Information processing systems, information processing methods, and programs

Abstract

This invention provides an information processing system, method, and program that make recruitment activities more efficient. [Solution] In the information processing system 1, the server device displays a first screen on the terminal 20 of a recruiter U1 who conducts recruitment activities, which includes a first field for specifying the mandatory requirements for a given job posting and a second field for specifying the desirable requirements for a given job posting. The server device receives the requirements entered in one or more first fields and one or more second fields, along with the registration information of job candidates U2 for the given job posting. The server device inputs the received requirements and the registration information of job candidates into an artificial intelligence module, generates information on the correlation of job candidates for each requirement specified in one or more first fields and one or more second fields, and displays a second screen on the recruiter's terminal that shows the generated information on the correlation of job candidates for each requirement specified in one or more first fields and one or more second fields.

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 system for executing an adoption process and the like.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] On the other hand, there is still room for improvement in technologies for streamlining the adoption activity.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that can make the adoption activity more efficient.

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 a first display control step, a first screen is displayed on the terminal of a recruiter conducting recruitment activities for inputting requirements related to recruitment activities, wherein the first screen displays one or more first fields for identifying essential requirements for a given job posting and one or more second fields for identifying desirable requirements for a given job posting; in a first reception step, the requirements entered in one or more first fields and one or more second fields, and registration information of job candidates for the given job posting are received; in a first generation step, the received requirements and registration information of job candidates are input to an artificial intelligence module to generate information relating to the correlation of job candidates for each requirement identified in one or more first fields and one or more second fields; and in a second display control step, a second screen is displayed on the terminal of a recruiter showing the generated information relating to the correlation of job candidates for each requirement identified in one or more first fields and one or more second fields.

[0007] In this configuration, an information processing system, etc., that can make recruitment activities more efficient will be provided. [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 is a block diagram showing the hardware configuration of user terminal 20. [Figure 4] This is a block diagram showing the functions implemented by the server device 10 (control unit 11) and the user terminal 20 (control unit 21). [Figure 5] This is an activity diagram illustrating the information processing of this embodiment. [Figure 6] This is an example of the first screen displayed on the recruiter's terminal. [Figure 7] This is an example of a screen displayed on a recruiter's terminal. [Figure 8] This is an example of the second screen displayed on the recruiter's terminal. [Figure 9] This is an example of a screen displayed on a recruiter's terminal. [Figure 10] This is a modified version of the first screen displayed on the recruiter's terminal. [Figure 11] This is a modified version of the second screen displayed on the recruiter's terminal. [Figure 12] This is a modified version of the first screen displayed on the recruiter's terminal. [Modes for carrying out the invention]

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

[0010] In other words, the information processing system of this embodiment is as follows. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the first display control step, a first screen for inputting requirements related to the recruitment activity is displayed on the terminal of the recruiter conducting the recruitment activity. Here, the first screen displays one or more first fields for identifying the essential requirements for a given job posting, and one or more second fields for identifying the desirable requirements for the given job posting. In the first application step, the requirements entered in the one or more first fields and the one or more second fields, and the registration information of the candidate for employment for the specified job posting are received. In the first generation step, by inputting the received requirements and the registration information of the candidate for employment into the artificial intelligence module, information regarding the correlation of the candidate for employment for each requirement specified in the one or more first columns and the one or more second columns is generated. In the second display control step, an information processing system that causes a second screen showing information regarding the correlation of the candidate for employment generated for each requirement specified in the one or more first columns and the one or more second columns to be displayed on the terminal of the employment activity person.

[0011] By the way, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium readable by a computer, may be provided so as to be downloadable from an external server, or may be provided so as to realize its function on a client terminal by starting the program on an external computer (so-called cloud computing).

[0012] Also, in various information processing according to one embodiment, input and output corresponding to the input can be realized. Here, if an output is obtained as a result of the input, the mode of information (hereinafter referred to as reference information) referred to in such information processing is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, a predetermined function (including a determination formula such as a regression formula constructed by a statistical method), a learned model in which the correlation between the input and the output has been learned in advance, or a large language model capable of outputting a desired result by inputting a prompt (these models include parameters for constructing the correlation between the input and the output), or a generative AI such as a vision language model.

[0013] Also, in one embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various information is handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a binary bit aggregate composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0014] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit (Circuit), circuitry (Circuitry), a processor (Processor), a memory (Memory), etc. Also, the processor may be a general-purpose processor or a dedicated circuit. That is, it includes application specific integrated circuits (ASICs), programmable logic devices (for example, simple programmable logic devices (SPLD), complex programmable logic devices (CPLD), and field programmable gate arrays (FPGA)), etc.

[0015] 1. Hardware Configuration In this section, the hardware configuration will be described.

[0016] <Information Processing System 1> Figure 1 is a configuration diagram representing information processing system 1. The information processing system 1 shown as an example in Figure 1 comprises a communication line 2, a server device 10, and a plurality of user terminals 20. The server device 10 and the plurality of user terminals 20 are configured to communicate with each other via the communication line 2. Although Figure 1 shows one user terminal 20 used by a recruiter U1 and one user terminal 20 used by a job candidate U2, there may be multiple recruiters U1 and multiple job candidates U2. Furthermore, the connection between the server device 10 and the plurality of user terminals 20 may be wired or wireless.

[0017] Recruiter U1 may be one or more users who conduct recruitment activities. In one embodiment, Recruiter U1 may be an employer who recruits personnel. In this embodiment, "employer" may include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.). Furthermore, "employer" may be a person in charge (recruitment officer, etc.) of the aforementioned types of corporations, and may include a person in charge of the organization's human resources department or a person in charge of the department that recruits personnel. In addition, Recruiter U1 may include persons who support the recruitment activities of the aforementioned employer. Examples of persons who provide support here include recruitment agencies. In this embodiment, "recruitment agency" is a person who supports the recruitment activities of employers, etc., and may be an organization or a person in charge thereof that mediates the communication between job candidates U2 (described later) and employers. Such recruitment agencies are sometimes also called recruitment agencies, headhunters, agents, etc.

[0018] Candidate U2 may be one or more users who are candidates in the recruitment process. In one embodiment, Candidate U2 may be a job seeker. A job seeker refers to various people who are looking for work, including, for example, currently employed people (those seeking a career change), unemployed people who wish to find work, and prospective graduates (job seekers). Candidate U2 can apply to job postings from the aforementioned employers, etc., or have interviews with recruiters U1, etc., in order to be hired. In addition, Candidate U2 can receive information about job postings from recruiters U1, etc., through scout messages, etc., and consider applying for relevant job postings.

[0019] Furthermore, the user terminals 20 used by recruiter U1 and candidate U2 may be referred to as "recruiter terminal," "candidate terminal," etc.

[0020] In one embodiment, the information processing system 1 may provide a platform used by recruiters U1 and job candidates U2. Such a platform may also be called a platform for talent acquisition. For example, the information processing system 1 provides and manages a talent matching platform or talent matching services used by recruiters U1 and job candidates U2. That is, from the perspective of recruiter U1, recruitment activities of employers, etc., are supported via the server device 10, so it can be said that recruitment support services are provided. Also, from the perspective of job candidate U2, their job-seeking activities are supported, so it can be said that job-seeking support services are provided.

[0021] In another embodiment, the information processing system 1 may provide a platform to support human resource management (employee management) and the formulation of personnel strategies within an organization. In such processes of human resource management and the formulation of personnel strategies, recruiters U1 and job candidates U2 can store (register) various information in the server device 10 via their own terminals (user terminals 20). In a typical embodiment, recruiter U1 may be a person belonging to a predetermined organization, and job candidate U2 may be a person belonging to the same organization (employee, etc.). In such a case, various activities can be carried out to recruit personnel within the organization. Furthermore, when such a platform is provided, various information may be sent and received between recruiter U1 and job candidate U2.

[0022] In one embodiment, the information processing system 1 consists of one or more devices or components. For example, the information processing system 1 may include a server device (e.g., server device 10) having a processor (e.g., control unit 11) and a terminal (e.g., user terminal 20) that can access the server. These components will be described below.

[0023] <Server device 10> Figure 2 is a block diagram showing the hardware configuration of the server device 10. As shown in Figure 2, the server device 10 comprises a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected within the server device 10 via the communication bus 14.

[0024] <Control Unit 11> The control unit 11 performs processing and control of the overall operation related to the server device 10. The control unit 11 is, for example, a Central Processing Unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading 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.

[0025] <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.

[0026] <Communications Department 13> The communication unit 13 preferably uses wired communication methods such as USB, IEEE1394, Thunderbolt®, and wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as LTE / 5G, and Bluetooth® communication as needed. In other words, it is more preferable to implement it as a collection of these multiple communication methods. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0027] 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.

[0028] <User terminal 20> Figure 3 is a block diagram showing the hardware configuration of the user terminal 20. This user terminal 20 is the terminal used by the various users described above. As shown in Figure 3, the user 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 user terminal 20 via the communication bus 26. The explanation of the control unit 21, storage unit 22, and communication unit 23 is the same as the explanation of each part in the server device 10, so it will be omitted.

[0029] <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 casing of the user 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.

[0030] <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 casing of the user terminal 20 or it may be an external component. 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 in accordance with the type of user terminal 20.

[0031] Although Figure 1 shows an example where the user terminal 20 is a laptop PC (Personal Computer), the type of terminal used by the user terminal 20 is not particularly limited in this embodiment. That is, each user terminal 20 may be a desktop PC, laptop PC, smartphone, tablet, or any other type of information processing terminal.

[0032] 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 (the processor provided by the information processing system 1).

[0033] Figure 4 is a block diagram showing the functions realized by the server device 10 (control unit 11) and the user terminal 20 (control unit 21).

[0034] As shown in Figure 4A, the server device 10 (control unit 11) may include a registration unit 110, a display control unit 111, a reception unit 112, a generation unit 113, a memory management unit 114, an extraction unit 115, and an artificial intelligence unit 116. As shown in Figure 4B, the user terminal 20 (control unit 21) may include a display control unit 210 and an operation reception unit 211.

[0035] <Registration Section 110> The registration unit 110 is configured to execute the registration step. In the registration step, the registration unit 110 performs user registration and various information registration for the platform provided by the information processing system 1. In this embodiment, the registration unit 110 registers one or more of the recruiters U1 and job candidates U2 as users of the platform. In this embodiment, the registration unit 110 may also register information regarding the user's work history, such as their career history and skills, in association with the job candidate U2, for example, a resume or work history document. Here, the work history document may be called a resume (resume document). Furthermore, in this embodiment, the registration unit 110 may register information regarding job postings on the platform based on terminal operations of the recruiter U1, etc. Here, the information regarding job postings may include, for example, information that can be written on a job posting, and may include information regarding job type, annual salary, industry, position (layer), required skills, employment type, work location, working hours, holidays, corporate culture, job content, and allowances. Furthermore, the information regarding job postings may also include information such as the location, number of employees, performance, and corporate culture of the employer providing the job posting. The information registered by the registration unit 110 may be stored in a predetermined memory area based on the functions of the memory management unit 114 described later.

[0036] <Display Control Unit 111> The display control unit 111 is configured to execute a display control step. In the display control step, the display control unit 111 controls whether or not visual information can be displayed on each user terminal 20. Also in the display control step, the display control unit 111 generates various display information and controls it so that content that can be seen by the user is displayed. The display information may be the information itself that is generated in a manner that can be seen by the user, such as a screen, image, icon, or text, or it may be rendering information for displaying a screen, image, icon, text, etc. on various terminals. In the example of this embodiment, the display control unit 111 causes predetermined screens, such as the first screen and the second screen, to be displayed on the user terminal 20. The content that can be displayed on the user terminal 20 will be explained later.

[0037] <Reception Desk 112> The reception unit 112 is configured to execute the reception step. In the reception step, the reception unit 112 receives various information related to the information processing system 1. In this embodiment, the reception unit 112 receives the requirements entered in one or more first fields and one or more second fields, and the registration information of the candidate U2 for a given job posting. Details of the information received by the reception unit 112 will be explained later.

[0038] <Generation unit 113> The generation unit 113 is configured to execute the generation step. In the generation step, the generation unit 113 generates various information based on the received information, etc. In this specification, the term "generation" may be replaced with terms such as "creation" as appropriate. In the example of this embodiment, the generation unit 113 inputs the received requirements and the registration information of the candidate U2 into the artificial intelligence module to generate correlation information of the candidate U2 for each requirement specified in one or more first columns and one or more second columns. Details of the content generated by the generation unit 113 will be explained later.

[0039] <Storage management section 114> The memory management unit 114 is configured to execute memory management steps. In the memory management steps, the memory management unit 114 manages the storage state of various information related to the information processing system 1. Typically, the memory management unit 114 can be configured to store information handled by the server device 10, various terminals, etc., in a memory area. This memory area is exemplified by the memory area (storage unit 12) of the server device 10 or the memory areas of various devices, but this memory area does not necessarily have to be within the system shown in Figure 1, and the memory management unit 114 can also store various information in external storage devices, etc.

[0040] <Extraction part 115> The extraction unit 115 is configured to perform the extraction step. In the extraction step, the extraction unit 115 extracts one or more pieces of information that satisfy predetermined criteria from the information that can be handled. Details of the processing performed by the extraction unit 115 will be described later.

[0041] <Artificial Intelligence Department 116> The artificial intelligence unit 116 is configured to receive input from each functional unit and return the instructed output, thus constituting an artificial intelligence module. The artificial intelligence used by the server device 10 in each functional unit may be common to all units, or it may be individually prepared for each functional unit. Furthermore, the artificial intelligence unit 116 may function as a core module that supports the artificial intelligence processing in each of these functional units.

[0042] The artificial intelligence unit 116 may be an AI (Artificial Intelligence) equipped with pre-trained models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNNs). The artificial intelligence unit 116 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include specific models such as OpenAI's GPT, Google's Gemini, and models provided through services and platforms such as Microsoft's Azure AI Studio. Generative AI may be, for example, text generation AI, image generation AI, or multimodal generation AI. The pre-trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 116 can include any pre-trained model.

[0043] 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 116 can apply these algorithms as appropriate.

[0044] The artificial intelligence unit 116 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.

[0045] The artificial intelligence unit 116 may include a natural language model as its artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large-scale data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by 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 116 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.

[0046] The pre-trained models included in the artificial intelligence unit 116 (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 116 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.

[0047] The trained model included in the artificial intelligence unit 116 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 (combination of input data and output data of the training model) is small. Compared to the original training model (teacher model), the distilled model has performance close to that of the trained model, but with fewer parameters and a lower processing load. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0048] 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.

[0049] An AI agent (also called an autonomous agent) is a system, program, or function that autonomously determines and executes the processes necessary to achieve a goal or accomplish a task, in response to a goal (objective, purpose, etc.) or task (output of XX) input by a user, such as "Teach me about XX." To achieve a goal or task, the AI ​​agent may break down the task into subtasks or actions, and may perform at least one of the following: collecting and analyzing necessary data, using external tools, generating and executing programs, etc. The AI ​​agent takes information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, and outputs information according to the goal, and does not require user intervention (operation input). However, the AI ​​agent may seek confirmation or feedback from the user as needed. Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously perform learning (including in-context learning, etc.) to aim at achieving the goal or improving the accuracy of achievement. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.). Furthermore, the AI ​​agent may be configured as a multi-agent system comprising multiple AI agents. In this case, the multiple AI agents may have different roles, capabilities, or access privileges. The multiple AI agents may cooperate to solve tasks by communicating (dialogue) with each other using natural language or predetermined protocols. The cooperation between each AI agent is not limited to a hierarchical structure (superior-subordinate relationship); the multiple AI agents may autonomously discuss and vote, and the final output may be determined by consensus.

[0050] <Display Control Unit 210> The display control unit 210 of the user terminal 20 controls the display to show the screen indicated by the screen data transmitted from the server device 10.

[0051] <Operation reception unit 211> The operation reception unit 211 of the user terminal 20 receives operations from users using the user terminal 20 (such as recruiter U1, job candidate U2, etc.).

[0052] 3. Information Processing Methods This section describes the information processing method for the server device 10, with examples. This information processing method may be executed by each part of the server device 10 as individual steps. The various features shown in this section can be combined with each other as long as they do not create technical inconsistencies.

[0053] Figure 5 is an activity diagram illustrating the information processing of this embodiment. As shown in the activity diagram in Figure 5, in the information processing method of this embodiment, when recruiter U1 inputs predetermined information to the first screen, correlation information is generated, and the generated information is displayed on the second screen.

[0054] Such a first screen can be displayed, for example, when recruiter U1 requests the server device 10 to display the first screen. That is, after the server device 10 receives the request from recruiter U1 to display the first screen, the display control unit 111 of the server device 10 displays the first screen for inputting requirements related to recruitment activities on the terminal of recruiter U1 who is conducting recruitment activities (Activities A101~A104).

[0055] An example of such a first screen will be explained with reference to Figure 6. Figure 6 is an example of a first screen displayed on a recruiter's terminal. Such a screen (first screen) is configured to allow setting of recruitment requirements for a given job posting. In this embodiment, the first screen displays one or more first fields for specifying mandatory requirements for a given job posting, and one or more second fields for specifying desirable requirements for a given job posting.

[0056] Figure 6 shows an example of a screen where various requirements can be set for a job posting for a position such as "Overseas Sales Manager Candidate." Fields C11 and C12 in Figure 6 are fields where the mandatory requirements for the job posting can be entered. Fields C21 and C22 are fields where the desirable requirements for the job posting can be entered. In other words, in the example shown in Figure 6, fields C11 and C12 correspond to the aforementioned "first field," and fields C21 and C22 correspond to the aforementioned "second field." A recruiter U1 who accesses the screen shown in Figure 6 can then enter the various requirements to be set for the job posting into the respective fields.

[0057] Note that the number of items in the first and second columns is not limited to the numbers shown in Figure 6. For example, in the example shown in Figure 6, the number of items set as required or preferred requirements can be increased by manipulating objects such as object OBJ1. Although not shown in detail in Figure 6, it may also be possible to delete columns corresponding to the first and second columns.

[0058] Furthermore, the example shown in Figure 6 illustrates a configuration in which a field C3 is provided for entering additional instructions. This field C3 corresponds to the "third field" described later, and allows the recruiter U1 to enter any instructions regarding the job posting.

[0059] Furthermore, the example shown in Figure 6 illustrates a configuration in which fields (fields C111, C211, etc.) are provided that allow the user to specify "importance" in relation to the first and second fields. In one embodiment, the reception unit 112 of the server device 10 can accept the setting of weights for each requirement specified in one or more first fields and / or one or more second fields, based on the content entered in such fields. Here, Figure 6 shows a configuration in which importance (weighting) based on ranks such as "A, B, C" is set for various requirements, but the weights to be set may be based on the input of information such as scores (numerical values), symbols (e.g., ◎, ○, △, etc.), or text information (e.g., high, medium, low, etc.). This input may be performed via any GUI, such as selecting from a pull-down menu, selecting with radio buttons, operating a slider object, or directly entering into a text box. Furthermore, while Figure 6 shows a configuration in which weights are assigned to both mandatory and welcome requirements, it may also be possible to set weights for only one type of requirement, such as only requirements corresponding to welcome requirements or only requirements corresponding to mandatory requirements, and it is not necessary to set weights for both mandatory and welcome requirements. In addition, it may be possible to set negative values ​​(negative weights) for "exclusion requirements (negative requirements)" that place importance on not meeting certain conditions. Also, while Figure 6 shows a configuration in which the same type of importance can be set for both mandatory and welcome requirements, the means of setting importance can also be different for mandatory and welcome requirements. For example, it may be possible to set weights such as "A, B, C" for mandatory requirements, while only setting weights such as "D, E, F" which are of lower importance, for welcome requirements. In one configuration, predetermined information such as coefficients and parameters used in the overall evaluation described later may be generated according to the input content in the field for specifying such importance. Details regarding such information generation will be explained later in relation to the processing performed by the generation unit 113.

[0060] Furthermore, a mechanism to assist in information input may be adopted for such a first screen. In the example shown in Figure 6, an object that allows the user to specify a job posting is shown as button BT1. The recruiter U1 can, for example, press this button BT1 to specify a particular job posting. Then, from the specified job posting, the user can extract the content to be entered on the first screen and enter the required information into each field.

[0061] In one embodiment, the reception unit 112 of the server device 10 may receive a designation of an object containing information about a predetermined job posting. The extraction unit 115 of the server device 10 may then extract from the content of the designated object the content of the essential requirements for the predetermined job posting and the content of the desirable requirements for the predetermined job posting. The display control unit 111 of the server device 10 may then transfer the extracted content to one or more first columns and / or one or more second columns and display the first screen.

[0062] Furthermore, the target that the reception unit 112 accepts as a designation may be any document containing information about a job posting. For example, if an electronic file (such as a PDF file) containing information about a job posting is designated, the system can extract the content corresponding to the required and preferred requirements from the information described in the electronic file and transcribe the extracted content into the first and second columns. In performing such transcription, known technologies for deciphering the information shown in the electronic file (for example, Optical Character Recognition (OCR)) may be used. In addition, by retrieving information registered in a predetermined database, such as information registered on the aforementioned platform (information about registered job postings), requirements linked to such registered information can also be transcribed into each column. Furthermore, the columns into which the information is transcribed are not necessarily limited to the first and second columns. For example, related information may also be transcribed into the field for entering the position name or into the third column (column C3). In addition, when transcribing to the columns shown on the first screen, adjustments to the expression of the content described in the target may be made as necessary.

[0063] Recruiter U1 can input the required information on the screen shown in Figure 6 and then press button BT2 to have the server device 10 receive the entered requirements. In other words, in response to the operation of the screen shown in Figure 6, the reception unit 112 of the server device 10 can receive the requirements entered in one or more first fields and one or more second fields (activities A105 to A106). In this embodiment, in addition to the requirements, the reception unit 112 also receives registration information of job candidates U2 for a given job posting. The manner in which this registration information of job candidates U2 is received will be explained with reference to Figure 7.

[0064] Figure 7 shows an example of a screen displayed on a recruiter's terminal. The screen shown in Figure 7 is typically used by recruiter U1 to specify a candidate U2 to be evaluated. Specifically, area Rg1 of the screen shown in Figure 7 may be an operation area for identifying candidate U2. For example, candidate U2 identified in response to operations in area Rg1 can be used to generate correlation information. In the example shown in Figure 7, area Rg1 is shown as a method for specifying a predetermined candidate U2 from an electronic file (e.g., a PDF file) held by recruiter U1. For example, candidate U2 to be evaluated can be specified by operating button BT3 or by dropping an electronic file containing details of candidate U2 into area Rg1. Then, with one or more candidate U2s identified in area Rg1, pressing button BT4 allows the reception unit 112 to receive registration information for the identified candidate U2s. Furthermore, when a candidate U2 is identified based on an electronic file, the reception unit 112 may utilize known technologies for deciphering the information contained in the electronic file (for example, Optical Character Recognition (OCR)) when receiving the registration information of the candidate U2. In one embodiment, the screen for identifying the candidate U2 whose registration information is to be received may display the details of the corresponding candidate U2's registration information. By displaying such details, the recruiter U1 can efficiently select the candidate U2 to be evaluated.

[0065] The timing of the display of the screen shown in Figure 7 can be set arbitrarily. For example, the screen shown in Figure 7 may be controlled to be displayed when button BT2 is pressed on the screen shown in Figure 6. On the other hand, a screen for specifying candidate U2, as shown in Figure 7, may be displayed prior to the display of the first screen as shown in Figure 6.

[0066] Furthermore, the acceptance of registration information for candidate U2 may be implemented by means other than the screen shown in Figure 7. For example, a field for specifying candidate U2 may be provided in the first screen (for example, in the screen shown in Figure 6), and candidate U2 whose registration information is to be accepted may be identified based on operations on this field. Alternatively, the acceptance unit 112 may accept registration information for candidate U2 by accepting a file (for example, a CSV file) containing the registration information of one or more candidate U2s.

[0067] Furthermore, while the above explanation describes a configuration in which recruiter U1 designates candidate U2 to be evaluated, the reception unit 112 may also perform a process to proactively receive (proactively acquire) registration information of candidate U2. For example, it may be configured to receive registration information of candidate U2 who performed a predetermined action related to a corresponding job posting. The predetermined action here may include applying for a job posting, viewing a page related to a job posting, registering a page related to a job posting (e.g., adding to favorites), opening or replying to a scout message related to a job posting, etc. Alternatively, at predetermined timings (times), a process may be performed to extract candidate U2 who have performed the aforementioned actions, and a process may be performed to receive registration information of the extracted candidate U2.

[0068] After receiving various information in this manner, the generation unit 113 of the server device 10 inputs the received requirements and the registration information of the candidate U2 into the artificial intelligence module to generate correlation information for candidate U2 for each requirement specified in one or more first columns and one or more second columns (Activity A107). Then, the display control unit 111 of the server device 10 displays a second screen on the terminal of the recruiter U1 that shows the generated correlation information for candidate U2 for each requirement specified in one or more first columns and one or more second columns (Activities A108-A109).

[0069] An example of such a second screen will be explained with reference to Figure 8. Figure 8 is an example of a second screen displayed on a recruiter's terminal. In the example screen shown in Figure 8, the evaluation for each requirement of the job posting is displayed as information regarding the correlation of the generated candidate U2. Specifically, in the example screen shown in Figure 8, it is indicated whether or not candidate U2 meets the predetermined requirements as an evaluation of the various requirements entered in columns C11, C12, C21, C22, etc. in Figure 6. Thus, in this embodiment, the generation unit 113 may generate information regarding the correlation of candidate U2, including the degree of satisfaction for essential requirements specified in one or more first columns, and / or the degree of satisfaction for desirable requirements specified in one or more second columns. Specifically, in the screen shown in Figure 8, a form is shown in which labels (evaluation EV1, evaluation EV2) indicating whether or not the predetermined requirements are met, such as "Applicable" or "Not Applicable," are displayed. Note that the correlation information may be generated in a form different from such labels. For example, the generation unit 113 may generate scores (e.g., numerical values), symbols (e.g., ◎, ○, △, etc.), marks, text, etc., to represent the correlation between each requirement and the registration information of candidate U2, and display them on the second screen. Furthermore, if the generation unit 113 cannot determine from the registration information of candidate U2 whether or not a predetermined requirement is met, it may generate information indicating a status such as "Undetermined," "Unknown," or "Insufficient Information" as the degree of fulfillment of that requirement. In this case, the second screen may display the status along with the missing information necessary to generate the degree of fulfillment (e.g., a message such as "There is no information regarding the number of years of experience in XX").

[0070] Information regarding the correlation of such job candidates U2 may be obtained by referring to reference information that includes the correlation between the requirements and the registration information of job candidates U2 and the correlation information. The reference information here may include a set of parameters for generating correlation information from the requirements and the registration information of job candidates U2. For example, the reference information may be various pre-trained models. For example, the reference information may include a first generative model which is a dedicated training model or a general-purpose training model that takes the requirements and the registration information of job candidates U2 as input and outputs correlation information. In this case, the generation unit 113 of the server device 10 inputs the requirements and the registration information of job candidates U2 into the first generative model and causes the first generative model to output correlation information.

[0071] The first generative model may be included in the artificial intelligence unit 116. The first generative model, which is a dedicated learning model, is a learning model that has learned using the requirements and registration information of candidate U2 and the corresponding correlation information as training data. In such a first generative model, the parameters calculated and tuned through learning construct the correlation relationship between the requirements and registration information of candidate U2 and the correlation information. The dedicated learning model may include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0072] If the first generative model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 113 of the server device 10 may input a prompt to the artificial intelligence unit 116 (artificial intelligence module) that includes an instruction to output correlation information based on the requirements and registration information of the candidate U2, and the requirements and registration information of the candidate U2, causing the artificial intelligence unit 116 to output (generate) correlation information corresponding to the requirements and registration information of the candidate U2. Alternatively, the generation unit 113 of the server device 10 may generate a prompt that gives the first generative model an instruction to output (generate) correlation information, and input this prompt to the first generative model. In addition to the instruction to output (generate) correlation information and the requirements and registration information of the candidate U2, the generation unit 113 of the server device 10 may input a prompt to the artificial intelligence unit 116 (artificial intelligence module) that includes, for example, one or more samples of the requirements and registration information of the candidate U2, and one or more samples of correlation information corresponding to them. Here, parameters for constructing the first generative model and prompts containing instructions to output (generate) correlation information based on the requirements and registration information of candidate U2 construct the correlation relationship between the requirements and registration information of candidate U2 and the correlation information. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed. The output (generated) correlation information may then be displayed on the second screen.

[0073] In this embodiment, the generation unit 113 of the server device 10 may further generate reasons that form the basis of the satisfaction level. The display control unit 111 of the server device 10 may further display the generated reasons. That is, in the example screen shown in Figure 8, the reasons that form the basis of the evaluation (satisfaction level) are displayed in a position adjacent to each requirement so as to correspond to the evaluation for each requirement. To explain from one perspective, the correlation information mentioned above may include such reasons that form the basis of the satisfaction level. The generation unit 113 generates such reasons based on the functions of the artificial intelligence unit 116 (artificial intelligence module), and the display control unit 111 can display the generated content on a predetermined screen. The display control unit 111 may, for example, display the relevant part (for example, specific experience, qualifications, skills, etc.) of the registration information of the candidate U2 (e.g., resume, curriculum vitae, etc.) that was used as the basis for the evaluation (satisfaction level) as reasons that form the basis of the satisfaction level. In other words, as explained earlier, the registration unit 110 can register information about work history, such as a resume or work history document, indicating career history and skills, in association with the candidate U2. However, as the generation unit 113 generates correlation information, the display control unit 111 may display such registered information, such as work history information, on the terminal of the recruiter U1 or the like. Note that the registered information displayed here is not limited to information displayed in a predetermined format, such as a resume or work history document. For example, information registered in any database can be displayed to the recruiter U1 or the like. Furthermore, the displayed registered information may include information about the candidate U2's work experience and experience (for example, a document that expresses the work experience and experience in chronological order, or a document that summarizes the work experience and experience), and information about the candidate U2's skills. After such registered information is displayed, the display control may be configured so that the section corresponding to the reason for the satisfaction level generated by the generation unit 113 can be identified. Such display control may typically be achieved by changing the color tone or adding predetermined tags or marks to fields or areas that indicate the basis for the degree of satisfaction. Other examples include, but are not limited to, changing the font of the text indicating the target area.In other words, display control means that highlight a predetermined part of the screen may be used as a means to help the user understand the part corresponding to the reason that forms the basis of such satisfaction. Alternatively, instead of, or in addition to, the method of helping the user understand a predetermined part of the registered information, the generation unit 113 may generate the reason that forms the basis of the satisfaction as information in natural language (e.g., text, sentences, etc.) and display it on the terminal of the recruiter U1. By displaying the reason that forms the basis of the satisfaction on the screen in this way, the recruiter U1 can easily confirm the reason for the evaluation and evaluate the candidate U2 more efficiently. In Figure 8, the method of displaying such reasons on the second screen is shown, but if necessary, the system may be controlled to display the generated reasons on a screen different from the second screen. In addition, the second screen may also display the relevant part of the registered information of candidate U2 that forms the basis of the satisfaction level, such as by displaying it as a pop-up. In this case, for example, the information of the relevant part can be displayed by clicking or hovering the mouse over the text of each requirement.

[0074] Furthermore, regarding the first screen, it was stated that the reception unit 112 of the server device 10 may accept weighting settings for each requirement specified in one or more second columns from the recruiter. However, on the second screen, the correlation information for each requirement specified in one or more second columns may be controlled to be displayed in different ways depending on the weighting settings. In other words, in this embodiment, it may be possible to identify requirements that recruiter U1 considers important among the welcome requirements by setting column C211, etc. For example, various display control means may be applied to make it easier for recruiter U1 to grasp the correlation information for such important requirements. For example, the correlation information for the corresponding requirements may be displayed by changing the color tone or attaching predetermined tags or marks to areas or ranges that indicate predetermined requirements (requirements with high weighting, requirements with high importance). For example, evaluation information corresponding to requirements set to high importance may be displayed in a larger font, highlighted in a conspicuous color, or preferentially placed higher in the display list compared to evaluation information for requirements set to low importance. This allows recruiter U1 to intuitively grasp the degree to which the requirements they consider important are being met. Other examples of display mode control include changing the font of text indicating the target requirements and information on the correlations corresponding to those requirements, but are not limited to these. In other words, display control means that emphasize a predetermined part of the screen may be used as a means of controlling such display modes. Here, we have explained how to control the display mode of welcome requirements, but similar display mode control may be applied to mandatory requirements in place of or in addition to welcome requirements. When controlling the display mode of such mandatory requirements, the weighting of the mandatory requirements, as set in column C111, may be referenced. That is, the display mode of each requirement on the second screen and the information on the correlations corresponding to those requirements may change in conjunction with the importance (weighting) settings set in Figure 6, etc.

[0075] Furthermore, regarding the correlation information of the candidate U2 generated by the generation unit 113, the memory management unit 114 of the server device 10 may store the generated correlation information of the candidate U2 in a predetermined memory area, associating it with the candidate U2 related to the registration information received by the reception unit 112. In this way, the recruiter U1 can retrieve the generated correlation information of the candidate U2 as needed, and proceed with the recruitment work appropriately.

[0076] As previously explained, the first screen may have a third field in addition to one or more first fields and one or more second fields, where information generation instructions from recruiter U1 can be entered. The reception unit 112 of the server device 10 may also receive information generation instructions entered in the third field. The generation unit 113 of the server device 10 then generates a response corresponding to the information generation instructions by inputting at least the information generation instructions into the artificial intelligence module, and the display control unit 111 may further display the response generated by the generation unit 113 on the second screen. In this case, the generation unit 113 may input the contents of each requirement entered in the first field and / or second field and / or the registration information of the candidate U2 into the artificial intelligence module, in addition to the information generation instructions entered in the third field. This makes it possible to generate a response RS that is individually optimized for the candidate U2.

[0077] For example, the third column contains input for information generation instructions related to the recruitment process of a job posting, and the generation unit 113 can generate predetermined information in response. In the example shown in Figure 8, the generation unit 113 generates a response RS as a "response to the request" and displays it on the screen. That is, in the example shown in Figure 6, the third column (column C3) contains an instruction to generate "questions to be asked in focus during the first interview" as an information generation instruction, and the generation unit 113 generates questions for the candidate U2 in response. Thus, the reception unit 112 of the server device 10 may receive an instruction to generate questions for the candidate U2 as an information generation instruction, and the display control unit 111 of the server device 10 may display the generated questions for the candidate U2 on the second screen as a response RS. Note that, unlike the example shown in Figure 8, the generation unit 113 may generate content different from the questions based on the received information generation instruction. For example, the generation unit 113 may generate content corresponding to the following based on instructions such as summarizing the career history of candidate U2 (instruction to generate a summary of career history), generating the annual salary offer amount to be presented to candidate U2, and generating information about candidates with similar career history to candidate U2.

[0078] The second screen may be displayed on the recruiter's terminal, for example, when recruiter U1 conducts an interview with candidate U2. In such cases, the screen displays information corresponding to the information generation instructions (questions, etc.) along with information regarding the correlation of various requirements, making it easier for recruiter U1 to communicate effectively with candidate U2. If necessary, control may be implemented to prevent information generation in response to information generation instructions. For example, if the content entered in the third column (column C3) is not relevant to the recruitment of the job posting (for example, if it is content that violates public order and morals, or content consisting of keywords unrelated to recruitment), the generation unit 113 may be controlled not to proceed with the information generation process. This prevents the waste of computational resources based on inappropriate instructions and the output of inappropriate answers. The determination of whether or not the content is relevant to the recruitment of the job posting may be performed, for example, by keyword matching of the string entered in the third column, or by an artificial intelligence module. For example, if the artificial intelligence module is a general-purpose learning model, the generation unit 113 inputs at least the input content of the third column to the artificial intelligence module along with a prompt (determination instruction) for determining whether the content of the information generation instruction is related to the recruitment process. Then, based on the determination result obtained from the second generation model (for example, an answer such as "relevant" or "not relevant"), it may control whether to continue the generation process of the answer RS ​​or to interrupt it by making information generation impossible.

[0079] The response RS displayed on this second screen may be generated by referring to reference information that includes the correlation between the content of the information generation instruction and the response RS. The reference information here may include a set of parameters for generating the response RS from the content of the information generation instruction. For example, the reference information may include various pre-trained models. For example, the reference information may include a dedicated training model or a general-purpose training model, which is a second generation model that takes the content of the information generation instruction as input and outputs the response RS. In this case, the generation unit 113 of the server device 10 inputs the content of the information generation instruction into the second generation model and causes the second generation model to output the response RS.

[0080] The second generative model may be included in the artificial intelligence unit 116. The second generative model, which is a dedicated learning model, is a learning model that has learned the content of information generation instructions and the corresponding response RS as training data. In such a second generative model, parameters calculated and tuned through learning build a correlation between the content of information generation instructions and the response RS. The dedicated learning model may include a generative AI capable of generating responses 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.

[0081] If the second generative model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 113 of the server device 10 may input a prompt to the artificial intelligence unit 116 (artificial intelligence module) that includes an instruction to output a response RS based on the content of the information generation instruction, and the content of the information generation instruction, causing the artificial intelligence unit 116 to output (generate) a response RS corresponding to the content of the information generation instruction. Alternatively, the generation unit 113 of the server device 10 may generate a prompt that gives the second generative model an instruction to output (generate) a response RS, and input this prompt to the second generative model. In addition to the instruction to output (generate) a response RS and the content of the information generation instruction, the generation unit 113 of the server device 10 may input a prompt to the artificial intelligence unit 116 (artificial intelligence module) that includes, for example, one or more samples of the content of the information generation instruction and one or more samples of the corresponding response RS. Here, the parameters for constructing the second generative model and the prompt including an instruction to output (generate) a response RS based on the content of the information generation instruction establish a correlation between the content of the information generation instruction and the response RS. Furthermore, the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input such as the content of the output information to be generated and the content of the task to be performed. The output (generated) response RS may then be displayed on the second screen.

[0082] Furthermore, the generation unit 113 of the server device 10 can also generate the following information. Specifically, the generation unit 113 of the server device 10 can also generate an overall evaluation of candidate U2 by inputting at least the requirements received by the reception unit 112 and the registration information of candidate U2 into the artificial intelligence module. Specifically, in the example shown in Figure 7, an evaluation (evaluation EV3) of candidate U2 based on all the requirements is displayed as "Overall evaluation: A". By utilizing such an overall evaluation, the recruiter U1 can more easily perform the selection process for multiple candidates U2. Although Figure 8 shows the overall evaluation of candidate U2 based on ranks such as "S / A / B / C", the overall evaluation may be expressed based on different content. For example, the overall evaluation may be expressed by a score (e.g., a numerical value), a symbol (e.g., ◎, ○, △, etc.), a mark, text, etc., different from the above ranks.

[0083] Such a comprehensive evaluation may be performed by referring to reference information that includes the correlation between the requirements and the registration information of the candidate U2 and the comprehensive evaluation. The reference information here may include a set of parameters for generating the comprehensive evaluation from the requirements and the registration information of the candidate U2. For example, the reference information may include various pre-trained models. For example, the reference information may include a dedicated training model or a general-purpose training model, which is a third-generation model, that takes the requirements and the registration information of the candidate U2 as input and outputs the comprehensive evaluation. In this case, the generation unit 113 of the server device 10 inputs the requirements and the registration information of the candidate U2 into the third-generation model and causes the third-generation model to output the comprehensive evaluation.

[0084] The third generative model may be included in the artificial intelligence unit 116. The third generative model, which is a dedicated learning model, is a learning model that has learned using the requirements and registration information of the candidate U2 and the corresponding overall evaluation as training data. In such a third generative model, the parameters calculated and tuned through learning build a correlation between the requirements, the registration information of the candidate U2 and the overall evaluation. The dedicated learning model may include a generative AI capable of generating answers not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0085] If the third generative model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 113 of the server device 10 may input a prompt to the artificial intelligence unit 116 (artificial intelligence module) that includes an instruction to output an overall evaluation based on the requirements and the registration information of the candidate U2, and the requirements and the registration information of the candidate U2, causing the artificial intelligence unit 116 to output (generate) an overall evaluation corresponding to the requirements and the registration information of the candidate U2. Alternatively, the generation unit 113 of the server device 10 may generate a prompt that gives the third generative model an instruction to output (generate) an overall evaluation, and input this prompt to the third generative model. In addition to the instruction to output (generate) an overall evaluation and the registration information of the requirements and the candidate U2, the generation unit 113 of the server device 10 may input a prompt to the artificial intelligence unit 116 (artificial intelligence module) that includes, for example, one or more samples of the requirements and the registration information of the candidate U2, and one or more samples of the overall evaluation corresponding to them. Here, parameters for constructing the third generative model and prompts containing instructions to output (generate) an overall evaluation based on the requirements and registration information of candidate U2 establish a correlation between the requirements, the registration information of candidate U2, and the overall evaluation. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on input information. The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed. The output (generated) overall evaluation can then be displayed on various screens, including the second screen.

[0086] Furthermore, when generating such an overall evaluation, the weightings set for the requirements may be referenced. That is, the receiving unit 112 of the server device 10 may receive information regarding the weightings set for each mandatory and / or welcome requirement, and the generation unit 113 may generate the overall evaluation based on these set weightings. More preferably, the receiving unit 112 of the server device 10 may receive the weightings for each requirement specified in one or more second columns from the recruiter U1, and the generation unit 113 of the server device 10 may generate the overall evaluation based on the set weightings. In other words, generally, the degree to which recruiter U1 places importance on "welcome requirements" specified in the second column may differ. In such cases, by setting appropriate weightings for the content that is particularly important among the "welcome requirements," a more accurate overall evaluation can be generated. Furthermore, weightings may be set not only for welcome requirements but also for mandatory requirements. That is, weightings may be set for both mandatory and welcome requirements, or for mandatory requirements only. Even in such cases, a comprehensive evaluation is more likely to be generated that takes into account the most important aspects of the essential requirements.

[0087] Furthermore, when generating an overall evaluation based on such weighting, it is preferable that the generation unit 113 performs appropriate processing. For example, the generation unit 113 may input predetermined input information (requirements, registration information of candidate U2, and weighting content) into a dedicated learning model or general-purpose learning model, which is trained to take requirements, registration information of candidate U2, and weighting content as inputs and output an overall evaluation, as a third generation model, thereby generating an overall evaluation that takes the weighting content into consideration. Alternatively, if the third generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 113 of the server device 10 may input an instruction to output an overall evaluation based on requirements, registration information of candidate U2, and weighting content, and a prompt inserting the requirements, registration information of candidate U2, and weighting content into the artificial intelligence unit 116 (artificial intelligence module), causing it to output (generate) a corresponding overall evaluation. In addition, the overall evaluation may be generated using correlation information generated by the generation unit 113 for each requirement. For example, the generation unit 113 may score the correlation information for each requirement it generates, and then weight each score based on the set content to generate an overall evaluation of candidate U2. More specifically, the generation unit 113 may calculate the overall evaluation by performing a weighted average process, which involves multiplying the score for the degree of satisfaction calculated for each individual requirement by a coefficient corresponding to the weighting and summing them up.

[0088] Furthermore, the overall evaluation generated in this manner may be stored in a predetermined memory area. That is, the memory management unit 114 of the server device 10 may store the overall evaluation generated by the generation unit 113 in a predetermined memory area, associating it with the candidate U2 related to the registration information received by the reception unit 112.

[0089] Although Figure 8 shows a configuration in which information generated for a predetermined candidate U2, "Candidate A," is displayed, the generation unit 113 can generate various types of information for multiple candidates U2. Specifically, the reception unit 112 of the server device 10 can receive registration information for multiple candidates U2 as registration information for candidates U2, and the generation unit 113 of the server device 10 can generate correlation information for each of the multiple candidates U2 all at once.

[0090] In other words, as shown in Figure 7 above, a screen for identifying multiple job candidates U2 is displayed, and the reception unit 112 of the server device 10 in this embodiment may receive registration information for each of the multiple job candidates U2 identified in this way. Then, based on separately set requirements and other conditions, the generation unit 113 can generate predetermined information for each of the multiple job candidates U2. Here, "generate in batch" refers to generating information about multiple job candidates U2 with a single instruction. In other words, "generate in batch" is not limited to the simultaneous generation of information for multiple job candidates U2, but also includes the mode in which information for the multiple job candidates U2 targeted for creation is generated sequentially. Furthermore, as described above, when the reception unit 112 receives registration information for multiple job candidates U2, in addition to correlation information, the aforementioned response RS and overall evaluation may also be generated in batch.

[0091] Furthermore, the following configuration may be adopted in relation to the information generated in this manner. Specifically, the display control unit 111 of the server device 10 may display correlation information for each of the multiple job candidates U2 on the second screen. Here, the second screen may be configured to allow the recruiter U1 to switch to display correlation information for each job candidate U2. That is, in the example in Figure 8, it is configured to allow specifying a predetermined job candidate U2 as tab TB. By switching tab TB, the generated information for various job candidates U2 can be viewed. In this embodiment, typically, correlation information for multiple job candidates U2 can be generated while keeping the various requirements set for the job posting the same. In such a case, the recruiter U1 can compare the generated information while switching the display, and thus efficiently search for job candidates U2 who are suitable for the job posting.

[0092] In the above explanation, the generation unit 113 has been shown to generate correlation information, response RS, overall evaluation, etc., but there may be predetermined limits on the number of times the generation unit 113 generates information and the amount of information generated. For example, there may be limits on the number of times the generation unit 113 generates information and the amount of information generated for a given recruiter U1. In addition, there may be restrictions on viewing the various types of information generated by the generation unit 113. For example, only those with viewing privileges set by recruiter U1 may be able to view the information generated by the generation unit 113.

[0093] Furthermore, when recruiter U1 evaluates candidate U2, the following methods may also be employed. Specifically, the extraction unit 115 of the server device 10 may extract candidate U2 that satisfies the search conditions from among multiple stored candidate U2, based on the search conditions related to essential requirements and / or preferred requirements set by recruiter U1. Alternatively, the extraction unit 115 of the server device 10 may extract candidate U2 that satisfies the search conditions from among multiple stored candidate U2, based on the search conditions related to the overall evaluation set by recruiter U1.

[0094] For example, in the example shown in Figure 8, labels such as "Applicable" and "Not Applicable" are displayed in conjunction with mandatory and desirable requirements, and a rank of "A" is displayed as the overall evaluation. By setting the content corresponding to such labels and ranks as search conditions, it is possible to extract job candidates U2 that match the search conditions.

[0095] The screen displayed on the recruiter's terminal in relation to this extraction process will now be described. Figure 9 is an example of a screen displayed on the recruiter's terminal. In the screen shown in Figure 9, search conditions related to the overall evaluation and various requirements can be set. When the recruiter U1 sets the search conditions and presses button BT5, the system is configured to extract the candidate U2 that matches the search conditions. In the example in Figure 9, a checkbox CB is shown to allow setting the search conditions. The search conditions may be set appropriately according to the content of the information generated by the generation unit 113. For example, a search (extraction of candidate U2) can be performed based on the score (e.g., a numerical value) of candidate U2 generated by the generation unit 113, or keywords related to candidate U2 generated by the generation unit 113. The results of the extraction of candidate U2 may be displayed on the recruiter's terminal. In this configuration, for example, recruiter U1 can extract candidates U2 based on arbitrary search criteria set by recruiter U1, such as candidate U2 who meets all the essential requirements, or candidate U2 who meets all the essential requirements and also meets the desirable requirements that recruiter U1 considers important. Recruiter U1 can then consider various measures related to recruitment activities while referring to the results displayed on the terminal.

[0096] In summary, the information processing method of this embodiment allows for the display of predetermined information on the second screen, thus enabling more efficient recruitment activities.

[0097] 4. Others 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.

[0098] 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. Also, the artificial intelligence unit 116 may be an external component of the server device 10. In that case, the external artificial intelligence unit 116 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, and may provide an LLM, generative AI, or AI agent. The artificial intelligence service server may, for example, receive prompt input in the form of text, images, or audio, and generate and respond to the prompt. The server device 10 may also cooperate with the API (Application Programming Interface) of the service server that provides generative AI, etc., and utilize the generative AI, etc.

[0099] The first and second screens shown in the above embodiments may be modified as appropriate. For example, although a configuration in which a third field is provided on the first screen where recruiter U1 can input information generation instructions was previously shown, the location of this third field may be on a different screen from the first screen. Figure 10 is a modified example of the first screen displayed on the recruiter's terminal. In the first screen shown in Figure 10, a first field and a second field are provided, similar to the screen shown in Figure 6, but a third field is not provided. Even in this case, information regarding the correlation of candidate U2 with respect to mandatory requirements and preferred requirements can be generated based on the content entered in the first and second fields. In contrast, the third field may be provided on a screen such as the following. Figure 11 is a modified example of the second screen displayed on the recruiter's terminal. Figure 11 shows a configuration in which a third field is provided on the second screen where recruiter U1 can input information generation instructions. When recruiter U1 interacts with the screen shown in Figure 11, they can, for example, confirm the correlation information regarding the various generated requirements and then input the content of a predetermined information generation instruction into the third column. For example, after inputting a predetermined instruction into column C3, the generated content may be output to column C31 when button BT6 is pressed. By adopting such a screen layout, recruiter U1 can efficiently perform information generation operations based on the generated correlation information. Note that the location of the third column may be other than the location described here. For example, such a third column may be provided on a screen displayed when the second screen is displayed (e.g., a pop-up screen), and in this case as well, recruiter U1 can give various information generation instructions in conjunction with the evaluation of candidate U2. Furthermore, the above-described third column may be provided on screens displayed in various situations corresponding to recruiter U1's recruitment activities.

[0100] Furthermore, although the first and second columns were shown above in a configuration where they are displayed on the first screen, the first screen may also include columns that do not correspond to the first and second columns, but are capable of specifying requirements for recruitment activities. Figure 12 shows a modified example of the first screen displayed on a recruiter's terminal. In the example of the first screen shown in Figure 12, there are columns (columns C41 and C42) that specify "Requirement 1" and "Requirement 2," but the requirements corresponding to these columns are not distinguished as "mandatory requirements" or "preferred requirements." Even in such a case, by entering the required requirements into the columns that specify these requirements, information regarding the correlation of the recruitment candidate U2 can be generated. For convenience, the column for specifying requirements that are not distinguished in this way may be called the "fourth column." In addition, the recruiter U1 may enter text into such a "fourth column" that specifies whether it is a mandatory requirement or a preferred requirement, and the input of options (e.g., checkboxes, radio buttons, etc.) to specify whether the "fourth column" is a mandatory requirement or a preferred requirement may be accepted separately. Furthermore, two or more requirements may be entered within the "fourth column." In the first screen, one or more fourth columns may be provided, as shown in Figure 12. In such a case, the reception unit 112 may receive the requirements entered in one or more fourth columns and the registration information of the candidate U2 for the predetermined job posting. The generation unit 113 may input the received requirements and the registration information of the candidate U2 into the artificial intelligence module to generate correlation information of the candidate U2 for each requirement specified in one or more fourth columns. The display control unit 111 may display a second screen on the terminal of the recruiter U1, showing the generated correlation information of the candidate U2 for each requirement specified in one or more fourth columns. In this configuration, a third column may be provided within the first screen as needed. In this case as well, the generated content based on the information generation instruction may be displayed on the second screen. Furthermore, the number of columns in the fourth column may be increased or decreased according to predetermined operations by manipulating the object OBJ2, etc.

[0101] 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.

[0102] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. The information processing method comprises each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0103] The product may be provided in any of the following embodiments.

[0104] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, in the first display control step, the system causes a terminal of a recruiter conducting recruitment activities to display a first screen for inputting requirements related to the recruitment activities, wherein the first screen displays one or more first fields for identifying essential requirements for a given job posting, and one or more second fields for identifying desirable requirements for the given job posting, and in the first reception step, the system displays the one or more first fields and the one or more second fields An information processing system that receives requirements entered in two fields and registration information of candidates for the predetermined job posting; in the first generation step, inputs the received requirements and the registration information of the candidates into an artificial intelligence module to generate correlation information of the candidates for each requirement specified in the one or more first fields and the one or more second fields; and in the second display control step, displays a second screen on the recruiter's terminal showing the generated correlation information of the candidates for each requirement specified in the one or more first fields and the one or more second fields.

[0105] (2) An information processing system as described in (1) above, wherein in the first generation step, the system generates, as information relating to the correlation of the candidates to be hired, the degree to which they satisfy the essential requirements specified in the one or more first columns, and / or the degree to which they satisfy the desirable requirements specified in the one or more second columns.

[0106] (3) An information processing system as described in (2) above, wherein the first generation step further generates reasons that serve as the basis for the degree of satisfaction, and the second display control step further displays the generated reasons.

[0107] (4) An information processing system according to any one of (1) to (3) above, wherein the first screen is provided with a third field in addition to the one or more first fields and the one or more second fields into which information generation instructions can be entered by the recruiter, the first reception step further receives the information generation instructions entered in the third field, the second generation step generates a response corresponding to the information generation instructions by inputting at least the information generation instructions into an artificial intelligence module, and the second display control step further displays the response generated in the second generation step on the second screen.

[0108] (5) An information processing system as described in (4) above, wherein in the first reception step, an instruction to generate questions for the candidate is received as the information generation instruction, and in the second display control step, the generated questions for the candidate are displayed on the second screen as the answer.

[0109] (6) An information processing system according to any one of (1) to (5) above, wherein in the first memory management step, information relating to the correlation of the recruit candidates generated in the first generation step is stored in a predetermined memory area in association with the recruit candidates related to the registration information received in the first reception step, and in the first extraction step, recruit candidates who satisfy the search conditions are extracted from among the stored recruit candidates based on the search conditions relating to the essential requirements and / or welcome requirements set by the recruiter.

[0110] (7) An information processing system according to any one of (1) to (6) above, wherein in the third generation step, the system generates an overall evaluation of the candidate by inputting at least the requirements received in the first reception step and the registration information of the candidate into an artificial intelligence module.

[0111] (8) An information processing system as described in (7) above, wherein in the second reception step, the system receives from the recruiter the setting of weights for each requirement specified in the one or more second columns, and in the third generation step, the system generates the overall evaluation based on the set weights.

[0112] (9) An information processing system as described in (7) or (8) above, wherein in the second memory management step, the overall evaluation generated in the third generation step is stored in a predetermined memory area in association with the candidate for employment related to the registration information received in the first reception step, and in the second extraction step, a candidate for employment that satisfies the search conditions is extracted from among the stored candidates for employment based on the search conditions for the overall evaluation set by the recruiter.

[0113] (10) An information processing system according to any one of (1) to (9) above, wherein in the second reception step, the recruiter receives the setting of weights for each requirement specified in the one or more second columns, and on the second screen, the information relating to the correlation for each requirement specified in the one or more second columns is controlled to be displayed in different ways according to the content of the set weights.

[0114] (11) An information processing system according to any one of (1) to (10) above, wherein in the third reception step, the system receives the designation of an object containing information about a predetermined job posting; in the third extraction step, the system extracts from the content of the designated object the content of the predetermined job posting that is a mandatory requirement for the predetermined job posting and the content of the predetermined job posting that is a welcome requirement for the predetermined job posting; and in the first display control step, the system transfers the extracted content to the one or more first columns and / or the one or more second columns to display the first screen.

[0115] (12) An information processing system according to any one of (1) to (11) above, wherein in the first reception step, registration information of multiple candidates for employment is received as registration information of the candidates for employment, and in the first generation step, correlation information for each of the multiple candidates for employment is generated all at once.

[0116] (13) An information processing system as described in (12) above, wherein in the second display control step, the second screen is configured to display correlation information for each of the multiple candidates, and the second screen is configured to allow the recruiter to switch to display correlation information for each candidate.

[0117] (14) An information processing system according to any one of (1) to (13) above, comprising a server device having the processor and a terminal that can access the server device.

[0118] (15) An information processing method comprising each step performed by the information processing system described in any one of (1) to (14) above.

[0119] (16) A program that causes a computer to perform each step of the information processing system described in any one of (1) through (14) above. Of course, this is not always the case.

[0120] 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]

[0121] 1: Information Processing System 2: Communication lines 10: Server device 11: Control Unit 12: Storage section 13: Communications Department 14: Communications bus 20: User terminal 21: Control Unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 110: Registration Department 111: Display Control Unit 112: Reception Department 113 :Generation part 114: Memory management department 115:Extraction part 116: Artificial Intelligence Department 210: Display Control Unit 211: Operation Reception Section BT1~BT6: Buttons C11, C12, C21, C22, C111, C211, C3, C31, C41, C42: Column CB: Checkbox EV1~EV3: Evaluation OBJ1, OBJ2: Objects RS:Answer Rg1: area TB: Tab U1: Recruitment agent U2: Candidate

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the first display control step, a first screen for inputting requirements related to the recruitment activity is displayed on the terminal of the recruiter conducting the recruitment activity. Here, the first screen displays one or more first fields for identifying the essential requirements for a given job posting, and one or more second fields for identifying the desirable requirements for the given job posting. In the first application step, the requirements entered as natural language in the one or more first fields and the one or more second fields, and the registration information of the candidate for employment for the specified job posting are received. In the first generation step, the received requirements and the registration information of the candidate are input into the artificial intelligence module to generate correlation information of the candidate for each requirement specified in the one or more first columns and the one or more second columns. Here, the information regarding the correlation of the candidates includes sentences that express the correlation between each requirement and the registration information of the candidates. An information processing system that, in the second display control step, causes the terminal of the recruiter to display a second screen showing the generated text as information relating to the correlation of the recruit candidates for each requirement specified in the one or more first columns and the one or more second columns.

2. In the information processing system described in claim 1, An information processing system that, in the first generation step, generates, in addition to the text, information relating to the correlation of the job candidates, including the degree to which they satisfy the essential requirements specified in the one or more first columns, and / or the degree to which they satisfy the desirable requirements specified in the one or more second columns.

3. In the information processing system described in claim 2, In the first generation step, the reason that forms the basis of the degree of satisfaction is generated as the text, The second display control step involves an information processing system that displays the reason for generation in relation to the degree of satisfaction.

4. In the information processing system described in claim 1, The first screen is provided with a third field, separate from the one or more first fields and the one or more second fields, in which the recruiter can input information generation instructions. In the first reception step, the information generation instruction entered in the third field is further received, In the second generation step, at least the information generation instruction is input to the artificial intelligence module to generate a response corresponding to the information generation instruction. An information processing system that, in the second display control step, further displays the answer generated in the second generation step on the second screen.

5. In the information processing system described in claim 4, In the first reception step, the information generation instruction is an instruction to generate questions for the candidate for employment. In the second display control step, the information processing system displays the generated questions for the candidate on the second screen as the answers.

6. In the information processing system described in claim 1, In the first memory management step, the correlation information of the recruit candidates generated in the first generation step is stored in a predetermined memory area in association with the recruit candidates related to the registration information received in the first reception step. In the first extraction step, an information processing system extracts candidates who satisfy the search criteria from among a plurality of stored candidates, based on the search criteria for the essential and / or preferred requirements set by the recruiting agent.

7. In the information processing system described in claim 1, In the third generation step, an information processing system generates an overall evaluation of the candidate by inputting at least the requirements received in the first reception step and the registration information of the candidate into an artificial intelligence module.

8. In the information processing system described in claim 7, In the second application step, the recruiter is asked to set the weights for each requirement specified in the second column (one or more) above. The third generation step involves an information processing system that generates the overall evaluation based on the set weightings.

9. In the information processing system described in claim 7, In the second memory management step, the overall evaluation generated in the third generation step is stored in a predetermined memory area in association with the candidate for employment related to the registration information received in the first reception step. In the second extraction step, an information processing system extracts candidates who satisfy the search criteria from among a plurality of stored candidates, based on the search criteria for the overall evaluation set by the recruiter.

10. In the information processing system described in claim 1, In the second application step, the recruiter is asked to set the weights for each requirement specified in the second column (one or more) above. An information processing system in which, on the second screen, the information relating to the correlation for each of the requirements specified in the one or more second columns is controlled to be displayed in different ways according to the set weighting.

11. In the information processing system described in claim 1, In the third application step, the designation of the target containing information about the aforementioned specified job posting is accepted. In the third extraction step, the content that constitutes a mandatory requirement for the specified job posting and the content that constitutes a desirable requirement for the specified job posting are extracted from the specified target content. An information processing system that, in the first display control step, transfers the extracted content to the one or more first columns and / or the one or more second columns to display the first screen.

12. In the information processing system described in claim 1, In the first reception step, the registration information of multiple candidates is received as the registration information of the candidate. The first generation step involves an information processing system that generates correlation information for each of the multiple candidates for employment in a single batch.

13. In the information processing system according to claim 12, In the second display control step, the second screen displays information regarding the correlation between each of the multiple candidates, The second screen is configured to allow the recruiter to switch to displaying information regarding the correlation for each of the recruit candidates, as part of an information processing system.

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

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

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

Images