Information processing systems, information processing methods, and programs

Abstract

We provide an information processing system, information processing method, and program to support job seekers' job-seeking activities. [Solution] In the information processing system 1, the control unit of the server 2 acquires input information about job seeker U1 from the job seeker terminal 3. The input information includes at least the job seeker's activity history information and registration information, and the activity history information includes a history of the job seeker's activities related to job searching. The generation unit generates a plurality of suggestion information based on the input information and first reference information. The suggestion information includes headline information and search conditions used for job searching, with the headline information and search conditions being associated, and the first reference information includes at least the correlation between the input information and the suggestion information. The display control unit displays the plurality of headline information included in the plurality of suggested information, and displays to the job seeker at least one of the search conditions associated with the headline information selected by the job seeker from among the plurality of headline information, and the results of the job search using the search conditions.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a technique for a job seeker to search for job offers.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is room for improvement in the technology related to an information processing system for supporting the job hunting activities of job seekers.

[0005] Therefore, in view of the above circumstances, the present invention aims to provide a technology related to an information processing system for supporting the job hunting activities of job seekers.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program, wherein in the acquisition step, input information relating to a job seeker is acquired, the input information includes at least the job seeker's behavioral history information and registration information, the behavioral history information includes a history of the job seeker's actions relating to job-seeking activities, in the generation step, a plurality of suggested information is generated based on the input information and first reference information, the suggested information includes headline information and search conditions used for job searching, the headline information and search conditions are associated with each other, the first reference information includes at least the correlation between the input information and the suggested information, and in the display control step, a plurality of headline information included in the generated plurality of suggested information is displayed, and at least one of the search conditions associated with the headline information selected by the job seeker from among the plurality of headline information and the results of a job search using the search conditions is displayed to the job seeker.

[0007] In this manner, it is possible to provide technologies related to information processing systems that support job seekers' job-seeking activities. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] Block diagram showing the hardware configuration of Server 2. [Figure 3] This is a block diagram showing the hardware configuration of job seeker terminal 3. [Figure 4] This block diagram shows the functions implemented by Server 2 (Control Unit 23) and Job Seeker Terminal 3 (Control Unit 33). [Figure 5] This diagram shows an overview of the processes performed by Information Processing System 1. [Figure 6] This is an activity diagram showing an example of the information processing flow performed by information processing system 1. [Figure 7] This is an activity diagram showing another example of the information processing flow performed by information processing system 1. [Figure 8] This figure shows screen G1, which is an example of a screen displayed by the information processing system 1 to job seeker U1, showing point axes and heading information. [Figure 9] This figure shows screen G2, which is an example of a screen that displays search criteria and the search results for job postings using those search criteria. [Modes for carrying out the invention]

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

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

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

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

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

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

[0015] <Information Processing System 1> FIG. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes a server 2 and a job seeker terminal 3. The server 2 and the job seeker terminal 3 are configured to be communicable through a telecommunication line (network). In an exemplary embodiment, the job seeker terminal 3 can function as a job seeker's terminal. Here, the system exemplified in the information processing system 1 is composed of one or more devices or components. Therefore, it should be noted that even the server 2 alone, or the server 2 and the job seeker terminal 3, may be included in the information processing system 1. More specifically, the information processing system 1 may include elements selected from the group consisting of the server 2 and the job seeker terminal 3. Even if the unselected elements are not included in the information processing system 1, they may be electrically connected to the selected elements as external elements. These components will be described below.

[0016] The information processing system 1 is composed of one or more elements selected from the group consisting of the server 2 and the job seeker terminal 3, and these are configured to be mutually communicable via a network. This system constitutes, for example, at least a part of a job posting and job seeking system. The job posting and job seeking system performs, for example, posting of job openings by employers, searching for job seekers by employers, searching for job openings by job seekers, mediation of communication between employers and job seekers (transmission and reception of scout messages), etc. Also, the job posting and job seeking system provides and manages, for example, a talent matching platform and talent matching services used by employers and job seekers. Here, the information processing system 1 generates a plurality of proposal information (including heading information and search conditions used for job search, and information in which the heading information and the search conditions are associated) based on input information regarding the job seeker (including at least action history information and registration information) and first reference information, and enables display of the plurality of generated heading information, and display of at least one of the search conditions associated with the heading information selected by the job seeker and the results of job search using the search conditions.

[0017] The "proposal information" in this specification refers to the information that forms the unit of the proposal presented to job seekers, and includes, for example, heading information and search conditions used for job search, and is information in which the heading information and the search conditions are associated with each other.

[0018] The "heading information" in this specification is a heading for identifying and displaying the proposal information, and may be referred to as a catchphrase, short text message, concept, theme, summary information, etc. The heading information may be an expression summarizing the search conditions, or a text such as a message based on a point axis such as the viewpoints emphasized by the job seeker.

[0019] The "search conditions" in this specification are the conditions, information, or parameters (including queries, etc.) used for job search. For example, it includes one or more conditions (a single condition or a combination of multiple conditions) such as industry, job type, work location, company size, annual income, work form (such as remote workability), treatment, skill requirements, free words, exclusion keywords, etc. Also, the search conditions are not limited to those specified by the user, and may include conditions automatically set based on the user's attributes and behavior history. The search conditions may include logical conjunctions such as AND / OR / NOT, weighting for each condition, decision thresholds, feature vectors, range specifications, and control parameters such as sorting order and the number of retrieved items. The search conditions may be the conditions used for job search corresponding to the heading information, or the conditions for conducting job search based on the point axis.

[0020] The "point axis" in this specification is an axis indicating the viewpoints (or viewpoints presumed to be emphasized) that job seekers attach importance to for job offers and employers, potential needs, career values, etc. Also, the point axis may indicate the interests or values of the job seeker, etc. The point axis is analogized, extracted, or generated based on action history information and / or registration information (such as resume information), etc. The point axis is not limited to viewpoints such as industry / type of business / company size / job type / treatment, etc., or combinations thereof, and includes abstract concepts and images such as growth potential, stability, degree of discretion, corporate culture, etc. At least one of the heading information and the search conditions may be generated based on the point axis.

[0021] <Server 2> Figure 2 is a block diagram showing the hardware configuration of Server 2. Server 2 comprises a communication unit 21, a storage unit 22, and a control unit 23, and these components are electrically connected within Server 2 via a communication bus 20. Each component will be described further.

[0022] The communication unit 21 is comprised of a communication module. The communication module may be a wireless communication module compliant with standards such as IEEE 802.11a / b / g / n / ac / ax, LTE, 5G, 6G, or a wired communication module compliant with standards such as IEEE 802.3. The communication unit 21 is configured to transmit various electrical signals from the server 2 to external components. The communication unit 21 is also configured to receive various electrical signals from external components to the server 2. More preferably, the communication unit 21 may have a network communication function, thereby enabling the communication of various information between the server 2 and external devices via a network.

[0023] The memory unit 22 stores various types of information as defined above. This can be done, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the server 2 executed by the control unit 23, or as memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The memory unit 22 stores various programs and variables related to the server 2 executed by the control unit 23.

[0024] The control unit 23 performs processing and control of the overall operation 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 predetermined programs stored in the memory unit 22. That is, information processing by software stored in the memory unit 22 is concretely realized by the control unit 23, which is an example of hardware, so that each step related to each function described later can be executed. These will be described in more detail in the next section. Note that the control unit 23 is not limited to being a single unit, and may be implemented with multiple control units 23 for each function, or a combination thereof.

[0025] <Job seeker terminal 3> Job seeker terminal 3 is an information processing device used by job seekers. "Job seekers" include various individuals who wish to find employment or work, such as those seeking a career change, recent graduates (job seekers), and may also include those currently engaged in job-seeking or career-changing activities, or those interested in changing jobs or finding employment.

[0026] Figure 3 is a block diagram showing the hardware configuration of the job seeker terminal 3. The job seeker terminal 3 comprises a communication unit 31, a storage unit 32, a control unit 33, a display unit 34, and an input unit 35, and these components are electrically connected within the job seeker terminal 3 via a communication bus 30. Each component will be described further. The descriptions of the communication unit 31, storage unit 32, and control unit 33 are the same as the descriptions of each part in the server 2, so they will be omitted.

[0027] The display unit 34 may be included in the housing of the job seeker terminal 3, or it may be an external component. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. Preferably, this is done by using a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display, depending on the type of job seeker terminal 3.

[0028] The display unit 34 displays the screen indicated by the screen data transmitted from the server 2. The display unit 34 displays a system screen related to the information processing system 1 indicated by the screen data transmitted from the server 2. The display unit 34 may also display the screen under the control of the display control unit 331.

[0029] The input unit 35 may be included in the casing of the job seeker terminal 3, or it may be an external component. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. If it is a touch panel, the user can input tap operations, swipe operations, etc. Of course, a switch button, mouse, QWERTY keyboard, etc. may be used instead of a touch panel. In other words, the input unit 35 receives operation input made by the user. This input is transmitted as a command signal to the control unit 33 via the communication bus 30, and the control unit 33 can perform predetermined controls and calculations as needed.

[0030] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory 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.

[0031] Figure 4 is a block diagram showing the functions realized by Server 2 (control unit 23) and Job Seeker Terminal 3 (control unit 33).

[0032] Figure 4A is a block diagram showing the functions realized by the control unit 23. As shown in Figure 4A, the control unit 23 includes an acquisition unit 231, a generation unit 232, a display control unit 233, a determination unit 234, a job number calculation unit 235, a specification unit 236, a feedback reception unit 237, a regeneration unit 238, a point axis estimation unit 239, a re-estimation unit 240, a holding unit 241, a determination unit 242, and an artificial intelligence unit 243.

[0033] As shown in Figure 4B, the job seeker terminal 3 (control unit 33) comprises a display control unit 331 and an operation acquisition unit 332.

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

[0035] The acquisition unit 231 acquires input information about the job seeker. The input information includes at least the job seeker's behavioral history information and / or registration information. In addition to the behavioral history information and / or registration information, the input information may also include at least one of the following: displayed proposal information, displayed point axis, and feedback information.

[0036] Behavioral history information includes a history of a job seeker's actions related to their job search activities. Behavioral history information is historical information that can identify a job seeker's actions related to their career development and job search activities. For example, behavioral history information includes at least one of the following: job postings viewed by the job seeker, job postings applied for by the job seeker, recruitment information viewed by the job seeker, and recruitment information to which the job seeker responded. Behavioral history information may also include the job seeker's job search history, dialogue history with employers, dialogue history with artificial intelligence, search result viewing history, execution of job searches, viewing of job postings on the search results screen (viewing search results), bookmarking (favorites / interesting) or hiding settings. Furthermore, behavioral history information may also include operation logs such as time spent on each screen, scroll amount, and tap or click location (heatmap information, etc.).

[0037] A job seeker's job search history refers to the history of job searches performed by the job seeker, and includes information recorded chronologically, such as the content of the search criteria used for job searches (e.g., industry, job type, work location, annual salary, company size, benefits, etc.), the date and time the search was performed, and the status of viewing the search results (viewing the search results screen, etc.). A job seeker's job search history may also include the history of modifications or saving of search criteria made by the job seeker. Note that search criteria are not limited to those explicitly entered, but also include selected categories, tags, etc.

[0038] The history of communication with employers refers to the history of messages and information exchanges between employers and job seekers. This includes, for example, recruitment information (recruitment messages) sent by employers and the job seekers' replies to them (including read status, open status, and clicks of reaction buttons), as well as communications regarding interview scheduling. This history can be managed in association with date and time information such as the date and time of sending and receiving.

[0039] An employer refers to a person who seeks labor, the performance of duties, or the provision of services, and recruits personnel. This includes organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.), or their personnel. Here, the personnel may also be called recruitment personnel, and may include personnel in the human resources department of an organization or personnel in the department that intends to recruit personnel. Furthermore, employers also include recruitment agencies and hiring agencies that act as intermediaries between job seekers and employers. Recruitment agencies and hiring agencies may also be called headhunters, agents, etc. In this specification, "employer" also includes agents who perform recruitment activities on behalf of the employer (RPO (Recruitment Process Outsourcing) operators, outsourcing partners, etc.). The history of interactions with employers may include, for example, interactions between agents, headhunters, career advisors, etc., and job seekers.

[0040] The dialogue history with artificial intelligence is a record of the content of the interaction between the job seeker and the artificial intelligence. The dialogue history with artificial intelligence may include, for example, the exchange between the job seeker and the artificial intelligence regarding confirmation of the job seeker's desired conditions, consultation regarding career changes, adjustment of job search conditions, and exchange of feedback on suggested information (headline information and search conditions) (this is not limited to natural language dialogue, but also includes the selection of options and predetermined input operations). The artificial intelligence that interacts with the job seeker may be called an AI agent or AI concierge.

[0041] Search result browsing history is a record of the facts and circumstances that indicate job seekers viewed job information (or a list of such job postings) presented as a result of a job search. Search result browsing history includes, for example, the display of the search results list, transitions from the search results list to the details screen of a specific job posting, the identifier of the viewed job posting, the number of views, the date and time of viewing, etc. Search result browsing history may also include the time spent viewing, the amount scrolled, cursor movements, or the frequency of screen transitions. It may also include information about jobs that were displayed on the list screen but were not clicked on and on to the details screen (impression history).

[0042] Behavioral history information may include date and time information. That is, behavioral history information is managed in association with date and time information of the date and time it occurred. The date and time information of behavioral history is information that can identify the time when an event such as behavioral information or dialogue occurred (or was updated). The date and time information of behavioral history includes, for example, the date and time of viewing job postings, the date and time of application, the date and time of viewing or replying to scout information, the date and time of executing a job search, the date and time of viewing the search results screen, the start and end dates and times of dialogue with artificial intelligence, etc. The date and time information of behavioral history can be used to calculate the difference between the most recent period and the past period, etc. The date and time information of behavioral history may also be used to calculate the degree of concentration or frequency of behavior within a given period (for example, concentration of viewing, etc. in a short period of time, the number of times viewing, etc. in a given time), or the cumulative viewing time, etc.

[0043] Registration information is information registered about job seekers. This information includes, for example, resume information such as a job seeker's CV and work history. Resume information is information (or a document) that job seekers use to communicate information about their work history to employers. Resume information includes, for example, desired industry, job type, work location, salary, experience, skills, qualifications, achievements, self-promotion, and work history information. Registration information may also be obtained as information recorded in a job seeker database.

[0044] The acquisition unit 231 may acquire feedback information from job seekers regarding at least one of the headline information, search conditions, and point axis in response to the feedback reception step. The feedback information may include, for example, at least one of the following: positive or negative evaluation, priority adjustment instructions, search condition modification instructions, adoption or rejection of headline information, and adoption or rejection of point axis. The acquisition unit 231 may acquire headline information selected by the job seeker as feedback information in response to the display control step. The acquisition unit 231 may also acquire search condition modification and save operations on the search screen as feedback information.

[0045] <Generation unit 232> The generation unit 232 generates multiple suggestion information based on the input information and the first reference information. The suggestion information includes headline information and search conditions used for job searching, with the headline information and search conditions being associated, and the first reference information includes at least the correlation between the input information and the suggestion information. By including behavioral history as input information, the generation unit 232 can generate suggestion information that takes into account the job seeker's interests, seriousness, areas in which they respond well, etc. This allows the system to present headline information that verbalizes the perspectives that the job seeker potentially values, rather than simply matching desired conditions, thereby providing insights that the job seeker themselves may not have been aware of and supporting the creation of search conditions.

[0046] The input information may be either the job seeker's activity history information or the registration information, and the multiple suggestion information generated based on the input information and the first reference information may be either multiple heading information or search conditions. For example, the generation unit 232 may generate multiple suggestion information based on the job seeker's activity history information and the first reference information. The generation unit 232 may generate multiple heading information based on the job seeker's activity history information and the first reference information. The generation unit 232 may generate multiple search conditions based on the job seeker's activity history information and the first reference information. The generation unit 232 may generate multiple suggestion information based on the job seeker's registration information and the first reference information. The generation unit 232 may generate multiple heading information based on the job seeker's registration information and the first reference information. The generation unit 232 may generate multiple search conditions based on the job seeker's registration information and the first reference information.

[0047] The first reference information includes at least the correlation between the input information and the suggested information. Here, the suggested information includes at least one of the headline information and the search conditions used for job searching, and if it includes both, the headline information and the search conditions are associated. The first reference information is stored, for example, in the memory unit 22. The first reference information may also include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the input information and the suggested information. The correlation included in the first reference information can be constructed, for example, by analyzing data including the input information and the corresponding suggested information (at least one of the headline information and the search conditions) using statistical methods or machine learning methods.

[0048] The first reference information may include a set of parameters for generating suggestion information from input information. For example, the first reference information may be various pre-trained models. The first reference information may include a machine learning model (hereinafter referred to as the suggestion information generation model) that is capable of taking input information as input and outputting suggestion information. In this case, the generation unit 232 inputs the input information into the suggestion information generation model and causes the suggestion information generation model to output the suggestion information. Here, the generation unit 232 can generate suggestion information that captures the job seeker's interests, needs, or level of seriousness by including behavioral history information as input information. Specifically, it becomes possible to generate suggestion information that dynamically reflects the job seeker's recent changes in preferences, potential areas of interest, or needs (insights) that the job seeker themselves has not yet been able to articulate, which cannot be read from registered information such as resumes and work history documents alone. This makes it possible to provide job search opportunities that are not merely condition matching, but are highly convincing to job seekers and give them new insights.

[0049] The proposal information generation model may be included in the artificial intelligence unit 243. If the proposal information generation model is a dedicated learning model, it may be constructed, for example, by learning using input information and corresponding proposal information data as training data. In such a proposal information generation model, parameters calculated or tuned through learning establish a correlation between the input information and the proposal information. The dedicated learning model may include a generative AI capable of generating proposal information not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be generated or the content of the task to be executed.

[0050] If the suggestion information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the suggestion information generation model that includes input information and instructions for outputting suggestion information (headline information and search conditions) based on the input information, causing the suggestion information generation model to output suggestion information. The generation unit 232 may also generate a prompt that includes instructions to generate suggestion information and input the prompt to the suggestion information generation model. Specific examples of instructions included in a prompt include, for example, "Analyze the following job seeker's resume (registration information) and / or behavioral history information, and estimate the 'point axes' that the job seeker seems to potentially value. Then, based on each value, generate and output three patterns of pairs of 'headlines' that the job seeker would want to click on and 'search conditions' for extracting job postings that match those point axes." It may also include instructions that focus on changes in the job seeker's behavior, such as "Analyze changes in behavioral history information and prioritize generating headlines that focus on changes in the job seeker." Furthermore, in addition to instructions for creating and outputting input information and proposed information, the generation unit 232 may also input prompts to the proposed information generation model that include, for example, one or more samples of input information and one or more samples of proposed information corresponding to them, as examples or samples of input and output pairs. In this case, a correlation between input information and proposed information is established by the parameters constituting the proposed information generation model and the prompts that include instructions to output proposed information corresponding to the input information. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input of instructions such as the content of the output information to be generated and the content of the task to be executed.

[0051] The generation unit 232 may generate multiple proposal information if the registered information and / or behavioral history information as input information meets predetermined conditions. Here, the predetermined conditions may include that at least one of the number of views, applications, and replies for at least one of the job postings and scout information within a predetermined period is equal to or greater than a predetermined value. The generation unit 232 may refrain from generating multiple proposal information if the input information does not meet predetermined information quantity or predetermined accuracy conditions. The generation unit 232 can control the timing of generating proposal information by receiving behavioral history information that meets predetermined conditions from the acquisition unit 231.

[0052] The generation unit 232 generates suggestion information based on information regarding changes in the job seeker. Changes in the job seeker include, for example, information regarding changes in the job seeker's status, attributes, or behavior. Information regarding changes in the job seeker can be derived, for example, from comparisons between the most recent period and past periods, comparisons between registration information and behavioral history information, or trends in time-series data. By using information regarding changes in the job seeker, the generation unit 232 can more easily generate suggestion information that reflects the job seeker's recent (or real-time) changes in interests, preferences, or potential changes in awareness.

[0053] The generation unit 232 generates multiple suggestion pieces of information based on at least one of the following: behavioral history information for the most recent period, the difference between behavioral history information for the most recent period and behavioral history information for past periods, and the difference between registered information and behavioral history information.

[0054] The most recent period of activity history information includes the history of activities that are identified as belonging to the most recent period based on the date and time information. The most recent period can be set as a predetermined period counting back from a predetermined point in time that triggers the generation or display of suggestion information (for example, the time when suggestion information is generated, or the time when it is determined that the activity history information meets predetermined conditions). The most recent period can be set as, for example, one day, three days, seven days, fourteen days, or thirty days.

[0055] The past period can be set, for example, as any period prior to the most recent period. The past period can be set, for example, as a period of the same length as the most recent period and consecutively immediately preceding the most recent period, but is not limited to this. For example, if the most recent period is 7 days, the past period can be set as the 7 days immediately preceding the most recent period. The past period may be set to include, for example, multiple periods prior to the most recent period (periods that are temporally separated from the most recent period; for example, the period immediately preceding the most recent period and the period before that), or it may be set to include a period longer than the most recent period (for example, the entire period from the time of the job seeker's registration, or a cumulative period in the past excluding the most recent period). The boundary, length, temporal position, and number of the most recent period and the past period may be stored in the storage unit 22 as setting values ​​of the information processing system 1, or may be set variably according to the attributes of the employer or job seeker.

[0056] The difference between the most recent period's activity history information and the activity history information of the past period includes the difference between the frequency, content, or attributes of the activities included in the most recent period's activity history information and the frequency, content, or attributes of the activities included in the past period's activity history information. The difference includes, for example, the difference in the number of times job postings were viewed, applied for, viewed, and replied to scout information, the number of job searches performed, the number of search results viewed, or the number of interactions between the most recent period and the past period. The difference may also include, for example, elements of search criteria that newly appeared or increased in the most recent period (industry, job type, work location, annual salary, company size, compensation, etc.), or elements of search criteria that decreased in the most recent period.

[0057] The differences between registration information and behavioral history information include discrepancies or divergences between the information regarding the job seeker's desired conditions or work history included in the registration information and the desired trends that appear in the job search history, search result viewing history, or interaction history with employers included in the behavioral history information. The differences include, for example, the differences between the desired conditions such as industry, job type, work location, annual salary, company size, or benefits included in the registration information and the content of the search conditions (industry, job type, work location, annual salary, company size, benefits, etc.) included in the job search history or the attributes of the viewed job information included in the search result viewing history. The differences may also include, for example, differences that indicate that the attributes of the job information frequently viewed or applied for in the behavioral history information differ from the desired conditions included in the registration information.

[0058] The generation unit 232 generates multiple suggestion information based on input information including at least one of the following: job search history, dialogue history with employers, dialogue history with artificial intelligence, and search result viewing history, and first reference information. For example, the generation unit 232 may estimate the industry, job type, work location, annual salary, company size, benefits, etc. that the job seeker is interested in based on the content of the search conditions (keywords, etc.) included in the job search history, and generate suggestion information based on the estimation results. For example, the generation unit 232 may estimate the attributes of job information that the job seeker is interested in based on the content of the scout information included in the dialogue history with employers (history of interactions with employers), and the content of the replies to the scout information, and generate suggestion information based on the estimation results. For example, the generation unit 232 may generate suggestion information based on the content included in the dialogue history with artificial intelligence (for example, history of interactions with an AI concierge). The generation unit 232 may, for example, estimate the types of industries that job seekers are interested in based on the job information they have viewed (e.g., job information identifier, number of views, and viewing date and time, etc.) included in the search results browsing history, and generate suggested information based on the estimation results.

[0059] The generation unit 232 generates multiple suggestion pieces of information for the job seeker using at least one of the behavioral history information and registration information of other identified job seekers together with the job seeker's input information. In order to identify other job seekers, the generation unit 232 may obtain the result of identifying other job seekers similar to the job seeker based on the input information. For example, the identification unit 236 may vectorize the input information (behavioral history information and / or registration information) as features and identify other job seekers similar to the job seeker by vector matching based on the similarity between the job seeker's vector and the vectors corresponding to other job seekers. The identification unit 236 can identify other job seekers similar to the job seeker by vector matching such as nearest neighbor search based on the dot product, cosine similarity, etc. Alternatively, the identification unit 236 may identify other job seekers similar to the job seeker by keyword matching based on the degree of agreement of keywords included in the input information (for example, job type, industry, skills, qualifications, work location, annual income range, or words included in resume information, etc.). Furthermore, the identification unit 236 may identify other similar job seekers by combining vector matching and keyword matching, and integrating the results of each matching.

[0060] The generation unit 232 uses at least one of the behavioral history information and registration information of other identified job seekers to easily generate suggestion information for the job seeker, even when the job seeker has little behavioral history information, such as a job seeker who has just registered. Furthermore, by referring to job postings and search criteria that similar job seekers have shown interest in, it becomes possible to present potential needs that the job seeker themselves may not yet be aware of, thereby broadening the job seeker's perspective.

[0061] The generation unit 232 generates heading information based on the input information and third reference information. The third reference information includes at least the correlation between the input information and the heading information. The generation unit 232 generates search conditions associated with the heading information based on the generated heading information and fourth reference information. The fourth reference information includes at least the correlation between the heading information and the search conditions. By generating the heading information first, the generation unit 232 can present a perspective or category that is easy for job seekers to understand, and then generate search conditions that are consistent with that perspective or category.

[0062] The third reference information includes at least the correlation between the input information and the heading information. Here, the generation unit 232 generates the heading information based on the input information and the third reference information. The third reference information is stored, for example, in the storage unit 22. The third reference information may include, for example, a table, a function, a simple algorithm, etc., that shows the correlation between the input information and the heading information. The correlation included in the third reference information can be constructed, for example, by statistically analyzing data that records the input information and the corresponding heading information.

[0063] The third reference information may include a set of parameters for generating headline information from input information. For example, the third reference information may be various pre-trained models. For example, the third reference information may include a headline information generation model which is a dedicated or general-purpose learning model that has been machine-trained to take input information as input and output headline information. In this case, the generation unit 232 inputs the input information to the headline information generation model and causes the headline information generation model to output headline information.

[0064] The headline information generation model may be included in the artificial intelligence unit 243. The headline information generation model, which is a dedicated learning model, may be constructed, for example, by training using input information data and corresponding headline information data as training data. In such a headline information generation model, parameters calculated and tuned through learning construct a correlation between the input information and the headline information. The dedicated learning model may include a generative AI capable of generating headline information not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be generated or the content of the task to be executed.

[0065] If the headline information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the headline information generation model that includes input information and an instruction to output headline information corresponding to the input information, causing the headline information generation model to output headline information. The generation unit 232 may also generate a prompt that gives the headline information generation model an instruction to generate headline information, and input this prompt to the headline information generation model. In addition to the input information and the instruction to create and output headline information, the generation unit 232 may also input a prompt to the headline information generation model that includes, for example, one or more samples of input information and one or more samples of corresponding headline information as examples, samples, or training data of input and output pairs. Here, the parameters that construct the headline information generation model and the prompt that includes an instruction to output headline information corresponding to the input information construct the correlation between the input information and the headline information. The general-purpose learning model may include a generation AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or a prompt containing such input). Generative AI for general-purpose learning models is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0066] The fourth reference information includes at least the correlation between the heading information and the search conditions. The fourth reference information may also include the correlation between the heading information, the input information and the search conditions. Here, the generation unit 232 generates search conditions associated with the heading information based on the generated heading information and the fourth reference information (or based on the heading information, the input information and the fourth reference information). The fourth reference information is stored, for example, in the storage unit 22. The fourth reference information may include, for example, a table, a function, a simple algorithm, etc., that shows the correlation between the heading information (or the heading information and the input information) and the search conditions. The correlations included in the fourth reference information can be constructed, for example, by statistically analyzing data that records the heading information (or the heading information and the input information) and the corresponding search conditions.

[0067] The fourth reference information may include a set of parameters for generating search conditions from the heading information (or the heading information and input information). For example, the fourth reference information may be various pre-trained models. For example, the fourth reference information may include a search condition generation model which is a dedicated or general-purpose learning model that has been machine-trained to take heading information (or the heading information and input information) as input and output search conditions. In this case, the generation unit 232 inputs the heading information (or the heading information and input information) into the search condition generation model and causes the search condition generation model to output search conditions.

[0068] The search condition generation model may be included in the artificial intelligence unit 243. The search condition generation model, which is a dedicated learning model, may be constructed, for example, by training using data of headline information (or headline information and input information) and data of corresponding search conditions as training data. In such a search condition generation model, parameters calculated and tuned through learning construct a correlation between headline information (or headline information and input information) and search conditions. The dedicated learning model may include a generative AI capable of generating search conditions not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0069] If the search condition generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the search condition generation model that includes headline information (or headline information and input information) and an instruction to output a search condition associated with the headline information, taking the headline information (or headline information and input information) as input, causing the search condition generation model to output the search condition. The generation unit 232 may also generate a prompt that gives the search condition generation model an instruction to generate a search condition, and input this prompt to the search condition generation model. In addition, the generation unit 232 may input a prompt to the search condition generation model that includes, in addition to headline information (or headline information and input information) and an instruction to create and output a search condition, an example, sample, or training data of an input and output pair, such as one or more samples of headline information (or headline information and input information) and one or more samples of corresponding search conditions. Here, parameters for constructing a search condition generation model and prompts containing instructions to output search conditions corresponding to heading information (or heading information and input information) establish a correlation between heading information (or heading information and input information) and search conditions. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0070] The generation unit 232 generates search conditions based on the input information and the fifth reference information. The fifth reference information includes at least the correlation between the input information and the search conditions. The generation unit 232 generates heading information associated with the search conditions based on the generated search conditions and the sixth reference information. The sixth reference information includes at least the correlation between the search conditions and the heading information. By generating the search conditions first, the generation unit 232 can prioritize generating search conditions that are likely to yield a predetermined number of job postings in a job search, and then generate heading information that matches those search conditions.

[0071] The fifth reference information includes at least the correlation between the input information and the search conditions. Here, the generation unit 232 generates the search conditions based on the input information and the fifth reference information. The fifth reference information is stored, for example, in the storage unit 22. The fifth reference information may include, for example, a table, a function, a simple algorithm, etc., that shows the correlation between the input information and the search conditions. The correlation included in the fifth reference information can be constructed, for example, by statistically analyzing data that records the input information and the corresponding search conditions.

[0072] The fifth reference information may include a set of parameters for generating search conditions from input information. For example, the fifth reference information may be various pre-trained models. For example, the fifth reference information may include a search condition generation model which is a dedicated or general-purpose learning model that has been machine-trained to take input information as input and output search conditions. In this case, the generation unit 232 inputs the input information into the search condition generation model and causes the search condition generation model to output search conditions.

[0073] The search condition generation model may be included in the artificial intelligence unit 243. The search condition generation model, which is a dedicated learning model, may be constructed, for example, by training using input information data and corresponding search condition data as training data. In such a search condition generation model, parameters calculated and tuned through learning construct a correlation between input information and search conditions. The dedicated learning model may include a generative AI capable of generating search conditions not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be generated or the content of the task to be executed.

[0074] If the search condition generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the search condition generation model that includes input information and an instruction to output a search condition corresponding to the input information, causing the search condition generation model to output the search condition. The generation unit 232 may also generate a prompt that gives the search condition generation model an instruction to create a search condition, and input this prompt to the search condition generation model. In addition to the input information and the instruction to create and output the search condition, the generation unit 232 may also input a prompt to the search condition generation model that includes, for example, one or more samples of input information and one or more samples of corresponding search conditions as examples, samples, or training data of input and output pairs. Here, the parameters that construct the search condition generation model and the prompt that includes an instruction to output a search condition corresponding to the input information construct the correlation between the input information and the search condition. The general-purpose learning model may include a generation AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or a prompt containing such input). Generative AI for general-purpose learning models is a general-purpose generative AI that requires input such as instructions on the content of the output information to be generated and the content of the task to be performed.

[0075] The sixth reference information includes at least the correlation between the search conditions and the heading information. Alternatively, the sixth reference information may include the correlation between the generated search conditions, the input information, and the heading information. Here, the generation unit 232 generates heading information associated with the search conditions based on the generated search conditions and the sixth reference information (or based on the search conditions, the input information, and the sixth reference information). The sixth reference information is stored, for example, in the storage unit 22. The sixth reference information may include, for example, a table, a function, a simple algorithm, etc., that shows the correlation between the search conditions (or the search conditions and the input information) and the heading information. The correlations included in the sixth reference information can be constructed, for example, by statistically analyzing data that records the search conditions (or the search conditions and the input information) and the corresponding heading information.

[0076] The sixth reference information may include a set of parameters for generating headline information from search conditions (or search conditions and input information). For example, the sixth reference information may be various pre-trained models. For example, the sixth reference information may include a headline information generation model which is a dedicated or general-purpose learning model that has been machine-trained to take search conditions (or search conditions and input information) as input and output headline information. In this case, the generation unit 232 inputs the search conditions (or search conditions and input information) to the headline information generation model and causes the headline information generation model to output headline information.

[0077] The headline information generation model may be included in the artificial intelligence unit 243. The headline information generation model, which is a dedicated learning model, may be constructed, for example, by training using search condition data (or search condition and input information) and corresponding headline information data as training data. In such a headline information generation model, parameters calculated and tuned through training construct a correlation between search condition data (or search condition and input information) and headline information. The dedicated learning model may include a generative AI capable of generating headline information not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0078] If the headline information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the headline information generation model that includes a search condition (or a search condition and input information) and an instruction to output headline information associated with the search condition, taking the search condition (or a search condition and input information) as input, causing the headline information generation model to output headline information. The generation unit 232 may also generate a prompt that gives the headline information generation model an instruction to create headline information and input the prompt to the headline information generation model. In addition, the generation unit 232 may input a prompt to the headline information generation model that includes, in addition to the search condition (or a search condition and input information) and the instruction to create and output headline information, an example, sample, or training data of input and output pairs, such as one or more samples of search conditions (or search conditions and input information) and one or more samples of corresponding headline information. Here, parameters for constructing a heading information generation model and prompts containing instructions to output heading information corresponding to search conditions (or search conditions and input information) establish a correlation between search conditions (or search conditions and input information) and heading information. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0079] The generation unit 232 generates search conditions based on the point axis and the eighth reference information. The eighth reference information includes at least the correlation between the point axis and the search conditions.

[0080] The eighth reference information includes at least the correlation between the point axis and the search conditions. Alternatively, the eighth reference information may include the correlation between the point axis, the input information and the search conditions. Here, the generation unit 232 generates the search conditions based on the point axis and the eighth reference information (or based on the point axis, the input information and the eighth reference information). The eighth reference information is stored, for example, in the storage unit 22. The eighth reference information may include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the point axis (or the point axis and the input information) and the search conditions. The correlations included in the eighth reference information can be constructed, for example, by statistically analyzing data that records the point axis (or the point axis and the input information) and the corresponding search conditions.

[0081] The eighth reference information may include a set of parameters for generating search conditions from the point axis (or the point axis and input information). For example, the eighth reference information may be various pre-trained models. For example, the eighth reference information may include a search condition generation model which is a dedicated or general-purpose learning model that has been machine-trained to take the point axis (or the point axis and input information) as input and output search conditions. In this case, the generation unit 232 inputs the point axis (or the point axis and input information) into the search condition generation model and causes the search condition generation model to output search conditions.

[0082] The search condition generation model may be included in the artificial intelligence unit 243. The search condition generation model, which is a dedicated learning model, may be constructed, for example, by training using data of point axes (or point axes and input information) and data of corresponding search conditions as training data. In such a search condition generation model, parameters calculated and tuned through training construct a correlation between point axes (or point axes and input information) and search conditions. The dedicated learning model may include a generative AI capable of generating search conditions not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0083] If the search condition generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the search condition generation model that includes a point axis (or a point axis and input information) and an instruction to output a search condition corresponding to the point axis (or a point axis and input information) as input, causing the search condition generation model to output the search condition. The generation unit 232 may also generate a prompt that gives the search condition generation model an instruction to generate a search condition, and input this prompt to the search condition generation model. In addition to the point axis (or a point axis and input information) and the instruction to generate and output the search condition, the generation unit 232 may also input a prompt to the search condition generation model that includes, for example, a sample of one or more point axis samples (or a point axis and one or more input information) and a sample of one or more search conditions corresponding to them, as an example, sample, or training data of input and output pairs. Here, parameters for constructing a search condition generation model and prompts containing instructions to output search conditions corresponding to the point axis (or the point axis and input information) establish a correlation between the point axis (or the point axis and input information) and the search conditions. Note that the general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI of the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0084] The generation unit 232 generates heading information based on the point axis and the ninth reference information. The ninth reference information includes at least the correlation between the point axis and the heading information. Alternatively, the generation unit 232 may generate heading information based on the point axis, input information and the ninth reference information. The ninth reference information may include the correlation between the point axis, input information and the heading information.

[0085] The ninth reference information includes at least the correlation between the point axis and the heading information. Here, the generation unit 232 generates heading information based on the point axis and the ninth reference information (or based on the point axis, input information and the ninth reference information). The ninth reference information is stored, for example, in the storage unit 22. The ninth reference information may include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the point axis (or the point axis and input information) and the heading information. The correlation included in the ninth reference information can be constructed, for example, by statistically analyzing data that records the point axis (or the point axis and input information) and the corresponding heading information.

[0086] The ninth reference information may include a set of parameters for generating heading information from the point axis (or the point axis and input information). For example, the ninth reference information may be various pre-trained models. For example, the ninth reference information may include a heading information generation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take the point axis (or the point axis and input information) as input and output heading information. In this case, the generation unit 232 inputs the point axis (or the point axis and input information) to the heading information generation model and causes the heading information generation model to output heading information.

[0087] The headline information generation model may be included in the artificial intelligence unit 243. The headline information generation model, which is a dedicated learning model, may be constructed, for example, by training using point axis (or point axis and input information) data and corresponding headline information data as training data. In such a headline information generation model, parameters calculated and tuned through training construct a correlation between the point axis (or point axis and input information) and the headline information. The dedicated learning model may include a generative AI capable of generating headline information not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0088] If the headline information generation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the generation unit 232 may input a prompt to the headline information generation model that includes a point axis (or a point axis and input information) and an instruction to output headline information corresponding to the point axis (or a point axis and input information) as input, causing the headline information generation model to output headline information. The generation unit 232 may also generate a prompt that gives the headline information generation model an instruction to generate headline information and input the prompt to the headline information generation model. In addition, the generation unit 232 may input a prompt to the headline information generation model that includes, in addition to the point axis (or a point axis and input information) and the instruction to generate and output headline information, an example, sample, or training data of an input and output pair, such as one or more sample point axes (or a point axis and input information) and one or more sample headline information corresponding to them. Here, parameters for constructing a heading information generation model and prompts containing instructions to output heading information corresponding to the point axis (or the point axis and input information) establish a correlation between the point axis (or the point axis and input information) and the heading information. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0089] The generation unit 232 may generate at least one of the search conditions and the heading information using the point axis re-estimated by the re-estimate unit 240. For example, the generation unit 232 generates the search conditions based on the re-estimated point axis (or the re-estimated point axis and input information) and the eighth reference information, and / or generates the heading information based on the re-estimated point axis and the ninth reference information.

[0090] Here, since the point axis may be re-estimated in response to the receipt of job seeker feedback information or updates to the input information, the input information after re-estimate may differ from the input information before re-estimate. Therefore, the reference information (for example, the first, third, fourth, fifth, sixth, eighth, and ninth reference information) referenced in the generation of search conditions or heading information performed after re-estimate may be updated by switching references, updating parameters, or relearning, etc., to fit the updated input information or the re-estimated point axis.

[0091] <Display Control Unit 233> The display control unit 233 is configured to display various information on the job seeker terminal 3 or other devices. The display control unit 233 controls the display of visual information such as screens, images including still images or videos, icons, and messages (text) on the job seeker terminal 3 or other devices. The display control unit 233 may also generate rendering information for displaying visual information on the job seeker terminal 3 or other devices and transmit this to the job seeker terminal 3, thereby controlling the job seeker terminal 3, etc. to generate visual information and display it on the display unit 34. Alternatively, the display control unit 233 may generate visual information and transmit it to the job seeker terminal 3, etc., thereby controlling the display unit 34, etc. to display visual information. The display control unit 233 executes processing to display system screens related to the information processing system 1 on each terminal. For example, the display control unit 233 performs processing such as generating and transmitting HTML (Hyper Text Markup Language) files and displays a web page showing the system screen on the display unit 34. The display control unit 233 may also perform processing such as generating and transmitting display data for applications that use the information processing system 1. For example, the display control unit 233 can display various visual information on the display unit 34.

[0092] The display control unit 233 displays multiple headline information included in the generated multiple proposal information. From the multiple headline information, the display control unit 233 displays to the job seeker at least one of the search conditions associated with the headline information selected by the job seeker and the results of the job search using the search conditions.

[0093] The display control unit 233 may display to the job seeker the search conditions associated with the selected headline information and the search results of the job search using the search conditions side by side. Furthermore, the display control unit 233 may accept changes or modifications to the search conditions on the screen and update and display the search results with the modified search conditions. In this configuration, since the search conditions and search results corresponding to the selected headline are displayed side by side, the job seeker can view the search conditions and the search results of the job search using the search conditions simultaneously. The display control unit 233 may also display the search screen that displays the job search results in a way that allows for editing and saving of the search conditions. The display control unit 233 may store the saved search conditions in the storage unit 22 in association with the job seeker. In addition, the job seeker can adjust the search conditions while checking whether the suggested search conditions match their intentions by looking at the search results. This eliminates the need to repeatedly switch screens to modify search conditions and check results, improving the efficiency with which the job seeker can reach their desired job.

[0094] The display control unit 233 displays multiple headings when the behavior history information meets predetermined conditions. The predetermined conditions include that at least one of the following for at least one of the job postings and scouting information within a predetermined period is equal to or greater than a predetermined value: the number of views, the number of applications, and the number of replies.

[0095] The display control unit 233 may control the display so as not to show heading information associated with search conditions where the number of job postings is less than a predetermined number. Less than a predetermined number may include, for example, cases where the number of job postings is 0, or cases where the number of job postings is 1 or more but less than 10. The display control unit 233 may hide heading information associated with search conditions where the number of job postings is 0. Alternatively, instead of hiding heading information associated with search conditions where the number of job postings is less than a predetermined number, the display control unit 233 may display it in a manner that reduces its visibility compared to other heading information (for example, grayscale, low saturation, semi-transparent, or deactivated), or it may display it with reduced emphasis, such as by reducing the display size.

[0096] The display control unit 233 may display the suggested information according to its priority. For example, the display control unit 233 may display a predetermined number of suggested information items with higher priority rankings. The display control unit 233 may change the display order of the heading information according to its priority, displaying heading information with higher priority at the top. The display control unit 233 may also display the heading information with an indicator of priority (for example, rank, score, or highlighting) according to its priority.

[0097] The display control unit 233 may, after displaying at least one of the search criteria and the results of the job search using the search criteria to the job seeker, redisplay the headline information included in the retained suggestion information when the job seeker returns to the screen displaying multiple headline information and redisplays the multiple headline information. The display control unit 233 may, when the job seeker performs an operation to return to the screen displaying multiple headline information, refer to the retained suggestion information and redisplay multiple headline information based on the same suggestion information.

[0098] The display control unit 233 displays multiple estimated point axes. The display control unit 233 may display multiple point axes in a selectable manner and, based on the point axis selected by the job seeker, display search conditions associated with that point axis, or search conditions generated based on that point axis and input information, on the job seeker terminal 3. The display control unit 233 may display point axes according to priority.

[0099] <Decision Section 234> The determination unit 234 may determine a priority for each of the generated multiple proposals based on the input information, the proposal information, and the second reference information. The second reference information includes at least the correlation between the input information, the proposal information, and the priority. In this embodiment, the display control unit 233 can display the proposal information according to the priority.

[0100] The second reference information includes at least the correlation between the input information, the proposed information, and the priority. Here, the decision unit 234 determines a priority for each of the multiple proposed information items generated based on the input information, the proposed information, and the second reference information. The second reference information is stored, for example, in the storage unit 22. The second reference information may include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the input information, the proposed information, and the priority. The correlations included in the second reference information can be constructed, for example, by statistically analyzing data that records the input information, the proposed information, and the corresponding priority (or proposed information to which a priority has been assigned).

[0101] The second reference information may include a set of parameters for determining priority from the input information and the proposed information. For example, the second reference information may be various pre-trained models. For example, the second reference information may include a priority determination model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take the input information and the proposed information as inputs and output a priority. In this case, the determination unit 234 inputs the input information and the proposed information into the priority determination model and causes the priority determination model to output a priority.

[0102] The priority determination model may be included in the artificial intelligence unit 243. The priority determination model, which is a dedicated learning model, may be constructed, for example, by training using input information, proposed information data, and corresponding priority data as training data. In such a priority determination model, parameters calculated and tuned through learning construct a correlation between the input information, proposed information, and priority. The dedicated learning model may include a generative AI capable of generating priorities (or priority assignment results) that are not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be generated or the content of the task to be executed.

[0103] If the priority determination model is a general-purpose learning model (for example, a language model such as a large-scale language model), the determination unit 234 may input a prompt to the priority determination model that includes input information, proposal information, and an instruction to output a priority corresponding to the input information and proposal information, causing the priority determination model to output the priority. The determination unit 234 may also generate a prompt that gives an instruction to the priority determination model to determine the priority, and input this prompt to the priority determination model. In addition to the input information, proposal information, and priority determination / output instruction, the determination unit 234 may also input a prompt to the priority determination model that includes, for example, one or more samples of input information, one or more samples of proposal information, and one or more samples of corresponding priorities as examples, samples, or training data of input and output pairs. Here, the parameters that construct the priority determination model and the prompt that includes an instruction to output a priority corresponding to the input information and proposal information construct the correlation between the input information, proposal information, and priority. Furthermore, a general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or a prompt containing such input). The generative AI of a general-purpose learning model is a general-purpose generative AI that requires input such as the content of the output information to be generated and the content of the task to be performed.

[0104] The decision unit 234 may estimate the probability (hereinafter referred to as the response probability) that a job seeker will apply, view the proposal, view the detailed information corresponding to the proposal, or express interest for each piece of proposal information, and may determine priority based on the estimated response probability. The decision unit 234 may use an estimation model that takes input information and the content of the proposal information as inputs to output a response probability in order to estimate the response probability. The decision unit 234 may also calculate the degree of matching between the job seeker's registration information or behavioral history information (or input information including these) and the proposal information, and may determine priority based on the calculated degree of matching. The degree of matching may be calculated, for example, based on the similarity between the features of the registration information or behavioral history information and the features of the proposal information (headline information and / or search conditions).

[0105] Furthermore, the determination unit 234 may determine the priority of each of the proposed information regenerated by the regeneration unit 238 based on the input information (and feedback information as necessary) and the second reference information. The second reference information may be the same as the one used for the initial priority determination, or it may be updated to match the input information or feedback information used for regeneration.

[0106] Furthermore, the determination unit 234 may determine the priority of the point axes estimated by the point axis estimation unit 239 and / or the point axes re-estimated by the re-estimate unit 240, based on the input information (and feedback information as necessary) and the second reference information. The second reference information may be the same as that used to determine the priority of the proposed information, or it may be adapted to the point axis priority determination. Also, the second reference information used to estimate the point axes after re-estimate may be the same as that used for the initial priority determination, or it may be updated to match the input information or feedback information used for estimation or re-estimate.

[0107] <Job posting calculation section 235> The job number calculation unit 235 calculates the number of job postings when a job search is performed using the search conditions contained in each of the generated multiple proposal information. For example, the job number calculation unit 235 performs a job search for each proposal information using the search conditions contained in the proposal information as the job search query, and calculates the number of job postings extracted by the job search as the number of job postings. The job number calculation unit 235 can also calculate the number of job postings by, for example, aggregating the number of job postings or identifiers returned as search results of the job search. For example, when performing a job search, the job number calculation unit 235 can search for job postings using search items (e.g., industry, job type, work location, annual salary, company size, benefits, etc.) included in the search conditions, and calculate the number of job postings that satisfy the search conditions as the number of job postings. For example, the job number calculation unit 235 can calculate the number of job postings for each of the multiple proposal information and store the calculated number of job postings in the storage unit 22 in association with the heading information or search conditions contained in the proposal information.

[0108] <Specific part 236> The identification unit 236 identifies other job seekers similar to the job seeker based on the input information. In this specification, "other job seekers" means one or more job seekers who are different from the job seeker for whom the suggestion information is generated, and who have been identified as similar to the job seeker based on the input information (including at least behavioral history information and registration information). The identification unit 236 identifies other job seekers similar to the job seeker based on the input information. For example, the identification unit 236 may identify other job seekers based on matching or similarity of desired conditions (industry, job type, work location, annual income, etc.) included in the registration information, and / or matching or similarity of behavioral trends included in the behavioral history information, such as viewing and applying for job postings, viewing and responding to scout information, performing job searches, viewing search results, dialogue history with employers, and dialogue history with artificial intelligence.

[0109] <Feedback Reception Department 237> The feedback receiving unit 237 accepts implicit feedback from job seekers, including not only explicit input (affirmative or negative, importance, comments, etc.) but also operation logs such as selection, viewing, editing, transitions, and time spent on heading information, search conditions, and point axes. Based on this feedback, it can generate feedback information, output it to the generation unit 232, or store it in the storage unit 22. The feedback receiving unit 237 may also generate feedback information by associating the received feedback with identifiers that indicate the subject of the feedback (identifiers that identify heading information, identifiers that identify search conditions, and / or identifiers that identify point axes).

[0110] The feedback receiving unit 237 receives feedback from job seekers regarding at least one of the headline information and / or search conditions. The feedback receiving unit 237 may, for example, receive at least one of the following as feedback on the headline information and / or search conditions: the selection operation of headline information, the editing operation of search conditions, the operation indicating affirmation or negation, and the input of comments on the job seeker terminal 3. The feedback receiving unit 237 generates feedback information by associating the received feedback with an identifier indicating the subject of the feedback (an identifier that identifies the headline information and / or an identifier that identifies the search conditions), and may output the generated feedback information to the generation unit 232 or store it in the storage unit 22. Depending on the subject of the generated feedback information, the feedback receiving unit 237 may output information to cause the regeneration unit 238 to regenerate the proposed information, and / or output information to cause the reestimation unit 240 to reestimate the point axis. For example, if the feedback information concerns the heading information and / or search criteria, the feedback receiving unit 237 may output the feedback information to the regeneration unit 238, causing the regeneration unit 238 to regenerate the suggestion information. The feedback receiving unit 237 may also output information to the display control unit 233 to display different suggestion information, depending on the feedback information. The display control unit 233 may display suggestion information with the next priority depending on the feedback information. Furthermore, the display control unit 233 may change the display order of already displayed heading information and search criteria, hide them, highlight them, etc., based on the feedback information.

[0111] The feedback receiving unit 237 receives feedback from job seekers regarding the point axes. The feedback receiving unit 237 may, for example, receive inputs indicating the importance of a point axis selected by the job seeker from among multiple point axes displayed by the display control unit 233, or inputs indicating the importance of a point axis, as feedback on the point axes. The feedback receiving unit 237 may also receive inputs indicating that none of the displayed point axes match the job seeker's intentions or preferences (for example, operation inputs such as "None applicable," "Show other suggestions," or "Does not match preferences") as feedback. The feedback receiving unit 237 may generate feedback information by associating the received feedback with an identifier that identifies the point axis and negative evaluation information, and output it to the generation unit 232 or store it in the storage unit 22. If the feedback information concerns the point axes, the feedback receiving unit 237 may output the feedback information to the re-estimation unit 240, causing the re-estimation unit 240 to re-estimate the point axes. In particular, if the feedback information includes a negative evaluation of the presented point axis (such as "there is no good point axis"), the re-estimation unit 240 may prioritize re-estimating a point axis using a different perspective, attribute, or category than the point axis presented this time. The feedback receiving unit 237 may also output information to the display control unit 233 to display a different point axis, depending on the feedback information. The display control unit 233 may display point axes in the following order of priority depending on the feedback information. Furthermore, the display control unit 233 may change the display order of already displayed point axes, hide them, highlight them, etc., based on the feedback information.

[0112] <Regeneration unit 238> The regeneration unit 238 regenerates the proposed information after receiving the feedback. Based on the feedback information, the regeneration unit 238 may regenerate new proposed information by, for example, changing the priority of the displayed heading information, replacing the heading information, modifying the search conditions, or replacing the search conditions. The regeneration unit 238 regenerates new proposed information based on the input information, the displayed proposed information, the feedback information, and the tenth reference information. The tenth reference information includes at least the correlation between the input information, the displayed proposed information, the feedback information, and the new proposed information.

[0113] The tenth reference information includes at least the correlation between the input information, the displayed proposal information, the feedback information, and the new proposal information. Here, the regeneration unit 238 regenerates the new proposal information based on the input information, the displayed proposal information, the feedback information, and the tenth reference information. The tenth reference information is stored, for example, in the storage unit 22. The tenth reference information may include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the input information, the displayed proposal information, the feedback information, and the new proposal information. The correlations included in the tenth reference information can be constructed, for example, by statistically analyzing data that records the input information, the displayed proposal information, the feedback information, and the newly regenerated proposal information in response to them.

[0114] The tenth reference information may include a set of parameters for regenerating new proposal information from the input information, the displayed proposal information, and the feedback information. For example, the tenth reference information may be various trained models. For example, the tenth reference information may include a proposal information regeneration model, which is a dedicated trained model or a general-purpose trained model that has been trained to take the input information, the displayed proposal information, and the feedback information as input and output new proposal information. In this case, the regeneration unit 238 inputs the input information, the displayed proposal information, and the feedback information into the proposal information regeneration model and causes the proposal information regeneration model to output new proposal information.

[0115] The proposal information regeneration model may be included in the artificial intelligence unit 243. The proposal information regeneration model, which is a dedicated learning model, may be constructed by training using, for example, (a) input information, (b) displayed proposal information, (c) feedback information, and (d) new proposal information corresponding to these as training data. In such a proposal information regeneration model, parameters calculated and tuned through learning construct correlations between the input information, displayed proposal information, feedback information, and new proposal information. The dedicated learning model may include a generative AI capable of generating new proposal information not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0116] If the proposal information regeneration model is a general-purpose learning model (for example, a language model such as a large-scale language model), the regeneration unit 238 may input a prompt to the proposal information regeneration model that includes input information, displayed proposal information and feedback information, and an instruction to output new proposal information corresponding to the input information, displayed proposal information and feedback information, taking the input information, displayed proposal information and feedback information as input, causing the proposal information regeneration model to output new proposal information. The regeneration unit 238 may also generate a prompt that gives the proposal information regeneration model an instruction to regenerate new proposal information, and input this prompt to the proposal information regeneration model. In addition, the regeneration unit 238 may input a prompt to the proposal information regeneration model that includes, in addition to the input information, displayed proposal information and feedback information and the instruction to regenerate and output new proposal information, an example of input and output pairs, such as one or more samples of input information, samples of displayed proposal information and feedback information, and one or more samples of new proposal information corresponding to them, as example, sample, or training data. Here, parameters for constructing a proposal information regeneration model and prompts containing instructions to output new proposal information corresponding to input information, displayed proposal information, and feedback information establish a correlation between the input information, displayed proposal information, feedback information, and new proposal information. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input instructions such as the content of the output information to be generated and the content of the task to be performed.

[0117] <Point axis estimation unit 239> The point axis estimation unit 239 estimates a point axis that indicates the aspects that job seekers consider important in a job posting, based on the input information and the seventh reference information. The seventh reference information includes at least the correlation between the input information and the point axis.

[0118] The points axis represents information that job seekers prioritize in job postings, and can be expressed, for example, as part of or a combination of search criteria in a job search. Specifically, the points axis may be expressed as a combination of conditions that include at least one of the following: industry, business type, company size, job type, work location, annual salary, benefits, etc. (e.g., "Growing company x Autonomy x Remote work possible").

[0119] Furthermore, the point axis is not limited to the enumeration of conditions as described above, but may also be expressed as a message that abstracts the job seeker's preferences or desires. For example, the point axis estimation unit 239 may infer the image of the job seeker's preferences based on the behavioral history information (behavioral logs such as browsing, applying, replying, editing and saving search conditions, etc.) and registration information (resume information, etc.) included in the input information, and estimate a message that summarizes that image of preferences (e.g., "I want to achieve results in the field rather than management," "I value growth opportunities more than stability," etc.) as the point axis. The display control unit 233 may also display the search conditions or heading information corresponding to the message.

[0120] The point axis is not limited to perspectives that match the desired conditions included in the registration information, but may also include perspectives different from the desired conditions (for example, perspectives for expanding the field of view, unexpected perspectives) based on behavioral history information and differences. In this case, the display control unit 233 may also display a message indicating that the point axis is a "proposal for expanding the field of view".

[0121] The seventh reference information includes at least the correlation between the input information and the point axis. Here, the point axis estimation unit 239 estimates the point axis that indicates the aspects that job seekers value in job postings, based on the input information and the seventh reference information. The seventh reference information is stored, for example, in the memory unit 22. The seventh reference information may include, for example, a table, a function, a simple algorithm, etc., that shows the correlation between the input information and the point axis. The correlation included in the seventh reference information can be constructed, for example, by statistically analyzing data that records the input information and the corresponding point axis.

[0122] The seventh reference information may include a set of parameters for estimating the point axis from the input information. For example, the seventh reference information may be various pre-trained models. For example, the seventh reference information may include a point axis estimation model which is a dedicated learning model or a general-purpose learning model that has been machine-trained to take the input information as input and output the point axis. In this case, the point axis estimation unit 239 inputs the input information to the point axis estimation model and causes the point axis estimation model to output the point axis.

[0123] The point axis estimation model may be included in the artificial intelligence unit 243. The point axis estimation model, which is a dedicated learning model, may be constructed, for example, by training using input information data and corresponding point axis data as training data. In such a point axis estimation model, parameters calculated and tuned through learning construct a correlation between the input information and the point axis. The dedicated learning model may include a generative AI capable of estimating point axes not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input instructions such as the content of the output information to be estimated or the content of the task to be performed.

[0124] If the point axis estimation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the point axis estimation unit 239 may input a prompt to the point axis estimation model that includes input information and an instruction to output a point axis corresponding to the input information, causing the point axis estimation model to output the point axis. The point axis estimation unit 239 may also generate a prompt that gives the point axis estimation model an instruction to estimate the point axis and input this prompt to the point axis estimation model. In addition to the input information and the instruction to estimate and output the point axis, the point axis estimation unit 239 may also input a prompt to the point axis estimation model that includes, for example, one or more samples of input information and one or more samples of corresponding point axes as examples, samples, or training data of input and output pairs. Here, the parameters for constructing the point axis estimation model and the prompt including an instruction to output a point axis corresponding to the input information construct the correlation between the input information and the point axis. Furthermore, a general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or a prompt containing such input). The generative AI of a general-purpose learning model is a general-purpose generative AI that requires input such as the content of the output information to be generated and the content of the task to be performed.

[0125] By using the estimated point axis, the generation unit 232 generates search conditions and heading information, thereby generating proposal information that aligns with the perspectives that job seekers prioritize in job postings. Note that the estimation of the point axis may be performed before or after the generation of heading information or search conditions, and the order of generation of the point axis, heading information, and search conditions is not limited.

[0126] <Re-estimation unit 240> The re-estimation unit 240 re-estimates the point axis after receiving feedback. The re-estimation unit 240 re-estimates the new point axis based on the input information, the displayed point axis, the feedback information, and the 11th reference information. The 11th reference information includes at least the correlation between the input information, the displayed point axis, the feedback information, and the new point axis. The re-estimation unit 240 may re-estimate the new point axis based on the feedback information, for example, by adding, deleting, or changing the weighting of viewpoints that constitute the point axis.

[0127] The 11th reference information includes at least the correlation between the input information, the displayed point axis, the feedback information, and the new point axis. Here, the re-estimation unit 240 re-estimates the new point axis based on the input information, the displayed point axis, the feedback information, and the 11th reference information. The 11th reference information is stored, for example, in the storage unit 22. The 11th reference information may include, for example, a table, function, rule set, or simple algorithm that shows the correlation between the input information, the displayed point axis, the feedback information, and the new point axis. The correlations included in the 11th reference information can be constructed, for example, by statistically analyzing data that records the input information, the displayed point axis, the feedback information, and the newly re-estimated point axis corresponding to these.

[0128] The 11th reference information may include a set of parameters for reestimating new point axes from the input information, displayed point axes, and feedback information. For example, the 11th reference information may be various trained models. For example, the 11th reference information may include a point axis reestimation model which is a dedicated trained model or a general-purpose trained model that has been machine-learned to take the input information, displayed point axes, and feedback information as input and output new point axes. In this case, the reestimation unit 240 inputs the input information, displayed point axes, and feedback information into the point axis reestimation model and causes the point axis reestimation model to output new point axes.

[0129] The point axis reestimation model may be included in the artificial intelligence unit 243. The point axis reestimation model, which is a dedicated learning model, may be constructed by training using, for example, (a) input information, (b) displayed point axes, (c) feedback information, and (d) data of new point axes corresponding to these as training data. In such a point axis reestimation model, parameters calculated and tuned through training construct correlations between the input information, displayed point axes, feedback information, and new point axes. The dedicated learning model may include a generative AI capable of estimating new point axes not included in the training data. The generative AI of the dedicated learning model is a limited-use generative AI that does not require input of instructions such as the content of the output information to be estimated or the content of the task to be performed.

[0130] If the point axis reestimation model is a general-purpose learning model (for example, a language model such as a large-scale language model), the reestimation unit 240 may input a prompt to the point axis reestimation model that includes input information, displayed point axes and feedback information, and an instruction to output new point axes corresponding to the input information, displayed point axes and feedback information, causing the point axis reestimation model to output new point axes. The reestimation unit 240 may also generate a prompt that gives the point axis reestimation model an instruction to reestimate the new point axes and input this prompt to the point axis reestimation model. In addition, the reestimation unit 240 may input a prompt to the point axis reestimation model that includes, in addition to the input information, displayed point axes and feedback information and the instruction to reestimate and output new point axes, includes, for example, one or more samples of input information, samples of displayed point axes and samples of feedback information, and one or more samples of new point axes corresponding to them, as examples, samples, or training data of input and output pairs. Here, parameters for constructing a point axis re-estimation model and prompts containing instructions to output new point axes corresponding to input information, displayed point axes, and feedback information establish a correlation between the input information, displayed point axes, feedback information, and new point axes. The general-purpose learning model may include a generative AI capable of generating arbitrary output information based on the information input to the general-purpose learning model (for example, the input described in this paragraph, or prompts containing such input). The generative AI in the general-purpose learning model is a general-purpose generative AI that requires input such as the content of the output information to be generated and the content of the task to be performed.

[0131] <Holding part 241> The storage unit 241 may, for example, acquire multiple generated proposal information and store the multiple proposal information in the storage unit 22. The storage unit 241 may, for example, provide the headline information included in the stored proposal information to the display control unit 233 when a job seeker returns to a screen displaying multiple headline information and requests that the multiple headline information be displayed again. The storage unit 241 stores multiple proposal information. The storage unit 241 may store multiple proposal information in association with the headline information and search conditions included in the proposal information. The storage unit 241 may store multiple proposal information in association with the generation date and time, display date and time, priority, or the number of job postings calculated by the job posting calculation unit 235. The storage unit 241 may store multiple proposal information in association with an identifier (for example, a job seeker ID) for each job seeker. The storage unit 241 may set a period equivalent to the most recent period as the retention period for the multiple proposal information, or it may control the system to delete or update the multiple proposal information after a predetermined period has elapsed. The holding unit 241 may hold multiple pieces of suggestion information in association with the feedback information received by the feedback receiving unit 237.

[0132] By having the storage unit 241 store the suggestion information, even if the suggestion information dynamically generated by the generation unit 232 may change each time it is generated, the same suggestion information as the previous time can be displayed when it is redisplayed. In other words, even if a job seeker re-accesses the system, such as by returning to a screen that displays multiple headline information, the headline information and / or search conditions that were displayed at that time can be redisplayed based on the suggestion information stored in the storage unit 241. As a result, job seekers can more easily consider the suggestion information while comparing it with the content displayed the previous time, enabling them to make stable decisions such as selecting headline information and adjusting search conditions, thereby improving the consistency of the job seeker's user experience.

[0133] <Determination unit 242> The determination unit 242 determines whether the behavioral history information satisfies predetermined conditions. The predetermined conditions include that at least one of the number of views, applications, and replies for at least one of the job postings and scouting information within a predetermined period is equal to or greater than a predetermined value. The determination unit 242 may use at least one of the viewing frequency, application frequency, or reply frequency for at least one of the job postings and scouting information as a predetermined condition. The determination unit 242 may use any one parameter related to viewing, applying, or replying for at least one of the job postings and scouting information, or a combination of parameters. The determination unit 242 may use a combination of multiple parameters such as the sum of the number of replies and the number of views, the sum of the number of applications and replies, or a weighted sum of the number of views, applications, and replies. The determination unit 242 may use the most recent period as the predetermined period used for the predetermined conditions, or it may distinguish between the most recent period and the past period. The determination unit 242 may use the number or frequency of at least one of the following included in the behavioral history information: job search history, dialogue history with employers, dialogue history with artificial intelligence, and search result viewing history, as a predetermined condition. Alternatively, the determination unit 242 may use the fact that the confidence level regarding the generation of the proposed information is above a predetermined threshold as a predetermined condition.

[0134] The determination unit 242 may output trigger information to start the generation of suggestion information by the generation unit 232 or to start the display of heading information by the display control unit 233 if it determines that predetermined conditions are met. The determination unit 242 may determine the reliability of generating or displaying suggestion information (e.g., search conditions) based on the amount or content of the input information. If the reliability is below a predetermined threshold, the determination unit 242 may not output trigger information to start the generation of suggestion information by the generation unit 232 or to start the display by the display control unit 233.

[0135] The conditions for determining whether the determination unit 242 will start generating the suggested information by the generation unit 232, and the conditions for determining whether the display control unit 233 will start displaying the headline information, may be the same or different. For example, the determination unit 242 may output trigger information to start generating the suggested information when the confidence level is above a predetermined threshold, and may output trigger information to start displaying the information when the number of job postings or the operation status of job seekers meets predetermined conditions.

[0136] <Artificial Intelligence Department 243> The artificial intelligence unit 243 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server 2 in each functional unit may be common to all units, or it may be individually prepared for each functional unit. The artificial intelligence unit 243 functions as a core module that supports the artificial intelligence processing in each of these functional units.

[0137] The artificial intelligence unit 243 may be an AI (Artificial Intelligence) equipped with pre-trained models such as transformers including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), and language models such as recurrent neural networks (RNNs). The artificial intelligence unit 243 may be, for example, a general-purpose learning model including various language models, large-scale language models, and generative AI, or an AI agent, and may include specific models such as OpenAI's GPT, Google's Gemini, and models provided through services and platforms such as Microsoft's Azure AI Studio. Generative AI may be, for example, text generation AI, image generation AI, or multimodal generation AI. The pre-trained model may be called an artificial intelligence model, machine learning model, or deep learning model. In addition, the artificial intelligence unit 243 can include any pre-trained model.

[0138] Specific machine learning algorithms used to build trained models include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 243 can apply these algorithms as appropriate.

[0139] The artificial intelligence unit 243 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. Furthermore, the trained model may not only be one trained for a specific task, but also a general-purpose learning model that can be used universally for a wide range of tasks.

[0140] The artificial intelligence unit 243 may include a natural language model as its artificial intelligence, or it may be a general-purpose learning model such as a Large Language Model (LLM). An LLM is a learning model that has been pre-trained on a large amount of large-scale data consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database), and can perform various language processing tasks by being given a task. According to the given prompt, it can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, responding to questions, and generating sentences. Such a general-purpose learning model may include a pre-trained model that can handle various tasks without fine-tuning by using One-shot Learning or Few-shot Learning. Furthermore, the general-purpose learning model may also be configured to handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 23 may be a separate pre-trained model, or it may be a common general-purpose pre-trained model. In addition, the artificial intelligence unit 243 may include a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model as a pre-trained model. Small-scale and medium-scale language models are natural language processing models that are trained on less data (and constructed with fewer parameters) compared to large-scale language models.

[0141] The pre-trained models included in the artificial intelligence unit 243 (pre-trained models used in each functional unit) can undergo additional training using methods such as transfer learning and fine-tuning. For example, whenever new data is registered, the artificial intelligence unit 243 may perform additional training and fine-tuning using this new data as training data. This improves the accuracy of the information output from the pre-trained models.

[0142] The trained model included in the artificial intelligence unit 243 may be a trained model (distilled model) obtained by knowledge distillation using the original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as the teacher model, and the student model is trained by adjusting its parameters so that the loss of the student model's output (soft target loss) relative to the teacher model's output (soft target) is small, and that student model becomes the distilled model. Alternatively, the student model may be trained so that the loss of the student model's output (hard target loss) relative to the correct labels (hard target) of the teacher data (combination of input data and output data of the trained model) is small. Compared to the original trained model (teacher model), the distilled model has performance close to that of the trained model, but with fewer parameters and a lower processing load. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0143] For example, the trained model used in each functional unit may be a distilled model trained using combinations of input and output data from a large-scale language model as training data. Alternatively, when the information processing system 1 is introduced, a large-scale language model may be used as the trained model in each functional unit, and once training data from the large-scale language model has been accumulated, the distilled model obtained by knowledge distillation using that training data may be used as the trained model in each functional unit.

[0144] An AI agent (also called an autonomous agent) is a model that, upon input of a goal (objective, purpose, etc.) such as "Teach me about XX" or a task such as "Output XX," breaks down the processes necessary to reach the goal or accomplish the task into subtasks, actions, etc., and performs necessary data collection and analysis, program generation and execution, etc. The AI ​​agent takes the information and instructions input by the user as its goal, autonomously selects and executes tasks and actions according to the goal, outputs information according to the goal, and does not require user intervention (operation input). Furthermore, the AI ​​agent may autonomously plan and execute, evaluate the execution results itself, and autonomously learn in order to aim for goal achievement. For example, the AI ​​agent may autonomously update itself based on the execution results of subtasks (e.g., collected information, results of information analysis, etc.).

[0145] <Display Control Unit 331> The display control unit 331 of the job seeker terminal 3 controls the display unit 34 to display the screen indicated by the screen data transmitted from the server 2.

[0146] <Operation acquisition unit 332> The operation acquisition unit 332 of the job seeker terminal 3 receives operations from the job seeker using the job seeker terminal 3.

[0147] 3. Information Processing Flow This section describes the flow of the information processing method executed by the information processing system 1. As shown below, the information processing method executed by the information processing system 1 comprises each step executed by the information processing system. The program of this embodiment causes the computer to execute each step of the information processing system. The order of processing can be changed as appropriate, multiple processes may be executed simultaneously, and some processes may be omitted.

[0148] 3.1 Overview Figure 5 is a diagram illustrating the overview of the processing performed by the information processing system 1. In this processing, first, the acquisition unit 231 acquires input information about the job seeker (step S001). The input information includes at least the job seeker's activity history information and registration information, and the activity history information includes a history of the job seeker's activities related to job searching. Next, the generation unit 232 generates a plurality of suggestion information based on the input information and the first reference information (step S002). The suggestion information includes headline information and search conditions used for job searching, with the headline information and search conditions being associated, and the first reference information includes at least the correlation between the input information and the suggestion information. Next, the display control unit 233 displays the plurality of headline information included in the plurality of suggested information, and displays to the job seeker at least one of the search conditions associated with the headline information selected by the job seeker from among the plurality of headline information, and the results of the job search using the search conditions (step S003).

[0149] In summary, according to one embodiment, the information processing system comprises at least one processor. The processor includes the following parts by reading a program. The acquisition unit 231 acquires input information about a job seeker. The input information includes at least the job seeker's behavioral history information and registration information, and the behavioral history information includes a history of the job seeker's actions related to job-seeking activities. The generation unit 232 generates a plurality of suggestion information based on the input information and first reference information. The suggestion information includes headline information and search conditions used for job searching, with the headline information and search conditions being associated, and the first reference information includes at least the correlation between the input information and the suggestion information. The display control unit 233 displays a plurality of headline information included in the generated plurality of suggestion information, and displays to the job seeker at least one of the search conditions associated with the headline information selected by the job seeker from among the plurality of headline information, and the results of a job search using the search conditions. According to this embodiment, it is possible to provide technology related to an information processing system that supports the job-seeking activities of job seekers.

[0150] 3.2 Specific Examples The following describes an example of the processing flow performed by the information processing system 1, using Figures 6 to 9. This example of the flow may be included within the scope defined in the overview described above. Note that this information processing may include any exception handling not shown. Exception handling includes interrupting the information processing or omitting each process. The selection or input performed in this information processing may be based on user operation or may be performed automatically without user operation.

[0151] <First Embodiment> The first embodiment shows an example of the information processing flow when performing a series of processing operations on the information processing system 1.

[0152] Figure 6 is an activity diagram showing an example of the information processing flow performed by the information processing system 1. The following explanation will follow each activity in this activity diagram.

[0153] First, the acquisition unit 231 acquires input information about the job seeker (Activity A101). The input information includes at least the job seeker's activity history information and registration information.

[0154] Next, the determination unit 242 determines whether the behavioral history information meets predetermined conditions (Activity A102). The predetermined conditions include that at least one of the following for at least one of the job postings and scouting information within a predetermined period is equal to or greater than a predetermined value: the number of views, the number of applications, and the number of replies. If the determination result is negative (NO), the process returns to Activity A102, and the determination is repeated until the predetermined conditions are met. If the amount or content of the input information does not meet predetermined accuracy conditions, the information processing system 1 may terminate the process without generating or displaying the suggested information, or it may display pre-prepared search conditions or heading information.

[0155] If the judgment result is positive (YES), the generation unit 232 generates multiple suggestion pieces of information based on the input information and the first reference information (activity A103).

[0156] Next, the decision unit 234 determines a priority for each of the generated proposal information based on the input information and the second reference information (activity A104). The second reference information includes at least the correlation between the input information and the priority. The display control unit 233 displays the proposal information according to the priority.

[0157] Next, the job posting calculation unit 235 calculates the number of job postings when a job search is performed using the search conditions contained in each of the generated multiple proposal information (Activity A105). The display control unit 233 may control the display so as not to show the heading information associated with search conditions for which the number of job postings is less than a predetermined number.

[0158] Next, the determination unit 242 determines whether the behavioral history information meets predetermined conditions (Activity A106). The predetermined conditions include that at least one of the following for at least one of the job postings and scouting information within a predetermined period is above a predetermined value: the number of views, the number of applications, and the number of replies. If the determination result is negative (NO), the process returns to Activity A106, and the determination is repeated until the predetermined conditions are met.

[0159] If the judgment result is positive (YES), the display control unit 233 displays the multiple heading information included in the multiple generated proposal information (Activity A107).

[0160] Next, the system accepts the selection of heading information from the job seeker (Activity A108). If the job seeker does not make a selection within a predetermined time, the display control unit 233 may terminate the process by holding the suggested information in the holding unit 241.

[0161] Next, the display control unit 233 displays to the job seeker the search criteria associated with the selected heading information and the search results of the job search using the search criteria side by side (Activity A109).

[0162] Next, the feedback receiving unit 237 receives feedback from job seekers regarding at least one of the headline information and search criteria (Activity A110).

[0163] If there is feedback (YES), the regeneration unit 238 receives the feedback and then regenerates the suggested information (Activity A111). After that, the process returns to Activity A107, and the process from the display of multiple headings onward is repeated.

[0164] On the other hand, if there is no feedback (NO), the holding unit 241 holds multiple pieces of suggestion information (Activity A112).

[0165] Next, the display control unit 233 displays at least one of the search criteria and the results of the job search using the search criteria to the job seeker, and then, when the job seeker returns to the screen where multiple headline information is displayed and redisplays multiple headline information, it redisplays the headline information included in the retained suggestion information (Activity A113).

[0166] With the above steps completed, the processes from activity A101 to activity A113 shown in Figure 6 are finished, and the series of processing flows according to this embodiment are terminated.

[0167] In the above embodiment, in activity A105, the display control unit 233 does not display the proposed information if the number of job postings is small. However, the feedback receiving unit 237 may receive feedback information regarding proposed information where the number of job postings is less than a predetermined number, and the regeneration unit 238 may relax some of the search conditions or replace them with other search conditions to regenerate proposed information where the number of job postings is greater than or equal to the predetermined number. The display control unit 233 may then display proposed information where the number of job postings is greater than or equal to the predetermined number through regeneration by the regeneration unit 238.

[0168] <Second Embodiment> The second embodiment shows another example of the information processing flow when the information processing system 1 performs a series of processes.

[0169] Figure 7 is an activity diagram showing another example of the information processing flow performed by information processing system 1. The following will explain each activity in this activity diagram.

[0170] First, the acquisition unit 231 acquires input information about the job seeker (Activity A201).

[0171] Next, the point axis estimation unit 239 estimates a point axis that indicates the aspects that job seekers consider important in a job posting, based on the input information and the seventh reference information (Activity A202). The seventh reference information includes at least the correlation between the input information and the point axis.

[0172] Next, the display control unit 233 displays the estimated point axis (activity A203).

[0173] Next, the feedback receiving unit 237 receives feedback from job seekers regarding the point axis (Activity A204).

[0174] If there is feedback (YES), after receiving the feedback, the re-estimation unit 240 re-estimates the point axis (Activity A205). Then, the process returns to Activity A203, and the process from the point axis display onward is repeated.

[0175] On the other hand, if there is no feedback (NO), the feedback reception unit 237 accepts the job seeker's selection of points (Activity A206).

[0176] Next, the generation unit 232 generates search conditions based on the point axis, input information, and eighth reference information (activity A207). The eighth reference information includes at least the correlation between the point axis, input information, and search conditions.

[0177] Next, the generation unit 232 generates heading information based on the point axis and the ninth reference information (activity A208). The ninth reference information includes at least the correlation between the point axis and the heading information.

[0178] Next, the display control unit 233 displays the generated heading information (Activity A209).

[0179] Next, the job seeker selects headline information (Activity A210).

[0180] Next, the display control unit 233 displays to the job seeker at least one of the search criteria and the results of the job search using the search criteria (Activity A211).

[0181] With the above steps completed, the processes from activity A201 to activity A211 shown in Figure 7 are finished, and the series of processing flows according to this embodiment are terminated.

[0182] Figure 8 shows screen G1, an example of a screen in which the information processing system 1 displays point axis and heading information to job seeker U1. Screen G1 includes area G11 for displaying point axis and area G12 for displaying heading information. The following describes an example of the configuration of each area. Note that the configuration of screen G1 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate depending on the specifications of the information processing system, the number of proposed information items to be displayed, and the specifications of the job search.

[0183] Area G11 is the area that displays the heading "Conditions you might value" to indicate that this screen is a presentation screen of point axes that show the direction of perspectives that job seekers value. Area G11 includes areas G111 to G113, which display point axes (e.g., "Point Axis 1", "Point Axis 2", "Point Axis 3", etc.). Job seeker U1 can select any of areas G111 to G113 to display suggested information (e.g., heading information and search conditions) based on the selected point axis.

[0184] Furthermore, area G11 may include area G114, which accepts that the offer does not match the job seeker U1's preferences. For example, if job seeker U1 selects area G114, the feedback receiving unit 237 accepts this as feedback indicating that the point axis (or the offered content) does not match their preferences, and may cause the display control unit 233 to display a different point axis or the re-estimation unit 240 to re-estimate the point axis.

[0185] Area G12 includes Area G121, which displays a message indicating that job searches are possible by selecting heading information (for example, "Job searches are possible by selecting headings"). Area G12 includes Areas G122 to G124, which display multiple heading information items (for example, "Heading 1" to "Heading 4"). Each heading information item corresponds to the heading information included in the suggested information and has associated search conditions (search conditions used for job searches).

[0186] When job seeker U1 selects any of the heading information in areas G122 to G124, the information processing system can perform a job search using the search conditions associated with the selected heading information and display the search conditions and / or the results of the job search using those search conditions to job seeker U1. The display control unit 233 may, for example, display a list of job postings as shown in screen G2, or it may display the search conditions or search results on the same screen.

[0187] Furthermore, area G12 may include area G125 for receiving feedback that the information does not match the applicant's preferences. For example, if job seeker U1 selects area G125, the feedback receiving unit 237 may receive this as feedback indicating that the presented heading information (or associated search conditions) does not match the applicant's preferences, and the regeneration unit 238 may regenerate the heading information and search conditions, or the display control unit 233 may display heading information of the next priority.

[0188] It should be noted that the point axis displayed in area G11 and the heading information displayed in area G12 do not necessarily have to be generated together. For example, the point axis and the heading information may be estimated or generated independently. Alternatively, the generation unit 232 may generate one or more heading information corresponding to the estimated point axis, and the display control unit 233 may cause the heading information associated with the point axis displayed in area G11 to be displayed in area G12.

[0189] Figure 9 shows Screen G2, an example of a screen that displays search criteria and the search results of a job search using those criteria. Screen G2 includes an area G21 that displays the search criteria associated with the selected heading information, and an area G22 that displays the search results (hit job information) of a job search using those search criteria. The following describes an example of the configuration of each area. Note that the configuration of Screen G2 is just an example, and the names, arrangement, and presence or absence of items may be changed as appropriate depending on the specifications of the job search service and database, the item structure of the search criteria, etc.

[0190] Area G21 is an area that displays the search conditions associated with the selected heading information (e.g., "Heading A"). Area G21 may also display a heading indicating that this area is a search condition for job postings with "Heading A". Here, the search conditions associated with the heading information may be composed of a combination of multiple search conditions (e.g., search condition S1, search condition S2). For example, it may be composed as a search condition (search condition S1 × search condition S2) formed by combining search condition S1 and search condition S2 with a logical AND. Note that "×" is an example and may broadly mean a combination that includes a logical connective (AND / OR / NOT, etc.) or grouping.

[0191] Area G211 is the area that displays the search conditions corresponding to "keywords," and for example, search condition S1 is displayed. Area G212 is the area that displays the search conditions corresponding to "job type," and for example, search condition S2 is displayed. Area G213 is the area that displays the search conditions corresponding to "work location," and if no search conditions are set, "Not specified" may be displayed as an example. Area G214 is the area that displays the search conditions corresponding to "annual income," and if no search conditions are set, "Not specified" may be displayed as an example.

[0192] Area G22 is the area that displays the search results when a job search is performed using the search criteria displayed in Area G21 (for example, search criteria S1 × search criteria S2). Area G22 may also display a heading (e.g., "Fitted Job Information") to indicate that this area is a list of job information that matches the search criteria. Area G22 includes areas G221 to G224, which display multiple job information (for example, job information 1 to job information 4). In other words, the job information displayed in Area G22 is the search result when searching using search criteria S1 × search criteria S2.

[0193] Search conditions S1 and S2 may be configured to be editable. For example, areas G211 and G212 may each include input fields or candidate selection fields that accept edit input for search conditions S1 and S2, respectively. Areas G211a, G211b, G211c, and G211d (example display: "Add") may be operation areas that accept operation instructions for adding or changing search conditions. When a job seeker makes an operation instruction for such an operation area, the display control unit 233 may display an input field or candidate list for the search conditions, accept the input or selection, and edit (update) search condition S1 or search condition S2.

[0194] The feedback receiving unit 237 accepts feedback from job seekers regarding at least one of the headline information and search conditions, and may accept edits (changes, additions, deletions, etc.) of search conditions S1 and S2 as such feedback. For example, the feedback receiving unit 237 may accept edits to search condition S1 or search condition S2 and record such edits as feedback.

[0195] The regeneration unit 238 may regenerate the suggested information based on the feedback received by the feedback receiving unit 237 (for example, editing of search conditions S1 and S2). Accordingly, the display control unit 233 may redisplay the search results of the job search using the edited search conditions (for example, edited search conditions S1 × search conditions S2) in area G22. This makes it possible to search for jobs starting from the headline information, and to update the search results by adjusting the search conditions according to the job seeker's intentions, thereby improving the efficiency and relevance of job searching.

[0196] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0197] 4. Others In the above embodiment, Server 2 performed various storage and control functions, but instead of Server 2, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 243 may be an external configuration of Server 2. In that case, the external artificial intelligence unit 243 may be provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of Server 2, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to 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 prompt input in the form of text, images, audio, etc., and generates and responds with answers to the prompts.

[0198] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. The information processing method comprises each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0199] The product may be provided in any of the following embodiments.

[0200] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, wherein in the acquisition step, input information relating to a job seeker is acquired, wherein the input information includes at least the job seeker's behavioral history information and registration information, wherein the behavioral history information includes a history of the job seeker's actions relating to job-seeking activities, in the generation step, a plurality of suggested information is generated based on the input information and first reference information, wherein the suggested information includes headline information and search conditions used for job searching, wherein the headline information and the search conditions are associated, and the first reference information includes at least the correlation between the input information and the suggested information, and in the display control step, the plurality of headline information included in the generated plurality of suggested information is displayed, and at least one of the search conditions associated with the headline information selected by the job seeker from the plurality of headline information and the results of a job search using the search conditions is displayed to the job seeker.

[0201] (2) An information processing system as described in (1) above, wherein in the display control step, the information processing system displays to the job seeker the search conditions associated with the selected heading information and the search results of the job search using the search conditions side by side.

[0202] (3) An information processing system as described in (1) or (2) above, wherein the behavioral history information includes at least one of the following: job postings viewed by the job seeker, job postings applied for by the job seeker, scouting information viewed by the job seeker, and scouting information to which the job seeker responded.

[0203] (4) An information processing system as described in (3) above, wherein the display control step displays the plurality of headings when the behavior history information satisfies predetermined conditions, and the predetermined conditions include that at least one of the number of views, applications, and replies for at least one of the job postings and scouting information within a predetermined period is equal to or greater than a predetermined value.

[0204] (5) An information processing system according to any one of (1) to (4) above, wherein the generation step generates the proposal information when the behavioral history information satisfies predetermined conditions, and the predetermined conditions include that at least one of the number of views, applications and replies for at least one of the job postings and scout information within a predetermined period is equal to or greater than a predetermined value.

[0205] (6) An information processing system according to any one of (1) to (5) above, wherein in the decision step, a priority is determined for each of the generated plurality of proposal information based on the input information, the proposal information and the second reference information, where the second reference information includes at least the correlation between the input information, the proposal information and the priority, and in the display control step, the proposal information is displayed according to the priority.

[0206] (7) An information processing system according to any one of (1) to (6) above, wherein in the job number calculation step, the number of job postings is calculated when a job search is performed using the search conditions contained in each of the generated multiple proposal information, and in the display control step, the system controls not to display the heading information associated with the search conditions for which the number of job postings is less than a predetermined number.

[0207] (8) An information processing system according to any one of (1) to (7) above, wherein the behavior history information includes date and time information, and in the generation step, the plurality of suggested information is generated based on at least one of the behavior history information for the most recent period, the difference between the behavior history information for the most recent period and the behavior history information for the past period, and the difference between the registration information and the behavior history information.

[0208] (9) An information processing system according to any one of (1) to (8) above, wherein the behavioral history information includes at least one of the job seeker's job search history, dialogue history with employers, dialogue history with artificial intelligence, and browsing history of search results, and in the generation step, the information processing system generates the plurality of suggested information based on the input information including at least one of the job search history, dialogue history with employers, dialogue history with artificial intelligence, and browsing history of search results, and the first reference information.

[0209] (10) An information processing system according to any one of (1) to (9) above, wherein in a specific step, other job seekers similar to the job seeker are identified based on the input information, and in a generation step, the plurality of proposal information for the job seeker is generated using at least one of the behavioral history information and registration information of the identified other job seekers together with the input information of the job seeker.

[0210] (11) An information processing system according to any one of (1) to (10) above, wherein the generation step generates the heading information based on the input information and the third reference information, wherein the third reference information includes at least the correlation between the input information and the heading information, and generates the search conditions associated with the heading information based on the generated heading information and the fourth reference information, wherein the fourth reference information includes at least the correlation between the heading information and the search conditions.

[0211] (12) An information processing system according to any one of (1) to (11) above, wherein the generation step generates the search conditions based on the input information and the fifth reference information, wherein the fifth reference information includes at least the correlation between the input information and the search conditions, and generates the heading information associated with the search conditions based on the generated search conditions and the sixth reference information, wherein the sixth reference information includes at least the correlation between the search conditions and the heading information.

[0212] (13) An information processing system according to any one of (1) to (12) above, wherein in the feedback receiving step, the system receives feedback from the job seeker regarding at least one of the heading information and the search conditions, and in the regeneration step, after receiving the feedback, the system regenerates the proposed information.

[0213] (14) An information processing system according to any one of (1) to (13) above, wherein in the point axis estimation step, a point axis indicating the perspectives that the job seeker considers important to the job is estimated based on the input information and the seventh reference information, where the seventh reference information includes at least the correlation between the input information and the point axis; in the generation step, the search conditions are generated based on the point axis and the eighth reference information, where the eighth reference information includes at least the correlation between the point axis and the search conditions; and the heading information is generated based on the point axis and the ninth reference information, where the ninth reference information includes at least the correlation between the point axis and the heading information.

[0214] (15) An information processing system as described in (14) above, wherein in the feedback receiving step, the system receives feedback from the job seeker regarding the point axis, and in the re-estimation step, the system re-estimates the point axis after receiving the feedback.

[0215] (16) An information processing system according to any one of (1) to (15) above, wherein in the retention step, the plurality of suggested information is retained, and in the display control step, after displaying at least one of the search conditions and the results of a job search using the search conditions to the job seeker, the headline information included in the retained suggested information is redisplayed when the job seeker returns to the screen displaying the plurality of headline information and redisplays the plurality of headline information.

[0216] (17) An information processing system according to any one of (1) to (16) above, comprising a server having the processor and a terminal that can access the server.

[0217] (18) An information processing method comprising each step performed by the information processing system described in any one of (1) to (16) above.

[0218] (19) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (16) above. Of course, this is not always the case.

[0219] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0220] 1: Information Processing System 2: Server 20: Communications bus 21: Communications Department 22: Storage section 23: Control Unit 231: Acquisition Department 232 :Generation part 233: Display Control Unit 234: Decision Section 235: Job Posting Calculation Department 236: Specific part 237: Feedback Reception Department 238: Regeneration section 239: Point axis estimation unit 240: Re-estimation part 241: Holding part 242: Judgment section 243: Artificial Intelligence Department 3: Job seeker terminal 30: Communications bus 31: Communications Department 32: Storage section 33: Control Unit 331: Display Control Unit 332: Operation acquisition section 34: Display section 35: Input section G1: Screen G11 :Area G111 :Area G114 :Area G12 :Area G121 :Area G122 :Area G125 :Area G2: Screen G21 :Area G211 :Area G211a :Area G211b :Area G211c :Area G211d :Area G212 :Area G213 :Area G214 :Area G22 :Area G221 :Area S1: Search criteria S2: Search criteria U1: Job seeker

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, input information relating to the job seeker is acquired, wherein the input information includes at least the job seeker's behavioral history information and registration information, and the behavioral history information includes a history of the job seeker's actions related to job-seeking activities. In the generation step, Based on the aforementioned input information and the first reference information, multiple proposal information is generated, where, The first reference information described above includes at least a general-purpose learning model, The input information and a first prompt including an instruction to output a plurality of point axes indicating the aspects that the job seeker considers important in a job posting, are input to the general-purpose learning model, causing the general-purpose learning model to output the plurality of point axes. The input information, the plurality of point axes, and a second prompt including an instruction to output a plurality of search conditions for job search corresponding to each of the plurality of point axes, are input to the general-purpose learning model, and the plurality of search conditions are generated by causing the general-purpose learning model to output the plurality of search conditions. The input information, the plurality of point axes, and a third prompt including an instruction to output a plurality of headings corresponding to each of the plurality of point axes, with the input information and the plurality of point axes as input, are input to the general-purpose learning model, and the plurality of headings are generated by causing the general-purpose learning model to output the plurality of headings. Each of the aforementioned multiple pieces of suggested information includes one heading from the aforementioned multiple pieces of heading information and one search condition from the aforementioned multiple search conditions, and the said heading and said search condition are associated with each other. In the display control step, An information processing system that displays the multiple headline information contained in the generated multiple proposal information, and displays to the job seeker at least one of the search conditions corresponding to the point axis corresponding to the headline information selected by the job seeker from among the multiple headline information, and the results of a job search using said search conditions.

2. In the information processing system described in claim 1, The information processing system, in the display control step, displays to the job seeker side by side the search conditions corresponding to the point axis corresponding to the selected heading information and the search results of a job search using those search conditions.

3. In the information processing system described in claim 1, An information processing system in which the behavioral history information includes at least one of the following: job postings viewed by the job seeker, job postings applied for by the job seeker, scouting information viewed by the job seeker, and scouting information to which the job seeker responded.

4. In the information processing system described in claim 3, In the display control step, the plurality of headings are displayed when the behavior history information satisfies predetermined conditions. The aforementioned predetermined conditions include an information processing system in which at least one of the following—the number of views, the number of applications, and the number of replies—for at least one of the job postings and scouting information within a predetermined period is equal to or greater than a predetermined value.

5. In the information processing system described in claim 1, In the generation step, the proposed information is generated when the behavioral history information satisfies predetermined conditions. The aforementioned predetermined conditions include an information processing system in which at least one of the following—the number of views, the number of applications, and the number of replies—for at least one of the job postings and scouting information within a predetermined period is equal to or greater than a predetermined value.

6. In the information processing system described in claim 1, Furthermore, in the decision step, a priority is determined for each of the generated plurality of proposal information based on the input information, the proposal information, and the second reference information, where the second reference information includes at least the correlation between the input information, the proposal information, and the priority. The information processing system, in the display control step, displays the proposed information according to the priority.

7. In the information processing system described in claim 1, Furthermore, in the job number calculation step, the number of job openings is calculated when a job search is performed using the search conditions included in each of the generated multiple proposal information. The information processing system, in the display control step, controls the system to not display the heading information associated with the search condition for which the number of job postings is less than a predetermined number.

8. In the information processing system described in claim 1, The aforementioned behavioral history information includes date and time information. An information processing system that generates the plurality of suggested information in the generation step based on at least one of the following: the behavioral history information for the most recent period, the difference between the behavioral history information for the most recent period and the behavioral history information for past periods, and the difference between the registered information and the behavioral history information.

9. In the information processing system described in claim 1, The aforementioned behavioral history information includes at least one of the following: the job seeker's job search history, the history of conversations with employers, the history of conversations with artificial intelligence, and the history of viewing search results. An information processing system that generates the plurality of suggested pieces of information in the generation step based on the input information, which includes at least one of the job search history, the dialogue history with the recruiter, the dialogue history with the artificial intelligence, and the browsing history of the search results, and the first reference information.

10. In the information processing system described in claim 1, Furthermore, in a specific step, other job seekers similar to the job seeker are identified based on the input information. An information processing system that, in the generation step, uses at least one of the identified behavioral history information and registration information of the other job seeker together with the job seeker's input information to generate the plurality of proposal information for the job seeker.

11. In the information processing system described in claim 1, In the above generation step, The header information is generated based on the input information and the third reference information, wherein the third reference information includes at least the correlation between the input information and the header information. An information processing system that generates search conditions associated with the heading information based on the generated heading information and fourth reference information, wherein the fourth reference information includes at least the correlation between the heading information and the search conditions.

12. In the information processing system described in claim 1, In the above generation step, The search conditions are generated based on the input information and the fifth reference information, wherein the fifth reference information includes at least the correlation between the input information and the search conditions. An information processing system that generates the heading information associated with the search conditions based on the generated search conditions and the sixth reference information, wherein the sixth reference information includes at least the correlation between the search conditions and the heading information.

13. In the information processing system described in claim 1, Furthermore, in the feedback reception step, feedback from the job seeker regarding at least one of the heading information and the search criteria is received. Furthermore, in the regeneration step, the information processing system regenerates the proposed information after receiving the feedback.

14. In the information processing system described in claim 1, Furthermore, in the feedback reception step, feedback from the job seeker regarding the point axis is received. Furthermore, in the re-estimation step, the information processing system re-estimates the point axis after receiving the feedback.

15. In the information processing system described in claim 1, Furthermore, in the retention step, the plurality of proposed information is retained, An information processing system that, in the display control step, displays at least one of the search conditions and the results of a job search using the search conditions to the job seeker, and then, when the job seeker returns to the screen displaying the multiple headline information and displays the multiple headline information again, the system redisplays the headline information included in the retained suggestion information.

16. In the information processing system according to any one of claims 1 to 15, A server having the aforementioned processor, An information processing system comprising a terminal capable of accessing the aforementioned server.

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

18. It is a program, A program for causing a computer to perform each step of the information processing system described in any one of claims 1 to 15.

Images