Information processing method, program, and information processing device

Abstract

To provide an information processing method, and the like, for properly presenting various types of advice regarding actions to a job seeker according to a result of an aptitude test of the job seeker.SOLUTION: A computer acquires a result of an aptitude test that a job seeker took. The computer receives a question regarding actions of the job seeker. The computer generates advice regarding actions of the job seeker using a language model, based on the acquired test result and the received question.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] In the field of human resource recruitment, whether or not to hire a job seeker is determined based on the results of an aptitude test taken by the job seeker. Patent Document 1 discloses a technology for setting the hiring standards required by a company based on the results of aptitude tests taken by the company's current employees. By using the technology disclosed in Patent Document 1, the hiring standards required by each company can be easily set based on the characteristics of current employees, and by determining whether or not to hire a job seeker according to the hiring standards set in this way, it is possible to realize the hiring of the human resources required by each company. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-158296 Summary of the Invention [Problem to be solved by the invention]

[0004] Recruiters often conduct job interviews and other similar activities based on the results of aptitude tests of job seekers. It is important to consider the personality of each job seeker during the interview; treating a job seeker improperly can discourage the job seeker from joining the company, potentially resulting in missed opportunities to hire talented personnel. Therefore, it is necessary to conduct recruitment activities (e.g., interviews) after understanding the personality traits of job seekers revealed by the aptitude test results. Recruiters may request detailed explanations of the personality traits of job seekers and important points to note when conducting recruitment activities. However, while the technology disclosed in Patent Document 1 can determine whether each job seeker meets appropriately set recruitment criteria, it is difficult to meet the above-mentioned demands.

[0005] In one aspect, the present invention aims to provide an information processing method etc. that can appropriately present various advice on how to deal with a job seeker according to the results of the job seeker's aptitude test. [Means for solving the problem]

[0006] In one aspect of the information processing method, a computer acquires test results of an aptitude test taken by a job seeker, accepts questions regarding the job seeker's response, and generates advice regarding the job seeker's response using a language model based on the acquired test results and the accepted questions. [Effects of the Invention]

[0007] In one aspect, various pieces of advice regarding how to deal with a job seeker can be appropriately presented depending on the results of the job seeker's aptitude test. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of the configuration of an information processing system. [Figure 2] FIG. 2 is a block diagram showing an example configuration of a server and a recruiter terminal. [Figure 3] FIG. 2 is an explanatory diagram showing an example of the record layout of an aptitude test DB and a company DB. [Figure 4] FIG. 2 is an explanatory diagram illustrating an example of a record layout of a job seeker DB. [Figure 5] FIG. 10 is an explanatory diagram illustrating an example of a prompt creation table. [Figure 6] FIG. 10 is an explanatory diagram illustrating an example of a prompt creation table. [Figure 7] FIG. 10 is an explanatory diagram illustrating an example of a prompt creation table. [Figure 8] 10 is a flowchart illustrating an example of a procedure for providing advice. [Figure 9] FIG. 10 is an explanatory diagram showing an example of a screen. [Figure 10] FIG. 10 is an explanatory diagram showing an example of a screen. [Figure 11] FIG. 10 is an explanatory diagram showing an example of a screen. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing method, a program, and an information processing device according to the present disclosure will be described in detail with reference to the drawings showing embodiments thereof.

[0010] FIG. 1 is an explanatory diagram showing an example of the configuration of an information processing system. In this embodiment, an information processing system is described that determines the suitability of a job seeker (job hunter) hoping to be employed by a target company based on the results of an aptitude test (personality test) taken by the job seeker, and provides advice and commentary (explanation) for dealing with the job seeker (recruitment activities). The information processing system of this embodiment generates various pieces of advice and commentary (explanation) using a general-purpose large-scale language model (LLM). In this embodiment, an example is described in which Japanese is used as the language input to the large-scale language model, but other languages ​​may also be used. Job seekers include students (new graduates), recent graduates, mid-career applicants, etc.

[0011] The information processing system of this embodiment includes an information processing device 1, a terminal 2 of a hiring company employee (hereinafter referred to as the hiring company terminal 2), and a job seeker terminal 3 (hereinafter referred to as the job seeker terminal 3), and the devices 1, 2, and 3 are communicatively connected via a network N. Multiple hiring company terminals 2 and multiple job seeker terminals 3 are provided. The network N may be the Internet or a public telephone network, or a local area network (LAN) established within the facility where the information processing system is installed. The information processing device 1 is a computer capable of various information processing and information transmission / reception, such as a server computer or a personal computer. In this embodiment, the information processing device 1 is a server computer, and for simplicity, will be referred to as the server 1 below. The server 1 may be a server managed by the hiring company or a server managed by a company supporting the hiring activity. The hiring company terminal 2 and job seeker terminal 3 are computers capable of various information processing and information transmission / reception, such as a personal computer, tablet terminal, or smartphone.

[0012] In the information processing system of this embodiment, server 1 transmits information on an aptitude test (personality test) to job seeker terminal 3, collects answers to the aptitude test via job seeker terminal 3, determines personality traits based on the collected answers, and generates personality test results. Server 1 also determines the aptitude (compatibility with each company) for each job seeker based on the personality test results, and presents the determination results (aptitude test results) to the recruiter via recruiter terminal 2. In this case, server 1 receives various questions from recruiter terminal 2 and performs a process of transmitting answers (advice, etc.) to the received questions to recruiter terminal 2.

[0013] FIG. 2 is a block diagram showing an example configuration of the server 1 and the recruiter terminal 2. The server 1 includes a control unit 11, a main memory unit 12, a communication unit 13, and an auxiliary memory unit 14. The control unit 11 has one or more processors, such as a central processing unit (CPU), a microprocessing unit (MPU), a graphics processing unit (GPU), a tensor processing unit (TPU), or an AI chip (AI semiconductor), and executes various information processing and control processes to be performed by the server 1. If the control unit 11 includes multiple processors, each process may be executed by a different processor. The main memory unit 12 is a temporary storage area, such as a static random access memory (SRAM), a dynamic random access memory (DRAM), or a flash memory, and temporarily stores data generated when the control unit 11 executes calculations. The communication unit 13 is a communication module for performing communication-related processes and transmits and receives information to and from other devices via the network N.

[0014] The auxiliary storage unit 14 is a non-volatile storage area such as a large-capacity memory, a hard disk, or an SSD (Solid State Drive), and stores a program P1 (program product) and other data required for the control unit 11 to execute processing. The server 1 also has web server functionality, and the auxiliary storage unit 14 stores a recruitment support site S that displays company information for each company, administers aptitude tests to job seekers seeking employment from each company, and provides the aptitude test results to recruiters and other parties. The auxiliary storage unit 14 also stores a language model M. The language model M is a general-purpose large-scale language model constructed by pre-training using a large set of sentences, etc. The language model M is trained to, when input data including, for example, text data written in a natural language is input, perform calculations based on the input data to generate output data corresponding to the content of the input data, and output the generated output data. The language model M can be configured using algorithms such as GPT (Generative Pre-trained Transformer)-3, GPT-3.5, GPT-4, etc., or may be configured by combining multiple algorithms. The language model M is not limited to the transformer-based model described above. It is anticipated that the language model M will be used as a program module constituting artificial intelligence software. The language model M performs a predetermined calculation on input data and outputs the calculation result. The auxiliary storage unit 14 stores data such as coefficients and thresholds of functions that define this calculation as the language model M. Instead of storing the language model M in the auxiliary storage unit 14, the server 1 may access a language processing server that stores the language model M and read it out. The auxiliary storage unit 14 also stores an aptitude test DB 141, a company DB 142, a job seeker DB 143, and a prompt creation table 144, which will be described later. The auxiliary storage unit 14 may be an external storage device connected to the server 1, and any or all of the DBs 141 to 143 and the prompt creation table 144 may be stored in another server.

[0015] In this embodiment, the server 1 may be a multi-computer consisting of multiple computers, or may be a virtual machine virtually constructed by software within a single device. The server 1 may also be a local server installed in a facility where the server 1 (information processing system) is installed, or a cloud server connected to the facility via a network N. The server 1 is not limited to the above configuration and may include, for example, an input unit for accepting operation inputs and a display unit for displaying images. The server 1 may also include a reading unit for reading a non-transitory computer-readable recording medium 1a and read the program P1, etc., from the recording medium 1a. The program P1 may be located on a single computer or at a single site, or may be distributed across multiple sites and executed in a distributed manner on multiple computers interconnected via the network N.

[0016] The recruiting officer terminal 2 includes a control unit 21, a main memory unit 22, a communication unit 23, a display unit 24, an input unit 25, and an auxiliary memory unit 26. The control unit 21 has one or more processors such as a CPU, and executes various information processing to be performed by the recruiting officer terminal 2 by reading and executing a program P2 stored in the auxiliary memory unit 26. The main memory unit 22 is a temporary storage area such as RAM, and temporarily stores data generated when the control unit 21 executes calculation processing. The communication unit 23 is a communication module for performing communication-related processing, and sends and receives information to and from other devices via the network N.

[0017] The display unit 24 is a liquid crystal display, an organic EL display, or the like, and displays various information in accordance with instructions from the control unit 21. The input unit 25 is an operation interface such as a keyboard or a mouse, and receives operation inputs from a user (recruiter), and sends a control signal according to the operation content to the control unit 21. The display unit 24 and the input unit 25 may be a touch panel configured as an integrated unit.

[0018] The auxiliary storage unit 26 is a non-volatile storage area such as a large-capacity memory, hard disk, or SSD, and stores the program P2 and other data necessary for the control unit 21 to execute processing. The auxiliary storage unit 26 also stores a web browser AP for accessing a web server. The recruiter terminal 2 may be equipped with a reading unit that reads the non-transitory computer-readable recording medium 2a, and may read the program P2 and other data from the recording medium 2a and store them in the auxiliary storage unit 26. The job seeker terminal 3 has the same configuration as the recruiter terminal 2, so a description thereof will be omitted.

[0019] FIG. 3 is an explanatory diagram showing an example of the record layout of the aptitude test DB 141 and the company DB 142. The aptitude test DB 141 is a database that stores information on questions (questionnaires) used in aptitude tests in this system. The aptitude test DB 141 includes a question ID column, an item column, and a question content column. The question ID column stores identification information (question ID) for identifying each question used in the aptitude test. The item column stores the item names of items related to personality traits identified by the aptitude test (test items and evaluation scales tested in the aptitude test). In this embodiment, the items related to personality traits have major items and minor items. The major items include interpersonal relationship characteristics, leadership characteristics, ability to perceive situations, ability to adapt to environments, resilience, activity, achievement motivation, mental health, etc., and each major item includes multiple minor items. For example, the sub-items of interpersonal relationship characteristics include listening tendency, assertive tendency, and relationship maintenance tendency; the sub-items of leadership characteristics include problem-solving orientation and emotional consideration orientation; and the sub-items of situational tolerance include unselfishness, optimism, independence, compromise ability, and criticality. The question content column stores the content of questions to be asked to job seekers in association with each sub-item. Each question is designed to analyze the respondent's personality and extract characteristic personality traits, and one or more questions are prepared for each item. The aptitude test DB141 is not limited to the configuration shown in FIG. 3; the number and types of items (major items and minor items) and the number and content of questions corresponding to each item can be set arbitrarily.

[0020] The company DB 142 is a database that stores information about companies that use the aptitude tests in this system. The company DB 142 includes a company ID column, a company name column, a company information column, and a hiring criteria column. The company ID column stores identification information (company ID) for identifying each company. The company name column and the company information column store the company name and information about the company in association with the company ID. The information about the company may include information describing the company, the company's homepage URL (Uniform Resource Locator), information about the company's recruitment, etc. The hiring criteria column stores information indicating the characteristics (personality, traits) of the personnel that the company desires to hire. It stores multiple hiring criteria for assessing the aptitude (personality) of job seekers, as well as items (scales) used for evaluation (judgment) based on each hiring criterion and the minimum score (judgment criteria, judgment score). In the example of Figure 3, three types of hiring criteria are used: "organizational culture," "stability," and "job type / team," and evaluation is performed for each hiring criterion using three personality trait items. That is, in this embodiment, the job seeker's suitability for the company is determined (evaluated) based on the job seeker's scores for each item, including how well the job seeker will fit into the company's organizational culture (corporate culture), the stability of performance if the job seeker is hired, and how well the job seeker will fit into each job type or team within the company. Note that these hiring criteria are just an example, and other criteria may be used. The hiring criteria may be two or less types, or four or more types, and the number of items used for evaluation based on each hiring criterion is not limited to three. The company DB 142 is not limited to the configuration shown in FIG. 3. For example, the hiring criteria for "job type / team" may be registered for each job type or team.

[0021] The server 1 of this embodiment generates an aptitude test screen based on the contents stored in the aptitude test DB 141, transmits it to the job seeker terminal 3, and acquires (collects) from the job seeker terminal 3 answers to each question entered via the aptitude test screen. The aptitude test of this embodiment is configured to allow answers to questions from five options, for example, "1: Doesn't apply at all," "2: Doesn't apply very much," "3: Can't say," "4: Somewhat applies," and "5: Apply very much," and the server 1 acquires the question ID and answer content (any of 1 to 5) of each question from the job seeker terminal 3. When the server 1 acquires the answers to the aptitude test from the job seeker terminal 3, the server 1 calculates a score for each item related to the job seeker's personality traits (each test item in the aptitude test) based on the answers to each question. The score for each item in the aptitude test can be calculated using a score assigned according to the answer to each question and a deviation value calculated based on the test results (scores, average score, etc.) of test takers who have previously taken the aptitude test. In other words, the score for each item indicates a standard deviation that indicates how high the job seeker's test results are compared to all other test takers, and the stronger the personality trait for each item, the higher the score. Note that the score for each item in the trait test may be the score assigned according to the answer to each question.

[0022] After calculating the score for each item, the server 1 identifies items (hereinafter referred to as "personalities") that indicate the job seeker's particularly unique personality traits based on the score for each item. For example, multiple personalities are set in advance, and for each personality, the score for each item and a combination of the item scores (e.g., a combination of high and low scores for each item) are set. The server 1 then identifies a compatible (closer) personality based on the job seeker's score for each item and the item scores and combinations set for each personality. At this time, each item may be weighted, and the personality may be identified based on the weighted score for each item. The combination of items used to identify each personality may be a combination of items of personality traits that tend to fluctuate in conjunction with each other. The server 1 also identifies the job seeker's type based on the score for each item and the identified personality. Multiple job seeker types are set in advance, and for each type, the score for each item and the degree of each personality are set. The server 1 then identifies a compatible (closer) type based on the job seeker's score for each item and personality. In this way, the server 1 identifies the score, individuality, and type of each item as the personality traits of the job seeker through the aptitude test.

[0023] After identifying the personality traits of the job seeker as described above, the server 1 determines the job seeker's aptitude (compatibility with the company, discrepancy with the company's hiring standards) for the company to which the job seeker applied (the company for which the job seeker took the aptitude test) based on the identified personality traits and the company's hiring standards registered in the company DB 142. Specifically, the server 1 determines the job seeker's aptitude for each of the multiple hiring standards of the company to which the job seeker applied registered in the company DB 142, and calculates an aptitude score indicating the degree of aptitude for each hiring standard. When calculating an aptitude score for one hiring standard (e.g., organizational culture), the server 1 compares the job seeker's score with the judgment standards (judgment scores) set by the company for each item used to evaluate the hiring standard, and calculates an aptitude score for that hiring standard out of 10 points. For example, the server 1 assigns 10 / (number of items) points to each of the multiple items used in the evaluation scale of the hiring criteria, calculates a higher aptitude score for each item the closer the company's judgment criteria are to the job seeker's score, and calculates the total of the aptitude scores for each item as the aptitude score for the hiring criteria. In other words, the job seeker's aptitude for the company is expressed by a higher aptitude score the more similar the job seeker's personality traits are to the company's hiring criteria.

[0024] The server 1 also calculates an aptitude score (total score) for the job seeker's overall evaluation by calculating the average value of the aptitude scores for each hiring criterion or a weighted average value by weighting each hiring criterion based on the aptitude scores calculated for each hiring criterion. The server 1 pre-sets thresholds for classifying the overall score into multiple rank levels, and when calculating the overall score, identifies the rank corresponding to the overall score based on the threshold level. Through the above-described process, the server 1 acquires the aptitude scores for each of the multiple hiring criteria, the overall score, and the rank as the job seeker's aptitude (compatibility) with the company. Note that the number of ranks for the overall evaluation can be any number, for example, six levels: S, A, B, C, D, and E. As described above, the server 1 can acquire the job seeker's personality traits (personality test results) and aptitude for the company to which the job seeker is applying (aptitude test results) through the aptitude test. The acquired personality test results and aptitude test results are stored in the job seeker DB 143 in association with the job seeker ID assigned to each job seeker.

[0025] FIG. 4 is an explanatory diagram showing an example of a record layout of the job seeker DB 143. The job seeker DB 143 is a database that stores information about job seekers seeking employment by companies that use this system. The job seeker DB 143 includes a job seeker ID column, a name column, a job seeker information column, a personality test result column, and an aptitude test result column. The job seeker ID column stores identification information (job seeker ID) for identifying each job seeker. The name column and the job seeker information column store personal information such as the job seeker's name and email address, in association with the job seeker ID. The personality test result column stores, in association with the job seeker ID, the scores for each item that represent personality traits obtained from the aptitude test taken by the job seeker, as well as personality (particularly items that indicate unique personality traits) and type. The aptitude test result column stores, in association with the job seeker ID, the aptitude test results for companies obtained from the aptitude test taken by the job seeker. The aptitude test results include the company ID of the company that was the subject of the aptitude test, an aptitude score for each company's hiring criteria (e.g., organizational culture, stability, job type / team), and a rank and overall score as a comprehensive assessment result. The job seeker DB 143 is not limited to the configuration shown in FIG. 4, and each piece of information may be divided into multiple DBs and registered, or some of the information may be registered in a DB on another server. For example, the personality test results or aptitude test results of a job seeker may be associated with the job seeker ID, etc., and stored on another server that manages information about job seekers. The job seeker DB 143 may also store, as aptitude test results, aptitude scores for each item used in evaluating each hiring criterion, calculated when calculating the aptitude score for each hiring criterion of the applying company.

[0026] As described above, the server 1 stores the personality test results and aptitude test results obtained through the aptitude test taken by each job seeker in the job seeker DB 143. In this embodiment, the server 1 performs a process of providing the aptitude test results of each job seeker to the recruiter. Specifically, the server 1 generates an aptitude test result screen displaying the aptitude test results of the job seeker and transmits it to the recruiter terminal 2. When the recruiter terminal 2 receives the aptitude test result screen from the server 1, it displays it on the display unit 24, allowing the recruiter to check the aptitude test results of each job seeker. On the aptitude test result screen, the recruiter can ask questions about the personality and aptitude of the job seeker, questions about how to interact with the job seeker, etc., and the server 1 can provide answers (advice) to the questions. In this process, the server 1 performs a process of generating answers (advice) to the received questions using the language model M. The language model M may be a general-purpose large-scale language model that is used as is, or may be one that has been fine-tuned using information on the personality traits of the respondent (job seeker) that can be determined from the results of a personality test, or information on the respondent's aptitude state that can be determined from the results of an aptitude test. The language model M may also be fine-tuned using company information about the companies that use this system. The company information may include information that explains the company, such as the company's homepage and brochures, and information about the company's recruitment activities. The language model M may be fine-tuned on the server 1 or on another learning device. The language model M that has been fine-tuned on another learning device is downloaded from the learning device to the server 1 via the network N or the recording medium 1a, for example, and stored in the auxiliary storage unit 14.

[0027] The following describes prompts that the server 1 inputs into the language model M when generating an answer (advice) to a question using the language model M. FIGS. 5 to 7 are explanatory diagrams showing an example of the prompt creation table 144. The prompt creation table 144 includes a prompt template shown in FIG. 5, a type description table, a personality description table, and a uniqueness description table shown in FIG. 6, and a strengths / weakness description table and a command statement table for personality items shown in FIG. 7. When generating answers (advice) to questions about a job seeker and questions about how to deal with (treat) the job seeker, the server 1 of this embodiment creates a prompt that includes not only the content of the question but also information based on the personality test results and information based on the aptitude test results of the job seeker, and inputs this into the language model M. The server 1 generates the prompt using the prompt creation table 144.

[0028] The prompt template shown in FIG. 5 includes sentences related to the premise (background) for generating advice (answers to questions), sentences related to the job seeker's personality based on the results of a personality test, sentences related to the job seeker's compatibility with the company to which the job seeker is applying (suitability for the company) based on the results of an aptitude test, and sentences related to commands. The sentences related to the premise are pre-defined sentences. The sentences related to the personality include sentences related to the overall tendency, sentences related to distinctive features, and sentences related to particularly unique features. The sentences related to the overall tendency use explanatory sentences corresponding to the type identified in the results of the personality test. The sentences corresponding to the type are identified from the type explanatory sentence table shown in FIG. 6. The type explanatory sentence table stores explanatory sentences for each type, corresponding to each type indicating personality traits. For the sentences related to distinctive features, for example, a predetermined number of distinctive items (five in the example shown in FIG. 5) are identified based on the scores of each personality trait item included in the personality test results, and explanatory sentences corresponding to the scores of the identified items are used. The sentences related to distinctive features are identified from the personality explanatory sentence table shown in FIG. 6. The personality description table stores, in association with each personality trait item, a description for when the score (standard deviation) for each item is less than 50 and a description for when the score is 50 or greater. Furthermore, characteristic items can be, for example, items with a large difference between the score of each item and 50. In this case, a predetermined number of items are identified in descending order of the difference between the score and 50. For descriptions relating to particular unique features, descriptions corresponding to the personality identified as a result of the personality test are used. The descriptions corresponding to the personality are identified from the personality description table shown in FIG. 6. In association with each personality trait, the personality description table stores descriptions for when the score for each personality (particularly an item representing a unique personality trait) is greater than or equal to a predetermined value and a description for when the score is less than the predetermined value. The predetermined value can be any value. The description relating to compatibility with the company includes descriptions relating to the points where the candidate matches with the company (company) and those where the candidate does not match with the company. The sentences regarding the matching points are explanatory sentences that explain whether the aptitude scores calculated based on the company's judgment criteria for each item used to evaluate a hiring criterion with a high aptitude score among the hiring criteria previously set by the company are above or below a specified value.On the other hand, the sentences regarding mismatches are explanatory sentences for hiring criteria with low aptitude scores, based on the company's judgment criteria, for each item used to evaluate the hiring criteria. The sentences for matching and mismatching items are identified from the personality item strength / weakness explanation table shown in Figure 7. The personality item strength / weakness explanation table stores explanations for high and low aptitude scores for each item used to evaluate hiring criteria that match the company's hiring criteria (hiring criteria with higher aptitude scores), as well as explanations for high and low aptitude scores for each item used to evaluate hiring criteria that do not match the company's hiring criteria (hiring criteria with low aptitude scores). The threshold for determining whether an aptitude score for each item is high or low can be set to any value. The sentences regarding commands are command sentences corresponding to questions entered via the aptitude test result screen. The command sentences are identified from the command sentence table shown in Fig. 7. In this embodiment, a plurality of options (questions) are prepared in advance for the questions to be accepted via the aptitude test result screen, and the command sentence table stores command sentences in association with the question items and the options for each item. As described above, a prompt to be input to the language model M is created by inserting into the prompt template sentences related to personality, sentences related to compatibility with the company the applicant is applying to, and command sentences corresponding to the questions to be answered.

[0029] The prompt template is not limited to the example shown in FIG. 5. For example, the prompt may include a message for controlling the output result from the language model M. For example, a message such as "Please output in approximately 300 characters" may be included in the premise sentence or command sentence in FIG. 5. Furthermore, the prompt may include a message (constraint) for specifying the output format, as in the command sentence in the command sentence table in FIG. 7. This makes it possible to control the output result from the language model M and guide the language model M to output desired content. The prompt may also include a rank and overall score included in the aptitude test results. Furthermore, the prompt may be configured to include at least one of a sentence about overall tendencies, a sentence about distinctive features, and a sentence about particularly unique features as a sentence about personality.

[0030] The following describes the process in the information processing system of this embodiment in which the server 1 generates and presents answers (advice) to questions received via the aptitude test result screen. FIG. 8 is a flowchart illustrating an example of the advice presentation process, and FIGS. 9 to 11 are explanatory diagrams showing example screens. In the following process, the server 1 transmits the aptitude test result screen to the recruiting staff terminal 2, which then receives operations from the recruiter via the aptitude test result screen displayed on the recruiting staff terminal 2 and transmits data corresponding to the received operations to the server 1. The server 1 performs processing based on the data received from the recruiting staff terminal 2 and transmits the processing results to the recruiting staff terminal 2. The recruiting staff terminal 2 then updates the aptitude test result screen based on the received processing results. This allows the recruiter to view the aptitude test result screen using the recruiting staff terminal 2 and receive advice on various questions via the aptitude test result screen. In this embodiment, data is transmitted and received (exchanged) between the server 1 and the recruiting staff terminal 2. However, for simplicity, FIG. 8 does not illustrate the data transmission and reception between the server 1 and the recruiting staff terminal 2.

[0031] In the information processing system of this embodiment, whenever a recruiter desires to know the results of a job seeker's aptitude test, the recruiter accesses the server 1 (recruitment support site S) using a predetermined URL and requests the results of the aptitude test for a job seeker. When the recruiter terminal 2 requests the results of the job seeker's aptitude test, the control unit 11 of the server 1 generates an aptitude test result screen displaying the requested aptitude test results for the job seeker and displays it on the recruiter terminal 2 (S11). Specifically, the control unit 11 transmits the aptitude test result screen to the recruiter terminal 2, and the control unit 21 of the recruiter terminal 2 displays the received aptitude test result screen on the display unit 24. FIG. 9 shows an example of the aptitude test result screen. The screen of FIG. 9 displays, as the aptitude test results for one job seeker, a rank and overall score representing the recruiter's suitability for the company (enterprise), an aptitude score for the hiring criteria set by the company, and a degree of suitability (suitable, somewhat suitable, inappropriate) for each item used to evaluate each hiring criterion relative to the evaluation criteria (evaluation score). The information displayed on the aptitude test result screen can be read from the job seeker DB 143.

[0032] The screen in FIG. 9 is provided with a "Personality Test Interpretation" button (operation button, hereinafter referred to as the "Mikiwame AI" button A1) for asking questions about the displayed aptitude test results and how to respond to the job seeker (recruitment activities such as interviews). When a recruiter wishes to receive the personality test results from the aptitude test, an explanation about the aptitude test results, or advice on how to interact with a job seeker, the recruiter operates the "Mikiwame AI" button A1 via the input unit 25 of the recruiter terminal 2. The control unit 11 of the server 1 determines whether the "Mikiwame AI" button A1 has been operated (S12). If it determines that the button has not been operated (S12: NO), the control unit 11 waits while performing other processing until the button A1 is operated. When the "Mikiwame AI" button A1 is operated, the control unit 21 of the recruiter terminal 2 notifies the server 1 that the button A1 has been operated, so that the control unit 11 of the server 1 can recognize that the "Mikiwame AI" button A1 has been operated.

[0033] When the control unit 11 determines that the "Mikiwame AI" button A1 has been operated (S12: YES), it displays a question menu field A2 on the aptitude test result screen currently displayed on the recruiting staff terminal 2 (S13), as shown in FIG. 10. The question menu field A2 displays a plurality of questions (question menu) related to each of a plurality of pre-prepared items, and the display area of ​​each question is a button that allows the recruiting staff member to select one of the questions (options). In the question menu field A2, the recruiting staff member selects the button for the question (option) that is closest to the question the recruiting staff member wishes to ask. The control unit 11 accepts the input of a question (selection of an option) via the question menu currently displayed on the recruiting staff terminal 2 (S14). In the example of FIG. 10, the option (question) for "Strengths (positive aspects) and Weaknesses (negative aspects)" in the "Basic interpretation of personality test" section has been selected.

[0034] When the control unit 11 receives a question, it reads out the personality test results and aptitude test results of the job seeker displayed on the aptitude test result screen from the job seeker DB 143 (S15). Based on the read personality test results and aptitude test results, the control unit 11 then creates a sentence to be used as a prompt for instructing the language model M to generate an answer (advice) to the question. Specifically, the control unit 11 creates a sentence related to the personality of the job seeker from the personality test results (S16). As described above, the control unit 11 retrieves an explanatory sentence corresponding to the type included in the personality test results from the type explanatory sentence table to create a sentence related to the overall tendency. Furthermore, the control unit 11 identifies a predetermined number of characteristic items based on the scores of each item (personality trait) included in the personality test results, and retrieves explanatory sentences corresponding to the scores for the identified items from the personality explanatory sentence table to create a sentence related to the characteristic features. Furthermore, the control unit 11 retrieves explanatory sentences corresponding to the personality included in the personality test results from the personality explanatory sentence table to create a sentence related to the particularly unique features.

[0035] The control unit 11 creates a statement regarding the job seeker's compatibility with the hiring manager's company (enterprise) based on the aptitude test results (S17). Here, the control unit 11 identifies hiring criteria with high aptitude scores based on the aptitude scores for the hiring criteria of the applying company included in the aptitude test results, and for each item used to evaluate these hiring criteria, reads an explanation from the strengths / weakness explanation table for personality items according to whether the aptitude score is above a predetermined value, and sets this as the statement for the matching item. The control unit 11 also identifies hiring criteria with low aptitude scores based on the aptitude scores for the hiring criteria of the applying company, and reads an explanation from the strengths / weakness explanation table for each item used to evaluate these hiring criteria according to whether the aptitude score is above a predetermined value, and sets this as the statement for the mismatched item.

[0036] The control unit 11 uses the sentences created in steps S16 and S17 to create a prompt corresponding to the question received in step S14 (S18). Here, the control unit 11 obtains a statement corresponding to the selected question from the statement table, and creates a prompt by inserting the statement related to personality created in step S16, the statement related to compatibility with the company created in step S17, and the statement obtained from the statement table into the prompt template shown in Fig. 5. Note that the prompt is not limited to a configuration including the above-mentioned sentences. For example, the prompt may be configured not to include a sentence related to how the candidate matches the company if there is no hiring criterion whose aptitude score for each hiring criterion is equal to or greater than a predetermined value, or may be configured not to include a sentence related to how the candidate does not match the company if there is no hiring criterion whose aptitude score for each hiring criterion is less than a predetermined value.

[0037] The control unit 11 inputs the created prompt into the language model M and acquires output information according to the content of the prompt generated and output by the language model M (S19). Then, based on the acquired output information from the language model M, the control unit 11 displays an answer (advice) to the question received in step S14 in the question menu field A2 currently displayed on the recruiter terminal 2, as shown in FIG. 11A (S20). For example, the control unit 11 acquires advice written in natural language from the language model M and displays the acquired advice in the question menu field A2. In the example of FIG. 10, the question "Strengths (positive aspects) and weaknesses (negative aspects)" is selected. As a result, the question menu field A2 in FIG. 11A displays the content related to the strengths and weaknesses of the job seeker and their explanations. By referring to the advice displayed in the question menu field A2 and understanding the personality traits of the job seeker, the recruiter can conduct recruitment activities such as interviews, thereby realizing the recruitment of excellent personnel. The control unit 11 may be configured to display the advice generated using the language model M in the question menu field A2, or may be configured to display it in a display field separate from the question menu field A2.

[0038] The question menu field A2 is provided with a message input field A3, and if the recruiter has any questions about the advice they viewed, they input a further question (message) into the input field A3. The control unit 21 of the recruiter terminal 2 accepts a message input into the input field A3 in the question menu field A2 via the input unit 25 and transmits the accepted message to the server 1, whereupon the control unit 11 of the server 1 accepts the message. The control unit 11 determines whether the message has been accepted (S21). If it determines that the message has been accepted (S21: YES), the control unit 11 returns to step S18 and creates a prompt corresponding to the accepted message (additional question) (S18). For example, the control unit 11 adds the output information acquired from the language model M in step S19 or the answer information displayed in the question menu field A2 in step S20, and the accepted message to the prompt created in the most recent step S18, to create a new prompt. In addition, the control unit 11 is not limited to a configuration in which a new prompt is created from the prompt created in the most recent step S18, but may create a new prompt that includes the sentence created in steps S16 to S17, the previous question and its answer, and a new question.

[0039] The control unit 11 then performs steps S19 and S20 using the newly created prompt. When the question "Are there any points I should be careful about regarding my weaknesses?" is entered in the input field A3 on the screen of FIG. 11A, the answer to the entered question is displayed as shown in the question menu field A2 of FIG. 11B. By entering a question in the input field A3, the recruiter can obtain questions about the job seeker's personality traits and aptitude test results, questions about recruitment activities for the job seeker, and advice on points to be careful about. Therefore, by conducting recruitment activities in accordance with the advice presented via the question menu field A2, the recruiter can realize smooth interviews and is expected to lead to the hiring of excellent personnel. If the control unit 11 determines that a message has not been received via the input field A3 in the question menu field A2 (S21: NO), the control unit 11 terminates the process.

[0040] Through the above-described processing, in this embodiment, the personality test results of the job seeker and the aptitude test results for the company are provided to the hiring manager of the company. At that time, the hiring manager can ask questions about any unclear points and receive advice on the job seeker's personality traits and how to conduct hiring activities. This supports the hiring manager in properly understanding (interpreting) the content of the personality test results and aptitude test results, enabling the hiring manager to take more appropriate actions during hiring activities. In this embodiment, multiple questions are prepared in advance, and questions and advice can be received in chatbot format, so the hiring manager can easily find out what he or she wants to know by receiving advice verbalized by the language model M.

[0041] Furthermore, in this embodiment, advice is presented that takes into account not only the job seeker's personality traits but also the suitability for each company (compatibility with each company, discrepancy with each company's hiring standards) determined based on the personality traits. This allows each company to propose optimal precautions and actions for each job seeker, thereby supporting recruiters. Recruiters can conduct recruitment activities taking into consideration not only the job seeker's personality traits but also their compatibility with their company. As a result, the workload of recruiters can be reduced, recruitment activities such as interviews can be carried out smoothly, and the acceptance rate for job offers can be improved. This is expected to increase opportunities to hire talented personnel, reduce recruitment mismatches, and curb early turnover rates.

[0042] In the above-described embodiment, a configuration has been described in which the aptitude (compatibility) of a job seeker (job hunter) hoping to be employed by a target company is determined based on the results of an aptitude test taken by the job seeker, and the determination result is presented to the hiring manager. However, the test takers of the aptitude test are not limited to job seekers. For example, a configuration may be adopted in which the aptitude of an employee already employed by the company is determined based on the results of an aptitude test taken by the employee, and the determination result is presented to a supervisor or the like. In this case, it becomes possible to present to the supervisor or the like precautions and advice when dealing with the employee, taking into account the employee's aptitude for the company.

[0043] Independent and dependent claims may be combined with each other in any and all combinations, regardless of the reference format. Furthermore, while the claims may be written in a format in which a claim references two or more other claims (multiple claim format), this is not a limitation. Multiple claims that reference at least one other multiple claim (multiple multiple claim format) may also be written.

[0044] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0045] 1. Server (information processing device) 11 Control section 12 Main memory 13 Communications Department 14 Auxiliary storage 2. Recruiter terminal 21 Control Unit 22 Main memory 23 Communications Department 24 Display section 25 Input section 26 Auxiliary storage M language model

Claims

1. Obtaining test results including scores for each of a plurality of test items in an aptitude test taken by a job seeker, Accepting questions about the job seeker when conducting recruitment activities for the job seeker; Identifying, from the plurality of inspection items, inspection items whose scores for each inspection item match the evaluation criteria set for each company and inspection items whose scores do not match the evaluation criteria, creating a prompt that instructs the generation of advice for conducting recruitment activities for the job seeker based on the scores for the identified matched and unmatched test items and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. An information processing method in which processing is performed by a computer.

2. A method for obtaining test results of an aptitude test taken by a job seeker, the test results including scores for each of a plurality of test items in the aptitude test; Accepting questions about the job seeker when conducting recruitment activities for the job seeker; creating a sentence corresponding to the score for each of the plurality of test items; creating a prompt that instructs the job seeker to generate advice for recruiting based on the sentences created for each test item and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. An information processing method in which processing is performed by a computer.

3. A method for obtaining test results of an aptitude test taken by a job seeker, the test results including scores for each of a plurality of test items in the aptitude test; Accepting questions about the job seeker when conducting recruitment activities for the job seeker; a memory unit stores a sentence corresponding to the score of each of the plurality of test items; A sentence corresponding to the score for each test item is read from the storage unit, creating a prompt that instructs the job seeker to generate advice for recruiting based on the sentence read for each test item and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. An information processing method in which processing is performed by a computer.

4. Accepting a selection from a plurality of questions prepared in advance as questions about the job seeker 4. The information processing method according to claim 1, wherein the processing is executed by the computer.

5. outputting a screen that displays the test results of the job seeker and has operation buttons for accepting questions about the job seeker; When an operation on the operation button is accepted, a screen is output that displays a selection of a plurality of questions prepared as questions about the job seeker, When a selection of one of the options is accepted, a screen is output that displays the advice generated based on the selected question and the test results of the job seeker.

4. The information processing method according to claim 1, wherein the processing is executed by the computer.

6. Obtaining test results including scores for each of a plurality of test items in an aptitude test taken by a job seeker, Accepting questions about the job seeker when conducting recruitment activities for the job seeker; Identifying, from the plurality of inspection items, inspection items whose scores for each inspection item match the evaluation criteria set for each company and inspection items whose scores do not match the evaluation criteria; creating a prompt that instructs the generation of advice for conducting recruitment activities for the job seeker based on the scores for the identified matched and unmatched test items and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. A program that causes a computer to perform a process.

7. In an information processing device having a control unit, The control unit Obtaining test results including scores for each of a plurality of test items in an aptitude test taken by a job seeker, Accepting questions about the job seeker when conducting recruitment activities for the job seeker; Identifying, from the plurality of inspection items, inspection items whose scores for each inspection item match the evaluation criteria set for each company and inspection items whose scores do not match the evaluation criteria; creating a prompt that instructs the generation of advice for conducting recruitment activities for the job seeker based on the scores for the identified matched and unmatched test items and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. Information processing device.

8. A method for obtaining test results of an aptitude test taken by a job seeker, the test results including scores for each of a plurality of test items in the aptitude test; Accepting questions about the job seeker when conducting recruitment activities for the job seeker; creating a sentence corresponding to the score for each of the plurality of test items; creating a prompt that instructs the job seeker to generate advice for recruiting based on the sentences created for each test item and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. A program that causes a computer to perform a process.

9. A method for obtaining test results of an aptitude test taken by a job seeker, the test results including scores for each of a plurality of test items in the aptitude test; Accepting questions about the job seeker when conducting recruitment activities for the job seeker; a memory unit stores a sentence corresponding to the score of each of the plurality of test items; A sentence corresponding to the score for each test item is read from the storage unit, creating a prompt that instructs the job seeker to generate advice for recruiting based on the sentence read for each test item and the received question; The created prompt is input into a language model, and advice on recruiting activities is obtained for the job seeker generated by the language model. A program that causes a computer to perform a process.

Images