 1 to 11.

14. It is a program, A program for causing a computer to perform each step of the information processing system described in any one of claims 1 to 11.

Images