Information processing systems, information processing methods, and programs

Abstract

This invention provides an information processing system, information processing method, and program that improves the convenience of job seekers when creating documents. [Solution] The server device 10 of the information processing system includes an acquisition unit 111 that acquires job information and recruiter information which is information about recruiters corresponding to the job information; an intermediate information generation unit 112 that generates intermediate information based on the job information, recruiter information and first reference information; and an output generation unit 113 that generates modified job information which is modified job information and at least one of a scout document corresponding to the job information based on the job information, intermediate information and second reference information. The first reference information includes the correlation between the job information and recruiter information and the intermediate information, the intermediate information includes target information which shows the profile of the person to be hired and message information which shows the appeal of the job, and the second reference information includes the correlation between the job information, the intermediate information and at least one of the modified job information and the scout document.

Description

Technical Field

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

[0002] In recent years, technologies for supporting creation of sentences and the like have been developed. For example, Patent Literature 1 discloses a technology for analyzing sentences used in a specific document. Prior Art Literature Patent Literature

[0003] Patent Literature 1 Japanese Unexamined Patent Application Publication No. 2018-045690 Summary of the Invention Problem to be Solved by the Invention

[0004] On the other hand, with respect to technologies for creating sentences, there is room for improving the convenience of job recruiters.

[0005] In view of the above circumstances, the present invention can improve convenience for a job recruiter when creating sentences. Means for Solving the Problem

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program: in the acquisition step, it acquires job information and recruiter information, which is information about a recruiter corresponding to the job information, and the job information includes at least a job posting; in the first generation step, it generates intermediate information based on the job information, recruiter information and first reference information, and the first reference information includes at least the correlation between the job information and recruiter information and the intermediate information, and the intermediate information includes target information indicating the profile of the person to be hired in the job information and message information indicating the appeal content of the job related to the job information; and in the second generation step, it generates at least one of modified job information, which is a modified version of the job information, and a scout document corresponding to the job information, based on the job information, intermediate information and second reference information, and the second reference information includes at least the correlation between the job information and intermediate information and at least one of the modified job information and the scout document.

[0007] This configuration can improve convenience for job seekers when creating documents. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of server device 10. [Figure 3] This block diagram shows the hardware configuration of the job seeker terminal 20 and the job applicant terminal 30. [Figure 4] This is a functional block diagram implemented by the server device 10 (control unit 11), the job seeker terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). [Figure 5] This figure shows an example of the job information input screen JA displayed on the job seeker terminal 20. [Figure 6] This figure shows an example of a target message display screen™. [Figure 7]This figure shows an example of a CI (Creative Interface) screen for displaying job applicant information. [Figure 8] This is an activity diagram showing an example of the information processing flow performed by information processing system 1. [Modes for carrying out the invention]

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

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

[0011] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as "reference information") is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a trained model that has been pre-trained to learn the correlation between input and output, or a large-scale language model that can output a desired result by inputting a prompt (these models include parameters that construct the correlation relationship between input and output), or a generative AI such as a visual language model. The reference information may be stored in the memory unit 12 in advance, or it may be dynamically generated and updated at runtime. The reference information may also be obtained from an external server or the like. Furthermore, the reference information may include access information (endpoint URL, API key, etc.) to a large-scale language model provided as a cloud service.

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

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

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

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

[0016] The information processing system 1 constitutes at least a part of a job recruiting and job seeking system used by, for example, a plurality of recruiters (a first recruiter U1 and a second recruiter U2) and a plurality of job seekers (a first job seeker U3 and a second job seeker U4). The information processing system 1 mainly performs functions such as recruiters searching for job seekers, job seekers searching for job postings, and mediating communication between recruiters and job seekers. For example, the information processing system 1 provides and manages talent matching platforms, talent matching services, etc. used by recruiters and job seekers. In one embodiment, the information processing system 1 consists of one or more devices or components. These components are described below.

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

[0018] <Control unit 11> The control unit 11 performs processing and control of overall operations related to the server device 10. The control unit 11 is, for example, a Central Processing Unit (CPU), which is an example of a processor. The control unit 11 implements various functions related to the server device 10 by reading a predetermined program stored in the storage unit 12. In other words, information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, so that it can be executed as each functional unit included in the control unit 11. These are described in further 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 a plurality of control units 11 for each function. Furthermore, the server device 10 may be configured by a combination of these.

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

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

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

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

[0023] "Employers" include organizations or their personnel who conduct recruitment activities. Employers are, for example, those who intend to hire job seekers or those who conduct the selection process for job seekers. In this specification, "recruitment" may include not only the recruitment of external personnel but also internal recruitment, promotion, transfer, and reassignment of employees and other personnel within the organization. Personnel within employers may be called recruitment officers, and these officers may include personnel from the organization's human resources department or personnel from the department that recruits personnel. Furthermore, "employers" may also include headhunters. A headhunter is an organization or its personnel that acts as an agent for employers, mediating between job seekers and employers. Headhunters are also called recruitment agencies, recruitment agents, etc.

[0024] Here, "hiring" may also be called "contract." Furthermore, "hiring" may include not only the job seeker's decision to take up employment or change jobs, but also the job offer from the employer to the job seeker, the job seeker's acceptance of the offer, and the job seeker's joining the employer. In addition, "organization" includes for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), public corporations (e.g., local governments, etc.). Moreover, "organization" is not limited to a single legal entity, but may also include a group composed of multiple legal entities with capital relationships or partnerships (e.g., a group consisting of a parent company, subsidiaries, affiliates, etc.).

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

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

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

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

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

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

[0031] Figure 4 is a block diagram showing the functions implemented by the server device 10 (control unit 11), the recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). Figure 4A shows the functional blocks of the control unit 11 of the server device 10, including the acquisition unit 111, intermediate information generation unit 112, target information generation unit 112a, message information generation unit 112b, output generation unit 113, scout document modification unit 113a, classification unit 114, display control unit 115, feedback acquisition unit 116, regeneration unit 117, and artificial intelligence unit 120. Figure 4B shows the functional blocks implemented by the control unit 21 of the recruiter terminal 20. Figure 4C shows the functional blocks implemented by the control unit 31 of the job seeker terminal 30.

[0032] As shown in Figure 4A, the server device 10 (control unit 11) includes an acquisition unit 111, an intermediate information generation unit 112, an output generation unit 113, a classification unit 114, a display control unit 115, a feedback acquisition unit 116, a regeneration unit 117, and an artificial intelligence unit 120.

[0033] As shown in Figure 4B, the applicant terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212.

[0034] As shown in Figure 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0035] <Acquisition part 111> The acquisition unit 111 is configured to acquire job postings and employer information, which is information about employers corresponding to the job postings. Here, the job postings and employer information acquired by the acquisition unit 111 may be referred to as target job postings and target employer information, respectively. Specifically, the acquisition unit 111 acquires specific job postings selected by the employer from at least one (typically more) job postings registered in the job database from the employer terminal 20. The acquisition unit 111 also acquires corresponding job postings from the job database based on job identification information entered from the employer terminal 20, for example. Here, "job identification information" is an identifier for uniquely identifying each job posting, for example, a job ID, which may consist of arbitrary alphanumeric characters, etc. Furthermore, the acquisition unit 111 may accept text input of at least some of the items described in the job posting and acquire job information based on said input, or it may acquire job information based on a file containing job information uploaded from the recruiter terminal 20, or it may acquire job information based on access information (for example, a URL, IP address, etc. of a recruitment site or recruitment management system) indicating the network location of the job information received from the recruiter terminal 20.

[0036] Here, "job information" refers to information provided by an employer regarding the recruitment of job seekers. Typically, this is a job posting, but it does not necessarily have to be formatted like a job posting; it may be an unstructured document such as a memo containing the job details. Job information may include, for example, the job description and the requirements for employment. "Job description" may include, for example, the name of the employer, the job title, the industry, the job type, the duties, the department, the position, the annual salary, the work location, the work style, the selection process, etc. "Requirements for employment" may include, for example, the necessary skills, the necessary experience, the necessary qualifications, etc. Job information may be described using, for example, keywords, numbers, sentences, etc.

[0037] The acquisition unit 111 acquires corresponding recruiter information from the recruiter database stored in the storage unit 12, for example, based on recruiter identification information entered from the recruiter terminal 20. Here, "recruiter identification information" is an identifier for uniquely identifying each recruiter, for example, a recruiter ID, which may consist of any alphanumeric characters. Furthermore, the acquisition unit 111 may accept text input of at least a portion of the information about the recruiter and acquire recruiter information based on said input, or it may acquire recruiter information based on a file containing recruiter information uploaded from the recruiter terminal 20, or it may acquire recruiter information based on access information indicating the network location of the recruiter information received from the recruiter terminal 20 (for example, a URL, IP address, etc., of a recruitment site or applicant tracking system (ATS)).

[0038] "Employer information" refers to information about an employer, including basic organizational information such as the employer's name, address, year of establishment, number of employees, capital, and business scale. Furthermore, employer information includes information on at least one of the following: the employer's philosophy, vision, business content, products or services, business environment, management policies, organizational characteristics, job characteristics of the position, and employment conditions. Employer information may be information registered by the employer, information collected from the web or other sources by the acquisition unit 111 described later, or a combination of these.

[0039] The job posting database and the job seeker database are stored, for example, in the storage unit 12. The job posting database and the job seeker database may be a single database. Furthermore, the job posting database and the job seeker database are not limited to databases registered or referenced by services that constitute the information processing system 1, but may also be databases in external services of the information processing system 1 (for example, human resources systems / services such as recruitment management systems) in which job postings or job seekers are registered. In other words, the job posting information and job seeker information acquired by the acquisition unit 111 may be job posting information and job seeker information imported from external services of the information processing system 1, or it may be job posting information and job seeker information that is publicly available on the internet (i.e., obtainable from the internet). The job posting database stores job posting information and job seeker information, such as job identification information, in association with each other.

[0040] The acquisition unit 111 may further acquire personnel information relating to individuals who may be candidates for employment related to the target job posting. Here, "personnel information" includes, for example, information indicating the recipients included in the scout history of the job posting corresponding to the target job posting (target job posting) or other job postings similar to the target job posting (similar job postings), and personnel list information indicating a list of individuals who may be candidates for employment related to the target job posting or similar job postings. Here, "scout history" is a history of scout documents that the employer has sent to job seekers in the past regarding the target job posting, and includes, for example, information regarding the date and time of transmission, recipients (e.g., job seeker identification information such as job seeker ID), the content of the sent scout document, and the job seeker's response (e.g., whether it was opened, whether a reply was sent, open rate, reply rate, etc.). The information processing system 1 can improve the quality of the intermediate information generated by using the recipient information based on the scout history to generate the intermediate information.

[0041] Furthermore, the acquisition unit 111 may acquire, as personnel information, job seeker information that has had some kind of interaction with the target job posting or similar job posting, such as job seeker information that has been flagged in association with the target job posting or similar job posting (e.g., favorite registration, bookmark registration, target list registration, etc.), job seeker information that has passed the screening of the target job posting or similar job posting (e.g., document screening, interview screening, etc.), job seeker information that has applied to the target job posting or similar job posting.

[0042] The acquisition unit 111 is further configured to acquire publicly available information about the employer. Based on at least one of the acquired job postings and employer information, the acquisition unit 111 performs web crawling, scraping, etc., on publicly available information on the network, such as the employer's website, the employer's disclosure information (e.g., IR information page), articles about the employer's employees (e.g., employee interview articles), information about the employer's products or services, news information about the employer, and evaluation information about the employer (e.g., evaluation sites), to acquire additional information about the employer. The acquisition unit 111 may also acquire additional information by performing API calls, database searches, etc. The acquisition unit 111 classifies the acquired additional information into categories such as the employer's basic information, founding background / growth background, market / competitor information, vision / mission / values, business strategy, organizational structure, operations / products, and compensation / work style, and stores it in the storage unit 12. The additional information acquired by the acquisition unit 111 may be treated as part of the employer information.

[0043] Web crawling and the like may be performed by the job seeker information collection model included in the artificial intelligence unit 120. The job seeker information collection model may be various pre-trained models such as AI (Artificial Intelligence), and may be a dedicated learning model or a general-purpose learning model that has been machine-trained to take at least one of job information and job seeker information as input, perform web crawling and the like, and output data that classifies the additional information collected by web crawling and the like into categories.

[0044] The job seeker information collection model collects publicly available information by web crawling or the like, based on at least one of the job information and / or job seeker information, and obtains additional information. The job seeker information collection model may periodically web crawl publicly available information and retain the results of the web crawling as a dataset. The artificial intelligence unit 120 inputs instructions to the job seeker information collection model to web crawl publicly available information based on at least one of the job information and / or job seeker information, and causes the job seeker information collection model to output additional information. The artificial intelligence unit 120 may also input prompts to the job seeker information collection model that include instructions to take the collected publicly available information as input and output data classified by category as additional information, causing the job seeker information collection model to output the categorized additional information. For example, the artificial intelligence unit 120 inputs instructions to the job seeker information collection model to obtain additional information regarding the attractiveness of the job by web crawling or the like, and the job seeker information collection model obtains the additional information by web crawling or the like according to the instructions. Furthermore, prompts may include templates such as, "Collect publicly available information from the following job seekers' websites, extract useful information for recruitment, and output it categorized by type (basic information / founding background / market and competitors / vision / business strategy / organizational structure / operations and products / compensation and work style)."

[0045] This allows employer information to be obtained from publicly available information on the network, etc., without the need for manual collection and organization of employer information, thereby improving the efficiency and comprehensiveness of information gathering.

[0046] Figure 5 shows an example of a job information input screen JA displayed on the recruiter terminal 20. The job information input screen JA includes a job identification information input area JA1, a job posting text input area JA2, a recruiter information input area JA3, a confirm button B21, and a cancel button B22.

[0047] The job identification information input area JA1 includes a text field for entering job identification information such as a job ID or job number. For example, when job identification information is entered into the job identification information input area JA1, the acquisition unit 111 retrieves the corresponding job information from the job database stored in the storage unit 12 based on the entered job identification information.

[0048] The job posting text input area JA2 includes a text input field for directly entering the information to be included in the job posting (job title, job description, required conditions, etc.). When the information to be included in the job posting is entered into the job posting text input area JA2, the acquisition unit 111 acquires the job information based on the entered information.

[0049] The job seeker information input area JA3 contains input fields for entering job seeker information. When job seeker information is entered into the job seeker information input area JA3, the acquisition unit 111 acquires the job seeker information based on the entered information.

[0050] When the confirm button B21 is pressed, the acquisition of job information begins based on the information entered in the job identification information input area JA1 or the job posting text input area JA2, the acquisition of employer information begins based on the information entered in the employer information input area JA3, and the generation of intermediate information begins. Specifically, the acquisition unit 111 starts acquiring job information and employer information, and the acquisition unit 111 also starts web crawling, etc., and then the intermediate information generation unit 112 generates intermediate information. Note that the screen configuration and layout shown in Figure 5 (job information input screen JA) are merely examples, and the present invention is not limited thereto. When the cancel button B22 is pressed, the entered content is discarded.

[0051] <Intermediate information generation unit 112> The intermediate information generation unit 112 is configured to generate intermediate information based on job information, recruiter information, and first reference information. For example, the intermediate information generation unit 112 takes the job information and recruiter information acquired by the acquisition unit 111 as input and generates intermediate information that includes target information indicating the profile of the person to be hired and message information indicating the appeal of the job. Alternatively, the intermediate information generation unit 112 may generate intermediate information by first generating target information using the target information generation unit 112a, and then generating message information using the target information using the message information generation unit 112b. Furthermore, the intermediate information generation unit 112 may generate target information and message information in parallel.

[0052] Here, "intermediate information" refers to intermediate deliverables generated based on job postings and employer information, and includes at least target information and message information. "Target information" refers to information that indicates the profile of the person to be hired in the job posting, and includes, for example, hiring requirements (essential skills, experience, qualifications, etc.), the persona of the target candidate (age group, work history, values, career aspirations, etc.), and the characteristics and conditions of the target candidate. "Message information" refers to information that indicates the appeal of the job posting related to the job posting, and includes, for example, a message to appeal to job seekers about the strengths, appeal, and characteristics of the employer. Message information may be classified by appeal category according to the classification section 114 described later. In addition, intermediate information may include other information.

[0053] The first reference information is information relating to the correlation between job postings and employer information and intermediate information. The first reference information is stored, for example, in the memory unit 12. The first reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between job postings and employer information and intermediate information. The correlations included in the first reference information can be constructed, for example, by statistically analyzing data that records job postings and employer information and the corresponding intermediate information.

[0054] The first reference information may include a set of parameters for generating intermediate information from job postings and employer information. For example, the first reference information may be various pre-trained models. For example, the first reference information may include an intermediate information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take job postings and employer information as inputs and output intermediate information. In this case, the intermediate information generation unit 112 inputs the job postings and employer information into the intermediate information generation model and causes the intermediate information generation model to output intermediate information.

[0055] The intermediate information generation model is included in the artificial intelligence unit 120. The intermediate information generation model, which is a dedicated learning model, may be constructed, for example, by training using job postings and job seeker information data and corresponding intermediate information data as training data. In such an intermediate information generation model, parameters calculated and tuned through training construct a correlation between job postings and job seeker information and intermediate 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.

[0056] If the intermediate information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the intermediate information generation unit 112 inputs a prompt to the intermediate information generation model that includes job information and recruiter information, and an instruction to output intermediate information corresponding to the job information and recruiter information as input, causing the intermediate information generation model to output the intermediate information. For example, the prompt may be an instruction template such as, "Based on the following job information and recruiter information, generate recruitment targets and appealing messages that will resonate with those targets," and the job information and recruiter information acquired by the acquisition unit 111 is inserted into the template. Here, the parameters for constructing the intermediate information generation model and the prompt including an instruction to output intermediate information corresponding to the job information and recruiter information construct the correlation between the job information and recruiter information and the intermediate information.

[0057] This allows for the efficient generation of recruitment targets and appeal messages based on job postings and applicant information.

[0058] <Target information generation unit 112a> The intermediate information generation unit 112 may also function as a target information generation unit 112a and be configured to generate target information based on job information, recruiter information, and third reference information. The target information generation unit 112a generates target information, for example, by taking job information and recruiter information as input. The target information generation unit 112a operates prior to the generation of message information by the message information generation unit 112b, which will be described later, and provides the target information to the message information generation unit 112b.

[0059] The third reference information is information relating to the correlation between job postings and employer information and target information. The third reference information is stored, for example, in the memory unit 12. The third reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between job postings and employer information and target information. The correlations included in the third reference information can be constructed, for example, by statistically analyzing data that records job postings and employer information and the corresponding target information.

[0060] The third reference information may include a set of parameters for generating target information from job postings and employer information. For example, the third reference information may be various pre-trained models. For example, the third reference information may include a target information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take job postings and employer information as inputs and output target information. In this case, the target information generation unit 112a inputs job postings and employer information into the target information generation model and causes the target information generation model to output target information.

[0061] The target information generation model is included in the artificial intelligence unit 120. The target information generation model, which is a dedicated learning model, may be constructed, for example, by training using job posting and job seeker information data and corresponding target information data as training data. In such a target information generation model, parameters calculated and tuned through training construct a correlation between job posting and job seeker information and target 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.

[0062] If the target information generation model is a general-purpose learning model, the target information generation unit 112a inputs a prompt to the target information generation model that includes job postings and job seeker information, and an instruction to output target information corresponding to the job postings and job seeker information as input, causing the target information generation model to output the target information. For example, the prompt may use an instruction template such as, "Generate a profile of the target candidate from the following job postings and job seeker information. Output it as a persona including recruitment requirements, skills, experience, values, etc." and the job postings and job seeker information acquired by the acquisition unit 111 is inserted into the template.

[0063] This allows for the efficient generation of information regarding the ideal candidate profile based on job postings and employer information. Compared to situations where the employer's representatives define the target candidate themselves, this method enables the objective generation of target information that is consistent with the job postings and employer information.

[0064] <Message information generation unit 112b> The intermediate information generation unit 112 may also function as a message information generation unit 112b and be configured to generate message information based on job information, recruiter information, target information, and fourth reference information. The message information generation unit 112b, for example, takes as input the target information generated by the target information generation unit 112a, as well as the job information and recruiter information acquired by the acquisition unit 111, a message information indicating the content of the appeal to the recruitment target.

[0065] The fourth reference information is information relating to the correlation between job postings, job seeker information, and target information (hereinafter referred to as input information) and message information. The fourth reference information is stored, for example, in the memory unit 12. The fourth reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between this input information and message information. The correlations included in the fourth reference information can be constructed, for example, by statistically analyzing data that records the input information and the corresponding message information.

[0066] The fourth reference information may include a set of parameters for generating message information from input information. For example, the fourth reference information may be various pre-trained models. For example, the fourth reference information may include a message information generation model which is a dedicated or general-purpose learning model that has been machine-trained to take job information, job seeker information, and target information as input and output message information. In this case, the message information generation unit 112b inputs the job information, job seeker information, and target information into the message information generation model and causes the message information generation model to output message information.

[0067] The message information generation model is included in the artificial intelligence unit 120. The message information generation model, which is a dedicated learning model, may be constructed, for example, by training using input data and corresponding message information data as training data. In such a message information generation model, parameters calculated and tuned through learning construct a correlation between the input information and the message information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data.

[0068] If the message information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the message information generation unit 112b inputs a prompt to the message information generation model that includes input information and an instruction to output the corresponding message information, causing the message information generation model to output the message information. For example, the prompt may use an instruction template such as, "Based on the following job information, applicant information, and target information, generate appealing messages that will resonate with the target applicants, and output them for each appeal category (business / vision related / growth / opportunity related / work / fulfillment related / compensation / environment related)."

[0069] This allows for the efficient generation of appeals tailored to the target audience.

[0070] Here, the first reference information may include the third and fourth reference information, and the intermediate information generation model may include the target information generation model and the message information generation model.

[0071] Figure 6 shows an example of a target message display screen TM displayed on the recruiter terminal 20. The target message display screen TM includes a target information display area TM1, a message information display area TM2, a modified job posting information generation button B31, and a scout document generation button B32.

[0072] The target information display area TM1 displays the target information generated by the intermediate information generation unit 112. The target information display area TM1 displays the target information in a list, allowing recruiters to confirm and select targets.

[0073] The message information display area TM2 displays message information generated by the intermediate information generation unit 112. The message information may be displayed for each corresponding target information, or for each appeal category classified by the classification unit 114, which will be described later. The message information display area TM2 may display message information classified into appeal categories such as business / vision, growth / opportunity, work / fulfillment, and compensation / environment, either as tabs or in a list, for each appeal category.

[0074] When an input operation is performed on the modified job posting information generation button B31, the generation of modified job posting information begins based on the target information and message information displayed in the target information display area TM1 and the message information display area TM2, or the target information and message information selected from there. When an input operation is performed on the scout document generation button B32, the generation of a scout document begins based on the selected target information and message information. Once these generation operations are complete, the display control unit 115 displays the modified job posting information and scout document on the recruiter terminal 20, associated with the intermediate information. Note that the screen configuration and layout shown in Figure 6 (Target / Message Display Screen TM) are merely examples, and the present invention is not limited thereto.

[0075] Figure 7 shows an example of a job seeker information display screen CI displayed on the job seeker terminal 20. The job seeker information display screen CI includes a job seeker information category area CI1 and a job seeker information display area CI2.

[0076] In the recruiter information category area CI1, recruiter information, including additional information acquired and classified by the acquisition unit 111, is displayed for each category, such as basic information, founding background / growth background, market / competitor information, vision / mission / values, business strategy, organizational structure, operations / products, and compensation / work style. The categories may be the same as the appeal categories described later. Recruiters can efficiently check recruiter information by referring to the recruiter information category area CI1.

[0077] The recruiter information display area CI2 displays recruiter information categorized by type. Recruiters can refer to the recruiter information display area CI2 to verify the content of scouting documents and revised job postings.

[0078] <Output generation unit 113> The output generation unit 113 is configured to generate at least one of revised job information and a scout document based on job information, intermediate information, and second reference information. For example, the output generation unit 113 takes target information and message information generated by the intermediate information generation unit 112, and job information acquired by the acquisition unit 111 as input, and generates at least one of revised job information modified to match the target information, and a scout document tailored to the message information directed at the target. The output generation unit 113 may also be configured to generate at least one of revised job information and a scout document based on recruiter information.

[0079] Here, "revised job posting" refers to job postings that have been revised based on intermediate information. "Recruitment letter" refers to a recruitment message sent by an employer to a job seeker, which includes personalized text tailored to the characteristics of the target candidate. A recruitment letter may include, for example, a subject line, body text, and a link to the job posting.

[0080] The second reference information is information relating to the correlation between job postings and intermediate information and at least one of revised job postings and scouting documents. The second reference information is stored, for example, in the memory unit 12. The second reference information may include, for example, tables, functions, simple algorithms, etc., that show the correlation between this input information and output information. The correlations included in the second reference information can be constructed, for example, by statistically analyzing data that records input information and corresponding output information.

[0081] The second reference information may include a set of parameters for generating at least one of the revised job posting and the scout document from the input information. For example, the second reference information may be various pre-trained models. For example, the second reference information may include an output generation model which is a dedicated or general-purpose learning model that has been machine-trained to take job posting and intermediate information as input and output at least one of the revised job posting and the scout document. In this case, the output generation unit 113 inputs the job posting and intermediate information into the output generation model and causes the output generation model to output at least one of the revised job posting and the scout document.

[0082] The output generation model is included in the artificial intelligence unit 120. The output generation model, which is a dedicated learning model, may be constructed, for example, by training with job posting and intermediate information data and corresponding modified job posting and scout document data as training data. In such an output generation model, parameters calculated and tuned through training construct a correlation between input information and output information. The dedicated learning model may also include a generative AI capable of generating answers not included in the training data.

[0083] If the output generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the output generation unit 113 inputs a prompt to the output generation model that includes job information and intermediate information, and an instruction to output at least one of the corresponding revised job information and scout document, causing the output generation model to output at least one of the revised job information and scout document. For example, the prompt may use a template such as, "Please revise the job posting based on the following intermediate information (target message). Please reflect appeals that will resonate with the target recruits in the job posting." Here, the parameters that construct the output generation model and the prompt that includes an instruction to output output information corresponding to the input information establish a correlation between the input information and the output information.

[0084] This allows for the generation of revised job postings and recruitment documents based on target information and message information, improving the quality of job postings and recruitment documents compared to when recruiters manually revise job postings or create recruitment documents.

[0085] <Scout Document Revision Section 113a> The output generation unit 113 may also function as a scout document modification unit 113a and be configured to modify the scout document based on the job information, intermediate information, and second reference information, including the reference scout document. The scout document modification unit 113a, for example, takes the reference scout document as input and modifies and improves the reference scout document to match the target information and message information generated by the intermediate information generation unit 112. Here, the reference scout document may include scout documents created or sent in the past, or scout documents created or saved as templates.

[0086] If the second reference information is information relating the correlation between the reference scout document and intermediate information and the modified scout document, the scout document modification unit 113a inputs the existing scout document and intermediate information into the output generation model and causes the output generation model to output the modified scout document. The output generation model may learn using the data and intermediate information of the existing scout document and the corresponding data of the modified scout document as training data.

[0087] If the output generation model is a general-purpose learning model, the scout document modification unit 113a inputs a prompt to the output generation model that includes a reference scout document and intermediate information, and instructions to output a corresponding modified scout document, causing the output generation model to output the modified scout document. For example, the prompt may use a template such as, "Modify the following reference scout document based on the target information and message information."

[0088] This allows for the creation of targeted scouting documents while reducing the cost of creating them by utilizing existing scouting documents and templates.

[0089] <Classification section 114> The classification unit 114 is configured to classify message information by target information or by appeal category. For example, the classification unit 114 classifies the message information generated by the intermediate information generation unit 112 by target information or by appeal category (business / vision, growth / opportunity, work / fulfillment, and compensation / environment, etc.).

[0090] Here, "appeal category" refers to a classification of message information, and includes, for example, business / vision-related (future prospects of the business, mission / vision, etc.), growth / opportunity-related (skill development opportunities, career paths, etc.), work / reward-related (attractiveness of the work content, job satisfaction, etc.), and compensation / environment-related (salary, benefits, working environment, etc.). Appeal categories are not limited to these and may be set as appropriate according to the characteristics of the employer or job seeker.

[0091] This organizes the generated message information, allowing job seekers to efficiently review and select messages in each category.

[0092] The classification process performed by the classification unit 114 involves, for example, analyzing the text contained in the message information and classifying it based on keywords or semantic similarity of the appeal categories. If a single text falls under multiple appeal categories, the classification unit 114 may associate the appeal text with multiple categories. Furthermore, the classification results from the classification unit 114 may be manually modified or adjusted by the job seeker.

[0093] Furthermore, the classification unit 114 may classify the message information according to the target information. For example, if the intermediate information generation unit 112 generates multiple target information, the classification unit 114 groups the message information corresponding to each target information according to the target information. This allows job seekers to refer to the message information for each target and select the most appropriate message information.

[0094] <Display Control Unit 115> The display control unit 115 is configured to display the classified message information on the screen of the recruiter terminal 20. For example, the display control unit 115 generates display data for displaying message information for each target information or appeal category classified by the classification unit 114 on the output unit 25 of the recruiter terminal 20, and transmits it to the recruiter terminal 20.

[0095] This allows job seekers to view a list of categorized message information on the job seeker terminal 20 screen and select messages they want to use for creating recruitment documents or modifying job postings.

[0096] The display data generated by the display control unit 115 includes, for example, screen data for a target / message display screen TM, which includes a target information display area TM1 and a message information display area TM2. The target information display area TM1 displays the profile of the target candidate generated by the target information generation unit 112a. The message information display area TM2 displays message information categorized by appeal category, as classified by the classification unit 114. The recruiter can confirm the displayed target information and message information and instruct the output generation unit 113 to perform the generation process by operating the modified job posting generation button B31 or the scout document generation button B32.

[0097] The display control unit 115 may further generate display data for displaying the job seeker information display screen CI. The job seeker information display screen CI displays the job seeker information acquired and classified by the acquisition unit 111, categorized by type. Job seekers can check the content of the job seeker information by referring to the job seeker information display screen CI.

[0098] Furthermore, the display control unit 115 is configured to output at least one of the revised job posting information and the scouting document in association with the intermediate information. For example, the display control unit 115 displays or outputs the revised job posting information and the scouting document generated by the output generation unit 113 to the recruiter terminal 20 in association with the intermediate information (target information and message information) that formed the basis for their generation.

[0099] This allows employers to simultaneously review revised job postings, recruitment documents, and the intermediate information that formed the basis for their creation, enabling them to verify the validity of the generated content. This makes it easier for employers to understand the intent and rationale behind the creation of the materials, facilitating revisions and adjustments.

[0100] Furthermore, the display control unit 115 is configured to display at least one of the following as present information on the recruiter terminal 20: intermediate information, revised job information, and scouting documents. The present information is, for example, information displayed on the display unit 211 of the recruiter terminal 20 for the recruiter to provide feedback, and includes some or all of the generated intermediate information, some or all of the revised job information, and some or all of the scouting documents.

[0101] <Feedback acquisition unit 116> The feedback acquisition unit 116 is configured to acquire feedback information regarding the presented information from the job seeker terminal 20. The feedback information includes, for example, input information such as correction instructions, evaluations (good, bad, etc.), additional information, and supplementary comments made by the job seeker after they have reviewed the content of the presented information. The feedback information is acquired through various input methods on the job seeker terminal 20, such as text input, selection input, and button operation. The feedback acquisition unit may also be configured as a function of the display control unit 115.

[0102] <Regeneration unit 117> The regeneration unit 117 is configured to regenerate at least one of the following based on the feedback information: intermediate information, revised job information, and scouting documents. For example, the regeneration unit 117 inputs the acquired feedback information to the artificial intelligence unit 120 and obtains the regenerated presentation information from the artificial intelligence unit 120. Depending on the content of the feedback information, the regeneration unit may determine which presentation information (intermediate information, revised job information, or scouting documents, or one or more of them) to be regenerated. The regeneration unit may also be configured as at least one function of the intermediate information generation unit 112 and the output generation unit 113.

[0103] The regeneration unit 117 is configured to regenerate new intermediate information, revised job information, and scout documents based on feedback information for at least one of the intermediate information, revised job information, and scout documents, the feedback information, and the regeneration reference information. The regeneration reference information includes, for example, a prompt template for instructing the artificial intelligence unit 120 to perform a regeneration process according to the content of the feedback information.

[0104] The prompt issued by the regeneration unit to the artificial intelligence unit 120 for regeneration is generated based on, for example, the following template. In the case of regeneration of intermediate information (target information and message information), the prompt can use the template: "The target information and message information generated based on the following job information and recruiter information has been met with the following feedback from the recruiter. Please regenerate the target information and message information based on this feedback." Similarly, in the case of regeneration of revised job information or scout documents, a prompt including the corresponding input information and feedback information is generated.

[0105] Feedback information can take various forms depending on the type of information presented and the user's instructions. For example, feedback information on target information may include instructions for revisions to the profile of the person to be hired (e.g., "Please broaden the age range" or "Please add specific skills"). Feedback information on message information may include instructions for revisions to the tone and expression of the appeal. Feedback information on recruitment documents may include instructions to rewrite the entire recruitment document, instructions to revise specific paragraphs or expressions, instructions for additional information, etc.

[0106] The feedback acquisition unit 116 and the regeneration unit 117 can repeat the feedback and regeneration cycle multiple times. For example, a cycle can be realized in which the display control unit 115 regenerates the presentation information based on the initial feedback information, presents the regenerated information again as presentation information to the job seeker terminal 20, and then acquires additional feedback information and repeats the regeneration. There is no limit to the number of repetitions, and it can continue until the user is satisfied with the generated result. In each regeneration cycle, all of the accumulated feedback information may be used as input, or only the most recent feedback information may be used as input.

[0107] In this configuration, by including a feedback acquisition unit 116 and a regeneration unit 117, recruiters can complete job postings and scouting documents while confirming and correcting the content of the generated intermediate information, revised job postings, and scouting documents.

[0108] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by each functional unit of the server device 10 may be common to all units, or it may be prepared individually for each functional unit.

[0109] The learning models included in the artificial intelligence unit 120 include, for example, at least one of the following model names: GPT (Generative Pre-trained Transformer) (GPT-1, GPT-2, GPT-3, GPT-4, GPT-5, etc.), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-Regressive Transformers), and other Transformers. Other deep learning models such as Recurrent Neural Networks (RNNs) may also be included. The artificial intelligence unit 120 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. Generative AI may be, for example, text generation AI, image generation AI, multimodal generation AI, etc. The trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 120 can include any pre-trained model.

[0110] The algorithms used to train the learning models included in the artificial intelligence unit 120 include, for example, at least one of the following: K-Nearest Neighbor (KNN), Naive Bayes, Decision Tree, Support Vector Machine (SVM), and Deep Learning.

[0111] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. Furthermore, the trained model may not only be one trained for a specific task, but also a general-purpose learning model that can be used universally for a wide range of tasks.

[0112] The artificial intelligence unit 120 may include a natural language model as artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by One-shot Learning or Few-shot Learning. Furthermore, the general-purpose learning model may also be configured to handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate pre-trained model, or it may be a common general-purpose pre-trained model. In addition, the artificial intelligence unit 120 may include a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model as a pre-trained model. Small-scale and medium-scale language models are natural language processing models that are trained on less data (and constructed with fewer parameters) compared to large-scale language models.

[0113] The pre-trained models included in the artificial intelligence unit 120 (such as the job posting creation model, which are used in each functional unit) can undergo additional training using methods such as transfer learning and fine-tuning. For example, whenever new data is registered, the artificial intelligence unit 120 may perform additional training and fine-tuning using this new data as training data. This improves the accuracy of the information output from the pre-trained models.

[0114] The trained model included in the artificial intelligence unit 120 may be a trained model (distilled model) obtained by knowledge distillation using the original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as the teacher model, and the student model is trained by adjusting the parameters of the student model so that the loss of the student model's output relative to the teacher model's output (Soft Target Loss) 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 relative to the correct labels (Hard Target) of the teacher data (combinations of input 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.

[0115] An AI agent (also called an autonomous agent) is a model that, upon input of a goal (objective, purpose, etc.) such as "Teach me about XX" or a task such as "Output XX," breaks down the processes necessary to reach the goal or accomplish the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, outputs information according to the goal, and does not require user intervention (operation input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously learn in order to aim for goal achievement. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.).

[0116] In particular, the artificial intelligence unit 120 may be an external component of the information processing system 1. In that case, each functional unit inputs input information to the external artificial intelligence unit 120, instructs it to generate output, and obtains the output. In this way, various external artificial intelligence services (for example, OpenAI's GPT, Google's Gemini, etc.) can be used to generate output.

[0117] <Display section> The display unit 211 of the job seeker terminal 20 shown in Figure 4B, and the display unit 311 of the job seeker terminal 30 shown in Figure 4C, respectively, display the screen (information) indicated by the data transmitted from the server device 10.

[0118] <Operation acquisition part> The operation acquisition unit 212 of the employer terminal 20 receives operations from the employer using the employer terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 receives operations from the job seeker using the job seeker terminal 30.

[0119] 3. Information Processing Methods This section describes the information processing method of the server device 10. In this information processing method, each part of the server device 10 is executed by a computer as a step.

[0120] The above-described information processing method comprises an acquisition step, an intermediate information generation step, an output generation step, a classification step, a display control step, and an output control step. In the acquisition step, job information and recruiter information are acquired. In the intermediate information generation step, intermediate information including target information and message information is generated based on the job information and recruiter information. In the output generation step, at least one of revised job information and a scout document is generated based on the intermediate information. In the classification step, the message information is classified by target information or by appeal category. In the display control step, the classified message information is displayed on the screen according to its classification. In the output control step, at least one of the revised job information and the scout document is output in association with the intermediate information.

[0121] Figure 8 is an activity diagram showing an example of the flow of information processing (recruitment target and scout document generation process) performed by Information Processing System 1. The following will explain the information processing in accordance with each activity in this activity diagram.

[0122] The recruitment target and scout document generation process is triggered by the input of job information via the job information input screen JA from the recruiter terminal 20. The acquisition unit 111 acquires job information and recruiter information based on the entered job identification information, etc. (Activity A101). The acquisition unit 111 performs web crawling, etc., on the recruiter's website, etc., and acquires publicly available information about the recruiter by category (Activity A102). Subsequently, the intermediate information generation unit 112 generates intermediate information including target information and message information based on the acquired job information and recruiter information and first reference information (Activity A103).

[0123] Specifically, the target information generation unit 112a generates target information based on job information, recruiter information, and third reference information, and then the message information generation unit 112b generates message information based on the target information, job information, recruiter information, and fourth reference information. The classification unit 114 classifies the generated message information by appeal category (Activity A104), and the display control unit 115 displays the classified message information and target information on the target / message display screen TM (Activity A105). In response to the recruiter's instructions, the output generation unit 113 generates at least one of the revised job information and the scout document based on the intermediate information and the second reference information (Activity A106), and the display control unit 115 outputs the revised job information and the scout document to the recruiter terminal 20 in association with the intermediate information (Activity A107). This completes the recruitment target and scout document generation process (Activity A108).

[0124] 4. Effect The operation of this embodiment can be summarized as follows: Based on job postings and employer information, recruitment targets and appeal messages can be generated, and revised job postings or scouting documents can be created based on the generated results. In particular, by generating intermediate information including target information and message information based on job postings, employer information and first reference information, and generating revised job postings and scouting documents based on this intermediate information and second reference information, the efficiency and quality of recruitment activities can be improved.

[0125] Furthermore, by having the acquisition unit 111 acquire publicly available information from job seekers through web crawling, etc., it becomes possible to utilize highly comprehensive job seeker information. This makes it possible to generate job postings and recruitment documents that do not depend on the experience or knowledge of recruiters, etc.

[0126] Furthermore, the classification unit 114 classifies message information by appeal category, and the display control unit 115 displays the classified message information on the screen, allowing job seekers to visually grasp the company's selling points.

[0127] Furthermore, the display control unit 115 outputs the revised job posting information and scouting document in association with the intermediate information, allowing the recruiter to confirm the target information and message information that form the basis of the generated job posting and scouting document.

[0128] 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.

[0129] The above embodiments are merely one embodiment of the present invention, and the present invention is not limited thereto. Modifications of the above embodiments will be described below.

[0130] In the above embodiment, an example of acquiring job information by inputting job identification information or information to be entered in a job posting has been described, but the method of acquiring job information is not limited to this. For example, job information may be constructed from information obtained through a conversational interview with the employer. Alternatively, job information may be constructed by combining multiple job postings. Furthermore, the server device 10 may periodically crawl the web to acquire job information, and the employer may select from the acquired job information.

[0131] In the above embodiment, an example was described in which the acquisition unit 111 acquires publicly available information of job seekers by web crawling, but the acquisition method is not limited to this. For example, job seeker information may be acquired through a form in which the job seeker directly inputs their own information. Alternatively, job seeker information may be extracted from documents such as PDFs and Word documents provided by the job seeker. Furthermore, information may be acquired from the job seeker's SNS account or video content. These acquisition methods may be used individually or in combination.

[0132] The above embodiment describes an example of outputting revised job postings and recruitment documents, but the output format is not limited to this. For example, the output may be in a format suitable for a specific medium (job change service, job site, etc.) specified by the employer on the job posting input screen JA, etc. Furthermore, the revised job postings may be directly linked to the employer's internal system (recruitment management system, talent management system, etc.). In addition, recruitment documents may be individually customized and generated for each of the multiple candidates.

[0133] Each of the above modifications may be applied individually, or multiple modifications may be applied in combination. Furthermore, each element of the above embodiments and modifications may be appropriately combined and implemented by those skilled in the art.

[0134] 5. Others In the above embodiment, the server device 10 performed various storage and control functions, but instead of the server device 10, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the external artificial intelligence unit 120 may be provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using an LLM. The artificial intelligence service server receives prompt input in the form of text, images, audio, etc., and generates and responds with answers to the prompts.

[0135] 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.

[0136] The control unit 11 does not necessarily have to include a target information generation unit 112a, a message information generation unit 112b, a scout document modification unit 113a, a classification unit 114, and a display control unit 115. In other words, the information processing system 1 does not necessarily have to have a function to independently generate target information, a function to independently generate message information, a scout document modification function, a classification function, and a classification-based display function. For example, the information processing system 1 does not need to have at least one of these functions.

[0137] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. In the information processing method, the information processing device executes each step of the information processing system 1. In the program, the computer causes the computer to execute each step of the information processing system 1.

[0138] The product may be provided in any of the following embodiments.

[0139] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, wherein in the acquisition step, it acquires job information and employer information which is information relating to an employer corresponding to the job information, the job information includes at least a job posting; in the first generation step, it generates intermediate information based on the job information, the employer information and first reference information, wherein the first reference information includes at least a correlation between the job information and the employer information and the intermediate information, the intermediate information includes target information indicating the profile of a person to be hired in the job information and message information indicating the appeal of the job related to the job information; and in the second generation step, it generates at least one of modified job information which is a modified version of the job information and a scout document corresponding to the job information, based on the job information, the intermediate information and second reference information, wherein the second reference information includes at least a correlation between the job information and the intermediate information and at least one of the modified job information and the scout document.

[0140] (2) In the information processing system described in (1) above, the job information includes a reference scout document, wherein the reference scout document is a scout document corresponding to the job application or a sample scout document, and in the second generation step, the system generates the scout document by modifying the reference scout document based on the job information including the reference scout document, the intermediate information and the second reference information, wherein the second reference information includes at least the correlation between the job information including the reference scout document, the intermediate information and the scout document.

[0141] (3) An information processing system as described in (1) or (2) above, wherein in the acquisition step, the system accepts the input of job identification information that identifies the job, or at least a part of the information described in the job application form, as information that identifies the job information, and acquires the job information based on the input.

[0142] (4) An information processing system according to any one of (1) to (3) above, wherein the acquisition step acquires personnel information relating to personnel who may be candidates for employment related to the job posting, wherein the personnel information includes at least one of information indicating the recipient of a scouting history of other job postings similar to the job posting, and personnel list information indicating a list of personnel, and the first generation step generates the intermediate information based on the job posting, the recruiter information, the personnel information, and the first reference information, wherein the first reference information includes at least the correlation between the job posting, the recruiter information, the personnel information, and the intermediate information.

[0143] (5) An information processing system according to any one of (1) to (4) above, wherein the first reference information includes third reference information and fourth reference information, and in the first generation step, the target information is generated based on the job information, the recruiter information and the third reference information, wherein the third reference information includes at least the correlation between the job information and the recruiter information and the target information, and the message information is generated based on the job information and the recruiter information and the target information and the fourth reference information, wherein the fourth reference information includes at least the correlation between the job information and the recruiter information and the target information and the message information.

[0144] (6) An information processing system according to any one of (1) to (5) above, wherein the processor is configured to further perform the following steps: in a display control step, the processor displays at least one of the intermediate information, the revised job information, and the scout document as display information on a user terminal; in a feedback acquisition step, the processor acquires input of feedback information for the display information from the user terminal, where the feedback information is information including at least one of the revision and evaluation of the display information; and in a regeneration step, the processor regenerates at least one of the intermediate information, the revised job information, and the scout document based on the feedback information.

[0145] (7) An information processing system according to any one of (1) to (6) above, wherein in the acquisition step, additional information relating to the employer is acquired as employer information by web crawling based on at least some of the information contained in the job information or the employer information, wherein the additional information includes information relating to at least one of the employer's philosophy, vision, business content, products or services, business environment, management policy, organizational characteristics, job characteristics of the job, and working conditions, and in the first generation step, the intermediate information is generated based on the job information, the employer information including the additional information, and the first reference information.

[0146] (8) An information processing system as described in (7) above, wherein in the acquisition step, an instruction is given to the AI ​​to acquire the additional information relating to the attractiveness of the job by web crawling, and the AI ​​acquires the additional information by web crawling in accordance with the instruction.

[0147] (9) An information processing system as described in (7) or (8) above, wherein the acquisition step involves web crawling at least one of the following: the recruiter's website, the recruiter's disclosure information, articles concerning the recruiter's employees, information concerning the recruiter's products or services, and evaluation information concerning the recruiter.

[0148] (10) An information processing system according to any one of (1) to (9) above, wherein the processor is configured to further perform the following steps: in the classification step, classify the message information according to the target information corresponding to the message information, or according to the appeal content of the job posting included in the message information; and in the display control step, display the classified message information according to its classification.

[0149] (11) An information processing system as described in (10) above, wherein the classification step classifies the message information according to the appeal content of the job posting, which includes at least one of the following: business, vision, growth, opportunities, work, job satisfaction, compensation, and environment.

[0150] (12) An information processing system according to any one of (1) to (11) above, wherein the processor is configured to further perform the following steps, and in the display control step, it displays at least one of the modified job information and the scout document in association with the intermediate information.

[0151] (13) An information processing system according to any one of (1) to (12) above, comprising a server having the processor and a terminal that can access the server.

[0152] (14) An information processing method comprising each step performed by the information processing system described in any one of (1) to (12) above.

[0153] (15) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (12) above. Of course, this is not always the case.

[0154] 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]

[0155] 1: Information Processing System 10: Server device 11: Control Unit 111: Acquisition Department 112: Intermediate Information Generation Unit 112a: Target information generation unit 112b: Message information generation unit 113: Output generation unit 113a: Scout Document Revision Section 114: Classification section 115: Display Control Unit 116: Feedback acquisition unit 117: Regeneration section 12: Storage section 120: Artificial Intelligence Department 13: Communications Department 14: Communications bus 2: Communication lines 20: Job seeker terminal 21: Control Unit 211: Display section 212: Operation acquisition section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 30: Job seeker terminal 31: Control Unit 311: Display section 312: Operation acquisition section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communications bus B21: Select button B22: Cancel button B31: Button to generate revised job information B32: Scout Document Generation Button CI: Job Posting Information Display Screen CI1: Job seeker information category area CI2: Recruiter information display area JA: Job posting input screen JA1: Job identification information input area JA2: Job posting text input area JA3: Job applicant information input area TM: Target message display screen TM1: Target information display area TM2: Message information display area U1: 1st job applicant U2: Second-choice applicant U3: 1st job applicant U4: 2nd job applicant

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, job information and employer information, which is information about the employer corresponding to the job information, are acquired, and the job information includes at least a job posting. In the first generation step, intermediate information is generated based on the job information, the applicant information, and the first reference information, and here, The first reference information includes at least the correlation between the job information and the job seeker information and the intermediate information, The aforementioned intermediate information includes target information indicating the profile of the person to be hired in the job posting, and message information indicating the appeal of the job posting related to the job posting. In the second generation step, the information processing system generates modified job information, which is a modified version of the job information, and at least one of the scout document corresponding to the job information, based on the job information, the intermediate information, and the second reference information, wherein the second reference information includes at least the correlation between the job information, the intermediate information, the modified job information, and at least one of the scout document.

2. In the information processing system described in claim 1, The aforementioned job information includes a reference scouting document, where the reference scouting document is a scouting document corresponding to the job posting, or a sample scouting document. In the second generation step, an information processing system generates a scout document by modifying the reference scout document based on the job information including the reference scout document, the intermediate information, and the second reference information, wherein the second reference information includes at least the correlation between the job information including the reference scout document, the intermediate information, and the scout document.

3. In the information processing system described in claim 1, In the acquisition step, the information processing system accepts the input of job identification information that identifies the job, or at least a portion of the information described in the job application form, as information that identifies the job information, and acquires the job information based on the input.

4. In the information processing system described in claim 1, In the acquisition step, personnel information relating to individuals who may be candidates for employment related to the job posting is acquired, wherein the personnel information includes at least one of the following: information indicating the recipient of a scouting history included in other job postings similar to the job posting, and personnel list information indicating a list of the individuals. An information processing system that, in the first generation step, generates the intermediate information based on the job information, the employer information, the personnel information, and the first reference information, wherein the first reference information includes at least the correlation between the job information, the employer information, the personnel information, and the intermediate information.

5. In the information processing system described in claim 1, The aforementioned first reference information includes the third reference information and the fourth reference information, In the first generation step, Based on the job information, the employer information, and the third reference information, the target information is generated, wherein the third reference information includes at least the correlation between the job information, the employer information, and the target information. An information processing system that generates message information based on the job information, the recruiter information, the target information, and the fourth reference information, wherein the fourth reference information includes at least the correlation between the job information, the recruiter information, the target information, and the message information.

6. In the information processing system described in claim 1, The aforementioned processor is configured to perform the following steps: In the display control step, at least one of the intermediate information, the revised job information, and the scout document is displayed on the user terminal as presentation information. In the feedback acquisition step, feedback information regarding the presented information is obtained from the user terminal, where the feedback information includes at least one of corrections and evaluations of the presented information. An information processing system that, in the regeneration step, regenerates at least one of the intermediate information, the revised job information, and the scout document based on the feedback information.

7. In the information processing system described in claim 1, In the acquisition step, additional information about the employer is acquired as employer information by web crawling based on at least some of the information contained in the job information or employer information, wherein the additional information includes information about at least one of the employer's philosophy, vision, business content, products or services, business environment, management policy, organizational characteristics, job characteristics of the job, and working conditions. An information processing system that generates the intermediate information in the first generation step based on the job information, the applicant information including the additional information, and the first reference information.

8. In the information processing system described in claim 7, The information processing system provides the AI ​​with instructions to acquire the additional information regarding the attractiveness of the job posting by web crawling in the acquisition step, and the AI ​​acquires the additional information by web crawling in accordance with the instructions.

9. In the information processing system described in claim 7, An information processing system that, in the acquisition step, web crawls at least one of the following: the employer's website, the employer's disclosure information, articles about the employer's employees, information about the employer's products or services, and evaluation information about the employer.

10. In the information processing system described in claim 1, The aforementioned processor is configured to perform the following steps: In the classification step, the message information is classified according to the target information corresponding to the message information, or according to the appeal content of the job posting included in the message information. The display control step involves an information processing system that displays the classified message information according to its classification.

11. In the information processing system according to claim 10, An information processing system that, in the classification step, classifies the message information according to the appeal of the job posting, which includes at least one of the following: business, vision, growth, opportunities, work, job satisfaction, compensation, and environment.

12. In the information processing system described in claim 1, The aforementioned processor is configured to perform the following steps: An information processing system that, in the display control step, displays at least one of the modified job information and the scout document in association with the intermediate information.

13. In the information processing system according to any one of claims 1 to 12, A server having the aforementioned processor, An information processing system comprising a terminal capable of accessing the aforementioned server.

14. An information processing method, An information processing method comprising each step performed by the information processing system according to any one of claims 1 to 12.

15. 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 12.

Images