Information processing system, information processing method and program

Abstract

An information processing system, method, and program for conducting interviews with applicants is provided. [Solution] The method includes starting a conference session in an interview preparation mode, and switching the conference session to the interview mode when an instruction to switch to the interview mode is received from a user, starting an interview with an avatar selected in the interview preparation mode as the interviewer, displaying an avatar in the interview preparation mode, outputting a first utterance for breaking the ice as the avatar's speech, outputting a second utterance for setting the avatar as the avatar's speech, and displaying selectable options for multiple setting items of the avatar, and accepting an avatar selection including a first response to the first utterance and a second response or selection of an option to the second utterance, and a switching instruction, a first display control step of displaying an avatar changed in accordance with the avatar selection, and a second display control step of displaying the changed avatar.

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 technique relating to an interview system in which an interview robot interviews applicants instead of a human interviewer. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-032164 Summary of the Invention [Problem to be solved by the invention]

[0004] There is room for improvement in the technology related to the information processing systems used to interview applicants.

[0005] In view of the above circumstances, the present invention provides a technology relating to an improved information processing system for conducting interviews with applicants. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system including at least one processor, the processor being configured to execute the following steps by reading a program: in a session control step, a conference session is started in an interview preparation mode; when an instruction to switch to the interview mode is received from a user, the conference session is switched to the interview mode, and an interview is started with an avatar selected in the interview preparation mode as the interviewer; in the interview preparation mode, in a first output step, an avatar is displayed and a first utterance for ice-breaking is output as an utterance of the avatar; and in a second output step, an utterance for ice-breaking is output. An information processing system is provided in which a second utterance for setting the avatar is output as the avatar utterance, and a setting screen displaying selectable options for each of a plurality of setting items for the avatar is output; a reception step receives a first response to the first utterance, an avatar selection in response to the second utterance, and a switching instruction, the avatar selection including a second response or a selection of an option; a first display control step receives the avatar selection, and then displays the avatar changed in accordance with the avatar selection; and a second display control step switches to interview mode and then displays the changed avatar.

[0007] According to this aspect, it is possible to provide technology relating to an information processing system for conducting improved interviews with applicants. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] FIG. 2 is a block diagram showing the hardware configuration of the server 2. [Figure 3] 3 is a block diagram showing the hardware configuration of a job seeker terminal 3. FIG. [Figure 4] 2 is a block diagram showing functions realized by a server 2 (control unit 23), a job seeker terminal 3 (control unit 33), and a recruiter terminal 4 (control unit 43). FIG. [Figure 5] FIG. 10 is a diagram showing a screen G1, which is an example of a screen in the interview preparation mode. [Figure 6] FIG. 10 is a diagram showing a screen G2, which is an example of a screen in an interview mode. [Figure 7] FIG. 2 is a diagram showing an outline of processing executed by the information processing system 1. [Figure 8] 2 is an activity diagram showing an example of the flow of information processing according to the first embodiment, which is executed by the information processing system 1. FIG. [Figure 9] FIG. 10 is an activity diagram showing an example of the flow of information processing according to the second embodiment, which is executed by the information processing system 1. [Figure 10] FIG. 10 is an activity diagram showing an example of the flow of information processing according to the third embodiment, which is executed by the information processing system 1. [Figure 11] FIG. 10 is a diagram showing an evaluation report R1 which is an example of an evaluation report. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

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

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

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

[0016] The information processing system 1 is composed of one or more elements selected from the group consisting of a server 2, a job seeker terminal 3, and an employer terminal 4, which are configured to be able to communicate with each other via a network. This system constitutes at least a part of a recruitment and job search system, and is a platform that performs processes such as job seeker searches by employers and job seekers searches for jobs, as well as interview preparation / interview execution using conference sessions, acquisition of job seeker information and job recruitment information, and generation of evaluation results and evaluation reports.

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

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

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

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

[0021] <Job Seeker Terminal 3> The job seeker terminal 3 is an information processing device used by the job seeker U1. A "job seeker" refers to a person who is seeking employment and is active with the aim of finding a job. For example, this includes people looking to change jobs, prospective new graduates (job seekers), etc., and may also include people who are currently looking for a new job or job, or people who are interested in changing jobs or finding employment.

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

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

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

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

[0026] <Recruiter Terminal 4> The recruiter terminal 4 is an information processing terminal used by recruiters. A "recruiter" refers to a person seeking labor and recruiting personnel with the aim of providing employment. Enterprises include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, incorporated foundations), and public corporations (e.g., local governments) or their personnel. Here, the personnel may be called recruiters, and may include personnel in the human resources department of an organization or personnel in a department seeking to hire personnel. Recruiters include recruitment agencies and employment placement agencies that act as intermediaries between job seekers and recruiters. Recruitment agencies are also called headhunters, agents, etc.

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

[0028] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the storage unit 22 is specifically realized by the control unit 23, which is an example of hardware, and can be executed as each functional unit included in the control unit 23 (at least one processor included in the information processing system 1).

[0029] FIG. 4 is a block diagram showing functions realized by the server 2 (controller 23), the job seeker terminal 3 (controller 33), and the recruiter terminal 4 (controller 43).

[0030] Fig. 4A is a block diagram showing functions realized by the control unit 23. As shown in Fig. 4A, the control unit 23 includes an output unit 2301, a reception unit 2302, a display control unit 2303, a determination unit 2304, an utterance extraction unit 2305, a dialogue management unit 2306, a session control unit 2307, an acquisition unit 2308, a question generation unit 2309, an identification unit 2310, an evaluation generation unit 2311, a calculation unit 2312, a missing item extraction unit 2313, a handover information generation unit 2314, a setting unit 2315, and an artificial intelligence unit 2316.

[0031] 4B, the job seeker terminal 3 (control unit 33) includes a display unit 331 and an operation acquisition unit 332. As shown in FIG. 4C, the recruiting party terminal 4 (control unit 43) includes a display unit 431 and an operation acquisition unit 432.

[0032] <Output unit 2301> The output unit 2301 can output various types of information. The output unit 2301 performs the output function in the information processing system and generates data for outputting avatar utterances and other information to the user. Specifically, the output unit 2301 generates the avatar's utterances as voice data and generates the content of the utterances as text data. The output unit 2301 outputs the voice data as voice and outputs the generated text data to the display control unit 2303. The output unit 2301 also outputs the generated utterance data to the dialogue management unit 2306. Furthermore, the output unit 2301 also performs the function of outputting an evaluation report. The evaluation report may be output in any of the following forms: stored as data within the system, transmitted to an external device, or displayed on a screen.

[0033] (First output step) As a first output step, the output unit 2301 displays an avatar and outputs a first utterance for ice-breaking as the avatar's utterance. Here, the ice-breaking utterance refers to a conversation that the AI ​​interviewer makes with the user before the start of the interview to relieve the user of the psychological burden of the AI ​​interview and encourage a smooth dialogue with the system. The first utterance for ice-breaking may be, for example, a greeting such as "Hello," a call such as "Is this your first AI interview?", "Please feel free to ask again if there is a pause," or "Are you ready?", or the provision of a general topic. In addition, the ice-breaking utterance may be a conversation in the preparation stage that is distinct from the actual interview, and the content of the ice-breaking conversation need not affect the evaluation of the actual interview. etc.

[0034] (Second output step) In a second output step, the output unit 2301 outputs a second utterance for setting the avatar as the avatar's utterance, and also outputs a setting screen displaying selectable options for each of multiple avatar setting items. The multiple avatar setting items include selection of avatar candidates and selection of the avatar's speech speed. Avatar candidates can be selected from multiple patterns with different attributes and characteristics, such as age or gender. When the reception unit 2302 receives the user's speed setting, the output unit 2301 outputs the speech at a speed corresponding to the selected speed. The setting may be performed by the user directly operating the displayed setting screen or by the user's voice response to the AI ​​interviewer, such as "speak a little faster." This allows the user to easily complete the setting through dialogue with the AI ​​interviewer without operating a keyboard or the like, thereby reducing the burden of system operation and the psychological hurdles for the interview. Furthermore, the preparation process, such as system setting, also functions as a warm-up for the interview.

[0035] (Third output step) As a third output step, the output unit 2301 outputs a third utterance to the user in the interview preparation mode to confirm the setting status of the conference session. Here, the setting status of the conference session includes at least one of the audio status, the video status, and the communication status. Examples of the third utterance to confirm the setting status of the conference session include "Is the screen displayed?", "Can you say something?", "Can you hear the audio?", etc.

[0036] (4th output step) As a fourth output step, the output unit 2301 outputs a question to the user regarding the user's job search activities in the interview mode. The output unit 2301 outputs the question generated by the question generation unit 2309 based on the job seeker information or the second history.

[0037] (5th output step) As a fifth output step, the output unit 2301 outputs to the hiring manager an evaluation report based on the evaluation results calculated by the evaluation generation unit 2311 etc. The evaluation report may be output in any form, such as being stored as data within the system, being sent to the hiring manager by email, or being displayed on a terminal screen.

[0038] <Reception Department 2302> The reception unit 2302 is configured to be able to receive information from the job seeker terminal 3 or another information processing terminal. The reception unit 2302 is also configured to receive various pieces of information by reading various pieces of information stored in a storage area, which is at least a part of the memory unit 22, and writing the read information to a work area, which is at least a part of the memory unit 22. The storage area is, for example, an area of ​​the memory unit 22 implemented as a storage device such as an SSD. The work area is, for example, an area implemented as memory such as RAM. For example, the reception unit 2302 is configured to be able to receive input from the job seeker U1 to the job seeker terminal 3. The input from the job seeker U1 includes input based on terminal operation and voice input. For example, the reception unit 2302 receives a first response to a first utterance, an avatar selection in response to a second utterance, and a switching instruction. The avatar selection includes a second response or a selection of an option. The reception unit 2302 receives the selection of one avatar candidate from multiple avatar candidates. When the receiving unit 2302 receives the selection of the speed setting, the output unit 2301 outputs the utterance at a speed according to the selected speed setting. The receiving unit 2302 receives a third response from the user regarding confirmation of the setting status. The receiving unit 2302 receives the third response by either a voice input in response to the third utterance or a change operation regarding the setting status. The receiving unit 2302 receives a fourth response to the question from the user.

[0039] <Display control unit 2303> The display control unit 2303 controls the display unit 34 to display visual information such as screens, images including still images and videos, icons, and messages (text). The control unit 23 may generate only rendering information for displaying the visual information on the display unit 34 and transmit this to the job seeker terminal 3, thereby causing the job seeker terminal 3 to generate the visual information and display the visual information on the display unit 34. The display control unit 2303 may also generate visual information and transmit it to the job seeker terminal 3, thereby causing the display unit 34 to display the visual information. The display control unit 2303 executes processing for displaying a system screen related to the information processing system 1 on each terminal. For example, the display control unit 2303 performs processing such as generating and transmitting an HTML (Hyper Text Markup Language) file and displays a web page showing the system screen on the display unit 34. The display control unit 2303 may also perform processing such as generating and transmitting display data for an application for using the information processing system 1. For example, the display control unit 2303 can cause the display unit 34 to display various types of visual information.

[0040] The display control unit 2303 is configured to display various information on the job seeker terminal 3, the employer terminal 4, or another device. For example, the display control unit 2303 displays a screen of a conference session as a first display control step and a second display control step. In the interview preparation mode, the screen includes an avatar and first text information in which an utterance and a response to the utterance are converted into text. In the interview mode, the screen includes an avatar and second text information in which a question and a fourth response to the question are converted into text. After switching to the interview mode, the display control unit 2303 displays the changed avatar as a second display control step.

[0041] Furthermore, in the first display control step or the second display control step, the display control unit 2303 may display career information (e.g., a resume or curriculum vitae) of the job seeker U1 on the screen of the conference session. The job seeker information may be acquired by the acquiring unit 2308 (described later) in the first acquisition step. Specifically, for example, in the interview preparation mode, an area for displaying career information may be provided on the screen G1 of FIG. 5, and the career information of the job seeker U1 may be displayed thereon. This allows the job seeker to check his or her own career and skills on the same screen before the start of the interview as part of preparation for the interview. Furthermore, for example, in the interview mode, an area for displaying career information may be provided on the screen G2 of FIG. 6, and the career information of the job seeker U1 may be displayed thereon. This allows the job seeker to respond to questions about his or her own career while checking the displayed career information on the same screen.

[0042] The acquisition unit 2308 may also accept direct input of data such as a resume or curriculum vitae from the job seeker U1. For example, the acquisition unit 2308 may accept upload of document data (e.g., PDF data) such as a curriculum vitae, upload of a folder containing data such as a curriculum vitae, or input of a link (e.g., a URL) to data such as a curriculum vitae stored in cloud storage, and acquire the curriculum vitae, etc. from these data. The career information acquired in this manner may be displayed on the screen as a first display control step or a second display control step.

[0043] (First display control step) As a first display control step, the display control unit 2303 causes a screen of the conference session to be displayed on the job seeker terminal 3. In the interview preparation mode, the screen includes an avatar and first text information in which utterances and responses to the utterances are converted into text.

[0044] FIG. 5 shows screen G1, an example of a screen in the interview preparation mode. Screen G1 includes areas G11, G12, G13, G14, G15, G16, G17, and object G18. Area G15 includes areas G151 and G152, and area G16 includes areas G161, G162, and G163. Area G11 is an area that displays the title of the interview preparation screen (e.g., "Interview Preparation Screen"). Area G12 is an area that displays an operation guidance message for job seeker U1. For example, a message may be displayed that instructs job seeker U1 to set up the screen according to the spoken instructions of the avatar, and then press "Start Interview" when ready.

[0045] Area G13 displays an avatar representing the AI ​​interviewer. In this specification, "AI interviewer" refers to software that outputs speech through an avatar displayed on the screen and progresses the interview while accepting the user's responses. The avatar representing the AI ​​interviewer is a virtual character of the AI ​​interviewer, and functions as an interface for interacting with the user during the interview, fulfilling the role of the interviewer. The avatar may include virtual characters with various expression styles, such as so-called anime-style characters, realistic characters, and animal-like characters. This enhances familiarity and immersion depending on the user's attributes, preferences, and the purpose of the interview. Area G14 is an avatar setting panel, which accepts various avatar-related settings. The avatar setting panel is configured to accept selection of an avatar representing the AI ​​interviewer and settings such as the avatar's speech speed. Area G15 displays a camera preview of job seeker U1.

[0046] Area G151 accepts the selection of an avatar to conduct an AI interview from among multiple avatar candidates. Area G151 displays multiple selectable avatar candidates with different attributes and characteristics, such as age or gender. As a first display control step, the display control unit 2303 selectably displays multiple avatar candidates with different attributes and characteristics, such as age or gender, as avatar setting options in the interview preparation mode. For example, a job seeker U1 can select an avatar for an interview from avatar candidates: a man in his 20s, a man in his 40s, a man in his 60s, a woman in her 20s, a woman in her 40s, and a woman in her 60s. The reception unit 2302 accepts changes to the avatar settings in the interview preparation mode, and the avatar settings accepted in the interview preparation mode are fixed after switching to the interview mode. A temporary avatar is displayed initially, and if the user does not make a selection, the interview can begin with the temporary avatar settings. The avatar's speech rate may also be set to a temporary setting (e.g., normal) by default, and the interview may begin with that speech rate setting unless the user makes a selection. When the display control unit 2303 accepts an avatar selection, it displays the avatar selected by the avatar selection. Note that differences in the avatar's appearance and speech voice do not need to affect the content of the interview questions or the algorithm used for evaluation, and may be intended to reduce the user's psychological burden and improve interactivity. Area G152 is an area for accepting the setting of the avatar's speech rate.

[0047] Area G16 is a setting panel for the setting status of the conference session and is an area for accepting settings for input / output devices to be used in the conference session. Area G161 is an area including a pull-down menu for selecting the camera to be used. Area G162 is an area including a pull-down menu for selecting the microphone to be used. Area G163 is an area including a pull-down menu for selecting the speaker to be used. Area G17 is an area for displaying text information (first text information) related to the first history. The first history is a dialogue history in the interview preparation mode. Area G17 may display text information such as the name and interview date and time of job seeker U1 along with the text information of the first history. Area G17 displays ice-breaking remarks from the AI ​​interviewer and job seeker U1's responses to those remarks. The dialogue history may be updated in real time. Object G18 is an interview start button that accepts an instruction to switch to interview mode. It is enabled when a predetermined condition is met and switches the conference session to interview mode when pressed.

[0048] In a first display control step, when it is determined that a predetermined condition is satisfied, the display control unit 2303 displays an object for receiving an instruction to switch to the interview mode on the screen of the user's interview preparation mode. In this manner, the job seeker U1 can start the interview by issuing an operation instruction via the object when he or she is ready to start the interview.

[0049] (Second display control step) In the first display control step and the second display control step, the display control unit 2303 causes the job seeker terminal 3 to display a screen of the conference session. In the interview preparation mode, the screen includes an avatar and first text information in which an utterance and a response to the utterance have been converted into text. In the interview mode, the screen includes an avatar and second text information in which a question and a fourth response to the question have been converted into text.

[0050] FIG. 6 shows screen G2, an example of a screen in the interview mode. Screen G2 includes areas G21, G22, G23, G24, G25, and an object G26. Area G21 displays the title of the interview screen (e.g., "Interview Screen"). Area G22 displays header information for the conference session (such as the name of job seeker U1, the interview date, and the time slot). Area G23 displays an avatar representing the AI ​​interviewer. Area G23 displays the avatar selected in the interview preparation mode. Area G24 displays the camera image of job seeker U1. The user can switch between areas G23 and G24 by clicking them at will, allowing the user to freely switch between the avatar display and the camera image display depending on the progress and purpose of the interview. Area G25 displays text information related to the second history (second text information). The second history is a dialogue history in the interview mode. Area G25 may display text information such as the name of job seeker U1, date and time, etc., along with the text information of the second history. The dialogue history may be updated in real time. Object G26 is an end button, which, when pressed, accepts an operation to end the interview mode conference session.

[0051] The display control unit 2303 may also include an area for displaying the job seeker's career information acquired by the acquisition unit 2308 on the conference session screens (screens G1 and G2). For example, in the interview preparation mode, the career information can be displayed so that the job seeker can reconfirm his or her career history and skills before the start of the interview and proceed with preparations with peace of mind. In the interview mode, the career information can be displayed alongside the avatar of the AI ​​interviewer. This may help the job seeker to respond more accurately and specifically to questions about his or her career history by referring to the displayed information.

[0052] <Judgment unit 2304> (Determining session configuration status) In the interview preparation mode, the determination unit 2304 determines whether the setting status of the conference session satisfies predetermined conditions. The predetermined conditions include at least one of avatar settings, audio status, video status, and communication status. In the interview preparation mode, the determination unit 2304 determines whether at least one of avatar settings, audio status, video status, and communication status satisfies predetermined conditions. In the interview preparation mode, the determination unit 2304 determines whether predetermined conditions are met, such as whether the avatar is displayed correctly, whether audio input and output is possible, whether camera images can be acquired, and whether the communication status is stable. If the determination unit 2304 determines that the predetermined conditions are met, it causes the display control unit 2303 to display an "object for accepting an instruction to switch to interview mode," allowing the user to voluntarily instruct the start of the interview. If the determination unit 2304 determines that the predetermined conditions are not met, the output unit 2301 outputs a message prompting the job seeker U1 to perform additional settings or an error message. The output unit 2301 may display a message or an error message on the screen G1, or may make an avatar speak.

[0053] In the interview preparation mode, the determination unit 2304 determines whether the first response, the second response, or the third response satisfies a predetermined condition. The determination unit 2304 can determine the microphone setting state, for example, based on the input level of the voice of the response of the job seeker U1 received by the reception unit 2302. For example, the determination unit 2304 may output "Can you hear me?" as the avatar's utterance, and determine the speaker state of the job seeker U1 based on the job seeker U1's response to that utterance.

[0054] (Pass / fail judgment of evaluation results) The determination unit 2304 determines whether the evaluation satisfies a predetermined condition. The determination unit 2304 receives the evaluation result of the job seeker U1 calculated by the evaluation generation unit 2311 and the like, and determines whether the result satisfies the pass criterion (an example of a predetermined condition). Specifically, the determination unit 2304 determines whether the evaluation result calculated in activity A305 to activity A308 satisfies the pass criterion. The pass criterion is set as a standard for relative evaluation (deviation score or ranking), a first suitability threshold, a second suitability threshold, or a combination of multiple conditions. The determination unit 2304 compares the calculated evaluation result with the pass criterion, and determines the result as "pass" if the pass criterion is met, or as "fail" if the pass criterion is not met. The determination result obtained in this manner is reflected in the evaluation report generated in activity A311. For example, if the judgment unit 2304 judges the job seeker U1 to be a pass, a symbol or object indicating "pass" is added to the evaluation report, and if the judgment unit 2304 judges the job seeker U1 to be a fail, a symbol or object indicating "fail" is added to the evaluation report. The judgment unit 2304 may also output the basis for the judgment of pass or fail and add it to the evaluation report. This allows the hiring manager or other person receiving the evaluation report to understand the evaluation results of job seeker U1 at a glance.

[0055] <Utterance Extraction Unit 2305> In the interview preparation mode, the utterance extraction unit 2305 extracts at least one utterance candidate from a plurality of utterance candidates prepared in advance. The utterance candidate refers to a selection of utterances that the AI ​​interviewer can output to the user, and is used for the purpose of checking the environment for the progress of the interview and reducing the psychological burden on the job seeker. The utterance candidate may be related to any of the following: greeting the user, checking the audio, checking the video, checking the communication status, operation instructions, or checking the user's past interview experiences. Other utterance candidates may include current events, talking about the weather, or personal experiences that empathize with the job seeker. The utterance extraction unit 2305 extracts at least one utterance candidate from among the plurality of utterance candidates based on the first history.

[0056] <Dialogue Management Unit 2306> The dialogue management unit 2306 is configured to determine whether various information and data satisfy predetermined standards and conditions. The dialogue management unit 2306 manages dialogues that occur during a conference session. The dialogue management unit 2306 manages utterances output by the output unit 2301 and responses received by the reception unit 2302 in chronological order.

[0057] (First dialogue management step) As a first dialogue management step, the dialogue management unit 2306 manages utterances and responses to the utterances in the interview preparation mode as a first history. The dialogue management unit 2306 does not permanently store the first history, but holds it in temporary memory. The dialogue management unit 2306 inputs the first history to the utterance extraction unit 2305 and causes the utterance extraction unit 2305 to output utterance candidates to be output next. For example, as a first dialogue management step, the dialogue management unit 2306 holds the first history while the interview preparation mode continues. When switching to the interview mode, the first history may be deleted.

[0058] (Second dialogue management step) As a second dialogue management step, the dialogue management unit 2306 manages the question and the fourth response to the question in the interview mode as a second history. The dialogue management unit 2306 inputs the second history to the question generation unit 2309 and causes the question generation unit 2309 to output the next question. As a second dialogue management step, the dialogue management unit 2306 records the second history while the interview mode continues. The second history is saved as part of the interview data.

[0059] Here, the type of interview data to be recorded as the second history may be selectable by the recruiter. For example, if the recruiter selects to record only audio data as the second history, video data will not be recorded as the second history and will not be used in the evaluation described below. This allows the recruiter to provide an environment that makes it easier for job seekers to take interviews, without having to worry about the location, etc., depending on the recruiter's selection.

[0060] <Session control unit 2307> The session control unit 2307 controls the entire conference session. When the reception unit 2302 receives a start instruction from job seeker U1, the session control unit 2307 starts the conference session in interview preparation mode, and when the reception unit 2302 receives an instruction to switch to interview mode from job seeker U1, it switches the conference session to interview mode. The session control unit 2307 controls the start and stop of recording the conference session. The session control unit 2307 does not record the conference session in interview preparation mode. After switching to interview mode, the session control unit 2307 starts recording the conference session. When the session control unit 2307 receives an instruction to end the interview in interview mode, it ends the interview mode and saves the interview data. The session control unit 2307 may be configured to allow the job seeker to re-conduct the interview up to a predetermined number of times. The predetermined number of times may be set by the employer or may be set in advance by the information processing system 1.

[0061] <Acquisition part 2308> The acquisition unit 2308 is configured to be able to acquire information from the job seeker terminal 3 or other devices. The acquisition unit 2308 is also configured to be able to accept various pieces of information by reading out various pieces of information stored in a storage area that is at least a part of the memory unit 22 and writing the read out information in a work area that is at least a part of the memory unit 22. The storage area is, for example, an area of ​​the memory unit 22 that is implemented as a storage device such as an SSD. The work area is, for example, an area that is implemented as a memory such as a RAM.

[0062] (First acquisition step) As a first acquisition step, the acquisition unit 2308 acquires job seeker information (job seeker data) of the job seeker U1. The job seeker information is information about the job seeker, and includes career information acquired from the job seeker U1, interview data of the job seeker U1, aptitude test data of the job seeker U1, etc.

[0063] The career information includes a resume, a curriculum vitae, information about job content, etc. For example, the acquisition unit 2308 may accept input of career information from the job seeker U1 via a screen displayed on the display unit 34 of the job seeker terminal 3. The acquisition unit 2308 may also acquire career information about the job seeker from a job seeker database. The job seeker database is a database that registers job seeker information used by the job seeker U1 in his or her job search. It includes job seeker information entered on the registration screen and registered in advance, and contains all information about registered or entered job seekers. Note that a "resume" is a document that mainly contains a job seeker's profile, current situation, educational background, work history, desired working conditions, etc., while a "curriculum vitae," also known as a resume, is a document in which a job seeker conveys their work history, experience, skills, qualifications, etc. to a recruiter. Information about job content includes information about organizations in which the job seeker U1 has worked and information describing the duties and tasks they have performed within those organizations. Job details may include, for example, the job seeker's previous organizations, department names, job titles, employment periods, positions held, work performed, projects held, specific achievements and results, work periods, the job seeker's management experience and language proficiency, awards, qualifications held, skills held, and highest level of education. Job seeker information may also include the career aspirations of job seeker U1. Career aspirations include job seeker U1's desired "career vision and future image," "important values," "reason and motivation for changing jobs," "corporate culture and climate," "important work style," and "working conditions (annual salary, work location, benefits)."

[0064] The interview data includes data obtained during an interview conducted either by AI interview, online interview, or face-to-face interview. The interview data for an AI interview is data recorded in interview mode. The interview data includes at least information about utterances or questions to the job seeker U1 and information about the responses from the job seeker U1. The interview data may be video data, audio data, a dialogue script, etc., and may include timestamps, speaker labels, and audio / video meta information.

[0065] The aptitude test data is data obtained based on an aptitude test administered to the job seeker U1. The aptitude test may be administered online or in person and may include various tests such as personality assessment, cognitive ability tests, logical thinking tests, numerical processing tests, language comprehension tests, and character trait tests. The aptitude test data includes at least the answers to each question, scores, time required, and log information related to the answering process. It may also include behavioral data during the test (e.g., reaction time, mouse and keyboard operation patterns, and eye tracking data). The aptitude test data is saved in a format that allows it to be associated with each competency element (e.g., leadership, communication skills, problem-solving skills, logical thinking, etc.). The aptitude test data is then combined with interview data and used for evaluation processing by the calculation unit 2312 and the evaluation generation unit 2311 in the downstream stage.

[0066] (Second acquisition step) The acquiring unit 2308 acquires reference data including information about the evaluation of each member of a reference group. Here, the reference data is data used as a comparison when calculating the evaluation of a job seeker, and includes data on employees belonging to the organization corresponding to the job opening for which the job seeker applied, or data related to the user group of the recruitment activity support system, job search support system, or career support system. The information about the evaluation may include an evaluation calculated when using the system, or an evaluation stored in the integrated database using external aptitude test results as input. The acquiring unit 2308 may use, for example, a score obtained by analyzing the employee's past interview data or aptitude test data as the reference data. The acquiring unit 2308 may use, as the reference data, an evaluation calculated by the calculating unit 2312 based on the employee's past interview data or aptitude test data.

[0067] The "evaluation information" included in the reference data includes each employee's aptitude test results, interview evaluation scores, job performance records, skill information, or information that allows an evaluation to be calculated based on these. The acquisition unit 2308 may acquire this reference data from a database stored in the information processing system, or may acquire it in conjunction with an external human resources management system, evaluation system, or employee database provided by the recruiting company. The reference data may also be provided as anonymized and statistical sample data. The reference data acquired in this manner is used for comparison with job seeker data in a subsequent calculation step, and serves as the basis for calculating the job seeker's deviation score, ranking, compatibility with the organizational culture, or compatibility with the hiring criteria.

[0068] (Third acquisition step) The acquisition unit 2308 acquires a checklist containing items to be checked during the interview. Here, a checklist is information that systematically summarizes the items that an interviewer or AI interviewer should check with a job seeker during the interview, and is used to prevent any omissions during the interview. The checklist includes, for example, confirmation of the job seeker's basic information (such as name and contact information), questions regarding motivation and aptitude for the job position, whether or not the job seeker has specific skills and experience, desired working conditions, or questions based on the company's unique evaluation criteria. The checklist may also include questions related to organizational culture and team compatibility, and items to be compared with aptitude test results and past interview data. The acquisition unit 2308 may acquire the checklist from a template pre-registered in the information processing system or from a proprietary checklist database provided by the employer. Alternatively, the automatic generation unit may acquire a checklist generated using a large-scale language model or rule-based system in accordance with the hiring policy and hiring requirements. The confirmation list thus obtained is collated with the interview data in the subsequent missing item extraction unit 2313 and is used to identify any items that have not been checked as missing items.

[0069] <Question generation section 2309> The question generation unit 2309 has a function of generating questions to be presented to job seekers. The question generation unit 2309 generates the questions based on job seeker information or the second history and reference information for question generation. Here, the reference information for question generation includes at least a correlation between the job seeker information or the second history and the questions, and may include rule-based information such as a database or a lookup table, a trained model, a large-scale language model, a generative AI, etc. The question generation unit 2309 may generate appropriate questions by using the trained model or rule-based reference information in the artificial intelligence unit 2316. Furthermore, the question generation unit 2309 can input the job seeker information or the second history to the artificial intelligence unit 2316 and obtain questions generated by the artificial intelligence unit 2316. The question generation unit 2309 may generate questions to be presented to job seekers based on the job seeker information or the second history, job information, and first reference information.

[0070] The reference information for generating questions includes correlations between the job seeker information or the second history and the questions to be generated. The reference information for generating questions may be stored in a storage unit, for example. The reference information for generating questions may include, for example, a table, a function, a simple algorithm, or the like that indicates the correspondence between the job seeker information or the second history and the corresponding questions. The correlations included in the reference information for generating questions can be constructed, for example, by statistically analyzing data that records the job seeker information or the second history and the corresponding questions.

[0071] The reference information for question generation may include a learning model that has been machine-learned to be capable of outputting questions using job seeker information or the second history as input, or a question generation model that is a generation AI. In this case, the question generation unit 2309 inputs the job seeker information or the second history into the question generation model and causes the question generation model to output a question. In the question generation model, parameters calculated, tuned, etc. through learning constitute correlations in the reference information for question generation.

[0072] The question generation model is included in the artificial intelligence unit 2316. The question generation model, which has been trained to be able to output questions, is trained using, for example, job seeker information or second history data and corresponding question data as training data.

[0073] When the question generation model is a generation AI including a general-purpose natural language model (large-scale language model), the question generation unit 2309 receives job seeker information or the second history as input, inputs a prompt including an instruction to output a question corresponding to the information to the question generation model, and causes the question to be output. The question generation unit 2309 may generate a prompt that instructs the question generation model to generate a question, and input the prompt to the question generation model. Furthermore, the question generation unit 2309 may input, to the question generation model, in addition to the instruction to generate a question and the job seeker information or the second history, a prompt in which, for example, one or more samples of job seeker information and corresponding sample questions are inserted as examples, samples, or training data of input and output pairs.

[0074] The reference information for question generation may include information defining a search formula or generation conditions for searching for or determining questions to be presented based on the job seeker information or the second history. For example, the reference information for question generation may be a table or algorithm that defines the relationship between feature amounts (e.g., feature vectors) extracted from the job seeker information and question types (e.g., questions about career goals, questions about skills, questions about job suitability, etc.). Furthermore, the question generator 2309 may input instructions for creating questions based on the job seeker information to a question creation model, which is a generation AI included in the reference information for question generation, and cause the model to output questions.

[0075] The reference information for generating a question may be, for example, a question template or format that defines question classification items (e.g., skills, experience, inclination, desired conditions, etc.) and information (variables) extracted from the job seeker information or the second history for each item. For example, the reference information for generating a question may be a question template or format such as "skills = {skill information of job seeker}, desired work location = {desired work location of job seeker}", and the question generating unit 2309 may specify a question by inserting the job seeker information or the second history into such reference information for generating a question.

[0076] The question generation unit 2309 can generate questions according to the characteristic elements identified by the identification unit 2310. For example, if a desired occupation is identified as a characteristic element, the question generation unit 2309 can generate questions according to the desired occupation. For example, if the desired occupation is "sales," the question generation unit 2309 generates questions asking about communication skills, and if the desired occupation is "engineer," the question generation unit 2309 generates questions asking about logical thinking skills. This makes it possible to present appropriate questions that link the competencies to be evaluated in the interview with the job seeker's desired occupation. Furthermore, when generating questions, the question generation unit 2309 may select from multiple question candidates prepared in advance, and may use job seeker information (e.g., work history, skills, career aspirations) when making the selection. The question generation unit 2309 can select questions using a decision tree or a conditional branching table. For example, if there is a predetermined condition that if the desired job type is "sales", a "question testing communication skills" should be selected, and if the desired job type is "engineer", a "question testing logical thinking skills" should be selected, the question generation unit 2309 selects questions in accordance with the predetermined condition. Furthermore, the question generation unit 2309 may analyze the content of the job seeker's most recent response (second history) in real time, and dynamically generate follow-up questions that delve deeper into the content, or adjust the difficulty of the questions in accordance with the state of the job seeker estimated from the state of the job seeker's response.

[0077] Furthermore, the reference information for question generation may be a language model, including a large-scale language model or a small-scale language model, or may be a question-generating AI agent that can access information contained in the job seeker information or the second history and generate questions for the job seeker based on that information.

[0078] Furthermore, the question generation unit 2309 may generate questions using not only information acquired from the job seeker U1, but also job information acquired from the employer U2 or a checklist acquired by the acquisition unit 2308. For example, the required skills described in the job information or check items included in the checklist may be input and analyzed using a language model, a model such as a generative AI, or rule-based processing to generate questions corresponding to the information. When a checklist is used, questions may be generated prioritizing unchecked items depending on the progress of the interview (this makes it possible to comprehensively acquire information necessary for evaluation). The questions generated in this manner are output to the job seeker from the output unit 2301 in the fourth output step, and the reception unit 2302 acquires the job seeker's responses. The questions and responses are then managed by the dialogue management unit 2306 as a second history and used in the evaluation process by the evaluation generation unit 2311.

[0079] <Specific part 2310> The identification unit 2310 can identify characteristic elements of the job seeker U1 based on the job seeker information and the second history. The characteristic elements are used to generate questions tailored to the job seeker U1. The characteristic elements include the job type, industry, job content, language ability, qualifications, work experience (management experience, overseas experience), past career, and future career aspirations. For example, the identification unit 2310 identifies the user's desired job type based on the job seeker information or the second history. Furthermore, the identification unit 2310 refers to pre-prepared determination rules and mapping tables to identify characteristic elements corresponding to the input job seeker information (e.g., the job type and qualification information listed in the resume). The identification unit 2310 identifies the characteristic elements from the input values ​​using a regression equation or a determination equation that shows the correlation between past job seeker data and the characteristic elements. The identification unit 2310 inputs the job seeker information and the second history into the artificial intelligence unit 2316 and identifies the characteristic elements as analysis results using natural language processing or generation AI. The artificial intelligence unit 2316 may be a module in the system server or an external AI service. The feature elements identified in this way are used in the question generation process in the question generation unit 2309 to present questions that match the job seeker's desired occupation and career aspirations.

[0080] Furthermore, the identification unit 2310 can analyze both the interview data and the aptitude test data when identifying the characteristic elements of the job seeker U1. The identification unit 2310 can extract competency elements as features indicative of behavioral characteristics by analyzing the content of utterances recorded in the interview mode, the speed and consistency of responses, the intonation and pauses of the voice, and facial expressions, gaze, and posture contained in the video data. Competency elements include leadership, communication skills, problem-solving skills, and logical thinking skills. The identification unit 2310 can also extract psychological and behavioral features. Based on the results of the aptitude test, psychological and behavioral features such as personality traits, cognitive ability, numerical and linguistic comprehension, and stress tolerance can be extracted as features indicative of the job seeker's psychological characteristics. This allows the job seeker's comprehensive characteristics to be grasped from both the behavioral features obtained from the interview data and the psychological features obtained from the aptitude test data. Furthermore, the identification unit 2310 can analyze both the interview data and the aptitude test data when identifying the characteristic elements of the job seeker U1. The identification unit 2310 can analyze either or both of these data to extract features related to the job seeker's behavioral characteristics (e.g., responses during the interview or responses to the aptitude test) and psychological characteristics (e.g., personality estimated from the results of the aptitude test or the content of speech during the interview). This enables a multifaceted analysis of the behavioral characteristics and psychological characteristics, making it possible to identify the job seeker's potential abilities and risks, which would be difficult to do from a single source of information. Note that the classification of behavioral characteristics and psychological characteristics mentioned here is merely an example, and the extracted features may be associated with specific competency elements, such as leadership or communication skills.

[0081] Furthermore, the identification unit 2310 integrates feature quantities based on the interview data and feature quantities based on the aptitude test data, and identifies feature elements by taking into account the correlation and complementary relationship between the two. For example, by comparing the relationship between the speaking attitude during the interview and stress tolerance in the aptitude test, feature elements related to interpersonal skills can be identified more accurately. This integration process may be realized by rule-based mapping, estimation using a regression equation or a statistical model, or analysis using a machine learning / generative AI model by the artificial intelligence unit 2316, or a combination of these. The feature elements identified in this manner are used in the question generation process by the question generation unit 2309 and the evaluation calculation process by the calculation unit 2312, contributing to the progress of the interview and the improvement of the evaluation in line with the job seeker's abilities and aptitude. The identification unit 2310 may also acquire public information about the job seeker (such as a profile on a business social networking site) from an external source and identify feature elements from this information.

[0082] <Evaluation Generation Unit 2311> The evaluation generation unit 2311 generates an evaluation result for a user based on the job seeker information or the second history and the evaluation generation reference information. The evaluation generation reference information includes a correlation between the job seeker information or the second history and the evaluation result to be generated. The evaluation generation reference information may be stored in, for example, a storage unit. The evaluation generation reference information may include, for example, a table, a function, a simple algorithm, or the like that indicates the relationship between the job seeker information or the second history and the corresponding evaluation result. The correlation included in the evaluation generation reference information can be constructed, for example, by statistically analyzing data that records the job seeker information or the second history and the corresponding evaluation result.

[0083] The reference information for generating an evaluation may include an evaluation generation model, which is a learning model that has been machine-learned to receive job seeker information or the second history and output an evaluation result, or a generation AI. In this case, the evaluation generation unit 2311 inputs the job seeker information or the second history into the evaluation generation model and causes the evaluation generation model to output an evaluation result. In the evaluation generation model, parameters calculated, tuned, etc. through learning constitute correlations in the reference information for generating an evaluation. The evaluation generation unit 2311 may obtain the deviation score or ranking in the reference group calculated by the calculation unit 2312, the degree of fit with the organizational culture (first degree of fit), the degree of fit with the hiring criteria (second degree of fit), etc., and generate an evaluation report based on the obtained information.

[0084] If the evaluation generation model is a generation AI including a general-purpose natural language model (e.g., a large-scale language model or a small-scale language model), the evaluation generation unit 2311 may input job seeker information or the second history and input a prompt including an instruction to output an evaluation result to the evaluation generation model, thereby generating an evaluation result. The evaluation generation unit 2311 may generate an instruction specifying the expression format of the evaluation result and input this as the prompt. Furthermore, if necessary, sample data including an input-output pair (e.g., job seeker information or the second history and an example evaluation result) may be added to the prompt.

[0085] The type of data included in the second history to be input to the evaluation generation model may be selected by the employer. If video data is selected as the data to be used for evaluation, not only the content of the utterances of job seeker U1 but also information such as facial expressions and movements may be analyzed by the evaluation generation model and used for evaluation.

[0086] (Generate assessment report) The evaluation generation unit 2311, as an evaluation report generation function, generates an evaluation report based on the evaluation and reference information for evaluation report generation. Here, the reference information for evaluation report generation is information that includes at least the correlation between the evaluation and the evaluation report. The reference information for evaluation report generation includes the correlation between the evaluation and the evaluation report. The reference information for evaluation report generation is stored, for example, in the storage unit 22. The reference information for evaluation report generation may include, for example, a table, a function, a simple algorithm, etc. that indicates the correlation between the evaluation value and the output content of the evaluation report (such as observation comments, graphs, tables, and compatibility score displays). The correlation included in the reference information for evaluation report generation can be constructed, for example, by statistically analyzing the evaluation values ​​of past job seekers and the content of the corresponding evaluation reports.

[0087] The reference information for generating an evaluation report may include an evaluation report generation model, which is a learning model trained by machine learning to input an evaluation value and output an evaluation report, or a generation AI. In this case, the evaluation generation unit 2311 inputs the evaluation value into the evaluation report generation model and generates an evaluation report using the model. In the evaluation report generation model, parameters calculated and adjusted by learning constitute the correlation of the reference information for generating an evaluation report.

[0088] The evaluation report generation model is included in the artificial intelligence unit 2316. The evaluation report generation model, which has been trained to be able to output an evaluation report, is trained using, for example, evaluation value data and the corresponding report headings, comments, and chart information as training data.

[0089] If the evaluation report generation model is a generative AI that includes a general-purpose natural language model (large-scale language model or small-scale language model), the evaluation generation unit 2311 may input an evaluation value and input a prompt including an instruction to output an evaluation report corresponding to the evaluation value to the evaluation report generation model, thereby generating an evaluation report. The evaluation generation unit 2311 may generate instructions specifying the expression format of observation comments and pass / fail based on the evaluation results and input these as prompts. Additionally, sample data including input-output pairs (e.g., past evaluation values ​​and example reports) may be added to the prompts as needed.

[0090] The reference information for generating an evaluation report may be, for example, a template or format that defines the relationship between display items of the report (e.g., scores by element, deviation value, average score, suitability score, overall judgment, handover information, etc.) and input variables (e.g., evaluation value, history information, etc.) for generating each display item. Furthermore, the template or format may be selected or changed depending on the role of the viewer of the report (e.g., recruiter or manager of the department to which the report is assigned).

[0091] For example, the evaluation report may include at least one of visual information such as a table or graph containing the evaluation, comments corresponding to the evaluation, and a transcript of the interview dialogue. The evaluation report may also include an input area for accepting a final evaluation from a user such as a recruiter. The evaluation report may also include a playback area for playing a video corresponding to the interview data. An example of visual information may be a radar chart displaying the scores for each competency element. An example of a table may display the job seeker's evaluation score, the average score of a reference group, and a standard deviation for each evaluation item. Supplementary comments, such as specific episodes or observations that serve as the basis for the evaluation, may be associated with each vertex of the radar chart, each evaluation item in the table, or other graph. Examples of comments may include observations on the evaluation results, such as "leadership is a strength" or "there is room for improvement in problem-solving ability," or a summary summarizing the job seeker's career history. The evaluation generation unit 2311 may generate an evaluation report that reflects project performance and skills based on the career information included in the job seeker information. Furthermore, an evaluation report may be generated that includes information on transfer obtained from the missing item extraction unit 2313 regarding items that could not be confirmed during the interview.

[0092] Furthermore, if the judgment unit 2304 judges that the evaluation satisfies predetermined conditions, the evaluation generation unit 2311 outputs the evaluation report with a symbol or object indicating "pass." If the evaluation does not satisfy predetermined conditions, the evaluation generation unit 2311 generates an evaluation report with a symbol or object indicating "fail" or with comments indicating areas for improvement. This allows the hiring manager to grasp at a glance whether the applicant passed or failed and areas for improvement.

[0093] <Calculation unit 2312> The calculation unit 2312 analyzes the interview data and aptitude test data of the job seeker U1 and calculates an evaluation based on a comparison with the reference data. The calculation unit 2312 calculates the job seeker's evaluation based on the job seeker data, the reference data, and the reference information for evaluation calculation. The reference information for evaluation calculation includes at least the correlation between the job seeker data, the reference data, and the evaluation. The calculation unit 2312 then compares the calculated evaluation of the job seeker with the reference data to calculate an evaluation indicating the job seeker's relative position. The evaluation indicating the relative position is, for example, the deviation score or rank of the job seeker within the group. Here, the reference data is acquired by the acquisition unit 2308. In this way, the calculation unit 2312 calculates an evaluation including information indicating the job seeker's relative relationship to the group. The calculation of the relative evaluation with respect to the reference data includes the following aspects: (a) If the group is employees of a hiring company, the calculation unit 2312 calculates the job seeker's relative position within the company by comparing the evaluation of the job seeker U1 with employee data. (b) If the group is all users of the system, the evaluation of job seeker U1 is made relative to the distribution of all users. (c) If the group is a specific attribute among system users (e.g., a group of users with the same desired job type), the relative evaluation within that subgroup is calculated. Here, the reference data is not limited to data on current employees or current users, but may also include data on employees who previously worked for the system and data on past users based on system usage history.

[0094] The calculation unit 2312 calculates individual evaluations for multiple characteristic elements. Based on the job seeker data, the standard data, and the evaluation calculation reference information, the calculation unit 2312 calculates multiple evaluations for each of the job seeker's evaluation elements. The evaluation elements may include competency-related elements. Competency, as used herein, refers to a systematized set of behavioral characteristics and abilities required to achieve high performance in a specific job or organization, and is an element that represents the job seeker U1's behavioral characteristics and job performance. The evaluation elements include at least one competency-related element, such as leadership, communication ability, problem-solving ability, or logical thinking ability. The evaluation elements may also include non-competency elements, such as clarity of responses and consistency of assertions and evidence, if necessary. The calculation unit 2312 calculates a score for the identified "communication ability" by combining the content of interview responses and interpersonal scales from aptitude tests. This method allows for the calculation of an evaluation for each evaluation element. This allows for a clear understanding of the job seeker U1's strengths or weaknesses in specific areas. Furthermore, the calculation unit 2312 may assign different weights to multiple evaluation elements based on the job information for which the job seeker applied, and calculate an overall evaluation score that reflects the weights. For example, it is possible to set a high weight on "communication ability" for a job posting for a sales position, and a high weight on "logical thinking ability" for a job posting for a development position.

[0095] (First fitness) The calculation unit 2312 calculates, as an evaluation, a first degree of fit indicating the degree to which the job seeker fits into the group's organization. The first degree of fit is calculated based on the job seeker data, the standard data, and the first reference information for fit, and the first reference information for fit includes at least the correlation between the job seeker data, the standard data, and the first degree of fit. This allows the degree of fit between the job seeker and the organizational culture of the employer U2 to which the job seeker has applied to be calculated. As used herein, "organizational culture" refers to characteristics such as behavioral patterns, judgment criteria, communication styles, decision-making tendencies, and weighting of desired competencies that are valued in the organization. The first reference information for fit includes interview data and aptitude test data of employees of the organization, distributions of evaluation element scores, and modeled correlation structures between these evaluation elements. The calculation unit 2312 extracts features such as language, acoustics, dialogue structure, and psychological scales from the interview data and aptitude test data of job seeker U1, and calculates a first degree of compatibility based on the features and the first reference information for compatibility.

[0096] An example of a specific method for calculating the first degree of fit will be described. The calculation unit 2312 constructs a reference model for calculating the first degree of fit based on the reference data acquired by the acquisition unit 2308. Here, the reference data includes evaluation element scores obtained based on interview data and aptitude test data of a group of employees belonging to the organization. Furthermore, the reference data is not limited to the group of employees of the entire organization, but can also be based on a group of employees belonging to a specific department or team to which the job seeker may be assigned. This makes it possible to calculate the degree of fit for a specific department or team rather than for the entire organization, such as a company. Furthermore, the data for the group of employees is not limited to data for all current employees. For example, data for a group of high performers who have achieved particularly high results, data for a group of prospective employees who have already been hired, or data modeled after a personality profile uniquely defined by the organization based on future business strategies, etc., can be used as the reference data. This makes it possible to calculate the degree of fit that reflects the type of talent the organization values ​​and its future direction.

[0097] Based on the reference data, the calculation unit 2312 generates, for example, an organizational prototype vector consisting of representative values ​​(average or median) for each evaluation element, a covariance matrix showing the correlation between the evaluation elements, and, if necessary, labels for supervised learning showing the employee's level of performance or retention, and stores these as part of the first reference information for compatibility.

[0098] The calculation unit 2312 extracts features based on the interview data and aptitude test data of job seeker U1 and converts them into evaluation element vectors. The extracted features include, for example, linguistic features (speech content, vocabulary diversity, logical structure) contained in the interview data, acoustic features (speech rate, intonation), dialogue structural features (number of turns, response delay), and psychological measures based on the aptitude test (agreeableness, decision-making tendency, etc.). The calculation unit 2312 standardizes these features through normalization processing (z-score transformation, quantile transformation, etc.) and converts them into scores for each evaluation element, such as leadership, communication ability, problem-solving ability, and logical thinking ability.

[0099] The calculation unit 2312 estimates the degree of compatibility with the organizational culture based on the evaluation element vector and the first compatibility reference information. The compatibility calculation is performed using a similarity calculation method, a learning model method, a rule-based method, or the like. The similarity calculation method calculates the cosine similarity or Mahalanobis distance between the evaluation element vector and the organizational prototype vector, and calculates a score between 0 and 100. The learning model method inputs the evaluation element vector into a trained model such as a logistic regression model or a neural network constructed based on employee data, and calculates the compatibility probability or score. The rule-based method calculates the linear sum of each evaluation element score or the satisfaction level of essential conditions based on weighting and threshold conditions defined by the organization. The calculation unit 2312 may integrate scores obtained by multiple methods to calculate the degree of compatibility with the organizational culture (first compatibility). The integration is achieved by performing a weighted average based on an integration parameter included in the first compatibility reference information. Furthermore, the calculated first goodness of fit may be calibrated against the employee distribution included in the reference data and calculated as a deviation value or percentile.

[0100] (Second fitness) The calculation unit 2312 compares the evaluation factor pattern of the job seeker with the standard data of a specific group and calculates a second degree of conformance that indicates the degree to which the evaluation factor pattern of the job seeker conforms to the market standard. The specific group may be a group of employees of the recruiter U2 or a group of users of the support system. Furthermore, the user group of the support system may be a group of users of the support system that meets specific conditions, such as a group of high performers by occupation or a market average group. The calculation unit 2312 calculates an evaluation including a second degree of suitability indicating the degree to which the job seeker fits into a group, the second degree of suitability being calculated based on an evaluation corresponding to each evaluation element of the job seeker, the reference data, and the second degree of suitability reference information. The second degree of suitability includes at least a correlation between the evaluation, the reference data, and the second degree of suitability. The second degree of suitability is, for example, the similarity between the scores of the evaluation elements A to E and the reference data of a reference group (e.g., a group of employees of the recruiter U2, a group of users of the support system, etc.). While the first degree of suitability is a degree of suitability based on organizational culture, the second degree of suitability is a degree of suitability based on market standards. The second degree of suitability can be calculated using a method similar to that of calculating the first degree of suitability, except for changing the group used. In calculating the first degree of suitability, the degree of suitability for the group of employees of the recruiting company is calculated, but in calculating the second degree of suitability, the degree of suitability for all system users or a group of system users with specific attributes is calculated. Furthermore, the calculation unit 2312 may calculate the suitability to the job information by using weighting based on requirements such as job type and rank included in the job information.

[0101] <Missing item extraction part 2313> The missing item extraction unit 2313 extracts, based on the interview data and the check list, items included in the check list that are not included in the interview data as missing items. The interview data includes questions and responses obtained during the interview, text data of the conversation, and competency scores used in the evaluation. The check list includes, for example, check items for required skills and qualifications defined based on the job information of the company to which the applicant applied, or evaluation criteria (e.g., leadership, problem-solving ability, language ability, management experience) predefined for each company. The missing item extraction unit 2313 compares each item on the check list and extracts the item as a missing item if information corresponding to the check item is not recorded in the interview data. Even if a response corresponding to a check item is included in the interview data, if the specificity or amount of information in the response does not meet predetermined standards, the check item may be extracted as a "missing item" that has not been sufficiently confirmed. This process allows all skills and experience elements that were not sufficiently confirmed during the interview to be identified. The missing item extraction unit 2313 further outputs the extracted missing items to the handover information generation unit 2314, and these are used as items to be confirmed in the next interview or consultation. This reduces the number of missed checks in the interview process and makes it possible to improve the accuracy of hiring decisions.

[0102] <Transfer Information Generation Unit 2314> As a second generation step, the handover information generation unit 2314 generates handover information that includes missing items as items to be confirmed in the next interview. Here, missing items are items included in the confirmation list extracted by the missing item extraction unit 2313 but not included in the current interview data. The handover information generation unit 2314 organizes the missing items and indicates them as items that must be confirmed in the next interview. At this time, each missing item may be prioritized based on the job information. For example, the handover information may include a list of missing items, recommended questions for confirming the missing items, supplementary information related to the missing items, etc. The handover information generation unit 2314 can incorporate the generated handover information into an evaluation report. Users of the evaluation report (such as recruiters and others involved in the next interview) can refer to the handover information to efficiently identify items that were not confirmed in the previous interview and thoroughly confirm them in the next interview.

[0103] Furthermore, the handover information generation unit 2314 may be configured not only to store the handover information as data, but also to send it to the person in charge by email or the like, or to automatically display it on the preparation screen for the next interview. In this way, the handover information generation unit 2314 ensures the continuity of interviews and contributes to improving the efficiency and comprehensiveness of the entire interview process.

[0104] <Settings Section 2315> The setting unit 2315 has a function of setting a check list according to the job offer applied for by the job seeker or the organization corresponding to the job offer. The check list organizes the skills, experience, qualifications, aptitude factors, etc. of the job seeker U1 to be checked during the interview, and is used to ensure the comprehensiveness of the interview evaluation.

[0105] The reference information for setting the check list includes at least the correlation between the job information and the check list. The reference information for setting the check list may be stored in a memory unit, for example, and may include a table, function, simple algorithm, or the like that associates the job information with the corresponding skill requirements and check items. The correlation can be established by statistically analyzing data on previously registered job information and the check items used during the interview.

[0106] The reference information for setting a check list may include a learning model that has been machine-learned to take job information as input and output a check list, or a check list generation model that is a generation AI. In this case, the setting unit 2315 inputs the job information into the generation model and causes the model to output a check list. Note that parameters calculated or tuned by learning in the check list generation model constitute correlations in the reference information for setting a check list.

[0107] The check list generation model may be included in the artificial intelligence unit 2316. For example, the check list generation model can be constructed by training the job information data and the corresponding check list data as training data. When the generation model is a generation AI such as a large-scale language model or a small-scale language model, the setting unit 2315 inputs the job information, inputs a prompt including an instruction to generate a check list corresponding to the job, and acquires the generated check list. Furthermore, the setting unit 2315 may combine the required skills and check items input by the employer U2 with the proposed list generated by the model to set a final check list.

[0108] The reference information for setting the check list may also include pre-prepared templates and formats for each industry and occupation. In this case, the setting unit 2315 calls up a template according to the occupation or industry extracted from the job information and sets the check list based on this. For example, if the "occupation = sales position," the sales template is referenced and a list is generated based on the check items in that template. Furthermore, the employer U2 inputs additions and deletions to the generated draft check list, and the setting unit 2315 reflects this and finalizes the check list. The check list set in this way is used by the missing item extraction unit 2313 and serves as basic information for extracting items that were not confirmed during the interview as missing items.

[0109] <Artificial Intelligence Department 2316>

[0110] The artificial intelligence unit 2316 is configured to receive input from each functional unit and return an instructed output. The artificial intelligence used by the server 2 for each functional unit may be a common unit, or may be prepared individually for each functional unit. The artificial intelligence unit 2316 can receive input from, for example, the utterance extraction unit 2305, the question generation unit 2309, the identification unit 2310, the evaluation generation unit 2311, the calculation unit 2312, the missing item extraction unit 2313, the handover information generation unit 2314, and the setting unit 2315, and return an output. The artificial intelligence unit 2316 can analyze the input job seeker information and interview data and perform processes such as natural language processing, voice recognition, and image analysis, and functions as a core module that supports the artificial intelligence processing in each of these functional units.

[0111] The artificial intelligence unit 2316 is an AI (Artificial Intelligence) equipped with a learning model such as a language model, such as a Transformer (including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, GPT-4, and GPT-4o)), a Recurrent Neural Network (RNN), or a Transformer (including BERT (Bidirectional Encoder Representations from Transformers) and a Bidirectional and Auto-regressive Transformer (BART)), and may include a generative AI or an AI agent. The generative AI may be, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The learning model may be referred to as an artificial intelligence model, a machine learning model, or a trained model.

[0112] 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 2316 can apply the above algorithms as appropriate.

[0113] The artificial intelligence unit 2316 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of pairs of input data for learning and output data (correct answer data). In addition, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0114] The artificial intelligence unit 2316 may use a natural language model as its artificial intelligence, or may include a general-purpose natural language processing trained model such as a large-scale language model (LLM). A large-scale language model is a learning model that has previously trained a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). It can perform various language processing tasks by providing tasks, and can perform a wide range of natural language processing tasks, such as understanding sentence patterns and contexts, answering questions, and generating sentences, according to given prompts. Such a general-purpose learning model may include a language model that can handle various tasks without fine-tuning, using one-shot learning, few-shot learning, or the like. Furthermore, a general-purpose learning model can also handle various tasks using zero-shot learning. The artificial intelligence used in each functional unit of the control unit 23 may be a separate learning model, or a common general-purpose learning model. A large-scale language model is a type of generative AI, and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. The artificial intelligence unit 2316 may also include, as its artificial intelligence, a small-scale language model or a medium-scale language model that is smaller in scale than a large-scale language model. The small-scale language model and the medium-scale language model are natural language processing models trained based on less data than the large-scale language model. The artificial intelligence unit 2316 may also include any machine learning model, deep learning model, artificial intelligence model, etc. The artificial intelligence unit 2316 may be constructed in a system external to the information processing system 1. The artificial intelligence unit 2316 may also be an interactive type (which may be interpreted as a chat type or a conversation type) that alternately receives input for performing instructed output and generates and outputs information.

[0115] The learning model included in the artificial intelligence unit 2316 can undergo additional learning using techniques such as transfer learning or fine tuning. For example, the artificial intelligence unit 2316 learns whether the output content has been modified by a user or the like. That is, the artificial intelligence unit 2316 may perform additional learning and fine tuning based on modifications to the content output by the learning model. Furthermore, for example, each time new data is registered, the artificial intelligence unit 2316 may perform additional learning and fine tuning using the new data as new training data. This improves the accuracy of the information output from the learning model.

[0116] The learning model included in the artificial intelligence unit 2316 may be a learning model (distilled model) obtained by knowledge distillation using an original trained model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model (distilled model) are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby training the student model, which becomes the distilled model. Alternatively, the student model may be trained to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (a combination of input data and output data of the learning model). Compared to the original trained model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the trained model. Therefore, using a distilled model allows the information processing system 1 to reduce costs.

[0117] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a model such as a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a model such as a large-scale language model may be used as the learning model used in each functional unit, and once training data from that model has been accumulated, the distilled model obtained by knowledge distillation using that training data may be used as the learning model used in each functional unit.

[0118] Furthermore, the learning model used in each functional unit may be configured to output information generated in response to a prompt containing some instruction when that prompt is input.

[0119] The artificial intelligence unit 2316 may be an external component of the server 2. In this case, the external artificial intelligence unit 2316 may be provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server 2, receive requests to execute an artificial intelligence service, and return instructed output as a processing result to the server 2. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using a model such as a large-scale language model or a small-scale language model. The artificial intelligence service server may receive prompt inputs such as text, images, or voice, and generate and respond to the prompts. Furthermore, the information processing system 1 may be configured to use, as the artificial intelligence unit 2316, an AI agent provided by an external provider that provides AI agents. For example, the information processing system 1 may be configured to use an AI agent using an API provided by the external provider.

[0120] <Display> The display unit 331 of the job seeker terminal 3 displays a screen indicated by the screen data transmitted from the server 2. The display unit 431 of the recruiting party terminal 4 displays a screen indicated by the screen data transmitted from the server 2.

[0121] <Operation acquisition section> The operation acquisition unit 332 of the job seeker terminal 3 accepts operations by the job seeker using the job seeker terminal 3. When job seeker U1 operates the job seeker terminal 3 as a user to use the information processing system 1, he or she logs in by entering a user ID (Identification) and password. This associates the user ID with information generated or updated on the job seeker terminal 3, making it possible to identify which user the information pertains to. The operation acquisition unit 432 of the recruiter terminal 4 accepts operations by the recruiter using the recruiter terminal 4.

[0122] 3. Information processing flow This section describes the flow of an information processing method executed by the information processing system 1. As shown below, the information processing method includes steps executed by the information processing system. The program of this embodiment causes a computer to execute each step of the information processing system. Note that the order of the processes can be changed as appropriate, multiple processes may be executed simultaneously, or some processes may be omitted.

[0123] 3.1 Overview FIG. 7 is a diagram illustrating an outline of a process executed by the information processing system 1. In this process, first, as a first output step, the output unit 2301 displays an avatar and outputs a first utterance for breaking the ice as the avatar's speech (step S001). Next, as a second output step, the output unit 2301 outputs a second utterance for setting the avatar as the avatar's speech, and outputs a setting screen that displays selectable options for each of a plurality of avatar setting items (step S002). Next, the receiving unit 2302 receives a first response to the first utterance, an avatar selection in response to the second utterance, and a switching instruction (step S003). The avatar selection includes a second response or a selection of an option. Next, as a first display control step, the display control unit 2303 receives the avatar selection and then displays an avatar that has been changed in accordance with the avatar selection (step S004). Subsequently, as a second display control step, the display control unit 2303 switches to the interview mode and then displays the changed avatar (step S005).

[0124] In summary, an information processing system according to one embodiment includes at least one processor. In a first output step, the output unit 2301 displays an avatar and outputs a first utterance for breaking the ice as the avatar's speech. In a second output step, the output unit 2301 outputs a second utterance for setting the avatar as the avatar's speech, and outputs a setting screen that selectably displays options for each of a plurality of avatar setting items. The receiving unit 2302 receives a first response to the first utterance, an avatar selection in response to the second utterance, and a switching instruction. The avatar selection includes a second response or selection of an option. In a first display control step, the display control unit 2303 receives the avatar selection and then displays an avatar that has been changed in accordance with the avatar selection. In a second display control step, the display control unit 2303 switches to interview mode and then displays the changed avatar. In this manner, the user can start the interview at their own timing after having a conversation with the avatar who will be the interviewer before the interview begins. By having a conversation with the avatar who will be the interviewer in the interview mode before the interview begins, the psychological burden on the user can be alleviated.

[0125] 3.2 Specific examples An example of the flow of processing executed by the information processing system 1 will be described below with reference to FIGS. 8 to 11. This example of the flow may fall within the scope defined in the above-mentioned outline. The information processing may include any exception processing not shown. Exception processing includes the interruption of the information processing or the omission of each process. Selection or input performed in the information processing may be based on a user operation or may be performed automatically without relying on a user operation.

[0126] First Embodiment The first embodiment shows an example of the flow of information processing when the information processing system 1 controls a conference session for an online interview and performs a series of processes from preparing for the interview to conducting the interview, storing the interview data, and generating an evaluation result.

[0127] 8 is an activity diagram showing an example of the flow of information processing according to the first embodiment, which is executed by the information processing system 1. Below, an explanation will be given along with each activity in this activity diagram.

[0128] First, upon receiving an instruction to start a session from the operation acquisition unit 332 of the job seeker terminal 3, the session control unit 2307 starts a session in interview preparation mode (activity A101). Here, the instruction to start a session from the job seeker is given, for example, by the job seeker U1 accessing a URL for an interview issued to the job seeker U1 by the employer. Here, the dialogue management unit 2306 manages utterances and responses to the utterances in the interview preparation mode as a first history as a first dialogue management step. The first history includes job seeker information, etc. acquired during the conference session in the interview preparation mode.

[0129] Next, the display control unit 2303 causes the job seeker terminal 3 to display a screen for the interview preparation mode (activity A102). The display unit 331 of the job seeker terminal 3 displays the screen for the interview preparation mode based on the screen data transmitted from the server 2. The above-mentioned screen G1 is an example of a screen for the interview preparation mode.

[0130] Next, in the interview preparation mode, the utterance extraction unit 2305 extracts at least one utterance candidate from a plurality of utterance candidates prepared in advance (activity A103). The utterance candidate relates to any of greetings to the job seeker U1, confirmation of audio, confirmation of video, confirmation of communication status, operation guidance, or confirmation of the job seeker U1's past interview experiences. The utterance extraction unit 2305 extracts at least one utterance candidate from the plurality of utterance candidates based on the first history. In this manner, an utterance corresponding to the first history can be output to the job seeker U1.

[0131] Next, as a first output step, the output unit 2301 displays an avatar for the job seeker U1 and outputs a first utterance for breaking the ice as an utterance from the avatar (activity A104). As a first output step, the output unit 2301 outputs an utterance corresponding to the extracted utterance candidate to the job seeker U1. Note that at the stage of activity A104, an avatar corresponding to the initial setting is displayed.

[0132] Next, the receiving unit 2302 receives a first response to the first utterance (activity A105). The operation acquisition unit 332 of the job seeker terminal 3 receives the voice response or input operation by the job seeker U1, and the receiving unit 2302 receives the information received by the operation acquisition unit 332.

[0133] Next, the display control unit 2303 displays options for each of a plurality of setting items for the avatar in a selectable manner (activity A106). The setting items for the avatar include candidates for the AI ​​interviewer avatar, speech rate, etc. As a first display control step, in the interview preparation mode, the display control unit 2303 displays a plurality of avatar candidates with different age or gender attributes in a selectable manner as options for avatar settings.

[0134] Next, in a second output step, the output unit 2301 outputs a second utterance for setting the avatar as an utterance of the avatar (activity A107). In the second output step, the output unit 2301 outputs an utterance corresponding to the extracted utterance candidate to the job seeker U1.

[0135] Next, the receiving unit 2302 receives an avatar selection for the second utterance (activity A108). The avatar selection includes a selection of a second response or an option. The receiving unit 2302 receives a selection of one avatar candidate from among a plurality of avatar candidates. Note that the avatar setting includes a setting of the speed at which the avatar speaks, and the selection of the avatar setting includes a selection of the speed setting.

[0136] Next, as a first display control step, the display control unit 2303 receives the avatar selection and then displays the avatar that has been changed in accordance with the avatar selection (activity A109). As a first display control step, the display control unit 2303 displays the selected avatar candidate as the changed avatar.

[0137] Next, the output unit 2301 outputs a third utterance regarding confirmation of the setting status of the conference session (activity A110). As a third output step, the output unit 2301 outputs an utterance corresponding to the extracted utterance candidate to the job seeker U1. As a third output step, the output unit 2301 outputs a third utterance regarding confirmation of the setting status of the conference session to the job seeker U1 in the interview preparation mode. The setting status of the conference session includes at least one of an audio status, a video status, and a communication status. When the receiving unit 2302 receives the selection of the speed setting, the output unit 2301 outputs the utterance at a speed corresponding to the selected speed setting.

[0138] Next, the receiving unit 2302 receives a third response (voice input or setting change operation) (activity A111). The receiving unit 2302 receives a third response from the job seeker U1 regarding confirmation of the setting status. The receiving unit 2302 receives the third response by either a voice input in response to the third utterance or a change operation regarding the setting status.

[0139] Next, the determination unit 2304 determines whether the session status of the job seeker terminal 3 satisfies a predetermined condition (activity A112). Based on the third response received by the reception unit 2302, the determination unit 2304 determines whether the setting status of the conference session satisfies a predetermined condition. The predetermined conditions may include whether the video, audio, and communication statuses are normal, whether the necessary settings have been completed, etc. If the conditions are not satisfied, the process returns to activity A110 and continues checking the setting status.

[0140] Next, if it is determined that the predetermined conditions are met, the display control unit 2303 displays an object for accepting an instruction to start an interview (activity A113). As a first display control step, if it is determined that the predetermined conditions are met, the display control unit 2303 displays an object for accepting an instruction to switch to interview mode on the screen of the user's interview preparation mode.

[0141] Next, the reception unit 2302 receives a start instruction via the display unit 331 of the job seeker terminal 3 (activity A114).

[0142] Next, the dialogue management unit 2306 deletes the dialogue history (first history) in the interview preparation mode (activity A115). Note that the session control unit 2307 does not record the conference session in the interview preparation mode. On the other hand, for the dialogue with job seeker U1, the dialogue management unit 2306 retains the first history while the interview preparation mode continues as a first dialogue management step, and deletes the first history when switching to the interview mode. By informing job seeker U1 of this in advance, job seeker U1 can prepare for the interview in a state of psychological safety, in which the contents of the interview preparation mode will not affect the interview outcome.

[0143] Next, the session control unit 2307 switches the conference session to the interview mode (activity A116). As a second display control step, the display control unit 2303 switches to the interview mode and then displays the changed avatar.

[0144] Next, the session control unit 2307 switches to the interview mode and starts recording the conference session, and the dialogue management unit 2306 manages the recorded data (activity A117).

[0145] Next, the acquiring unit 2308 acquires the job seeker information of the user (activity A118). The job seeker information includes at least one of the user's occupation, work experience, skills, and career aspirations.

[0146] Next, the identifying unit 2310 identifies the desired occupation of the user based on the job seeker information or the second history (activity A119).

[0147] Next, the question generation unit 2309 generates a question based on the job seeker information or the second history and the first reference information (reference information for question generation) (activity A120). The first reference information (reference information for question generation) includes at least a correlation between the job seeker information or the second history and the question. The question includes at least one of a question about work experience, a question about past career, and a question about future career. When the desired job type of the job seeker U1 is identified, the question generation unit 2309 can generate a question according to the desired job type. The question according to the desired job type is, for example, a question about the abilities required for that job type.

[0148] Next, as a fourth output step, the output unit 2301 outputs questions about the user's job search to the user in the interview mode (activity A121).

[0149] Next, the receiving unit 2302 receives a fourth response to the question from the user (activity A122).

[0150] Next, as a second dialogue management step, the dialogue management unit 2306 manages the questions and the fourth responses to the questions in the interview mode as a second history (activity A123). The second history refers to information that records the correspondence between questions and their responses in chronological order in the interview mode. The second history is converted into text in real time and displayed on the screen in the interview mode.

[0151] Next, the determining unit 2304 determines whether a predetermined condition for determining whether to continue or end the interview is met (activity A124). If not, the process returns to A119, where a question for the job seeker U1 is generated and the dialogue continues.

[0152] Next, if it is determined that the predetermined condition is satisfied, the session control unit 2307 ends the conference session (activity A125).

[0153] Next, the dialogue management unit 2306 saves the interview data in the memory unit 22 (activity A126). The interview data includes video recording data in interview mode, audio data, information accepted in interview mode, etc. The second history displayed in interview mode is also part of the interview data.

[0154] Next, the evaluation generation unit 2311 generates an evaluation result of the user based on the job seeker information or the second history and the second reference information (reference information for generating evaluation result) (activity A127). Here, the second reference information (reference information for generating evaluation result) includes at least the correlation between the job seeker information or the second history and the evaluation result.

[0155] As a result, the processing from activity A101 to activity A127 is completed, and the series of processing flows in the conference session according to this embodiment ends.

[0156] In activity A112, the determination unit 2304 determines whether the setting state of the conference session satisfies a predetermined condition based on the third response. However, in the interview preparation mode, the determination unit 2304 determines whether the setting state of the first response, the second response, or the conference session satisfies a predetermined condition. The predetermined condition includes at least one of avatar settings, audio status, video status, and communication status. In the first display control step, the display control unit 2303 displays an object for accepting an instruction to switch to the interview mode on the user's interview preparation mode screen if it determines that the predetermined condition is satisfied. According to this aspect, if the predetermined condition is satisfied, an object for accepting an instruction to switch to the interview mode is displayed even before all of the first to third responses are made. This allows the job seeker U1 to start the interview without completing all of the first to third responses. Here, if a second response is not made, i.e., if no avatar is selected, the interview begins with an avatar with default settings. If a third response is not made, the interview begins with default settings.

[0157] <Second embodiment> The second embodiment shows an example of the flow of information processing when the information processing system 1 generates handover information for the next interview.

[0158] 9 is an activity diagram showing an example of the flow of information processing according to the second embodiment, which is executed by the information processing system 1. Below, an explanation will be given along with each activity in this activity diagram.

[0159] First, the acquisition unit 2308 acquires job information (activity A201).

[0160] Next, the setting unit 2315 sets a check list according to the job offer applied for by the job seeker or the organization corresponding to the job offer (activity A202). The check list may be selected from templates according to the job type, rank, recruitment department, etc., or may be automatically generated and supplemented by the artificial intelligence unit 2316 by analyzing the job offer information.

[0161] Next, as a third acquisition step, the acquisition unit 2308 acquires a confirmation list including items to be confirmed in the interview (activity A203).

[0162] Next, the acquiring unit 2308 acquires interview data relating to the interview conducted with the job seeker U1 (activity A204).

[0163] Next, the missing item extraction unit 2313 extracts, based on the interview data and the check list, items in the check list that are not included in the interview data as missing items (activity A205).

[0164] Next, the handover information generation unit 2314 generates handover information that includes the missing items as items to be confirmed in the next interview (activity A206). The handover information may include the candidate identifier, the job offer identifier, the details of the missing items, recommended questions, the location of the log to be referenced, etc.

[0165] As described above, the processing from activity A201 to activity A206 is completed, and the series of processing flows for generating handover information according to this embodiment is completed.

[0166] <Third embodiment> The third embodiment shows an example of the flow of information processing when the information processing system 1 calculates an evaluation of a job seeker and outputs it as a report.

[0167] 10 is an activity diagram showing an example of the flow of information processing according to the third embodiment, which is executed by the information processing system 1. Below, an explanation will be given along with each activity in this activity diagram.

[0168] First, the acquisition unit 2308 acquires job offer data (activity A301).

[0169] Next, the setting unit 2315 sets a target group to be used as the evaluation standard (activity A302). The target group may be a group of employees of the recruiter U2 or a group of users of the support system. The target group for calculating the first degree of suitability may be a group of employees of the recruiter U2, and the target group for calculating the relative evaluation and the second degree of suitability may be a group of users with a specific attribute from the user group of the support system. For example, if job seeker U1 desires a sales position, the group of users with a specific attribute is a group of users whose desired occupation is sales.

[0170] Next, as a second acquisition step, the acquisition unit 2308 acquires reference data including information about the evaluation of each member of the reference group (activity A303). Here, the information about the evaluation includes the evaluation or information from which the evaluation can be calculated.

[0171] If the reference group is a group of employees belonging to an organization (employer U2) corresponding to the job opening applied for by the job seeker, the acquisition unit 2308 acquires, as a second acquisition step, reference data including information on the evaluation of each employee of the employer U2. If the reference group is a group of users of a support system related to recruitment support, job search support, or career support, the acquisition unit 2308 acquires, as a second acquisition step, reference data including information on the evaluation of each user of the system.

[0172] On the other hand, the acquiring unit 2308 acquires job seeker data of the job seeker U1 as a first acquisition step (activity A304). The job seeker data includes, for example, interview data, aptitude test data, career information, etc. of the recruiter U2.

[0173] Next, the calculation unit 2312 calculates the job seeker's evaluation based on the job seeker data, the standard data, and the evaluation calculation reference information. The evaluation calculation reference information includes at least the correlation between the job seeker data, the standard data, and the evaluation. The evaluation includes information indicating the job seeker's relative relationship to the group. In this manner, the relative evaluation of the job seeker in the standard group can be calculated (activity A305). When the target group for calculating the evaluation is a user group with a specific attribute of the support system, the calculation unit 2312 calculates an evaluation (relative evaluation) indicating the relative position of the job seeker U1 in the user group. The relative evaluation is the deviation score or ranking of the job seeker in the group.

[0174] Furthermore, the calculation unit 2312 can calculate multiple evaluations corresponding to multiple evaluation elements of the job seeker based on the job seeker data, the standard data, and the evaluation calculation reference information (activity A306). The evaluation elements are the elements that are the subject of evaluation among the characteristic elements identified by the identification unit 2310. The evaluation elements include at least one of leadership, communication ability, problem-solving ability, and logical thinking ability.

[0175] Next, the calculation unit 2312 calculates an evaluation including a second suitability indicating the degree to which the job seeker suits the group, calculated based on the evaluation corresponding to each evaluation element of the job seeker, the standard data, and the second reference information for calculating suitability (activity A307). The second reference information for calculating suitability includes at least the correlation between the evaluation, the standard data, and the second suitability. The calculation unit 2312 calculates the similarity between the evaluation corresponding to each evaluation element of the recruiter U2 and the standard data of the group being referenced.

[0176] The calculation unit 2312 also calculates, as an evaluation, a first degree of fit indicating the degree to which the job seeker fits into the group's organization (activity A308). The first degree of fit is calculated based on the job seeker data, the reference data, and reference information for calculating the first degree of fit, and the reference information for calculating the first degree of fit includes at least the correlation between the job seeker data, the reference data, and the first degree of fit. In this manner, the job seeker's degree of fit with the corporate culture can be calculated. Note that the calculation processes for each evaluation (activities A305, A306, A308) by the calculation unit 2312 may be performed in any order or in parallel. This can improve the flexibility and efficiency of the process.

[0177] Next, the determining unit 2304 determines whether the evaluation satisfies a predetermined condition (activity A309). The determining unit 2304 determines pass / fail based on the first degree of conformance, the second degree of conformance, the relative evaluation, etc., in light of the predetermined condition.

[0178] Next, the acquisition unit 2308 acquires handover information including information on missing items in the AI ​​interview (activity A310). The handover information is, for example, information generated in activity A206.

[0179] Next, the evaluation generation unit 2311 generates an evaluation report based on the evaluation and the reference information for evaluation report generation (activity A311). The evaluation generation unit 2311 generates an evaluation report based on the evaluation (e.g., evaluation score, first degree of conformance, second degree of conformance) calculated by the calculation unit 2312 and the evaluation report reference information. The evaluation report includes at least one of visual information such as a table or graph including the evaluation and a comment corresponding to the evaluation, and the reference information for evaluation report generation includes at least the correlation between the evaluation and the evaluation report. The evaluation generation unit 2311 can generate an evaluation report including information related to career information and handover information.

[0180] The evaluation generating unit 2311 may generate an evaluation report including the result of the determination made by the determining unit 2304 in activity A309. That is, in the evaluation generating step, if it is determined that a predetermined condition is satisfied, the evaluation generating unit 2311 outputs an evaluation report that further includes a symbol or object indicating that the evaluation is successful. If it is determined that the predetermined condition is not satisfied, the evaluation generating unit 2311 generates an evaluation report that further includes a symbol or object indicating that the evaluation is unsuccessful.

[0181] Next, as a fifth output step, the output unit 2301 outputs the evaluation report to the recruiter in charge of hiring the job seeker (activity A312). For example, the recruiter in charge of hiring job seeker U1 is recruiter U2.

[0182] Next, the reception unit 2302 receives manual evaluations and comments from the hiring manager, and stores them in the dialogue management unit 2306 or the evaluation generation unit 2311 (activity A313).

[0183] Next, the evaluation generation unit 2311 integrates the AI ​​evaluation and the manual evaluation and outputs a comprehensive evaluation (activity A314).

[0184] As a result, the processing from activity A301 to activity A314 is completed, and the series of processing flows for generating an evaluation report according to this embodiment ends.

[0185] 11 is a diagram showing an example of an evaluation report, evaluation report R1. Evaluation report R1 includes areas R10, R11, R12, R13, R14, R15, R16, R17, R18, and R19. Area R12 includes areas R121, R122, and R123, area R13 includes area R131, area R15 includes area R151, area R16 includes area R161 (grade display), and area R19 includes areas R191 and R192.

[0186] Area R10 is an area that displays the report header (addressee, job seeker U1 name, report title, etc.). Area R11 is an area that displays a summary of the interview content. The evaluation generation unit 2311 may input the interview data into the artificial intelligence unit 2316, generate a summary, and insert it into area R11.

[0187] Area R12 is an area that displays an overview of the evaluation results for job seeker U1. The evaluation generation unit 2311 generates information about the overview of the evaluation results based on the evaluation calculated by the calculation unit 2312 and the reference information for generating evaluation results. The information about the overview of the evaluation results includes, for example, visual information showing the evaluation for each evaluation element, an evaluation table for each evaluation element, and comments on the evaluation results. Area R121 is an area that displays a radar diagram (an example of visual information) showing the evaluations of elements A to E. The radar diagram shows the job seeker U1's score for each element A to E with a solid line and the average score of the target group with a dotted line. Area R122 is an area that displays a table showing the evaluation results. Area R122 displays a table listing the job seeker U1's score, the average score of the group, and the job seeker U1's deviation score for each element A to E. Area R123 is an area that displays observations and comments about the evaluation results, and displays comments generated based on the evaluation results.

[0188] Area R13 is an area that displays the final evaluation of job seeker U1. In the evaluation report output in activity A312, this area is left blank, and in activity A313, this area is inserted with information corresponding to the input of employer U2 received by reception unit 2302.

[0189] Area R14 is an area that displays the interview data and links to data related to the interview data. The evaluation generation unit 2311 inserts a reference link to the interview data stored in the storage unit 22 into this area.

[0190] Area R15 is an area for displaying information related to the degree of compatibility with organizational culture (first degree of compatibility). The first degree of compatibility calculated by the calculation unit 2312 and comments related to the first degree of compatibility are displayed. Area R151 is an area for displaying the grade of the degree of compatibility with organizational culture, and displays the calculation result as a graded evaluation (for example, A to D).

[0191] Area R16 is an area that displays the compatibility with the target job type, and displays the second compatibility calculated by the calculation unit 2312 and comments regarding the second compatibility. Area R161 is an area that displays a grade regarding the relative strengths and weaknesses of job seeker U1 compared to users of the target job type among system users, and displays a grade based on a deviation value or percentile.

[0192] Area R17 is an area that displays the overall evaluation by AI (e.g., pass) and recommended actions (such as proceeding to the next process). The pass / fail judgment result and the action proposal made by the judgment unit 2304 are displayed.

[0193] Area R18 is an area for displaying handover information (items that have not been confirmed this time but should be confirmed at the next interview). The handover information generated by the handover information generation unit 2314 is displayed.

[0194] Area R19 is an area that displays an overview of job seeker information for job seeker U1. Area R191 is an area that displays a summary of career information, and displays basic information and job content of job seeker U1. Area R192 is an area that displays a summary of aptitude test information, and displays the analysis results of aptitude test data.

[0195] In the information processing system according to this embodiment, an AI interview is conducted, an evaluation score is calculated based on the results, and an evaluation report is output. However, the present invention is not limited to this. The entire process from calculating the evaluation score to outputting the evaluation report may be performed based not only on the results of the AI ​​interview, but also on interview data obtained through online or face-to-face interviews. In other words, the interview data includes data obtained from interviews conducted by either an AI interview, an online interview, or a face-to-face interview. The information processing system according to the present invention has a flexible configuration capable of integrating interview data obtained from multiple interview formats and generating evaluation scores and evaluation reports.

[0196] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be modified as appropriate within the scope of the technical idea of ​​the invention.

[0197] 4. Effect In this manner, the AI ​​interviewer conducts an icebreaker (such as a speech from the AI) before the AI ​​interview, ensuring psychological safety for the job seeker U1 in interviewing with the AI. Furthermore, since the avatar's speech speed and the conference session settings can be set, the job seeker U1 can be interviewed at a speech speed and settings that are optimal for the job seeker U1. Therefore, an interview can be conducted that allows the job seeker U1 to fully demonstrate their abilities.

[0198] Furthermore, this method allows for a multifaceted evaluation of job seeker U1 using their interview data and aptitude test data. By calculating their relative evaluation within the target group, job seeker U1's relative position can be objectively grasped. By calculating their compatibility with the employer's organizational culture, mismatches can be reduced. An evaluation report is generated that summarizes job seeker U1's relative evaluation (standard deviation score and ranking), compatibility with hiring criteria, and compatibility with the corporate culture, making hiring decisions easier. This reduces variability due to interviewer subjectivity and semi-automates the process of comparing multiple job seekers U1, making pass / fail decisions, and creating handover instructions for the next interview, thereby improving the speed of the selection process while maintaining evaluation quality.

[0199] 5.Other In the above embodiment, the server 2 performs various storage and control functions. However, multiple external devices may be used instead of the server 2. That is, various information and programs may be distributed and stored in multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 2316 may be an external component of the server 2. In this case, the external artificial intelligence unit 2316 is provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server 2, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server 2. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using a large-scale language model. The artificial intelligence service server receives inputs of prompts such as text, images, and voice, and generates and responds to the prompts.

[0200] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes steps executed by the information processing system 1. The program causes a computer to execute the steps of the information processing system 1.

[0201] It may be provided in the following manner.

[0202] (1) An information processing system, comprising at least one processor, configured to execute the following steps by reading a program: a session control step of starting a conference session in an interview preparation mode; and, upon receiving an instruction to switch to the interview mode from a user, switching the conference session to the interview mode and starting an interview with an avatar selected in the interview preparation mode as an interviewer; and, in the interview preparation mode, a first output step of displaying the avatar and outputting a first utterance for ice-breaking as an utterance of the avatar; and a second output step of outputting a first utterance for ice-breaking as an utterance of the avatar. an avatar selection step of receiving a first response to the first utterance, an avatar selection step of receiving an avatar from the user, and an avatar selection step of displaying the avatar after the first utterance has been received; an avatar selection step of receiving a second utterance to set the avatar and an avatar selection setting screen that displays selectable options for each of a plurality of setting items for the avatar; an avatar selection step of receiving a second response to the avatar, an avatar selection step of displaying the avatar after the second utterance has been received; an avatar selection step of displaying the avatar after the second utterance has been received;

[0203] In this manner, the user can start the interview at their own timing after having a conversation with the avatar who will be the interviewer before the interview begins. By having a conversation with the avatar who will be the interviewer in the interview mode before the interview begins, the psychological burden on the user can be alleviated.

[0204] (2) In the information processing system described in (1) above, further, in the judgment step, in the interview preparation mode, it is determined whether the first response or the second response or the setting status of the conference session satisfies predetermined conditions, the predetermined conditions including at least one of avatar settings, audio status, video status, and communication status, and in the first display control step, if it is determined that the predetermined conditions are satisfied, an object for accepting the instruction to switch to the interview mode is displayed on the screen of the user's interview preparation mode.

[0205] In this manner, when the settings of audio, video, communication status, etc. in the interview preparation mode satisfy predetermined conditions, an instruction to switch to the interview mode can be accepted.

[0206] (3) In the information processing system described in (1) or (2) above, further, in a third output step, in the interview preparation mode, a third utterance regarding confirmation of the setting status of the conference session is output to the user, wherein the setting status of the conference session includes at least one of an audio status, a video status, and a communication status, and in the reception step, a third response from the user regarding confirmation of the setting status is received.

[0207] In this manner, the interview can begin after checking settings such as audio, video, and communication status in the interview preparation mode. Audio, video, and communication status are important in AI interviews, and by checking these in advance, the user can approach the interview with peace of mind.

[0208] (4) In the information processing system described in (3) above, the reception step receives the third response by either voice input in response to the third utterance or a change operation regarding the setting state, and further, in the determination step, based on the third response received in the reception step, it is determined whether the setting state of the conference session satisfies a predetermined condition, and in the first display control step, if it is determined that the predetermined condition is satisfied, an object for accepting the instruction to switch to the interview mode is displayed on the screen of the user's interview preparation mode.

[0209] (5) In the information processing system described in any one of (1) to (4) above, the avatar setting includes setting the speed of the speech by the avatar, the selection of the avatar setting includes selecting the speed setting, and when the selection of the speed setting is accepted in the acceptance step, the speech is output at the speed corresponding to the selected speed setting in all output steps.

[0210] In this manner, the speech rate can be adjusted to a level that is easy for the user to respond to.

[0211] (6) In the information processing system described in any one of (1) to (5) above, in the first display control step, in the interview preparation mode, a plurality of avatar candidates having different age or gender attributes are displayed as selectable options for avatar settings, and in the reception step, a selection of one of the plurality of avatar candidates is accepted, and in the first display control step and the second display control step, the selected avatar candidate is displayed as the changed avatar.

[0212] (7) In the information processing system described in any one of (1) to (6) above, further, in the utterance extraction step, at least one utterance candidate is extracted from a plurality of utterance candidates prepared in advance in the interview preparation mode, wherein the utterance candidate is related to any of greetings to the user, confirmation of audio, confirmation of video, confirmation of communication status, operation guidance, or confirmation of the user's previous interview experience, and in the first output step and the second output step, the utterance corresponding to the extracted utterance candidate is output to the user.

[0213] (8) In the information processing system described in (7) above, further, in the first dialogue management step, the utterances and responses to the utterances in the interview preparation mode are managed as a first history, in the utterance extraction step, at least one utterance candidate is extracted from the multiple utterance candidates based on the first history, and in the first output step and the second output step, the utterance corresponding to the extracted utterance candidate is output.

[0214] In this manner, it is possible to output to the user an utterance that corresponds to the first history.

[0215] (9) In the information processing system described in (8) above, the first dialogue management step maintains the first history while the interview preparation mode continues, and deletes the first history when switching to the interview mode, and the session control step does not record the conference session in the interview preparation mode, and starts recording the conference session after switching to the interview mode.

[0216] In this manner, the content of the dialogue in the interview preparation mode does not affect the interview questions or the interview evaluation, allowing the user to prepare for the interview in a state of psychological safety.

[0217] (10) In the information processing system described in any one of (1) to (9) above, further, in the acquisition step, job seeker information of the user is acquired, wherein the job seeker information includes at least one of the user's occupation, work experience, skills, or career aspirations; further, in the fourth output step, questions regarding the user's job search activities are output to the user in the interview mode; in the reception step, a fourth response to the question is received from the user; and further, in the second dialogue management step, the question and the fourth response to the question in the interview mode are managed as a second history.

[0218] (11) In the information processing system described in (10) above, the system further includes, in the question generation step, generating the question based on the job seeker information or the second history and first reference information, wherein the first reference information includes at least a correlation between the job seeker information or the second history and the question, and in the fourth output step, outputting the generated question to the user.

[0219] (12) In the information processing system described in (11) above, the system further includes, in the identification step, identifying the user's desired occupation based on the job seeker information or the second history, and in the question generation step, generating the question according to the desired occupation.

[0220] (13) In the information processing system described in (12) above, the question corresponding to the desired job type is a question about the abilities required for that job type.

[0221] (14) In the information processing system described in any one of (10) to (13) above, the questions include at least one of questions about work experience, questions about past careers, and questions about future careers.

[0222] (15) In the information processing system described in any one of (10) to (14) above, the evaluation generation step further generates an evaluation result of the user based on the job seeker information or the second history and second reference information, wherein the second reference information includes at least a correlation between the job seeker information or the second history and the evaluation result.

[0223] (16) In the information processing system described in any one of (10) to (15) above, the first display control step and the second display control step display a screen of the conference session, and in the interview preparation mode, the screen includes the avatar and first text information in which the utterance and the response to the utterance have been converted into text, and in the interview mode, the screen includes the avatar and second text information in which the question and the fourth response to the question have been converted into text.

[0224] (17) The information processing system according to any one of (1) to (16) above, further comprising: a server having the processor; and a terminal that can access the server.

[0225] (18) An information processing method, comprising steps executed by the information processing system according to any one of (1) to (16) above.

[0226] (19) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (16) above. Of course, this is not the case.

[0227] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0228] 1: Information processing system 2: Server 20: Communication bus 21: Communications Department 22: Storage section 23: Control section 2301: Output section 2302: Reception 2303: Display control unit 2304: Judgment section 2305: Speech extraction unit 2306: Dialogue Management Department 2307: Session control section 2308: Acquisition Department 2309:Question generation section 2310: Specific part 2311: Evaluation Generation Unit 2312: Calculation section 2313: Missing item extraction part 2314: Handover information generation unit 2315: Settings section 2316: Artificial Intelligence Department 3: Job seeker terminal 30: Communication bus 31: Communications Department 32: Storage section 33: Control section 331: Display section 332: Operation acquisition section 34:Display section 35: Input section 4: Recruiter terminal 40: Communication bus 41: Communications Department 42: Storage section 43: Control section 431: Display section 432 :Operation acquisition part 44: Display section 45: Input section G1: Screen G11 :Area G12 :Area G13 :Area G14 :Area G15 :Area G151 :Area G152 :Area G16 :Area G161 :Area G162 :Area G163 :Area G17 :Area G18: Objects G2: Screen G21 :Area G22 :Area G23 :Area G24 :Area G25 :Area G26 :Object R1: Evaluation Report R10: area R11 :Region R12: area R121 :Region R122 :Region R123 :Region R13: area R131 :Region R14: area R15: area R151 :Region R16: area R161 :Region R17 :Region R18: area R19 :Region R191 :Region R192 :Region

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 session control step, the conference session is started in an interview preparation mode, and when an instruction to switch to the interview mode is received from the user, the conference session is switched to the interview mode, and an interview is started with the avatar selected in the interview preparation mode as the interviewer; In the interview preparation mode, In the first output step, the avatar is displayed, and a first utterance for breaking the ice is output as an utterance of the avatar, wherein the first utterance is a predetermined utterance corresponding to a candidate utterance prepared in advance; In the second output step, a second utterance for setting the avatar is output as the avatar's utterance, and a setting screen is output that displays options for each of a plurality of setting items of the avatar in a selectable manner, wherein the second utterance is a predetermined utterance corresponding to a prepared utterance candidate; the receiving step receives a first response to the first utterance, an avatar selection in response to the second utterance, and the switching instruction, wherein the avatar selection includes a second response or a selection of the option; In the first display control step, after accepting the avatar selection, the avatar is changed in accordance with the avatar selection and displayed; In the second display control step, after switching to the interview mode, the information processing system displays the changed avatar.

2. 2. The information processing system according to claim 1, Furthermore, in the determination step, in the interview preparation mode, it is determined whether or not the first response, the second response, or a setting state of the conference session satisfies a predetermined condition, and the predetermined condition includes at least one of an avatar setting, an audio state, an image state, and a communication state; In the first display control step, when it is determined that the specified condition is met, the system displays an object on the user's interview preparation mode screen for accepting the instruction to switch to the interview mode.

3. 2. The information processing system according to claim 1, Furthermore, in the third output step, in the interview preparation mode, a third utterance regarding confirmation of a setting status of the conference session is output to the user, wherein the setting status of the conference session includes at least one of an audio status, a video status, and a communication status; In the receiving step, the system receives a third response from the user regarding confirmation of the setting state.

4. 4. The information processing system according to claim 3, In the receiving step, the third response is received by either a voice input in response to the third utterance or a change operation related to the setting state; Furthermore, in the determining step, it is determined whether or not the setting state of the conference session satisfies a predetermined condition based on the third response received in the receiving step; In the first display control step, when it is determined that the specified condition is met, the system displays an object on the user's interview preparation mode screen for accepting the instruction to switch to the interview mode.

5. 2. The information processing system according to claim 1, the avatar settings include setting a speed of the speech by the avatar; selecting the avatar setting includes selecting the speed setting; When the selection of the speed setting is accepted in the accepting step, the system outputs the speech at the speed corresponding to the selected speed setting in all output steps.

6. 2. The information processing system according to claim 1, In the first display control step, in the interview preparation mode, a plurality of avatar candidates having different age attributes or gender attributes are displayed in a selectable manner as the options for avatar setting; In the receiving step, a selection of one of the plurality of avatar candidates is received; In the first display control step and the second display control step, the selected avatar candidate is displayed as the changed avatar.

7. 2. The information processing system according to claim 1, Furthermore, in the utterance extraction step, in the interview preparation mode, at least one utterance candidate is extracted from a plurality of utterance candidates prepared in advance, wherein the utterance candidate is related to any one of greetings to the user, confirmation of audio, confirmation of video, confirmation of communication status, operation guidance, or confirmation of the user's past interview experiences; In the first output step and the second output step, the utterance corresponding to the extracted utterance candidate is output to the user.

8. 8. The information processing system according to claim 7, Furthermore, in the first dialogue management step, the utterances and responses to the utterances in the interview preparation mode are managed as a first history; In the utterance extraction step, at least one utterance candidate is extracted from the plurality of utterance candidates based on the first history; In the first output step and the second output step, the utterance corresponding to the extracted utterance candidate is output.

9. 9. The information processing system according to claim 8, In the first dialogue management step, maintaining the first history while the interview preparation mode continues; When switching to the interview mode, the first history is deleted; The session control step includes: In the interview preparation mode, no recording of the conference session is performed; After switching to the interview mode, the system begins recording the conference session.

10. 2. The information processing system according to claim 1, Furthermore, in the obtaining step, job seeker information of the user is obtained, wherein the job seeker information includes at least one of the user's occupation, work experience, skills, or career aspirations; Furthermore, in the question generation step, a question is generated based on the job seeker information or the second history and first reference information, wherein the first reference information includes at least one of rule-based information such as a database or a lookup table, a trained model, a large-scale language model, or generative AI, which includes at least a correlation between the job seeker information or the second history and the question, and in the question generation step, the question is generated using at least one of the first reference information; Furthermore, in a fourth output step, the questions regarding the user's job search activities are output to the user in the interview mode; the receiving step includes receiving a fourth response to the question from the user; Furthermore, in the second dialogue management step, the system manages the question and the fourth response to the question in the interview mode as the second history.

11. 11. The information processing system according to claim 10, Furthermore, in the identifying step, a desired occupation of the user is identified based on the job seeker information or the second history, In the question generating step, the system generates the question according to the desired job type.

12. 12. The information processing system according to claim 11, The system wherein the questions according to the desired job type are questions about the abilities required for that job type.

13. 11. The information processing system according to claim 10, The system, wherein the questions include at least one of questions about work experience, questions about past careers, and questions about future careers.

14. 11. The information processing system according to claim 10, Furthermore, in the evaluation generation step, an evaluation result of the user is generated based on the job seeker information or the second history and second reference information, wherein the second reference information includes at least a correlation between the job seeker information or the second history and the evaluation result.

15. 11. The information processing system according to claim 10, In the first display control step and the second display control step, a screen of the conference session is displayed, and the screen includes: In the interview preparation mode, the avatar and first text information obtained by converting the utterance and a response to the utterance into text are included; In the interview mode, the system includes the avatar and second text information that is a text version of the question and the fourth response to the question.

16. 2. The information processing system according to claim 1, a server having the processor; a terminal that can access the server.

17. 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 15.

18. 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 15.

Images