Information processing system, information processing method, and program

Abstract

Provided is an information processing system capable of creating various information related to human resources. [Solution] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program, wherein a first reception step receives an instruction to create human resources-related information relating to job offers, job searches, or personnel matters, a second reception step requests input information required for creating the human resources-related information, which is set according to the type of human resources-related information, and accepts the input of the input information, and an information creation step selects reference information according to the type of human resources-related information and creates the human resources-related information based on the input information and the reference information, and the reference information includes at least a correlation between the input information and the human resources-related information.

Description

[Technical field]

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

[0002] Patent Document 1 discloses a technology for automatically generating a job posting. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7329159 Summary of the Invention [Problem to be solved by the invention]

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

[0005] In view of the above circumstances, the present invention provides an information processing system and the like capable of creating various information relating to human resources. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program, wherein a first reception step receives an instruction to create human resources-related information relating to job offers, job searches, or personnel matters, a second reception step requests input information required for creating the human resources-related information, the input information being set according to the type of human resources-related information, and accepts the input information, and an information creation step selects reference information according to the type of human resources-related information and creates the human resources-related information based on the input information and the reference information, the reference information including at least a correlation between the input information and the human resources-related information.

[0007] According to this embodiment, the user can create information relating to various human resources. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of the server device 10. FIG. [Diagram 3] FIG. 2 is a block diagram showing the hardware configuration of a recruiter terminal 20 and a job seeker terminal 30. [Figure 4] FIG. 2 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiter terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Diagram 5] FIG. 2 is a diagram showing an example of a human resources related information type selection screen TD displayed on the recruiter terminal 20 or the job seeker terminal 30. [Figure 6] FIG. 2 is a diagram showing an example of an information input screen ID displayed on the recruiter terminal 20 or the job seeker terminal 30. [Figure 7] 13 is a diagram showing an example of an information creation result screen RD displayed on the recruiter terminal 20 or the job seeker terminal 30. FIG. [Figure 8] 2 is an activity diagram showing an example of the flow of information processing (human resources related information creation processing) executed by the information processing system 1. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

[0010] Incidentally, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or 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] In addition, in various information processing according to an embodiment, an input and an output according to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of 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 judgment formula such as a regression formula constructed by a statistical method), or may be a trained model that has previously trained the correlation between the input and the output, or may be a large-scale language model that can output a desired result by inputting a prompt.

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

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

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

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

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

[0017] <Server device 10> Fig. 2 is a block diagram showing a 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 to each other inside the server device 10 via the communication bus 14.

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

[0019] <Storage section 12> The storage unit 12 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the 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 Division 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, 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 in an on-premise form or in a cloud form. The server device 10 in a cloud form may provide the above-mentioned functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] <Employer Terminal 20> FIG. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. The recruiter terminal 20 is an information processing terminal used by the recruiter. The "recruiter" includes organizations such as profit-making corporations (e.g., companies, etc.), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.) or their personnel. Here, the personnel may be called a recruiter, and may include personnel in the organization's human resources department, personnel in the department that hires personnel, etc. The recruiter also includes a human resources agency that acts as an agent of the organization and acts as an intermediary between the job seeker and the organization. A human resources agency is also called a headhunter, agent, etc.

[0023] 3A, the recruiter terminal 20 comprises a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected within the recruiter terminal 20 via the communication bus 26. Descriptions of the control unit 21, the memory unit 22, and the communication unit 23 will be omitted as they are similar to the descriptions of the respective units in the server device 10.

[0024] <Input section 24> The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 may execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter terminal 20, or may be externally attached. 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, and the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, and the like can be adopted instead of a touch panel.

[0025] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the recruiter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, a plasma display, or the like. It is preferable that these display devices are implemented by using different devices depending on the type of recruiter terminal 20.

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

[0027] 3B, the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected within the job seeker terminal 30 via the communication bus 36. Descriptions of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are the same as the descriptions of the respective units in the recruiter terminal 20.

[0028] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (at least one processor included in the information processing system 1).

[0029] FIG. 4 is a block diagram showing functions realized by the server device 10 (control unit 11), the recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0030] As shown in FIG. 4A, the server device 10 (control unit 11) includes 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] 4B, the recruiting party terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in FIG. 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0032] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the recruiter terminal 20 or the job seeker terminal 30. For example, the basic display control unit 111 displays information on job seekers or recruiters registered in the database, information (documents) created by the information creation unit 114, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30 in response to a request from each user (recruiters U1, U2 or job seekers U3, U4).

[0033] <First Reception Unit 112> The first reception unit 112 is configured to receive, from the recruiter terminal 20 or the job seeker terminal 30, an instruction to create human resources related information relating to a job offer or a job search.

[0034] "Human resources-related information" includes at least one of first human resources-related information about job offers (mainly created by employers) and second human resources-related information about job searches (mainly created by job seekers). Types of first human resources-related information include job postings, scouting documents for job seekers, search conditions for job seekers, summary information about employers, minutes of interviews between employers and job seekers, analytical information on the behavior of job seekers, statistical information on organizational employees, etc. Types of second human resources-related information include documents about the work history of job seekers, reply documents from employers to scouting documents, search conditions for job offers, analytical information on job information, etc. This allows the user, the employer or job seeker, to reduce the amount of work required to create documents, papers, data, etc. necessary for job offers or job searches.

[0035] The "job seeker search criteria" is a search query that includes keywords, attribute information, etc. for searching for job seekers who meet the job requirements, the conditions desired by employers, etc. in the information processing system 1 or a job seeker search system external to the information processing system 1.

[0036] "Employer summary information" is a summary of information about the employer themselves or the organization to which the employer belongs. The summary information may be, for example, a document that summarizes the information about the organization by item. Items of organizational information include, for example, basic information (name, year of establishment, etc.), organization overview, business content, products handled (products or services provided), industry, organizational size, performance, financial situation, business plan (management policy), organizational structure (management structure), corporate culture (mission, vision, etc.), job types (positions) being recruited for, and items that combine these (for example, "organization overview and business content").

[0037] "Minutes of interviews between recruiters and job seekers" include minutes of interviews for job applications, minutes of conversations between recruiters and job seekers before applying for a job, etc. "Interviews" may also include interviews conducted between recruiters and job seekers in the hiring process.

[0038] "Analysis information of job seeker behavior" is information obtained by analyzing the behavior of job seekers on the service provided by the information processing system 1. Analysis information of job seeker behavior includes, for example, data (numerical values ​​or graphs) analyzing the timing of job seeker actions (for example, viewing a job offer, opening a scouting letter from an employer, replying to a scouting letter from an employer, applying for a job offer, passing the screening process, concluding a job offer, leaving the service, etc.) and the occurrence rate of these actions for each attribute of the job seeker.

[0039] "Statistical information on organization employees" is statistical information on human resources working for the employer's organization (i.e., hired job seekers). The statistical information on organization employees includes, for example, data (numerical values ​​or graphs) on the distribution of attributes of organization employees, and may also include information obtained by analyzing data from an employee management system or an applicant tracking system (ATS). The statistical information may also include, for example, statistical values ​​(e.g., average, median, maximum, minimum, time-series change, etc.) of data on organization employees described below. Furthermore, the statistical information may also include information comparing the statistical values ​​of the data with previously prepared judgment data (reference values). For example, the statistical information may include indicators that have declined or worsened from the previous year, indicators with achievement rates for targets or KPIs that are less than 100% (i.e., targets or KPIs that have not been achieved), etc.

[0040] A "document relating to the job seeker's work history" is, for example, a document called a resume, in which the job seeker conveys to the employer his or her work history, experience, skills, qualifications, etc. The document relating to the job seeker's work history may include the job seeker's resume, other profile information, and the job seeker's desired industry, job type, and other conditions. A "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, work history, desired working conditions, etc.

[0041] The "job search criteria" is a search query including keywords, attribute information, etc. for searching for jobs or employers that meet the conditions desired by the job seeker in the information processing system 1 or in a job search system external to the information processing system 1.

[0042] "Job information analysis information" is information obtained by analyzing documents, etc., created by employers, such as job postings, scouting documents, etc. Job information analysis information includes, for example, data (numerical values ​​or graphs) obtained by classifying or analyzing the recruitment requirements (e.g., annual salary, etc.) described in job postings, scouting documents, etc., based on text information.

[0043] An instruction to create human resources-related information may include first information indicating a type (category) of the human resources-related information and second information indicating a more detailed aspect (subcategory) of the human resources-related information than the type. For example, an instruction to "create a new job posting" includes first information called "job posting" and second information called "new creation". Also, for example, an instruction to "modify a job posting" includes first information called "job posting" and second information called "modification". The first information and the second information may have a hierarchical structure, and for example, the second information may be stored in association with a lower level of the first information. Also, the first information may be called first-level information, and the second information may be called second-level information. Also, the first information may represent an object to be created based on an instruction, and the second information may represent a method or means of creation (for example, "new creation" or "modification"). The first receiving unit 112 may receive instructions including the type of human resources related information and instructions indicating the form of the human resources related information from the recruiter terminal 20 or the job seeker terminal 30 separately (that is, in two stages).

[0044] An instruction to create human resources-related information may be accepted by an input operation into an object that accepts input of instructions and is displayed on the employer terminal 20 or the job seeker terminal 30, or by inputting a sentence on the employer terminal 20 or the job seeker terminal 30 that includes the type of human resources-related information and an instruction to create it.

[0045] The first reception unit 112 may present options set in advance for each type of human resource related information to the recruiter terminal 20 or the job seeker terminal 30, and may receive, by selecting an option, an instruction to create the type of human resource related information associated with the option from the recruiter terminal 20 or the job seeker terminal 30. This allows the user, that is, the recruiter or job seeker, to easily give an instruction to create the desired human resource related information.

[0046] The correspondence between the type and the options is stored in the storage unit 12 as, for example, a table. For example, an option "automatic job offer creation" is set in advance for the type of human resource related information "job posting." When a recruiter selects this option "automatic job offer creation," the first receiving unit 112 receives an instruction to create human resource related information of the type "job posting."

[0047] Also, multiple options may be set in advance for one type. For example, 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 for a type of human resources-related information called "job posting." In this case, each option includes first information indicating the type "job posting," and second information indicating a specific creation policy (new creation, modification, creation based on a template, creation of a template, etc.), which is an example of a form of human resources-related information.

[0048] The first reception unit 112 may present options associated with the types of human resource related information selectable by the user, according to the attributes of the user, to the recruiter terminal 20 or the job seeker terminal 30. This improves the user's operability when creating desired human resource related information, since only options corresponding to the human resource related information that can be created by the user, that is, the recruiter or job seeker, are presented to the recruiter terminal 20 or the job seeker terminal 30.

[0049] The first reception unit 112 may, for example, determine the user category, whether the user is a recruiter or a job seeker (for example, whether the user ID is the registered ID of a recruiter or a job seeker), and present pre-prepared options for recruiters or options for job seekers to the recruiter terminal 20 or the job seeker terminal 30.

[0050] The first reception unit 112 may present to the employer terminal 20 or the job seeker terminal 30 options prepared for each user attribute according to the user attributes. If the user is an employer, the attributes include, for example, the employer's affiliated organization, affiliated department, job title, etc. If the user is a job seeker, the attributes include, for example, age, educational background, current affiliated organization, current industry, current job type, current job title, current annual income, possessed skills, possessed qualifications, experienced organizations (years of tenure at each organization), experienced industries (years of experience per industry), experienced job types (years of experience per job type), desired industry, desired job type, desired annual income, desired work location, behavioral history, etc.

[0051] 5 is a diagram showing an example of a human resources related information type selection screen TD displayed on the recruiter terminal 20 or the 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 human resources 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 human resources related information to be instructed to be created.

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

[0053] The format of the input information requested by the second receiving unit 113 is not limited, and for example, text such as sentences and words, audio, images, and the like may be received as the input information.

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

[0055] For example, for a category called "minutes of interview", audio, video, text memos, etc. that record the contents of an interview, interview, meeting, or meeting are set as input information. For example, for a category called "summary information of employer", documents (data files) disclosing information about the employer, the URL of the employer's website, etc. are set as input information.

[0056] Furthermore, for example, for the category "statistical information of organization employees", data on organization employees is set as input information. "Data on organization employees" includes data registered in the personnel database of each recruiter, in addition to data from employee management systems and ATSs. Data registered in the personnel database includes, for example, employee basic data, labor and attendance data, personnel evaluation data, salary data, survey data, stress check test data, 360-degree feedback data, job posting data of the organization, candidate data, etc. Furthermore, data on organization employees may include, for example, changes in indicators (for example, comparison with the previous year), achievement rates for goals and KPIs, etc. Furthermore, data on organization employees may include, for example, information such as the intention to resign or transfer of personnel within the organization. The intention to resign or transfer of personnel within the organization is data indicating that personnel belonging to the organization have indicated an intention to resign or transfer, and is extracted from, for example, survey data, personnel evaluation data, etc.

[0057] In addition, the input information may be set according to a combination of the type (first information) of the human resources related information and the mode (second information) of the human resources related information. For example, in the case of a type (first information) of "job posting", when the mode (second information) is "new creation", only the initial information such as the position name is set as the input information, and when the mode (second information) is "modification", the initial information and the existing job posting to be modified are set as the input information.

[0058] The second reception unit 113 may select an input form from a plurality of input forms prepared in advance according to the type of human resources-related information, display the selected input form on the recruiter terminal 20 or the job seeker terminal 30, and receive input information from the displayed input form. This allows the user, the recruiter or job seeker, to input the necessary input information concisely and without omissions.

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

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

[0061] The input form may have an auxiliary input field for accepting auxiliary information arbitrarily input by the user in addition to the required input fields. The auxiliary information is detailed conditions and requests for the human resources-related information to be created, such as the format of the document to be created as the human resources-related information, and information that the user considers important when creating the information.

[0062] The second receiving unit 113 may modify the input form according to the aspect included in the instruction to create the human resources related information received by the first receiving unit 112, and display the modified input form on the recruiter terminal 20 or the job seeker terminal 30. This makes it possible to acquire input information using an input form that corresponds to the aspect of the human resources related information desired by the user, thereby improving the accuracy of generating the human resources related information in the information creation unit 114.

[0063] For example, the second reception unit 113 may call up a registered input form corresponding to the type of human resources-related information (first information), and then modify the input form by correcting, adding, etc., required input fields of the input form based on the aspect of the human resources-related information (second information).

[0064] The second reception unit 113 may correct the input form based on the difference between the sample output result of the information creation model prepared for each type of human resource related information, which is included in the reference information referred to by the information creation unit 114 described later, and the aspect of the human resource related information. The sample output result is human resource related information obtained when input information that is accepted in the registered input form (i.e., a required input field is prepared) is input to the information creation model. In other words, the second reception unit 113 may guess the input information to be input to the information creation model in order to eliminate the difference between the aspect of the sample output result and the aspect of the human resource related information input by the user, and generate an input form that can accept the input of the guessed input information.

[0065] For example, if the registered input form and sample are for a "newly created job posting" and the user's instructions are to "edit an existing job posting," the input form is edited to eliminate the difference between the "newly created job posting" mode and the "edited job posting" mode.

[0066] The second reception unit 113 may input the registered input form and the difference between the mode included in the instruction to create human resource related information received by the first reception unit 112 and a sample of the output result of the information creation model to the form correction model, thereby causing the form correction model to output a corrected input form in which the input form is corrected so as to reduce the difference. The form correction model is a learning model or a generation AI (artificial intelligence) that has been trained to be able to output a corrected input form using the input form and the difference as input. As a result, an input form that receives input information necessary to create human resource related information with the content desired by the user is presented to the user, thereby improving the accuracy of generating human resource related information.

[0067] The form correction model is included in the artificial intelligence unit 120. The form correction model, which has been trained to be able to output a corrected input form, is trained using, for example, information corresponding to the difference in appearance between the input form to be corrected and two pieces of human resource-related information (target human resource-related information and sample human resource-related information) and data of the corrected input form corresponding to these as training data.

[0068] When the form correction model is a generative AI including a large-scale language model or an AI agent described later, the second reception unit 113 receives an input of an input form and a difference between the aspects of two pieces of human resource-related information, inputs a prompt including an instruction to generate a corrected input form by correcting the input form so as to reduce the difference, and causes the form correction model to output the corrected input form. The second reception unit 113 may generate a prompt that gives an instruction to generate a corrected input form to the form correction model, and inputs the prompt to the form correction model. In addition to the instruction to generate and output the corrected input form and the original input form and the difference, the second reception unit 113 may input to the form correction model a prompt in which, for example, one or more samples of the input form and the difference and one or more samples of the corresponding corrected input form are inserted as examples, samples, or teacher data of pairs of input and output.

[0069] In addition, the second reception unit 113 may input the form of the human resources-related information and instructions to modify the form based on the information to the form modification model, thereby causing the form modification model to modify the input form and output the modified input form.

[0070] 6 is a diagram showing an example of an information input screen ID displayed on the recruiter 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 send button B12.

[0071] In the example of Figure 6, a required input field IF1 and an auxiliary input field IF2 required for "creating a new job posting" are displayed. In this example, the required input field IF1 requests the input of "company name" and "job title" as input information. Additionally, the auxiliary input field IF2 displays candidates for keywords (sentences) to be inserted into the prompt entered into the information creation model, and selection is accepted by check boxes.

[0072] When an input operation is performed on the Cancel button B11, the input contents are discarded. When an input operation is performed on the Send button B12, the contents input in each required input field IF1 are accepted as input information, and the keyword (sentence) selected in the auxiliary input field IF2 is accepted as auxiliary information. Note that if no input has been made in all required input fields IF1, the input operation on the Send button B12 is not accepted.

[0073] The second reception unit 113 may present a plurality of information creation models selectable according to the type of human resource related information to the recruiter terminal 20 or the job seeker terminal 30, and may also receive a selection of the information creation model into which the input information is to be inputted at the information creation unit 114. This allows the user, that is, the recruiter or job seeker, to instruct the creation of human resource related information, taking into consideration the characteristics of each of the plurality of prepared information processing creation models.

[0074] The "selectable information creation model" may be set in advance according to, for example, the type of human resource-related information (or a combination of the type and aspect of the human resource-related information). The multiple selectable information creation models may include both a learning model and a generation AI. The multiple information creation models may include models with different construction conditions (e.g., teacher data, learning algorithm, number of parameters, etc.), or may include information creation models provided by different vendors.

[0075] The first reception unit 112 may sequentially receive an instruction to create the human resources related information, and the second reception unit 113 may sequentially receive the request to input the input information and receive the input of the input information in a chat format. This allows the user, a recruiter or a job seeker, to seamlessly execute the process from issuing an instruction to create the human resources related information to inputting the input information in a chat format.

[0076] Specifically, the process from the instruction to create the human resources related information to the report of completion of the creation of the human resources related information may be performed, for example, in the following manner. First, the first reception unit 112 receives an instruction to create the human resources related information by text input from the user on a chat screen displayed on the employer terminal 20 or the job seeker terminal 30. The creation instruction input by the user is displayed on the chat screen as a user message. Next, the second reception unit 113 displays a response message requesting necessary input information following the user message on the same chat screen. Furthermore, the second reception unit 113 receives input or upload of input information from the user on the chat screen. The input information input by the user is displayed on the chat screen as a user message. Then, 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 information creation unit 114 has completed the creation of the human resources related information (for example, a response message including a link to the human resources related information) following the user message.

[0077] Instructions for creating human resource related information and acceptance of input information may be performed via a chat model, which is a large-scale language model that can return appropriate responses to messages input in chat format from users.

[0078] <Information Creation Department 114> The information creation unit 114 is configured to select reference information according to the type of human resources-related information for which the first receiving unit 112 has received an instruction, and to create human resources-related information based on the input information received by the second receiving unit 113 and the selected reference information.

[0079] The reference information includes at least a correlation between the input information and the human resource 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 human resource related information. The reference information may be prepared for each combination of a type of human resource related information (first information) and a form of the human resource related information (second information).

[0080] The reference information may include, for example, a table, a function, a simple algorithm, etc., that indicates the correlation between the input information and the talent-related information. The correlation included in the reference information may be constructed, for example, by statistically analyzing data that records the input information and the corresponding talent-related information.

[0081] The reference information may include an information creation model, which is a learning model or a generative AI that has been trained to be able to input the input information and output the talent-related information. In the information creation model, parameters calculated, tuned, etc., by learning form the correlation of the reference information. This makes it possible to propose talent-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 talent-related information or a combination of the type and aspect of the talent-related information.

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

[0083] When the information creation model is a generative AI including a large-scale language model or an AI agent described later, the information creation unit 114 takes input information as input, inputs a prompt including an instruction to generate human resource related information based on the input information to the information creation model, and causes the information creation model to output the human resource related information. The information creation unit 114 may generate a prompt that gives an instruction to generate human resource related information to the information creation model, and inputs the prompt to the information creation model. In addition to the instruction to generate and output human resource related information and the input information, the information creation unit 114 may input a prompt into which, for example, one or more samples of input information and one or more samples of human resource related information corresponding thereto are inserted as examples, samples, or teacher data of pairs of input and output to the information creation model.

[0084] The reference information may further include a template of a prompt to be input to the information creation model. The template of the prompt is prepared for each type of human resource related information or for each combination of the type and mode of human resource related information. In other words, as the reference information, a model set combining the information creation model, which is the generating AI, and the template of the prompt may be prepared for each type of human resource related information or for each combination of the type and mode of human resource related information. In this case, the information creation unit 114 selects a model set according to the type of human resource related information or the combination of the type and mode of human resource related information.

[0085] The reference information may further include a sample output result of the information creation model prepared for each type of human resource related information. The sample output result may be prepared for each combination of the type and aspect of the human resource related information. In other words, as the reference information, a model set combining the information creation model, which is the generating AI, and the sample output result may be prepared for each type of human resource related information or for each combination of the type and aspect of the human resource related information. The model set may further include a prompt template as described above.

[0086] When the reference information includes an information creation model, the information creation unit 114 inputs the input information accepted by the second accepting unit 113 to an information creation model corresponding to the type of human resource related information (or a combination of the type and aspect of the human resource related information) and causes the information creation model to output the human resource related information. Also, when the second accepting unit 113 accepts the selection of an information creation model from the user, the information creation unit 114 inputs the input information to the selected information creation model and causes it to output the human resource related information.

[0087] When the information creation model to which the input information is input is a generation AI and the reference information includes a prompt template, the information creation unit 114 may select a prompt template according to the type of human resource related information, and input a prompt obtained by adding the input information to the template to the information creation model. This allows the human resource related information to be created using a prompt according to the output of the human resource related information, thereby improving the quality of the generated human resource related information.

[0088] The prompt template includes a sentence describing the instruction content and an insertion area for input information or sample information (dummy information) for input information. The information creation unit 114 creates a prompt by inserting the input information accepted by the second acceptance unit 113 into the insertion area for the prompt or by replacing the input information with the sample information in the template, and inputs the prompt into the information creation model. In addition, when the second acceptance unit 113 accepts auxiliary information, the information creation unit 114 also adds the auxiliary information to the template.

[0089] The information creation unit 114 may modify a prompt template according to the aspect included in the instruction to create the human resource related information received by the first reception unit 112 or the auxiliary information received by the second reception unit 113 together with the input information, and may input the prompt obtained by adding the input information to the modified template to the information creation model. This allows tuning of the prompt according to the contents of the user's input, and therefore allows fine adjustments to be made to the created human resource related information in accordance with the user's wishes.

[0090] When correcting the prompt template based on the aspect of the human resources related information, the information creation unit 114 may correct the prompt template based on the difference between the sample output result of the information creation model prepared for each type of human resources related information and the aspect of the human resources related information. In other words, in order to eliminate the difference between the sample output result and the aspect of the human resources related information input by the user, the information creation unit 114 may infer instructions to be input to the information creation model, which is a generation AI, and generate a prompt template (correction template) for inputting the inferred instructions. The information creation unit 114 inputs the prompt obtained by adding the input information to the correction template to the information creation model.

[0091] The information creation unit 114 may input to the first template correction model the registered prompt template and the difference between the aspect included in the instruction to create human resource related information received by the first receiving unit 112 and a sample of the output result of the information creation model, thereby causing the first template correction model to output a corrected template in which the prompt template is corrected so as to reduce the difference. The first template correction model is a learning model or a generation AI that is trained so as to be able to output a corrected template using the template and the difference as input. As a result, a prompt including instructions necessary to create human resource related information with the content desired by the user is input to the information creation model, thereby improving the accuracy of generating human resource related information.

[0092] The first template correction model is included in the artificial intelligence unit 120. The first template correction model, which has been trained to be able to output a corrected template, is trained using, for example, information corresponding to the difference in aspects between the template to be corrected and two pieces of human resource-related information (target human resource-related information and sample human resource-related information) and data of the corrected template corresponding thereto as training data.

[0093] When the first template correction model is a generative AI including a large-scale language model or an AI agent described later, the information creation unit 114 inputs a prompt including an instruction to generate a modified template by modifying the template so as to reduce the difference, and outputs the modified template to the first template correction model. The information creation unit 114 may generate a prompt that gives an instruction to generate the modified template to the first template correction model, and input the prompt to the first template correction model. Furthermore, the information creation unit 114 may input a prompt into which, in addition to the instruction to generate and output the modified template and the original template and difference, one or more samples of the template and difference and one or more corresponding samples of the modified template are inserted as examples, samples, or teacher data of input and output pairs to the first template correction model.

[0094] In addition, the information creation unit 114 may input, to the first template correction model, the aspect of the human resources related information and an instruction to correct the template based on the information, thereby causing the first template correction model to correct the template and output the corrected template.

[0095] Furthermore, when modifying a 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 an instruction to refer to the auxiliary information is included). The information creation unit 114 inputs a prompt obtained by adding the 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 to the second template correction model, thereby causing the second template correction model to output a modified template in which the prompt template is modified so as to refer to the auxiliary information in addition to the input information. The second template correction model is a learning model or a generation AI that has been trained so as to be able to output a modified template using a template and auxiliary information as input.

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

[0098] When the second template correction model is a generative AI including a large-scale language model or an AI agent described later, the information creation unit 114 inputs a prompt including an instruction to generate a modified template in which the template is modified so that the auxiliary information is referred to when the information creation model creates human resource-related information, to the second template correction model, and causes the second template correction model to output the modified template. The information creation unit 114 may generate a prompt that gives an instruction to generate the modified template to the second template correction model, and input the prompt to the second template correction model. Furthermore, the information creation unit 114 may input a prompt to the second template correction model in which, for example, one or more samples of the template and auxiliary information and one or more samples of the modified template corresponding thereto are inserted as examples, samples, or teacher data of input and output pairs in addition to the instruction to generate and output the modified template and the original template and auxiliary information.

[0099] In addition, the information creation unit 114 may input the auxiliary information and an instruction to modify the template based on the auxiliary information to the second template correction model, thereby causing the second template correction model to correct the template and output the modified template.

[0100] Fig. 7 is a diagram showing an example of the information creation result screen RD displayed on the recruiter terminal 20 or the job seeker terminal 30. The information creation result screen RD displays the contents of the human resources related information created by the information creation unit 114. In the example of Fig. 7, a job advertisement created as the human resources related information is displayed.

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

[0102] The "function usage conditions" are, for example, the attributes of a user who can use the function for creating the corresponding type of human resources-related information (instruct the creation of human resources-related information). The "user attributes" here include the user classification, such as whether the user is a recruiter or a job seeker, as well as the organization, department, and job title of the user who is the recruiter. For example, if the user is a job seeker, the information creation unit 114 will not create human resources-related information of the type "job posting." Also, for example, even if the user is a recruiter (organization employee), if the user does not belong to a department included in the function usage conditions (a department that has the authority to create job postings), the information creation unit 114 will not create human resources-related information of the type "job posting."

[0103] Function usage conditions may be set for each combination of type (first information) and mode (second information) of human resources-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, if the user's job title meets the function usage condition of "modifying an existing job posting," the information creation unit 114 executes this function, but does not execute this function if the user's job title does not meet the requirements of the function usage condition of "creating a new job posting."

[0104] When the user does not satisfy the function usage conditions, the information creation unit 114 may create the corresponding human resources related information with limited content. For example, when the user does not satisfy the function usage conditions of "creating a new job posting", the information creation unit 114 may create the human resources related information (job posting) by referring to less information (data) than when the user satisfies the function usage conditions. Also, for example, when the user does not satisfy the function usage conditions of "creating a new job posting", the information creation unit 114 may create the human resources related information (job posting) with fewer items (containing less information) than when the user satisfies the function usage conditions.

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

[0106] An "AI agent" is a model that, when a target (goal, objective, etc.) such as "I want to make XX" or a task such as "output XX" is input, breaks down the processing required to reach the goal or accomplish the task into subtasks, actions, etc., and collects and analyzes necessary data, generates and executes programs, etc. The AI ​​agent autonomously selects and executes tasks, actions, etc., without requiring user intervention (operation input). The AI ​​agent may also autonomously learn to achieve the goal by autonomously making and executing plans and evaluating the results of the execution. For example, the AI ​​agent may be autonomously updated based on the results of the execution of subtasks (e.g., collected information, analysis results of information, etc.). The AI ​​agent may include a generative AI (including a large-scale language model) that has been trained to be able to perform these processes.

[0107] The AI ​​agent has, for example, a function of causing a processing model such as a generation AI to generate a task in response to input from a user including instructions, a function of collecting information from the memory unit 12 of the information processing system 1 or an external system, and a function of causing a processing model such as a generation AI to analyze the collected information. In addition, the AI ​​agent can collect information necessary for correction from an internal memory unit or an external system, and generate correction information by correcting the collected information by using the collected information as part of the input to the processing model.

[0108] The AI ​​agent may generate a prompt for executing a subtask and input the prompt to an external large-scale language model to obtain a result of the execution of the subtask from the external large-scale language model, or may execute the generated prompt by itself. The AI ​​agent may also create input information for causing an external processing model that executes a specific process to execute a specific process, and input the input information to the processing model to obtain a result of the execution of the subtask from the processing model.

[0109] Specifically, the AI ​​agent may execute a task, for example, in the following procedure. First, the AI ​​agent receives a specific instruction including a goal or a task from a user. Next, the AI ​​agent divides the goal or task into multiple subtasks or actions required to achieve the goal or task, and generates the subtasks or actions. After dividing the goal or task, the AI ​​agent collects information required to execute the multiple subtasks and actions. For example, the AI ​​agent collects information by accessing a database, the Internet, etc., web search, API (Application Programming Interface) linkage to an external service, etc. After collecting the information, the AI ​​agent executes multiple subtasks and actions based on the collected information, for example, by using an external tool, etc., by generating and executing a code, and outputs a task corresponding to the goal or the execution result of an input task.

[0110] In addition, the AI ​​agent may verify or evaluate the results of the subtask or action by itself, and if it determines that review is necessary, it may correct or improve the subtask or action and re-execute it. For example, after generating code to execute a specific subtask, the AI ​​agent may verify the code by itself and correct the code by providing feedback.

[0111] In specific steps of the control unit 11, the first reception unit 112 may receive an instruction to the AI ​​agent to create human resource related information from the user. Also, the second reception unit 113 may cause the AI ​​agent to request the user to input input information (to present an input form) and receive input information from the user to the AI ​​agent. In other words, the first reception unit 112 and the second reception unit 113 may obtain necessary instructions, information, etc. from a conversation between the AI ​​agent and the user.

[0112] When accepting input information, the AI ​​agent may, as a subtask, autonomously modify the input form based on instructions for creating human resources-related information entered by the user, or may have a processing model modify the input form and present the modified input form to the user.

[0113] The information creation unit 114 may cause the AI ​​agent to create the human resource related information. For example, the information creation unit 114 uses an API provided by a business (vendor) that provides the AI ​​agent to cause the AI ​​agent to create the human resource related information and acquires the human resource related information created by the AI ​​agent. The AI ​​agent that receives an instruction to create the human resource related information inputs a prompt including an instruction to output the human resource related information based on the input information to an information creation model that is a generation AI, and causes the information creation model to output the human resource related information. Here, when inputting the prompt to the information creation model, the AI ​​agent may autonomously correct the prompt based on the human resource related information creation instruction (type of human resource related information) and auxiliary information input by the user as a subtask, or may cause the processing model to correct the prompt and input the corrected 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 the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0115] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with a learning model such as a transformer 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), or a language model such as a recurrent neural network (RNN), and may include a generative AI including a large-scale language model. The large-scale language model is a type of generative AI and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. In addition, the artificial intelligence unit 120 may include any machine learning model, deep learning model, artificial intelligence model, etc.

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

[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). The training data is composed of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used 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) that has learned a huge amount of data as an artificial intelligence. The LLM is a learning model that has learned a large amount of large data (for example, (i) web content on the Internet, or (ii) data stored in a specified database) composed of text data and the like in advance, and can execute various language processing tasks by giving tasks. According to a given prompt, it can perform a wide range of natural language processing tasks such as grasping sentence patterns and contexts, answering questions, and generating sentences. Such a general-purpose learning model includes a language model that can handle various tasks without fine tuning by One-shot Learning, Few-shot Learning, etc. In addition, the general-purpose learning model may be configured to be able to handle various tasks by Zero-shot Learning as well. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

[0119] The learning model included in the artificial intelligence unit 120 (the learning model used in each functional unit, such as the information creation model) can perform additional learning as transfer learning or fine tuning. For example, each time new data is registered, the artificial intelligence unit 120 may perform additional learning and fine tuning using the new data as new teacher data. This improves the accuracy of 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 an original learning model. In knowledge distillation, a learned model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted so that the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model is reduced, thereby learning the student model, and the student model becomes a distilled model. In addition, the student model may be learned so that the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model) is reduced. Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while having performance close to that of the learning model. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0121] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the learning model used in each functional unit, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the learning model used in each functional unit.

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

[0123] <Operation acquisition part> The operation acquisition unit 212 of the recruiting party terminal 20 accepts operations by a recruiter who uses the recruiting party terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by a job seeker who uses the job seeker terminal 30.

[0124] 3. Information processing method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

[0125] This information processing includes a first reception step, a second reception step, and an information creation step. In the first reception step, an instruction to create human resources related information related to a job offer or job search is received. In the second reception step, input information required for creating the human resources related information, which is set according to the type of human resources related information, is requested, and the input information is accepted. In the information creation step, reference information is selected according to the type of human resources related information, and the human resources related information is created based on the input information and the reference information.

[0126] 8 is an activity diagram showing an example of the flow of information processing (human resources related information creation processing) executed by the information processing system 1. The information processing will be described below along with each activity of this activity diagram.

[0127] The human resources related information creation process begins with a user (employer or job seeker) issuing an instruction to create human resources related information. The user inputs an instruction to create human resources related information at the recruiter terminal 20 or the job seeker terminal 30 (activity A101). The server device 10 accepts the instruction input to the recruiter terminal 20 or the job seeker terminal 30 (activity A102). Next, the server device 10 requests the recruiter terminal 20 or the job seeker terminal 30 to input information according to the type of human resources related information instructed (activity A103). As a result, an input information request screen is displayed on the recruiter terminal 20 or the job seeker terminal 30, and the user inputs the input information (activity A104).

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

[0129] 4. Effect The operation of this embodiment can be summarized as follows: That is, various information related to human resources can be created.

[0130] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and can be modified as appropriate without departing from the technical concept of the invention.

[0131] 5.Other In the above embodiment, the server device 10 performs various storage and control, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain 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 artificial intelligence unit 120, which is an external configuration, is 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 a request to execute an artificial intelligence service, and return an instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides a service using a language model as a learning model, or may be a server that executes a language processing task using a language model. The artificial intelligence service server may be constructed by LLM. The artificial intelligence service server receives input of a prompt by text, image, voice, etc., and generates and responds to the prompt.

[0132] The human resource related information created by the server device 10 (control unit 11) is not limited to information related to job offers or job searches, and may be information related to personnel. For example, the first reception unit 112 may receive an instruction to create human resource related information related to personnel from an administrator terminal used by an administrator (personnel officer) of an organization. The second reception unit 113 may request the administrator terminal to input input information required to create human resource related information related to personnel, and may also receive the input of the input information from the administrator terminal.

[0133] The aspect of the present embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes 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] It may be provided in any of the following ways:

[0135] (1) An information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: a first reception step, receiving an instruction to create human resources related information relating to job offers, job searches, or personnel; a second reception step, requesting input information required for creating the human resources related information, the input information being set according to a type of the human resources related information, and accepting the input of the input information; an information creation step, selecting reference information according to the type of the human resources related information, and creating the human resources related information based on the input information and the reference information, wherein the reference information includes at least a correlation between the input information and the human resources related information.

[0136] (2) In the information processing system described in (1) above, the types of the human resources-related information include at least one of job postings, scouting documents for job seekers, search conditions for job seekers, summary information about employers, minutes of interviews between employers and job seekers, analytical information on job seeker behavior, documents related to the work history of job seekers, reply documents to scouting documents from employers, search conditions for job postings, analytical information on job information, and statistical information on organizational employees.

[0137] (3) In the information processing system described in (1) or (2) above, the reference information includes an information creation model, which is a learning model or a generative AI that has been trained to be able to input the input information and output the human resources-related information, and in the information creation step, the input information is input into the information creation model and the information creation model is caused to output the human resources-related information.

[0138] (4) In the information processing system described in (3) above, the information creation model is a generative AI, the reference information further includes a template of a prompt to be input to the information creation model, and in the information creation step, the template is selected according to the type of the human resources-related information, and a prompt obtained by adding the input information to the template is input to the information creation model.

[0139] (5) In the information processing system described in (4) above, in the information creation step, the template is modified according to an aspect included in the instruction for creating the human resources-related information received in the first reception step, or auxiliary information received together with the input information in the second reception step, and a prompt obtained by adding the input information to the modified template is input into the information creation model.

[0140] (6) In the information processing system described in (5) above, the reference information further includes a sample of an output result of the information creation model, and in the information creation step, the template and a difference between the sample and an aspect included in the instruction to create the human resources related information received in the first reception step are input to a template correction model, thereby causing the template correction model to output a modified template obtained by modifying the template, and here, the template correction model is a learning model or a generation AI that has been trained so as to be able to input the template and the difference and output the modified template.

[0141] (7) In an information processing system described in any one of (3) to (6) above, in the second reception step, a plurality of information creation models selectable according to the type of the human resources-related information are presented, and a selection of the information creation model into which the input information is input in the information creation step is accepted.

[0142] (8) In the information processing system described in any one of (1) to (7) above, in the second reception step, an input form is selected from a plurality of input forms prepared in advance according to the type of the human resources-related information, the selected input form is displayed, and the input of the input information is received from the displayed input form.

[0143] (9) In the information processing system described in (8) above, in the second reception step, the input form is modified in accordance with the aspect included in the instruction for creating the human resources-related information received in the first reception step, and the modified input form is displayed.

[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 generation AI trained to be capable of using the input information as input and outputting the human resources related information, and a sample of an output result of the information creation model prepared for each type of the human resources related information, and in the second reception step, the input form and a difference between the mode included in the instruction for creating the human resources related information received in the first reception step and the sample are input into a form correction model, thereby causing the form correction model to output a corrected input form obtained by correcting the input form, and here, the form correction model is a learning model or a generation AI trained to be capable of using the input form and the difference as input and outputting the corrected input form.

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

[0146] (12) In the information processing system described in any one of (1) to (11) above, in the first reception step, preset options are presented for each type of the human resources-related information, and an instruction to create the human resources-related information of the type to which the option is associated is received by selecting one of the options.

[0147] (13) In the information processing system described in (12) above, in the first reception step, the options corresponding to the types of the human resources-related information selectable by the user are presented according to the attributes of the user.

[0148] (14) In an information processing system according to any one of (1) to (13) above, the first reception step receives an instruction to create the human resources-related information, and the second reception step requests the input of the input information and receives the input of the input information sequentially in a chat format.

[0149] (15) An information processing method comprising steps executed by an information processing system according to any one of (1) to (14) above.

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

[0151] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0152] 1: Information processing system 2: Communication lines 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter terminal 21: Control section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job Seeker Terminal 31: Control section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 111: Basic display control unit 112: First Reception Section 113: Second Reception Section 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: Category selection screen TF: Type input field

Claims

1. An information processing system, At least one processor; The processor is configured to execute the following steps by reading the program: In the first reception step, an instruction to create human resources-related information related to a job offer, a job search, or personnel is received, In the second reception step, input of input information necessary for creating the human resources related information, which is set according to the type of the human resources related information, is requested, and the input of the input information is received; An information processing system, in which in an information creation step, reference information is selected according to the type of the human resources-related information, and the human resources-related information is created based on the input information and the reference information, wherein the reference information includes at least a correlation between the input information and the human resources-related information.

2. 2. The information processing system according to claim 1, An information processing system in which the types of human resources-related information include at least one of job postings, scouting documents for job seekers, search conditions for job seekers, summary information about employers, minutes of interviews between employers and job seekers, analytical information on job seeker behavior, documents related to the job seeker's work history, reply documents to scouting documents from employers, job search conditions, analytical information on job information, and statistical information on organizational employees.

3. 2. The information processing system according to claim 1, The reference information includes an information creation model, which is a learning model or a generative AI that has been trained to be able to input the input information and output the human resources-related information, In the information creation step, the input information is input to the information creation model, and the information creation model is caused to output the human resources-related information.

4. 4. The information processing system according to claim 3, The information generating model is a generative AI, the reference information further includes templates of prompts to be input into the information creation model; In the information creation step, the template is selected according to the type of the human resources-related information, and a prompt obtained by adding the input information to the template is input to the information creation model.

5. 5. The information processing system according to claim 4, In the information creation step, the template is modified according to the aspect included in the instructions for creating the human resources-related information received in the first reception step, or auxiliary information received together with the input information in the second reception step, and a prompt obtained by adding the input information to the modified template is input into the information creation model.

6. 6. The information processing system according to claim 5, The reference information further includes a sample of an output result of the information creation model; an information processing system, in which, in the information creation step, the template and a difference between the aspect included in the instructions for creating the human resources related information received in the first reception step and the sample are input to a template correction model, thereby causing the template correction model to output a modified template obtained by modifying the template, and the template correction model is a learning model or a generative AI that has been trained so as to be able to input the template and the difference and output the modified template.

7. 4. The information processing system according to claim 3, In the second reception step, a plurality of information creation models selectable according to the type of the human resources-related information are presented, and the selection of the information creation model into which the input information is input in the information creation step is received, in an information processing system.

8. 2. The information processing system according to claim 1, In the second reception step, an information processing system selects an input form from a plurality of input forms prepared in advance according to the type of the human resources-related information, displays the selected input form, and receives input of the input information from the displayed input form.

9. 9. The information processing system according to claim 8, In the second reception step, the input form is modified in accordance with the aspect included in the instructions for creating the human resources-related information received in the first reception step, and the modified input form is displayed.

10. 10. The information processing system according to claim 9, The reference information is An information creation model, which is a learning model or a generative AI that has been trained to be able to input the input information and output the human resources-related information; A sample of an output result of the information creation model prepared for each type of the human resources-related information; Including, In the second reception step, the input form and the difference between the aspect included in the instructions for creating the human resources-related information received in the first reception step and the sample are input into a form correction model, thereby causing the form correction model to output a corrected input form by correcting the input form, wherein the form correction model is a learning model or a generative AI that has been trained so as to be able to input the input form and the difference and output the corrected input form.

11. 2. The information processing system according to claim 1, In the information creation step, if the user does not satisfy function usage conditions set for each type of human resources related information, the information processing system restricts creation of the human resources related information received from the user.

12. 2. The information processing system according to claim 1, In the first reception step, an information processing system presents pre-set options for each type of human resources-related information, and, upon selection of an option, receives an instruction to create the human resources-related information of the type to which the option is associated.

13. 13. The information processing system according to claim 12, In the first receiving step, the information processing system presents the options associated with types of the human resources-related information selectable by the user in accordance with attributes of the user.

14. 2. The information processing system according to claim 1, An information processing system which sequentially receives instructions for creating the human resources-related information in the first reception step, and requests the input of the input information and accepts the input of the input information in the second reception step in a chat format.

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

16. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 14.

Images