Information processing systems, information processing methods, and programs

Abstract

We provide an information processing system that allows employers to obtain evaluations of job seekers. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program, the acquisition step acquiring condition information including at least one evaluation condition and registration information of a job seeker, the evaluation condition being a condition that an employer requires of a job seeker, the evaluation creation step creating an evaluation of the registration information based on a combination of the condition information and the registration information and evaluation reference information, the evaluation reference information being information relating to the correlation between the combination of the condition information and the registration information and the evaluation, the result display control step simultaneously displaying the evaluation and an input area that accepts editing of the evaluation condition, and the update step updating the evaluation condition according to the content entered into the input area.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a technique for assisting in obtaining information on job applicants and job seekers.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need for a technique that enables a job applicant to obtain an evaluation of a job seeker.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that enable a job applicant to obtain an evaluation of a job seeker.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program, wherein in the acquisition step, condition information including at least one evaluation condition and registration information of a job seeker are acquired, the evaluation condition being a condition that an employer requires of a job seeker; in the evaluation creation step, an evaluation of the registration information is created based on a combination of the condition information and the registration information and evaluation reference information, the evaluation reference information being information relating to the correlation between the combination of the condition information and the registration information and the evaluation; in the result display control step, the evaluation and an input area that accepts editing of the evaluation condition are displayed simultaneously; and in the update step, the evaluation condition is updated according to the content entered into the input area.

[0007] In this manner, employers can obtain evaluations of job seekers. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of server device 10. [Figure 3] This block diagram shows the hardware configuration of the job seeker terminal 20 and the job applicant terminal 30. [Figure 4] This is a block diagram showing the functions realized by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). [Figure 5] This figure shows an example of the condition creation screen CD displayed on the job seeker terminal 20. [Figure 6] This figure shows an example of the preliminary evaluation result display screen PD that is displayed on the applicant terminal 20. [Figure 7] This figure shows an example of the conditions editing screen MD displayed on the job seeker terminal 20. [Figure 8] This figure shows an example of the screening results display screen SD that is displayed on the job seeker terminal 20. [Figure 9]This figure shows an example of the detailed results display screen RD shown on the job seeker terminal 20. [Figure 10] This is an activity diagram showing an example of the flow of information processing (evaluation display processing) performed by Information Processing System 1. [Modes for carrying out the invention]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0023] "Employers" include organizations such as for-profit corporations (e.g., companies), non-profit organizations (e.g., cooperatives, foundations), and public corporations (e.g., local governments), or their representatives. Representatives within employers may also be called hiring managers, and may include personnel from the organization's human resources department or the department responsible for hiring. Furthermore, employers may also include headhunters. A headhunter is an organization or its representative that acts as an intermediary between job seekers and employers (organizations) on behalf of the organization (employer). Headhunters are also known as recruitment agencies, hiring agents, or recruitment agencies.

[0024] Furthermore, "organization" includes for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.). In addition, "organization" is not limited to a single legal entity, but may also include a group composed of multiple legal entities with capital relationships or partnerships (e.g., a group consisting of a parent company, subsidiaries, affiliated companies, etc.).

[0025] As shown in Figure 3A, the job seeker terminal 20 comprises a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, storage unit 22, communication unit 23, input unit 24, and output unit 25 are electrically connected within the job seeker terminal 20 via the communication bus 26. The descriptions of the control unit 21, storage unit 22, and communication unit 23 are the same as the descriptions of each part in the server device 10 and are therefore omitted.

[0026] <Input section 24> The input unit 24 receives operation inputs made by the user. The operation inputs are transmitted as command signals to the control unit 21 via the communication bus 26. The control unit 21 can perform predetermined controls or calculations based on the transmitted command signals as needed. The input unit 24 may be included in the housing of the job seeker terminal 20 or it may be an external component. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 24. Instead of a touch panel, the input unit 24 can be a switch button, mouse, trackpad, QWERTY keyboard, etc.

[0027] <Output section 25> The output unit 25 displays a graphical user interface (GUI) screen that can be operated by the user. The output unit 25 may be included in the housing of the job seeker terminal 20 or it may be an external device. Specifically, the output unit 25 can be implemented as a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display. It is preferable that these display devices be used according to the type of job seeker terminal 20.

[0028] <Job seeker terminal 30> The job seeker terminal 30 is an information processing terminal used by job seekers and is capable of accessing the server device 10. "Job seekers" include various types of people seeking employment, such as those who are looking to change jobs or find employment (e.g., currently employed people (those seeking a job change), prospective graduates (job seekers), students, etc.), and those who are interested in changing jobs or finding employment.

[0029] As shown in Figure 3B, the job seeker terminal 30 comprises a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are electrically connected within the job seeker terminal 30 via the communication bus 36. The descriptions of the control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are the same as the descriptions of each part in the employer terminal 20 and are therefore omitted.

[0030] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (at least one processor provided by the information processing system 1).

[0031] Figure 4 is a block diagram showing the functions realized by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0032] As shown in Figure 4A, the server device 10 (control unit 11) comprises a basic display control unit 110, a group registration unit 111, a condition creation unit 112, an acquisition unit 113, an evaluation creation unit 114, a result display control unit 115, an update unit 116, an evaluation reception unit 117, a correction proposal unit 118, a candidate extraction unit 119, and an artificial intelligence unit 120.

[0033] As shown in Figure 4B, the job seeker terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in Figure 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0034] <Basic display control unit 110> The basic display control unit 110 is configured to display various information on the employer terminal 20 or the job seeker terminal 30. For example, in response to requests from each user (employers U1, U2 or job seekers U3, U4), the basic display control unit 110 displays the registration information of job seekers registered in the database on the display unit 211 of the employer terminal 20 or the display unit 311 of the job seeker terminal 30.

[0035] <Group Registration Section 111> The group registration unit 111 is configured to register a group of job seekers, including multiple job seekers, in association with a target job posting.

[0036] A "job seeker group" is composed of, for example, any job seekers (candidates) designated by the employer. Job seeker groups include those referred to by names such as target lists, scout lists, and candidate folders.

[0037] The group registration unit 111 receives, for example, the selection of multiple job seekers to be registered in a job seeker group and the job postings (target job postings) to be linked to the job seeker group from the employer terminal 20, and registers them in the database.

[0038] Furthermore, the linking of job seeker groups to target job postings is not limited to input received from the employer terminal 20 mentioned above. For example, the group registration unit 111 may automatically extract (identify) a set of job seekers from the database based on the requirements of the target job posting or the job seeker search conditions set by the employer, and link this set of job seekers to the target job posting as a job seeker group. This eliminates the need for employers to individually search for and register job seekers.

[0039] <Condition Creation Section 112> The condition creation unit 112 is configured to create condition information used for creating evaluations by the evaluation creation unit 114, which will be described later.

[0040] "Condition information" includes at least one evaluation criterion. "Evaluation criteria" are the conditions that employers require of job seekers. Evaluation criteria may also be conditions that employers require of job seekers during the screening process. Examples of evaluation criteria include skill requirements, experience requirements, and qualification requirements. Condition information may include multiple evaluation criteria. Evaluation criteria may also be called evaluation standards.

[0041] The condition creation unit 112 may accept input of evaluation conditions that differ from the requirements of the target job posting. This allows for the evaluation of job seekers from a different perspective than the requirements of the target job posting. Specifically, for example, qualitative evaluation conditions such as conditions based on the hiring manager's experience or suitability for the organizational culture can be reflected in the evaluation and screening of job seekers. Furthermore, since evaluation criteria can be flexibly input or adjusted without modifying the job posting itself, it becomes possible to input or adjust evaluation conditions according to changes in the desired candidate profile or the application status. The "requirements of the target job posting" are, for example, job requirements that define the conditions and qualities that job seekers are required to have for the position being advertised. Job requirements include, for example, required skills, required experience, and required qualifications.

[0042] The evaluation criteria may include both requirements that job seekers must meet and exclusion criteria that job seekers must not meet. This allows employers to flexibly set evaluation criteria. The criteria information may include multiple requirements and / or multiple exclusion criteria.

[0043] Conditional information may include the priority of the evaluation criteria. In particular, if the conditional information includes multiple evaluation criteria, the conditional information may include the priority of each of the evaluation criteria.

[0044] "Priority" is an indicator that shows the degree of importance of the evaluation criteria, and represents types such as mandatory conditions and desired conditions. Mandatory conditions are conditions with a higher priority than desired conditions (minimum conditions that must be met). Mandatory conditions in necessary conditions are "characteristics that must be met," and desired conditions in necessary conditions are "characteristics that are preferable to meet." Mandatory exclusion conditions are "characteristics that must not apply," and desired exclusion conditions are "characteristics that are preferable not to apply."

[0045] The condition information may include both mandatory and welcome conditions as evaluation criteria, or it may include only one of them. Furthermore, the condition information may include multiple mandatory and / or welcome conditions. In addition, further individual priorities (hierarchical priorities) may be set among the multiple mandatory and / or welcome conditions. Priorities may also be expressed numerically, not just by type (rank, etc.).

[0046] The condition creation unit 112, for example, receives input of at least one evaluation condition from the recruiter terminal 20 and creates condition information including the input evaluation condition. The condition creation unit 112 may also receive priority settings for each evaluation condition from the recruiter terminal 20 and display the evaluation conditions on the recruiter terminal 20 in a manner corresponding to the set priority. This makes it easier for recruiters to manage and set the priority of individual evaluation conditions.

[0047] "Display in a manner corresponding to priority" includes, for example, changing the display manner (color, shape, presence or absence of icons, etc.) of the input area that accepts priority settings and / or evaluation conditions according to priority, and changing the position of the input area according to priority (for example, welcome conditions are displayed below mandatory conditions).

[0048] The condition creation unit 112 may, for example, display an input field for receiving evaluation conditions and a priority setting object associated with the input field on the recruiter terminal 20, and accept the input of evaluation conditions and the setting of priorities. The priority setting object accepts the setting of the evaluation condition's priority as either a "mandatory condition" or a "preferred condition". The appearance of the priority setting object may change depending on the priority. For example, the priority setting object may be displayed in either a first form representing a "mandatory condition" or a second form representing a "preferred condition". In this case, when an input operation is performed on the priority setting object in the first form, the evaluation condition corresponding to the priority setting object is changed from a mandatory condition to a preferred condition, and the priority setting object changes to the second form. Conversely, when an input operation is performed on the priority setting object in the second form, the evaluation condition corresponding to the priority setting object is changed from a preferred condition to a mandatory condition, and the priority setting object changes to the first form.

[0049] Furthermore, the condition creation unit 112 may display input fields on the recruiter terminal 20 for accepting input of evaluation conditions according to priority. In this case, the priority of the evaluation conditions is set according to the input field in which the recruiter enters the evaluation conditions.

[0050] The condition creation unit 112 may display suggestions regarding the setting of evaluation conditions on the recruiter terminal 20. These suggestions may include, for example, the content to be included as conditions, and examples of condition input. These suggestions may be standard phrases, or they may be generated by artificial intelligence or the like based on the content of the target job posting (recruitment requirements), the evaluation conditions currently being entered, etc.

[0051] The condition creation unit 112 may create condition information based on job information that includes at least the requirements of the target job and reference information for creating the first condition. This reduces the effort required for the employer to create evaluation conditions. The condition creation unit 112 may create only evaluation conditions as condition information, or it may create evaluation conditions along with their priority.

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

[0053] "Description of the organization or business" is a job description document that explains at least one of the following: the organization, industry, department, job type, duties, position, annual salary, and work style. For example, the job description document may include a description of the organization's history, business environment, characteristics, a specific description of the job type or duties, and a description of working conditions.

[0054] Job postings are typically in the form of job descriptions, but they do not necessarily need to be formatted like job descriptions. They may also be in the form of a non-standard document such as a memo that at least outlines the requirements. Furthermore, the job postings used to create the requirements information may be for job postings other than those targeted for candidate screening (for example, job postings that have already been filled).

[0055] The condition creation unit 112 may, for example, accept the upload of job information from the recruiter terminal 20 and acquire the uploaded job information. The condition creation unit 112 may also accept input from the recruiter terminal 20 such as information indicating the target job (for example, the title and ID of the target job), the location where the job information is stored (network address, URL (Uniform Resource Locator), path, etc.), and acquire the corresponding job information from a database or the like. Furthermore, the condition creation unit 112 may accept input of job information (for example, the content of the requirements) from the recruiter terminal 20.

[0056] The first condition creation reference information is information relating to the correlation between job postings and condition information. The first condition creation reference information is stored, for example, in the memory unit 12. The first condition creation reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between job postings and condition information. The correlation included in the first condition creation reference information can be constructed, for example, by statistically analyzing data that records job postings and corresponding condition information.

[0057] The reference information for creating the first condition may include a set of parameters for generating condition information from job postings. For example, the reference information for creating the first condition may be various pre-trained models. For example, the reference information for creating the first condition may include a first condition creation model which is a dedicated or general-purpose learning model that has been machine-trained to take job postings as input and output condition information. In this case, the condition creation unit 112 inputs the job postings into the first condition creation model and causes the first condition creation model to output condition information.

[0058] The first condition creation model is included in the artificial intelligence unit 120. The first condition creation model, which is a dedicated learning model, may be constructed, for example, by learning using job information data and corresponding condition information data as training data. In such a first condition creation model, parameters calculated and tuned through learning construct a correlation between job information and condition information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0059] If the first condition creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the condition creation unit 112 inputs a prompt to the first condition creation model that includes job information and an instruction to output condition information corresponding to the job information as input, causing the first condition creation model to output the condition information. The condition creation unit 112 may also generate a prompt that gives the first condition creation model an instruction to create condition information and input this prompt to the first condition creation model. In addition to job information and instructions to create and output condition information, the condition creation unit 112 may also input a prompt to the first condition creation model that includes, for example, one or more samples of job information and one or more samples of corresponding condition information as examples, samples, or training data of input and output pairs. Here, the parameters that construct the first condition creation model and the prompt that includes an instruction to output condition information corresponding to the job information construct the correlation between job information and condition information. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. Generative AI for general-purpose learning models is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0060] The condition creation unit 112 may accept edits from the recruiter terminal 20 to the condition information (evaluation conditions, priority, etc.) created based on the job information.

[0061] Figure 5 shows an example of the condition creation screen CD displayed on the job seeker terminal 20. The condition creation screen CD includes an information display area DA, a condition setting area CA, an input hint IH, a cancel button B11, and a screening start button B12.

[0062] The information display area DA displays an explanation of the automatic generation of evaluation conditions, information about the job posting used for the automatic creation of evaluation conditions (in the example in Figure 5, "Selected Job Posting"), etc. The information display area DA also displays the sample creation acceptance object SO. When an input operation is performed on the sample creation acceptance object SO, a sample of evaluation conditions is automatically generated based on the content of the selected job posting, and this sample is automatically entered into the condition setting area CA. In addition, a message MG indicating that the sample of evaluation conditions has been created and entered is displayed at the top of the condition creation screen CD.

[0063] The condition setting area CA displays multiple condition input fields CF, multiple priority acceptance objects PO, and a condition addition acceptance object AO. Each condition input field CF accepts the input or editing of one evaluation condition. If sample evaluation conditions are generated, one or more of the generated sample evaluation conditions are automatically inserted into the condition input field CF one by one in an editable state.

[0064] Priority reception objects (PO) are assigned to each condition input field (CF). Each priority reception object (PO) accepts a change in the priority of the associated evaluation condition. In the example in Figure 5, priority reception objects (PO) for evaluation conditions (condition input field CF) with priority set to "mandatory condition" are circled, while priority reception objects (PO) for evaluation conditions (condition input field CF) with priority set to "preferred condition" are not circled. When an input operation is performed on a priority reception object (PO) with a circle, the corresponding evaluation condition is set to a preferred condition, and the circle disappears from the priority reception object (PO). On the other hand, when an input operation is performed on a priority reception object (PO) without a circle, the corresponding evaluation condition is set to a mandatory condition, and a circle is added to the priority reception object (PO). Note that the display characteristics of the priority reception object (PO), such as color and size, may change according to the priority.

[0065] When an input operation is performed on the condition addition acceptance object AO, the combination of the condition input field CF and the priority acceptance object PO is added to the condition setting area CA.

[0066] The input hint IH displays the content to be entered as evaluation conditions, examples of evaluation conditions, etc. For example, the input hint IH displays messages encouraging the concretization of evaluation conditions and specific examples of evaluation conditions. This allows job seekers to intuitively understand what level of detail and expression they should use when entering evaluation conditions. If an input operation is performed on the cancel button B11, the content entered in the condition setting area CA is discarded. If an input operation is performed on the screening start button B12, the evaluation creation unit 114, described later, will perform the creation of evaluations (screening).

[0067] <Acquisition part 113> The acquisition unit 113 is configured to acquire condition information including at least one evaluation criterion and registration information of job seekers. The acquisition unit 113 may also acquire condition information including multiple evaluation criterion and registration information of one or more job seekers included in a job seeker group.

[0068] The acquisition unit 113 may acquire condition information that includes evaluation conditions that have been input by the condition creation unit 112 or evaluation conditions that have been created by the condition creation unit 112 based on the job information.

[0069] Furthermore, the acquisition unit 113 may acquire condition information including pre-prepared evaluation conditions and evaluation conditions determined by the result display control unit 115, which will be described later.

[0070] <Evaluation Creation Department 114> The evaluation creation unit 114 is configured to create an evaluation of the job seeker's registration information registered in the database, based on the condition information (evaluation conditions).

[0071] "Job seeker registration information" includes, for example, the job seeker's basic information (name, age, gender, address, etc.), current employment information (organization, industry, department, job title, duties, job description, position, annual income, etc.), and past employment information.

[0072] The registration information of job seekers may include, for example, a resume, which is a document detailing the job seeker's work history, experience, skills, qualifications, etc., to employers. The work history document may include the job seeker's resume, other profile information, and conditions such as the type of industry or job the job seeker desires. A "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, work history, and desired working conditions. The work history document may be automatically generated by artificial intelligence such as generation AI, or it may be created by the job seeker themselves.

[0073] The evaluation creation unit 114 performs a preliminary evaluation process and a screening process. The preliminary evaluation process is a process in which a preliminary evaluation of a specific job seeker is performed in order to determine the condition information (evaluation conditions) to be used for screening. The screening process is a process in which job seekers within a group of job seekers are evaluated using the condition information determined in the preliminary evaluation process, and candidates for the target job are screened based on the evaluation. Note that the evaluation creation unit 114 may perform only the screening process without performing the preliminary evaluation process.

[0074] <Preliminary evaluation process> In the preliminary evaluation process, the evaluation creation unit 114 creates an evaluation of the registration information based on the combination of the condition information and the registration information of the specific job seeker acquired by the acquisition unit 113, and the evaluation reference information.

[0075] A "specific job seeker" is a job seeker selected by the employer or the evaluation creation unit 114 from a population of job seekers registered in the database, job seeker groups (target lists), etc. There may be one specific job seeker or multiple specific job seekers. The evaluation creation unit 114 may extract specific job seekers, for example, based on the employer's evaluation of the job seeker. For example, the evaluation creation unit 114 may select or present as specific job seekers job seekers whose evaluation by the employer is above a predetermined value or predetermined rank. Alternatively, the evaluation creation unit 114 may select or present as specific job seekers job seekers who represent each range (e.g., each rank such as A, B, C) in the employer's evaluation. Note that the condition information (evaluation conditions) used to create the evaluation in the preliminary evaluation process does not have to be linked to a specific job (target job).

[0076] The "evaluation of registration information" is determined by comparing the registration information with the evaluation conditions included in the conditional information. In other words, the evaluation of registration information is based on whether or not the registration information satisfies the necessary conditions, or to what extent, and whether or not the registration information satisfies the exclusion conditions, or to what extent it does not.

[0077] The evaluation creation unit 114 may create one evaluation (overall evaluation) for one registration information, or it may create multiple evaluations (individual evaluations) for multiple evaluation conditions for one registration information. Furthermore, the evaluation creation unit 114 may create an overall evaluation of the registration information based on the multiple individual evaluations created for each evaluation condition. This improves the accuracy of the overall evaluation of the registration information. Individual evaluations and overall evaluations may be represented numerically, or by symbols representing ranks, classes, grades, etc., such as "○, △, ×" or "A, B, C...".

[0078] The evaluation reference information is information relating to the correlation between combinations of condition information and registration information and evaluations (individual evaluations or overall evaluations). The evaluation reference information is stored, for example, in the storage unit 12. The evaluation reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of condition information and registration information and evaluations. The correlations included in the evaluation reference information can be constructed, for example, by statistically analyzing data that records combinations of condition information and registration information and corresponding evaluations.

[0079] The evaluation reference information may include a set of parameters for generating an evaluation from a combination of condition information and registration information. For example, the evaluation reference information may be various pre-trained models. For example, the evaluation reference information may include an evaluation creation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take a combination of condition information and registration information as input and output an evaluation. In this case, the evaluation creation unit 114 inputs the combination of condition information and registration information into the evaluation creation model and causes the evaluation creation model to output an evaluation.

[0080] The evaluation creation model is included in the artificial intelligence unit 120. The evaluation creation model, which is a dedicated learning model, may be constructed, for example, by training using data of combinations of condition information and registered information and corresponding evaluation data as training data. In such an evaluation creation model, parameters calculated and tuned through learning construct a correlation between the combination of condition information and registered information and the evaluation.

[0081] If the evaluation creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the evaluation creation unit 114 inputs a prompt to the evaluation creation model that includes a combination of condition information and registered information, and an instruction to output an evaluation corresponding to the combination of condition information and registered information, taking the combination of condition information and registered information as input, causing the evaluation creation model to output an evaluation. The evaluation creation unit 114 may also generate a prompt that gives an instruction to the evaluation creation model to create an evaluation, and input this prompt to the evaluation creation model. In addition to the combination of condition information and registered information and the instruction to create and output an evaluation, the evaluation creation unit 114 may also input a prompt to the evaluation creation model that includes, for example, one or more sample combinations of condition information and registered information and one or more sample evaluations corresponding to them, as examples, samples, or training data of input and output pairs. Here, the parameters that construct the evaluation creation model and the prompt that includes an instruction to output an evaluation corresponding to the combination of condition information and registered information construct a correlation between the combination of condition information and registered information and the evaluation.

[0082] The evaluation creation unit 114 may create an overall evaluation based on the number of evaluation conditions that are satisfied, or on a score that quantifies the degree to which each of multiple evaluation conditions is satisfied. This allows for a uniform determination of the overall evaluation, thereby improving evaluation accuracy.

[0083] When the overall evaluation is created based on the number of fulfilled evaluation conditions, the overall evaluation is determined based on, for example, a conditional expression, judgment expression, table, etc., that defines the relationship between the number of fulfilled conditions and the overall evaluation. The "score" is a numerical value that indicates the degree of fulfillment of each evaluation condition, and is calculated, for example, by an evaluation creation model. When the overall evaluation is created based on the score, the overall evaluation is determined based on, for example, a conditional expression, judgment expression, table, etc., that defines the relationship between the score and the overall evaluation. Alternatively, the evaluation creation unit 114 may create the overall evaluation using both the number of fulfilled conditions and the score.

[0084] The evaluation creation unit 114 may create an overall evaluation based on the weighting of each evaluation condition. For example, the evaluation creation unit 114 may determine the overall evaluation based on an overall score obtained by summing the values ​​obtained by multiplying the score of each evaluation condition by a weighting coefficient set for each evaluation condition. The weighting is set, for example, by the type of evaluation condition (e.g., whether it is a required condition or an exclusion condition).

[0085] The weighting may be set according to the priority of the evaluation conditions. For example, the evaluation creation unit 114 may create an overall evaluation based on multiple evaluations and the priority of the corresponding evaluation conditions. This will create an overall evaluation that reflects the priority of each individual evaluation condition. For example, the evaluation creation unit 114 may create an overall evaluation based on the priority received from the job seeker terminal 20 by the condition creation unit 112.

[0086] The evaluation creation unit 114 may, for example, create an overall evaluation based only on the evaluation of evaluation conditions for which priority has been set as essential conditions. In other words, the evaluation creation unit 114 may determine the overall evaluation based on the number of essential conditions that are met. For example, the overall evaluation may be determined based on the number of essential conditions that are met, the percentage of conditions that are met, etc., regardless of the total number of evaluation conditions that are met (the number of welcome conditions that are met).

[0087] Alternatively, the evaluation creation unit 114 may determine the overall evaluation based on an overall score (the sum of the products of the score and weight for each evaluation condition) obtained by giving greater weight to evaluation conditions that are given priority as essential conditions than to evaluation conditions that are given priority as recommended conditions.

[0088] The results display control unit 115 may create a corresponding reason for evaluation (a document explaining the reason for the individual evaluation) for each evaluation condition. The "reason for evaluation" may include, for example, the part of the job seeker's registration information that formed the basis for the evaluation, the correspondence (satisfaction relationship) between that part and the evaluation condition, etc. The reason for evaluation may also include elements that are lacking in relation to the evaluation condition, or the reasons why the evaluation condition was determined not to be satisfied, etc.

[0089] The result display control unit 115, for example, for each job seeker included in a job seeker group, creates individual evaluations of the registered information and the reasons for those evaluations for each of several evaluation conditions, based on a combination of condition information and the job seeker's registration information, and evaluation reference information. In this case, the evaluation reference information is information regarding the correlation between the combination of condition information and registration information and the combination of individual evaluations and their reasons. This evaluation reference information may include an evaluation creation model, which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take the combination of condition information and registration information as input and output the combination of individual evaluations and their reasons. In this case, the evaluation creation unit 114 inputs the combination of condition information and registration information into the evaluation creation model and causes the evaluation creation model to output the combination of individual evaluations and their reasons.

[0090] In the preliminary evaluation process, the evaluation creation unit 114 may recreate the evaluation based on the evaluation conditions updated by the update unit 116, which will be described later. In other words, the evaluation creation unit 114 may recreate the evaluation of the registration information based on the combination of condition information including the evaluation conditions updated by the update unit 116 and the registration information of a specific job seeker, and the evaluation reference information.

[0091] The evaluation creation unit 114, upon receiving instructions from the employer, such as instructions to determine evaluation conditions, instructions to link condition information (evaluation conditions) to target job postings, or instructions to start the screening process, terminates the preliminary evaluation process and starts the screening process. The employer inputs these instructions from the employer terminal 20, for example, if the evaluation of a specific job seeker created in the preliminary evaluation process is satisfactory. The evaluation creation unit 114 may also start the screening process even without instructions from the employer, triggered by, for example, the updating or confirmation of condition information, or the addition of a new job seeker to the job seeker group.

[0092] <Screening process> In the screening process, the evaluation creation unit 114 creates individual evaluations of the registered information for each job seeker included in the job seeker group, based on a combination of condition information and the job seeker's registration information, and evaluation reference information, for each of the multiple evaluation conditions. Alternatively, after the execution of the preliminary evaluation process, the evaluation creation unit 114 may create evaluations (individual evaluations or overall evaluations) of multiple job seekers based on a combination of condition information and the registration information of multiple job seekers included in the job seeker group linked to the target job.

[0093] The condition information used in the screening process may be information acquired by the acquisition unit 113 (either created by the job seeker or automatically created by the condition creation unit 112), or it may be condition information updated by the update unit 116. Furthermore, the reference information for evaluation is the same as that used in the preliminary evaluation process described above.

[0094] The evaluation creation unit 114 receives the selection of a group of job seekers to be screened (target list) or a target job from the employer terminal 20, and creates an evaluation for the selected group of job seekers (the group of job seekers associated with the selected target job). The evaluation creation unit 114 may create an evaluation for all job seekers included in the job seeker group at once, or it may create an evaluation for only some of the job seekers included in the job seeker group. For example, the evaluation creation unit 114 may receive the selection of job seekers for whom to create an evaluation from the employer terminal 20.

[0095] The evaluations created in the screening process are the same as those created in the preliminary evaluation process. That is, in the screening process, the evaluation creation unit 114 may create an overall evaluation for each of the multiple job seekers, or it may create individual evaluations for each of the multiple evaluation conditions for the multiple job seekers. Furthermore, the evaluation creation unit 114 may create an overall evaluation of the registration information based on the multiple individual evaluations. In addition, the evaluation creation unit 114 may create reasons for each of the individual evaluations.

[0096] <Result Display Control Unit 115> The results display control unit 115 is configured to display the evaluation created by the evaluation creation unit 114 (the evaluation in the preliminary evaluation process or the evaluation in the screening process) on the job seeker terminal 20.

[0097] The result display control unit 115 performs preliminary result display processing and screening result display processing. Preliminary result display processing is the process of displaying the evaluation created by the evaluation creation unit 114 in the preliminary evaluation processing. Screening result display processing is the process of displaying the evaluation created by the evaluation creation unit 114 in the screening processing. Note that if the evaluation creation unit 114 has not performed preliminary evaluation processing, preliminary result display processing is not executed.

[0098] <Preliminary result display processing> In the preliminary results display process, the results display control unit 115 simultaneously displays on the recruiter terminal 20 the evaluation of a specific job seeker created by the evaluation creation unit 114, and an input area that accepts edits to the evaluation conditions used in the evaluation.

[0099] The "input area" includes, for example, an input field that accepts input for each evaluation criterion, and a priority setting object for each evaluation criterion associated with that input field. "Displaying the evaluation and input area simultaneously" means displaying them on the recruiter terminal 20 in such a way that the recruiter can operate the recruiter terminal 20 while referencing both the evaluation and the input area.

[0100] The result display control unit 115 displays the evaluation display area and the input area on the job seeker terminal 20, for example, by arranging them vertically or horizontally. The evaluation display area and the input area may be displayed on the same screen (within the same window), or they may be displayed on different screens (separate windows). Furthermore, the evaluation display area and the input area do not always need to be displayed on the same screen. For example, the input area may be displayed in a call format that responds to the job seeker's operation (e.g., a pop-up window, an expandable display using an accordion format, a switchable display using tabs, etc.). The input area may also be displayed overlaid on top of the evaluation display area.

[0101] The evaluation display area may display a list of evaluations (individual evaluations or overall evaluations) of multiple specific job seekers who were the subject of the evaluation, or it may display only the evaluations of specific job seekers selected by the employer. The result display control unit 115 may also display the evaluations of specific job seekers in multiple result lists for each evaluation category. An "evaluation category" is a category corresponding to, for example, the overall evaluation of a specific job seeker, or the number of evaluation conditions that a specific job seeker satisfies (all evaluation conditions, or evaluation conditions of a specific priority).

[0102] If the evaluation creation unit 114 has created individual evaluations for each of the multiple evaluation conditions, the results display control unit 115 may display the individual evaluations for each evaluation condition. Alternatively, the results display control unit 115 may simultaneously display the individual evaluations for each evaluation condition and an input area that accepts edits for multiple evaluation conditions. This makes it easier for recruiters to optimize each evaluation condition. In this case, the input areas may be arranged separately for each evaluation condition, or they may be a collection of editing acceptance areas for multiple evaluation conditions.

[0103] Furthermore, if the evaluation creation unit 114 has created individual evaluations and an overall evaluation based on them, the result display control unit 115 may display the overall evaluation in addition to the individual evaluations.

[0104] The results display control unit 115 may also display the employer's activity history for job seekers for whom an evaluation has been created, along with the evaluation, on the employer terminal 20. This allows employers to check the activity history of the evaluated job seekers along with their evaluations, making it easier to optimize the evaluation conditions.

[0105] "Employer activity history" includes, for example, the history of sending recruitment letters to job seekers, the history of assigning evaluations to job seekers' registration information, and the history of job seekers' registration to job seeker groups (target lists). Here, "recruitment letter" is a document sent by an employer or recruitment agency to a job seeker with the aim of encouraging them to apply for a selection process or proposing an interview, and may also be called a recruitment email.

[0106] The results display control unit 115 displays, for example, the activity history of the recruiter's actions toward the job seeker (such as sending a recruitment letter or assigning an evaluation) and the date and time of the action, along with the job seeker's evaluation and some of the registration information (for example, age, gender, address, current annual income, affiliated organization, current occupation, etc.) on the recruiter's terminal 20.

[0107] The results display control unit 115 may also display the reasons for the evaluation, corresponding to the evaluation conditions, created by the evaluation creation unit 114, on the recruiter terminal 20 along with the evaluation. This allows recruiters to understand the reasons for the evaluation along with the evaluation results. In particular, by showing the reasons (such as the parts of the registered information that form the basis) along with the evaluation, recruiters can make decisions regarding the suitability of a candidate with a sense of satisfaction. Furthermore, by allowing recruiters to modify the evaluation conditions while confirming the evaluation results and reasons for the evaluation, it becomes possible to efficiently create evaluation conditions that reflect the recruiter's intentions.

[0108] The result display control unit 115 may, for example, display the relevant portion of the registered information corresponding to the evaluation on the applicant terminal 20 near the evaluation (for example, in the form of a tooltip, callout, etc.).

[0109] The result display control unit 115 may display sentences or words extracted, summarized, abstracted, or paraphrased from the sentences or words included in the registered information as reasons for evaluation in a more emphasized form than other parts. "A more emphasized form than other parts" includes, for example, coloring (highlighting) the characters or background of the characters, displaying in a bold font, displaying in a large font, adding decorations (underline, shading, frame, icon, etc.), flashing display, animation display, etc. Furthermore, the items to be emphasized do not necessarily have to be displayed in an emphasized form at all times; for example, they may be displayed in an emphasized form in response to a predetermined operation by the user (mouse over, click, tap, etc.) (the display form changes dynamically).

[0110] The results display control unit 115 may display the job seeker's registration information on the employer terminal 20 in a form that emphasizes the parts that form the basis of the evaluation more than other parts. This allows the employer to confirm the parts of the job seeker's registration information that form the basis of the evaluation or are the subject of the evaluation. Alternatively, the results display control unit 115 may extract and display only the parts that form the basis of the evaluation on the employer terminal 20, or it may automatically scroll the results display screen displayed on the employer terminal 20 so that the parts that form the basis of the evaluation are included in the information display area of ​​the employer terminal 20 (i.e., included in a position that is visible to the employer).

[0111] The registration information of job seekers who have been evaluated is displayed on the employer terminal 20, for example, by selecting any job seeker included in the results list. At this time, the individual evaluation and the reasons for it may be displayed along with the registration information.

[0112] The results display control unit 115 may receive a predetermined operation (selection operation or instruction operation such as click, tap, mouseover, etc.) for the evaluation conditions or individual evaluations (or the reasons for them) from the recruiter terminal 20, and display the individual evaluation of the evaluation condition that was the target of the operation or the part of the registered information corresponding to the target individual evaluation (the part that forms the basis of the individual evaluation) on the recruiter terminal 20. In this case, the results display control unit 115 may display only the part of the registered information that forms the basis of the targeted individual evaluation in an emphasized form, or it may display all the parts that form the basis of the individual evaluations (both the parts that form the basis of the selected individual evaluation and the parts that form the basis of the unselected individual evaluation) in an emphasized form. In the latter case, the parts that form the basis of the targeted individual evaluation and the parts that form the basis of the untargeted individual evaluation may be displayed in different forms from each other (i.e., in a form that allows them to be distinguished and recognized).

[0113] Furthermore, the results display control unit 115 may receive a predetermined operation from the recruiter terminal 20 on the area where the evaluation conditions, evaluation, or reasons for evaluation are displayed, and in response to the operation, control the display of the results display screen displayed on the recruiter terminal 20 so that the portion of the job seeker's registered information (such as a resume) that formed the basis of the evaluation is included in the information display area of ​​the recruiter terminal 20 (i.e., included in a position visible to the recruiter). This display control includes, for example, scrolling the results display screen to the position containing the portion that formed the basis, moving the focus on the results display screen to the portion that formed the basis, displaying the page containing the portion that formed the basis (transition of the results display screen), displaying the portion that formed the basis as a pop-up, and displaying the portion that formed the basis as a collapsed state. This eliminates the need to search for specific descriptions that form the basis of the evaluation in the registered information, allowing recruiters to efficiently confirm the basis of the evaluation. As a result, recruiters can efficiently confirm the validity of the evaluation, leading to faster and more accurate pass / fail decisions.

[0114] Furthermore, the results display control unit 115 may receive a predetermined operation from the recruiter terminal 20 on any part (word, sentence, etc.) in the display area of ​​the registered information, and may highlight the evaluation (individual evaluation) created based on the operated part, the evaluation conditions that the part satisfies, etc., through highlighting, pop-up display, etc. This allows the registered information to bidirectionally confirm which parts of the job seeker's history are linked to which evaluations.

[0115] When the evaluation creation unit 114 recreates the evaluation of a specific job seeker's registration information using the updated evaluation conditions, the result display control unit 115 may simultaneously display the recreated evaluation and an input area that accepts re-editing of the updated evaluation conditions on the employer terminal 20. This allows the employer to create evaluation conditions suitable for screening job seekers by repeating the cycle of editing the evaluation conditions and confirming the evaluation based on the edited evaluation conditions. The result display control unit 115 may also change the evaluation results displayed on the employer terminal 20 (update the displayed content to the recreated evaluation) in response to operations such as text input into the input area or setting changes, without waiting for instructions from the employer to determine the evaluation conditions.

[0116] The results display control unit 115 may simultaneously display an input area and a policy input area for inputting a policy for modifying evaluation conditions on the recruiter terminal 20. The "policy for modification" is a sentence or word that will be referenced when creating a proposed modification of the evaluation conditions in the modification proposal unit 118, which will be described later. The policy input area may include a text box into which the recruiter can input instructions in natural language (text), or it may include an object (selection button, etc.) into which the recruiter can select an instruction from a set of pre-prepared options (for example, "make the conditions stricter," "make the conditions looser," "emphasize specific skills," etc.). The modification policy may include instructions based on the evaluation results, such as "increase (or decrease) the evaluation of a specific job seeker," or "increase the number of specific job seekers whose evaluation is above (or below) a certain level."

[0117] The result display control unit 115 may also display the proposed revisions created by the revision suggestion unit 118 on the job seeker terminal 20, in addition to the input area. This allows the job seeker to edit the evaluation conditions while reviewing the proposed revisions.

[0118] The result display control unit 115 may display a decision reception object on the recruiter terminal 20 in addition to the input area, which accepts input for determining evaluation conditions. In response to the input to the decision reception object, the unit may determine the evaluation conditions for screening and register the condition information linked to the target job. This allows the recruiter to finalize the edited evaluation conditions and execute the candidate screening process for the target job without having to switch to an evaluation condition editing screen.

[0119] "Determination of evaluation criteria" means deciding that the evaluation criteria used in the preliminary evaluation process will be used as the evaluation criteria in the screening process, and may be reinterpreted as "completion of preliminary evaluation process," "commencement of screening process," "association of condition information with target job postings," etc. The decision acceptance object is placed, for example, near the input area.

[0120] The result display control unit 115 receives, for example, the selection of target job postings to which condition information including the determined evaluation conditions is linked from the recruiter terminal 20, and links the condition information to the selected target job postings. Furthermore, by linking the condition information to the target job postings, the condition information is also linked to the job seeker group associated with those target job postings. Therefore, in the screening process by the evaluation creation unit 114, evaluations are created for the job seekers included in the job seeker group.

[0121] Figure 6 shows an example of the preliminary evaluation results display screen PD displayed on the job seeker terminal 20. The preliminary evaluation results display screen PD includes a switching tab CT and an evaluation display area EA.

[0122] The CT switch tab allows switching between the result lists of specific job seekers displayed in the evaluation display area EA. In the preliminary evaluation result display screen PD in Figure 6, the CT switch tab includes tabs for the result lists of specific job seekers whose overall evaluation is "A" or "B" ("AB Evaluation" tab) and tabs for the result lists of specific job seekers whose overall evaluation is "C" ("C Evaluation" tab). Each tab also displays the number of specific job seekers (the number of specific job seekers included in the result list). Note that Figure 6 shows the AB Evaluation tab selected.

[0123] The evaluation display area EA is displayed for each specific job seeker included in the results list. The evaluation display area EA displays the action label AL, basic information BI, resume display acceptance object RO, and evaluation content EC.

[0124] Action Label AL is a label that represents the history of actions taken by employers towards job seekers. In the example in Figure 6, the history of sending recruitment documents and the history of assigning evaluations are displayed as Action Label AL.

[0125] Basic Information BI includes basic information about a specific job seeker (such as facial image, registration ID, age, gender, address, current annual income, and current position).

[0126] The Resume Display Reception Object RO receives instructions to display the registration information (resume) of a specific job seeker. When an input operation is performed on the Resume Display Reception Object RO, the registration information of the specific job seeker is displayed on the employer terminal 20, for example, with the basis for the evaluation highlighted.

[0127] The evaluation details section displays the overall evaluation, the number of evaluation conditions (mandatory and preferential conditions) that have been met, the content of each evaluation condition, and the reasons for the individual evaluation. In the example in Figure 6, the result shows that one mandatory condition has been met and both preferential conditions have been met. In addition, the reasons for the evaluation highlight content extracted from the registration information (shaded in the example in Figure 6).

[0128] Figure 7 shows an example of the condition editing screen MD displayed on the recruiter terminal 20. The condition editing screen MD is displayed side by side with, for example, the preliminary evaluation result display screen PD in Figure 6. The condition editing screen MD includes a first input area IA1, a first editing hint MH1, a second input area IA2, a second editing hint MH2, a re-evaluation button B21, and a condition confirmation button B22.

[0129] The first input area IA1 accepts edits to the current required conditions. The first editing hint MH1 displays the content to be entered as required conditions, examples of evaluation conditions, etc. The second input area IA2 accepts edits to the current welcome conditions. The second editing hint MH2 displays the content to be entered as welcome conditions, examples of evaluation conditions, etc.

[0130] When an input operation is performed on the re-evaluation button B21 (the button labeled "Retry evaluation"), the evaluation conditions are updated by the update unit 116 (described later), and then the evaluation creation unit 114 performs a re-evaluation. As a result, the evaluation results displayed on the preliminary evaluation result display screen PD are also updated.

[0131] The condition determination button B22 (a button displaying "Determine evaluation conditions") is an example of a decision acceptance object that accepts input for determining evaluation conditions. When an input operation is performed on the condition determination button B22, the evaluation conditions are determined, and the screening process by the evaluation creation unit 114 using those evaluation conditions becomes possible.

[0132] <Screening result display processing> In the screening results display process, the results display control unit 115 displays the evaluations of job seekers included in the job seeker group on the employer terminal 20. In the screening results display process, the results display control unit 115 may also display individual evaluations for each evaluation condition, similar to the preliminary results display process. In addition, the results display control unit 115 may also display an overall evaluation in addition to individual evaluations.

[0133] The results display control unit 115 displays the evaluations of multiple job seekers who were the subject of the evaluation as a results list on the employer terminal 20. The results display control unit 115 may also display the job seekers in the results list in an order corresponding to their evaluations. "Order corresponding to evaluations" could be, for example, in descending order of overall evaluation, or in descending order of the number of evaluation conditions met (all evaluation conditions, or evaluation conditions of a specific priority).

[0134] In the screening result display process, the result display control unit 115 may display the evaluation along with the reasons for the individual evaluation corresponding to the evaluation conditions on the recruiter terminal 20, similar to the preliminary result display process. In addition, the result display control unit 115 may display the job seeker's registration information on the recruiter terminal 20 in a format in which the parts that form the basis of the individual evaluation are emphasized more than other parts, similar to the preliminary result display process.

[0135] Figure 8 shows an example of the screening results display screen SD displayed on the employer terminal 20. The screening results display screen SD displays a list of result information RI for each job seeker who has been evaluated. The result information RI includes the job seeker's basic information (age, gender, address, current annual income, current organization, current position, educational background, previous occupations, previous industries, etc.), the overall evaluation AE, and the evaluation reception object EO. ​​This allows employers to grasp the evaluation status of multiple job seekers at a glance without having to navigate to the detailed screen of each individual job seeker. Furthermore, since the basic information and the overall evaluation AE are displayed in parallel in the list, employers can efficiently select job seekers who should be prioritized for further details by comprehensively considering the evaluation results and the job seeker's attributes (annual income, occupation, etc.).

[0136] The overall evaluation (AE) displays an overall evaluation of the job seeker's registration information. In the example in Figure 8, a symbol indicating the rank of the overall evaluation (e.g., a circle) and the number of evaluation conditions that have been met (e.g., "5 / 5") are displayed.

[0137] The evaluation receiving object EO receives evaluations from employers of job seekers (in the example in Figure 8, evaluations are given on a three-level scale: A, B, and C). When an input operation is performed for any of the evaluations in the evaluation receiving object EO, the corresponding evaluation is received as an additional evaluation by the evaluation receiving unit 117, which will be described later.

[0138] Figure 9 shows an example of the detailed results display screen RD displayed on the recruiter terminal 20. The detailed results display screen RD is displayed, for example, when any job seeker (result information RI) is selected in the screening results display screen SD in Figure 8. The detailed results display screen RD includes basic information BI, evaluation display area EA, first switch button B31, second switch button B32, target list add button B33, and scout send button B34.

[0139] The basic information BI includes some of the job seeker's registration information. The evaluation display area EA displays the overall evaluation AE, the evaluation content EC, and the evaluation acceptance object EO. ​​The overall evaluation AE and the evaluation acceptance object EO are the same as those in the screening results display screen SD in Figure 8. The evaluation content EC is the same as those in the preliminary evaluation results display screen PD in Figure 6.

[0140] When an input operation is performed on the first toggle button B31, the job seeker information displayed on the detailed results screen RD switches to the information of the previous job seeker in the results list. When an input operation is performed on the second toggle button B32, the job seeker information displayed on the detailed results screen RD switches to the information of the next job seeker in the results list.

[0141] When an input operation is performed on the "Add to Target List" button B33, the displayed job seeker is added to the target list. If the displayed job seeker has already been added to the target list, the "Add to Target List" button B33 will be hidden or inactive (not accepting input). When an input operation is performed on the "Send Scout" button B34, the screen for creating and sending a scout message to the displayed job seeker will be displayed.

[0142] Furthermore, the preliminary evaluation result display screen PD in Figure 6 may be used as the screening process result display screen, and the screening result display screen SD in Figure 8 and the detailed result display screen RD in Figure 9 may be used as the preliminary evaluation process result display screens.

[0143] <Updated section 116> The update unit 116 is configured to update the evaluation conditions according to the input content displayed in the input area on the applicant terminal 20 by the result display control unit 115 during the preliminary evaluation process. The updated evaluation conditions are used for re-evaluation by the evaluation creation unit 114.

[0144] The update unit 116 may change the priority of the evaluation conditions according to the content entered in the input area. This allows the recruiter to adjust the priority of the evaluation conditions while referring to the evaluation results based on the current evaluation conditions. The "content entered" here includes the priority settings described above (for example, input operations on the priority setting object).

[0145] <Evaluation Reception Department 117> The evaluation reception unit 117 is configured to accept input of additional evaluations from employers for job seekers for whom evaluations (individual evaluations or overall evaluations) have been created by the evaluation creation unit 114. Note that the additional evaluation may use different notation (evaluation axes) than the evaluation created by the evaluation creation unit 114, or it may use notation consistent with the evaluation. Furthermore, the additional evaluation is typically an overall evaluation (a single evaluation) of the registered information, but it may also include, for example, multiple evaluations for each item of the registered information.

[0146] Additional evaluations are performed, for example, by inputting data into the evaluation reception object EO on the screening results display screen SD in Figure 8, or the evaluation reception object EO on the detailed results display screen RD in Figure 9. The additional evaluations are registered as management information for job seekers from employers, along with the evaluations created by the evaluation creation unit 114.

[0147] <Revision proposal section 118> The revision proposal unit 118 is configured to present proposed revisions to the evaluation conditions to the job seeker during the preliminary evaluation processing stage by the evaluation creation unit 114.

[0148] The revision proposal unit 118 may create a revised evaluation condition based on the combination of the condition information used by the evaluation creation unit 114 to create the evaluation, the evaluation created by the evaluation creation unit 114 using said condition information, and the additional evaluation received by the evaluation reception unit 117, as well as the reference information for the first proposal. This reduces the effort required for recruiters to optimize the evaluation condition.

[0149] A "revised proposal" is information that indicates, for example, revisions to individual evaluation criteria. Here, "revisions" include not only changes to the content, but also deletions and additions. Furthermore, a revised proposal may include specific revisions (e.g., revised sentences, words, etc.) or sentences indicating countermeasures (e.g., "add XX"). The purpose of a revised proposal here is, for example, to reduce the difference between the additional evaluation and the evaluation (i.e., the evaluation based on the evaluation criteria becomes closer to the additional evaluation conducted by the employer). A revised proposal may also include proposed changes to the priority of the evaluation criteria.

[0150] The first proposal reference information is information regarding the correlation between combinations of condition information, evaluations, and additional evaluations and proposed modifications. The first proposal reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of condition information, evaluations, and additional evaluations and proposed modifications. The correlations included in the first proposal reference information can be constructed, for example, by statistically analyzing data that records combinations of condition information, evaluations, and additional evaluations and corresponding proposed modifications.

[0151] The first proposal reference information may include a set of parameters for generating a revised version from a combination of conditional information, evaluation, and additional evaluation. For example, the first proposal reference information may be various pre-trained models. For example, the first proposal reference information may include a first revised version generation model, which is a dedicated or general-purpose learning model that has been machine-trained to take a combination of conditional information, evaluation, and additional evaluation as input and output a revised version. In this case, the revised proposal unit 118 inputs the combination of conditional information, evaluation, and additional evaluation into the first revised version generation model and causes the first revised version generation model to output a revised version.

[0152] The first revision proposal generation model is included in the artificial intelligence unit 120. The first revision proposal generation model, which is a dedicated learning model, may be constructed by training using, for example, data of combinations of condition information, evaluation, and additional evaluation, and corresponding revision proposal data, as training data. In such a first revision proposal generation model, parameters calculated and tuned through learning construct a correlation between the combination of condition information, evaluation, and additional evaluation and the revision proposal.

[0153] If the first revision proposal generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the revision proposal unit 118 inputs a prompt to the first revision proposal generation model that includes a combination of condition information, evaluation, and additional evaluation, and an instruction to output a revision proposal corresponding to the combination of condition information, evaluation, and additional evaluation, taking the combination of condition information, evaluation, and additional evaluation as input, causing the first revision proposal generation model to output a revision proposal. The revision proposal unit 118 may also generate a prompt that gives the first revision proposal generation model an instruction to create a revision proposal, and input this prompt to the first revision proposal generation model. In addition, the revision proposal unit 118 may input a prompt to the first revision proposal generation model that includes, in addition to the combination of condition information, evaluation, and additional evaluation and the instruction to create and output a revision proposal, an example, sample, or training data of input and output pairs, such as one or more sample combinations of condition information, evaluation, and additional evaluation and one or more sample revision proposals corresponding to them. Here, parameters for constructing the first revision proposal model and prompts containing instructions to output revision proposals corresponding to combinations of condition information, evaluation, and additional evaluation establish a correlation between the combinations of condition information, evaluation, and additional evaluation and the revision proposals.

[0154] The revision proposal unit 118 may create a revised proposal based on at least one of the condition information, evaluation, and additional evaluation, and the reference information for the first proposal. For example, the revision proposal unit 118 may input at least one of the condition information, evaluation, and additional evaluation into the first revised proposal creation model and output the revised proposal to the first revised proposal creation model.

[0155] The revision proposal unit 118 may create a revised proposal using a combination of the evaluation and additional evaluation of one job seeker, or it may create a revised proposal using a combination of the evaluation and additional evaluation of multiple job seekers.

[0156] Furthermore, the revision proposal unit 118 may create revised evaluation conditions based on the combination of the condition information used to create the evaluation by the evaluation creation unit 114, the revised policy entered by the job seeker in the policy input area displayed by the result display control unit 115, and the reference information for the second proposal. This allows the job seeker to input revised policies while confirming the evaluation results, thereby enabling the revision proposal unit 118 to present more specific revised proposals.

[0157] The second proposal reference information is information regarding the correlation between combinations of condition information and modification policies and proposed modifications. The second proposal reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between combinations of condition information and modification policies and proposed modifications. The correlations included in the second proposal reference information can be constructed, for example, by statistically analyzing data that records combinations of condition information and modification policies and corresponding proposed modifications.

[0158] The reference information for the second proposal may include a set of parameters for generating a revised version from a combination of condition information and a revision policy. For example, the reference information for the second proposal may be various pre-trained models. For example, the reference information for the second proposal may include a second revised version generation model, which is a dedicated training model or a general-purpose training model that has been machine-trained to take a combination of condition information and a revision policy as input and output a revised version. In this case, the revision proposal unit 118 inputs the combination of condition information and a revision policy into the second revised version generation model and causes the second revised version generation model to output a revised version.

[0159] The second revision proposal generation model is included in the artificial intelligence unit 120. The second revision proposal generation model, which is a dedicated learning model, may be constructed, for example, by training using data of combinations of condition information and revision policies and corresponding revision proposal data as training data. In such a second revision proposal generation model, parameters calculated and tuned through learning construct a correlation between the combination of condition information and revision policies and the revision proposal.

[0160] If the second revision proposal generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the revision proposal unit 118 inputs a prompt to the second revision proposal generation model that includes a combination of condition information and a revision policy, and an instruction to output a revision proposal corresponding to the combination of condition information and a revision policy, taking the combination of condition information and a revision policy as input, causing the second revision proposal generation model to output a revision proposal. The revision proposal unit 118 may also generate a prompt that gives an instruction to the second revision proposal generation model to create a revision proposal, and input this prompt to the second revision proposal generation model. In addition, the revision proposal unit 118 may input a prompt to the second revision proposal generation model that includes, in addition to the combination of condition information and a revision policy and the instruction to create and output a revision proposal, an example, sample, or training data of input and output pairs, such as one or more sample combinations of condition information and a revision policy and one or more sample revision proposals corresponding to them. Here, parameters for constructing the second revision proposal model, and prompts containing instructions to output revision proposals corresponding to combinations of condition information and revision policies, establish a correlation between the combinations of condition information and revision policies and the revision proposals.

[0161] The revision proposal unit 118 may create a revised proposal based on at least one of the condition information and revision policy, and the reference information for the second proposal. For example, the revision proposal unit 118 may input at least one of the condition information and revision policy into the second revised proposal creation model and output the revised proposal to the second revised proposal creation model. For example, the revision proposal unit 118 may receive an instruction from the recruiter to create a revised policy even when no revision policy has been entered in the policy input area, and create evaluation conditions different from the current evaluation conditions (condition information).

[0162] <Candidate extraction section 119> The candidate selection unit 119 is configured to select job seekers (candidates) to register in a job seeker group. The candidate selection unit 119 selects candidates based on the evaluations (individual evaluations or overall evaluations) created by the evaluation creation unit 114.

[0163] The candidate extraction unit 119 creates extraction conditions for extracting candidates suitable for the target job based on the registration information of specific job seekers who have received an evaluation of a predetermined level or higher from among multiple specific job seekers for whom evaluations have been created based on condition information by the evaluation creation unit 114, and the reference information for creating conditions. Furthermore, it may extract job seekers who meet the extraction conditions from among the job seekers registered in the database as candidates. This makes it possible to extract job seekers who should be registered in the job seeker group by referring to the registration information of specific job seekers with high evaluations.

[0164] "Extraction criteria" define the requirements that must be met in a job seeker's registration information. For example, extraction criteria are set so that candidates with similar attributes to a specific job seeker whose registration information is used to create the extraction criteria are extracted. Furthermore, if the registration information of multiple specific job seekers is used to create the extraction criteria, the extraction criteria will extract candidates who share common characteristics with these specific job seekers.

[0165] The reference information for creating conditions is information regarding the correlation between the registration information of job seekers whose evaluation is above a certain level and the extraction conditions. The reference information for creating conditions is stored, for example, in the storage unit 12. The reference information for creating conditions may include, for example, tables, functions, simple algorithms, etc., that show the correlation between the registration information and the extraction conditions. The correlations included in the reference information for creating conditions can be constructed, for example, by statistically analyzing data that records the registration information and the corresponding extraction conditions.

[0166] The reference information for creating conditions may include a set of parameters for generating extraction conditions from registered information. For example, the reference information for creating conditions may be various pre-trained models. For example, the reference information for creating conditions may include an extraction condition creation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take registered information as input and output extraction conditions. In this case, the candidate extraction unit 119 inputs the registered information into the extraction condition creation model and causes the extraction condition creation model to output extraction conditions.

[0167] The extraction condition creation model is included in the artificial intelligence unit 120. The extraction condition creation model, which is a dedicated learning model, may be constructed, for example, by training using registered information data and corresponding extraction condition data as training data. In such an extraction condition creation model, parameters calculated and tuned through learning establish a correlation between registered information and extraction conditions.

[0168] If the extraction condition creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the candidate extraction unit 119 inputs a prompt to the extraction condition creation model that includes registration information and an instruction to output an extraction condition corresponding to the registration information, causing the extraction condition creation model to output the extraction condition. The candidate extraction unit 119 may also generate a prompt that gives an instruction to the extraction condition creation model to create an extraction condition, and input this prompt to the extraction condition creation model. In addition to the registration information and the instruction to create and output the extraction condition, the candidate extraction unit 119 may also input a prompt to the extraction condition creation model that includes, for example, one or more samples of registration information and one or more samples of corresponding extraction conditions as examples, samples, or training data of input and output pairs. Here, the parameters that construct the extraction condition creation model and the prompt that includes an instruction to output an extraction condition corresponding to the registration information construct the correlation between the registration information and the extraction condition.

[0169] The candidate extraction unit 119 may add candidates to the job seeker group associated with the target job (which is screened by the evaluation creation unit 114), or propose such additions. This reduces the effort required for employers to create job seeker groups.

[0170] For example, the candidate extraction unit 119 may display one or more extracted candidates on the employer terminal 20 and accept the employer's choice as to whether or not to add them to the job seeker group. The candidate extraction unit 119 registers the candidates whose addition is approved by the employer to the job seeker group.

[0171] The candidate extraction unit 119 may perform a search process and an extraction process. In the search process, the candidate extraction unit 119 creates search conditions to find the first candidate, who is a job seeker to be evaluated, based on the job information of the target job and the reference information for creating the first search conditions, and then uses these search conditions to search for the first candidate from among the job seekers registered in the database.

[0172] The "search criteria" include at least one of the following as conditions: the job seeker's occupation, annual salary, and activity history. The search criteria are set so, for example, that job seekers who meet the essential requirements of the target job posting are found. The "job seeker's activity history" includes, for example, the attributes or number of jobs viewed, the attributes or number of jobs applied for, the attributes or number of jobs registered in the bookmark list, and the attributes or number of jobs to which the job seeker responded to recruitment documents. Here, the "bookmark list" (also called the "favorites list," "interesting list," etc.) is a list prepared for each job seeker where the job seeker can register any job posting they wish. Furthermore, the activity history may include not only actions related to job postings, but also negative actions such as hiding job postings or withdrawing from the selection process. In addition, the activity history may include login history to services provided by Information Processing System 1 (last login date and time, login frequency, etc.).

[0173] The first search condition creation reference information is information regarding the correlation between job postings and search conditions. This reference information is stored, for example, in the memory unit 12. The first search condition creation reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between job postings and search conditions. The correlations included in the first search condition creation reference information can be constructed, for example, by statistically analyzing data that records job postings and corresponding search conditions.

[0174] The reference information for creating the first search conditions may include a set of parameters for generating search conditions from job postings. For example, the reference information for creating the first search conditions may be various pre-trained models. For example, the reference information for creating the first search conditions may include a first search condition creation model which is a dedicated or general-purpose learning model that has been machine-trained to take job postings as input and output search conditions. In this case, the candidate extraction unit 119 inputs the job postings into the first search condition creation model and causes the first search condition creation model to output search conditions.

[0175] The first search condition creation model is included in the artificial intelligence unit 120. The first search condition creation model, which is a dedicated learning model, may be constructed, for example, by training using job information data and corresponding search condition data as training data. In such a first search condition creation model, parameters calculated and tuned through learning construct the correlation between job information and search conditions.

[0176] If the first search condition creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the candidate extraction unit 119 inputs a prompt to the first search condition creation model that includes job information and an instruction to output search conditions corresponding to the job information, causing the first search condition creation model to output the search conditions. The candidate extraction unit 119 may also generate a prompt that gives an instruction to the first search condition creation model to create search conditions and input this prompt to the first search condition creation model. In addition to job information and instructions to create and output search conditions, the candidate extraction unit 119 may also input a prompt to the first search condition creation model that includes, for example, one or more samples of job information and one or more samples of corresponding search conditions as examples, samples, or training data of input and output pairs. Here, the parameters that construct the first search condition creation model and the prompt that includes an instruction to output search conditions corresponding to the job information construct the correlation between job information and search conditions.

[0177] The candidate extraction unit 119 creates search conditions for searching for the first candidate based on the registration information of specific job seekers who have received an evaluation of a predetermined level or higher from among multiple specific job seekers for whom evaluations have been created based on condition information by the evaluation creation unit 114, and reference information for creating the second search condition. Furthermore, it may use these search conditions to search for the first candidate from among the job seekers registered in the database. This makes it possible, for example, to create search conditions that refer to the registration information of specific job seekers with high evaluations.

[0178] The second search condition creation reference information is information regarding the correlation between the registration information of job seekers whose evaluation is above a certain level and the search conditions. The second search condition creation reference information is stored, for example, in the storage unit 12. The second search condition creation reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between the registration information and the search conditions. The correlations included in the second search condition creation reference information can be constructed, for example, by statistically analyzing data that records the registration information and the corresponding search conditions.

[0179] The reference information for creating the second search condition may include a set of parameters for generating search conditions from the registered information. For example, the reference information for creating the second search condition may be various pre-trained models. For example, the reference information for creating the second search condition may include a second search condition creation model which is a dedicated or general-purpose learning model that has been machine-trained to take the registered information as input and output search conditions. In this case, the candidate extraction unit 119 inputs the registered information into the second search condition creation model and causes the second search condition creation model to output search conditions.

[0180] The second search condition creation model is included in the artificial intelligence unit 120. The second search condition creation model, which is a dedicated learning model, may be constructed, for example, by training using registered information data and corresponding search condition data as training data. In such a second search condition creation model, parameters calculated and tuned through learning construct the correlation between registered information and search conditions.

[0181] If the second search condition creation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the candidate extraction unit 119 inputs a prompt to the second search condition creation model that includes registration information and an instruction to output a search condition corresponding to the registration information, causing the second search condition creation model to output the search condition. The candidate extraction unit 119 may also generate a prompt that gives an instruction to the second search condition creation model to create a search condition, and input this prompt to the second search condition creation model. In addition to the registration information and the instruction to create and output the search condition, the candidate extraction unit 119 may also input a prompt to the second search condition creation model that includes, for example, one or more samples of registration information and one or more samples of corresponding search conditions as examples, samples, or training data of input and output pairs. Here, the parameters that construct the second search condition creation model and the prompt that includes an instruction to output a search condition corresponding to the registration information construct the correlation between the registration information and the search condition.

[0182] Furthermore, the candidate extraction unit 119 may create search conditions based on a combination of the registration information of a specific job seeker for whom a predetermined evaluation or higher has been created, at least one of the reference search conditions and the job information, and reference information for creating the second search conditions. In this case, the reference information for creating the second search conditions is information regarding the correlation between the combination and the search conditions. The candidate extraction unit 119 may, for example, input the combination of the registration information and at least one of the reference search conditions and the job information into the second search condition creation model, thereby causing the second search condition creation model to output the search conditions.

[0183] In the extraction process, the candidate extraction unit 119 creates an evaluation of the first candidate's registration information based on a combination of condition information and the first candidate's registration information, as well as evaluation reference information. Based on this evaluation, it extracts a second candidate from the first candidate who is suitable for the target job. As a result, candidates are extracted through a two-stage process, which improves the quality of the extracted candidates.

[0184] The procedure for creating an evaluation of registered information (individual evaluation or overall evaluation) by the candidate selection unit 119 is the same as the procedure for creating an evaluation of registered information by the evaluation creation unit 114.

[0185] For example, the candidate selection unit 119 selects as second candidates from among the first candidates those whose registered information evaluation is above a predetermined value, or whose evaluation ranking is within a predetermined range, etc.

[0186] The candidate extraction unit 119 may further perform additional processing, such as adding a second candidate to the job seeker group or proposing such addition. This reduces the effort required for employers to create job seeker groups.

[0187] For example, the candidate extraction unit 119 may display one or more extracted second candidates on the employer terminal 20 and accept the employer's choice as to whether or not to add them to the job seeker group. The candidate extraction unit 119 registers the second candidates whose addition has been approved by the employer to the job seeker group.

[0188] The candidate extraction unit 119 may repeatedly perform search, extraction, and addition processes at predetermined periodic intervals. This allows for the periodic addition or suggestion of candidates to a group of job seekers in accordance with updates to the job seeker registration information or the job seeker database.

[0189] "A predetermined regular timing" refers to a point in time after a certain period has elapsed since the last search, extraction, and addition process was performed (for example, monthly, weekly, or daily).

[0190] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by each functional unit of the server device 10 may be common to all units, or it may be prepared individually for each functional unit.

[0191] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with trained models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNN). The artificial intelligence unit 120 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include specific models such as OpenAI's GPT (registered trademark), Google's Gemini (registered trademark), and models provided through services and platforms such as Microsoft's Azure (registered trademark) AI Studio. Generative AI may be, for example, text generation AI, image generation AI, multimodal generation AI, etc. The trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 120 can include any pre-trained model.

[0192] Specific machine learning algorithms used to build trained models include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply these algorithms as appropriate.

[0193] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. Furthermore, the trained model may not only be one trained for a specific task, but also a general-purpose learning model that can be used universally for a wide range of tasks.

[0194] The artificial intelligence unit 120 may include a natural language model as artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by One-shot Learning or Few-shot Learning. Furthermore, the general-purpose learning model may also be configured to handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate pre-trained model, or it may be a common general-purpose pre-trained model. In addition, the artificial intelligence unit 120 may include a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model as a pre-trained model. Small-scale and medium-scale language models are natural language processing models that are trained on less data (and constructed with fewer parameters) compared to large-scale language models.

[0195] The pre-trained models included in the artificial intelligence unit 120 (such as the first condition creation model and other pre-trained models used in each functional unit) can undergo additional training using methods such as transfer learning and fine-tuning. For example, whenever new data is registered, the artificial intelligence unit 120 may perform additional training and fine-tuning using this new data as training data. This improves the accuracy of the information output from the pre-trained models.

[0196] The trained model included in the artificial intelligence unit 120 may be a trained model (distilled model) obtained by knowledge distillation using the original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as the teacher model, and the student model is trained by adjusting the parameters of the student model so that the loss of the student model's output (soft target loss) relative to the teacher model's output (soft target) is small, and that student model becomes the distilled model. Alternatively, the student model may be trained so that the loss of the student model's output (hard target loss) relative to the correct labels (hard target) of the teacher data (combinations of input data and output data of the trained model) is small. Compared to the original trained model (teacher model), the distilled model has performance close to that of the trained model, but with fewer parameters and a lower processing load. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0197] For example, the trained model used in each functional unit may be a distilled model trained using combinations of input and output data from a large-scale language model as training data. Alternatively, when the information processing system 1 is introduced, a large-scale language model may be used as the trained model in each functional unit, and once training data from the large-scale language model has been accumulated, the distilled model obtained by knowledge distillation using that training data may be used as the trained model in each functional unit.

[0198] An AI agent (also called an autonomous agent) is a model that, upon input of a goal (objective, purpose, etc.) such as "Teach me about XX" or a task such as "Output XX," breaks down the processes necessary to reach the goal or accomplish the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, outputs information according to the goal, and does not require user intervention (operation input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously learn in order to aim for goal achievement. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.).

[0199] <Display> The display unit 211 of the job seeker terminal 20 shown in Figure 4B, and the display unit 311 of the job seeker terminal 30 shown in Figure 4C, respectively, display the screen (information) indicated by the data transmitted from the server device 10.

[0200] <Operation acquisition part> The operation acquisition unit 212 of the employer terminal 20 receives operations from the employer using the employer terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 receives operations from the job seeker using the job seeker terminal 30.

[0201] 3. Information Processing Methods This section describes the information processing method of the server device 10. In this information processing method, each part of the server device 10 is executed by a computer as a step.

[0202] The above-described information processing method comprises an acquisition step, an evaluation creation step, a result display control step, and an update step. In the acquisition step, condition information including at least one evaluation condition and the job seeker's registration information are acquired. In the evaluation creation step, an evaluation of the registration information is created based on a combination of the condition information and registration information, and evaluation reference information. In the result display control step, the evaluation and an input area that accepts editing of the evaluation conditions are displayed simultaneously. In the update step, the evaluation conditions are updated according to the content entered in the input area.

[0203] Figure 10 is an activity diagram showing an example of the flow of information processing (evaluation display processing) performed by the information processing system 1. The information processing will be explained below in accordance with each activity in this activity diagram.

[0204] The evaluation display process begins with an instruction from the employer to create an evaluation based on the job seeker's registration information. The employer inputs the instruction to create an evaluation on the employer terminal 20 (Activity A101). The server device 10 receives the instruction from the employer terminal 20 and obtains condition information, including the evaluation criteria, and the registration information of the job seeker to be evaluated (Activity A102).

[0205] After obtaining the condition information and registration information, the server device 10 creates an evaluation of the job seeker's registration information (Activity A103). Next, the server device 10 outputs the created evaluation and an input area that accepts edits to the evaluation conditions to the employer terminal 20 (Activity A104). As a result, the job seeker's evaluation and the input area are displayed on the employer terminal 20 (Activity A105).

[0206] The recruiter edits the evaluation criteria by entering information into the input field on the recruiter terminal 20 (Activity A106). The server device 10 updates the evaluation criteria with the information entered into the input field (Activity A107). The updated evaluation criteria are used when re-evaluating the registered information.

[0207] 4. Effect The operation of this embodiment can be summarized as follows: Employers can obtain evaluations of job seekers. In particular, since employers can edit evaluation criteria while reviewing job seekers' evaluations, they can efficiently and accurately design evaluation criteria for screening candidates.

[0208] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0209] 5. Others In the above embodiment, the server device 10 performed various storage and control functions, but instead of the server device 10, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the external artificial intelligence unit 120 may be provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using an LLM. The artificial intelligence service server receives prompt input in the form of text, images, audio, etc., and generates and responds with answers to the prompts.

[0210] At least one of the devices included in the information processing system 1 may be located outside the country in which the functions of the information processing system 1 are performed.

[0211] The control unit 11 does not necessarily have to include a group registration unit 111, a condition creation unit 112, an evaluation reception unit 117, a revision proposal unit 118, and a candidate extraction unit 119. For example, the information processing system 1 does not necessarily have to include at least one of the following: a job seeker group registration function, a condition information creation function, an additional evaluation reception function, a revision proposal creation function, and a candidate extraction function.

[0212] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. In the information processing method, the information processing device executes each step of the information processing system 1. In the program, the computer causes the computer to execute each step of the information processing system 1.

[0213] The product may be provided in any of the following embodiments.

[0214] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, the acquisition step of acquiring condition information including at least one evaluation condition and registration information of a job seeker, where the evaluation condition is a condition that an employer requires of a job seeker; the evaluation creation step of creating an evaluation of the registration information based on a combination of the condition information and the registration information and evaluation reference information, where the evaluation reference information is information relating to the correlation between the combination of the condition information and the registration information and the evaluation; the result display control step of simultaneously displaying the evaluation and an input area that accepts editing of the evaluation condition; and the update step of updating the evaluation condition according to the content of the input area.

[0215] (2) An information processing system as described in (1) above, wherein the condition information includes a plurality of evaluation conditions, the evaluation creation step creates an evaluation for each of the plurality of evaluation conditions, and the result display control step simultaneously displays the evaluation for each of the evaluation conditions and the input area that accepts edits for the plurality of evaluation conditions.

[0216] (3) An information processing system as described in (1) or (2) above, wherein the condition information includes the priority of the evaluation conditions, and in the update step, the priority of the evaluation conditions is changed according to the content of the input to the input area.

[0217] (4) An information processing system according to any one of (1) to (3) above, wherein in the result display control step, the information processing system displays the history of the employer's actions toward the job seeker for whom the evaluation was created, together with the evaluation.

[0218] (5) An information processing system according to any one of (1) to (4) above, wherein in the evaluation creation step, the evaluation is recreated based on the updated evaluation conditions, and in the result display control step, the recreated evaluation and the input area that accepts re-editing of the updated evaluation conditions are displayed simultaneously.

[0219] (6) An information processing system according to any one of (1) to (5) above, wherein in the evaluation acceptance step, the system accepts input of an additional evaluation by an employer for a job seeker for whom the evaluation has been created, and in the revision proposal step, it creates a revised version of the evaluation conditions based on the combination of the condition information, the evaluation, and the additional evaluation and the first proposal reference information, where the first proposal reference information is information relating to the correlation between the combination of the condition information, the evaluation, and the additional evaluation and the revised version, and in the result display control step, it displays the revised version in addition to the input area.

[0220] (7) An information processing system according to any one of (1) to (6) above, wherein in the result display control step, in addition to the input area, a policy input area for inputting a policy for modifying the evaluation conditions is displayed simultaneously; in the modification proposal step, a modification proposal for the evaluation conditions is created based on the combination of the condition information and the modification policy and the second proposal reference information, wherein the second proposal reference information is information relating to the correlation between the combination of the condition information and the modification policy and the modification proposal; and in the result display control step, the modification proposal is displayed in addition to the input area.

[0221] (8) An information processing system according to any one of (1) to (7) above, wherein in the result display control step, an object that accepts input for determining the evaluation conditions is displayed in addition to the input area, the condition information is registered in association with the target job in accordance with the input to the object, and in the evaluation creation step, the evaluation of multiple job seekers is created based on a combination of the condition information and the registered information of multiple job seekers included in the group associated with the target job.

[0222] (9) An information processing system according to any one of (1) to (8) above, wherein in the candidate extraction step, extraction conditions are created for extracting candidates suitable for the target job based on the registration information of job seekers for whom an evaluation of a predetermined level or higher has been created from among a plurality of job seekers for whom an evaluation of the condition information has been created, and reference information for creating conditions, and further, job seekers who satisfy the extraction conditions are extracted as candidates from among the job seekers registered in the database, wherein the reference information for creating conditions is information relating to the correlation between the registration information and the extraction conditions.

[0223] (10) An information processing system as described in (9) above, wherein the candidate extraction step includes adding the candidate to the group associated with the target job, or proposing such addition.

[0224] (11) An information processing system according to any one of (1) to (10) above, comprising a server device having the processor and a terminal that can access the server device.

[0225] (12) An information processing method wherein an information processing device performs each step of the information processing system described in any one of (1) to (11) above.

[0226] (13) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (11) above. Of course, this is not always the case.

[0227] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0228] 1: Information Processing System 2: Communication lines 10: Server device 11: Control Unit 110: Basic display control unit 111: Group Registration Department 112: Condition Creation Section 113: Acquisition Department 114: Evaluation Creation Department 115: Result display control unit 116: Update section 117: Evaluation Reception Department 118: Revision proposal department 119: Candidate extraction department 120: Artificial Intelligence Department 12: Storage section 13: Communications Department 14: Communications bus 20: Job seeker terminal 21: Control Unit 211:Display section 212: Operation acquisition section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 30: Job seeker terminal 31: Control Unit 311: Display section 312: Operation acquisition section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communications bus AE: Overall Rating AL: Action Label AO: Object for accepting additional conditions B11: Cancel button B12: Screening Start Button B21: Re-evaluation button B22: Condition Confirmation Button B31: First toggle button B32: Second toggle button B33: Add to Target List Button B34: Send Scout Button BI: Basic Information CA: Condition setting area CD: Condition creation screen CF: Condition input field CT: Switch tab DA: Information display area EA: Evaluation display area EC: Evaluation details EO: Evaluation Acceptance Object IA1: First input area IA2: Second input area IH: Input Hint MD: Condition Editing Screen MG: Message MH1: First Editing Hint MH2: Second Editing Hint PD: Preliminary evaluation results display screen PO: Priority Receiving Object RD: Detailed result display screen RI:Result information RO: Resume display / reception object SD: Screening results display screen SO: Sample creation request object

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, condition information including at least one evaluation criterion and the job seeker's registration information are acquired, where the evaluation criterion is a condition that the employer requires of the job seeker. In the evaluation creation step, an evaluation of the registered information is created based on the combination of the condition information and the registered information and the evaluation reference information, where the evaluation reference information is information relating to the correlation between the combination of the condition information and the registered information and the evaluation. In the result display control step, the evaluation and an input area that accepts editing of the evaluation conditions used to create the evaluation are displayed simultaneously, and an object that accepts input for determining the evaluation conditions is displayed, and the condition information is registered and linked to the target job in accordance with the input to the object. An information processing system that, in the evaluation creation step, creates evaluations of multiple job seekers based on a combination of the condition information and the registration information of multiple job seekers included in the group linked to the target job.

2. In the information processing system described in Claim 1, An information processing system that, in the update step, updates the evaluation conditions according to the content entered into the input area.

3. In the information processing system described in claim 1, The aforementioned condition information includes a plurality of evaluation conditions, In the evaluation creation step, the evaluation is created for each of the multiple evaluation conditions. An information processing system that, in the result display control step, simultaneously displays the evaluation for each evaluation condition and the input area that accepts editing of multiple evaluation conditions.

4. In the information processing system described in claim 2, The aforementioned condition information includes the priority of the evaluation conditions, An information processing system that, in the update step, changes the priority of the evaluation conditions according to the content of the input to the input area.

5. In the information processing system described in claim 1, The information processing system, in the result display control step, displays the history of the employer's actions toward the job seeker for whom the evaluation was created, along with the evaluation.

6. In the information processing system described in claim 2, In the evaluation creation step, the evaluation is recreated based on the updated evaluation conditions. The information processing system, in the result display control step, simultaneously displays the recreated evaluation and the input area that accepts re-editing of the updated evaluation conditions.

7. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, condition information including at least one evaluation criterion and the job seeker's registration information are acquired, where the evaluation criterion is a condition that the employer requires of the job seeker. In the evaluation creation step, an evaluation of the registered information is created based on the combination of the condition information and the registered information and the evaluation reference information, where the evaluation reference information is information relating to the correlation between the combination of the condition information and the registered information and the evaluation. In the result display control step, the evaluation and an input area that accepts editing of the evaluation conditions are displayed simultaneously. In the update step, the evaluation conditions are updated according to the content entered into the input area. In the evaluation submission step, the employer submits additional evaluations for job seekers for whom the aforementioned evaluation has been created. In the revision proposal step, a revised version of the evaluation conditions is created based on the combination of the condition information, the evaluation, and the additional evaluation, and the first proposal reference information, where the first proposal reference information is information relating to the correlation between the combination of the condition information, the evaluation, and the additional evaluation and the revised version. The information processing system, in the result display control step, displays the proposed revisions in addition to the input area.

8. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, condition information including at least one evaluation criterion and the job seeker's registration information are acquired, where the evaluation criterion is a condition that the employer requires of the job seeker. In the evaluation creation step, an evaluation of the registered information is created based on the combination of the condition information and the registered information and the evaluation reference information, where the evaluation reference information is information relating to the correlation between the combination of the condition information and the registered information and the evaluation. In the result display control step, the evaluation and an input area that accepts editing of the evaluation conditions are displayed simultaneously. In the update step, the evaluation conditions are updated according to the content entered into the input area. In the result display control step, in addition to the input area, a policy input area for inputting the policy for modifying the evaluation conditions is displayed simultaneously. In the revision proposal step, a revised version of the evaluation conditions is created based on the combination of the condition information and the revision policy, and the second proposal reference information, where the second proposal reference information is information relating to the correlation between the combination of the condition information and the revision policy and the revised version. The information processing system, in the result display control step, displays the proposed revisions in addition to the input area.

9. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, condition information including at least one evaluation criterion and the job seeker's registration information are acquired, where the evaluation criterion is a condition that the employer requires of the job seeker. In the evaluation creation step, an evaluation of the registered information is created based on the combination of the condition information and the registered information and the evaluation reference information, where the evaluation reference information is information relating to the correlation between the combination of the condition information and the registered information and the evaluation. In the result display control step, the evaluation and an input area that accepts editing of the evaluation conditions are displayed simultaneously. In the update step, the evaluation conditions are updated according to the content entered into the input area. In the candidate extraction step, the information processing system creates extraction conditions for extracting candidates suitable for the target job based on the registration information of job seekers who have received an evaluation of a predetermined level or higher from among a plurality of job seekers for whom the evaluation has been created based on the condition information, and reference information for creating conditions, and further extracts job seekers who meet the extraction conditions from among the job seekers registered in the database as candidates, where the reference information for creating conditions is information regarding the correlation between the registration information and the extraction conditions.

10. In the information processing system described in claim 9, An information processing system that, in the candidate extraction step, adds the candidate to the group associated with the target job, or proposes such addition.

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

12. Information processing method, An information processing method comprising an information processing device performing each step of the information processing system described in any one of claims 1 to 11.

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

Images