Information processing system, information processing method, and program

Abstract

To provide an information processing system etc. capable of efficiently matching employers and job seekers. [Solution] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program, in which in a candidate extraction step, at least one candidate to whom the recruiter has already sent a scouting document is extracted based on the job seeker's behavioral history and reference information, where the reference information includes a correlation between the behavioral history and the job seeker's motivation to search for a job, and in a presentation step, the information processing system presents the candidates to the recruiter.

Description

[Technical field]

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

[0002] Patent Document 1 discloses a method for matching companies with job seekers using a scout function. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2013-246453 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for technology that can more efficiently match employers and job seekers.

[0005] In view of the above circumstances, the present invention provides an information processing system etc. capable of efficiently matching employers and job seekers. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program, in which in a candidate extraction step, at least one candidate to whom the recruiter has already sent a scouting document is extracted based on the job seeker's behavioral history and reference information, where the reference information includes a correlation between the behavioral history and the job seeker's motivation to search for a job, and in a presentation step, the information processing system presents the candidates to the recruiter.

[0007] According to this embodiment, the recruiter can approach the job seeker who has previously received a scouting letter, by sending a scouting letter, when the job seeker's motivation to start job-seeking increases. This allows efficient matching between the recruiter and the job seeker. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of the server device 10. FIG. [Diagram 3] FIG. 2 is a block diagram showing the hardware configuration of a recruiter terminal 20 and a job seeker terminal 30. [Figure 4] FIG. 2 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiter terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Diagram 5] 13 is a diagram showing an example of a candidate display screen CD displayed on the recruiter terminal 20. FIG. [Figure 6] 13 is a diagram showing another example of the candidate display screen CD displayed on the recruiter terminal 20. FIG. [Figure 7] 13 is a diagram showing an example of a target list display screen TD displayed on the recruiter terminal 20. FIG. [Figure 8] 1 is an activity diagram showing an example of a flow of information processing (candidate presentation processing) executed by the information processing system 1. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

[0010] Incidentally, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or 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] In addition, in various information processing according to an embodiment, an input and an output according to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of 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 judgment formula such as a regression formula constructed by a statistical method), or may be a trained model that has previously trained the correlation between the input and the output, or may be a large-scale language model that can output a desired result by inputting a prompt.

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

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

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

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

[0016] The information processing system 1 constitutes at least a part of a recruitment and job search system used, for example, by multiple recruiters (a first recruiter U1 and a second recruiter U2) and multiple job seekers (a first job seeker U3 and a second job seeker U4). The information processing system 1 mainly performs tasks such as searching for job seekers by recruiters and sending scouting documents to job seekers. In one embodiment, the information processing system 1 is made up of one or more devices or components. These components will be described below.

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

[0018] <Control unit 11> The control unit 11 performs processing and control of the overall operation related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 can be specifically realized by the control unit 11, which is an example of hardware, and executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have multiple control units 11 for each function. Also, the server device 10 may be configured with a combination of these.

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

[0020] <Communications Division 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

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

[0022] <Employer Terminal 20> 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. The recruiter terminal 20 is an information processing terminal used by the recruiter. Recruiters include organizations such as profit-making corporations (e.g., companies, etc.), non-profit organizations (e.g., cooperatives, incorporated foundations, etc.), and public corporations (e.g., local governments, etc.) or their personnel. Recruiters also include human resource agencies that act as agents of organizations and act as intermediaries between job seekers and organizations. Human resource agencies are also called headhunters, agents, etc.

[0023] 3A, the recruiter terminal 20 comprises a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected within the recruiter terminal 20 via the communication bus 26. Descriptions of the control unit 21, the memory unit 22, and the communication unit 23 will be omitted as they are similar to the descriptions of the respective units in the server device 10.

[0024] <Input section 24> The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 may execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter terminal 20, or may be externally attached. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, and the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, and the like can be adopted instead of a touch panel.

[0025] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the recruiter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, a plasma display, or the like. It is preferable that these display devices are implemented by using different devices depending on the type of recruiter terminal 20.

[0026] <Job Seeker Terminal 30> The job seeker terminal 30 is an information processing terminal used by a job seeker. "Job seekers" include, for example, employed people (people looking to change jobs), prospective new graduates (job seekers), and the like.

[0027] 3B, the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected within the job seeker terminal 30 via the communication bus 36. Descriptions of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are the same as the descriptions of the respective units in the recruiter terminal 20.

[0028] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (at least one processor included in the information processing system 1).

[0029] FIG. 4 is a block diagram showing functions realized by the server device 10 (control unit 11), the recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0030] As shown in Fig. 4A, server device 10 (control unit 11) includes a basic display control unit 111, a candidate extraction unit 112, a presentation unit 113, a reception unit 114, a scout document transmission unit 115, and an artificial intelligence unit 120. As shown in Fig. 4B, recruiter terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in Fig. 4C, job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0031] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the recruiter terminal 20 or the job seeker terminal 30. For example, the basic display control unit 111 displays registration information of job seekers registered in the database, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30 in response to a request from each user (recruiters U1, U2 or job seekers U3, U4).

[0032] The registration information of job seekers registered in the database includes the job seeker's resume, work history, and other profile information. A "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, employment history, desired working conditions, etc., while a "work history" is also called a résumé, and is a document in which a job seeker conveys to an employer his or her work history, experience, skills, qualifications, etc. related to his or her past work. The job seeker registration information may also include conditions such as the job seeker's desired industry and job type.

[0033] <Candidate extraction section 112> The candidate extraction unit 112 is configured to extract at least one candidate to whom the scout document has been resent from among a plurality of job seekers to whom the recruiter has already sent the scout document, based on the job seeker's behavioral history and reference information.

[0034] A "job seeker to whom a scouting document has been sent" (hereinafter referred to as a "specific job seeker") is a job seeker whose registration information is registered in the database and who has been sent at least one scouting document created by a user (employer) using the same account by the scouting document sending unit 115, which will be described later. Here, a "scouting document" may also be called a scout email, an offer email, a job information email, etc., and refers to a document or message sent from a recruiter to a job seeker.

[0035] The "job seeker's behavioral history" is a record of the job seeker's login to the service provided by the information processing system 1 via the job seeker terminal 30, the operations or instructions performed on the service, and the actions received from employers on the service, and is registered in the database.

[0036] The behavioral history may include at least one of actions taken on the job seeker's registered information, actions taken on scouting documents received by the job seeker, and actions taken on job offers. This can improve the accuracy of predicting the job seeker's motivation for job-seeking activities.

[0037] "Actions for registered information" include, for example, registering registered information, updating registered information, and entering or updating specific items of registered information. "Specific items" include, for example, items related to job-seeking motivation. As the behavioral history, the registration date of registered information, the update date, the date of entry into specific items, etc. may be recorded.

[0038] "Actions on scout documents" include opening (confirming) or replying to scout documents sent by the user who is a recruiter, opening or replying to scout documents sent by recruiters other than the user, etc. As the behavioral history, the date or number of times a scout document was opened, the date or number of times a reply was made to a scout document (reply rate), etc. may be recorded.

[0039] "Actions for a job offer" include applying for a job offer, having an interview, searching for or viewing a job offer, etc. As the behavioral history, the date or number of applications for a job offer, the date or number of interviews conducted, the date or number of searches for a job offer, the date or number of views of a job offer, etc. may be recorded.

[0040] In addition to the above-mentioned actions, the behavioral history may also record the last login date and time, login frequency, and the like as login-related actions.

[0041] The behavioral history may include history information for each of multiple different actions taken by the job seeker. The "multiple different actions" may be actions with different targets (e.g., a combination of an action on a scouting document and an action on a job offer) or actions with different action content (e.g., a combination of applying for a job and searching for a job). Examples of "history information" include the date and time of a specific action (e.g., the date of registration of the registration information), the number of times a specific action was performed (e.g., the number of interviews conducted), the frequency of a specific action (e.g., the number of replies to a scouting document in a specific period), etc.

[0042] The reference information is information including a correlation between the behavioral history and the job seeker's motivation to search for a job. The reference information is stored in, for example, the storage unit 12. The reference information is, for example, an estimator constructed so as to be able to input the behavioral history of the job seeker and output the job seeker's motivation to search for a job. The reference information is, for example, an estimator constructed so as to input a plurality of job seekers and their behavioral histories and output at least one candidate who is estimated to have a high motivation to search for a job. Note that "motivation to search for a job" indicates the degree of enthusiasm of the job seeker in job hunting or job change. Also, "motivation to search for a job" may be read as the possibility of the job seeker replying to a scouting document or the possibility of the job seeker being hired, and may indicate the possibility of the job seeker replying to a scouting document or the possibility of the job seeker being hired.

[0043] The reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates a correlation between a feature (e.g., vector data) extracted from the behavioral history of a job seeker and a willingness to search for a job, a likelihood of replying to a scouting letter, or a likelihood of being hired. The correlation included in the reference information can be constructed, for example, by statistically analyzing data that records an actual behavioral history of a job seeker and an indicator indicating a willingness to search for a job, a likelihood of replying to a scouting letter, or a likelihood of being hired.

[0044] When a specific action is accepted from the employer terminal 20 by the acceptance unit 114 described below, the candidate extraction unit 112 may extract candidates based on the behavioral history and reference information for the specific action. A "specific action" is an action designated by the employer, who is the user, from among the actions of a job seeker. In other words, the candidate extraction unit 112 may extract candidates based on the behavioral history for the action set by the employer (for example, a reply to a scout document). The candidate extraction unit 112 may also extract candidates based on the behavioral history of each of a plurality of specific actions.

[0045] The candidate extraction unit 112 extracts candidates by either the first extraction pattern or the second extraction pattern described below using the reference information.

[0046] <First extraction pattern> In the first extraction pattern, the candidate extraction unit 112 calculates an activity score indicating the level of motivation for job-seeking activities of the specific job seeker based on the behavioral history of the specific job seeker and the reference information, and extracts candidates from the specific job seekers based on the activity score. This makes it possible to adjust the candidates to be extracted by changing the activity score threshold. The activity score is a score that indicates the level of motivation for job-seeking activities, the likelihood of replying to a scouting document, or the likelihood of being hired by a recruiting organization.

[0047] The candidate extraction unit 112 calculates the activity scores of a plurality of specific job seekers (typically, all specific job seekers) and determines the specific job seekers whose activity scores exceed a threshold as candidates. The candidate extraction unit 112 may also determine the specific job seekers whose activity scores are within a predetermined range (for example, the top 10) as candidates.

[0048] The candidate extraction unit 112 may input the activity score of a specific job seeker to the judgment model and cause the judgment model to output whether or not the specific job seeker is a candidate (candidate judgment result). The judgment model is a learning model included in the artificial intelligence unit 120 that is trained to be able to input the activity score and output the candidate judgment result. The judgment model is a learning model that has been trained using, for example, the activity score and the corresponding candidate judgment result data as training data.

[0049] The judgment model may be a generative AI including a large-scale language model. In this case, the candidate extraction unit 112 inputs the activity score, inputs a prompt including an instruction to judge the candidate based on the activity score to the judgment model, and causes the judgment model to output the judgment result. The candidate extraction unit 112 may generate a prompt that gives an instruction to the judgment model to judge the candidate from the activity score, and input the prompt to the judgment model. In addition to the candidate's judgment / output instruction and the activity score, the candidate extraction unit 112 may input a prompt into the judgment model in which, for example, one or more activity score samples and one or more corresponding judgment result samples are inserted as examples, samples, or teacher data of input and output pairs. The judgment model judges the candidate from the activity score according to the input prompt.

[0050] In the first extraction pattern, the candidate extraction unit 112 may calculate the activity score using a table that defines a calculation formula and / or a weighting coefficient for the score for each behavioral history of the job seeker, which is included in the reference information. The candidate extraction unit 112 calculates the activity score as, for example, a simple sum of the scores for each behavioral history, a sum of the values ​​obtained by multiplying the scores for each behavioral history by the weighting coefficient, an average value of the scores for each behavioral history, or the like.

[0051] In the first extraction pattern, the reference information may include a score calculation model that is trained to input the behavioral history of a job seeker and output an activity score. In this case, the candidate extraction unit 112 inputs the behavioral history of a specific job seeker to the score calculation model and causes the score calculation model to output an activity score. This makes it possible to calculate the activity score based on behavioral analysis of the job seeker (for example, the association between a specific behavior and a reply to a scouting document derived from the behavioral data of the job seeker) or natural language processing.

[0052] The score calculation model is a learning model included in the artificial intelligence unit 120. The score calculation model is a learning model that is trained using, for example, data on behavioral history and corresponding results indicating willingness to search for a job, possibility of replying to a scouting letter, or possibility of employment by a recruiting organization (for example, whether or not there is willingness to search for a job, whether or not there is a reply to a scouting letter, whether or not there is employment, etc.) as training data. This makes it possible to calculate optimal parameters for predicting willingness to search for a job, possibility of replying to a scouting letter, or possibility of employment based on the behavioral history of the job seeker, and to construct a learning model. In training the score calculation model, for example, the probability of replying to a scouting letter, employment (conclusion of a job offer), etc. is calculated from the behavioral history of the job seeker, and the parameters that are most consistent with the results are searched for, thereby determining the parameters of the model. The activity score is output as a similarity to the feature values ​​of, for example, a job seeker with a high willingness to search for a job, a job seeker who is replying to a scouting letter, or a job seeker who is employed by a recruiting organization. The score calculation model may be trained using behavioral history and corresponding activity score data as training data. In addition, the score calculation model may be trained to calculate probabilities of the job seeker's motivation to search for a job, the likelihood of replying to a scouting letter, the likelihood of being hired, etc., from the job seeker's attributes and behavioral history, using as training data the job seeker's attributes (e.g., age, educational background, current organization, current industry, current job type, current position, current annual income, possessed skills, possessed qualifications, organizations experienced (years of tenure at each organization), industries experienced (years of experience in each industry), job types experienced (years of experience in each job type), desired industry, desired job type, desired annual income, desired work location, etc.) in addition to the behavioral history.

[0053] The score calculation model may be a generation AI including a large-scale language model. In this case, the candidate extraction unit 112 inputs the behavioral history of the job seeker, inputs a prompt including an instruction to calculate an activity score based on the behavioral history to the score calculation model, and causes the score calculation model to output the activity score. The candidate extraction unit 112 may generate a prompt that gives an instruction to the score calculation model to calculate an activity score from the behavioral history, and inputs the prompt to the score calculation model. The prompt generated by the candidate extraction unit 112 may include an example of the activity score to be output. In addition to the instruction to calculate and output the activity score and the behavioral history, the candidate extraction unit 112 may input a prompt into the score calculation model in which, for example, one or more samples of the behavioral history and one or more samples of the corresponding activity score are inserted as examples, samples, or teacher data of pairs of input and output. The score calculation model calculates the activity score from the behavioral history according to the input prompt. In the score calculation model, parameters calculated, tuned, etc. by learning configure the correlation of the reference information.

[0054] The score calculation model and the judgment model may be a common generation AI (large-scale language model). In this case, the candidate extraction unit 112 may input a prompt to the generation AI to calculate the activity score, output the activity score, and further input a prompt to the generation AI to judge the candidates using the activity score.

[0055] The score calculation model may include a first calculation model that is trained to be able to input history information for each of a plurality of actions and output an evaluation value of the history information, and a second calculation model that calculates an activity score from the evaluation value of each of the plurality of pieces of history information. As a result, the activity score is calculated based on the evaluation of each of the plurality of actions, making it possible to estimate the job seeker's motivation to search for a job from multiple angles.

[0056] The first calculation model is a learning model included in the artificial intelligence unit 120. The first calculation model is, for example, a learning model that learns using historical information and data of the corresponding evaluation value as teacher data. Note that the first calculation model may receive one piece of historical information as input and output an evaluation value of the historical information, or may receive multiple pieces of historical information as input and simultaneously output evaluation values ​​for each of the multiple pieces of historical information.

[0057] The first calculation model may be a generation AI including a large-scale language model. In this case, the candidate extraction unit 112 receives history information as an input, inputs a prompt including an instruction to calculate an evaluation value based on the history information to the first calculation model, and causes the first calculation model to output the evaluation value. The candidate extraction unit 112 may generate a prompt that gives an instruction to the first calculation model to calculate an evaluation value from the history information, and inputs the prompt to the first calculation model. In addition to the instruction to calculate and output the evaluation value and the history information, the candidate extraction unit 112 may input a prompt into which, for example, one or more samples of history information and one or more samples of the corresponding evaluation value are inserted as examples, samples, or teacher data of input and output pairs to the first calculation model. The first calculation model calculates an evaluation value from the history information according to the input prompt.

[0058] The second calculation model is, for example, a learning model included in the artificial intelligence unit 120. For example, the second calculation model is a learning model that learns a plurality of evaluation values ​​(a group of evaluation values) and data of the activity scores corresponding to the evaluation values ​​as teacher data.

[0059] The second calculation model may be a generation AI including a large-scale language model. In this case, the candidate extraction unit 112 inputs the evaluation value group, inputs a prompt including an instruction to calculate an activity score based on the evaluation value group to the second calculation model, and causes the second calculation model to output the activity score. The candidate extraction unit 112 may generate a prompt that gives an instruction to the second calculation model to calculate an activity score from the evaluation value group, and input the prompt to the second calculation model. In addition to the instruction to calculate and output the activity score and the evaluation value group, the candidate extraction unit 112 may input a prompt into the second calculation model in which, for example, one or more samples of the evaluation value group and one or more samples of the corresponding activity score are inserted as examples, samples, or teacher data of input and output pairs. The second calculation model calculates the activity score from the evaluation value group according to the input prompt.

[0060] The second calculation model may be a calculation model (algorithm) that calculates an activity score based on a plurality of evaluation values ​​output by the first calculation model and weightings set for each type of history information (i.e., type or content of action). For example, the second calculation model may calculate the activity score as the sum of the values ​​obtained by multiplying the plurality of evaluation values ​​by their respective weighting coefficients. The weighting coefficient is set higher, for example, for an action that has a higher correlation with a motivation for job-seeking activity.

[0061] <Second extraction pattern> In the second extraction pattern, the candidate extraction unit 112 directly extracts candidates from among a plurality of specific job seekers (typically, all specific job seekers) based on the behavioral history and reference information of the plurality of specific job seekers.

[0062] In the second extraction pattern, the reference information may include a candidate extraction model that has been trained to be able to input the behavioral history of multiple job seekers and output candidates from among these job seekers. In this case, the candidate extraction unit 112 inputs the behavioral history of multiple job seekers (specific job seekers) to which scout documents have been sent, into the candidate extraction model, and causes the candidate extraction model to output candidates. This allows candidates to be directly extracted based on their behavioral history, thereby reducing the load of information processing for extracting candidates.

[0063] The candidate extraction model is a learning model included in the artificial intelligence unit 120. The candidate extraction model is a learning model that learns, for example, like the score calculation model, using the behavioral history of the job seeker and the corresponding data on the results indicating the willingness to search for a job, the possibility of replying to a scouting document, or the possibility of being employed by the recruiting organization as training data. For example, based on the input behavioral history, the candidate extraction model calculates an internal score that indicates the similarity between the feature values ​​of a job seeker with a high willingness to search for a job, a job seeker who is replying to a scouting document, or a job seeker who is employed by the recruiting organization, and further determines whether the job seeker whose behavioral history is input is a candidate or not based on the magnitude of this internal score. Note that the score calculation model may be one that learns using the behavioral history and the corresponding data on whether or not the job seeker is a candidate as training data. In addition, a list including information on multiple specific job seekers other than the behavioral history (for example, an ID, name, etc. that identifies a specific job seeker) may be input to the candidate extraction model. In addition, like the score calculation model, the candidate extraction model may be trained to use the job seeker's attributes as training data in addition to the behavioral history, and to calculate probabilities (internal scores) of the job seeker's motivation to search for a job, likelihood of replying to a scouting letter, likelihood of being hired, etc., from the job seeker's attributes and behavioral history.

[0064] The candidate extraction model may be a generation AI including a large-scale language model. In this case, the candidate extraction unit 112 inputs the behavioral history of the job seeker, calculates a score indicating the level of motivation for job-seeking activities, the likelihood of replying to a scouting document, or the likelihood of being employed by a recruiting organization based on the behavioral history, and further inputs a prompt including an instruction to determine whether or not the job seeker is a candidate based on the score to the candidate extraction model, and causes the candidate extraction model to output the determination result. The candidate extraction unit 112 may generate a prompt that gives an instruction to the candidate extraction model to determine the candidate based on the behavioral history (score), and inputs the prompt to the candidate extraction model. In addition to the candidate's determination / output instruction and behavioral history, the candidate extraction unit 112 may input to the candidate extraction model a prompt in which, for example, one or more samples of the behavioral history and one or more samples of the corresponding candidate's determination result and / or one or more samples of the score are inserted as examples, samples, or teacher data of input and output pairs. The candidate extraction model determines whether or not the job seeker is a candidate based on the behavioral history according to the input prompt. In the candidate extraction model, parameters calculated, tuned, etc. through learning constitute correlations of reference information.

[0065] The candidate extraction unit 112 extracts candidates (i.e., updates the candidates) at predetermined intervals using either the first extraction pattern or the second extraction pattern. An example of the "predetermined interval" is once a day. In other words, the candidate extraction unit 112 may extract candidates on a daily basis. In addition, the candidate extraction unit 112 extracts candidates for each employer (i.e., for each employer's account).

[0066] Note that if the user, who is the employer, resends a scout document to a job seeker who has been extracted as a candidate, the job seeker will remain a candidate until the candidate extraction unit 112 re-extracts candidates. Furthermore, even after the scout document is resent, the candidate extraction unit 112 may still extract the job seeker as a candidate. To prevent the job seeker from being presented as a candidate, the user, who is the employer, needs to set the sending date of the scout document using the filtering conditions described below. Furthermore, the job seeker may be removed from the list by the presentation unit 113 described below.

[0067] On the other hand, the candidate extraction unit 112 may use the date and time of sending the scout document or the number of times of sending the scout document as a criterion for determining candidates. For example, the candidate extraction unit 112 may be configured to exclude from candidates (i.e., not extract as candidates) job seekers who have sent a scout document less than a predetermined value in the period from the date and time of the last scout document to the present, or job seekers who have sent a scout document a predetermined value or more.

[0068] <Presentation part 113> The presentation unit 113 is configured to present the candidates extracted by the candidate extraction unit 112 to the employer. Specifically, the presentation unit 113 causes information of at least one candidate (e.g., part of the registered information) to be displayed on the employer terminal 20. The presentation unit 113 may present all of the multiple candidates extracted by the candidate extraction unit 112, or may present only a part of them.

[0069] The presentation unit 113 may preferentially display, among multiple candidates, candidates to whom a scout document with a specific job posting attached has been sent on the recruiter terminal 20. Here, a "specific job posting" is a job posting that is the same as or similar to a job posting attached to a scout document sent by a recruiter within a specified period of time. This allows the user (the recruiter) to approach the job seeker who sent the scout document again at a stage when the job seeker's motivation to start job-seeking increases, regarding the job posting that the user (the recruiter) attached to the scout document within a specified period of time.

[0070] The "predetermined period" is, for example, a period within a certain range from the current time, such as within one month from the current time, or within one week from the current time.

[0071] The similarity of two job advertisements is determined by the difference in the features of each of the two job advertisements (for example, the distance between feature vectors obtained by vectorizing words or sentences). For example, job advertisements whose feature difference is less than a predetermined threshold (for example, cosine similarity is equal to or greater than a threshold) are determined to be similar to each other.

[0072] The presentation unit 113 may display multiple candidates on the recruiter terminal 20 in descending order of activity score. This makes it easier for the user (the recruiter) to approach job seekers who are highly motivated to search for a job. The presentation unit 113 may display information (e.g., a numerical value, an icon, etc.) representing the candidate's activity score on the recruiter terminal 20 together with the candidate's information.

[0073] The presentation unit 113 may receive input of narrowing-down conditions regarding the date and time of sending or the number of times of sending of a scout document to a candidate from the recruiter (recruiter terminal 20), and display candidates who satisfy the input narrowing-down conditions on the recruiter terminal 20. This allows the user (recruiter) to exclude a candidate to whom a scout document has just been sent (or resent) from approach candidates.

[0074] For example, the presentation unit 113 accepts input of the date and time (period) when the scout document was last sent or the number of times the scout document was sent (e.g., a designated value, an upper limit value, a lower limit value, etc.) as the narrowing-down condition. The presentation unit 113 may also accept input of narrowing-down conditions regarding the attributes of the candidate (e.g., application history, screening history, etc.).

[0075] Furthermore, when the user, i.e., the employer, resends a scouting document to a presented candidate, the presentation unit 113 may not present the candidate (remove the candidate from the list). In this case, the presentation unit 113 may re-present the candidate, for example, when there is no reply from the candidate even after a predetermined period of time has elapsed since the resending of the scouting document.

[0076] The presentation unit 113 may display the number of candidates included in each target list on the employer terminal 20. Here, a target list is a list in which an employer registers arbitrary job seekers. This allows the user (employer) to preferentially check the contents of a target list with a large number of candidates among his / her own target lists.

[0077] A target list (which may also be called a bookmark list, a favorites list, etc.) is a list in which any job seekers whom a recruiter is considering as candidates for scouting are registered. A recruiter can create and register multiple target lists. The presentation unit 113, for example, causes the recruiter terminal 20 to display a list of target lists including information such as the number of candidates.

[0078] The presentation unit 113 may display, for each job posting, candidates extracted from the job seekers who sent the scout document to which the job posting is attached, or the number of candidates, on the recruiter terminal 20. This allows the user (recruiter) to know which of his / her job postings have a large number of candidates. The presentation unit 113, for example, displays, on the recruiter terminal 20, a list of job postings including information on the number of candidates.

[0079] FIG. 5 is a diagram showing an example of the candidate display screen CD displayed on the recruiter terminal 20. The candidate display screen CD includes a job posting list JL. The job posting list JL displays a list of information about job postings for which scout documents have been sent to candidates extracted by the candidate extraction unit 112. The job posting information includes, for example, the name of the available position and the number of eligible candidates. In the job posting list JL, the job postings are displayed, for example, in order of most recent scout sending date (the sending date of the last scout document sent is closest to the current time).

[0080] When the employer selects any job posting from the job posting list JL, a list of candidates for that job posting is displayed on the employer terminal 20. When a candidate is further selected from this list, an operation screen for creating a scouting document for that candidate, adding that candidate to a target list, etc. is displayed on the employer terminal 20. In addition, the candidate display screen CD in Fig. 5 is displayed as the initial screen (home screen) or a so-called My Page screen when the employer logs in, for example, on the management screen where the employer manages job postings, searches for job seekers, creates and sends scouting documents, etc.

[0081] Fig. 6 is a diagram showing another example of the candidate display screen CD displayed on the recruiter terminal 20. The candidate display screen CD in Fig. 6 includes a condition setting area CA and a candidate list CL.

[0082] The condition setting area CA is an area for setting conditions for narrowing down the candidates to be displayed in the candidate list CL. The condition setting area CA includes a target selection area TA, a sending date selection area DA, a sending count selection area NA, and an evaluation selection area EA.

[0083] The target selection area TA displays objects (tabs) that accept the selection of targets to be displayed in the candidate list CL. The example in Fig. 6 shows a state in which candidates extracted by the candidate extraction unit 112 are selected as targets (the "Sent" tab is selected). When the "All" tab is selected, all job seekers to whom scouting documents can be sent, not limited to candidates, are displayed in the candidate list CL.

[0084] The sending date selection area DA displays an object (date input field) that accepts input of the sending date period of the last sent scouting document in order to narrow down the candidates to be displayed in the candidate list CL. In the example of Fig. 6, only candidates whose scouting documents were sent between "June 1, 2023 and June 30, 2024" entered in the sending date selection area DA are displayed in the candidate list CL.

[0085] The transmission count selection area NA displays an object (pull-down menu) that accepts input of the number of times the scout document has been sent in order to narrow down the candidates to be displayed in the candidate list CL. In the example of Fig. 6, only candidates whose scout document has been sent "once or more" as input in the transmission date selection area DA are displayed in the candidate list CL.

[0086] The evaluation selection area EA displays objects (check boxes) that accept the selection of job seeker attributes to narrow down the candidates to be displayed in the candidate list CL. In the example of Fig. 6, the evaluation value given to the job seeker is displayed as the attribute condition of the job seeker to be displayed as a candidate in the candidate list CL. Therefore, only candidates who have any of the attributes checked in the evaluation selection area EA are displayed in the candidate list CL.

[0087] In the candidate list CL of FIG. 6, the candidate information displayed includes, for example, basic information about the candidate, information about scouting documents sent in the past, and the total number of times scouting documents have been sent. The candidate's basic information includes, for example, age, annual income, organization, department, and job title. The scouting document information includes, for example, the sending date and time, subject, sending account, and the like for each scouting document. The "time to resume activities" is determined, for example, by the login date and time, the update date and time of registered information, the date and time of viewing a job posting, the date and time of replying to a scouting document, and the like.

[0088] 6 also includes an action selection area AA and a display order selection area SA. The action selection area AA displays objects that accept actions such as selecting candidates all at once, sending scout documents to the selected candidates all at once, deleting the selected candidates from the candidate list CL, deleting the selected candidates from the target list, etc.

[0089] The display order selection area SA displays an object (pull-down menu) that accepts the selection of the display order of the candidates in the candidate list CL. The display order options include, for example, the order of activity resumption date, the order of the last scout document transmission date and time, the order of the number of times the scout document was transmitted, the order of activity motivation (activity score), etc.

[0090] 7 is a diagram showing an example of a target list display screen TD displayed on the recruiter terminal 20. The target list display screen TD includes a message MG and a target list TL.

[0091] The message MG includes a sentence notifying the employer that at least one of the target lists registered with the employer includes the candidate extracted by the candidate extraction unit 112. The message MG may display the number of target lists that include the candidate. Note that if there is no target list that includes the candidate, the message MG is not displayed.

[0092] The target list list TL displays a list of information on the target lists created by the recruiter. The target list information includes, for example, the target list name, the number of candidates, the date on which the job seeker was last added (the date on which the target list was last edited), the name of the target position, etc. When the recruiter selects any target list in the target list list TL, a list of job seekers (including candidates) registered in that target list is displayed on the recruiter terminal 20.

[0093] <Reception Department 114> The reception unit 114 receives input of specific actions from among the actions of job seekers from the employer (employer terminal 20) for the candidate extraction unit 112 to extract candidates. This allows candidates to be extracted based on the actions of job seekers that the user (employer) values, thereby improving the accuracy of matching with job seekers to be re-approached.

[0094] For example, the reception unit 114 displays a selection of multiple actions (candidates for specific actions) for the job seeker on the employer terminal 20, and accepts the action selected on the employer terminal 20 as the specific action. The behavioral history for the specific action accepted by the reception unit 114 is input by the candidate extraction unit 112 to a candidate extraction model, a score calculation model, etc.

[0095] <Scout Document Transmission Unit 115> The scouting document sending unit 115 is configured to send a scouting document created by a recruiter to the job seeker terminal 30. The scouting document may be created, for example, by text input at the recruiter terminal 20, or by generation using a learning model based on information such as a job advertisement.

[0096] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0097] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with a learning model such as a transformer including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), or a language model such as a recurrent neural network (RNN), and may include a generative AI including a large-scale language model. The large-scale language model is a type of generative AI and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. In addition, the artificial intelligence unit 120 may include any machine learning model, deep learning model, artificial intelligence model, etc.

[0098] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0099] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data is composed of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

[0100] The artificial intelligence unit 120 may be a general-purpose natural language processing learning model such as a large language model (LLM) that has learned a huge amount of data as an artificial intelligence. The LLM is a learning model that has learned a large amount of large data (for example, (i) web content on the Internet, or (ii) data stored in a specified database) composed of text data and the like in advance, and can execute various language processing tasks by giving tasks. According to a given prompt, it can perform a wide range of natural language processing tasks such as grasping sentence patterns and contexts, answering questions, and generating sentences. Such a general-purpose learning model includes a language model that can handle various tasks without fine tuning by One-shot Learning, Few-shot Learning, etc. In addition, the general-purpose learning model may be configured to be able to handle various tasks by Zero-shot Learning as well. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

[0101] The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as the score calculation model, the candidate extraction model, etc.) can undergo additional learning as transfer learning or fine tuning. For example, each time a new record of the behavioral history of a job seeker is generated, the artificial intelligence unit 120 may perform additional learning and fine tuning using the new training data. This improves the accuracy of the information output from the learning models.

[0102] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using an original learning model. In knowledge distillation, a learned model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted so that the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model is reduced, thereby learning the student model, and the student model becomes a distilled model. In addition, the student model may be learned so that the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model) is reduced. Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while having performance close to that of the learning model. Therefore, by using the distilled model, the cost of the information processing system 1 can be reduced.

[0103] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the learning model used in each functional unit, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the learning model used in each functional unit.

[0104] <Display section> The display unit 211 of the recruiter terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen indicated by the screen data transmitted from the server device 10.

[0105] <Operation acquisition section> The operation acquisition unit 212 of the recruiting party terminal 20 accepts operations by a recruiter who uses the recruiting party terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by a job seeker who uses the job seeker terminal 30.

[0106] 3. Information processing method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

[0107] This information processing includes a candidate extraction step and a presentation step. In the candidate extraction step, at least one candidate to whom the scout document is to be resent is extracted from among a plurality of job seekers to whom the recruiter has already sent the scout document, based on the job seeker's behavioral history and reference information. In the presentation step, the candidate is presented to the recruiter.

[0108] 8 is an activity diagram showing an example of the flow of information processing (candidate presentation processing) executed by the information processing system 1. The information processing will be described below along with each activity of this activity diagram.

[0109] The candidate presentation process is executed at a predetermined timing (for example, at a fixed time each day). The server device 10 extracts candidates for each employer from among job seekers based on the information in the database (activity A101). After extracting the candidates, the server device 10 outputs the candidates to the employer terminal 20 (activity A102). As a result, the candidates are displayed (presented) on the employer terminal 20 (activity A103).

[0110] The recruiter selects a job seeker for whom to create a scouting document from among the candidates displayed on the recruiter terminal 20 (activity A104). Furthermore, the recruiter creates a scouting document using the recruiter terminal 20, or instructs the server device 10 to create a scouting document (activity A105). The server device 10 sends the created scouting document to the specified candidate (job seeker) (activity A106).

[0111] 4. Effect The operation of this embodiment can be summarized as follows. That is, when a job seeker to whom a scouting document has been sent in the past becomes more motivated to search for a job, the recruiter can approach the job seeker by sending a scouting document, etc. This allows efficient matching between the recruiter and the job seeker.

[0112] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and can be modified as appropriate without departing from the technical concept of the invention.

[0113] 5.Other In the above embodiment, the server device 10 performs various storage and control, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 120, which is an external configuration, is provided by, for example, an artificial intelligence service server, and is configured to receive input from each functional unit of the server device 10, receive a request to execute an artificial intelligence service, and return an instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides a service using a language model as a learning model, or may be a server that executes a language processing task using a language model. The artificial intelligence service server may be constructed by LLM. The artificial intelligence service server receives input of a prompt by text, image, voice, etc., and generates and responds to the prompt.

[0114] The server device 10 does not necessarily have to include the reception unit 114. For example, the server device 10 may extract candidates based only on the behavior history of predetermined actions.

[0115] The aspect of the present embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0116] It may be provided in any of the following ways:

[0117] (1) An information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: in a candidate extraction step, at least one candidate to whom a scouting document has already been sent by a recruiter is extracted based on the job seeker's behavioral history and reference information, the reference information including a correlation between the behavioral history and the job seeker's motivation to search for a job; and in a presentation step, the candidate is presented to the recruiter.

[0118] (2) In the information processing system described in (1) above, the reference information includes a candidate extraction model that has been trained to be able to input the behavioral histories of a plurality of job seekers and output the candidates extracted from among these job seekers, and in the candidate extraction step, the behavioral histories of a plurality of job seekers to which scout documents have been sent are input into the candidate extraction model, and the candidate extraction model is caused to output the candidates.

[0119] (3) In the information processing system described in (1) above, in the candidate extraction step, an activity score indicating the degree of motivation for job search activities is calculated based on the behavioral history and the reference information, and the candidates are extracted based on the activity score.

[0120] (4) In the information processing system described in (3) above, the reference information includes a score calculation model that has been trained to use the behavioral history as input and output the activity score, and in the candidate extraction step, the behavioral history is input into the score calculation model and the score calculation model is caused to output the activity score.

[0121] (5) In the information processing system described in (4) above, the behavioral history includes history information for each of a plurality of different actions taken by the job seeker, and the score calculation model includes: a first calculation model that is trained to be able to input the history information and output an evaluation value of the history information; and a second calculation model that calculates the activity score from the evaluation value of each of the plurality of pieces of history information.

[0122] (6) In the information processing system described in any one of (1) to (5) above, the behavioral history includes at least one of actions taken on the job seeker's registration information, actions taken on a scouting document received by the job seeker, and actions taken on a job offer.

[0123] (7) In the information processing system described in any one of (1) to (6) above, in the presentation step, among the multiple candidates, the candidate to whom a scouting document with a specific job posting attached has been sent is preferentially displayed, and the specific job posting is a job posting that is identical or similar to a job posting attached to a scouting document sent by the employer during a specified period.

[0124] (8) In the information processing system described above in (3), in the presenting step, the multiple candidates are displayed in descending order of the activity score.

[0125] (9) In the information processing system described in any one of (1) to (8) above, in the presentation step, an information processing system receives input of filtering conditions from the employer regarding the date and time of sending a scouting document to the candidate or the number of times it is sent, and displays the candidates who satisfy the filtering conditions among the candidates.

[0126] (10) In the information processing system described in any one of (1) to (9) above, in the presentation step, the number of candidates included in a target list is displayed for each target list, and the target list is a list in which the employer has registered any job seeker.

[0127] (11) In the information processing system described in any one of (1) to (10) above, the processor is configured to further execute the following steps: in the reception step, an input of a specific action among the actions of job seekers for extracting the candidates is received from the employer; and in the candidate extraction step, the candidate is extracted based on the behavioral history of the specific action and the reference information.

[0128] (12) An information processing method comprising steps executed by an information processing system according to any one of (1) to (11) above.

[0129] (13) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (11) above. Of course, this is not the case.

[0130] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0131] 1: Information processing system 2: Communication lines 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter terminal 21: Control section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job Seeker Terminal 31: Control section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 111: Basic display control unit 112: Candidate extraction department 113: Presentation part 114: Reception 115: Scout Document Transmission Department 120: Artificial Intelligence Department 211:Display section 212: Operation acquisition section 311: Display section 312: Operation acquisition section AA : Action selection area CA: Condition setting area CD: Candidate display screen CL: Candidate list DA: Sending date selection area EA: Evaluation Selection Area JL: Job listings MG: Message NA: Transmission count selection area SA: Display order selection area TA: Target selection area TD: Target list display screen TL: Target list

Claims

1. An information processing system, At least one processor; The processor is configured to execute the following steps by reading the program: In the candidate extraction step, the employer extracts at least one candidate to whom the scout document is to be resent from among a plurality of job seekers to whom the scout document has already been sent, based on the action history and reference information of the job seeker; Here, the reference information includes a correlation between the behavioral history and the job seeker's motivation to search for a job, In the presentation step, the information processing system presents the candidate or the number of candidates to the employer for each job posting attached to the scout document.

2. 2. The information processing system according to claim 1, the reference information includes a candidate extraction model that is trained so as to be able to input the behavioral histories of a plurality of job seekers and output the candidate extracted from among these job seekers; An information processing system, in the candidate extraction step, inputting the behavioral histories of a plurality of job seekers to whom scout documents have been sent into the candidate extraction model, and causing the candidate extraction model to output the candidates.

3. 2. The information processing system according to claim 1, The information processing system, in the candidate extraction step, calculates an activity score indicating the degree of motivation for job search based on the behavioral history and the reference information, and extracts the candidates based on the activity score.

4. 4. The information processing system according to claim 3, the reference information includes a score calculation model that is trained to be able to input the behavioral history and output the activity score, An information processing system, in the candidate extraction step, inputting the behavioral history into the score calculation model and causing the score calculation model to output the activity score.

5. 5. The information processing system according to claim 4, The behavioral history includes history information for each of a plurality of different actions taken by the job seeker, The score calculation model is a first calculation model that is trained so as to be able to receive the history information as an input and output an evaluation value of the history information; a second calculation model that calculates the activity score from the evaluation value of each of the plurality of pieces of history information; An information processing system comprising:

6. 2. The information processing system according to claim 1, In the information processing system, the behavioral history includes at least one of actions taken on the job seeker's registered information, actions taken on a scouting document received by the job seeker, and actions taken on a job offer.

7. 2. The information processing system according to claim 1, In the presenting step, the candidate to whom the scout document to which the specific job posting is attached is sent is preferentially displayed among the plurality of candidates; Here, the specific job posting is a job posting that is identical or similar to a job posting attached to a scouting document sent by the employer during a specified period, in an information processing system.

8. 4. The information processing system according to claim 3, In the presenting step, the information processing system displays the multiple candidates in descending order of the activity score.

9. 2. The information processing system according to claim 1, In the presentation step, an information processing system accepts input of filtering conditions from the employer regarding the date and time or number of times a scouting document is sent to the candidate, and displays the candidates who meet the filtering conditions.

10. 2. The information processing system according to claim 1, In the presenting step, the number of the candidates included in each target list is displayed, In this information processing system, the target list is a list in which the recruiter registers any job seekers.

11. An information processing system, comprising: At least one processor; The processor is configured to execute the following steps by reading the program: In the reception step, the employer receives input of a specific action for extracting candidates to whom the scout document is to be resent from among the actions of job seekers, In the candidate extraction step, at least one candidate is extracted from among a plurality of job seekers to whom the recruiter has sent a scout document, based on the job seeker's behavioral history and reference information regarding the specific action; Here, the reference information includes a correlation between the behavioral history and the job seeker's motivation to search for a job, In the presenting step, the information processing system presents the candidate to the recruiting party.

12. 1. An information processing method, comprising: An information processing method comprising the steps executed by the information processing system according to any one of claims 1 to 11.

13. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 11.

Images