Programs, information processing devices, methods, and systems

Abstract

The goal is to achieve more accurate job matching that reflects actual needs. [Solution] A program according to one aspect of the present disclosure is a program for operating a computer comprising a processor and memory, wherein the program causes the processor to perform the following steps: acquire job information to be matched with job candidates; input the acquired job information into a generating AI and have it classify and extract multiple requirements contained in the job information into multiple categories based on the degree of the requirements; input instructions to the generating AI to calculate a matching score based on the extracted multiple requirements, candidate information of job candidates, and predetermined priorities between the categories, and have it calculate a matching score for job candidates; and present the calculated matching score to the user's terminal device.

Description

Technical Field

[0001] This disclosure relates to programs, information processing apparatuses, methods, and systems.

Background Art

[0002] Improving the efficiency of personnel recruitment, particularly reducing the burden on the staff in document screening, is an important issue.

[0003] In recent years, to address this issue, a recruitment system based on keyword matching has been conventionally used.

[0004] Patent Document 1 discloses a technique for extracting skills and the like from job offers using generative AI and evaluating and recommending candidates.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, in the conventional technology as described in Patent Document 1, requirements such as skills and experience included in job offers were uniformly extracted and evaluated. Therefore, there was a limit in achieving matching accuracy that reflected the intentions of the recruitment staff.

[0007] An object of this disclosure is to be made in view of the problems of the conventional technology as described above, and to realize job matching that is more in line with the actual situation.

Means for Solving the Problems

[0008] To solve the above problems, a program according to one aspect of the present disclosure is a program for operating a computer comprising a processor and memory, wherein the program causes the processor to perform the following steps: acquire job information to be matched with job candidates; input the acquired job information into a generating AI and have it classify and extract multiple requirements contained in the job information into multiple categories based on the degree of the requirements; input instructions to the generating AI to calculate a matching score based on the extracted multiple requirements, candidate information of job candidates, and predetermined priorities between the categories, and have it calculate a matching score for job candidates; and present the calculated matching score to the user's terminal device. [Effects of the Invention]

[0009] This disclosure will enable more accurate job matching that reflects actual circumstances. [Brief explanation of the drawing]

[0010] [Figure 1] This block diagram shows the overall configuration of the recruitment matching system according to this embodiment. [Figure 2] This block diagram shows a functional configuration example of a terminal device according to this embodiment. [Figure 3] This block diagram shows an example of the functional configuration of the server according to this embodiment. [Figure 4] This figure shows an example of the data structure of a job postings table. [Figure 5] This figure shows an example of the data structure of a requirements table. [Figure 6] This figure shows an example of the data structure of a candidate table. [Figure 7] This figure shows an example of the data structure of a score table. [Figure 8] This figure shows an example of the data structure of the evaluator character table. [Figure 9] This flowchart shows an example of the server processing flow in this embodiment. [Figure 10]This is a diagram showing an example of a screen for listing candidate matching results. [Figure 11] This is a diagram showing an example of a screen for setting an evaluator character. [Figure 12] This is a diagram showing an example of a screen for a candidate evaluation report (technical perspective). [Figure 13] This is a diagram showing an example of a screen for a candidate evaluation report (product perspective). [Figure 14] This is a block diagram showing the basic hardware configuration of a computer.

Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for describing the embodiments, the same reference numerals are assigned to common components, and repeated descriptions are omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure. Also, each figure is a schematic diagram and is not necessarily drawn precisely.

[0012] Also, in the following description, a "processor" is one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0013] Also, at least one processor may be a processor in a broad sense such as a hardware circuit (for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing.

[0014] In the following description, expressions such as "xxx table" may be used to describe information from which an output is obtained for an input. This information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, "xxx table" may be referred to as "xxx information".

[0015] In the following description, the configuration of each table is an example. One table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0016] In the following description, the "program" may be used as the subject to describe a process. Since the program is executed by a processor to perform a defined process while appropriately using a storage unit and / or an interface unit, etc., the subject of the process may be the processor (or a device such as a controller having the processor).

[0017] The program may be installed in a device such as a computer, or may be in, for example, a program distribution server or a computer-readable (e.g., non-temporary) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0018] In the following description, an identification number is used as identification information for various objects, but other types of identification information (e.g., an identifier including letters and symbols) may be adopted.

[0019] In the following description, when describing elements of the same type without distinction, reference signs (or common signs among the reference signs) are used, and when describing elements of the same type by distinction, the identification numbers (or reference signs) of the elements may be used.

[0020] Furthermore, in the following explanation, only control lines and information lines deemed necessary for the explanation are shown, and not all control lines and information lines in the product are necessarily shown. All components may be interconnected.

[0021] Each information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by this hardware configuration will be described later for each of the terminal devices 10 and server 20, respectively, and any explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0022] (First Embodiment) <1. Overview> The recruitment matching system 1 utilizes generative AI technology to provide a document screening support service that accurately matches job postings with candidates. In this service, the generative AI internally maintains an extraction logic that classifies multiple requirements included in job postings into multiple categories based on the degree of those requirements (e.g., required, preferred), and a scoring logic that calculates a candidate matching score based on the priority between categories, and autonomously controls the document screening process based on these. Note that "required" and "preferred" here are merely examples; it is also possible to create intermediate categories such as "semi-required" or classify into three or more categories depending on the degree of the requirements. Server 20 is primarily responsible for relaying job postings and candidate information entered by recruiters to the generative AI and presenting the calculated matching scores and other evaluation results to the recruiters. The document screening process proceeds through a "requirements extraction phase" in which the AI ​​analyzes the job postings and extracts requirements by category, a "scoring phase" in which a score is calculated based on the extracted requirements and candidate information, and a "results presentation phase" in which the calculation results are presented to the user. The generated evaluation results can also be linked with the applicant tracking system (ATS) 40. Large-scale language models (LLMs) and similar technologies can be used for generative AI.

[0023] <2. Overall System Configuration> Figure 1 is a block diagram showing an example of the overall configuration of the recruitment matching system 1 related to this disclosure. In this disclosure, we will explain using as an example a case in which the recruitment matching system is introduced within a corporate organization, and the recruitment personnel of that organization use the system as users, and the results are used to improve the efficiency and accuracy of recruitment activities.

[0024] As shown in Figure 1, System 1 of this embodiment consists of, for example, a terminal device 10, a server 20, and a generation AI system 30. System 1 is communicated with the Applicant Tracking System (ATS) 40 via the network 80.

[0025] Figure 1 shows an example where System 1 includes one terminal device 10, for the sake of illustration simplification. However, in reality, System 1 may include multiple terminal devices 10 for use by multiple recruiters.

[0026] In Figure 1, System 1 is shown as an example that includes one Server 20, but for example, a collection of multiple devices may be considered as one Server 20. The way in which the multiple functions required to realize Server 20 are distributed to one or more hardware can be appropriately determined according to the processing capacity of each hardware and / or the specifications required for Server 20.

[0027] In Figure 1, an example is shown where the generative AI system 30 is an external cloud service or the like, independent of the server 20. However, the server 20 may also include the functions of the generative AI system 30. In other words, the server 20 may store generative AI models, such as large-scale language models (LLMs), that are included in the generative AI system 30.

[0028] In Figure 1, the Applicant Tracking System (ATS) 40 may be integrated as an existing system located outside of System 1, or it may be integrated as part of the functions of Server 20.

[0029] Terminal device 10 is, for example, an information processing device operated by a recruiter. The recruiter accesses the recruitment matching service via a web browser or the like installed on terminal device 10 to input job information and view the results of matching with candidates.

[0030] Server 20 is, for example, an information processing device for managing and providing a recruitment matching service, and is implemented by a computer connected to network 80.

[0031] Server 20 generates prompts for input to the generating AI system 30 based on the job information (data) received from the terminal device 10. By inputting the generated prompts into the generating AI system 30, a classified and extracted list of requirements is obtained. Furthermore, Server 20 inputs the obtained list of requirements and the candidate information held in the memory unit into the generating AI system 30, along with a prompt instructing score calculation, and performs processing such as obtaining the calculated matching score. Note that the pattern of obtaining job information is not limited to the above. For example, Terminal device 10 may accept input of information (such as a URL) to identify the storage location of job information in the Applicant Tracking System (ATS) 40, and obtain job information directly from the external system without going through Server 20. In that case, Terminal device 10 can become the main entity that processes the input of the obtained job information into the generating AI system 30.

[0032] The storage unit 202 of the server 20 stores data and programs used to provide the recruitment matching service. In particular, the storage unit 202 stores "instruction statements" used to generate prompts, which will be described later. The storage unit 202 also stores job information, various tables that store requirement lists and calculated scores generated by the generation AI system 30, and a candidate database that stores candidate resumes and other documents.

[0033] The generative AI system 30 is, for example, a cloud server having a large-scale language model (LLM). In this specification, generative AI is a natural language model that generates desired documents, and a large-scale language model (LLM) is one example of such a model.

[0034] LLM (Language Modeling) is a single-modal natural language model built by training on large amounts of text data, and is used for many NLG (Natural Language Generation) tasks, such as generating responses to specific questions, automatically generating sentences, and summarizing text. LLM is an example of a generative AI model. Examples of LLMs include the following: • OpenAI: GPT-4 Google: Gemini 1.5 Flash Anthropic:Claude 3.5 Sonnet

[0035] When the generation AI system 30 receives a prompt from the server 20, it executes a predetermined process based on the instruction text and data contained in the prompt and outputs the result to the server 20. In this embodiment, requirements are extracted from job information and categorized to generate a list of requirements.

[0036] In this specification, a prompt consists of an "instruction statement" that causes the generating AI to generate a predetermined output, and "data" that is input to the generating AI. The instruction statement is static text that describes the instructions for the generating AI to generate a predetermined output. The data is information that is dynamically incorporated into the prompt in response to user input (queries), and in this embodiment, it is the original text of the job posting entered by the recruiter.

[0037] The instructions included in the prompts generated by server 20 are designed to include multiple elements, such as role instructions, processing instructions, and output format instructions, so that the generating AI system 30 can produce output with the intended structure.

[0038] Role instructions include text that specifies the role (position) the generating AI will play when performing its tasks. For example, an instruction might read, "You are a highly skilled recruiter. Deeply understand the job description text and accurately identify the required skills, experience, qualifications, and other requirements for applicants."

[0039] Processing instructions include text that tells the generating AI what processing it should perform. For example, an instruction might be: "Analyze the following job posting text and list all the requirements required of the candidate. Then, determine and classify each requirement as either an 'essential requirement' that is absolutely necessary for hiring, or a 'desirable requirement' that is desirable."

[0040] The prompt includes a placeholder within the instruction statement where the job information (data) obtained from the recruiter will be included, for example, "The following text will be analyzed: {job information text}". Server 20 dynamically generates the prompt by replacing this placeholder with the actual job information text.

[0041] The output format instructions include instructions regarding the output format (template), structure, or both of the results generated by the generating AI.

[0042] For example, the output format instructions in this embodiment include instructions such as, "The response must be in JSON format and include a list of requirements. Each requirement should be an object with two keys: 'requirement_text' (the string of the extracted requirement) and 'category' (the string 'Required' or 'Welcome')." Such strict instructions enable the server 20 to mechanically interpret the analysis results of the generated AI and accurately link them to the subsequent scoring process.

[0043] The Applicant Tracking System (ATS) 40 is an existing system that manages the entire recruitment process of a company, centrally managing candidate information, selection status, interview records, etc. Server 20 may have the function of transmitting calculated matching scores, etc., to the ATS 40 and recording them in association with the information of the relevant candidate. This allows recruiters to make comprehensive selection decisions while checking the objective evaluation results from this system on the ATS they are familiar with.

[0044] Each information processing device or system, such as the terminal device 10, server 20, generation AI system 30, and applicant tracking system (ATS) 40, may be composed of a computer 90 equipped with a processing unit and a memory device. The basic hardware configuration of the computer 90 and the basic functional configuration of the computer 90 realized by said basic hardware configuration will be described later. Note that explanations of each component that overlap with the basic hardware configuration of the computer 90 and the basic functional configuration of the computer will be omitted. The recruitment matching system 1 provides a document screening support service that uses generation AI technology to match job information with candidates with high accuracy. In this service, the generation AI system 30 internally holds an extraction logic that classifies multiple requirements included in job information into multiple categories based on the degree of those requirements (e.g., required, welcome), and a scoring logic that calculates a candidate matching score based on the priority between categories, and autonomously controls the document screening process based on these. The server 20 is mainly responsible for relaying job information and candidate information entered by recruiters to the generation AI system 30 and presenting evaluation results such as the calculated matching score to the recruiters.

[0045] <3. Configuration of terminal equipment> Figure 2 is a block diagram showing an example of the functional configuration of the terminal device 10. Each functional unit, such as the control unit 190 and the storage unit 180 shown in Figure 2, is realized through the cooperation of hardware resources such as the processor 19, memory 15, and storage 16 shown in Figure 1. As shown in Figure 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, and optionally an audio processing unit 17, a microphone 171, a speaker 172, a camera 160, a location information sensor 150, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus. In this embodiment, the terminal device 10 primarily provides an interface for recruiters, who are users, to use the recruitment matching service.

[0046] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and sends it to an external source (for example, the server 20). The communication unit 120 performs reception processing on the signal received from the external source and outputs it to the control unit 190. As a result, the job information or various instructions entered by the recruiter are sent to the server 20, and the candidate matching score or evaluation comments are received by the terminal device 10 from the server 20.

[0047] The input device 13 is a device for a user (recruiter) operating the terminal device 10 to input instructions or information. The input device 13 can be implemented, for example, by a touch-sensitive device 131 on which instructions are input by touching the operating surface. If the terminal device 10 is a PC, the input device 13 may be implemented by a keyboard, mouse, etc. The input device 13 converts the instructions input by the user (for example, text input of job information, setting of evaluator character, request to execute matching, etc.) into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that accepts electrical signals input from an external input device.

[0048] The output device 14 is a device for presenting information to the user (recruiter) operating the terminal device 10. The output device 14 is implemented by, for example, a display 141. The display 141 displays data (for example, a candidate list, a matching score for each candidate, comments that formed the basis of the evaluation, recommendation information for other job openings, etc.) in accordance with the control of the control unit 190. The display 141 is implemented by, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0049] The audio processing unit 17, microphone 171, and speaker 172 are components related to audio input and output. While audio functionality is not essential in the matching service adopted by this embodiment, it can be used if extended functions such as a text-to-speech function for improved accessibility or operation via voice commands are envisioned.

[0050] Camera 160 is a device that receives light using a photodetector and outputs it as a shooting signal. In the recruitment matching service of this embodiment, the camera function is not essential, but it can be used, for example, to register facial photos in candidate information or to enable web interview functions linked to the system.

[0051] The location information sensor 150 is a sensor that detects the location of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. In the employment matching service of this embodiment, the location information sensor is not essential, but it can be used, for example, when managing job postings related to specific businesses or regions.

[0052] The storage unit 180 is implemented, for example, by memory and storage, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, personnel information 181, a web browser for using the recruitment matching service, or configuration information.

[0053] Personnel information 181 includes, for example, information about the user (recruitment officer) using terminal device 10. User information includes, for example, the user's name, department, contact information, usage history of the recruitment matching service, and templates of evaluator characters created.

[0054] The control unit 190 is realized when the processor reads a program stored in the memory unit 180 and executes instructions contained in the program. The control unit 190 controls the operation of the terminal device 10. By operating according to the program, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193.

[0055] The operation reception unit 191 processes instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 can receive information related to the recruitment matching service, such as the text of job postings, the setting of evaluation criteria and weightings for evaluator characters, and instructions to execute matching, which are input from a keyboard, mouse, etc.

[0056] Furthermore, the operation reception unit 191 may, as an extended function, accept voice commands input from the microphone 171. Specifically, for example, the operation reception unit 191 receives voice signals input from the microphone 171 and converted into digital signals by the voice processing unit 17. This may enable recruiters to input job information or control the display of matching results using voice commands.

[0057] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with external devices such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 sends job information entered by the user (recruiter), evaluator character setting information, and various operation instructions to the server 20. The transmitting / receiving unit 192 also receives information provided by the server 20 (candidate matching score, evaluation comments, recommended job information, etc.).

[0058] The presentation control unit 193 controls the output device 14 in order to present the information provided by the server 20 to the user (recruiter). Specifically, for example, the presentation control unit 193 displays various information related to the recruitment matching service (matching result list screen, detailed evaluation result screen, etc.) transmitted from the server 20 on the display 141.

[0059] <4. Server Configuration> Figure 3 is a block diagram showing an example of the functional configuration of the server 20 shown in Figure 1. Each functional unit, such as the control unit 203 and the storage unit 202 shown in Figure 3, is realized through the cooperation of hardware resources such as the processor 29, memory 25, and storage 26 shown in Figure 1. As shown in Figure 3, the server 20 performs the functions of the communication unit 201, the storage unit 202, and the control unit 203.

[0060] The communication unit 201 performs processing to enable the server 20 to communicate with external devices, such as the terminal device 10, the generation AI system 30, or the applicant tracking system (ATS) 40.

[0061] The memory unit 202 is implemented by memory 25 and storage 26 and stores data and programs used by the server 20 to provide the recruitment matching service. The programs include application programs for providing the recruitment matching service. The memory unit 202 also stores, for example, a job posting table 2021, a requirements table 2022, a candidate table 2023, and a score table 2024. Furthermore, it may store an evaluator character table 2025 used in extended functions.

[0062] The Job Listings Table 2021 stores job information entered by recruiters. Specifically, each record is uniquely identified by a Job ID and includes information such as the job name and the original text of the job posting, which is used as the basis for analysis by the AI ​​generator.

[0063] The requirements table 2022 stores, for each job posting, the text of the requirements extracted and classified by the generating AI system 30, along with its category ("Required" or "Welcome").

[0064] The candidate table 2023, which makes up the candidate database, stores information about the candidates being evaluated. Specifically, each record is uniquely identified by a candidate ID and includes information such as the candidate's name and text data from their resume, which is referenced when calculating their score.

[0065] The Score Table 2024 stores the calculated matching score for each specific job and candidate combination. In addition to the score, it may also store information that formed the basis of the evaluation (e.g., a list of fulfilled mandatory and desirable requirements, comments from the evaluator character, etc.).

[0066] The control unit 203 is implemented when the processor reads a program stored in the memory unit 202 and executes the instructions contained in that program. The control unit 203 controls the operation of the server 20. By operating according to the loaded program, the control unit 203 can perform the functions of a receive control module 2031, a transmit control module 2032, a prompt generation module 2033, a score calculation module 2034, and an information presentation module 2035.

[0067] The receiving control module 2031 controls the process by which the server 20 receives signals from external devices according to a communication protocol. For example, it receives operational information such as job posting text and matching execution instructions from the terminal device 10. It also receives a classified requirements list (e.g., in JSON format) output from the generation AI system 30. The received information is passed to other relevant modules.

[0068] The transmission control module 2032 controls the process by which the server 20 transmits signals to external devices according to a communication protocol. For example, it performs processes such as transmitting prompts generated by the prompt generation module 2033 to the generation AI system 30, transmitting evaluation results such as matching scores to the terminal device 10 based on instructions from the information presentation module 2035, and transmitting evaluation information to the applicant tracking system (ATS) 40.

[0069] The prompt generation module 2033 is responsible for generating prompts to be input to the generation AI system 30. Specifically, it generates prompts by combining job information (data) received from the terminal device 10 via the reception control module 2031 with instruction sentences pre-stored in the storage unit 202. The generated prompts are input to the generation AI system 30 via the transmission control module 2032. Alternatively, in another configuration, the prompt generation module 2033 of the server 20 may generate the instruction sentences, which are the main part of the prompt, and then the terminal device 10 may directly acquire job information from the applicant tracking system (ATS) 40 based on instructions from the server 20. In that case, the terminal device 10 is responsible for inputting the acquired job information to the generation AI system 30. Note that the terminal device 10 may have some or all of the functions performed by the prompt generation module 2033.

[0070] The score calculation module 2034 manages the core evaluation process of this system. Specifically, it is responsible for passing the requirements list obtained from the generation AI system 30 via the receiving control module 2031 and the candidate information obtained from the candidate database in the memory unit 202 to the prompt generation module 2033. The prompt generation module 2033 generates a new prompt that includes this information and an instruction statement that instructs score calculation. This instruction statement instructs the generation AI to calculate the score considering the priority defined between the requirement categories. Specifically, it includes instructions to apply a higher weighting coefficient to the degree of fulfillment of mandatory requirements and a lower weighting coefficient to the degree of fulfillment of welcome requirements to calculate the overall score. When this prompt is sent to the generation AI system 30, the matching score is calculated. Information regarding the calculated score and the basis for the evaluation is received via the receiving control module 2031 and passed to the information presentation module 2035.

[0071] The information presentation module 2035 processes information such as matching scores and evaluation criteria received from the score calculation module 2034, formats it into a format suitable for the screen of the terminal device 10 used by the user, the recruiter, and transmits and presents it to the terminal device 10 via the transmission control module 2032.

[0072] <5. Data Structure> The main data structures used in the matching system 1 adopted in this embodiment will be explained with reference to Figures 4 to 8. Note that the data structures described here are examples, and data not listed is not excluded. Furthermore, each table is a logical unit and can be physically implemented by being divided into or merged into multiple tables.

[0073] Figure 4 shows an example of the data structure of the job posting table 2021 used in this embodiment. The job posting table 2021 includes items such as job ID and job information text. This table is intended to store job information entered by recruiters. The item "Job ID" stores an identifier to uniquely identify each job posting. The item "Job Information Text" stores the text data of the job posting itself, which is the target of analysis by the generating AI. Records in this table are generated when the server 20 receives job information from the terminal device 10 in step S11 of the processing flow (Figure 9) described later.

[0074] Figure 5 shows an example of the data structure of the requirements table 2022 used in this embodiment. The requirements table 2022 includes items such as job ID, requirement text, and requirement type. This table is intended to store individual requirements extracted and classified from job information by the generation AI. The item "Job ID" is an external key that indicates which job the requirement is associated with. The item "Requirement Text" stores the specific content of the extracted requirement (e.g., "3 years or more of development experience using Java"). The item "Requirement Type" stores the category of the requirement, such as whether it is "required" or "welcome". Records in this table are generated in step S12 of the processing flow described later, when the server 20 receives the list of requirements extracted and classified from the generation AI system 30, and are linked to the corresponding job ID.

[0075] Figure 6 shows an example of the data structure of the candidate table 2023 used in this embodiment. The candidate table 2023 includes items such as candidate ID and resume. The purpose of this table is to store information on candidates to be evaluated. The item "Candidate ID" stores an identifier to uniquely identify each candidate. The item "Resume" stores the text data of the resume, which is used by the generating AI to analyze the candidate's skills and experience.

[0076] Figure 7 shows an example of the data structure of the score table 2024 used in this embodiment. The score table 2024 includes items such as candidate ID, job ID, and overall score. This table is intended to store evaluation results for specific job and candidate combinations. The items "Candidate ID" and "Job ID" can function as a composite key to identify which candidate and which job match the result. The item "Overall Score" stores the final matching score calculated based on predetermined logic. This table may also store additional information such as a list of fulfillment requirements that formed the basis of the score, and comments from evaluator characters. Records in this table are generated and updated in step S13 of the processing flow described later, when the server 20 receives the matching score calculated from the generation AI system 30, and are linked to the corresponding job ID and candidate ID.

[0077] Figure 8 shows an example of the data structure of the evaluator character table 2025 used in this embodiment. The evaluator character table 2025 includes items such as character ID, character name, position, evaluation style, and weighting settings. This table is intended to store information for the personification and management of evaluation axes for each job posting, which is an extended function of this system. The item "Character ID" uniquely identifies each evaluator character. The items "Character Name" and "Position" store the display name that the user uses to identify the character. The item "Evaluation Style" stores the qualitative direction of evaluation, such as "emphasis on technical skills," in tag format or similar. The item "Weighting Settings" stores the weighting values ​​for multiple evaluation items, such as "depth of technical skills" and "teamwork," for example in JSON format.

[0078] <6. Operation> The operation of System 1 in this embodiment will now be described. Server 20 primarily executes the basic flow according to the flowchart shown in Figure 9, but may also execute additional processes related to arbitrary flows or modifications described later.

[0079] (Basic Flow) First, let's explain the basic operation.

[0080] In step S11 (job information reception step), the server 20's reception control module 2031 receives data, including the original text of job information to be matched with job candidates, from a terminal device 10 operated by a recruiter via a web browser or the like.

[0081] In step S12 (prompt generation step for requirements extraction), the prompt generation module 2033 of the server 20 combines the original text of the received job information with templates of instruction statements (role instructions, processing instructions, output format instructions, etc.) that are pre-stored in the memory unit 202, and generates a prompt for the generation AI system 30 to execute the requirements extraction process.

[0082] In step S13 (requirements list receiving step), the transmission control module 2032 of the server 20 sends the generated prompt to the generation AI system 30. Subsequently, the receiving control module 2031 receives a requirements list, which is structured data (e.g., in JSON format) in which multiple requirements are categorized (e.g., "required", "welcome"), and the generation AI system 30 analyzes the job information and sends back. In this specification, the "requirements list" corresponds to the "multiple extracted requirements" that have been materialized as data within the server for subsequent processing.

[0083] In step S14 (Requirements List Analysis and Saving Step), the score calculation module 2034 of server 20 analyzes the received structured data requirements list. Specifically, it parses data in JSON format, extracts individual requirement texts and their categories ("Required" or "Welcome"), links them to the corresponding job IDs, and registers them as records in the requirements table 2022 of the storage unit 202.

[0084] After step S14 is completed and the requirements list is saved to the requirements table 2022, the subsequent steps S15 and beyond do not necessarily have to be executed consecutively. For example, they can be executed at any time, such as when a new candidate applies or when instructed to do so by the hiring manager.

[0085] In step S15 (step for acquiring information for score calculation), the score calculation module 2034 of the server 20 identifies the candidate for whom the matching score is to be calculated, and reads the requirements list saved in step S14 and candidate information such as the resume of the candidate stored in the candidate table 2023 from the storage unit 202.

[0086] In step S16 (Matching Score Calculation and Reception Step), the prompt generation module 2033 of the server 20 generates a new prompt for score calculation, which includes the read requirement list and candidate information, and scoring logic (e.g., an instruction to prioritize mandatory requirements). An example prompt is: "Based on the following requirement list and candidate information, calculate this candidate's matching score on a scale of 0 to 100, using the logic that mandatory requirements take precedence over preferred requirements." The prompt generation module 2033 may also generate prompts that specify more concrete weighting values, such as: "Calculate the overall score by applying a weight of 1.5 to the degree of satisfaction of mandatory requirements and a weight of 1.0 to the degree of satisfaction of preferred requirements." Furthermore, it is also possible to generate prompts that specify the contribution to the score itself, such as: "Calculate the matching score so that the satisfaction of mandatory requirements accounts for 70% of the total score and the satisfaction of preferred requirements accounts for 30% of the total score." Next, the transmission control module 2032 sends the prompt to the generation AI system 30, and the reception control module 2031 receives the matching score calculated by the generation AI system 30.

[0087] In step S17 (matching score presentation step), the information presentation module 2035 of the server 20 formats the received matching score into data in a display format suitable for the screen layout of the terminal device 10. Then, the transmission control module 2032 transmits the formatted data to the terminal device 10 used by the recruiter and displays it on the screen.

[0088] (Optional flow of the first embodiment: Evaluator character setting) The server 20's receiving control module 2031 may, before calculating the matching score in step S16, perform a step of receiving input from the user, responding to the job information, and setting up an evaluator character with weighted evaluation criteria to be the entity that evaluates candidates. In this case, in step S16, the prompt generation module 2033 generates a prompt instructing the generating AI to calculate the matching score considering the weighted evaluation criteria of the set evaluator character, and causes the generating AI to calculate the matching score. An example prompt is: "You are an evaluator with the role of 'Senior Engineer who values ​​technical depth'. Based on the requirements list and candidate information below, calculate this candidate's matching score on a scale of 0 to 100, considering the set weights (evaluation direction: 38%, project results: 34%, teamwork: 29%)."

[0089] Furthermore, in the step of setting the evaluator character, the prompt generation module 2033 and transmission control module 2032 of server 20 cause the generated AI to analyze the acquired job information and generate the basic settings for a recommended evaluator character. The receiving control module 2031 then receives the results, and the information presentation module 2035 may propose them to the user. An example prompt is: "You are an experienced recruitment consultant. Analyze the following job information and generate a proposal in JSON format for the 'job title,' 'evaluation style,' and 'weighting of evaluation items' of the evaluator character best suited to evaluating candidates for this position."

[0090] If the evaluator character also has personality and speaking style, the prompt generation module 2033 of server 20 may further perform the step of generating a prompt for generating a comment that shows the basis for the evaluation, which will be presented along with the matching score, and sending this to the generation AI for generation by the transmission control module 2032. An example prompt is: "You are an evaluator with a 'logical' personality and who speaks using 'polite language (desu / masu style).' Based on the calculated matching score (95 points) and the candidate information below, please generate a comment that concisely explains the basis for your evaluation."

[0091] If the user sets multiple evaluator characters, the server 20 may instruct the generating AI in step S16 to calculate matching scores from the perspective of each of the multiple evaluator characters, and the information presentation module 2035 may instruct the multiple calculated matching scores to be presented in a comparative manner in step S17. An example prompt is: "For the following candidate information, please calculate matching scores from the perspectives of two evaluators, a 'technical perspective character' and a 'product perspective character,' based on their respective evaluation criteria. Please provide the response in JSON format, with each character's name and the score calculated by that character as a set."

[0092] <7. Screen example> Figures 10 to 13 illustrate examples of the screen of the display 141 of the terminal device 10 in this disclosure.

[0093] Figure 10 shows an example of a screen that displays a list of matching results for a specific job opening with multiple candidates. Through this screen, recruiters can efficiently identify individuals who should be prioritized for review from among a large number of candidates.

[0094] Area 1401 is the area for displaying the candidate list. Each row displays basic information such as the candidate's name and application date, as well as a matching score. This matching score is calculated by Server 20 based on the criteria of the configured evaluator character and a logic that prioritizes the degree to which the essential requirements are met. A function to sort by score from highest to lowest may be provided. In addition, recruiters can select any candidate on the list to transition to a screen showing a detailed evaluation report for that candidate.

[0095] If no evaluator character is set, the detailed evaluation report screen accessed from the candidate list screen in Figure 10 may display a screen configuration similar to those shown in Figures 12 and 13, but with the information related to the evaluator character (such as the direction of evaluation and scores for each character) omitted.

[0096] Figure 11 shows an example of a screen where a user (a recruiter) sets the evaluator character that will be responsible for evaluating candidates for each job posting. Through this screen, recruiters can reflect different evaluation criteria and weightings in the system for each job posting.

[0097] Area 1411 is where you set the basic information of the evaluator character. This area includes fields such as "Name" and "Position" to identify the character. It is also possible to set "Personality," "Speaking Style," or both, which affect the text of the comments displayed with the evaluation results.

[0098] Area 1412 is where you set the "evaluation style," which defines the direction of evaluation. Recruiters can input or select an evaluation style, for example, "We value technical depth, especially algorithm design ability and the ability to write clean code." Note that the evaluation style shown here is just an example, and it is possible to set a variety of other evaluation styles. Furthermore, the selection method is not limited to this screen example, and can include text input or selection using tags. This makes it possible to reflect the qualitative evaluation criteria behind the job posting in the system.

[0099] Area 1413 is where you set the "weighting" of specific evaluation items. In the example in Figure 11, you can intuitively adjust the importance of each item using a slider-type user interface so that the total of evaluation items such as "evaluation direction," "project results," and "teamwork" equals 100%. Note that these evaluation items (evaluation axes) are just examples, and various items can be set according to the characteristics of the job posting. This setting is reflected in the logic that Server 20 uses to calculate the matching score.

[0100] Figures 12 and 13 are examples of detailed analysis result reports generated by AI, which are displayed when a specific candidate (in the example shown, "Taro Yamada") is selected from the candidate list screen (Figure 10). This system allows the same candidate to be evaluated from different perspectives by switching the evaluation points (evaluator character). Figure 12 shows an example of an evaluation report from a "technical perspective" that emphasizes technical abilities, and Figure 13 shows an example of an evaluation report from a "product perspective" that emphasizes contributions to product development. This allows recruiters to gain a deep and multifaceted understanding of a candidate's abilities and characteristics.

[0101] In the report screen from a "technical perspective" shown in Figure 12, area 1421 is the area that displays the candidate's basic information. This includes their name, current affiliation, and position. Area 1422 is the area that displays the candidate's "evaluation direction (technical perspective)" as analyzed by the generating AI. Here, the candidate's behavioral characteristics and values ​​from a technical perspective are shown, such as "emphasis on technical curiosity," "emphasis on code quality," and "autonomous learning."

[0102] Area 1423 is the area for visualizing "Evaluation Scores (Technical Perspective)". In addition to the overall score (e.g., 95%), sub-scores for individual competency items such as "Logical Thinking," "Leadership," and "Collaboration" are displayed as progress bars. This allows recruiters to intuitively grasp the candidate's technical strengths and weaknesses. A text summary that forms the basis of the score, such as "High level of logical thinking, and particularly excellent leadership. Past project experience has confirmed a track record of leading teams and making significant contributions to achieving goals," is also displayed. Note that the evaluation axes shown here are just examples, and various evaluation axes may be displayed depending on the set evaluator character.

[0103] Area 1424 is the area that recommends other job postings that may match the candidate. In the example in Figure 12, the match rate with other job postings in the system is displayed, such as "Job A (Backend Engineer) Match Score 95%" and "Job B (Tech Lead Candidate) Match Score 70%". Server 20 automatically matches a single candidate with multiple job postings in the system and lists other job postings with high scores here. This makes it possible to guide excellent candidates who were not suitable for the job they applied for to other suitable positions, contributing to maximizing recruitment opportunities throughout the company.

[0104] Area 1425 is designed to support the next actions based on the evaluation results. For example, when a user operates a button, Server 20 can have the AI ​​automatically generate interview questions based on the candidate's strengths and weaknesses, and display them in this area, such as a "Generate Interview Question List" button. This helps to realize a data-driven and consistent selection process.

[0105] Figure 13 is an example of a report screen evaluating the same candidate, "Taro Yamada," from a "product perspective," which is a different evaluation point than that used in Figure 12.

[0106] In the report screen shown in Figure 13, area 1431 displays the candidate's basic information, including their name, current affiliation, and position. Area 1432 displays the candidate's "evaluation direction (product perspective)" as analyzed by the AI. Here, the candidate's behavioral characteristics and values ​​from a product management perspective are shown, such as "emphasizes team results," "emphasizes project success," and "acts proactively."

[0107] Area 1433 is the area for visualizing "Evaluation Scores (Product Perspective)". In addition to the overall score (e.g., 80%), sub-scores for individual competency items such as "Logical Thinking," "Leadership," and "Collaboration" are displayed as progress bars. This allows recruiters to intuitively grasp a candidate's strengths and weaknesses in product management. A text summary that underlies the score, such as "High level of logical thinking, particularly strong leadership. Past project experience has demonstrated a track record of leading teams and making significant contributions to achieving goals," is also displayed.

[0108] Area 1434 is an area that recommends other job postings that may be a good match for the candidate. In the example in Figure 13, the degree of match with other job postings in the system is displayed, such as "Job A (Product Leader) Match Score 92%" or "Job B (Project Manager) Match Score 70%".

[0109] Area 1435 is designed to support the next steps based on the evaluation results, and contains the "Generate Interview Question List" button.

[0110] <8.Summary> As described above, according to the information processing system of this embodiment, the generating AI classifies the requirements included in job postings into multiple categories based on the degree of importance of the requirements, such as "essential" or "preferred," and scores them considering the degree of importance of those requirements. This makes it possible to achieve more realistic job matching that reflects the intentions of recruiters, which was difficult with conventional uniform evaluations. Furthermore, by making it possible to set "evaluator characters" that personify the evaluation criteria, it becomes possible to intuitively introduce multifaceted evaluations, such as technical and product perspectives, rather than being limited to a single evaluation axis, thereby supporting more accurate decision-making.

[0111] (modified version) Although the main configuration has been described in the above embodiment, various modifications can be made without departing from the spirit of the present invention.

[0112] For example, specific logic may be added to the score calculation process. Specifically, the prompts generated by the prompt generation module 2033 of the server 20 may include instructions to the generating AI system 30 to automatically set the matching score to a predetermined low value if the candidate does not meet all of the requirements classified into the first category indicating essential requirements. This "predetermined low value" refers to a score arbitrarily determined during the system design phase in order to mechanically exclude candidates who do not meet the core of the hiring criteria, such as a score of 0 or a score clearly below the passing standard.

[0113] Furthermore, during the requirements setting stage, the server 20's receiving control module 2031 may allow users to add sensitive requirements not explicitly stated in the job posting (for example, compatibility with the company culture or willingness to contribute to the team) via text input, and set them as required or desirable requirements. This allows implicit hiring criteria not appearing in the job posting to be incorporated into the evaluation, further improving the accuracy of matching.

[0114] Furthermore, in the evaluator character setting screen (area 1412) shown in Figure 11, users may set a qualitative evaluation style as a requirement, such as "emphasize technical depth." In this case, the server 20 treats this evaluation style as a mandatory or desirable requirement, extracts relevant descriptions (for example, descriptions showing deep knowledge or curiosity regarding specific technologies) from the candidate's resume, and reflects them in the scoring. This enables a more multifaceted and realistic evaluation.

[0115] Furthermore, as an operation after score calculation, the score calculation module 2034 of server 20 may calculate a matching score for the candidate with other job information other than the job they applied for, and the information presentation module 2035 may add a function to present other job information as recommendation information if the score exceeds a predetermined threshold. Specifically, as shown in area 1424 of Figure 12 and area 1434 of Figure 13, other job titles and their matching degree are displayed in a list on the candidate evaluation report screen. This allows excellent candidates who were not suitable for the applied job to be guided to other appropriate positions, maximizing recruitment opportunities throughout the company.

[0116] Furthermore, based on the calculated matching score and evaluation results, the prompt generation module 2033 of the server 20 may have a function to have the generation AI automatically generate questions regarding matters to be confirmed in interviews with job candidates and present them to the information presentation module 2035. Specifically, when the user operates the "Generate Interview Question List" button shown in area 1425 of Figure 12 or area 1435 of Figure 13, the server 20 generates a list of questions based on the candidate's strengths and weaknesses indicated by the evaluation score (for example, area 1423 of Figure 12) and displays it on the screen. This supports the realization of a data-driven and consistent selection process.

[0117] In addition, for job candidates whose matching score falls below a predetermined threshold, the prompt generation module 2033 of the server 20 can be configured to have the generation AI generate information on which requirements are lacking and specific improvement suggestions to fulfill those requirements, which are then presented to the information presentation module 2035. These improvement suggestions may, for example, be generated as a notification message to the candidate and sent to the candidate via the applicant tracking system (ATS) 40. This helps maintain good relationships with candidates and contributes to cultivating a talent pool of potential future hires.

[0118] Furthermore, in the above embodiment, the steps of extracting requirements from job information (S13) and calculating a candidate matching score based on the extracted requirements (S16) were performed sequentially as separate instructions to the generating AI. However, it is also possible to integrate these processes into a single step and execute them with a single instruction. In this case, the prompt generation module 2033 of the server 20 acquires both the job information to be matched with the candidate and the candidate information of the candidate, and generates a prompt to input these together into the generating AI system 30. The prompt includes instructions to the generating AI to autonomously interpret the degree of requirements (e.g., required, preferred) from the input job information, evaluate the candidate information considering the priority based on that interpretation, and perform a series of processes at once to calculate the final matching score. An example of a prompt is: "You are an excellent recruiter. Simultaneously analyze the following job information and the candidate's resume, and calculate a candidate matching score from 0 to 100 points, taking into account the importance of the required and preferred requirements that can be read from the job information." This configuration reduces the number of communications between the server 20 and the generation AI system 30, enabling more efficient and faster matching processing.

[0119] <Basic Computer Hardware Configuration> Figure 14 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 comprises at least a processor 901, main memory 902, auxiliary storage 903, and a communication interface IF991. These are electrically connected to each other by a communication bus.

[0120] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0121] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0122] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0123] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards. A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0124] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0125] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 14) will be explained. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0126] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0127] The control unit is realized when the processor 901 reads various programs stored in the auxiliary storage device 903, loads them into the main memory device 902, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0128] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0129] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs. Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0130] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0131] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0132] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0133] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0134] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0135] The functions realized by the components described herein may be implemented in a circuit or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor is considered to be a circuit or processing circuitry, including transistors and other circuits. A processor may be a programmed processor that executes a program stored in memory. In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein. If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0136] While several embodiments of this disclosure have been described above, these embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications are permitted 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.

[0137] (Note) The details described in each of the above embodiments are noted below.

[0138] (Note 1) A program for operating a computer that includes a processor and memory, The aforementioned processor, Steps to obtain job postings that are suitable for matching with job candidates, The steps include: inputting the acquired job information into a generating AI, and classifying and extracting the multiple requirements contained in the job information into multiple categories based on the degree of the requirements; The steps include inputting the extracted requirements, candidate information of the candidates, and instructions to calculate a matching score based on predetermined priorities between the categories into the generating AI, and causing it to calculate the matching score of the candidates; The steps include: displaying the calculated matching score on the user's terminal device; A program that executes the command.

[0139] (Note 2) The aforementioned categories include a first category indicating mandatory requirements and a second category indicating preferred requirements. In the step of calculating the matching score, the instruction instructs the generating AI to calculate the matching score by setting the priority of the first category higher than the priority of the second category. The program described in (Note 1).

[0140] (Note 3) In the step of calculating the matching score, the instruction instructs the generating AI to set the matching score to a predetermined low value if the candidate does not meet all the requirements classified in the first category. The program described in (Appendix 2).

[0141] (Note 4) The aforementioned processor further includes, In response to the aforementioned job posting, the step of setting up evaluator characters with weighted evaluation criteria, to be the entities that evaluate candidates, is performed before the step of calculating the matching score. In the step of calculating the matching score, the instruction instructs the generating AI to calculate the matching score, taking into account the weighting of the evaluation criteria for the set evaluator character. The program described in any of (Appendix 1) to (Appendix 3).

[0142] (Note 5) The aforementioned evaluator character further possesses personality and manner of speaking, The aforementioned processor further includes, A step in which the generating AI generates comments indicating the basis for the evaluation presented along with the matching score, based on the set personality and speaking style. The program described in (Appendix 4) that executes the above.

[0143] (Note 6) Multiple evaluator characters are set, In the step of calculating the matching score, the instruction instructs the generating AI to calculate the matching score from the perspective of each of the multiple evaluator characters. In the step of presenting the results, the multiple matching scores calculated are presented in a way that allows for comparison. The program described in (Appendix 4).

[0144] (Note 7) The aforementioned processor further includes, A step of receiving input for sensitive requirements not explicitly stated in the job posting, classifying the received sensitive requirements into one of the aforementioned multiple categories and adding them to the requirements, A program described in any of (Appendix 1) to (Appendix 6) that executes the above.

[0145] (Note 8) The aforementioned processor further includes, A step of defining a qualitative evaluation style as a requirement that falls into one of the aforementioned multiple categories, A program described in any of (Appendix 1) to (Appendix 7) that executes the above.

[0146] (Note 9) The aforementioned processor further includes, The steps include having the generating AI calculate a matching score for the aforementioned candidate with other job postings besides the aforementioned job posting, and having the AI ​​present other job postings whose scores exceed a predetermined threshold as recommended information. The program described in any of (Appendix 1) to (Appendix 8) that executes the above.

[0147] (Note 10) The aforementioned processor further includes, Based on the calculation results of the matching score, the generation AI generates and presents questions regarding matters to be confirmed during the interview with the candidate for employment. The program to execute one of the notes (Appendix 1) through (Appendix 9).

[0148] (Note 11) The aforementioned processor further includes, The steps include: having the acquired job information analyzed by the generating AI, generating basic settings for the evaluator character recommended for the job information, and proposing them to the user; The program described in (Appendix 4) that executes the above.

[0149] (Note 12) The aforementioned processor further includes, For candidates whose matching score falls below a predetermined threshold, the generation AI is used to generate and present unmet requirements and proposed improvements to satisfy those requirements. The program to execute one of the notes (Appendix 1) through (Appendix 11).

[0150] (Note 13) An information processing device comprising a control unit and a storage unit, wherein the control unit executes all steps in any of the programs described in (Appendix 1) to (Appendix 12).

[0151] (Note 14) A method to be executed on a computer comprising a processor and memory, wherein the processor executes all steps in any of the programs described in (Appendix 1) to (Appendix 12).

[0152] (Note 15) A system comprising means for executing all steps in any of the programs described in (Appendix 1) to (Appendix 12). [Explanation of symbols]

[0153] 1... System 10…Terminal device 12…Communication IF 13…Input device 14…Output device 15…Memory 16…Storage 19… Processor 20... Server 22...Communication IF 23…Input / Output Interface 25…Memory 2 hours… storage 29… Processor 30…Generating AI system 40. Applicant Tracking System (ATS) 80…Network

Claims

1. A program for operating a computer that includes a processor and memory, The aforementioned processor, Steps to obtain job postings that are suitable for matching with job candidates, The steps include: inputting the acquired job information into a generating AI, and classifying and extracting the multiple requirements contained in the job information into multiple categories based on the degree of the requirements; The steps include inputting the extracted requirements, candidate information of the candidates, and instructions to calculate a matching score based on predetermined priorities between the categories into the generating AI, and causing it to calculate the matching score of the candidates, The steps include: displaying the calculated matching score on the user's terminal device; Make it run, The aforementioned processor further includes, In response to the aforementioned job posting, the step of setting up evaluator characters with weighted evaluation criteria, to be the entities that evaluate candidates, is performed before the step of calculating the matching score. In the step of calculating the matching score, the instruction is a program that instructs the generating AI to calculate the matching score, taking into account the weighting of the evaluation criteria of the set evaluator character.

2. The aforementioned categories include a first category indicating mandatory requirements and a second category indicating preferred requirements. In the step of calculating the matching score, the instruction instructs the generating AI to calculate the matching score by setting the priority of the first category higher than the priority of the second category. The program according to claim 1.

3. In the step of calculating the matching score, the instruction instructs the generating AI to set the matching score to a predetermined low value if the candidate does not meet all the requirements classified in the first category. The program according to claim 2.

4. The aforementioned evaluator character further possesses personality and manner of speaking, The aforementioned processor further includes, A step in which the generating AI generates comments indicating the basis for the evaluation presented along with the matching score, based on the set personality and speaking style. The program according to claim 1, which causes to execute.

5. Multiple evaluator characters are set, In the step of calculating the matching score, the instruction instructs the generating AI to calculate the matching score from the perspective of each of the multiple evaluator characters. In the step of presenting the results, the multiple matching scores calculated are presented in a way that allows for comparison. The program according to claim 1.

6. The aforementioned processor further includes, A step of receiving input for sensitive requirements not explicitly stated in the job posting, classifying the received sensitive requirements into one of the aforementioned multiple categories and adding them to the requirements, The program according to claim 1, which causes to execute.

7. The aforementioned processor further includes, A step of defining a qualitative evaluation style as a requirement that falls into one of the aforementioned multiple categories, The program according to claim 1, which causes to execute.

8. The aforementioned processor further includes, The steps include having the generating AI calculate a matching score for the aforementioned candidate with other job postings besides the aforementioned job posting, and having the AI ​​present other job postings whose matching score exceeds a predetermined threshold as recommended information. The program according to claim 1, which causes to execute.

9. The aforementioned processor further includes, Based on the calculation results of the matching score, the generation AI generates and presents questions regarding matters to be confirmed during the interview with the candidate for employment. The program according to claim 1, which causes to execute.

10. The aforementioned processor further includes, The steps include: having the acquired job information analyzed by the generating AI, generating basic settings for the evaluator character recommended for the job information, and proposing them to the user; The program according to claim 1, which causes to execute.

11. The aforementioned processor further includes, For candidates whose matching score falls below a predetermined threshold, the generation AI is used to generate and present unmet requirements and proposed improvements to satisfy those requirements. The program according to claim 1, which causes to execute.

12. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all steps in the program described in any one of claims 1 to 11.

13. A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps of a program according to any one of claims 1 to 11.

14. A system comprising means for performing all steps in the program described in any one of claims 1 to 11.

Images