Information processing systems, information processing methods, and programs

Abstract

We provide an information processing system that can create job postings suitable for matching job seekers. [Solution] 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: in a job information acquisition step, it acquires job information including at least one of the following: person profile, requirements, and description of the organization or work in the target job; in a job seeker information acquisition step, it acquires job seeker information including at least one of the job seeker's career, skills, qualifications, and desired conditions; in an estimation step, it estimates the concerns that the job seeker has regarding the target job based on a comparison between the job seeker information and the job information, based on a combination of the job seeker information and the job information and first reference information, the first reference information being information relating to the correlation between the combination of the job seeker information and the job information and the concerns; and in an analysis information display control step, it displays analysis information including at least the concerns.

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 technique for matching a company and a job seeker.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need for a technique capable of creating job information suitable for matching job seekers.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that can create job information suitable for matching job seekers.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program: in a job information acquisition step, it acquires job information including at least one of a person profile, requirements, and a description of the organization or work in the target job; in a job seeker information acquisition step, it acquires job seeker information including at least one of the job seeker's career, skills, qualifications, and desired conditions; in an estimation step, it estimates the concerns that the job seeker has regarding the target job based on a comparison of the job seeker information and the job information, based on a combination of the job seeker information and the job information and first reference information, the first reference information being information relating to the correlation between the combination of the job seeker information and the job information and the concerns; and in an analysis information display control step, it displays analysis information including at least the concerns.

[0007] This approach makes it possible to create job postings that are suitable for matching 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 is an example of the job analysis screen RD displayed on the job seeker terminal 20. [Figure 6] This is a continuation of the job analysis screen RD shown in Figure 5. [Figure 7] This figure shows an example of an IPD (Interactive Programming Device) information input screen displayed on the job seeker terminal 20. [Figure 8] This is an example of the analysis information display screen AD shown on the recruiter terminal 20. [Figure 9] This is an activity diagram showing an example of the flow of information processing (display processing of analytical 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 for implementing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or it may be provided as a downloadable medium from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

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

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

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

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

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

[0016] The information processing system 1 constitutes at least a part of a job offer and job search system used by, for example, a plurality of employers (first employer U1 and second employer U2) and a plurality of job seekers (first job seeker U3 and second job seeker U4). The information processing system 1 mainly performs searches for job seekers by employers, searches for job offers by job seekers, mediation of communication between employers and job seekers, and the like. For example, the information processing system 1 provides and manages a human resource matching platform, a human resource matching service, etc. used by employers and job seekers. In one embodiment, the information processing system 1 is composed of one or more devices or components. Hereinafter, these components will be described.

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

[0018] <Control unit 11> The control unit 11 performs processing and control of the overall operation 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 realizes various functions related to the server device 10 by reading a predetermined program stored in the storage unit 12. That is, the information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have a plurality of control units 11 for each function. Also, the server device 10 may be configured by a combination of these.

[0019] <Storage unit 12> The storage unit 12 stores various information defined by the foregoing description. This can be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the calculation of a program. The storage unit 12 stores various programs, variables, etc. 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, wireless LAN network communication, mobile communication such as LTE / 5G, and BLUETOOTH (registered trademark) communication may be included as necessary. That is, the communication unit 13 may be implemented as a collection of these plurality of communication means. Also, the server device 10 may communicate various 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 such as for-profit corporations (e.g., companies), non-profit organizations (e.g., cooperatives, foundations), and public corporations (e.g., local governments), or their representatives. Representatives within employers may also be called hiring managers, and may include personnel from the organization's human resources department or the department responsible for hiring. Furthermore, employers may also include headhunters. A headhunter is an organization or its representative that acts as an intermediary between job seekers and employers (organizations) on behalf of the organization (employer). Headhunters are also known as recruitment agencies, hiring agents, or recruitment agencies.

[0024] 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.

[0025] <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.

[0026] <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.

[0027] <Job seeker terminal 30> The job seeker terminal 30 is an information processing terminal used by job seekers and is capable of accessing 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.

[0028] 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.

[0029] 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).

[0030] 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).

[0031] As shown in Figure 4A, the server device 10 (control unit 11) comprises a basic display control unit 111, a job information acquisition unit 112, a job analysis unit 113, a job seeker information acquisition unit 114, an important item determination unit 115, an estimation unit 116, a plan creation unit 117, an analysis information display control unit 118, a revision proposal unit 119, a revision information display control unit 120, and an artificial intelligence unit 121.

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

[0033] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the employer terminal 20 or the job seeker terminal 30. For example, in response to requests from each user (employers U1, U2 or job seekers U3, U4), the basic display control unit 111 displays the registration information of job seekers 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.

[0034] <Job Information Acquisition Department 112> The job information acquisition unit 112 is configured to acquire job information that includes at least one of the following: a description of the candidate profile, requirements, and a description of the organization or work. A "target job" is a job that is subject to the estimation of concerns by the estimation unit 116 described later, the creation of a plan by the plan creation unit 117, etc. Note that the target job may be one whose recruitment period has ended (for example, a job that has already been filled, or a job that has been withdrawn, etc.).

[0035] A "personal profile" refers to keywords or phrases that describe the attributes of the ideal candidate (persona) sought by the employer. These attributes may include, for example, age, gender, occupation, position, behavioral characteristics, interests, personality, values, and attitude.

[0036] "Requirements" are, for example, job requirements that define the conditions and qualities that job seekers are expected to have for the position being advertised. Job requirements may include, for example, necessary skills, necessary experience, and necessary qualifications. Furthermore, job requirements may include mandatory requirements, which are conditions that are not required, and desirable requirements, which are conditions that are not mandatory but are desirable to have. In addition, job requirements may include exclusion requirements (characteristics to be avoided), which are conditions that are preferable not to have.

[0037] "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.

[0038] Job postings are typically in the form of job descriptions, but they do not necessarily need to be formatted like job descriptions. They may be in the form of a non-standard document such as a memo containing at least one of the following: a description of the person to be hired, requirements, and a description of the organization or work. Furthermore, the job posting acquisition unit 112 should acquire job postings that include at least the requirements in order to create revised information by the revision proposal unit 119, which will be described later.

[0039] The job information acquisition unit 112 may, for example, accept job information uploads from the recruiter terminal 20 and acquire the uploaded job information. The job information acquisition unit 112 may also accept input from the recruiter terminal 20 such as information indicating the target job (for example, the title and ID of the target job), the location where the job information is stored (network address, URL (Uniform Resource Locator), path, etc.), and acquire the corresponding job information from a database or the like. Furthermore, the job information acquisition unit 112 may accept input of job information (for example, keywords or sentences describing the candidate's profile) from the recruiter terminal 20.

[0040] Furthermore, the job information acquisition unit 112 may acquire job analysis information created by the job analysis unit 113, which will be described later, as job information. For example, the job information acquisition unit 112 may acquire a profile or requirements created by the job analysis unit 113 based on the job information of the target job as job information.

[0041] <Recruitment Analysis Department 113> The job analysis unit 113 is configured to create job analysis information that includes at least one of the candidate profile and requirements for the target job, based on initial information that includes at least one of the following: the job posting, the position being recruited, and the recruiting organization information of the target job, and fifth reference information (reference information for job analysis). As a result, the job analysis information itself, a part of the job analysis information, and information created by referencing the job analysis information can be used as job information acquired by the job information acquisition unit 112, thereby reducing the effort required for employers to prepare job information.

[0042] In particular, the initial information should ideally include at least a job posting or at least a combination of information about the open position and the recruiting organization. Job postings generally include at least the job requirements.

[0043] "Information about the recruiting organization" (hereinafter referred to as "recruiting organization information") refers to information that can identify the recruiting organization, such as the name of the recruiting organization (the organization to which the position being recruited belongs) and the URL of the website where the recruiting organization information is disclosed. In addition, the recruiting organization information may also include detailed information about the recruiting organization's business, organizational structure, size, history, representative, products (goods or services), finances, and recruitment.

[0044] The job analysis unit 113 may, for example, accept the upload of initial information from the recruiter terminal 20 and obtain the uploaded initial information. The job analysis unit 113 may also accept input from the recruiter terminal 20 such as information indicating the initial information (e.g., job posting title, ID, etc.) and the storage location of the initial information (network address, URL, path, etc.), and obtain the corresponding initial information from a database or the like. Furthermore, the job analysis unit 113 may accept input of initial information (e.g., the name of the recruiting organization, etc.) from the recruiter terminal 20.

[0045] The recruitment analysis unit 113 may, for example, refer to the name and URL of the recruiting organization included in the initial information to obtain further details of the recruiting organization from publicly available information as additional initial information. The recruitment analysis unit 113 may also obtain publicly available information about organizations that are competitors in recruitment for the recruiting organization as initial information.

[0046] The fifth reference information is information regarding the correlation between the initial information and the job analysis information. The fifth reference information is stored, for example, in the memory unit 12. The fifth reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between the initial information and the job analysis information. The correlation included in the fifth reference information can be constructed, for example, by statistically analyzing data that records the initial information and the corresponding job analysis information.

[0047] The fifth reference information may include a set of parameters for generating job analysis information from initial information. For example, the fifth reference information may be various pre-trained models. For example, the fifth reference information may include a job analysis model that is a dedicated or general-purpose machine learning model that is capable of taking initial information as input and outputting job analysis information. In this case, the job analysis unit 113 inputs the initial information into the job analysis model and causes the job analysis model to output job analysis information.

[0048] The job analysis model is included in the artificial intelligence unit 121. The job analysis model, which is a dedicated learning model, may be constructed, for example, by training using initial information data and corresponding job analysis information data as training data. In such a job analysis model, parameters calculated and tuned through training construct a correlation between the initial information and the job analysis information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0049] If the job analysis model is a general-purpose learning model (for example, a language model such as a large-scale language model), the job analysis unit 113 inputs a prompt to the job analysis model that includes initial information and an instruction to output job analysis information corresponding to the initial information, causing the job analysis model to output job analysis information. The job analysis unit 113 may also generate a prompt that gives the job analysis model an instruction to create job analysis information and input this prompt to the job analysis model. In addition to the initial information and the instruction to create and output job analysis information, the job analysis unit 113 may also input a prompt to the job analysis model that includes, for example, one or more samples of initial information and one or more samples of corresponding job analysis information as examples, samples, or training data of input and output pairs. Here, the parameters for constructing the job analysis model and the prompt that includes an instruction to output job analysis information corresponding to the initial information construct a correlation between the initial information and the job analysis information. 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.

[0050] The recruitment analysis unit 113 may create recruitment analysis information that further includes the attractiveness of the recruiting organization, based on the initial information and the fifth reference information. This allows recruiters to organize or confirm the attractiveness of the recruiting organization and reflect it, for example, in the job posting.

[0051] The job analysis unit 113 may, for example, input prompts to a job analysis model, which is a general-purpose learning model, that include instructions to create attractiveness for multiple perspectives, such as job attractiveness, people attractiveness, organizational attractiveness, and compensation attractiveness, based on initial information, and have the job analysis model output attractiveness for multiple perspectives. Here, "job attractiveness" may include, for example, business content, business model, uniqueness, sense of fulfillment, experience or skills gained, career path, etc. "People attractiveness" may include, for example, the background or expertise of managers or employees, organizational culture, corporate atmosphere, training system, etc. "Organizational attractiveness" may include growth potential, position in the industry, mission, vision, etc. "Compensation attractiveness" may include salary level, benefits, flexibility in working style, evaluation system, etc.

[0052] Furthermore, the recruitment analysis unit 113 may, for example, input prompts to the recruitment analysis model, which is a general-purpose learning model, including instructions to create an EVP (Employee Value Proposition) based on initial information, and have the recruitment analysis model output the EVP. Specifically, the recruitment analysis unit 113 may, for example, have the recruitment analysis model analyze the unique value (selling points) that multiple (e.g., 3 to 5) recruiting organizations or positions can offer, the proposed value that differentiates them from competitors in recruitment, and any areas where they fall short.

[0053] The recruitment analysis unit 113 may, after creating the attractiveness of the recruiting organization (attractiveness from each perspective and / or EVP), create a corresponding candidate profile (for example, a candidate profile that meets the requirements of the job and is attracted to the attractiveness of the recruiting organization) based on the initial information and the attractiveness. For example, the recruitment analysis unit 113 may input prompts to a general-purpose learning model, the recruitment analysis model, which includes instructions to create attractiveness based on initial information (for example, information about the recruiting organization), and then to output the candidate profile to the recruitment analysis model based on the created attractiveness and initial information (for example, the job posting or the position being recruited). The recruitment analysis unit 113 may also create multiple candidate profiles based on the initial information, etc.

[0054] Furthermore, the job analysis unit 113 may create, in addition to the candidate profile, a relationship between the candidate profile and the EVP, based on the initial information and the created EVP. For example, the job analysis unit 113 may input prompts to the job analysis model, which is a general-purpose learning model, that include instructions to create appealing points that resonate with the candidate profile, concerns that the candidate profile might have, etc., as relationships between the candidate profile and the EVP, and have the job analysis model output these relationships.

[0055] The Job Analysis Department 113 may, after creating a profile of a candidate based on initial information including the job posting, create a gap between that profile and the target profile of the job posting (for example, the profile described in or derived from the job posting). Here, "gap" refers to the degree of inconsistency, deviation, etc., in attributes, conditions, tendencies, etc., between the comparison targets. In addition to missing elements, the elements compared as a gap may also include excessive elements, differences in thinking, etc. Furthermore, the Job Analysis Department 113 may create a revision policy for the target profile (content of the job posting) based on the gap.

[0056] The job analysis unit 113 may create job analysis information that includes multiple requirements with different priorities, based on the initial information and the fifth reference information. This allows the prediction unit 116 to predict points of concern, the plan creation unit 117 to create a plan, and so on, based on the multiple requirements with different priorities.

[0057] The "priority" of a requirement is an indicator of the degree of importance of the requirement, and represents categories such as mandatory requirements that job seekers must meet, and desirable requirements that job seekers should meet. Priority may also be expressed numerically (rank, etc.), not limited to categories. Mandatory requirements have a higher priority than desirable requirements. Exclusion requirements may be set as "characteristics that must be avoided" and have a higher priority than mandatory and desirable requirements, or as "characteristics that are preferable to avoid" and have a lower priority than mandatory and desirable requirements. Multiple requirements may be set for both mandatory and desirable requirements, or multiple requirements may be set for only one of them. In addition, individual priorities may be set among multiple mandatory requirements and / or multiple desirable requirements.

[0058] The job analysis unit 113 may, for example, input prompts to the job analysis model, which is a general-purpose learning model, including instructions to create mandatory requirements and preferred requirements based on initial information, and have the job analysis model output the mandatory requirements and preferred requirements.

[0059] The recruitment analysis department 113 may, for example, create mandatory requirements and desirable requirements for each of several items (e.g., items related to skills, items related to personality, etc.). The recruitment analysis department 113 may also create exclusion requirements.

[0060] Figure 5 is an example of the job analysis screen RD displayed on the recruiter terminal 20. Figure 6 is a continuation of the job analysis screen RD in Figure 5. As shown in Figures 5 and 6, the job analysis screen RD displays four items: attractiveness summary CS, EVP comparison EC, target persona TP, and recruitment requirements RM.

[0061] The attractiveness summary CS ("Company Attractiveness Elements (Four-Axis Analysis) Summary") shown in Figure 5 lists the name of the attractiveness aspect and the content of the attractiveness for each aspect, created by the Recruitment Analysis Department 113, for each of the multiple attractiveness aspects CH. In the example in Figure 5, the attractiveness of four aspects such as the attractiveness of the work ("Work Axis: Opportunities for Challenge and Growth") and the attractiveness of the people ("Company Axis: Innovative Corporate Culture") are displayed. Note that in Figure 5, the remaining two attractiveness aspects CH (for example, organizational attractiveness, attractiveness of compensation, etc.) are not illustrated.

[0062] Figure 5 shows the EVP Comparison EC ("EVP (Employee Value Proposition) and Competitor Comparison"), which includes the EVP Summary ES, Strengths SP, and Weaknesses WP, all created by the Recruitment Analysis Department 113. The EVP Summary ES includes, for example, key points of the EVP that differentiate the company compared to competitors. The Strengths SP ("Differentiation Points (Strengths)") includes, for example, strengths against competitors (value that can be uniquely provided). The Weaknesses WP ("Points to Note (Weak Points)") includes, for example, weaknesses that are judged to be inferior to competitors.

[0063] Figure 6 shows the Target Persona TP ("Target Persona and Specific Selling Points"), which contains multiple persona profiles created by the Recruitment Analysis Department 113. Each persona profile includes the persona's name, a description of the person (e.g., behavioral characteristics, interests, etc.), what should be communicated in the interview (e.g., selling points based on the attractiveness of the recruiting organization), and a combination of anticipated concerns and example answers (e.g., anticipated questions from the candidate and example answers to those questions).

[0064] The recruitment requirements RM ("Proposed Recruitment Requirements (MUST / WANT)") shown in Figure 6 includes mandatory requirements MR ("MUST") and desirable requirements WR ("WANT"), which were created by the Job Analysis Department 113. In the example in Figure 6, mandatory requirements MR and desirable requirements WR are presented for each of the multiple items (in Figure 6, "Experience / Skills" and "Stance / Orientation").

[0065] <Job applicant information acquisition department 114> The job seeker information acquisition unit 114 is configured to acquire job seeker information that includes at least one of the following: the job seeker's work history, skills, qualifications, and desired conditions.

[0066] Job seeker information may also include, for example, basic information about the job seeker (name, age, gender, address, etc.), current employment information (organization, industry, department, job title, duties, job description, position, annual income, etc.), and past employment information.

[0067] Job seeker information may include, for example, a resume, which is a document detailing a job seeker's work history, experience, skills, qualifications, etc., to employers. A work history document may include the job seeker's resume, other profile information, and the conditions such as the industry and job type 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.

[0068] The work history document may be automatically generated by artificial intelligence such as a generation AI, or it may be created by the job seeker themselves. The work history document may also be, for example, part of the registration information of a job seeker registered in a job seeker database.

[0069] The job seeker information acquisition unit 114 may, for example, accept input from the employer terminal 20 of job seekers (i.e., candidates for the target job) (e.g., input of a job seeker ID, selection from a list of job seeker search results, etc.) and acquire the job seeker information of the entered job seeker. Typically, candidates whose job seeker information is acquired are applicants for the target job, recipients of scouting documents based on the target job, etc. Here, a "scouting document" is a document sent from an employer to a job seeker with the purpose of encouraging them to apply for selection or proposing an interview, and may also be called a scouting email.

[0070] Furthermore, instead of accepting candidate input from the employer terminal 20, the job seeker information acquisition unit 114 may automatically acquire job seeker information of job seekers who have contact with the target job, that is, job seekers related to the target job (hereinafter referred to as "related job seekers"). Specifically, the job seeker information acquisition unit 114 may acquire job seeker information of multiple related job seekers who have an activity history related to the target job, or who are stored in association with the target job.

[0071] "Action history related to the target job posting" includes, for example, viewing the target job posting, applying for the target job posting, adding the target job posting to a bookmark list, and responding to recruitment documents based on the target job posting. Here, the "bookmark list" (also called the "favorites list" or "interesting list") is a list prepared for each job seeker where they can register any job posting they wish. Furthermore, the action history may include not only actions related to the target job posting, but also actions related to other job postings with similar attributes (job type, annual salary, job description, work location, etc.). In addition, the action history may include negative actions such as hiding a job posting or withdrawing from the selection process.

[0072] "A state of being associated with a target job posting" refers to a state in which an employer has managed, saved, or registered a particular job seeker (candidate) for a target job posting. Such states include, for example, being registered in the target list for the target job posting, having a scouting document sent based on the target job posting (i.e., being registered in the history of scouting documents sent), being tagged for the target job posting, being automatically extracted (grouped) according to the requirements of the target job posting, and being recorded in the management history of the target job posting. Here, "target list" is a list prepared for each job posting in which the employer can register any job seeker (candidate). The target list may include, for example, what is called a scouting list or a candidate folder.

[0073] The job seeker information acquisition unit 114 may acquire at least information regarding the selection process of related job seekers as job seeker information. This allows the revision proposal unit 119, described later, to create revised information, etc., taking into account the progress of the job seekers' recruitment.

[0074] "Information regarding the selection process" includes, for example, the history of casual interviews conducted prior to applying for the target job, the status of passing the screening process for the target job application (document screening, interview screening, etc.), whether or not a job offer was secured, and whether or not the job offer was accepted.

[0075] The job seeker information acquisition unit 114 may receive supplementary information about job seekers from the employer terminal 20 and acquire job seeker information that includes this supplementary information. This improves the accuracy of the priority item determination by the priority item determination unit 115, which will be described later.

[0076] "Supplementary information" refers to additional information not included in the job seeker information, such as information that cannot be obtained from the information registered in the job seeker database. Supplementary information is information about the job seeker (candidate) that the employer has obtained, and may include, for example, reasons for changing jobs, selection status, etc.

[0077] Figure 7 shows an example of the information input screen IPD displayed on the job seeker terminal 20. The information input screen IPD includes an ID input field IF, a supplementary information input field SF, a persona input field PF, a close button B11, and a create button B12.

[0078] The ID input field IF accepts the input of a candidate ID. The job seeker information of the job seeker corresponding to the candidate ID entered in the ID input field IF is acquired by the job seeker information acquisition unit 114. The supplementary information input field SF accepts the input of supplementary information for the candidate. Keywords, sentences, etc. entered in the supplementary information input field SF are acquired by the job seeker information acquisition unit 114 as supplementary information. The persona input field PF accepts the input of a target persona. The target persona may be, for example, a profile created by the job analysis unit 113, a target profile described in the job posting for the target job, or keywords, sentences, etc. created by the employer. Keywords, sentences, etc. entered in the persona input field PF are acquired by the job information acquisition unit 112 as job information.

[0079] When an input operation is performed on the close button B11, the contents entered in the ID input field IF, the supplementary information input field SF, and the persona input field PF are discarded, and the information input screen IPD is closed. When an input operation is performed on the create button B12, processing is started by the importance item determination unit 115, the estimation unit 116, the plan creation unit 117, etc., based on the contents entered in the ID input field IF, the supplementary information input field SF, and the persona input field PF, as described later.

[0080] <Important item determination section 115> The importance item determination unit 115 is configured to determine the important items that job seekers prioritize in their job search, based on job seeker information and third-party reference information (reference information for determining important items). This allows employers to understand the important items of job seekers (candidates) and then proceed with considering and formulating policies regarding the target job opening.

[0081] "Key priorities" are items related to the job seeker's wishes and desires regarding the organization, work, etc., that are considered more important to the job seeker than other items, and may also be called "career criteria." Key priorities include objective conditions such as salary, work style, work location, employment type, job content, organizational structure, and salary increase system, as well as subjective environmental conditions such as career advancement, growth, job satisfaction, work-life balance, and interpersonal relationships.

[0082] The priority item determination unit 115 may determine one priority item or multiple priority items for a single job seeker. Determining multiple priority items allows the predictions of concerns made by the prediction unit 116, described later, to become more specific. For example, the maximum number of priority items is three.

[0083] The third reference information is information regarding the correlation between job seeker information and important items. The third reference information is stored, for example, in the memory unit 12. The third reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between job seeker information and important items. The correlations included in the third reference information can be constructed, for example, by statistically analyzing data that records job seeker information and corresponding important items.

[0084] The third reference information may include a set of parameters for generating important items from job seeker information. For example, the third reference information may be various pre-trained models. For example, the third reference information may include an important item determination model, which is either a dedicated learning model or a general-purpose learning model that has been machine-trained to take job seeker information as input and output important items. In this case, the important item determination unit 115 inputs the job seeker information into the important item determination model and causes the important item determination model to output important items.

[0085] The priority item determination model is included in the artificial intelligence unit 121. The priority item determination model, which is a dedicated learning model, may be constructed, for example, by training using job seeker information data and corresponding priority item data as training data. In such a priority item determination model, parameters calculated and tuned through learning construct a correlation between job seeker information and priority items.

[0086] If the priority item determination model is a general-purpose learning model (for example, a language model such as a large-scale language model), the priority item determination unit 115 inputs a prompt to the priority item determination model that includes job seeker information and an instruction to output a priority item corresponding to the job seeker information, causing the priority item determination model to output the priority item. The priority item determination unit 115 may also generate a prompt that gives an instruction to the priority item determination model to determine a priority item, and input this prompt to the priority item determination model. In addition to the job seeker information and the instruction to determine and output the priority item, the priority item determination unit 115 may also input a prompt to the priority item determination model that includes, for example, one or more samples of job seeker information and one or more samples of corresponding priority items as examples, samples, or training data of input and output pairs. Here, the parameters that construct the priority item determination model and the prompt that includes an instruction to output a priority item corresponding to the job seeker information construct the correlation between the job seeker information and the priority item.

[0087] The third reference information may include a list of important items (patterns of important items). In other words, the important item determination unit 115 may determine the important items by extracting important items from a plurality of pre-prepared items (candidate important items).

[0088] If the job seeker information acquisition unit 114 has acquired job seeker information including supplementary information, the importance item determination unit 115 may determine the importance items based on the job seeker information including supplementary information and the third reference information.

[0089] The priority item determination unit 115 may create a summary of the job seeker information based on the combination of the job seeker information and the priority items, and the fourth reference information (reference information for summary creation). This reduces the burden on the employer in understanding the candidate's personal characteristics by allowing the employer to review a summary based on what the job seeker (candidate) considers important in their job search. The summary may include, for example, notable experience (e.g., projects, positions, skills, qualifications, etc.) and aspirations (e.g., career advancement, salary increase, desired job, etc.).

[0090] The fourth reference information is information regarding the correlation between combinations of job seeker information and important items and summaries. The fourth reference information is stored, for example, in the memory unit 12. The fourth reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of job seeker information and important items and summaries. The correlations included in the fourth reference information can be constructed, for example, by statistically analyzing data that records combinations of job seeker information and important items and corresponding summaries.

[0091] The fourth reference information may include a set of parameters for generating a summary from a combination of job seeker information and important items. For example, the fourth reference information may be various pre-trained models. For example, the fourth reference information may include a summary generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take a combination of job seeker information and important items as input and output a summary. In this case, the job seeker information acquisition unit 114 inputs the combination of job seeker information and important items into the summary generation model and causes the summary generation model to output a summary.

[0092] The summary generation model is included in the artificial intelligence unit 121. The summary generation model, which is a dedicated learning model, may be constructed, for example, by training with data of combinations of job seeker information and important items and corresponding summary data as training data. In such a summary generation model, parameters calculated and tuned through learning construct a correlation between the combination of job seeker information and important items and the summary.

[0093] If the summarization model is a general-purpose learning model (for example, a language model such as a large-scale language model), the job seeker information acquisition unit 114 inputs a prompt to the summarization model that includes a combination of job seeker information and important items, and an instruction to output a summary corresponding to the combination of job seeker information and important items, taking the combination of job seeker information and important items as input, causing the summarization model to output a summary. The job seeker information acquisition unit 114 may also generate a prompt that gives an instruction to the summarization model to create a summary, and input this prompt to the summarization model. In addition, the job seeker information acquisition unit 114 may input a prompt to the summarization model that includes, in addition to the combination of job seeker information and important items and the instruction to create and output a summary, an example, sample, or training data of input and output pairs, such as one or more sample combinations of job seeker information and important items and one or more sample summaries corresponding to them. Here, the parameters that construct the summarization model and the prompt that includes an instruction to output a summary corresponding to the combination of job seeker information and important items construct the correlation between the combination of job seeker information and important items and the summary.

[0094] The job seeker information acquisition unit 114 may create a summary based on the job seeker information and at least one of the important items, as well as the fourth reference information. For example, the job seeker information acquisition unit 114 may input the job seeker information and at least one of the important items into the summary creation model and output the summary to the summary creation model.

[0095] If the job seeker information acquisition unit 114 has acquired job seeker information including supplementary information, the importance item determination unit 115 may create a summary based on the combination of the job seeker information including supplementary information and the importance items, and the fourth reference information.

[0096] <Guessing part 116> The estimation unit 116 is configured to estimate concerns that job seekers have regarding a target job, based on a comparison between the job seeker information and the job posting information, using a combination of job seeker information acquired by the job seeker information acquisition unit 114 and job posting information acquired by the job posting information acquisition unit 112, and first reference information (reference information for creating concerns).

[0097] "Concerns" refer to factors that may hinder job seekers from considering applying for a job, participating in the selection process, or accepting a job offer (joining the company). For example, these include concerns that job seekers (candidates) may have about the job description and concerns that they may have about the recruiting organization. Concerns about the job description may include concerns about the job duties, compensation, and requirements such as skills and qualifications. Concerns about the recruiting organization may include concerns about career advancement and concerns about interpersonal relationships.

[0098] The estimation unit 116 may estimate one concern (presumably the greatest concern) or multiple concerns for a single job seeker.

[0099] The first reference information is information relating to the correlation between combinations of job seeker information and job posting information and concerns. The first reference information is stored, for example, in the memory unit 12. The first reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of job seeker information and job posting information and concerns. The correlations included in the first reference information can be constructed, for example, by statistically analyzing data that records combinations of job seeker information and job posting information and corresponding concerns.

[0100] The first reference information may include a set of parameters for generating concerns from a combination of job seeker information and job posting information. For example, the first reference information may be various pre-trained models. For example, the first reference information may include a concern generation model, which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take a combination of job seeker information and job posting information as input and output concerns. In this case, the inference unit 116 inputs the combination of job seeker information and job posting information into the concern generation model and causes the concern generation model to output concerns.

[0101] The concern generation model is included in the artificial intelligence unit 121. The concern generation model, which is a dedicated learning model, may be constructed, for example, by training with data of combinations of job seeker information and job posting information and corresponding concern data as training data. In such a concern generation model, parameters calculated and tuned through learning construct a correlation between the combination of job seeker information and job posting information and the concerns.

[0102] If the concern generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the inference unit 116 inputs a prompt to the concern generation model that includes a combination of job seeker information and job posting information, and an instruction to output a concern corresponding to the combination of job seeker information and job posting information, causing the concern generation model to output the concern. The inference unit 116 may also generate a prompt that gives the concern generation model an instruction to create a concern and input this prompt to the concern generation model. In addition to the combination of job seeker information and job posting information and the instruction to create and output a concern, the inference unit 116 may also input a prompt to the concern generation model that includes, for example, one or more samples of combinations of job seeker information and job posting information and one or more samples of corresponding concerns as examples, samples, or training data of input and output pairs. Here, the parameters for constructing the concern generation model and the prompt including an instruction to output a concern corresponding to the combination of job seeker information and job posting information construct a correlation between the combination of job seeker information and job posting information and the concern.

[0103] The estimation unit 116 may generate concerns based on at least one of the job seeker information and job posting information, and the first reference information. For example, the estimation unit 116 may input at least one of the job seeker information and job posting information into the concern generation model and output the concerns to the concern generation model.

[0104] The first reference information may include reference information for gap determination and reference information for concern estimation. In this case, the estimation unit 116 determines the gap between the job seeker's career, skills, qualifications, or desired conditions and the description of the person, requirements, or organization or work of the target job, based on the combination of job seeker information and job information, and the reference information for gap determination. Furthermore, it estimates concerns based on the gap and the reference information for concern estimation. This makes it possible to estimate concerns that are suitable for conducting studies, formulating policies, etc., to bridge the anticipated gaps in the target job.

[0105] "Gaps" include, for example, requirement gaps, which indicate that the job seeker's experience, skills, qualifications, etc., do not meet the requirements of the target job; profile gaps, which indicate that the job seeker's experience, skills, qualifications, etc., do not match the profile of the target candidate; and desired conditions gaps, which indicate that the job seeker's desired conditions are not met by the compensation, job content, etc., described in the organizational or operational description of the target job.

[0106] The gap determination reference information is information regarding the correlation between combinations of job seeker information and job posting information and the gap. The gap determination reference information is stored, for example, in the memory unit 12. The gap determination reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of job seeker information and job posting information and the gap. The correlations included in the gap determination reference information can be constructed, for example, by statistically analyzing data that records combinations of job seeker information and job posting information and the corresponding gaps.

[0107] The gap detection reference information may include a set of parameters for generating a gap from a combination of job seeker information and job posting information. For example, the gap detection reference information may be various pre-trained models. For example, the gap detection reference information may include a gap detection model that is a dedicated learning model or a general-purpose learning model that has been machine-trained to take a combination of job seeker information and job posting information as input and output a gap. In this case, the prediction unit 116 inputs the combination of job seeker information and job posting information into the gap detection model and causes the gap detection model to output a gap.

[0108] The gap detection model is included in the artificial intelligence unit 121. The gap detection model, which is a dedicated learning model, may be constructed, for example, by training with data of combinations of job seeker information and job posting information and data of the corresponding gaps as training data. In such a gap detection model, parameters calculated and tuned through learning construct a correlation between the combination of job seeker information and job posting information and the gap.

[0109] If the gap detection model is a general-purpose learning model (for example, a language model such as a large-scale language model), the inference unit 116 inputs a prompt to the gap detection model that includes a combination of job seeker information and job posting information, and an instruction to output the gap corresponding to the combination of job seeker information and job posting information, causing the gap detection model to output the gap. The inference unit 116 may also generate a prompt that gives the gap detection model an instruction to determine a gap, and input this prompt to the gap detection model. In addition, the inference unit 116 may input a prompt to the gap detection model that includes, in addition to the combination of job seeker information and job posting information and the instruction to determine and output the gap, an example of input and output pairs, such as one or more samples of job seeker information and job posting information combinations and one or more samples of corresponding gaps, as example, sample or training data. Here, the parameters that construct the gap detection model and the prompt that includes an instruction to output the gap corresponding to the combination of job seeker information and job posting information construct the correlation between the combination of job seeker information and job posting information and the gap.

[0110] The estimation unit 116 may create a gap based on at least one of the job seeker information and the job posting information, as well as the reference information for gap determination. For example, the estimation unit 116 may input at least one of the job seeker information and the job posting information into the gap determination model and output the gap to the gap determination model.

[0111] For example, the prediction unit 116 may create a gap based on the job seeker information and the gap determination reference information. In this case, the prediction unit 116 may create a hypothetical job (hypothetical requirements, etc.) based on the desired conditions included in the job seeker information, and further input a prompt to the gap determination model, which is a general-purpose learning model, that includes an instruction to determine the gap between the hypothetical job and the job seeker information (information other than the information used to create the hypothetical job, such as desired conditions), causing the gap determination model to output the gap.

[0112] The reference information for predicting concerns is information regarding the correlation between gaps and concerns. This reference information is stored, for example, in the memory unit 12. The reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between gaps and concerns. The correlations included in the reference information for predicting concerns can be constructed, for example, by statistically analyzing data that records gaps and corresponding concerns.

[0113] The reference information for predicting concerns may include a set of parameters for generating concerns from gaps. For example, the reference information for predicting concerns may be various pre-trained models. For example, the reference information for predicting concerns may include a concern prediction model which is a dedicated learning model or a general-purpose learning model that has been trained to take gaps as input and output concerns. In this case, the prediction unit 116 inputs the gaps into the concern prediction model and causes the concern prediction model to output concerns.

[0114] The concern prediction model is included in the artificial intelligence unit 121. The concern prediction model, which is a dedicated learning model, may be constructed, for example, by training using gap data and corresponding concern data as training data. In such a concern prediction model, parameters calculated and tuned through learning construct a correlation between gaps and concerns.

[0115] If the concern prediction model is a general-purpose learning model (for example, a language model such as a large-scale language model), the prediction unit 116 inputs a prompt to the concern prediction model that includes a gap and an instruction to output a concern corresponding to the gap, causing the concern prediction model to output the concern. The prediction unit 116 may also generate a prompt that gives the concern prediction model an instruction to predict a concern and input this prompt to the concern prediction model. In addition to the gap and the instruction to predict and output the concern, the prediction unit 116 may also input a prompt to the concern prediction model that includes, for example, one or more gap samples and one or more corresponding concern samples as examples, samples, or training data of input and output pairs. Here, the parameters that construct the concern prediction model and the prompt that includes an instruction to output a concern corresponding to the gap construct the correlation between the gap and the concern.

[0116] The gap determination model and the concern prediction model may be common general-purpose learning models. For example, the prediction unit 116 may determine a gap based on the combination of job seeker information and job information, and further input a prompt to a general-purpose learning model that includes instructions to predict concerns based on the gap, causing the general-purpose learning model to output the concerns.

[0117] The estimation unit 116 may estimate concerns based on the combination of job seeker information, job posting information, and the important items determined by the important item determination unit 115, as well as the first reference information. As a result, the job seeker's (candidate's) important items are reflected in the concerns, providing employers with meaningful information that can be used for consideration and policy formulation regarding the target job posting.

[0118] In this case, the first reference information is information regarding the correlation between the combination of job seeker information, job postings, and important items, and the points of concern. The concern generation model, which is a dedicated learning model included in this first reference information, may be constructed, for example, by training with data on the combination of job seeker information, job postings, and important items, and the corresponding data on the points of concern, as training data. Furthermore, if the concern generation model included in this first reference information is a general-purpose learning model, the prediction unit 116 inputs a prompt to the concern generation model that includes, for example, a combination of job seeker information, job postings, and important items, and an instruction to take the combination as input and output the points of concern corresponding to that combination, causing the concern generation model to output the points of concern.

[0119] <Plan Creation Department 117> The plan creation unit 117 is configured to create a plan for the employer of the target job posting to resolve the concerns inferred by the estimation unit 116 and the second reference information (reference information for plan creation). This allows the employer to consider the actions they should take regarding the target job posting to increase its appeal to candidates, while referring to the plan.

[0120] A "plan" may include, for example, a job adjustment plan that adjusts (modifies) the content of a job posting to bridge the gap between the candidate and the job, and a candidate plan (which may also be called an "action plan") that outlines practical actions taken by candidates to increase their acceptance rate of job offers. A job adjustment plan may include actions such as modifying the profile, requirements, organizational structure, or job description of the job posting. The plan may also include plans related to the employer's internal processes, such as operational improvement plans. An operational improvement plan may include, for example, changing the interviewer to one with similar attributes to the candidate, adjusting the schedule of the selection process, or changing the questions asked in interviews.

[0121] Candidate planning includes actions such as adjusting candidate expectations (e.g., communicating the challenges of the team for the job opening and the role expected of the candidate), improving transparency of information (e.g., providing candidates with a 90-day plan after joining the company), building personal connections (e.g., conducting casual interviews between candidates and employees with similar backgrounds), and communicating the appeal of the future (e.g., having the business unit manager talk to candidates about the future vision and prospects of the business).

[0122] The second reference information is information regarding the correlation between concerns and plans. The second reference information is stored, for example, in the memory unit 12. The second reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between concerns and plans. The correlations included in the second reference information can be constructed, for example, by statistically analyzing data that records concerns and corresponding plans.

[0123] The second reference information may include a set of parameters for generating a plan from the concerns. For example, the second reference information may be various pre-trained models. For example, the second reference information may include a plan generation model which is a dedicated or general-purpose trained model that has been trained to take concerns as input and output a plan. In this case, the plan generation unit 117 inputs the concerns into the plan generation model and causes the plan generation model to output a plan.

[0124] The plan creation model is included in the artificial intelligence unit 121. The plan creation model, which is a dedicated learning model, may be constructed, for example, by learning using data on concerns and corresponding plan data as training data. In such a plan creation model, parameters calculated and tuned through learning construct a correlation between concerns and plans.

[0125] If the plan creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the plan creation unit 117 inputs a prompt to the plan creation model that includes a concern and an instruction to output a plan corresponding to that concern, causing the plan creation model to output a plan. The plan creation unit 117 may also generate a prompt that gives the plan creation model an instruction to create a plan and input this prompt to the plan creation model. In addition to the concern and the instruction to create and output a plan, the plan creation unit 117 may also input a prompt to the plan creation model that includes, for example, one or more sample concerns and one or more sample plans corresponding to them, as examples, samples, or training data of input and output pairs. Here, the parameters that construct the plan creation model and the prompt that includes an instruction to output a plan corresponding to a concern construct a correlation between the concern and the plan.

[0126] The plan creation unit 117 may create a plan based on the combination of concerns and the important items determined by the important item determination unit 115, and the second reference information. This ensures that the job seeker's (candidate's) important items are reflected in the gap, providing employers with meaningful information that can be used for considering and formulating policies regarding the target job opening. The concerns combined with the important items may themselves be created by referring to the important items (i.e., based on a combination of job seeker information, job information, and important items).

[0127] In this case, the second reference information is information regarding the correlation between combinations of concerns and priorities and the plan. The plan creation model, which is a dedicated learning model included in this second reference information, may be constructed, for example, by training with data on combinations of concerns and priorities and data on the corresponding plans as training data. Furthermore, if the plan creation model included in this second reference information is a general-purpose learning model, the plan creation unit 117 inputs a prompt to the plan creation model, for example, which includes a combination of concerns and priorities and an instruction to output a plan corresponding to that combination as input, causing the plan creation model to output a plan.

[0128] <Analysis Information Display Control Unit 118> The analysis information display control unit 118 is configured to display analysis information that includes at least the concerns created by the prediction unit 116 on the job seeker terminal 20.

[0129] The analysis information display control unit 118 may display analysis information on the recruiter terminal 20 that includes at least the points of concern and the plan created by the plan creation unit 117. The analysis information display control unit 118 may also display analysis information on the recruiter terminal 20 that includes at least the points of concern and the important items determined by the important item determination unit 115. Furthermore, the analysis information display control unit 118 may display analysis information on the recruiter terminal 20 that includes at least the important items, points of concern, and the plan, and the analysis information display control unit 118 may also display analysis information on the recruiter terminal 20 that includes at least the important items, a summary of the job seeker information created by the job seeker information acquisition unit 114, points of concern, and the plan.

[0130] The analysis information may include gaps determined by the estimation unit 116. In other words, the analysis information display control unit 118 may display the gaps on the job seeker terminal 20.

[0131] Furthermore, the analysis information display control unit 118 may display only one of the following as analysis information on the recruiter terminal 20: important items, summary of job seeker information, gaps, concerns, and plans.

[0132] Figure 8 shows an example of the analysis information display screen AD displayed on the recruiter terminal 20. The analysis information display screen AD displays the priority items PI, the job seeker information summary SM, the concerns CP, and the plan PL.

[0133] The PI ("Career Aptitude") section lists three key priorities derived from the job seeker's information. The SM ("About This Person") section summarizes the job seeker's information, describing the candidate based on their experience, aspirations, etc. The CP ("Anticipated Concerns") section lists potential concerns about the candidate, derived from a comparison between the job seeker's information and the job description. The PL ("Example Response") section outlines the course of action for addressing Concerns ("Adjusting Expectations") and its specific details.

[0134] <Revision proposal section 119> The revision proposal unit 119 is configured to create revised information, including revisions to the job posting, based on a comparison between multiple job seeker information and the job posting information, using a combination of job seeker information of multiple related job seekers acquired by the job seeker information acquisition unit 114 and job posting information acquired by the job posting information acquisition unit 112, as well as sixth reference information (reference information for creating revised information). As a result, revisions that reduce the discrepancy between multiple related job seekers and the target job posting are presented, thereby increasing the probability of successful recruitment for the target job posting by the employer.

[0135] "Revision details" refers to information indicating revisions to the content of the job posting, such as the profile, requirements, organizational structure, or job description. "Revisions" here include not only changes to the content, but also deletions and additions. Furthermore, the revision details may be specific proposed revisions (e.g., revised keywords, sentences, etc.) or a general revision policy (e.g., "to highlight new appeal").

[0136] The proposed revision unit 119 may create revised information, including proposed revisions to the requirements of the target job, based on a combination of multiple job seeker and job posting information and the sixth reference information. This allows the requirements of the target job to be revised to meet the requirements of relevant job seekers, thereby lowering the barrier to application for job seekers. As a result, relevant job seekers will be more likely to become interested in and apply for the target job.

[0137] For example, if the revision proposal unit 119 determines that there are few relevant job seekers who have taken action such as applying for the target job, it may create revised proposals to relax the requirements or to delete the requirements. Also, for example, if the revision proposal unit 119 determines that there are too many relevant job seekers who have taken action (too much noise), it may create revised proposals to tighten the requirements or to add new requirements. Furthermore, if the revision proposal unit 119 determines that there are enough applicants but their attributes do not match the target (a mismatch with the requirements), it may create revised proposals to make the description of the target person more specific or to delete or change expressions that may mislead job seekers.

[0138] The revised information may include proposed changes to the priority of requirements in the target job posting. This allows for a concise and accurate reduction of the discrepancy between the target job posting and relevant job seekers. For example, if the revised proposal unit 119 determines that there are few relevant job seekers who have taken action such as applying for the target job posting, it will create a revised proposal to change mandatory requirements to welcome requirements, and if it determines that there are too many relevant job seekers who have taken action such as applying for the target job posting, it will create a revised proposal to change welcome requirements to mandatory requirements.

[0139] The sixth reference information is information relating to the correlation between multiple combinations of job seeker information and job posting information and modification information. The sixth reference information is stored, for example, in the memory unit 12. The sixth reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between multiple combinations of job seeker information and job posting information and modification information. The correlations included in the sixth reference information can be constructed, for example, by statistically analyzing data that records multiple combinations of job seeker information and job posting information and corresponding modification information.

[0140] The sixth reference information may include a set of parameters for generating corrected information from a combination of multiple job seeker information and job posting information. For example, the sixth reference information may be various pre-trained models. For example, the sixth reference information may include a first corrected information creation model, which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take a combination of multiple job seeker information and job posting information as input and output corrected information. In this case, the correction suggestion unit 119 inputs the combination of multiple job seeker information and job posting information into the first corrected information creation model and causes the first corrected information creation model to output corrected information.

[0141] The first correction information creation model is included in the artificial intelligence unit 121. The first correction information creation model, which is a dedicated learning model, may be constructed, for example, by training with data of combinations of multiple job seeker information and job posting information and corresponding correction information data as training data. In such a first correction information creation model, parameters calculated and tuned through learning construct a correlation between combinations of multiple job seeker information and job posting information and the correction information.

[0142] If the first correction information creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the correction suggestion unit 119 inputs a prompt to the first correction information creation model that includes a combination of multiple job seeker information and job posting information, and an instruction to output correction information corresponding to the combination of multiple job seeker information and job posting information, taking the combination of multiple job seeker information and job posting information as input, causing the first correction information creation model to output the correction information. The correction suggestion unit 119 may also generate a prompt that gives the first correction information creation model an instruction to create correction information, and input this prompt to the first correction information creation model. In addition to the combination of multiple job seeker information and job posting information and the instruction to create and output correction information, the correction suggestion unit 119 may also input a prompt to the first correction information creation model that includes, for example, one or more samples of combinations of multiple job seeker information and job posting information and one or more samples of corresponding correction information, as examples, samples, or training data of input and output pairs. Here, parameters for constructing the first correction information creation model and prompts containing instructions to output correction information corresponding to combinations of multiple job seeker and job posting information establish a correlation between combinations of multiple job seeker and job posting information and the correction information.

[0143] The revision proposal unit 119 may create revised information based on at least one of the multiple job seeker information and job posting information, and the sixth reference information. For example, the revision proposal unit 119 may input at least one of the multiple job seeker information and job posting information into the first revised information creation model and output the revised information to the first revised information creation model.

[0144] The sixth reference information may include pre-processing reference information and post-processing reference information. In this case, the modification suggestion unit 119 extracts differences between the attributes and requirements of multiple related job seekers based on combinations of job seeker information and job posting information, and the pre-processing reference information, and further creates modification information based on these differences and the post-processing reference information. This makes it possible to present the employer with modification information that reduces the differences between the attributes of multiple related job seekers and the requirements of the target job posting.

[0145] "Related job seeker attributes" refer to items included in the requirements of the target job posting (items that can be compared with the requirements). Specifically, related job seeker attributes include work experience, skills, qualifications, etc.

[0146] The preprocessing reference information is information regarding the correlation between combinations of multiple job seeker information and job posting information, and the differences between the attributes and requirements of multiple related job seekers. The preprocessing reference information is stored, for example, in the storage unit 12. The preprocessing reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of multiple job seeker information and job posting information and the differences. The correlations included in the preprocessing reference information can be constructed, for example, by statistically analyzing data that records combinations of multiple job seeker information and job posting information and the corresponding differences.

[0147] The preprocessing reference information may include a set of parameters for generating differences from multiple combinations of job seeker information and job posting information. For example, the preprocessing reference information may be various pre-trained models. For example, the preprocessing reference information may include a difference extraction model, which is either a dedicated learning model or a general-purpose learning model, that has been machine-trained to take multiple combinations of job seeker information and job posting information as input and output differences. In this case, the modification suggestion unit 119 inputs multiple combinations of job seeker information and job posting information into the difference extraction model and causes the difference extraction model to output differences.

[0148] The difference extraction model is included in the artificial intelligence unit 121. The difference extraction model, which is a dedicated learning model, may be constructed, for example, by training with data of combinations of multiple job seeker information and job posting information and data of the corresponding differences as training data. In such a difference extraction model, parameters calculated and tuned through learning construct a correlation between combinations of multiple job seeker information and job posting information and the differences.

[0149] If the difference extraction model is a general-purpose learning model (for example, a language model such as a large-scale language model), the modification suggestion unit 119 inputs a prompt to the difference extraction model that includes a combination of multiple job seeker information and job posting information, and an instruction to output the differences corresponding to the combination of job seeker information and job posting information, taking the combination of job seeker information and job posting information as input, causing the difference extraction model to output the differences. The modification suggestion unit 119 may also generate a prompt that gives the difference extraction model an instruction to extract differences, and input this prompt to the difference extraction model. In addition to the combination of multiple job seeker information and job posting information and the instruction to extract and output differences, the modification suggestion unit 119 may also input a prompt to the difference extraction model that includes, for example, one or more samples of combinations of job seeker information and job posting information and one or more samples of differences corresponding to them, as examples, samples, or training data of input and output pairs. Here, the parameters for constructing the difference extraction model and the prompt including an instruction to output the differences corresponding to the combination of multiple job seeker information and job posting information construct a correlation between the combination of multiple job seeker information and job posting information and the differences.

[0150] The revision proposal unit 119 may create differences based on at least one of the multiple job seeker information and job posting information, and preprocessing reference information. For example, the revision proposal unit 119 may input at least one of the multiple job seeker information and job posting information into the difference extraction model and output the differences to the difference extraction model.

[0151] Post-processing reference information is information regarding the differences between the attributes and requirements of multiple related job seekers and the correlation with the correction information. Post-processing reference information is stored, for example, in the storage unit 12. Post-processing reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between the differences and the correction information. The correlations included in the post-processing reference information can be constructed, for example, by statistically analyzing data that records the differences and the corresponding correction information.

[0152] The post-processing reference information may include a set of parameters for generating correction information from the difference. For example, the post-processing reference information may be various pre-trained models. For example, the post-processing reference information may include a dedicated training model or a general-purpose training model, which is trained to take the difference as input and output correction information. In this case, the correction suggestion unit 119 inputs the difference into the second correction information creation model and causes the second correction information creation model to output the correction information.

[0153] The second correction information generation model is included in the artificial intelligence unit 121. The second correction information generation model, which is a dedicated learning model, may be constructed, for example, by learning using difference data and corresponding correction information data as training data. In such a second correction information generation model, parameters calculated and tuned through learning construct a correlation between the difference and the correction information.

[0154] If the second correction information creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the correction suggestion unit 119 inputs a prompt to the second correction information creation model that includes a difference and an instruction to output correction information corresponding to that difference, causing the second correction information creation model to output the correction information. The correction suggestion unit 119 may also generate a prompt that gives the second correction information creation model an instruction to create correction information and input this prompt to the second correction information creation model. In addition to the difference and the instruction to create and output correction information, the correction suggestion unit 119 may also input a prompt to the second correction information creation model that includes, for example, one or more difference samples and one or more corresponding correction information samples as examples, samples, or training data of input and output pairs. Here, the parameters that construct the second correction information creation model and the prompt that includes an instruction to output correction information corresponding to the difference construct a correlation between the difference and the correction information.

[0155] The difference extraction model and the second correction information creation model may be common general-purpose learning models. For example, the inference unit 116 may extract differences based on combinations of job seeker information and job posting information of multiple related job seekers, and further input a prompt to a single general-purpose learning model that includes an instruction to create correction information based on those differences, causing the general-purpose learning model to output the correction information.

[0156] The revision proposal unit 119 may create revised information using job seeker information that includes information regarding the selection of relevant job seekers and / or supplementary information entered by the employer. For example, the revision proposal unit 119 may create revised information for the requirements of the target job posting to adjust the application rate, screening pass rate, etc., based on the attributes of relevant job seekers who passed a specific screening (e.g., document screening, interview screening, etc.) and the attributes of relevant job seekers who did not pass.

[0157] The revision proposal unit 119 may create revised information based on a combination of the job seeker information and priorities of multiple related job seekers, as well as the job information, and the sixth reference information. The priorities of multiple related job seekers are determined by the priorities determination unit 115 based on the job seeker information of each related job seeker. For example, the revision proposal unit 119 may create revised information that modifies the requirements of the target job based on the overall trend of the priorities of multiple related job seekers.

[0158] In this case, the sixth reference information is information regarding the correlation between the combination of job seeker information and important items of multiple related job seekers, as well as job posting information, and the correction information. The first correction information creation model, which is a dedicated learning model included in this sixth reference information, may be constructed, for example, by training with data of combinations of job seeker information and important items of multiple related job seekers, as well as job posting information, and corresponding correction information data as training data. Furthermore, if the first correction information creation model included in this sixth reference information is a general-purpose learning model, the correction suggestion unit 119 inputs a prompt to the first correction information creation model that includes a combination of job seeker information and important items of multiple related job seekers, as well as job posting information, and an instruction to output correction information corresponding to that combination as input, causing the first correction information creation model to output the correction information.

[0159] Furthermore, when using priority items, the preprocessing reference information is information regarding the correlation between the differences between the attributes and requirements of multiple related job seekers and combinations of job seeker information and priority items for multiple related job seekers. If the difference extraction model included in this preprocessing reference information is a general-purpose learning model, the modification suggestion unit 119 inputs a prompt to the difference extraction model that includes a combination of job seeker information and priority items for multiple related job seekers and job information, and an instruction to take the combination as input and output the difference corresponding to the combination, causing the difference extraction model to output the difference.

[0160] Furthermore, the revision proposal unit 119 may create revision information for each of the multiple types of related job seekers. Here, "type of related job seeker" refers to a classification based on the degree of interest of the job seeker in the target job, the stage of the selection phase, etc. Specifically, "type of related job seeker" includes actions by job seekers (viewing the target job, applying for the target job, adding the target job to a bookmark list, replying to a scouting document based on the target job, etc.) and actions by employers (registering on a target list for the target job, sending a scouting document based on the target job, etc.).

[0161] The revision suggestion unit 119 may, for example, group the job seeker information of multiple related job seekers according to type, and create revision information using the grouped job seeker information. Alternatively, the revision suggestion unit 119 may classify multiple related job seekers by type, input a prompt to the first revision information creation model, which is a general-purpose learning model, that includes an instruction to create revision information for each classified job seeker information, and have the first revision information creation model output the revision information. Or, it may input a prompt to the difference extraction model, which is a general-purpose learning model, that includes an instruction to create a difference between the classified job seeker information and the job information, and have the difference extraction model output the difference.

[0162] <Correction Information Display Control Unit 120> The correction information display control unit 120 is configured to display the correction information created by the correction proposal unit 119 on the job seeker terminal 20.

[0163] If correction information is created for each type of related job seeker, the correction information display control unit 120 may display multiple correction information entries for each type on the job seeker terminal 20.

[0164] <Artificial Intelligence Department 121> The artificial intelligence unit 121 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.

[0165] The artificial intelligence unit 121 may be an AI (Artificial Intelligence) equipped with pre-trained models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNNs). The artificial intelligence unit 121 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include specific models such as OpenAI's GPT, Google's Gemini, and models provided through services and platforms such as Microsoft's Azure AI Studio. Generative AI may be, for example, text generation AI, image generation AI, or multimodal generation AI. The pre-trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 121 can include any pre-trained model.

[0166] 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 121 can apply these algorithms as appropriate.

[0167] The artificial intelligence unit 121 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.

[0168] The artificial intelligence unit 121 may include a natural language model as its artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large-scale data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by using 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 121 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.

[0169] The pre-trained models included in the artificial intelligence unit 121 (such as the concern generation model and other 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 121 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.

[0170] The trained model included in the artificial intelligence unit 121 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.

[0171] 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.

[0172] An AI agent (also called an autonomous agent) is a model that, upon input of a goal (objective, purpose, etc.) such as "Teach me about XX" or a task such as "Output XX," breaks down the processes necessary to reach the goal or accomplish the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, outputs information according to the goal, and does not require user intervention (operation input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously learn in order to aim for goal achievement. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.).

[0173] <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.

[0174] <Operation acquisition section> 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.

[0175] 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.

[0176] The above-described information processing method comprises a job information acquisition step, a job seeker information acquisition step, a priority item determination step, an estimation step, a plan creation step, and an analysis information display control step. In the job information acquisition step, job information is acquired that includes at least one of the following: person profile, requirements, and description of the organization or work in the target job. In the job seeker information acquisition step, job seeker information is acquired that includes at least one of the following: job seeker's work history, skills, qualifications, and desired conditions. In the priority item determination step, the priority items that the job seeker considers important in job searching are determined based on the job seeker information and third reference information. In the estimation step, concerns are estimated based on the combination of job seeker information, job information, and priority items, and first reference information. In the plan creation step, a plan is created to address the concerns of the target job seeker based on the concerns and second reference information. In the analysis information display control step, analysis information that includes at least the concerns is displayed.

[0177] Figure 9 is an activity diagram showing an example of the flow of information processing (display processing of analytical information) performed by the information processing system 1. Below, the information processing will be explained according to each activity in this activity diagram.

[0178] The process of displaying the analysis information begins with the employer's selection of target job postings, candidates, etc. The employer inputs information such as target job postings and candidates (job seekers whose information is to be obtained) on the employer terminal 20 (Activity A101). The server device 10 acquires job posting information, job seeker information, etc., based on the information input from the employer terminal 20 (Activity A102). Subsequently, the server device 10 determines the important items based on the job seeker information (Activity A103).

[0179] After determining the priority items, the server device 10 infers potential concerns based on the job seeker information, job posting information, and priority items (Activity A104). Subsequently, the server device 10 creates a plan based on the potential concerns (Activity A105). Furthermore, the server device 10 outputs analytical information, including potential concerns, priority items, and the plan, to the employer terminal 20 (Activity A106). As a result, the analytical information about the target job posting is displayed on the employer terminal 20 (Activity A107).

[0180] 4. Effect The function of this embodiment can be summarized as follows: It enables the creation of job postings suitable for matching job seekers. In particular, by presenting the concerns of candidates (potential job seekers) to employers, employers can consider actions to resolve those concerns.

[0181] 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.

[0182] 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 121 may be an external component of the server device 10. In that case, the external artificial intelligence unit 121 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. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that performs language processing tasks using a language model. 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.

[0183] 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.

[0184] The control unit 11 does not necessarily have to include the job analysis unit 113, the important item determination unit 115, the plan creation unit 117, the revision proposal unit 119, and the revision information display control unit 120. For example, the information processing system 1 does not necessarily have to include at least one of the following: the job analysis information creation function, the important item determination function, the plan creation function, and the revision information creation function.

[0185] 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.

[0186] The product may be provided in any of the following embodiments.

[0187] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program: in a job information acquisition step, it acquires job information including at least one of a person profile, requirements, and a description of the organization or work in the target job; in a job seeker information acquisition step, it acquires job seeker information including at least one of a job seeker's career, skills, qualifications, and desired conditions; in an estimation step, it estimates the concerns that the job seeker has regarding the target job based on a comparison of the job seeker information and the job information, where the first reference information is information relating to the correlation between the combination of the job seeker information and the job information and the concerns; and in an analysis information display control step, it displays analysis information including at least the concerns.

[0188] (2) An information processing system as described in (1) above, wherein in the plan creation step, the employer of the target job is to create a plan to resolve the concerns based on the concerns and the second reference information, wherein the second reference information is information relating to the correlation between the concerns and the plan, and in the analysis information display control step, the system displays analysis information that includes at least the concerns and the plan.

[0189] (3) An information processing system as described in (1) or (2) above, wherein in the important item determination step, the important items that the job seeker considers important in job searching are determined based on the job seeker information and the third reference information, where the third reference information is information relating to the correlation between the job seeker information and the important items, and in the analysis information display control step, the system displays analysis information that includes at least the concerns and the important items.

[0190] (4) An information processing system as described in (3) above, wherein in the job seeker information acquisition step, the system accepts input of supplementary information about the job seeker and acquires the job seeker information including the supplementary information, and in the important item determination step, the system determines the important items based on the job seeker information including the supplementary information and the third reference information.

[0191] (5) An information processing system as described in (3) or (4) above, wherein in the important item determination step, a summary of the job seeker information is created based on the combination of the job seeker information and the important items and the fourth reference information, wherein the fourth reference information is information relating to the correlation between the combination of the job seeker information and the important items and the summary.

[0192] (6) An information processing system according to any one of (3) to (5) above, wherein in the estimation step, the concerns are estimated based on the combination of the job seeker information, the job posting information, and the important items, and the first reference information, wherein the first reference information is information relating to the correlation between the combination of the job seeker information, the job posting information, and the important items and the concerns.

[0193] (7) An information processing system as described in (2) above, wherein in the important item determination step, the important items that the job seeker considers important in job hunting are determined based on the job seeker information and the third reference information, where the third reference information is information relating to the correlation between the job seeker information and the important items, and in the plan creation step, the plan is created based on the combination of the concerns and the important items and the second reference information, where the second reference information is information relating to the correlation between the combination of the concerns and the important items and the plan.

[0194] (8) An information processing system according to any one of (1) to (7) above, wherein the first reference information includes gap determination reference information and concern estimation reference information, and in the estimation step, the system determines a gap between the job seeker's career, skills, qualifications, or desired conditions and the person profile, requirements, or description of the target job based on the combination of the job seeker information and the job information and the gap determination reference information, and further estimates the concerns based on the gap and the concern estimation reference information, wherein the gap determination reference information is information relating to the correlation between the combination of the job seeker information and the job information and the gap, and the concern estimation reference information is information relating to the correlation between the gap and the concerns.

[0195] (9) An information processing system described in any one of (1) to (8) above, wherein in the job analysis step, the information processing system creates job analysis information including at least one of the candidate profile and requirements based on initial information including at least one of the job posting, recruitment position and recruitment organization information of the target job, and fifth reference information, wherein the fifth reference information is information relating to the correlation between the initial information and the job analysis information.

[0196] (10) An information processing system as described in (9) above, wherein in the job analysis step, the information processing system creates the job analysis information which further includes the attractiveness of the recruiting organization based on the initial information and the fifth reference information.

[0197] (11) An information processing system as described in (9) or (10) above, wherein in the job analysis step, the information processing system creates the job analysis information, which includes a plurality of requirements with different priorities, based on the initial information and the fifth reference information.

[0198] (12) An information processing system according to any one of (1) to (11) above, wherein in the job information acquisition step, the job information is acquired which includes at least the requirements; in the job seeker information acquisition step, the job seeker information is acquired which includes the actions of a plurality of related job seekers that have an action history relating to the target job or which is stored in association with the target job; in the modification proposal step, modification information is created which includes modifications to the job information based on a comparison between the plurality of job seeker information and the job information, based on a combination of the plurality of job seeker information and the job information and a sixth reference information, wherein the sixth reference information is information relating to the correlation between the plurality of job seeker information and the job information and the modification information; and in the modification information display control step, the modification information is displayed.

[0199] (13) An information processing system as described in (12) above, wherein in the job seeker information acquisition step, the information processing system acquires at least information relating to the selection of the relevant job seeker as the job seeker information.

[0200] (14) An information processing system as described in (12) or (13) above, wherein the sixth reference information includes pre-processing reference information and post-processing reference information, wherein in the modification proposal step, the system extracts differences between the attributes of multiple related job seekers and the requirements based on a combination of a plurality of the job seeker information and the job posting information and the pre-processing reference information, and further creates the modification information based on the differences and the post-processing reference information, wherein the pre-processing reference information is information relating to the correlation between a combination of a plurality of the job seeker information and the job posting information and the differences, and the post-processing reference information is information relating to the correlation between the differences and the modification information.

[0201] (15) An information processing system described in any one of (12) to (14) above, wherein in the modification proposal step, the system creates the modification information, which includes a proposed modification of the requirements as the modification content, based on a combination of a plurality of the job seeker information and the job posting information and the sixth reference information.

[0202] (16) An information processing system as described in (15) above, wherein the corrected information includes a proposed change in the priority of the requirements as the proposed correction.

[0203] (17) An information processing system according to any one of (1) to (16) above, comprising a server device having the processor and a terminal that can access the server device.

[0204] (18) An information processing method wherein an information processing device performs each step of the information processing system described in any one of (1) to (17) above.

[0205] (19) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (17) above. Of course, this is not always the case.

[0206] 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]

[0207] 1: Information Processing System 2: Communication lines 10: Server device 11: Control Unit 111: Basic Display Control Unit 112: Recruitment information acquisition department 113: Recruitment Analysis Department 114: Job applicant information acquisition department 115: Priority item determination section 116: Guessing part 117: Planning Department 118: Analysis Information Display Control Unit 119: Revision proposal department 120: Correction Information Display Control Unit 121: 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 AD:Analysis information display screen B11: Button B12: Create button CH: Attractiveness CP: Points of concern CS: Summary of Appeal EC:EVP comparison ES :EVP summary IF: ID input field IPD: Information Input Screen MR: Mandatory requirement PF: Persona input field PI:Priority items PL: Plan PR: Portrait RD: Job analysis screen RM:Recruitment requirements SF: Supplementary Information Input Field SM: Summary SP: Strengths TP: Target Persona WP: Weakness WR: Welcome Requirements

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 job information acquisition step, the job information is acquired that includes at least one of the following: the candidate profile, requirements, and a description of the organization or work. In the job seeker information acquisition step, we acquire job seeker information that includes at least one of the following: job seeker's work history, skills, qualifications, and desired conditions. In the estimation step, based on the combination of the job seeker information and the job posting information and the first reference information, the concerns that the job seeker has regarding the target job posting are estimated based on a comparison of the job seeker information and the job posting information, where the first reference information is information relating to the correlation between the combination of the job seeker information and the job posting information and the concerns. An information processing system that, in the analytical information display control step, displays analytical information that includes at least the aforementioned concerns.

2. In the information processing system described in claim 1, In the plan creation step, based on the aforementioned concerns and the second reference information, the employer of the target job creates a plan to resolve the aforementioned concerns, where the second reference information is information regarding the correlation between the aforementioned concerns and the plan. The information processing system, in the aforementioned analysis information display control step, displays analysis information that includes at least the concerns and the plan.

3. In the information processing system described in claim 1, In the priority item determination step, the priority items that the job seeker considers important in job searching are determined based on the job seeker information and the third reference information, where the third reference information is information regarding the correlation between the job seeker information and the priority items. The information processing system, in the aforementioned analysis information display control step, displays analysis information that includes at least the concerns and the items of importance.

4. In the information processing system described in claim 3, In the aforementioned job seeker information acquisition step, the input of supplementary information about the job seeker is accepted, and the job seeker information including said supplementary information is acquired. An information processing system that determines the important items in the aforementioned important item determination step based on the job seeker information including the supplementary information and the third reference information.

5. In the information processing system described in claim 3, In the aforementioned priority item determination step, an information processing system creates a summary of the job seeker information based on the combination of the job seeker information and the priority items, and the fourth reference information, where the fourth reference information is information relating to the correlation between the combination of the job seeker information and the priority items and the summary.

6. In the information processing system described in claim 3, An information processing system that, in the estimation step, estimates the concerns based on the combination of the job seeker information, the job posting information, and the important items, and the first reference information, where the first reference information is information relating to the correlation between the combination of the job seeker information, the job posting information, and the important items and the concerns.

7. In the information processing system described in claim 2, In the priority item determination step, the priority items that the job seeker considers important in job searching are determined based on the job seeker information and the third reference information, where the third reference information is information regarding the correlation between the job seeker information and the priority items. In the plan creation step, the information processing system creates the plan based on the combination of the concerns and the priorities and the second reference information, wherein the second reference information is information relating to the correlation between the combination of the concerns and the priorities and the plan.

8. In the information processing system described in claim 1, The first reference information includes reference information for gap determination and reference information for inferring points of concern. In the estimation step, the system determines the gap between the job seeker's career, skills, qualifications, or desired conditions and the candidate profile, requirements, or description of the target job, based on the combination of the job seeker information and the job posting information and the gap determination reference information, and further estimates the concerns based on the gap and the concern estimation reference information, wherein the gap determination reference information is information relating to the correlation between the combination of the job seeker information and the job posting information and the gap, and the concern estimation reference information is information relating to the correlation between the gap and the concerns.

9. In the information processing system described in claim 1, In the job analysis step, the information processing system creates job analysis information, which includes at least one of the candidate profile and requirements, based on initial information, which includes at least one of the job posting, recruitment position, and recruiting organization information of the target job, and fifth reference information, wherein the fifth reference information is information relating to the correlation between the initial information and the job analysis information.

10. In the information processing system described in claim 9, An information processing system that, in the job analysis step, creates the job analysis information, which further includes the attractiveness of the recruiting organization, based on the initial information and the fifth reference information.

11. In the information processing system described in claim 9, An information processing system that, in the job analysis step, creates job analysis information including multiple requirements with different priorities based on the initial information and the fifth reference information.

12. In the information processing system described in claim 1, In the job information acquisition step, the job information that includes at least the above requirements is acquired. In the job seeker information acquisition step, the job seeker information of multiple related job seekers who have an activity history related to the target job or who are stored in association with the target job is acquired. In the proposed revision step, based on multiple combinations of the job seeker information and the job posting information, and the sixth reference information, revised information is created that includes revisions to the job posting information based on a comparison between the multiple job seeker information and the job posting information, where the sixth reference information is information relating to the correlation between multiple combinations of the job seeker information and the job posting information and the revised information. The correction information display control step involves an information processing system that displays the correction information.

13. In the information processing system according to claim 12, An information processing system that, in the step of acquiring job seeker information, acquires at least information relating to the selection of the relevant job seeker as the job seeker information.

14. In the information processing system according to claim 12, The sixth reference information includes pre-processing reference information and post-processing reference information. An information processing system in which, in the aforementioned modification proposal step, differences between the attributes of multiple related job seekers and the requirements are extracted based on a combination of multiple job seeker information and job posting information and the pre-processing reference information, and further, the modified information is created based on these differences and the post-processing reference information, wherein the pre-processing reference information is information regarding the correlation between the combination of multiple job seeker information and job posting information and the differences, and the post-processing reference information is information regarding the correlation between the differences and the modified information.

15. In the information processing system according to claim 12, In the aforementioned revision proposal step, an information processing system creates revised information, which includes proposed revisions to the requirements, as the revision content, based on a combination of multiple job seeker information and job posting information and the sixth reference information.

16. In the information processing system described in claim 15, The aforementioned modification information includes, as the proposed modification, a proposed change in the priority of the requirements, in an information processing system.

17. In the information processing system described in claim 1, A server device having the aforementioned processor, A terminal that can access the aforementioned server device, An information processing system equipped with the following features.

18. Information processing method, An information processing method comprising an information processing device performing each step of the information processing system described in any one of claims 1 to 17.

19. 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 17.

Images