Information processing systems, information processing methods, and programs

Abstract

We provide information processing systems and other tools that can create various types of information related to human resources. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program: in a first reception step, it receives instructions for creating personnel-related information relating to job postings, job seekers, or personnel; in a second reception step, it requests and accepts input information necessary for creating personnel-related information, which is set according to the type of personnel-related information; and in an information creation step, it selects reference information according to the type of personnel-related information and creates personnel-related information based on the input information and the reference information, wherein the reference information includes at least the correlation between the input information and the personnel-related information.

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 automatically generating job offer documents.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need for a technique that can create various types of information related to human resources.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that can create various types of information related to human resources.

Means for Solving the Problems

[0006] According to one aspect of the present invention, there is provided an information processing system including at least one processor. The processor is configured to execute the following steps by reading a program. In a first reception step, an instruction to create human resource-related information regarding job offers, job applications, or personnel is received. In a second reception step, in accordance with the type of the human resource-related information, an input of input information necessary for creating the human resource-related information is requested and received. In an information creation step, reference information is selected in accordance with the type of the human resource-related information, and human resource-related information is created based on the input information and the reference information. The reference information includes at least a correlation between the input information and the human resource-related information.

[0007] In this configuration, users can create information about various types of personnel. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of server device 10. [Figure 3] This block diagram shows the hardware configuration of the job seeker terminal 20 and the job applicant terminal 30. [Figure 4] This is a block diagram showing the functions realized by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). [Figure 5] This figure shows an example of a selection screen TD for the type of personnel-related information displayed on the recruiter terminal 20 or the job seeker terminal 30. [Figure 6] This figure shows an example of an information input screen ID displayed on the employer terminal 20 or the job seeker terminal 30. [Figure 7] This figure shows an example of the information creation result screen RD displayed on the employer terminal 20 or the job seeker terminal 30. [Figure 8] This is an activity diagram showing an example of the flow of information processing (human resources-related information creation process) 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 pre-trained model that has learned the correlation between input and output in advance, or a large-scale language model that can output a desired result by inputting a prompt.

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

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

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

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

[0016] The information processing system 1 constitutes at least a part of a job offer - job seeking system used by, for example, a plurality of job offerers (the first job offerer U1 and the second job offerer U2) and a plurality of job seekers (the first job seeker U3 and the second job seeker U4). The information processing system 1 mainly performs operations such as searching for job seekers by job offerers, searching for job offers by job seekers, and mediating communication between job offerers and job seekers. For example, the information processing system 1 provides and manages a talent matching platform, a talent matching service, etc. that are used by job offerers and job seekers. In one embodiment, the information processing system 1 consists 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 operations related to the server device 10. The control unit 11 is, for example, a Central Processing Unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading a predetermined program stored in the storage unit 12. That is, the information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have a plurality of control units 11 for each function. Also, the server device 10 may be configured by combinations of these.

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

[0020] <Communications Department 13> The communication unit 13 preferably uses wired communication methods such as USB, IEEE1394, Thunderbolt®, and wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as LTE / 5G, and Bluetooth® communication as needed. In other words, it is more preferable to implement it as a collection of these multiple communication methods. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The server device 10 may be 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. "Employers" include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.), or their personnel. Here, the personnel may also be called recruitment personnel, and may include personnel in the organization's human resources department or personnel in the department that recruits talent. Furthermore, employers also include recruitment agencies that act as agents for organizations, mediating between job seekers and organizations. Recruitment agencies are also called headhunters or agents.

[0023] 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.

[0024] <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.

[0025] <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.

[0026] <Job seeker terminal 30> The job seeker terminal 30 is an information processing terminal used by job seekers. "Job seekers" include, for example, currently employed individuals (those seeking a career change), prospective graduates (job seekers), students, etc., and include those who are currently looking for a new job or career change, or those who are interested in changing jobs or finding employment.

[0027] 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.

[0028] 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).

[0029] 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).

[0030] As shown in Figure 4A, the server device 10 (control unit 11) comprises a basic display control unit 111, a first reception unit 112, a second reception unit 113, an information creation unit 114, and an artificial intelligence unit 120.

[0031] 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.

[0032] <Basic display control unit 111> The basic display control unit 111 is configured to display various types of 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 information about job seekers or employers registered in the database, information (documents) created by the information creation unit 114, etc., on the display unit 211 of the employer terminal 20 or the display unit 311 of the job seeker terminal 30.

[0033] <First Reception Area 112> The first reception unit 112 is configured to receive instructions from the employer terminal 20 or the job seeker terminal 30 to create personnel-related information concerning job postings or job applications.

[0034] "Personnel-related information" includes at least one of the following: 1. Personnel-related information (primarily created by employers) related to job postings, and 2. Personnel-related information (primarily created by job seekers) related to job applications. Types of 1. Personnel-related information include job postings, recruitment letters to job seekers, job seeker search criteria, employer summary information, meeting minutes of interviews between employers and job seekers, analysis of job seeker behavior, and statistical information on organizational personnel. Types of 2. Personnel-related information include documents related to job seekers' work histories, replies to recruitment letters from employers, job search criteria, and analysis of job information. This reduces the effort required for users, whether employers or job seekers, to create the necessary documents, materials, and data for job postings or job applications.

[0035] "Job seeker search criteria" are search queries that include keywords, attribute information, etc., used in Information Processing System 1 or an external job seeker search system to search for job seekers who meet the job requirements, the conditions sought by the employer, etc.

[0036] "Job seeker summary information" is a summary of information about the job seeker themselves or the organization to which the job seeker belongs. Summary information may be, for example, a document that summarizes the organization's information item by item. Examples of items of organizational information include basic information (name, year of establishment, etc.), organizational overview, business activities, products and services handled (products or services offered), industry, organizational size, performance, financial status, management plan (management policy), organizational structure (management structure), corporate culture (mission, vision, etc.), job openings (positions) being recruited, and items combining these (for example, "organizational overview and business activities").

[0037] "Minutes of interviews between employers and job seekers" include minutes of interviews conducted during job applications, minutes of discussions between employers and job seekers prior to job applications, etc. Furthermore, "interviews" may also include interviews conducted between employers and job seekers during the hiring process.

[0038] "Analysis information on job seeker behavior" refers to information that analyzes the behavior of job seekers on the services provided by Information Processing System 1. This analysis information on job seeker behavior includes, for example, data (numerical values ​​or graphs) that analyze the timing of job seeker actions (e.g., viewing job postings, opening recruitment letters from employers, replying to recruitment letters from employers, applying for jobs, passing screening, securing employment, leaving the service, etc.) and the occurrence rate of these actions for each job seeker attribute.

[0039] "Statistical information on organizational personnel" refers to statistical information about the personnel working in the recruiter's organization (i.e., the job seekers who have been hired). This statistical information may include, for example, data (numerical or graphical) on the distribution of organizational personnel attributes, and may also include information derived from analysis of data from employee management systems or applicant tracking systems (ATS). Furthermore, the statistical information may include statistical values ​​of the organizational personnel data described later (e.g., mean, median, maximum, minimum, time-series change, etc.). In addition, the statistical information may include comparative information between the statistical values ​​of the data and pre-prepared judgment data (reference values). For example, the statistical information may include indicators that have decreased or worsened compared to the previous year, or indicators with an achievement rate of less than 100% against targets or KPIs (i.e., unachieved targets or KPIs).

[0040] "Documents relating to a job seeker's work history" refer to documents such as resumes, which are documents that job seekers submit to employers to convey their past work history, experience, skills, qualifications, etc. Documents relating to a job seeker's work history may also 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 contains the job seeker's profile, current situation, educational background, work history, and desired working conditions.

[0041] "Job search criteria" are search queries that include keywords, attribute information, etc., used to search for job openings or employers that meet the conditions desired by job seekers in Information Processing System 1 or an external job search system of Information Processing System 1.

[0042] "Recruitment information analysis" refers to information obtained by analyzing documents and materials created by recruiters, such as job postings and recruitment letters. This analysis includes data (numerical values ​​or graphs) that classifies or analyzes recruitment requirements (e.g., annual salary) listed in job postings and recruitment letters based on text information.

[0043] Instructions for creating personnel-related information may include first-order information indicating the type (category) of personnel-related information, and second-order information indicating a more detailed aspect (subcategory) of personnel-related information. For example, the instruction "Create a new job posting" includes first-order information "Job posting" and second-order information "Create new". Similarly, the instruction "Modify a job posting" includes first-order information "Job posting" and second-order information "Modify". The first and second-order information may have a hierarchical structure; for example, the second-order information may be associated with and stored at a lower level of the first-order information. The first-order information may also be called first-level information, and the second-order information may be called second-level information. Furthermore, the first-order information may represent the object to be created based on the instruction, and the second-order information may represent the method or means of creation (for example, "Create new" or "Modify"). Furthermore, the first reception unit 112 may receive instructions from the employer terminal 20 or job seeker terminal 30 in two stages: instructions including the type of personnel-related information and instructions indicating the form of personnel-related information.

[0044] Instructions for creating personnel-related information may be received by inputting instructions into an object displayed on the employer terminal 20 or job seeker terminal 30, or by inputting text containing the type of personnel-related information and instructions for its creation on the employer terminal 20 or job seeker terminal 30.

[0045] The first reception unit 112 may present pre-configured options for each type of personnel-related information to the employer terminal 20 or job seeker terminal 30, and may also receive instructions from the employer terminal 20 or job seeker terminal 30 to create personnel-related information of the type to which the selected option corresponds. This allows the user, whether an employer or a job seeker, to confidently give instructions for creating the desired personnel-related information.

[0046] The correspondence between types and options is stored in the storage unit 12 as a table, for example. For example, for the type of personnel-related information called "job posting," the option "automatic job posting creation" is pre-set. When a job seeker selects this option "automatic job posting creation," the first reception unit 112 receives an instruction to create personnel-related information of the type "job posting."

[0047] Furthermore, multiple options may be pre-set for a single category. For example, for a category of personnel-related information called "job posting," options such as "create a new job posting," "modify an existing job posting," "create a job posting based on a template," and "create a job posting template" may be set. In this case, each option includes first information indicating the category "job posting," and second information indicating a specific creation policy (new creation, modification, creation based on a template, creation of a template, etc.) as an example of the form of personnel-related information.

[0048] The first reception unit 112 may present the recruiter terminal 20 or job seeker terminal 30 with options corresponding to the types of personnel-related information that the user can select, according to the user's attributes. As a result, the recruiter terminal 20 or job seeker terminal 30 will only be presented with options corresponding to the personnel-related information that the user (recruiter or job seeker) can create, improving the user's operability when creating the desired personnel-related information.

[0049] The first reception unit 112 may, for example, determine the user's classification, such as whether the user is an employer or a job seeker (for example, whether the user ID is an employer's registration ID or a job seeker's registration ID), and then present pre-prepared options for employers or job seekers to the employer terminal 20 or job seeker terminal 30.

[0050] The first reception unit 112 may present the recruiter terminal 20 or job seeker terminal 30 with options prepared for each user attribute, depending on the user's attributes. If the user is a recruiter, their attributes include, for example, the recruiter's organization, department, and position. If the user is a job seeker, their attributes include, for example, age, educational background, current organization, current industry, current job, current position, current annual income, skills, qualifications, organizations worked for (years of service at each organization), industries worked for (years of experience in each industry), jobs worked for (years of experience in each job), desired industry, desired job, desired annual income, desired work location, and activity history.

[0051] Figure 5 shows an example of a personnel-related information type selection screen TD displayed on the employer terminal 20 or job seeker terminal 30. The type selection screen TD includes a type input field TF. The type input field TF displays options set for each type of personnel-related information, for example, in the form of a pull-down list. The type corresponding to the option selected in the type input field TF is accepted as the type of personnel-related information to be created.

[0052] <Second Reception Desk 113> The second reception unit 113 is configured to request the employer terminal 20 or job seeker terminal 30 to input the necessary input information for creating the personnel-related information, which is set according to the type of personnel-related information for which the first reception unit 112 has received instructions to create, and to accept the input of the input information from the employer terminal 20 or job seeker terminal 30.

[0053] The format of the input information requested by the second reception unit 113 is not limited; for example, text such as sentences and words, audio, images, etc., can be accepted as input information.

[0054] The correspondence between type and input information is stored in the storage unit 12 as a table, for example. For example, for the type of personnel-related information called "job posting," the initial information necessary to create the job posting (e.g., position name, organization name, business division, department, job title, job description, etc.) is set as input information in the information creation unit 114, which will be described later. When the first reception unit 112 receives an instruction to create personnel-related information of the type "job posting," the second reception unit 113 requests the job seeker terminal 20 to input the initial information and receives the input of the initial information from the job seeker terminal 20.

[0055] Furthermore, for example, under the category "Interview Minutes," input information can include audio, video, text memos, etc., that record the content of interviews, meetings, or discussions. For example, under the category "Job Seeker Summary Information," input information can include documents (data files) in which the job seeker's information is disclosed, the URL of the job seeker's website, etc.

[0056] Furthermore, for example, for the category "Statistical Information on Organizational Employees," data related to organizational employees is set as input information. "Data related to organizational employees" includes data from employee management systems and ATS, as well as data registered in each recruiter's HR database. Data registered in the HR database includes, for example, basic employee data, labor and attendance data, performance evaluation data, salary data, survey data, stress check test data, 360-degree feedback data, the organization's job posting data, and candidate data. In addition, data related to organizational employees may include, for example, changes in indicators (e.g., comparison with the previous year), and achievement rates against targets and KPIs. Furthermore, data related to organizational employees may include, for example, information on the intention to resign or transfer of personnel within the organization. The intention to resign or transfer of personnel within the organization is data that indicates that personnel belonging to the organization intend to resign or transfer, and this is extracted from, for example, survey data and performance evaluation data.

[0057] Furthermore, input information may be set according to the combination of the type of personnel-related information (first information) and the form of personnel-related information (second information). For example, in the case of the type "job posting" (first information), if the form (second information) is "new creation," only initial information such as the position name is set as input information, and if the form (second information) is "modification," the initial information and the existing job posting to be modified are set as input information.

[0058] The second reception unit 113 may select an input form from a pre-prepared set of input forms according to the type of personnel-related information, display the selected input form on the employer terminal 20 or job seeker terminal 30, and accept input information from the displayed input form. This allows the user, either the employer or the job seeker, to input all the necessary information completely and concisely.

[0059] The correspondence between the type and the input form is stored in the storage unit 12 as a table, for example. The input form has required input fields that accept input information corresponding to the type. The input format for the required input fields is set according to the type of input information, for example, by selecting an item, by free input, or by a combination thereof. In addition, the required input fields may accept file uploads from the employer terminal 20 or job seeker terminal 30, and input of information indicating the location of files on the network (for example, a URL).

[0060] The input form may be configured according to the combination of the type of personnel-related information (first information) and the form of personnel-related information (second information). For example, different input forms may be set for "creating a new job posting" and "modifying an existing job posting."

[0061] Furthermore, the input form may include auxiliary input fields that accept optional supplementary information entered by the user, in addition to the required input fields. This supplementary information may include detailed conditions and requirements regarding the personnel-related information to be created, such as the format of the document to be created as personnel-related information, and information that the user considers important when creating it.

[0062] The second reception unit 113 may modify the input form according to the manner of instructions for creating personnel-related information received by the first reception unit 112, and may also display the modified input form on the employer terminal 20 or the job seeker terminal 30. This allows input information to be obtained using an input form that matches the manner of personnel-related information requested by the user, thereby improving the accuracy of personnel-related information generation in the information creation unit 114.

[0063] For example, the second reception unit 113 may, after calling up a registered input form corresponding to the type of personnel-related information (first information), modify the input form by correcting or adding required input fields to the input form based on the characteristics of the personnel-related information (second information).

[0064] The second reception unit 113 may modify the input form based on the difference between the sample output result of the information creation model, which is provided for each type of personnel-related information and is included in the reference information referenced by the information creation unit 114 described later, and the actual personnel-related information. The sample output result is personnel-related information obtained when input information that can be entered into the registered input form (i.e., for which required input fields are provided) is entered into the information creation model. In other words, the second reception unit 113 may infer the input information that should be entered into the information creation model in order to eliminate the difference between the actual output result of the sample and the actual personnel-related information entered by the user, and generate an input form that can accept the inferred input information.

[0065] For example, if the registered input form and sample are for "newly created job postings," but the user's instructions are for "modifying existing job postings," the input form will be modified to eliminate the difference between "creating a new job posting" and "modifying a job posting."

[0066] The second reception unit 113 may input the difference between the registered input form and the sample output result of the information creation model, which is included in the instructions for creating personnel-related information received by the first reception unit 112, into the form modification model, thereby causing the form modification model to output a modified input form in which the input form has been modified to reduce the difference. The form modification model is a learning model or generative AI (artificial intelligence) that has been trained to take the input form and the difference as input and output a modified input form. As a result, the user is presented with an input form that accepts the input information necessary to create personnel-related information with the content desired by the user, thereby improving the accuracy of personnel-related information generation.

[0067] The form modification model is included in the artificial intelligence unit 120. The form modification model, which is trained to output a modified input form, is trained using, for example, information corresponding to the difference in the form of the input form to be modified and the form of two pieces of personnel-related information (the target personnel-related information and the sample personnel-related information), and the data of the modified input form corresponding to these as training data.

[0068] If the form modification model is a generative AI including a large-scale language model or an AI agent as described later, the second reception unit 113 inputs a prompt to the form modification model that includes an instruction to generate a modified input form by modifying the input form so that the difference between the input form and the two types of personnel-related information is reduced, and outputs the modified input form to the form modification model. The second reception unit 113 may also generate a prompt that gives the form modification model an instruction to generate a modified input form and input the prompt to the form modification model. In addition, the second reception unit 113 may input a prompt to the form modification model that includes, in addition to the instruction to generate and output the modified input form and the original input form and the difference, an example of input and output pairs, sample, or training data, such as one or more samples of input forms and differences and one or more corresponding samples of modified input forms.

[0069] Furthermore, the second reception unit 113 may input the type of personnel-related information and instructions to modify the form based on it into the form modification model, causing the form modification model to modify the input form and output the modified input form.

[0070] Figure 6 shows an example of an information input screen ID displayed on the employer terminal 20 or the job seeker terminal 30. The information input screen ID includes a required input field IF1, an auxiliary input field IF2, a cancel button B11, and a submit button B12.

[0071] In the example in Figure 6, the required input field IF1 and the auxiliary input field IF2 necessary for "creating a new job posting" are displayed. In this example, the required input field IF1 requests input of "Company Name" and "Job Title". In the auxiliary input field IF2, candidate keywords (sentences) to be inserted into the prompts entered into the information creation model are displayed, and selection is accepted via checkboxes.

[0072] If an input operation is performed on the Cancel button B11, the entered content will be discarded. If an input operation is performed on the Send button B12, the content entered in each of the required input fields IF1 will be accepted as input information, and the keyword (text) selected in the auxiliary input field IF2 will be accepted as auxiliary information. Note that if all required input fields IF1 are not filled in, an input operation on the Send button B12 will not be accepted.

[0073] The second reception unit 113 may present multiple information creation models, selectable according to the type of personnel-related information, to the employer terminal 20 or job seeker terminal 30, and may also accept the selection of an information creation model into which the input information will be entered in the information creation unit 114. This allows the user, either an employer or a job seeker, to instruct the creation of personnel-related information while considering the characteristics of each of the multiple information processing creation models provided.

[0074] The "selectable information generation models" may be pre-configured, for example, according to the type of personnel-related information (or a combination of the type and form of personnel-related information). Multiple selectable information generation models may include both learning models and generative AI. Multiple information generation models may include those with different construction conditions (e.g., training data, learning algorithms, number of parameters, etc.) and may include those provided by different vendors.

[0075] The receiving of instructions for creating personnel-related information at the first reception unit 112, and the request for input of input information and the acceptance of input of input information at the second reception unit 113 may be carried out sequentially in a chat format. This allows users, whether employers or job seekers, to seamlessly perform the process from receiving instructions for creating personnel-related information to inputting input information in a chat format.

[0076] Specifically, the process from issuing instructions for creating personnel-related information to reporting the completion of its creation may be carried out in the following manner, for example. First, the first reception unit 112 receives instructions from the user to create personnel-related information via text input on a chat screen displayed on the recruiter terminal 20 or job seeker terminal 30. The creation instructions entered by the user are displayed on the chat screen as a user message. Next, the second reception unit 113 displays a response message requesting the necessary input information on the same chat screen, following the user message. Furthermore, the second reception unit 113 accepts input or upload of input information from the user on the chat screen. The input information entered by the user is displayed on the chat screen as a user message. After that, the second reception unit 113 displays a response message indicating that the input information has been received, and / or a response message indicating that the creation of personnel-related information has been completed by the information creation unit 114 (for example, a response message including a link to the personnel-related information) following the user message.

[0077] Instructions for creating personnel-related information and the acceptance of input information may be carried out via a chat model, which is a large-scale language model capable of returning appropriate responses to messages entered by users in a chat format.

[0078] <Information Creation Department 114> The information creation unit 114 is configured to select reference information according to the type of personnel-related information instructed by the first reception unit 112, and to create personnel-related information based on the input information received by the second reception unit 113 and the selected reference information.

[0079] The reference information includes at least the correlation between the input information and the personnel-related information. The reference information is stored, for example, in the storage unit 12. The reference information is prepared in advance for each type of personnel-related information. The reference information may also be prepared for each combination of the type of personnel-related information (first information) and the characteristics of the personnel-related information (second information).

[0080] Reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between input information and personnel-related information. The correlations included in the reference information can be constructed, for example, by statistically analyzing data that records input information and corresponding personnel-related information.

[0081] The reference information may include an information creation model, which is a learning model or generative AI trained to take input information as input and output personnel-related information. In the information creation model, parameters calculated and tuned through learning constitute the correlation of the reference information. This makes it possible to propose personnel-related information based on a large amount of learning data or natural language processing. In this case, the information creation unit 114 selects an information creation model according to the type of personnel-related information, or a combination of the type and form of personnel-related information.

[0082] The information generation model is included in the artificial intelligence unit 120. The information generation model may be prepared for each type of personnel-related information, or a common model (e.g., a general-purpose large-scale language model) may be used regardless of the type of personnel-related information. An information generation model trained to output personnel-related information is trained, for example, using input information and corresponding personnel-related information data as training data.

[0083] If the information creation model is a generative AI including a large-scale language model or an AI agent as described later, the information creation unit 114 inputs a prompt to the information creation model that includes an instruction to generate personnel-related information based on the input information, and causes the information creation model to output the personnel-related information. The information creation unit 114 may also generate a prompt that gives the information creation model an instruction to generate personnel-related information and input the prompt to the information creation model. In addition to the instructions for generating and outputting personnel-related information and the input information, the information creation unit 114 may also input a prompt to the information creation model that includes, for example, one or more samples of input information and one or more samples of corresponding personnel-related information, as examples, samples, or training data of input and output pairs.

[0084] The reference information may further include prompt templates to be input into the information creation model. Prompt templates are prepared for each type of personnel-related information, or for each combination of type and form of personnel-related information. In other words, as reference information, a set of models combining the information creation model, which is the generating AI, and the prompt templates may be prepared for each type of personnel-related information, or for each combination of type and form of personnel-related information. In this case, the information creation unit 114 selects a model set according to the type of personnel-related information, or the combination of type and form of personnel-related information.

[0085] The reference information may further include samples of the output results of the information creation model, prepared for each type of personnel-related information. These sample output results may be prepared for each combination of type and form of personnel-related information. In other words, the reference information may consist of model sets combining the information creation model, which is a generating AI, and sample output results, prepared for each type of personnel-related information, or for each combination of type and form of personnel-related information. The model sets may further include prompt templates, as described above.

[0086] If the reference information includes an information creation model, the information creation unit 114 inputs the input information received by the second reception unit 113 into an information creation model corresponding to the type of personnel-related information (or a combination of the type and form of personnel-related information), and causes the information creation model to output the personnel-related information. Furthermore, if the second reception unit 113 has received a selection of an information creation model from the user, the information creation unit 114 inputs the input information into the selected information creation model and causes it to output the personnel-related information.

[0087] If the information creation model that inputs the input information is a generating AI, and the reference information includes a prompt template, the information creation unit 114 may select a prompt template according to the type of personnel-related information and input the prompt obtained by adding the input information to the template into the information creation model. This makes it possible to create personnel-related information using prompts that correspond to the output of personnel-related information, thereby improving the quality of the generated personnel-related information.

[0088] The prompt template includes text describing the instructions and an area for inserting input information or sample input information (dummy information). The information creation unit 114 creates a prompt by inserting the input information received by the second reception unit 113 into the prompt insertion area, or by replacing the input information with the sample information in the template, and inputs this prompt into the information creation model. In addition, if the second reception unit 113 receives auxiliary information, the information creation unit 114 also adds the auxiliary information to the template.

[0089] The information creation unit 114 may modify the prompt template according to the form included in the instructions for creating personnel-related information received by the first reception unit 112, or the auxiliary information received by the second reception unit 113 along with the input information, and input the prompt obtained by adding the input information to the modified template into the information creation model. This makes it possible to tune the prompt according to the user's input, and thus make fine adjustments to the created personnel-related information to suit the user's wishes.

[0090] When modifying the prompt template based on the nature of the personnel-related information, the information creation unit 114 may modify the prompt template based on the difference between the sample output result of the information creation model, which is prepared for each type of personnel-related information, and the nature of the personnel-related information. In other words, the information creation unit 114 may predict the instructions that should be input to the information creation model, which is a generating AI, in order to eliminate the difference between the sample output result and the nature of the personnel-related information entered by the user, and generate a prompt template (modified template) into which the predicted instructions are input. The information creation unit 114 inputs the prompt obtained by adding input information to the modified template into the information creation model.

[0091] The information creation unit 114 may input the difference between the registered prompt template and the portion of the instructions for creating personnel-related information received by the first reception unit 112, as well as a sample output result of the information creation model, into the first template modification model, thereby causing the first template modification model to output a modified template with the prompt template modified to reduce the difference. The first template modification model is a learning model or a generating AI that has been trained to take the template and the difference as input and output a modified template. As a result, prompts containing the necessary instructions to create personnel-related information with the content desired by the user are input into the information creation model, thereby improving the accuracy of personnel-related information generation.

[0092] The first template modification model is included in the artificial intelligence unit 120. The first template modification model, which is trained to output a modified template, is trained using, for example, information corresponding to the difference in the characteristics of the template to be modified and two pieces of personnel-related information (the target personnel-related information and the sample personnel-related information), and the data of the modified template corresponding to these as training data.

[0093] If the first template modification model is a generative AI including a large-scale language model or an AI agent as described later, the information creation unit 114 inputs a prompt to the first template modification model that includes an instruction to generate a modified template by taking the template of the prompt and the difference between the two types of personnel-related information as input and modifying the template so that the difference becomes smaller, and outputs the modified template to the first template modification model. The information creation unit 114 may also generate a prompt that gives an instruction to the first template modification model to generate a modified template and input the prompt to the first template modification model. In addition, the information creation unit 114 may input a prompt to the first template modification model that includes an instruction to generate and output a modified template, the original template and the difference, and, as an example, sample, or training data of input and output pairs, for example, one or more samples of templates and differences and one or more samples of corresponding modified templates.

[0094] Alternatively, the information creation unit 114 may input the type of personnel-related information and instructions to modify the template based on it into the first template modification model, causing the first template modification model to modify the template and output the modified template.

[0095] Furthermore, when modifying the prompt template based on auxiliary information, the information creation unit 114 may modify the prompt template so that auxiliary information can be added (so that instructions to refer to auxiliary information are included). The information creation unit 114 inputs the prompt obtained by adding input information and auxiliary information to the modified template into the information creation model.

[0096] The information creation unit 114 may input the registered prompt template and the auxiliary information received by the second reception unit 113 into the second template modification model, causing the second template modification model to output a modified template that modifies the prompt template to also refer to the auxiliary information in addition to the input information. The second template modification model is a learning model or generative AI that has been trained to take the template and auxiliary information as input and output a modified template.

[0097] The second template modification model is included in the artificial intelligence unit 120. The second template modification model, which is trained to output a modified template, is trained using, for example, the template to be modified and its auxiliary information, and the data of the corresponding modified template, as training data.

[0098] If the second template modification model is a generative AI including a large-scale language model or an AI agent as described later, the information creation unit 114 inputs a prompt to the second template modification model that takes the prompt template and auxiliary information as input and includes an instruction to generate a modified template that modifies the template so that the auxiliary information is referenced when the information creation model creates personnel-related information, and causes the second template modification model to output the modified template. The information creation unit 114 may also generate a prompt that gives the second template modification model an instruction to generate a modified template and input the prompt to the second template modification model. In addition, the information creation unit 114 may input a prompt to the second template modification model that includes, in addition to the instruction to generate and output a modified template and the original template and auxiliary information, inserts, for example, one or more sample templates and auxiliary information and one or more sample modified templates corresponding to them as examples, samples, or training data of input and output pairs.

[0099] Alternatively, the information creation unit 114 may input auxiliary information and instructions to modify the template based on that information to the second template modification model, causing the second template modification model to modify the template and output the modified template.

[0100] Figure 7 shows an example of the information creation result screen RD displayed on the employer terminal 20 or job seeker terminal 30. The information creation result screen RD displays the contents of the personnel-related information created by the information creation unit 114. In the example in Figure 7, a job posting created as personnel-related information is displayed.

[0101] The information creation unit 114 may restrict the creation of personnel-related information received from a user (employer terminal 20 or job seeker terminal 30) if the user does not meet the function usage conditions set for each type of personnel-related information. This makes it possible to provide a common service (application, platform, etc.) to various users while providing different personnel-related information creation functions for each user.

[0102] "Function usage conditions" refer to the attributes of users who are eligible to use (instruct the creation of) the function for creating personnel-related information of a corresponding type. "User attributes" here include user classifications such as whether the user is an employer or a job seeker, as well as the organization, department, and position of the employer user. For example, the information creation unit 114 will not create a personnel-related information of the "job posting" type if the user is a job seeker. Furthermore, even if the user is an employer (an organizational employee), the information creation unit 114 will not create a personnel-related information of the "job posting" type if the user does not belong to a department included in the function usage conditions (a department with the authority to create job postings).

[0103] Function usage conditions may be set for each combination of the type (first information) and form (second information) of personnel-related information. For example, function usage conditions may be set for each function such as "creating a new job posting," "modifying an existing job posting," and "creating a job posting based on a template." In this case, for example, the information creation unit 114 will execute the function "modifying an existing job posting" if the user's job title satisfies the function usage conditions, but will not execute the function if the user's job title does not meet the requirements for the function usage conditions "creating a new job posting."

[0104] The information creation unit 114 may create the corresponding personnel-related information with restrictions if the user does not meet the function usage conditions. For example, if the user does not meet the function usage conditions for "Create a new job posting," the information creation unit 114 may create personnel-related information (job posting) by referring to less information (data) than when the user meets the function usage conditions. Also, for example, if the user does not meet the function usage conditions for "Create a new job posting," the information creation unit 114 may create personnel-related information (job posting) with fewer items (less information included) than when the user meets the function usage conditions.

[0105] <AIエージェント> The processing (steps) performed by the first reception unit 112, the second reception unit 113, and the information creation unit 114 may be performed by a so-called AI agent (autonomous agent) that autonomously performs tasks such as data collection and conversation necessary for executing tasks or goals entered by the user, using natural language processing, processing models constructed by machine learning, general-purpose large-scale language models, etc. The conversation (instructions in natural language) between the user and the AI ​​agent is conducted, for example, in the form of a voice or text chat. The AI ​​agent is included, for example, in the artificial intelligence unit 120.

[0106] An "AI agent" is a model that, upon input of a goal (objective, purpose, etc.) such as "I want to create XX" or a task such as "output XX," breaks down the processes necessary to reach the goal or achieve the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent autonomously selects and executes tasks, actions, etc. without requiring user intervention (operational input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and learn autonomously in order to achieve the goal. 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.). The AI ​​agent may include a generative AI (including a large-scale language model) that has been trained to perform these processes.

[0107] The AI ​​agent has functions such as generating tasks in response to user input, including instructions, using a processing model such as a generation AI; collecting information from the memory unit 12 of the information processing system 1 or from external systems; and having the collected information analyzed by a processing model such as a generation AI. Furthermore, the AI ​​agent can collect information necessary for correction from its internal memory unit or an external system, and use the collected information as part of the input to the processing model to generate corrected information by modifying the collected information.

[0108] The AI ​​agent may generate a prompt to execute a subtask and input this prompt into an external large-scale language model to obtain the execution result of the subtask from the large-scale language model, or it may execute the generated prompt itself. Alternatively, the AI ​​agent may create input information to cause an external processing model to execute a specific process, and input this input information into the processing model to obtain the execution result of the subtask from the processing model.

[0109] Specifically, an AI agent may perform a task in the following manner, for example: First, the AI ​​agent receives specific instructions from the user, including a goal or task. Next, the AI ​​agent divides the goal or task into multiple subtasks or actions necessary to achieve the goal or task, and generates subtasks or actions. After dividing the goal or task, the AI ​​agent collects information necessary to execute the multiple subtasks and actions. For example, the AI ​​agent collects information by accessing databases, the internet, web searches, or API (Application Programming Interface) integration with external services. After collecting the information, the AI ​​agent executes the multiple subtasks and actions based on the collected information, for example by using external tools, by generating and executing code, and outputs the task corresponding to the goal or the execution result of the input task.

[0110] Furthermore, the AI ​​agent may verify or evaluate the results of a subtask or action itself, and if it determines that revision is necessary, it may modify or improve the subtask or action and re-execute it. For example, after generating code to perform a specific subtask, the AI ​​agent may verify the code itself and provide feedback to modify the code.

[0111] In the specific steps of the control unit 11, the first reception unit 112 may receive instructions from the user to create personnel-related information for the AI ​​agent. The second reception unit 113 may also prompt the user to input information for the AI ​​agent (by presenting an input form) and receive input information from the user for the AI ​​agent. In other words, the first reception unit 112 and the second reception unit 113 may obtain necessary instructions, information, etc., from the conversation between the AI ​​agent and the user.

[0112] When an AI agent receives input information, it may, as a subtask, autonomously modify the input form based on instructions from the user to create personnel-related information, or have the processing model modify it, and then present the modified input form to the user.

[0113] The information creation unit 114 may have the AI ​​agent create personnel-related information. The information creation unit 114 may, for example, use an API provided by a vendor that provides the AI ​​agent to have the AI ​​agent create personnel-related information and to acquire the personnel-related information created by the AI ​​agent. The AI ​​agent that has received instructions to create personnel-related information inputs a prompt to the information creation model, which is a generating AI, that includes an instruction to output personnel-related information based on the input information, and has the information creation model output personnel-related information. Here, when the AI ​​agent inputs a prompt to the information creation model, it may, as a subtask, autonomously modify the prompt based on the instructions to create personnel-related information (type of personnel-related information) and auxiliary information input by the user, or it may have the processing model modify the prompt and input the modified prompt to the information creation model.

[0114] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by each functional unit of the server device 10 may be common to all units, or it may be prepared individually for each functional unit.

[0115] The artificial intelligence unit 120 is an AI (Artificial Intelligence) equipped with learning models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNNs), and may include generative AI including large-scale language models. Large-scale language models are a type of generative AI and include models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. In addition, the artificial intelligence unit 120 can include any machine learning model, deep learning model, artificial intelligence model, etc.

[0116] The language model is an example of a learning model using a machine learning algorithm. Specific machine learning algorithms include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0117] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. Furthermore, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used universally for a wide range of tasks.

[0118] The artificial intelligence unit 120 may be a general-purpose natural language processing learning model, such as a Large Language Model (LLM), which has learned from a vast amount of data. An LLM is a learning model that has been pre-trained on a large amount of 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. It can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences, according to the given prompts. Such a general-purpose learning model includes language models that can handle various tasks without fine-tuning using One-shot Learning or Few-shot Learning. Furthermore, the general-purpose learning model may also be configured to handle various tasks using Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or it may be a common general-purpose learning model.

[0119] The learning models included in the artificial intelligence unit 120 (such as information creation models and other learning models used in each functional unit) can undergo additional learning through transfer learning or fine-tuning. For example, the artificial intelligence unit 120 may perform additional learning and fine-tuning each time new data is registered, using it as new training data. This improves the accuracy of the information output from the learning model.

[0120] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using the original learning model. In knowledge distillation, a pre-trained model, such as a large-scale language model, is used as the teacher model, and the parameters of the student model are adjusted so that the output loss of the student model (distilled model) relative to the output (Soft Target Loss) of the teacher model is small. The student model is then trained, and this student model becomes the distilled model. Alternatively, the student model may be trained so that the output loss of the student model relative to the correct labels (Hard Target) of the teacher data (combinations of input and output data of the learning model) is small. Compared to the original learning model (teacher model), the distilled model has similar performance to the original learning model, but with fewer parameters and a lower processing load. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0121] For example, the learning model used in each functional unit may be a distilled model that has been 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 learning 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 learning model in each functional unit.

[0122] <Display> The display unit 211 of the job seeker terminal 20 and the display unit 311 of the job seeker terminal 30 each display the screen (information) indicated by the data transmitted from the server device 10.

[0123] <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.

[0124] 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.

[0125] This information processing comprises a first reception step, a second reception step, and an information creation step. In the first reception step, instructions for creating personnel-related information concerning job postings or job seekers are received. In the second reception step, input of input information necessary for creating personnel-related information, which is set according to the type of personnel-related information, is requested and accepted. In the information creation step, reference information is selected according to the type of personnel-related information, and personnel-related information is created based on the input information and the reference information.

[0126] Figure 8 is an activity diagram showing an example of the flow of information processing (human resources-related information creation processing) performed by Information Processing System 1. The information processing will be explained below in accordance with each activity in this activity diagram.

[0127] The process of creating personnel-related information begins with a user (employer or job seeker) giving instructions to create personnel-related information. The user inputs the instructions to create personnel-related information on the employer terminal 20 or job seeker terminal 30 (Activity A101). The server device 10 receives the instructions entered on the employer terminal 20 or job seeker terminal 30 (Activity A102). Subsequently, the server device 10 requests the employer terminal 20 or job seeker terminal 30 to input information according to the type of personnel-related information instructed (Activity A103). As a result, an input request screen for input information is displayed on the employer terminal 20 or job seeker terminal 30, and the user inputs the information (Activity A104).

[0128] The server device 10 receives input information entered into the employer terminal 20 or the job seeker terminal 30 (Activity A105). Next, the server device 10 selects reference information according to the type of personnel-related information (Activity A106). After selecting the reference information, the server device 10 creates personnel-related information based on the input information and the selected reference information (Activity A107). Next, the server device 10 outputs the created personnel-related information to the employer terminal 20 or the job seeker terminal 30 (Activity A108). As a result, the personnel-related information is displayed on the employer terminal 20 or the job seeker terminal 30 (Activity A109).

[0129] 4. Effect The function of this embodiment can be summarized as follows: it can generate various types of information related to personnel.

[0130] 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.

[0131] 5. Others In the above embodiment, the server device 10 performed various storage and control functions, but instead of the server device 10, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the external artificial intelligence unit 120 may be provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using 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.

[0132] The personnel-related information created by the server device 10 (control unit 11) is not limited to information relating to job postings or job applications, but may also relate to human resources. For example, the first reception unit 112 may receive instructions for creating personnel-related information relating to human resources from an administrator terminal used by an organization's administrator (human resources manager). The second reception unit 113 may request the administrator terminal to input the necessary input information for creating personnel-related information relating to human resources, and may also receive the input information from the administrator terminal.

[0133] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. The information processing method comprises each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0134] The product may be provided in any of the following embodiments.

[0135] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, wherein in a first reception step, it receives instructions for creating personnel-related information relating to job postings, job seekers, or personnel matters; in a second reception step, it requests input of input information necessary for creating the personnel-related information, which is set according to the type of personnel-related information, and accepts the input of the input information; and in an information creation step, it selects reference information according to the type of personnel-related information and creates the personnel-related information based on the input information and the reference information, wherein the reference information includes at least the correlation between the input information and the personnel-related information.

[0136] (2) An information processing system as described in (1) above, wherein the types of personnel-related information include at least one of the following: job postings, recruitment letters to job seekers, job seeker search criteria, employer summary information, minutes of interviews between employers and job seekers, analysis information on job seekers' behavior, documents relating to job seekers' work history, reply documents to recruitment letters from employers, job search criteria, job information analysis information, and statistical information on employees of the organization.

[0137] (3) An information processing system as described in (1) or (2) above, wherein the reference information includes an information creation model which is a learning model or a generating AI that has been trained to take the input information as input and output the personnel-related information, and in the information creation step, the input information is input to the information creation model and the information creation model is made to output the personnel-related information.

[0138] (4) An information processing system as described in (3) above, wherein the information creation model is a generating AI, the reference information further includes a prompt template to be input to the information creation model, and in the information creation step, the system selects the template according to the type of personnel-related information and inputs the prompt obtained by adding the input information to the template to the information creation model.

[0139] (5) An information processing system as described in (4) above, wherein in the information creation step, the system modifies the template according to the form included in the instructions for creating the personnel-related information received in the first reception step, or the auxiliary information received in the second reception step along with the input information, and inputs a prompt obtained by adding the input information to the modified template into the information creation model.

[0140] (6) In the information processing system described in (5) above, the reference information further includes a sample of the output result of the information creation model, and in the information creation step, the template and the difference between the sample and the manner included in the instructions for creating the personnel-related information received in the first reception step are input to the template modification model, causing the template modification model to output a modified template, wherein the template modification model is a learning model or a generative AI that has been trained to take the template and the difference as inputs and output the modified template.

[0141] (7) An information processing system according to any one of (3) to (6) above, wherein in the second reception step, a plurality of information creation models that can be selected according to the type of personnel-related information are presented, and the information processing system accepts the selection of the information creation model into which the input information is entered in the information creation step.

[0142] (8) An information processing system according to any one of (1) to (7) above, wherein in the second reception step, an input form is selected from a plurality of pre-prepared input forms according to the type of personnel-related information, the selected input form is displayed, and the input information is accepted from the displayed input form.

[0143] (9) An information processing system as described in (8) above, wherein in the second reception step, the system modifies the input form according to the form included in the instructions for creating the personnel-related information received in the first reception step, and displays the modified input form.

[0144] (10) In the information processing system described in (9) above, the reference information includes an information creation model which is a learning model or a generative AI that has been trained to take the input information as input and output the personnel-related information, and a sample of the output result of the information creation model prepared for each type of personnel-related information, wherein in the second reception step, the input form and the difference between the form included in the instructions for creating the personnel-related information received in the first reception step and the sample are input to a form modification model, causing the form modification model to output a modified input form which has been modified from the input form, wherein the form modification model is a learning model or a generative AI that has been trained to take the input form and the difference as input and output the modified input form, in the information processing system.

[0145] (11) An information processing system described in any one of (1) to (10) above, wherein in the information creation step, the information processing system restricts the creation of the personnel-related information received from the user if the user does not satisfy the function usage conditions set for each type of personnel-related information.

[0146] (12) An information processing system according to any one of (1) to (11) above, wherein in the first reception step, the system presents pre-set options for each type of personnel-related information, and receives an instruction to create personnel-related information of the type to which the option is associated based on the selection of the option.

[0147] (13) An information processing system as described in (12) above, wherein in the first reception step, the system presents the options corresponding to the types of personnel-related information that the user can select, according to the user's attributes.

[0148] (14) An information processing system described in any one of (1) to (13) above, wherein the system sequentially performs, in a chat format, the following: receiving instructions for the creation of the personnel-related information in the first reception step, and in the second reception step, a request for the input of the input information and acceptance of the input of the input information.

[0149] (15) An information processing method comprising each step performed by the information processing system described in any one of (1) to (14) above.

[0150] (16) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (14) above. Of course, this is not always the case.

[0151] 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]

[0152] 1: Information Processing System 2: Communication lines 10: Server device 11: Control Unit 12: Storage section 13: Communications Department 14: Communications bus 20: Job seeker terminal 21: Control Unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 30: Job seeker terminal 31: Control Unit 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communications bus 111: Basic Display Control Unit 112: Reception Desk 1 113: Second Reception Department 114: Information Creation Department 120: Artificial Intelligence Department 211:Display section 212: Operation acquisition section 311: Display section 312: Operation acquisition section B11: Cancel button B12: Send button ID: Information input screen IF1: Required field IF2: Auxiliary input field RD: Information creation result screen TD: Type Selection Screen TF: Type input field

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the first application step, instructions are received for the creation of personnel-related information concerning job postings, job seekers, or human resources. In the second reception step, the user is requested to input the input information necessary for creating the personnel-related information, which is set according to the type of personnel-related information, and the input of the input information is accepted. An information processing system in which, in the information creation step, reference information is selected according to the type of personnel-related information, and the personnel-related information is created based on the input information and the reference information, wherein the reference information includes at least the correlation between the input information and the personnel-related information.

2. In the information processing system described in claim 1, An information processing system in which the types of personnel-related information include at least one of the following: job postings, recruitment letters to job seekers, job seeker search criteria, employer summary information, minutes of interviews between employers and job seekers, analysis information on job seeker behavior, documents concerning job seekers' work history, replies to recruitment letters from employers, job search criteria, analysis information on job postings, and statistical information on organizational personnel.

3. In the information processing system described in claim 1, The aforementioned reference information includes an information creation model, which is a learning model or generative AI trained to take the aforementioned input information as input and output the aforementioned personnel-related information. An information processing system that, in the information creation step, inputs the input information into the information creation model and causes the information creation model to output the personnel-related information.

4. In the information processing system described in claim 3, The aforementioned information creation model is a generative AI, The aforementioned reference information further includes a template for a prompt to be input into the information creation model, An information processing system that, in the information creation step, selects a template according to the type of personnel-related information and inputs a prompt obtained by adding the input information to the template into the information creation model.

5. In the information processing system described in claim 4, An information processing system that, in the information creation step, modifies the template according to the form included in the instructions for creating the personnel-related information received in the first reception step, or the auxiliary information received along with the input information in the second reception step, and inputs a prompt obtained by adding the input information to the modified template into the information creation model.

6. In the information processing system described in claim 5, The aforementioned reference information further includes a sample of the output result of the information creation model, In the information creation step, the template and the difference between the sample and the manner included in the instructions for creating the personnel-related information received in the first reception step are input to the template modification model, causing the template modification model to output a modified template, wherein the template modification model is a learning model or a generative AI trained to take the template and the difference as inputs and output the modified template, in this information processing system.

7. In the information processing system described in claim 3, An information processing system that, in the second reception step, presents a plurality of information creation models that can be selected according to the type of personnel-related information, and accepts the selection of an information creation model into which the input information will be entered in the information creation step.

8. In the information processing system described in claim 1, In the second reception step, the information processing system selects an input form from a plurality of pre-prepared input forms according to the type of personnel-related information, displays the selected input form, and accepts input information from the displayed input form.

9. In the information processing system described in claim 8, An information processing system that, in the second reception step, modifies the input form according to the form included in the instructions for creating the personnel-related information received in the first reception step, and displays the modified input form.

10. In the information processing system described in claim 9, The aforementioned reference information is, An information creation model, which is a learning model or generative AI trained to take the aforementioned input information as input and output the aforementioned personnel-related information, Sample output results of the information creation model, prepared for each type of personnel-related information, Includes, In the second reception step, the input form and the difference between the form included in the instructions for creating the personnel-related information received in the first reception step and the sample are input to the form modification model, causing the form modification model to output a modified input form, wherein the form modification model is a learning model or a generating AI that has been trained to take the input form and the difference as inputs and output the modified input form, in this information processing system.

11. In the information processing system described in claim 1, In the information creation step, the information processing system restricts the creation of the personnel-related information received from the user if the user does not satisfy the function usage conditions set for each type of personnel-related information.

12. In the information processing system described in claim 1, An information processing system that, in the first reception step, presents pre-set options for each type of personnel-related information, and accepts an instruction to create personnel-related information of the type to which the option is associated, based on the selection of the option.

13. In the information processing system according to claim 12, An information processing system that, in the first reception step, presents the options corresponding to the types of personnel-related information that the user can select, according to the user's attributes.

14. In the information processing system described in claim 1, An information processing system that sequentially performs, in a chat format, the following: receiving instructions for creating the personnel-related information in the first reception step, and in the second reception step, requesting the input of the input information and accepting the input of the input information.

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

16. 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 14.

Images