Information processing system, information processing method and program

Abstract

To provide an information processing system etc. that can recommend job offers that are more suitable for job seekers. [Solution] According to one aspect of the present invention, there is provided an information processing system having at least one processor, which, in a first acquisition step, acquires job information regarding a job vacancy from an employer, in a second acquisition step, presents a first question to a job seeker, acquires a response to the first question from the job seeker, inputs the response into a large-scale language model, generates the next question, and acquires a response to the next question by repeating this process to acquire job seeker information including the response, in an identification step, identifies recommended job information to recommend to the job seeker based on the job information, the acquired job seeker information, and first reference information, the first reference information including at least the relationship between the job information, the job seeker information, and the recommended job information, and in an output step, outputs the identified recommended job information.

Description

[Technical Field]

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

[0002] Patent Document 1 discloses an information processing technology for matching job offers with job seekers. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-79900 Summary of the Invention [Problem to be solved by the invention]

[0004] There is room for improvement in the technology used to match job openings with job seekers.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can recommend job offers that are more suited to job seekers. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system having at least one processor, which includes: a first acquisition step of acquiring job information regarding a job vacancy from an employer; a second acquisition step of repeating the process of presenting a first question to a job seeker, acquiring a response to the first question from the job seeker, inputting the response into a large-scale language model, generating a next question, and acquiring a response to the next question, thereby acquiring job seeker information including the response; an identification step of identifying recommended job information to recommend to the job seeker based on the job information, the acquired job seeker information, and first reference information, the first reference information including at least the relationship between the job information, the job seeker information, and the recommended job information; and an output step of outputting the identified recommended job information.

[0007] According to this aspect, it is possible to provide an information processing system or the like that can recommend job offers that are more suited to job seekers. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] FIG. 2 is a block diagram showing the hardware configuration of the server 2. [Figure 3] 3 is a block diagram showing the hardware configuration of a job seeker terminal 3. FIG. [Figure 4] 2 is a block diagram showing functions realized by a server 2 (control unit 23), a job seeker terminal 3 (control unit 33), a recruiter terminal 4 (control unit 43), and an intermediary terminal 5 (control unit 53). [Figure 5] FIG. 2 is a diagram showing an outline of processing executed by the information processing system 1. [Figure 6] 2 is an activity diagram showing an example of the flow of information processing according to the first embodiment, which is executed by the information processing system 1. FIG. [Figure 7] FIG. 10 is an activity diagram showing an example of the flow of information processing according to the second embodiment, which is executed by the information processing system 1. [Figure 8] FIG. 10 is a diagram showing a screen G1 as an example of an output screen. [Figure 9] FIG. 10 is a diagram showing a screen G2 which is an example of a chat screen. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0011] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. 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 formula constructed using a statistical method), a trained model that has previously learned the correlation between input and output, or a generative AI such as a large-scale language model (these models include parameters that establish the correlation between input and output) or a visual language model that can output a desired result in response to a prompt.

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

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

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

[0015] <Information Processing System 1> FIG. 1 is a configuration diagram illustrating an information processing system 1. The information processing system 1 includes a server 2, a job seeker terminal 3, a recruiter terminal 4, and an intermediary terminal 5. The server 2, the job seeker terminal 3, the recruiter terminal 4, and the intermediary terminal 5 are configured to be able to communicate with each other via a telecommunications line (network). In an exemplary embodiment, the job seeker terminal 3 can function as a job seeker terminal. The recruiter terminal 4 can function as a recruiter terminal. The intermediary terminal 5 can function as an intermediary terminal. Here, the system exemplified by the information processing system 1 is comprised of one or more devices or components. Therefore, it should be noted that the information processing system 1 includes the server 2 alone, the server 2 and the job seeker terminal 3, the server 2 and the recruiter terminal 4, or the server 2 and the intermediary terminal 5. More specifically, the information processing system 1 may include an element selected from the group consisting of the server 2, the job seeker terminal 3, the recruiter terminal 4, and the intermediary terminal 5. The unselected elements may be electrically connected to the selected elements as external elements, and may not be included in the information processing system 1. These components will be described below.

[0016] The information processing system 1 constitutes at least a part of a recruitment and job search system used by, for example, multiple job seekers U1 and multiple recruiters U2. The information processing system 1 mainly performs searches for job seekers by recruiters and searches for job openings by job seekers. In one embodiment, the information processing system 1 is comprised of one or more devices or components. The information processing system 1 provides and manages a talent matching platform and talent matching services used by job seekers. These components are described below.

[0017] <Server 2> 2 is a block diagram showing the hardware configuration of server 2. Server 2 includes a communication unit 21, a storage unit 22, and a control unit 23, and these components are electrically connected via a communication bus 20 inside server 2. Each component will be further described below.

[0018] The communication unit 21 is configured by a communication module. The communication module may be a wireless communication module conforming to standards such as IEEE802.11a / b / g / n / ac / ax, LTE, 5G, or 6G, or may be a wired communication module conforming to standards such as IEEE802.3. The communication unit 21 is configured to be able to transmit various electrical signals from the server 2 to external components. The communication unit 21 is also configured to be able to receive various electrical signals from the external components to the server 2. More preferably, the communication unit 21 has a network communication function, which allows various information to be communicated between the server 2 and external devices via a network.

[0019] The memory unit 22 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server 2 executed by the control unit 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The memory unit 22 stores various programs, variables, etc. related to the server 2 executed by the control unit 23.

[0020] The control unit 23 processes and controls the overall operations related to the server 2. The control unit 23 is, for example, a central processing unit (CPU) not shown. The control unit 23 realizes various functions related to the server 2 by reading out predetermined programs stored in the storage unit 22. In other words, information processing by software stored in the storage unit 22 is specifically realized by the control unit 23, which is an example of hardware, and each step related to each function described below can be executed. This will be described in further detail in the next section. Note that the control unit 23 is not limited to being single, and multiple control units 23 may be provided for each function. A combination of these may also be used.

[0021] <Job Seeker Terminal 3> The job seeker terminal 3 is an information processing device used by the job seeker U1. The "job seeker" includes, for example, a person looking to change jobs, a prospective new graduate (job seeker), etc., and may also include a person who is currently looking for a new job or job, or a person who is interested in changing jobs or finding employment.

[0022] 3 is a block diagram showing the hardware configuration of the job seeker terminal 3. The job seeker terminal 3 includes a communication unit 31, a memory unit 32, a control unit 33, a display unit 34, and an input unit 35, and these components are electrically connected via a communication bus 30 inside the job seeker terminal 3. Each component will be further described below. The description of the communication unit 31, memory unit 32, and control unit 33 will be omitted as they are the same as the description of each unit in the server 2.

[0023] The display unit 34 may be included in the housing of the job seeker terminal 3 or may be attached externally. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. This is preferably implemented by using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display, depending on the type of job seeker terminal 3.

[0024] The display unit 34 displays a screen indicated by the screen data transmitted from the server 2. The display unit 34 displays a system screen relating to the information processing system 1 indicated by the screen data transmitted from the server 2.

[0025] The input unit 35 may be included in the housing of the job seeker terminal 3, or may be attached externally. For example, the input unit 35 may be implemented as a touch panel integrated with the display unit 34. A touch panel allows the user to input operations such as tapping and swiping. Of course, switch buttons, a mouse, a QWERTY keyboard, etc. may be used instead of a touch panel. In other words, the input unit 35 accepts operation inputs made by the user. The inputs are transferred as command signals to the control unit 33 via the communication bus 30, and the control unit 33 can execute predetermined control and calculations as necessary.

[0026] <Recruiter Terminal 4> The recruiter terminal 4 is an information processing terminal used by the recruiter. "Recruiters" include organizations such as profit-making corporations (e.g., companies), non-profit corporations (e.g., cooperatives, incorporated foundations), and public corporations (e.g., local governments) or their personnel. Here, the personnel may be called recruiters, and may include personnel in the human resources department of an organization or personnel in the department seeking to hire personnel.

[0027] The recruiter terminal 4 comprises a communication unit 41, a memory unit 42, a control unit 43, a display unit 44, and an input unit 45, and these components are electrically connected within the recruiter terminal 4 via a communication bus 40. Each component will be further described below. The description of the communication unit 41, memory unit 42, and control unit 43 will be omitted as they are the same as the description of each unit in the server 2. The description of the display unit 44 and input unit 45 will be omitted as they are the same as the description of each unit in the job seeker terminal 3.

[0028] <Intermediary Terminal 5> The intermediary terminal 5 is an information processing terminal used by the intermediary. "Intermediaries" include human resource agencies and recruitment agencies that act as intermediaries between job seekers and employers. Human resource agencies are also called headhunters, agents, etc.

[0029] The intermediary terminal 5 comprises a communication unit 51, a memory unit 52, a control unit 53, a display unit 54, and an input unit 55, and these components are electrically connected within the intermediary terminal 5 via a communication bus 50. Each component will be further described below. The description of the communication unit 51, memory unit 52, and control unit 53 is omitted as they are similar to the description of each unit in the server 2. The description of the display unit 54 and input unit 55 is omitted as they are similar to the description of each unit in the job seeker terminal 3.

[0030] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the storage unit 22 is specifically realized by the control unit 23, which is an example of hardware, and can be executed as each functional unit included in the control unit 23 (at least one processor included in the information processing system 1).

[0031] FIG. 4 is a block diagram showing functions realized by the server 2 (controller 23), job seeker terminal 3 (controller 33), recruiter terminal 4 (controller 43), and intermediary terminal 5 (controller 53).

[0032] Fig. 4A is a block diagram showing functions realized by the control unit 23. As shown in Fig. 4A, the control unit 23 includes an acquisition unit 231, an identification unit 232, an output unit 233, a generation unit 234, an estimation unit 235, an assignment unit 236, a display control unit 237, an addition unit 238, a determination unit 239, a reception unit 240, an execution unit 241, a recording unit 242, a calculation unit 243, and an artificial intelligence unit 244.

[0033] As shown in Fig. 4B, the job seeker terminal 3 (control unit 33) includes a display unit 331 and an operation acquisition unit 332. As shown in Fig. 4C, the recruiter terminal 4 (control unit 43) includes a display unit 431 and an operation acquisition unit 432. As shown in Fig. 4D, the intermediary terminal 5 (control unit 53) includes a display unit 531 and an operation acquisition unit 532.

[0034] <Acquisition part 231> The acquisition unit 231 is configured to be able to acquire information from the job seeker terminal 3 or other devices. The acquisition unit 231 is also configured to be able to accept various pieces of information by reading out various pieces of information stored in a storage area that is at least a part of the memory unit 22 and writing the read out information in a work area that is at least a part of the memory unit 22. The storage area is, for example, an area of ​​the memory unit 22 that is implemented as a storage device such as an SSD. The work area is, for example, an area that is implemented as a memory such as a RAM.

[0035] <First acquisition step> In the first acquisition step, the acquisition unit 231 acquires job information from a recruiter. Job information includes "information acquired from the web," "information acquired from job information," "information acquired through interviews," and the like. "Information acquired from the web" is information acquired by the acquisition unit 231 accessing a website that lists recruiters and job offers and collecting information about the recruiters and job offers listed on the website using techniques such as crawling. "Information acquired from the web" includes the recruiter's "management issues and business issues," "business strategy and vision," "business content," "employee benefits," "corporate culture and organizational climate," "career path and promotion opportunities," and "salary and compensation system." Information acquired from job information is information acquired from information in a specific job posting. "Information acquired from job information" includes "recruitment background," "job content and responsibilities," "required skills and experience," and the like. The acquisition unit 231 can acquire this information from a specific job posting using natural language processing of text data, etc. A specific job posting may be acquired by uploading a file, or by specifying access information (e.g., a URL) for a website or folder containing the specific job posting. Information acquired through interviews is information acquired by interviewing the employer. Interviews with the employer include interviews with the employer's recruiting staff. "Information acquired through interviews from the employer" includes "position details," "expected results," "desired person and behavior type," and "non-negotiable personnel conditions." As a first acquisition step, the acquisition unit 231 presents a second question to the employer and acquires a response to the second question from the employer. The acquisition unit 231 presents the next question generated by the large-scale language model based on the acquired response, and repeats the process of acquiring a response to the next question. Information acquired through interviews can be acquired in this manner. This makes it possible to acquire information that cannot be acquired from websites or job postings, thereby improving the accuracy of matching.

[0036] The process in which the acquisition unit 231 presents a question to a recruiter or a job seeker and obtains a response to the question is referred to as an interview. The information obtained through this process is referred to as "information obtained through an interview." Specifically, the acquisition unit 231 presents a question (initial question) and obtains a response from the recruiter or the job seeker. The acquisition unit 231 inputs the obtained response into a language model such as a large-scale language model, analyzes the large-scale language model, and generates a next question to elicit information from the recruiter or the job seeker based on the analysis results. The acquisition unit 231 presents the generated next question and obtains a response to the next question from the recruiter or the job seeker. The interview is performed by repeating this cycle until a predetermined end condition is met (when the required items are met or when the recruiter or the like gives an instruction to end the interview).

[0037] <Second acquisition step> The acquisition unit 231 is configured to be able to acquire input based on terminal operation by the job seeker U1 on the job seeker terminal 3. Specifically, the acquisition unit 231 is configured to be able to acquire input by the job seeker U1. The acquisition unit 231 may acquire job seeker information U11 of the job seeker U1 via the job seeker terminal 3.

[0038] The acquisition unit 231 is configured to acquire input from the job seeker U1. For example, the acquisition unit 231 may accept input from the job seeker U1 via a chat screen displayed on the display unit 34 of the job seeker terminal 3. The acquisition unit 231 may also acquire job seeker information related to the job seeker from a job seeker database. The job seeker database stores job seeker information used by the job seeker U1 in his or her job search activities. Job seeker information is information about the job seeker, including pre-registered job seeker information entered on the registration screen and all registered or entered information about the job seeker. Job seeker information includes a resume and a curriculum vitae, and includes information about the job content. A "resume" is a document that primarily contains the job seeker's profile, current situation, educational background, work history, desired working conditions, etc., while a "curriculum vitae," also known as a resume, is a document in which the job seeker conveys their work history, experience, skills, qualifications, etc. to the employer. The information about the job content includes information about the organizations in which the job seeker U1 has worked, and information describing the job duties and tasks performed in the organizations. The job content may include, for example, the job seeker's previous organizations, department names, job titles, employment periods, positions held, tasks held, projects held, specific achievements and results, work periods, the job seeker's management experience, language skills, awards, qualifications held, skills held, and highest level of education.

[0039] In a second acquisition step, the acquisition unit 231 presents a first question to the job seeker and acquires a response to the first question from the job seeker. In the second acquisition step, the acquisition unit 231 inputs the response into a large-scale language model, generates the next question, and acquires the response to the next question, repeating the process to acquire job seeker information including the response. In this manner, the acquisition unit 231 can specify the job seeker's desired "career vision and future image," "important values," "reason and motivation for changing jobs," "corporate culture and climate for the company to which the job seeker is applying," "important work style," and "desires (annual salary, work location, benefits)." This allows the acquisition of job seeker information not contained in resumes or curriculum vitae, thereby improving the accuracy of matching with job information and providing appropriate career support to the job seeker.

[0040] The acquisition unit 231 can acquire the behavioral history of the job seeker U1's job search activities in the information processing system 1. The behavioral history of the job seeker U1's job search activities includes the job seeker U1's actions regarding job postings and the job seeker U1's actions in the information processing system 1. The job seeker U1's actions regarding job postings include, for example, viewing job postings, applying for job postings, registering job postings in a bookmark list, replying to scouting messages sent based on job postings, and passing job posting screenings (document screening, interview screening, etc.). The job seeker U1's actions regarding job postings are composed of, for example, information indicating the job posting that was the target or starting point of the job search and the details of the job search activities. The job seeker U1's actions in the information processing system 1 include the number of times the job seeker U1's job seeker information (registered information) is updated, the frequency of updates, the number of times the job seeker information registration screen is displayed, the frequency of display, the number of times messages are checked, the frequency of checking, etc. The job-seeker U1's job-seeking behavior history is recorded for each job seeker (i.e., linked to job seeker information) in, for example, a job seeker database.

[0041] The information processing system 1 according to the present embodiment may provide continuous support for the career of job seeker U1 over time, and may be configured to acquire job seeker information over time. Here, "continuous support" refers to providing support for job seeker U1 at multiple stages in his / her career, such as (a) when job seeker U1 first starts a job search (e.g., when job seeker U1 first starts job hunting or when job seeker U1 already working at an organization starts job hunting for the first time), (b) when job seeker U1 is working at the organization where job seeker U1 found employment as a result of job hunting, (c) when job seeker U1 is considering changing jobs and conducting another job search, (d) when job seeker U1 is working at the organization where job seeker U1 found employment as a result of job hunting, or (e) when job seeker U1 repeats these stages multiple times, and may also refer to acquiring job seeker information at multiple stages in his / her career.

[0042] The acquisition unit 231 may acquire responses from the job seeker U1 at multiple stages in the job seeker U1's career. The timing for acquiring the response may be the timing when the determination unit 239 determines that a predetermined condition is met, or may be a preset timing. Furthermore, the acquisition unit 231 may acquire an input or a response when an input (for example, an input by voice or text) or a response is made from the job seeker U1.

[0043] Examples of cases in which an input or a response is acquired at the timing when the determination unit 239 determines that a predetermined condition is satisfied include, but are not limited to, the following: In a second acquisition step, when the behavioral history of the job seeker satisfies a predetermined condition, the acquisition unit 231 presents a question to the job seeker and acquires a response to the question, thereby acquiring job seeker information including the response. For example, the acquisition unit 231 acquires the response of the job seeker when the behavioral history of the job seeker U1 satisfies a predetermined condition. For example, the determination unit 239 analyzes the behavioral history, past responses, etc. of the job seeker U1 to determine whether the predetermined condition is satisfied. When the determination unit 239 determines that the predetermined condition is satisfied, the acquisition unit 231 presents a question to the job seeker and acquires a response to the question, thereby acquiring job seeker information including the response. In this way, by actively presenting a question to the job seeker U1 from the information processing system 1 and engaging in a dialogue with the job seeker U1 at a predetermined timing, it is possible to encourage a response from the job seeker U1. This allows, for example, even if the job seeker does not voluntarily access the information processing system 1, to facilitate the acquisition of job seeker information, thereby enabling appropriate support to be determined and provided to the job seeker U1. The determination unit 239 may quantify multiple indicators included in the behavioral history and determine that a predetermined condition is met when the numerical value exceeds a threshold. If the determination unit 239 determines that the predetermined condition is met, the acquisition unit 231 presents a question to the job seeker U1. Here, as a second acquisition step, the acquisition unit 231 may present a question based on the job seeker's behavioral history. The acquisition unit 231 may provide various support contents based on the behavioral history of the job seeker U1. Examples of the support contents include "initial usage support," "job change interview," and "interview preparation." The "initial usage support" may include a functional explanation of the talent matching platform or talent matching service provided by the information processing system 1, guidance on entering a profile, etc., and is provided immediately after a new user registers with the talent matching platform or talent matching service. A "job change interview" is a consultation about changing jobs, advice on self-promotion, etc., and is conducted, for example, when behavior that suggests starting job hunting is determined."Interview preparation" includes providing expected questions and answers for a job interview with an employer, conducting a mock interview, and providing feedback, and is carried out, for example, when it is determined that an interview with an employer has been confirmed.

[0044] Examples of cases in which the acquisition unit 231 acquires a response from the job seeker U1 at a predetermined timing include, but are not limited to, the following. The acquisition unit 231 may present a question to the job seeker U1 and acquire a response at a predetermined interval. For example, the acquisition unit 231 may periodically acquire a response from the job seeker U1, such as once a year or once a quarter. Furthermore, the acquisition unit 231 may, in response to an input from the job seeker U1, present a question in response to the input and acquire an additional response from the job seeker U1. For example, the acquisition unit 231 may provide career support, such as career counseling, to the job seeker U1 by repeatedly acquiring an input from the job seeker U1 regarding career consultations or concerns, analyzing the acquired input using a language model such as a large-scale language model, generating questions in response to the input and responses from the job seeker U1, and acquiring responses to the questions from the job seeker U1.

[0045] The acquisition unit 231 accumulates the questions presented and the inputs and responses acquired from the job seeker U1, thereby improving the accuracy of analysis using large-scale language models, etc., and enabling career support that is more tailored to the job seeker U1.

[0046] The information processing system 1 may not only recommend a job offer only once, but may also store responses from previous communications over multiple occasions, allowing the same object (agent) to accompany the job seeker U1 throughout his or her first job search (e.g., a job search during student days or the first job change after employment) and even subsequent job searches. As a second acquisition step, the acquisition unit 231 presents questions and acquires responses to the questions at multiple times via a user interface with a common configuration or display format. This enables support from the second time onward to be provided at the optimal timing based on past inputs and responses, and by continuously presenting questions via a unified user interface, the job seeker's engagement can be enhanced. Furthermore, the identification unit 232 identifies recommended job offers based on chronological job seeker information. This enables support to be provided to the job seeker U1 throughout his or her career.

[0047] The multiple timings include a first job search stage and a second job search stage. The first job search stage is, for example, immediately after starting or resuming a job search, and the second job search stage is, for example, when applying for a job or having an interview.

[0048] The multiple timings may include at least one of a pre-employment stage and a non-job-seeking stage. The pre-employment stage timing is a job-seeking stage, such as a student period when one first starts job hunting or a job-changing stage when one first starts job-changing. The non-job-seeking stage timing is a stage when job-seeking has ended and one is still employed at a company or other organization, such as a time when one is still employed and has little intention of changing jobs.

[0049] <Specific part 232> The identification unit 232 can identify recommended job information, recommendation grounds, etc. based on the job seeker information and job information. The identification unit 232 can identify various information based on information acquired from users such as the job seeker U1, the employer U2, or the intermediary U3, and reference information.

[0050] <Steps to identify recommended job information> The identification unit 232 identifies recommended job information to recommend to the job seeker based on the job information, the acquired job seeker information, and the first reference information. The first reference information includes at least the relationship between the job information, the job seeker information, and the recommended job information.

[0051] The identification unit 232 identifies recommended job information for the job seeker based on the job information, job seeker information, and reference information for identifying recommended job information (an example of first reference information). The reference information for identifying recommended job information includes at least a correlation between the job information, job seeker information, and recommended job information. The reference information for identifying recommended job information also includes a recommendation model, which is a learning model, an artificial intelligence model, or a generative AI that has been machine-learned to use the job information and the job seeker information as input and output the recommended job information. The reference information for identifying recommended job information may also be a language model, including a large-scale language model or a small-scale language model, or an AI agent for identifying recommended job information. The reference information for identifying recommended job information includes an AI agent that can access the job information and the job seeker information and identify the recommended job information based on that information. The AI ​​agent for identifying recommended job information is an AI agent that can access the job information and the job seeker information and, as an action, identify the recommended job information based on that information.

[0052] For example, the identification unit 232 searches the job information database using a query vector obtained by vectorizing the job seeker information U11 (including input information and registered information) to identify recommended job information. The identification unit 232 may identify recommended job information by comparing the vector data of the job information U21 with the vector data of the job seeker information U11. The identification unit 232 may identify recommended job information based on the proximity of the distance between the vector data of the job seeker information U11 and the vector data of the job information U21. Note that the proximity of the distance between the vector data here may be evaluated using various methods, but typically may be evaluated using the angle formed by the two vectors (cosine similarity). This makes it possible to identify recommended job information with attributes similar to the feature elements included in the job seeker information U11. The identification unit 232 may perform both a keyword search and a vector data search, and use the union or intersection of the search results as the recommended job information. The identification unit 232 vectorizes the feature elements of the job seeker U1 identified from the job seeker information U11 using an embedding model or the like. The identification unit 232 calculates the cosine similarity between the vector data of the job seeker information U11 and the vector data of each job information U21 stored in the job information database, and can identify job openings whose similarity exceeds a predetermined threshold as recommended job information.

[0053] In the recommended job posting identification step, the reference information (recommended job posting identification model) may be a language model or a generation AI including a large-scale language model or a small-scale language model, or may be a learning model trained to input training job seeker information and job postings and output recommended job postings based on the inputs. When the reference information (recommended job posting identification model) is a language model or a generation AI including a large-scale language model or a small-scale language model, the identification unit 232 may input job seeker information U11 and job postings U21 and input an instruction to the language model or the generation AI such as "recommend a job posting based on the degree of match and output the reason (recommendation basis)." Furthermore, the reference information (recommended job posting identification model) may be a model trained on training job seeker information U11 and job postings U21 that satisfy predetermined training conditions, and trained to output a score representing the recommendation ranking or degree of match of the job postings U21. Furthermore, if the recommended job information identification model is a large-scale language model, the identification unit 232 may further input characteristic elements of the job seeker information U11 and input instructions to the language model or generation AI such as "recommend the job that best suits these characteristic elements, and output the recommendation ranking or score representing the degree of match, along with the reason (basis for recommendation)."

[0054] When the identification unit 232 adds the response from the job seeker U1 to the job seeker information, the identification unit 232 may reanalyze the job seeker information using a learning model such as a large-scale language model and identify new recommended job information based on the reanalysis results. The identification unit 232 may also identify recommended job information based on job information U21 that includes the request of the employer U2.

[0055] <Recommendation basis identification step> The identification unit 232 identifies the recommendation basis for the recommended job information based on the recommended job information, job seeker information (or characteristic elements of the job seeker), and reference information for identifying a recommendation basis. The reference information for identifying a recommendation basis includes at least a correlation between the recommended job information, job seeker information (or characteristic elements), and the recommendation basis. The reference information for identifying a recommendation basis also includes an explanatory model, which is a learning model, an artificial intelligence model, or a generative AI, that has been machine-learned to input the recommended job information and job seeker information (or the characteristic elements) and output a recommendation basis. The reference information for identifying a recommendation basis may also be a language model, including a large-scale language model or a small-scale language model, and may also include an AI agent for identifying a recommendation basis. The reference information for identifying a recommendation basis includes an AI agent that can access the recommended job information and job seeker information (or characteristic elements) and identify a recommendation basis based on that information. The AI ​​agent for identifying a recommendation basis is an AI agent that can access the recommended job information and job seeker information (or characteristic elements) and, as an action, generate or identify a recommendation basis based on that information.

[0056] In the recommendation basis identification step, the identification unit 232 identifies the recommendation basis of the recommended job information. The recommendation basis is information that serves as the basis for recommending the recommended job information to the job seeker U1. The identification unit 232 identifies the recommendation basis based on the job seeker information U11 and the recommended job information. For example, the identification unit 232 may compare the desired personnel conditions of the recommended job information with each item of the desired conditions of the job seeker U1 and identify the recommendation basis based on matching or similar items. Examples of recommendation basis include "meets the desired work location" and "meets the desired annual salary." The identification unit 232 may also input the job seeker information U11 and the recommended job information into a model such as a large-scale language model or a generative AI and identify the recommendation basis through inference. The identification unit 232 may compare the job seeker information U11 and the recommended job information using a large-scale language model or a generative AI, extract similarities, and identify the recommendation basis based on the similarities.

[0057] The recommendation grounds may also be related to the characteristic elements of the job seeker U1 that were also used to identify the recommended job information. Examples include, "This fits your core value of XX" and "Your previous experience in △△ can be utilized." For example, in the grounds identification step, the identification unit 232 uses a large-scale language model to identify the recommendation grounds that identified the recommended job information based on the characteristic elements. The identification unit 232 may generate a prompt including instructions for identifying the recommendation grounds based on the characteristic elements of the job seeker U1, input the prompt to a model such as a large-scale language model or a generation AI, and output the recommendation grounds using the large-scale language model.

[0058] <Output section 233> The output unit 233 can output various types of information. For example, the output unit 233 outputs the identified recommended job information.

[0059] <Generation unit 234> The generating unit 234 can generate various types of information.

[0060] <Question generation step> In the question generation step, the generation unit 234 analyzes the responses acquired from the job seeker U1 using a model such as a large-scale language model or a generative AI, thereby generating questions for, for example, estimating the job seeker's latent characteristics. In the question generation step, the generation unit 234 analyzes the responses acquired from the employer U2 using a model such as a large-scale language model or a generative AI, thereby generating questions for, for example, estimating the employer U2's latent needs. The latent characteristics and latent needs are, for example, characteristics and needs that the job seeker U1 or the employer U2 themselves are unaware of. The acquisition unit 231 acquires responses to questions for estimating such latent characteristics and needs, and the estimation unit 235 estimates the latent characteristics and needs, thereby enabling more accurate matching of the job seeker U1 with the job information U21.

[0061] The generation unit 234 generates a next question for the job seeker based on the answer acquired from the job seeker to the question and the reference information for acquiring job seeker information. The reference information for acquiring job seeker information includes at least the correlation between the answer and the next question. The reference information for acquiring job seeker information also includes a learning model, an artificial intelligence model, or a response generation model that is a generative AI that has been machine-learned to use the answer as input and is capable of outputting the next question for the job seeker. The reference information for acquiring job seeker information may also be a language model, including a large-scale language model or a small-scale language model, or may also be a job seeker information acquisition AI agent. The reference information for acquiring job seeker information includes a question generation AI agent that can access the answer acquired from the job seeker and generate the next question for the job seeker based on the answer. The question generation AI agent for the job seeker is an AI agent that can access the answer acquired from the job seeker and job seeker information including the answer, and that can generate the next question for the job seeker based on the answer from the job seeker as an action.

[0062] The generation unit 234 generates a next question based on the answer acquired from the recruiter to the second question (question for the recruiter) and the reference information for generating a question for the recruiter. The reference information for generating a question for the recruiter includes at least the correlation between the answer to the second question and the next question. The reference information for generating a question for the recruiter includes a response creation model that is a learning model, an artificial intelligence model, or a generative AI that has been machine-learned so as to be able to input the answer to the second question and output the next question for the recruiter. The reference information for generating a question for the recruiter may be a large-scale language model or a small-scale language model, or may be an AI agent for generating a question for the recruiter. The reference information for generating a question for the recruiter includes a question generation AI agent that can access the answer acquired from the recruiter and generate the next question for the recruiter based on the answer acquired from the recruiter. The AI ​​agent for generating a question for the recruiter is an AI agent that can access the answer acquired from the recruiter and job information including the answer, and is capable of generating the next question for the recruiter based on the answer from the recruiter as an action.

[0063] <Support information generation step> In the support information generation step, the generation unit 234 generates support information to support the job seeker's job search activities based on the job seeker information and the support information generation reference information. The support information generation reference information includes at least a correlation between the job seeker information and the support information. The support information generation reference information also includes a support information generation model, which is a learning model, an artificial intelligence model, or a generation AI that has been machine-learned to use the job seeker information as input and is capable of outputting the support information. The support information generation reference information may also be a language model, including a large-scale language model or a small-scale language model, or a support information generation AI agent. The support information generation reference information includes a support information generation AI agent that can access job seeker information and generate the support information based on that information. The support information generation AI agent is an AI agent that can access job seeker information and, as an action, generate the support information based on the job seeker information.

[0064] In the support information generation step, the generation unit 234 receives the job seeker information acquired by the acquisition unit 231 as input and analyzes it using a model such as a large-scale language model or a generative AI. Then, based on the analysis results, it generates support information to support the job seeker's job search activities. The generation unit 234 can extract characteristic elements from the profile, work history, desired conditions, etc. included in the job seeker information, and generate support information according to the characteristic elements. Here, the support information includes, for example, the following: information to support applying for recommended job information (reason for applying, appealing points, etc.), information to support the job seeker's career development (suggestions for skill improvement, advice on career paths, etc.), and information to support searching for job information (suggested search conditions, presentation of job offers with high matching rates, etc.).

[0065] Furthermore, in the support information generation step, the generation unit 234 inputs the job seeker information and the selected recommended job information into a large-scale language model, and can generate anticipated questions that the job seeker may have in an interview regarding the job. This enables the job seeker to efficiently prepare for the job application and prepare for the interview.

[0066] When the generation unit 234 acquires a response from the job seeker to the anticipated question, it generates feedback information for the response. The feedback information is information that includes an evaluation of the answer acquired from the job seeker and suggestions for improvement. The anticipated question and the feedback information are examples of support information. In this way, the generation unit 234 may generate further support information based on the response from the job seeker to the support information.

[0067] The generation unit 234 generates feedback information based on the expected questions, the responses to the expected questions, and the reference information for generating feedback information. The reference information for generating feedback information includes at least a correlation between the expected questions, the responses to the expected questions, and the feedback information. The reference information for generating feedback information also includes an explanation model, which is a learning model, an artificial intelligence model, or a generative AI, that is machine-learned to receive the expected questions and the responses to the expected questions as input and output feedback information. The reference information for generating feedback information may also be a language model, including a large-scale language model or a small-scale language model, or a feedback information generating AI agent. The reference information for generating feedback information includes a feedback information generating AI agent that has access to the expected questions and the responses to the expected questions and generates feedback information based on the information. The feedback information generating AI agent is an AI agent that has access to the expected questions and the responses to the expected questions and is capable of generating feedback information based on the information as an action.

[0068] <Estimation part 235> <Feature element estimation step> In the feature element estimation step, the estimation unit 235 estimates feature elements of the job seeker based on the responses and job seeker information acquired from the job seeker, and the reference information for feature element estimation. The reference information for feature element estimation includes at least correlations between the responses and job seeker information acquired from the job seeker and the feature elements. The reference information for feature element estimation also includes an estimation model, which is a learning model, an artificial intelligence model, or a generative AI that has been machine-learned to input the responses and job seeker information acquired from the job seeker and to output the feature elements of the job seeker. The reference information for feature element estimation may also be a language model, including a large-scale language model or a small-scale language model, or a feature element estimation AI agent. The reference information for feature element estimation includes a feature element estimation AI agent that has access to the responses and job seeker information acquired from the job seeker and estimates the feature elements of the job seeker based on the responses and job seeker information. The characteristic element estimation AI agent is an AI agent that can access responses and job seeker information obtained from job seekers and, as an action, can estimate characteristic elements of job seekers based on the responses and job seeker information.

[0069] In the feature element estimation step, the estimation unit 235 analyzes the job seeker information using a model such as a large-scale language model or generative AI to estimate the feature elements of the job seeker. The feature elements include points that the job seeker places importance on in job search activities or latent aspirations. In the feature element estimation step, the estimation unit 235 may estimate the feature elements of the job seeker using a model such as a large-scale language model or generative AI depending on the weight of the job seeker information.

[0070] <Demand estimation step> In the need estimation step, the estimation unit 235 estimates the needs of the recruiter based on the responses and job information acquired from the recruiter and the need estimation reference information. The need estimation reference information includes at least a correlation between the responses and job information acquired from the recruiter and the needs. The need estimation reference information also includes an estimation model, which is a machine-learned learning model, an artificial intelligence model, or a generative AI, that is capable of inputting the responses and job information acquired from the recruiter and outputting the recruiter's needs. The need estimation reference information may also be a language model, including a large-scale language model or a small-scale language model, or a need estimation AI agent. The need estimation reference information includes a need estimation AI agent that can access the responses and job information acquired from the recruiter and estimate the recruiter's needs based on the responses and job information. The need estimation AI agent is an AI agent that can access the responses acquired from the recruiter and job information including the responses, and that can, as an action, estimate the recruiter's needs based on the responses from the recruiter. In the need estimation step, the estimation unit 235 estimates the needs of the recruiter by analyzing the responses of the recruiter using a model such as a large-scale language model or a generative AI.

[0071] <Addition section 236> The weighting unit 236 assigns a weight to each item in the job seeker information U11 according to the time at which each item was acquired. For example, each item registered in the job seeker database is stored in association with information about the time at which it was registered in the database, and the weighting unit 236 can assign a weight to the information in each item according to the time elapsed since the job seeker information U11 was registered. The weighting unit 236 assigns a higher weight to an item that has been registered for a shorter period of time and a lower weight to an item that has been registered for a longer period of time, based on the time information stored in association with the time at which it was acquired (database registration time). For example, the weighting coefficient can be set to 1.0 for an item that was registered immediately after registration, 0.6 for an item that has been registered for six months, and 0.3 for an item that has been registered for one year. This configuration makes it possible to identify recommended job information while prioritizing new information and taking previously acquired information into consideration.

[0072] <Display control unit 237> The display control unit 237 controls the display unit 34 to display visual information such as screens, images including still images and videos, icons, and messages (text). The control unit 23 may generate only rendering information for displaying the visual information on the display unit 34 and transmit this information to the job seeker terminal 3, thereby causing the job seeker terminal 3 to generate the visual information and display the visual information on the display unit 34. The display control unit 237 may also generate visual information and transmit it to the job seeker terminal 3, thereby causing the display unit 34 to display the visual information. The display control unit 237 executes processing for displaying a system screen related to the information processing system 1 on each terminal. For example, the display control unit 237 performs processing such as generating and transmitting an HTML (Hyper Text Markup Language) file and causing the display unit 34 to display a web page showing the system screen. The display control unit 237 may also perform processing such as generating and transmitting display data for an application for using the information processing system 1. For example, the display control unit 237 can cause the display unit 34 to display various visual information.

[0073] The display control unit 237 is configured to display various information on the job seeker terminal 3, the employer terminal 4, the intermediary terminal 5, or other devices. For example, the display control unit 237 displays a screen for accepting the acquisition of job seeker information U11 and a screen for outputting recommended job information on the display unit 331 of the job seeker terminal 3. The display control unit 237 displays a chat screen, etc. on the display unit 331 of the job seeker terminal 3. The display control unit 237 displays a screen related to a job seeker interview on the user terminal. The screen includes feature elements and recommended job information. The screen related to the job seeker interview may also include the basis for recommendation. The display control unit 237 displays a screen for accepting the acquisition of job information U21 on the display unit 431 of the employer terminal 4. The display control unit 237 displays a screen for outputting recommended job information and an interview screen on the display unit 531 of the intermediary terminal 5.

[0074] <Additional Section 238> The adding unit 238 adds the information acquired from the job seeker U1 to the job seeker information U11, and adds the information acquired from the employer U2 to the job information U21. The adding unit 238 adds the job seeker's response during the job seeker interview as job seeker information.

[0075] <Judgment section 239> The determination unit 239 is configured to determine whether various information and data satisfy predetermined standards and conditions. The determination unit 239 quantifies multiple indicators included in the behavioral history and determines that the predetermined condition is satisfied if the numerical value exceeds a threshold. For example, the determination unit 239 determines that the predetermined condition is satisfied if the number of times the job seeker U1 has viewed a job posting included in the behavioral history exceeds a preset threshold. The predetermined condition is not limited to a threshold determination of the number of views, and may be, for example, the following condition: The determination unit 239 determines that the predetermined condition is satisfied if the number of scout replies within a predetermined period exceeds a threshold. For example, if the predetermined period is seven days and the threshold is three, the determination unit 239 determines that the predetermined condition is satisfied if the number of scout replies sent by the job seeker U1 in the past seven days exceeds a set threshold (e.g., three). The determination unit 239 determines that the predetermined condition is satisfied if the job seeker U1 has logged into the system a number of times equal to or greater than the threshold within the predetermined period. For example, if the predetermined period is 30 days and the threshold is three times, the determination unit 239 determines that the predetermined condition is met if the job seeker U1 has logged in at least three times within the last 30 days. The predetermined condition may also be a combination of conditions for multiple actions. For example, the determination unit 239 determines that the predetermined condition is met if both the number of scout replies and whether or not a login has occurred meet the threshold within the predetermined period. In this way, the determination unit 239 may be configured to evaluate the behavior history from multiple perspectives and flexibly set the predetermined condition using multiple indicators alone or in combination.

[0076] <Reception Department 240> The reception unit 240 is configured to be able to receive information from the job seeker terminal 3 or other information processing terminals. The reception unit 240 is also configured to receive various pieces of information by reading various pieces of information stored in a storage area, which is at least a part of the memory unit 22, and writing the read information to a work area, which is at least a part of the memory unit 22. The storage area is, for example, an area of ​​the memory unit 22 implemented as a storage device such as an SSD. The work area is, for example, an area implemented as memory such as RAM. For example, the reception unit 240 is configured to be able to receive input based on terminal operations by the job seeker U1 on the job seeker terminal 3. Specifically, the reception unit 240 is configured to be able to receive input by the job seeker U1. The reception unit 240 may also be configured to be able to receive instructions from the job seeker U1 to edit text or select an option. For example, the reception unit 240 receives a selection of at least one piece of recommended job information from the job seeker.

[0077] <Executive Department 241> The execution unit 241 presents expected questions to the job seeker, acquires responses to the expected questions from the job seeker, and presents feedback information in response to the acquired responses. The feedback information is generated by a large-scale language model in accordance with feature elements of the job seeker information and the responses to the expected questions. Here, the execution unit 241 may use a model such as a generation AI in addition to the large-scale language model.

[0078] The execution unit 241 inputs execution instructions to the AI ​​agent based on the response from the job seeker or employer. If the AI ​​agent consists of a manager agent and multiple sub-AI agents, the execution unit 241 may cause the manager AI agent to select a target AI agent from among the multiple sub-AI agents based on the response from the job seeker or employer, generate an action execution instruction for the target AI agent based on the response from the job seeker or employer, and input the execution instruction to the target AI agent. The manager AI agent selects a corresponding sub-AI agent based on the response from the employer or job seeker, generates an execution instruction, and inputs it to the selected sub-AI agent. This allows the manager AI agent to dynamically generate sub-tasks necessary to achieve a goal, such as identifying recommended job information for a job seeker or generating support information for a job seeker, when that goal is input.

[0079] The management AI agent manages a series of processing flows in a multi-AI agent environment by linking the outputs from the sub-AI agents (e.g., feature elements, requests, recommended job information, etc.) as input for the next sub-task. The results output by the management AI agent are fed back from the management AI agent to the execution unit 241, which generates and inputs additional execution instructions to the AI ​​agents as necessary.

[0080] <Recording Unit 242> The recording unit 242 controls the memory unit 22 of its own device and writes and reads data to the memory unit 22. The recording unit 242 stores, for example, job seeker information (input information) about job seeker U1 entered on the input screen. The recording unit 242 registers the response of job seeker U1 acquired by the acquisition unit 231 in the job seeker database as job seeker information U11. The recording unit 242 registers the job seeker information (registration information) of job seeker U1, which is generated or updated in response to the input of job seeker U1, and the job seeker information (input information) entered on the input screen in the job seeker database. The recording unit 242 also registers the response of employer U2 acquired by the acquisition unit 231 in the job database as job information U21. The recording unit 242 registers job information U21 acquired by the acquisition unit 231 via the web or a job posting in the job database.

[0081] The recording unit 242 chronologically records job seeker information acquired from the job seeker U1 at multiple points in the job seeker's career. Specifically, the recording unit 242 acquires input information entered by the job seeker U1 at multiple points in the job seeker's career, such as entering a profile when registering for the first time with a talent matching platform or talent matching service provided by the information processing system 1, updating desired conditions during job hunting, self-promotion during interview preparation, joining information after receiving a job offer, and updating skills / job position while employed, and stores each piece of input information in the job seeker database with a timestamp. The recording unit 242 saves the job seeker information entered via the input screen or chat screen. If the content of an item of the job seeker information is changed, the old value may be kept as a history, and version management of the job seeker information may be performed, which allows the difference between the old and new values ​​to be tracked chronologically.

[0082] In addition, part of the job seeker information U11 is held as registered information and reused as input data at different stages of a career. In this way, by storing the job seeker information U11 in chronological order in the recording unit 242, models such as large-scale language models and generative AI can perform analysis and proposals while referring to past information, thereby realizing consistent support at each stage of a career.

[0083] <Calculation unit 243> The calculation unit 243 calculates a first score and a second score. The first score and the second score are used to determine whether to recommend a job offer and, if so, to determine the recommendation order. The first score indicates the degree to which the job offer information U21 matches the job seeker information U11 based on the desired conditions included in the job seeker information U11. The first score is a score related to the degree of match between the job seeker information U11 and the job offer information U21 calculated from the job seeker's perspective. The first score is calculated so that a high first score is obtained when the job offer information U21 matches the desired conditions of the job seeker U1. It is assumed that the job seeker U1 is more likely to apply for a job offer with a high first score. Therefore, the first score may be referred to as an "application rate score." The first score is calculated based on the degree of match between the desired conditions, such as desired work location, desired annual salary range, and employment type included in the job seeker information, and the corresponding items listed in the job offer information.

[0084] The second score indicates the degree to which the job seeker information matches the job posting based on the desired personnel requirements contained in the job posting. The second score is calculated from the perspective of the employer (company) and is a score relating to the degree to which the job seeker information U11 matches the job posting U21. In other words, the score indicates the degree to which the job seeker information U11 matches the desired personnel requirements, such as required / welcome skills, years of experience, and personality profile, contained in the job posting U21. The second score is calculated so that it is high when the job seeker information U11 matches the requirements of the job posting, and it is assumed that job seekers with high second scores are more likely to be successful. Therefore, the second score can also be called a "pass rate score." The second score is calculated based on the degree of match between the required / welcome skills, years of experience, and personality profile contained in the job posting and the corresponding items, such as skills, experience, and qualifications, contained in the job seeker information.

[0085] When the number of job openings is greater than the number of job seekers (the number of job openings is greater than the number of job seekers), job seekers have more room to choose job openings. Therefore, the identification unit 232 adjusts the first weight W1 so that the first score is more important than the second score. Here, the case where the number of job openings is greater than the number of job seekers may be rephrased as a case where labor demand exceeds supply, including, but not limited to, a case where the ratio of the number of job openings to the number of job seekers (such as the effective job opening ratio) exceeds 1 or where the absolute number of job openings exceeds the number of job seekers. For example, it may refer to an objective situation in which it is difficult to secure labor in a specific occupation, region, or period, i.e., a "seller's market" state in general. When the number of job openings is less than the number of job seekers (the number of job seekers is greater than the number of job openings), job seekers have more room to choose job seekers. Therefore, the identification unit 232 adjusts the second weight W2 so that the second score is more important than the first score. Here, the case where the number of job openings is less than the number of job seekers may be rephrased as a case where the supply of labor exceeds the demand, including, but not limited to, a case where the ratio of the number of job openings to the number of job seekers (e.g., the job-to-applicant ratio) is less than 1 or where the absolute number of job seekers exceeds the number of job openings. For example, it may refer to an objective situation in which job seekers have difficulty finding employment in a particular occupation, region, or period, i.e., a "buyer's market" in general. In this way, the identification unit 232 can optimize the determination of recommended job openings and their recommendation ranking by adjusting the contributions of the first score and the second score according to the balance between the number of job openings and the number of job seekers and calculating the overall score. Note that, in the comparison between the number of job seekers and the number of job openings, the first weight W1 or the second weight W2 may be adjusted if the ratio of the number of job openings to the number of job seekers or the ratio of the number of job seekers to the number of job openings exceeds a reference value (e.g., 1).

[0086] The identification unit 232 monitors the balance (supply and demand balance) between the number of job openings and the number of job seekers in the recruitment market or labor market, and dynamically sets the first weight W1 and the second weight W2 according to the situation. The supply and demand balance in the recruitment market or labor market is the balance between the number of job openings (e.g., the number (quantity) of job information) and the number of job seekers (e.g., the number (quantity) of job seeker information). For example, when the number of job openings is greater than the number of job seekers, this can be rephrased as a case where the demand for labor exceeds the supply. Also, when the number of job openings is less than the number of job seekers, this can be rephrased as a case where the supply of labor exceeds the demand. The first weight W1 and the second weight W2 can be set by adjusting the first weight W1 and the second weight W2 so that the "value obtained by multiplying the first score by the first weight W1" and the "value obtained by multiplying the second score by the second weight W2" are balanced, that is, so that the contribution of the first weight W1 to the first score and the contribution of the second weight W2 to the second score are equal. First, the identification unit 232 sets a reference combination of the first weight and the second weight so that the "value obtained by multiplying the first score by the first weight W1" and the "value obtained by multiplying the second score by the second weight W2" are balanced.

[0087] In a market environment where the number of job openings is greater than the number of job seekers, the identification unit 232 prioritizes the first score and preferentially recommends recommended job information that highly matches the desired conditions of job seekers because job seekers are more likely to be "selective" about job openings. On the other hand, in a market environment where the number of job seekers is greater than the number of job openings, the identification unit 232 prioritizes the second score and preferentially recommends recommended job information that highly matches the desired human resources conditions because employers are more likely to be "selective" about job seekers. For example, the identification unit 232 may set a first weight W1 and a second weight W2, and then determine the recommendation order of the recommended job information based on a total score obtained by linearly adding a term obtained by multiplying the first score by W1 and a term obtained by multiplying the second score by W2. For example, the total score may be calculated by multiplying the first score by the first weight W1 and the second score by the second weight W2, and the recommendation order of the recommended job information may be determined based on the magnitude of the total score. The identification unit 232 dynamically adjusts the first weight W1 and the second weight W2 in real time or at a predetermined interval in accordance with the supply-demand balance between the number of job seekers and the number of job openings, optimizing the contribution of the first score and the second score to the total score, thereby identifying the recommendation order of the recommended job information. This embodiment dynamically adjusts the contribution of the first score and the second score in accordance with the supply-demand balance between the number of job openings and the number of job seekers in the recruitment market or labor market, and identifies recommended job information that is suited to the market environment. In other words, the identification unit 232 prioritizes the first score when the amount of job information is large relative to the amount of job seeker information, and prioritizes the second score when the amount of job seeker information is large relative to the amount of job information.

[0088] <Artificial Intelligence Department 244> The artificial intelligence unit 244 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server 2 for each functional unit may be a common one, or may be prepared individually for each functional unit.

[0089] The artificial intelligence unit 244 is an AI (Artificial Intelligence) equipped with a learning model such as a Transformer including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, GPT-4, and GPT-4o), BERT (Bidirectional Encoder Representations from Transformers), and BART (Bidirectional and Auto-regressive Transformer), or a language model such as a Recurrent Neural Network (RNN), and may include a generative AI or an AI agent. The generative AI may be, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The learning model may be referred to as an artificial intelligence model, a machine learning model, or a trained model.

[0090] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 244 can apply the above algorithms as appropriate.

[0091] The artificial intelligence unit 244 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of pairs of input data for learning and output data (correct answer data). In addition, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0092] The artificial intelligence unit 244 may use a natural language model as its artificial intelligence, or may include a general-purpose natural language processing trained model such as a large-scale language model (LLM). A large-scale language model is a learning model that has previously trained a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). It can perform various language processing tasks when given a task, and can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, answering questions, and generating sentences, according to given prompts. Such a general-purpose learning model may include a language model that can handle various tasks without fine-tuning, using one-shot learning, few-shot learning, etc. Furthermore, a general-purpose learning model can also handle various tasks using zero-shot learning. The artificial intelligence used in each functional unit of the control unit 23 may be a separate learning model, or a common general-purpose learning model. A large-scale language model is a type of generative AI, and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. The artificial intelligence unit 244 may also include, as its artificial intelligence, a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model. The small-scale language model and the medium-scale language model are natural language processing models trained based on less data than the large-scale language model. The artificial intelligence unit 244 may also include any machine learning model, deep learning model, artificial intelligence model, etc. The artificial intelligence unit 244 may be constructed in a system external to the information processing system 1. The artificial intelligence unit 244 may also be an interactive type (which may be interpreted as a chat type or a conversation type) that alternately receives input for performing instructed output and generates and outputs information.

[0093] The learning model included in the artificial intelligence unit 244 can undergo additional learning using techniques such as transfer learning or fine tuning. For example, the artificial intelligence unit 244 learns whether the output content has been modified by a user or the like. That is, the artificial intelligence unit 244 may perform additional learning and fine tuning based on modifications to the content output by the learning model. Also, for example, each time new data is registered, the artificial intelligence unit 244 may perform additional learning and fine tuning using the new data as new training data. This improves the accuracy of the information output from the learning model.

[0094] The learning model included in the artificial intelligence unit 244 may be a learning model (distilled model) obtained by knowledge distillation using an original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model (distilled model) are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby training the student model, which becomes the distilled model. Alternatively, the student model may be trained to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (a combination of input data and output data of the learning model). Compared to the original trained model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the trained model. Therefore, using a distilled model allows the information processing system 1 to reduce costs.

[0095] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a model such as a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a model such as a large-scale language model may be used as the learning model used in each functional unit, and once training data from that model has been accumulated, the distilled model obtained by knowledge distillation using that training data may be used as the learning model used in each functional unit.

[0096] Furthermore, the learning model used in each functional unit may be configured to output information generated in response to a prompt containing some instruction when that prompt is input.

[0097] The artificial intelligence unit 244 may include an AI agent. The AI ​​agent may also be called an autonomous agent. An "AI agent" is a model that, when a target (goal, objective, etc.) such as "teach me XX" or a task such as "output XX" is input, breaks down the processing required to reach the goal or accomplish the task into subtasks, actions, etc., and performs the necessary data collection and analysis, program generation, and execution. The AI ​​agent targets information and instructions input by a user, autonomously selects and executes tasks and actions according to the target, and outputs information according to the target, without requiring user intervention (operational input). The AI ​​agent may also autonomously plan and execute the plan, evaluate the execution results, and autonomously learn to achieve the target. For example, the AI ​​agent may be autonomously updated based on the results of subtask execution (e.g., collected information, information analysis results, etc.).

[0098] The information processing system 1 includes an AI agent. The AI ​​agent uses a large-scale language model to perform at least one of the following processes: generating questions for employers regarding job information; generating the next question for a job seeker; analyzing acquired responses or job seeker information; and identifying recommended job information. Here, the AI ​​agent may be a software program that, for example, uses a language model such as a large-scale language model or a small-scale language model or a generative AI to autonomously plan and sequentially execute processes to be executed according to the situation from among multiple processes, such as acquiring job information, generating questions through dialogue, analyzing job seeker information, and identifying recommended job information, depending on the goal of career support for job seekers or recruitment support for employers. The AI ​​agent may also be interactive software that, upon receiving instructions or requests in natural language, identifies the processes necessary to respond to the input instructions or requests and automatically executes them using the generative AI or a language model.

[0099] An AI agent may include a manager AI agent and multiple AI agents operating under its management (hereinafter, each AI agent is collectively referred to as a "sub-AI agent"). The sub-AI agents include, for example, an AI agent that generates questions for employers, an AI agent that generates questions for job seekers, an AI agent that estimates feature elements, an AI agent that estimates needs, an AI agent that identifies recommended job offers, an AI agent that identifies recommendation grounds, and an AI agent that generates support information. These sub-AI agents are AI agents that can perform their respective actions (generating questions for employers, generating questions for job seekers, estimating feature elements, estimating needs, identifying recommended job offers, identifying recommendation grounds, generating support information, etc.), and can access related data (job offers, job seeker information, responses, feature elements, etc.) and output results based on that data.

[0100] Multiple AI agents may be based on a common language model, with functions virtually separated by switching input prompts. Alternatively, multiple AI agents may be physically implemented as independent generative AI or learning models, and controlled by a management AI agent via an external I / F.

[0101] Multiple AI agents may be configured with a single common natural language model. In this case, a virtual multi-AI agent environment can be created by assigning functions to AI agents based on prompts entered into the natural language model. In this way, orchestration by the management AI agent selects the optimal sub-AI agent depending on the situation, providing an information processing system that can autonomously and efficiently execute a series of processes suited to supporting both job seekers and employers.

[0102] The artificial intelligence unit 244 may be an external component of the server 2. In this case, the external artificial intelligence unit 244 may be provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server 2, receive requests to execute an artificial intelligence service, and return instructed output as a processing result to the server 2. 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 a model such as a large-scale language model or a small-scale language model. The artificial intelligence service server may receive prompt inputs such as text, images, or voice, and generate and respond to the prompts. Furthermore, the information processing system 1 may be configured to use, as the artificial intelligence unit 244, an AI agent provided by an external provider that provides AI agents. For example, the information processing system 1 may be configured to use an AI agent using an API provided by the external provider.

[0103] <Display section> The display unit 331 of the job seeker terminal 3 displays a screen indicated by the screen data transmitted from the server 2. The display unit 431 of the recruiter terminal 4 displays a screen indicated by the screen data transmitted from the server 2. The display unit 531 of the intermediary terminal 5 displays a screen indicated by the screen data transmitted from the server 2.

[0104] <Operation acquisition section> The operation acquisition unit 332 of the job seeker terminal 3 accepts operations by the job seeker using the job seeker terminal 3. When a job seeker U1 operates the job seeker terminal 3 as a user to use the information processing system 1, he or she logs in by entering a user ID (Identification) and password. This associates the user ID with information created or updated on the job seeker terminal 3, making it possible to identify which user the information pertains to. The operation acquisition unit 432 of the recruiter terminal 4 accepts operations by the recruiter using the recruiter terminal 4. The operation acquisition unit 532 of the intermediary terminal 5 accepts operations by the intermediary using the intermediary terminal 5.

[0105] 3. Information processing flow This section describes the flow of an information processing method executed by the information processing system 1. As shown below, the information processing method includes steps executed by the information processing system. The program of this embodiment causes a computer to execute each step of the information processing system. Note that the order of the processes can be changed as appropriate, multiple processes may be executed simultaneously, or some processes may be omitted.

[0106] 3.1 Overview

[0107] FIG. 5 is a diagram illustrating an overview of the processing executed by the information processing system 1. In this processing, first, as a first acquisition step, the acquisition unit 231 acquires job information U21 related to a job offer from a recruiter U2 (step S001). Next, as a second acquisition step, the acquisition unit 231 presents a first question to a job seeker U1 and acquires a response to the first question from the job seeker. As the second acquisition step, the acquisition unit 231 inputs the response into a large-scale language model, generates the next question, and acquires job seeker information U11 including the response by repeating the process (step S002). Next, the identification unit 232 identifies recommended job information to recommend to the job seeker based on the job information U21, the acquired job seeker information U11, and the first reference information (step S003). The first reference information includes at least the relationship between the job information, job seeker information, and recommended job information. Next, the output unit 233 outputs the identified recommended job information (step S004).

[0108] In summary, an information processing system according to one embodiment includes at least one processor. In a first acquisition step, the acquisition unit 231 acquires job information U21 related to a job offer from a recruiter U2. In a second acquisition step, the acquisition unit 231 presents a first question to a job seeker U1 and acquires a response to the first question from the job seeker U1. In a second acquisition step, the acquisition unit 231 inputs the response into a large-scale language model, generates a next question, and acquires a response to the next question, thereby acquiring job seeker information including the response. The identification unit 232 identifies recommended job information to recommend to the job seeker based on the job information, the acquired job seeker information, and the first reference information. The first reference information includes at least the relationship between the job information, the job seeker information, and the recommended job information. The output unit 233 outputs the identified recommended job information. This aspect provides an information processing system that outputs job information to recommend to a job seeker based on information obtained from the job seeker.

[0109] 3.2 Specific examples An example of the flow of processing executed by the information processing system 1 will be described below with reference to Figures 6 to 9. This example of the flow may fall within the scope defined in the above-mentioned outline. The information processing may include any exception processing not shown. Exception processing includes the interruption of the information processing or the omission of each process. Selection or input performed in the information processing may be based on a user operation or may be performed automatically without relying on a user operation.

[0110] First Embodiment The first embodiment shows an example of the flow of information processing when the information processing system 1 acquires job information U21 related to a job offer from a recruiter U2, acquires job seeker information U11 from a job seeker U1, identifies recommended job information to recommend to the job seeker U1 based on the job information U21, the job seeker information U11, and reference information, and outputs the identified recommended job information. In the first embodiment, the information processing system 1 interviews the job seeker U1 to acquire the job seeker information U11, and the information processing system 1 interviews the recruiter U2 to acquire the job information U21.

[0111] 6 is an activity diagram showing an example of the flow of information processing according to the first embodiment, which is executed by the information processing system 1. Below, an explanation will be given along with each activity in this activity diagram.

[0112] The control unit 23 interviews the job seeker U1 and acquires the job seeker information U11. In the interview with the job seeker U1, the display control unit 237 first displays a first question to the job seeker U1 (activity A101). The first question is the first question to be displayed. The first question may be predetermined, or, like the next question, may be generated by the generation unit 234 based on the job seeker information U11, etc.

[0113] Next, as a second acquisition step, the acquisition unit 231 acquires a response to the first question from the job seeker (activity A102).

[0114] Next, the generation unit 234 generates the next question (activity A103). In the question generation step, the generation unit 234 analyzes the acquired response using a large-scale language model to generate the next question for estimating the characteristics of the job seeker U1.

[0115] Next, the display control unit 237 displays the next question to the job seeker U1 (activity A104).

[0116] Next, the acquisition unit 231 acquires a response to the next question from the job seeker U1 (activity A105).

[0117] Next, the recording unit 242 registers the acquired response as job seeker information U11 in the job seeker database (activity A106).

[0118] Next, the determination unit 239 determines whether a predetermined condition for terminating the acquisition of job seeker information U11 is met (activity A107). The predetermined condition may be, for example, whether an instruction to proceed to the next step has been received from the job seeker U1, or whether a predetermined number of questions, time, or content of questions and answers have been completed. The determination unit 239 may also determine whether the quality or quantity of the acquired job seeker information U11 is sufficient.

[0119] If it is determined that the predetermined condition is not met, the control unit 23 returns to activity A103 and continues to acquire job seeker information U11.

[0120] Next, if it is determined that the predetermined condition is satisfied, the control unit 23 proceeds to activity A108, where the estimation unit 235 analyzes the job applicant information using a large-scale language model and estimates the job applicant's feature elements as a feature element estimation step (activity A108).

[0121] Here, the assigning unit 236 assigns a weight to the job seeker information depending on the time when the job seeker information was acquired. In the feature element estimation step, the estimation unit 235 estimates feature elements of the job seeker using a large-scale language model according to the weight of the job seeker information.

[0122] The control unit 23 also interviews the recruiter U2 and acquires the recruitment information U21. In the interview with the recruiter U2, the display control unit 237 first displays a second question to the recruiter U2 (activity A109).

[0123] Next, as a first acquisition step, the acquisition unit 231 acquires a response to the second question from the recruiter U2 (activity A110).

[0124] Next, the generator 234 generates the next question using the large-scale language model in accordance with the acquired response (activity A111).

[0125] Next, the display control unit 237 displays the next question to the recruiter U2 (activity A112).

[0126] Next, as a first acquisition step, the acquisition unit 231 acquires a response to the next question (activity A113).

[0127] Next, the recording unit 242 registers the acquired response as job information U21 in the job database (activity A114).

[0128] Next, the determination unit 239 determines whether a predetermined condition for terminating the acquisition of the job information U21 is met (activity A115). The predetermined condition may be, for example, whether an instruction to proceed to the next step has been received from the recruiter U2, or whether a predetermined number of questions and answers have been completed. The determination unit 239 may also determine whether the quality or quantity of the acquired job information U21 is sufficient.

[0129] If it is determined that the predetermined condition is not satisfied, the control unit 23 returns to the activity A112 and continues to acquire the job information U21.

[0130] Next, if it is determined that the specified conditions are met, the control unit 23 proceeds to activity A116, and the estimation unit 235 estimates the employer's requests by analyzing the employer's response using a large-scale language model as a request estimation step (activity A116).

[0131] Next, the identifying unit 232 identifies recommended job information to be recommended to the job seeker based on the job information, the acquired job seeker information, and the reference information (activity A117).

[0132] Next, as a basis identification step, the identification unit 232 identifies the recommendation basis for identifying the recommended job information based on the feature elements using the large-scale language model (activity A118).

[0133] Next, the output unit 233 outputs the identified recommended job information (activity A119). The display control unit 237 displays a screen related to the job seeker's interview on the user terminal. The screen includes the characteristic elements and the recommended job information. The display control unit 237 may further display a screen including the basis for recommendation.

[0134] <Second embodiment> The second embodiment shows an example of the flow of information processing when the information processing system 1 uses the recommended job information identified in the first embodiment to generate anticipated questions for the job seeker U1 and presents feedback to the job seeker U1 regarding the response to the anticipated questions.

[0135] 7 is an activity diagram showing an example of the flow of information processing according to the second embodiment, which is executed by the information processing system 1. Below, an explanation will be given along with each activity in this activity diagram.

[0136] First, the display control unit 237 displays recommended job information to the job seeker U1 (activity A201).

[0137] Next, the reception unit 240 receives a selection of at least one of the recommended job information from the job seeker (activity A202).

[0138] Next, the control unit 23 analyzes the job seeker information and the selected recommended job information using a large-scale language model (activity A203).

[0139] Next, as a support information generation step, the generation unit 234 generates hypothetical questions based on the analysis results, assuming an interview when a job seeker applies for the recommended job information (activity A204).

[0140] Next, the execution unit 241 presents the assumed questions to the job seeker (activity A205).

[0141] Next, the acquisition unit 231 acquires a response to the assumed question from the job seeker (activity A206).

[0142] Next, the generating unit 234 generates feedback information in response to the response (activity A207).

[0143] Next, the execution unit 241 presents feedback information in response to the acquired response (activity A208).

[0144] FIG. 8 is a diagram showing screen G1, an example of an output screen. Screen G1 is an example of an output screen displayed to job seeker U1, and is a screen showing an interview between intermediary U3 and job seeker U1. The display control unit 237 causes the job seeker terminal 3 to display screen G1 related to the interview with job seeker U1. Screen G1 includes characteristic elements and recommended job information. Screen G1 includes intermediary U3, area G11, and area G12. Area G12 includes area G121, area G122, and area G123.

[0145] U3 is a video of intermediary U3 interviewing job seeker U1. Area G11 is an area displaying the "job seeker axis," which is an example of the characteristic elements of job seeker U1. The characteristic elements include points that the job seeker places importance on in their job search activities or their latent hopes. The characteristic elements are identified by the identification unit 232 according to the characteristic elements.

[0146] Area G12 is an area showing a list of recommended job information identified in accordance with the characteristic elements. Area G12 includes area G121, area G122, and area G123. Area G121 is an area displaying recommended job information with the first recommendation rank. Area G122 is an area displaying recommended job information with the second recommendation rank. Area G123 is an area displaying recommended job information with the third recommendation rank. The identification unit 232 may identify the recommended job information together with the recommendation rank, and the display control unit 237 may display the list of recommended job information in area G12 in order according to the identified recommendation rank. The display control unit 237 may display the basis for recommendation along with the recommended job information on screen G1.

[0147] Areas G121 to G123 include the recommendation ranking, job information U21, and a detail display button. The job information U21 includes identification information of the employer U2 corresponding to the job information U21 and an overview of the job information U21. When an operation instruction to the detail display button is received, the display control unit 237 displays detailed information of the recommended job information to the job seeker U1. In this manner, the job seeker U1 can check detailed information of the recommended job information with one click.

[0148] When the acquisition unit 231 acquires a response from the job seeker U1 during the interview, the estimation unit 235 analyzes the job seeker information including the response content using a large-scale language model as a feature element estimation step, and re-estimates the job seeker's feature elements. The identification unit 232 identifies recommended job information based on the re-estimated feature elements, and the display control unit 237 displays the newly estimated feature elements and newly identified recommended job information on the screen G1. In this way, by reflecting the feature elements and recommended job information in real time in response to the job seeker U1's response, the points that the job seeker U1 prioritizes in their job search or their latent preferences can be clarified during the interview, making it possible to identify recommended job information that is more suitable for the job seeker U1. The acquisition unit 231 may also acquire the utterances of the intermediary U3 during the interview along with the job seeker U1's response content. By obtaining the utterances of intermediary U3 along with the responses of job seeker U1, and analyzing the utterances of intermediary U3 using a large-scale language model, it is possible to more accurately estimate the characteristic elements of job seeker U1.

[0149] Specifically, for example, speech from a job seeker during an online interview or the like is converted into text in real time using voice recognition technology, and predetermined keywords and the like are extracted from the text data. The job seeker's characteristic elements are then updated based on the extracted keywords and the recommended job information is recalculated based on the updated characteristic elements and reflected on screen G1. Responses during an interview or the like may be obtained by any other means, such as voice input or text input via a chat system.

[0150] When the acquisition unit 231 acquires the content of the response of job seeker U1 while the interview is in progress, the addition unit 238 adds the job seeker's response during the interview as job seeker information. When the identification unit 232 adds the response during the interview to the job seeker information, it reanalyzes the job seeker information using a large-scale language model and identifies new recommended job information based on the reanalysis results. The output unit 233 outputs the newly identified recommended job information. Since the newly identified recommended job information is reflected successively in area G12, the job seeker and interviewer can continue the interview while always checking the latest matching results.

[0151] Furthermore, the screen G1 may be displayed to the intermediary U3. In this case, an image of the job seeker U1 is displayed instead of an image of the intermediary U3. Here, the output unit 233 may output recommended job information including the employer's requests to the intermediary terminal 5. In the information processing system 1, the acquisition unit 231 presents a second question to the employer as a first acquisition step and acquires a response to the second question from the employer. The acquisition unit 231 presents a next question generated by a large-scale language model in response to the acquired response, and repeats the process of acquiring a response to the next question. As a request estimation step, the estimation unit 235 can estimate the employer's requests by analyzing the employer's response using a large-scale language model. This aspect makes it possible to extract the latent requests of the employer U2 that are not reflected in the job posting, etc.

[0152] The potential needs of the employer U2 identified by the estimation unit 235 are displayed only on the intermediary terminal 5 by the output unit 233, and are not disclosed to the job seeker terminal 3. In this manner, the intermediary U3 can provide advice to the job seeker U1 after understanding the potential needs of the employer U2. As a result, the intermediary U3 can provide appropriate advice and job offers to the job seeker U1, and can also improve the accuracy of matching between job offers and job seekers.

[0153] While the screen shown in Figure 8 shows an example of support information regarding interviews between an intermediary and a job seeker, the information processing system may also present career advice (e.g., skill improvement plans, future career paths) and information to support job searches (e.g., suggestions for adjusting conditions, search query improvements) on the same screen or related screens. This support information is generated using a model such as a large-scale language model or generative AI, using job seeker information and recommended job information as input.

[0154] FIG. 9 is a diagram showing screen G2, which is an example of a chat screen. Screen G2 includes a character icon CI and areas G20 to G29. The character icon CI is an avatar of the information processing system 1. The chat corresponding to the character icon CI indicates a system-initiated utterance. Areas G20 to G29 are an example of a chat exchange between the system and job seeker U1. Areas G20, G22, G24, G25, G27, and G29 are examples of support information generated by the generation unit 234 to support the job seeker's job search activities. Areas G21, G23, G26, and G28 are examples of responses from job seeker U1 to the support information from the system. In a support information generation step, the generation unit 234 analyzes the acquired job seeker information using a large-scale language model and generates support information to support the job seeker's job search activities according to the analysis results, and the output unit 233 can output the support information. In the support information generating step, the generating unit 234 generates support information according to the characteristic elements of the job seeker identified from the job seeker information using a large-scale language model.

[0155] Area G20 includes a comment from the system: "Mr. / Ms. XX, you previously mentioned that you wanted to develop your skill XX. This position will allow you to utilize that skill. Let's focus on that point." This comment was generated based on the "skills you want to develop" content included in Job Seeker U1's past input or response, suggesting its relevance to the current job opening. Area G21 includes a comment from Job Seeker U1: "I see, if you talk about that skill as the core, it will be easier to get your point across!" Area G22 includes a comment from the system: "That's right! Also, looking at your past application history, you've been particularly valued for roles like XX. If you organize your experience around that, it will be easier to narrow down the focus this time as well." This comment analyzes job seeker information, including behavioral history, and provides support for Job Seeker U1's job search based on the analysis results. Area G23 includes a comment from Job Seeker U1: "I understand. I'll prepare so I can speak with confidence!" Area G24 includes a comment from Job Seeker U1: "In our previous discussion, you said, 'I want to speak with more confidence.'" The system includes a comment: "Start your conversation with confidence by showing your achievements in numbers." This comment conveys to job seeker U1 the unique way of communicating that job seeker U1 possesses. Area G25 includes a comment from the system: "Also, your 'sincerity' is evident from our interactions so far. Your honest and positive attitude in answering even difficult questions is the most typical of you." This comment conveys that the system deeply understands job seeker U1 based on their interactions so far and supports them. Area G26 includes a comment from job seeker U1: "Yes, we value sincerity!" Area G27 includes a comment from the system: "In line with your goal of demonstrating a 'strategic perspective,' I will ask questions from the perspective of what you would do if you were the business manager. Let's try to answer hypothetically." This comment explains the system's provision of hypothetical interview questions to support job seeker U1's job search. Area G28 contains a comment from job seeker U1, "Thank you, I'll practice!" Area G29 contains a comment from job seeker U1, "One last thing."We have been watching over you ever since you decided to take on the challenge of entering the △△ industry. If you have the determination you had back then, you should be able to answer any question." This comment encourages job seeker U1 and gives him or her a push towards the interview, thereby supporting his or her job search. In this way, the system can provide support to job seeker U1 as he or she searches for work.

[0156] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be modified as appropriate within the scope of the technical idea of ​​the invention. 4. Effect In this manner, it is possible to provide an information processing system that outputs job information recommended to job seeker U1 in accordance with information obtained from job seeker U1.

[0157] 5.Other In the above embodiment, the server 2 performs various storage and control functions. However, multiple external devices may be used instead of the server 2. That is, various information and programs may be distributed and stored in multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 244 may be configured external to the server 2. In this case, the artificial intelligence unit 244, which is an external component, is provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server 2, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server 2. 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 a large-scale language model. The artificial intelligence service server receives inputs of prompts such as text, images, and voice, and generates and responds to the prompts.

[0158] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes steps executed by the information processing system 1. The program causes a computer to execute the steps of the information processing system 1.

[0159] It may be provided in the following manner.

[0160] (1) An information processing system comprising at least one processor, wherein in a first acquisition step, job information regarding a job vacancy is acquired from an employer, in a second acquisition step, a first question is presented to a job seeker, a response to the first question is acquired from the job seeker, the response is input into a large-scale language model, a next question is generated, and a response to the next question is acquired by repeating the process, thereby acquiring job seeker information including the response, in an identification step, based on the job information, the acquired job seeker information, and first reference information, recommended job information to be recommended to the job seeker, wherein the first reference information includes at least a relationship between the job information, the job seeker information, and the recommended job information, and in an output step, the identified recommended job information is output.

[0161] In this manner, it is possible to provide an information processing system that outputs job information to be recommended to a job seeker in accordance with information obtained through interviews with the job seeker.

[0162] (2) An information processing system according to (1) above, comprising an AI agent, which performs at least one of the following processes using the large-scale language model: generating a question for the employer regarding the job information; generating a next question for the job seeker; analyzing the acquired response or the job seeker information; and identifying the recommended job information.

[0163] (3) In the information processing system described in (1) or (2) above, the question generation step further generates a next question for estimating characteristic elements of the job seeker by analyzing the acquired response using the large-scale language model, and the second acquisition step presents the generated next question and acquires the response to the next question.

[0164] (4) In the information processing system described in any one of (1) to (3) above, further, in the characteristic element estimation step, the job seeker information is analyzed using the large-scale language model to estimate the characteristic elements of the job seeker, wherein the characteristic elements include points that the job seeker places importance on in job search activities or latent hopes, and in the identification step, the information processing system identifies the recommended job information according to the characteristic elements.

[0165] (5) In the information processing system described in (4) above, the assigning step further assigns a weight to the job seeker information depending on the time of acquisition of the job seeker information, the feature element estimating step estimates the feature elements of the job seeker using the large-scale language model depending on the weight of the job seeker information, and the identifying step identifies the recommended job information depending on the feature elements.

[0166] (6) In the information processing system described in (4) or (5) above, the display control step further includes displaying a screen regarding the job seeker's interview on a user terminal, wherein the screen includes the characteristic elements and the recommended job information.

[0167] (7) In the information processing system described in (6) above, in the basis identification step, the large-scale language model is used to identify the recommendation basis for identifying the recommended job information based on the feature elements, and in the display control step, the screen including the recommendation basis is further displayed.

[0168] (8) In the information processing system described in any one of (1) to (7) above, the information processing system further includes: in the adding step, adding the job seeker's response in the interview as the job seeker information; in the identifying step, if the response in the interview is added to the job seeker information, reanalyzing the job seeker information using the large-scale language model and identifying new recommended job information according to the reanalysis results; and in the output step, outputting the newly identified recommended job information.

[0169] (9) In the information processing system described in any one of (1) to (8) above, in the first acquisition step, a second question is presented to the employer, a response to the second question is obtained from the employer, a next question generated by the large-scale language model is presented according to the obtained response, and the process of obtaining the response to the next question is repeated; further, in the need estimation step, the needs of the employer are estimated by analyzing the response of the employer using the large-scale language model; and in the identification step, the recommended job information is identified according to the job information including the needs.

[0170] (10) In the information processing system described in (9) above, in the output step, the identified recommended job information is output to a user terminal, wherein the user terminal includes a job seeker terminal and an intermediary terminal for the job seeker's job search activities, and the recommended job information not including the request is output to the job seeker terminal, and the recommended job information including the request is output to the intermediary terminal.

[0171] (11) In the information processing system described in any one of (1) to (10) above, in the second acquisition step, if the behavioral history of the job seeker satisfies a predetermined condition, the question is presented to the job seeker and the response to the question is acquired, thereby acquiring the job seeker information including the response; in the identification step, the recommended job information is identified based on the acquired job seeker information; and in the output step, the identified recommended job information is output.

[0172] (12) In the information processing system described in (11) above, in the judgment step, multiple indicators included in the behavioral history are quantified, and if the numerical value exceeds a threshold value, it is determined that the specified condition is met.

[0173] (13) In the information processing system described in (11) or (12) above, in the second obtaining step, the question is presented according to the behavioral history of the job seeker.

[0174] (14) In the information processing system described in any one of (1) to (13) above, the support information generation step further analyzes the acquired job seeker information using the large-scale language model, generates support information to support the job seeker's job search activities according to the analysis results, and outputs the support information in the output step.

[0175] (15) In the information processing system described in (14) above, in the support information generation step, the support information is generated using the large-scale language model according to characteristic elements of the job seeker identified from the job seeker information.

[0176] (16) In the information processing system described in (14) or (15) above, the support information includes any of information that supports the job seeker's job search activities for the recommended job information, information that supports the job seeker's career development, and information that supports the job seeker's search for the job information.

[0177] (17) In the information processing system described in any one of (14) to (16) above, further, in the reception step, a selection of at least one of the recommended job information is received from the job seeker, and in the support information generation step, the job seeker information and the selected recommended job information are analyzed using the large-scale language model to generate anticipated questions assuming an interview when the job seeker applies for the recommended job information, and in the execution step, the anticipated questions are presented to the job seeker, responses to the anticipated questions are obtained from the job seeker, and feedback information on the obtained responses is presented, wherein the feedback information is generated by the large-scale language model according to characteristic elements of the job seeker information and the responses to the anticipated questions.

[0178] (18) An information processing system according to any one of (1) to (17) above, further comprising, in the recording step, recording the job seeker information obtained from the job seeker at multiple times in the job seeker's career in chronological order, and in the identifying step, identifying the recommended job information based on the job seeker information in chronological order.

[0179] (19) In the information processing system described in (18) above, the multiple timings include a first job search stage and a second job search stage.

[0180] (20) In the information processing system described in (18) or (19) above, the multiple timings include at least one of a pre-employment stage and a non-job-seeking stage.

[0181] (21) In the information processing system described in any one of (18) to (20) above, in the second acquisition step, the question is presented at the multiple timings via a user interface having a common configuration or display format, and the response to the question is acquired.

[0182] (22) The information processing system according to any one of (1) to (21) above, further comprising: in the calculation step, calculating a first score and a second score, wherein the first score indicates the degree to which the job information matches the job seeker information based on the desired conditions included in the job seeker information, and the second score indicates the degree to which the job seeker information matches the job information based on the desired personnel conditions included in the job information; and in the identification step, when the amount of job information is greater than the amount of job seeker information, the first score is given priority, and when the amount of job seeker information is greater than the amount of job information, the second score is given priority, thereby identifying the recommended job information.

[0183] (23) An information processing method, comprising steps executed by the information processing system according to any one of (1) to (22) above.

[0184] (24) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (22) above. Of course, this is not the case.

[0185] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0186] 1: Information processing system 2: Server 20: Communication bus 21: Communications Department 22: Storage section 23: Control section 231: Acquisition Department 232: Specific part 233: Output section 234 :Generation part 235:Estimation part 236: Granting section 237: Display control section 238: Additional section 239: Judgment section 240: Reception 241: Executive Department 242: Recording section 243: Calculation section 244: Artificial Intelligence Department 3: Job seeker terminal 30: Communication bus 31: Communications Department 32: Storage section 33: Control section 331: Display section 332: Operation acquisition section 34:Display section 35: Input section 4: Recruiter terminal 40: Communication bus 41: Communications Department 42: Storage section 43: Control section 431: Display section 432 :Operation acquisition part 44: Display section 45: Input section 5: Intermediary terminal 50: Communication bus 51: Communications Department 52: Storage section 53: Control unit 531: Display section 532: Operation acquisition section 54:Display section 55: Input section CI: Character Icon G1: Screen G11 :Area G12 :Area G121 :Area G122 :Area G123 :Area G2: Graphics G20: Areas G21: Domain G22: Domain G23: Domain G24: Domain G25: Domain G26: Domain G27: Domain G28: Domain G29: Domain U1: Job seeker U11: Job Seeker Intelligence U2: Seeking help U21: Seeking information U3: intermediary

Claims

1. An information processing system, at least one processor; In the first acquisition step, job information relating to a job offer is acquired from a recruiter, and the job information includes at least information on a job posting of the recruiter; In the second acquisition step, presenting a first question to a job seeker and obtaining a response from the job seeker to the first question, wherein the first question is a predetermined question or a question obtained by inputting previously acquired job seeker information and an instruction to generate the first question in accordance with the previously acquired job seeker information into a large-scale language model and outputting the large-scale language model; inputting the job seeker's response to the first question and an instruction to generate a next question in response to the response into the large-scale language model, causing the large-scale language model to generate the next question, presenting the next question to the job seeker, obtaining the job seeker's response to the next question from the job seeker, and accumulating the job seeker's response to the first question and the job seeker's response to the next question as job seeker information, the job seeker information including the job seeker's responses to questions previously asked to the job seeker; In the identification step, the job information and the accumulated job seeker information are input into a recommended job identification model, and the recommended job information to be recommended to the job seeker is output from the recommended job identification model, thereby identifying the recommended job information, the recommended job offer identification model is a machine-learned learning model or a large-scale language model that is capable of learning job seeker information for learning and job offer information for learning that satisfy predetermined conditions for learning, and outputting the recommended job offer information using the job offer information and the job seeker information as inputs, When the recommended job offer identification model is the large-scale language model, in the identification step, the job offer information, the job seeker information, and an instruction to output the recommended job offer information based on the job offer information and the job seeker information are input to the recommended job offer identification model, and the recommended job offer information is identified by causing the recommended job offer identification model to output the recommended job offer information; In the output step, the information processing system outputs the identified recommended job information.

2. In the information processing system according to claim 1, The second acquisition step involves inputting the job seeker's response to a question asked up to that point and an instruction to generate the next question in accordance with the response into the large-scale language model to generate the next question, presenting the next question to the job seeker, and repeating the process of acquiring the job seeker's response to the next question until a predetermined termination condition is met, thereby accumulating the job seeker's response to the next question as the job seeker information, wherein: the job seeker information includes the job seeker's responses to questions previously asked of the job seeker; The predetermined termination condition is at least one of receiving a termination instruction from the job seeker, completing a predetermined number of times, elapse of a predetermined time, and completing acquisition of predetermined content.

3. 3. The information processing system according to claim 2, The system includes a question generation AI agent and a job recommendation identification AI agent, In the second obtaining step, the job seeker's response to the question so far and an instruction to generate the next question in accordance with the response are input to the question generation AI agent; the question generation AI agent inputs the job seeker's responses to questions asked up to that point and instructions for generating the next question in accordance with the responses into the large-scale language model to generate the next question, presents the next question to the job seeker, and repeats the process of obtaining the job seeker's response to the next question from the job seeker until the predetermined termination condition is met, thereby executing a process of accumulating the job seeker's response to the next question as the job seeker information; In the specifying step, the job information, the accumulated job seeker information, and an instruction to specify the recommended job information are input to the recommended job information specifying AI agent; The recommended job offer identification AI agent inputs the job offer information and the accumulated job seeker information into the recommended job offer identification model, and executes a process to cause the recommended job offer identification model to output the recommended job offer information to be recommended to the job seeker.

4. 2. The information processing system according to claim 1, Furthermore, in the question generation step, the response of the job seeker to the question so far asked to the job seeker and an instruction to generate the next question in response to the response are input to the large-scale language model, thereby causing the large-scale language model to generate the next question, wherein: the instructions for generating the next question include instructions for generating the next question for estimating a characteristic element of the job seeker; In the instructions: The characteristic elements include points that the job seeker places importance on in job search activities or the wishes of the job seeker, The next questions for estimating the characteristic elements of the job seeker include questions regarding at least one of the job seeker's desired career vision, desired future image, important values, reason for changing jobs, motivation for changing jobs, corporate culture and climate to which the job seeker is applying, important work style, desired working conditions, and desired annual salary conditions, In the second obtaining step, the information processing system presents the generated next question to the job seeker and obtains the job seeker's response to the next question.

5. 2. The information processing system according to claim 1, Furthermore, in the characteristic element estimation step, the job seeker information and an instruction to estimate a characteristic element of the job seeker, including points that the job seeker places importance on in job search activities or the job seeker's wishes, based on the job seeker information, are input to the large-scale language model, and the characteristic elements of the job seeker are estimated by the large-scale language model; an information processing system in which, in the identification step, the characteristic elements, the job information, and the acquired job seeker information are input into the recommended job identification model, and the recommended job information to be recommended to the job seeker is output from the recommended job identification model, thereby identifying the recommended job information; and, if the recommended job identification model is the large-scale language model, in the identification step, the characteristic elements, the job information, the job seeker information, and instructions for outputting the recommended job information based on the characteristic elements, the job information, and the job seeker information are input into the recommended job identification model, and the recommended job information is identified by outputting the recommended job information.

6. 6. The information processing system according to claim 5, Furthermore, in the assigning step, based on the time information stored in association with the job seeker information, a higher weight is assigned to an item for which a shorter time has elapsed since the stored time information, and a lower weight is assigned to an item for which a longer time has elapsed since the stored time information, the feature element estimation step inputs the job applicant information to which the weights have been assigned and an instruction to estimate the feature elements of the job applicant in accordance with the weights assigned to the job applicant information into the large-scale language model, and causes the large-scale language model to estimate the feature elements of the job applicant; In the specifying step, the information processing system specifies the recommended job information according to the characteristic elements.

7. 6. The information processing system according to claim 5, Furthermore, in the display control step, a screen of the job seeker's interview is displayed on the user terminal, wherein the screen includes the characteristic elements and the recommended job information.

8. 8. The information processing system according to claim 7, Furthermore, in the basis identification step, an instruction to identify a recommendation basis for recommending the recommended job information to the job seeker based on the feature element, the job seeker information, and the recommended job information, and the feature element, the job seeker information, and the recommended job information are input to the large-scale language model, and the large-scale language model is caused to identify the recommendation basis; In the display control step, the information processing system further displays the screen including the recommendation grounds.

9. 2. The information processing system according to claim 1, Furthermore, in the adding step, a response of the job seeker in the interview of the job seeker is added as the job seeker information; Furthermore, in the feature element estimation step, when a response of the job seeker in the interview is added to the job seeker information, the added job seeker information and an instruction to estimate a feature element of the job seeker based on the added job seeker information are input to the large-scale language model, and the feature element of the job seeker is estimated by the large-scale language model; In the identification step, the estimated feature elements, the job information, and the job seeker information are input into the recommended job identification model, and the recommended job information is newly identified by the recommended job identification model. Here, if the recommended job identification model is the large-scale language model, in the identification step, the feature elements, the job information, the job seeker information, and an instruction to output the recommended job information based on the feature elements, the job information, and the job seeker information are input into the recommended job identification model, and the recommended job information is identified by causing the recommended job identification model to output the recommended job information. In the output step, the information processing system outputs the newly identified recommended job information.

10. 2. The information processing system according to claim 1, In the first obtaining step, presenting a second question to the recruiter and obtaining a response from the recruiter to the second question, wherein the second question is a predetermined question that is initially presented to the recruiter; The responses of the recruiter to the questions asked up to that point to the recruiter and instructions for generating the next question in response to the responses are input to the large-scale language model, the large-scale language model is made to generate the next question, the generated next question is presented to the recruiter, and the process of obtaining the recruiter's response to the next question from the recruiter is repeated until a predetermined termination condition is met, thereby accumulating the recruiter's response to the next question as the recruitment information, wherein: The recruiter's responses to the previous questions to the recruiter include the recruiter's response to the second question and the recruiter's responses to the previous next question; The job information includes the recruiter's responses to previous questions to the recruiter, The predetermined termination condition is either an end instruction from the employer or completion of a predetermined number of times, time, or content, Furthermore, in the need estimation step, the responses of the recruiter to the questions so far asked to the recruiter and instructions for estimating the needs of the recruiter based on the responses are input to the large-scale language model, and the needs of the recruiter are estimated by the large-scale language model; An information processing system in which, in the identification step, the job information including the request and the job seeker information are input into the recommended job identification model, and the recommended job information is identified by the recommended job identification model, and if the recommended job identification model is the large-scale language model, in the identification step, the job information including the request, the job seeker information, and an instruction to output the recommended job information based on the job information including the request and the job seeker information are input into the recommended job identification model, and the recommended job information is identified by having the recommended job identification model output the recommended job information.

11. 11. The information processing system according to claim 10, In the output step, the specified recommended job information is output to a user terminal, The user terminal includes a job seeker terminal and an intermediary terminal for the job seeker's job search activity, The recommended job information not including the request is output to the job seeker terminal, An information processing system that outputs the recommended job information including the request to the intermediary terminal.

12. 2. The information processing system according to claim 1, In the second obtaining step, when at least one of the number of times the job seeker has viewed a job offer, the number of applications for the job offer, the number of bookmarks for the job offer, the number of replies to scout messages, whether the job seeker has passed the screening, the number of times the job seeker information has been updated, the number of times the registration screen has been displayed, and the number of times the job seeker has checked messages exceeds a predetermined threshold, the first question is presented to the job seeker, and a response from the job seeker to the first question is obtained, and the response is stored as the job seeker information; In the identifying step, the job information and the accumulated job seeker information are input into the recommended job identification model, and the recommended job information is identified using the recommended job identification model; In the output step, the information processing system outputs the identified recommended job information.

13. 2. The information processing system according to claim 1, Furthermore, in the support information generation step, inputting the acquired job seeker information and instructions for generating support information for supporting a job search based on the job seeker information into the large-scale language model, wherein the instructions for generating the support information are instructions for generating the support information including at least one of information for supporting the job seeker's job search for the recommended job information, information for supporting the job seeker's career development, and information for supporting the job seeker's search for the job information; outputting the assistance information from the large-scale language model; In the output step, the information processing system outputs the support information.

14. 14. The information processing system according to claim 13, Furthermore, in the feature element estimation step, the job seeker information and an instruction to estimate feature elements of the job seeker, including points that the job seeker places importance on in the job search activity or the job seeker's wishes, based on the job seeker information, are input to the large-scale language model, and the large-scale language model is caused to estimate the feature elements; In the support information generation step, the accumulated job seeker information, the characteristic elements, and instructions for generating support information to support the job search activity based on the job seeker information and the characteristic elements are input to the large-scale language model, and the support information is output from the large-scale language model.

15. 15. The information processing system according to claim 14, Furthermore, in the receiving step, a selection of at least one of the recommended job information is received from the job seeker, In the support information generation step, the job seeker information, the selected recommended job information, and an instruction to generate anticipated questions assuming an interview when the job seeker applies for the recommended job information based on the job seeker information and the selected recommended job information are input to the large-scale language model, and the large-scale language model is caused to generate the anticipated questions; In the execution step, the assumed questions are presented to the job seeker, and a response to the assumed questions is obtained from the job seeker. Furthermore, in the feedback information generating step, the job seeker information, the feature elements, the responses to the anticipated questions, and instructions for generating feedback information according to the job seeker information, the feature elements, and the responses to the anticipated questions are input to the large-scale language model, and the large-scale language model is caused to generate the feedback information, wherein the instructions for generating the feedback information are instructions for generating the feedback information including an evaluation or improvement suggestion for the responses to the anticipated questions; In the presentation step, the information processing system presents the feedback information.

16. 2. The information processing system according to claim 1, Furthermore, in the recording step, the job seeker information acquired from the job seeker at a plurality of times in the job seeker's career is recorded in chronological order, the times including immediately after new user registration, a time when job hunting is suggested to start, a time when an interview is confirmed, and a time during the interview; In the specifying step, the job information and the time-series job seeker information are input into the recommended job information specifying model, and the recommended job information is specified by the recommended job information specifying model.

17. 17. The information processing system according to claim 16, An information processing system in which the multiple timings include a first job search stage and a second job search stage, the first job search stage being immediately after starting or resuming job search activities, and the second job search stage being the timing of applying for a job or having an interview or meeting.

18. 17. The information processing system according to claim 16, The information processing system, wherein the plurality of timings include at least one of a pre-employment stage and a non-job-seeking stage.

19. 17. The information processing system according to claim 16, In the second obtaining step, the information processing system presents the first question at the plurality of times via a user interface having a common configuration or display format, and obtains the job seeker's response to the first question.

20. 2. The information processing system according to claim 1, Furthermore, in the calculation step, a first score and a second score are calculated, where: the first score indicates the degree to which the job information matches the job seeker information based on desired conditions included in the job seeker information; the second score indicates the degree to which the job seeker information matches the job information based on desired personnel conditions included in the job information; In the identification step, if the number of job information items is greater than the number of job seeker information items, the first score is given priority, and if the number of job seeker information items is greater than the number of job information items, the second score is given priority, and the recommended job information is identified.

21. An information processing method executed by at least one processor of a computer, comprising: An information processing method, wherein the processor executes each step of the information processing system according to any one of claims 1 to 20.

22. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 20.

Images