Terminal device, information processing apparatus, simulation system, simulation method, and program

Abstract

To improve interviewing capability in an interview intended to solve a problem.SOLUTION: A terminal device is provided with: an acquisition unit that, in order to solve a problem set for a first character to be interviewed, acquires a response to the first character input by a user; and a presentation unit that presents, to the user, a response from the first character generated by a generation unit according to the response acquired by the acquisition unit.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present invention relates to a technique for conducting a simulation of an interview. [Background technology]

[0002] In school education, three-way conferences are held between teachers, students, and parents. Three-way conferences are important for teachers and parents to share information about the student's school life and home life, while checking whether the student has any issues (problems or worries). In three-way conferences, teachers must identify the issues the student has and engage in dialogue with the student and parent to solve those issues. Not only do students have a wide range of issues, but each student has a different personality, so teachers must respond flexibly to the students and parents. However, for teachers with little experience, their ability to conduct interviews (hereinafter referred to as "interviewing ability") is insufficient, so it is not easy to communicate smoothly with students and parents and conduct interviews, which places a heavy burden on teachers. In order to solve students' issues through three-way conferences, it is necessary for teachers to have many interviews and improve their interviewing ability. On the other hand, the reality is that teachers have no choice but to practice with actual students and parents in order to improve their interviewing ability.

[0003] Therefore, Patent Document 1 proposes an interview support device that simulates an interview as a technology for improving interview skills without actually conducting an interview. Specifically, the technology of Patent Document 1 allows a user (e.g., a superior) to practice an interview with an avatar of a virtual interviewee (e.g., a subordinate). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2023-109464 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology of Patent Document 1 cannot improve interview skills to deal with various interviewees who have various problems. In consideration of the above circumstances, the present invention aims to improve interview skills in interviews aimed at solving problems. [Means for solving the problem]

[0006] [1] The terminal device of the present invention is a device for executing an interview simulation, and includes an acquisition unit that acquires a response input by a user to a first character that is the subject of the interview in order to solve a problem set for the first character, and a presentation unit that presents to the user a reaction of the first character that is generated by a generation unit in response to the response acquired by the acquisition unit.

[0007] [2] The terminal device of [1], wherein the acquisition unit further acquires a response input by the user in response to the reaction presented by the presentation unit, and the presentation unit presents to the user the reaction generated by the generation unit each time the response is input by the user.

[0008] [3] The terminal device of [1] or [2], wherein the presentation unit presents to the user an evaluation generated based on predetermined evaluation criteria for the response input by the user.

[0009] [4] A terminal device according to any one of [1] to [3], wherein the task is one of a plurality of tasks prepared in advance.

[0010] [5] The first character is a character of a school student, and the acquisition unit acquires the response entered by the user from the perspective of a teacher of the student.

[0011] [6] A terminal device according to any one of [1] to [5], wherein the presentation unit presents to the user a reaction of a second character related to the first character, the reaction being generated by the generation unit in response to the response acquired by the acquisition unit.

[0012] [7] A terminal device according to any one of [1] to [6], wherein attributes of the first character are set, and the generation unit sets the task to the first character according to the attributes.

[0013] [8] A terminal device according to any one of [1] to [7], wherein a task corresponding to one of a plurality of themes prepared in advance is set for the first character.

[0014] [9] A terminal device according to any one of [1] to [8], wherein the reaction generated by the generation unit changes depending on a difficulty level set for the simulation.

[0015]

[10] The generation unit is a terminal device according to any one of [1] to [9], which is an interactive large-scale language model.

[0016]

[11] The terminal device of

[10] , wherein when the acquisition unit receives an instruction to start the simulation from the user, the acquisition unit transmits a prompt to start the simulation to the generation unit.

[0017]

[12] The terminal device of

[11] , wherein the prompt includes information instructing the generation unit to set a problem faced by the first character, information instructing the generation unit to control the first character, and information indicating the role of the user.

[0018]

[13] A terminal device according to any one of [1] to

[12] , wherein the generation unit generates an episode including the task, and the presentation unit presents the episode to the user.

[0019]

[14] An information processing device for executing an interview simulation, comprising: a generation unit that generates a reaction of a first character in response to a response input by a user to the first character in order to solve a problem set for the first character who is the subject of the interview.

[0020]

[15] A system for performing a simulation of an interview, comprising: an acquisition unit that acquires a response input by a user to a first character who is the subject of the interview in order to solve a task set for the first character; a generation unit that generates a reaction of the first character in accordance with the response acquired by the acquisition unit; and a presentation unit that presents the reaction generated by the generation unit to the user.

[0021]

[16] A method for performing a simulation of an interview, the simulation method being realized by a computer system that acquires responses input by a user to a first character that is the subject of the interview in order to solve a task set for the first character, and presents to the user a reaction of the first character that is generated in response to the acquired responses.

[0022]

[17] A program for executing a simulation of an interview, the program causing a computer system to function as an acquisition unit that acquires a response input by a user to a first character that is the subject of the interview in order to solve a problem set for the first character, and a presentation unit that presents to the user a reaction of the first character that is generated in response to the response acquired by the acquisition unit. Effect of the Invention

[0023] According to the terminal device, information processing device, simulation system, simulation method, and program of the present invention, it is possible to improve interview skills in interviews aimed at solving problems. [Brief description of the drawings]

[0024] [Figure 1] 1 is a block diagram illustrating a configuration of a simulation system according to a first embodiment. [Diagram 2] 1 is a block diagram illustrating a configuration of an information processing device according to a first embodiment. [Diagram 3] FIG. 1 is a schematic diagram showing the relationship between attributes, themes, and issues. [Figure 4] 2 is a block diagram illustrating a configuration of a terminal device according to the first embodiment. FIG. [Diagram 5] 2 is a block diagram illustrating a functional configuration of a control device in a terminal device according to the first embodiment. FIG. [Figure 6] 4 is a flowchart showing a specific procedure of an interview process executed by the simulation system according to the first embodiment. [Figure 7] 4 is an example of an image displayed on a display device of the terminal device according to the first embodiment. [Figure 8] 13 is an example of an image displayed on a display device of the terminal device according to the second embodiment. [Figure 9] 13 is a flowchart showing a specific procedure of an interview process executed by the simulation system according to the third embodiment. [Figure 10] 13 is an example of an image displayed on a display device of the terminal device according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] First Embodiment 1 is a block diagram illustrating the configuration of a simulation system 100 in the first embodiment. The simulation system 100 is a system capable of simulating an interview, and is used to improve the interview ability (interview ability) of a user U. Specifically, the simulation system 100 executes a simulation (hereinafter referred to as "interview simulation") that assumes an interview with a first character to which a task has been set.

[0026] The user U in the first embodiment is, for example, a school teacher (homeroom teacher) who is expected to have an interview with a student. The first character in the first embodiment is a student character. Therefore, the user U can practice an interview with a student who has a problem. The simulation system 100 makes it possible to perform various interview simulations for the purpose of, for example, life guidance, student guidance, and educational counseling.

[0027] The simulation system 100 simulates an interview with a student who has a problem. In the first embodiment, a one-on-one interview between a first character and a user U is simulated. The user U solves the problem (problem or worry) of the first character by having a dialogue with the first character in the interview.

[0028] The simulation system 100 of the first embodiment includes a terminal device 10 and an information processing device 20. The terminal device 10 and the information processing device 20 can communicate with each other via a communication network 300 such as the Internet. The information processing device 20 is realized by, for example, a server system. On the other hand, the terminal device 10 is realized by, for example, a portable information device such as a smartphone or a tablet terminal, or a portable or stationary information device such as a personal computer.

[0029] [Information processing device 20] The information processing device 20 is a device that controls a first character who is the subject of the interview. That is, the information processing device 20 performs the role of the first character. As described above, the first character in the first embodiment is a student character, and a task is set for the first character. The details of the task will be described later.

[0030] 2 is a block diagram illustrating an example of the configuration of the information processing device 20. Specifically, the information processing device 20 includes a control device 21, a storage device 22, and a communication device .

[0031] The control device 21 is a single or multiple processors that control the operation of the information processing device 20. Specifically, the control device 21 is configured by one or more types of processors, such as a central processing unit (CPU), a graphics processing unit (GPU), a sound processing unit (SPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).

[0032] The storage device 22 is one or more memories that store programs executed by the control device 21 and various data used by the control device 21. For example, a known recording medium such as a semiconductor recording medium or a magnetic recording medium, or a combination of multiple types of recording media, is used as the storage device 22. For example, a portable recording medium that is detachable from the information processing device 20, or a recording medium that the control device 21 can access via the communication network 300 (for example, cloud storage) may be used as the storage device 22.

[0033] The communication device 23 is a communication device that communicates with the terminal device 10 via the communication network 300. Note that the communication device 23, which is separate from the information processing device 20, may be connected to the information processing device 20 by wire or wirelessly.

[0034] The control device 21 executes a program stored in the storage device 22 to realize a function (a generation unit 211) for executing an interview simulation.

[0035] First, the generation unit 211 sets a task for the first character (student). Specifically, a task is set for the first character under a predetermined theme (hereinafter referred to as a "set theme").

[0036] The generation unit 211 of the first embodiment further generates an episode (a simple story) including a task set for the first character. The episode is an episode including a task that the student has, and is assumed to be a sentence of about 200 to 1000 characters, for example.

[0037] The set theme is, for example, any one of a plurality of themes prepared in advance. The themes are classifications that represent the types (genres) of tasks, and tasks of the same type belong to a common theme. The set theme in the first embodiment is any one of the plurality of themes arbitrarily selected by the generation unit 211. For example, any one of the plurality of themes randomly selected by the generation unit 211 is set as the set theme. However, the theme selected by the user U from the plurality of themes may also be set as the set theme.

[0038] In the first embodiment, an attribute of a student (first character) is set. The attribute of a student is, for example, the type of school to which the student belongs (for example, elementary school, middle school, or high school). Then, the generation unit 211 sets an assignment corresponding to the set theme and the attribute to the first character, and generates an episode including the assignment. In the first embodiment, the type of school is specified by the user U. However, a configuration in which the generation unit 211 sets an arbitrary type to the first character is also exemplified.

[0039] 3 is a schematic diagram showing the relationship between attributes, themes, and tasks. As illustrated in FIG. 3, for each of a plurality of attributes, a plurality of themes and a task corresponding to each of the themes are associated. Then, one of the plurality of themes in the attribute designated by the user U is selected as a set theme, and a task corresponding to the set theme is set for the first character. As can be understood from the above description, in the first embodiment, one of a plurality of tasks (a plurality of tasks prepared for each of a plurality of attributes) prepared in advance is set for the first character.

[0040] Secondly, the generation unit 211 controls a first character having the set task. Specifically, the generation unit 211 controls the first character by generating the words and actions (utterances, attitudes, facial expressions, etc.) of the first character. The generation unit 211 in the first embodiment generates a reaction of the first character in response to a response input by the user U to the first character (student) to solve the task.

[0041] In the first embodiment, a case is illustrated in which the response input by the user U is a statement (hereinafter referred to as an "input statement"), and the reaction of the first character generated in response to the response is also a statement (hereinafter referred to as a "reply statement"). The reply statement generated by the generation unit 211 is transmitted to the terminal device 10 and presented to the user U. The user U further inputs an input statement in response to the reply statement. In other words, a dialogue between the user U and the first character (student) becomes possible. As can be understood from the above explanation, the generation unit 211 in the first embodiment controls (generates) the statements of the first character.

[0042] Furthermore, in the first embodiment, the input utterance generated by the generating unit 211 changes according to the difficulty level set for the interview simulation. The difficulty level is set, for example, to one of a plurality of options (for example, easy, normal, and difficult). For example, when the difficulty level is set to "easy," the generating unit 211 generates an obedient reply utterance to the input utterance, when the difficulty level is set to "difficult," the generating unit 211 does not easily accept the input utterance and repeatedly generates a rebellious reply utterance, and when the difficulty level is set to "normal," the generating unit 211 generates a rebellious reply utterance at least once. In other words, the difficulty level set for the simulation can be said to be the difficulty level of the first character (student). In the following configuration, a configuration in which the difficulty level is specified by the user U is exemplified. However, the generating unit 211 may set the difficulty level arbitrarily.

[0043] The generating unit 211 of the first embodiment is constructed by a generative model. The generative model is configured by, for example, a deep neural network. For example, any type of deep neural network, such as a recurrent neural network (RNN) or a convolutional neural network (CNN), is used as the generative model. The generative model may be configured by combining a plurality of types of deep neural networks.

[0044] It is preferable to use a large-scale language model (LLM) capable of natural language processing, which is trained in advance using a large amount of text data and in which the occurrence probability of words is modeled, as the generation model. In particular, it is preferable to use an interactive large-scale language model (generative artificial intelligence) in which a large-scale language model is fine-tuned using a dialogue data set as the generation model. As the interactive large-scale language model, any known model such as ChatGPT (manufactured by OPEN AI), Bard (manufactured by Google), and Bing AI (manufactured by Microsoft) is used. In the following description, a case where the generation unit 211 is an interactive large-scale language model is exemplified. The interactive language model is capable of generating dialogue-style text.

[0045] [Terminal device 10] 4 is a block diagram illustrating an example of the configuration of the terminal device 10. Specifically, the terminal device 10 includes a control device 11, a storage device 12, a communication device 13, an operation device 15, and a display device 14. The terminal device 10 is realized by, for example, a portable information device such as a smartphone or a tablet terminal, or a portable or stationary information device such as a personal computer.

[0046] The control device 11 is a single or multiple processors that control the operation of the terminal device 10. Specifically, the control device 11 is configured by one or more types of processors, such as a central processing unit (CPU), a graphics processing unit (GPU), a sound processing unit (SPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).

[0047] The storage device 12 is one or more memories that store the programs executed by the control device 11 and various data used by the control device 11. For example, a known recording medium such as a semiconductor recording medium or a magnetic recording medium, or a combination of multiple types of recording media, is used as the storage device 12. Note that, for example, a portable recording medium that is detachable from the terminal device 10, or a recording medium that the control device 11 can access via the communication network 300 (for example, cloud storage) may be used as the storage device 12.

[0048] The communication device 13 is a communication device that communicates with the information processing device 20 via the communication network 300. Note that the communication device 13, which is separate from the terminal device 10, may be connected to the terminal device 10 by wire or wirelessly.

[0049] The display device 14 displays various images under the control of the control device 11. For example, various display panels such as a liquid crystal display panel or an organic EL panel are used as the display device 14. Note that an operation device 15 or the display device 14 separate from the information processing system may be connected to the information processing system by wire or wirelessly.

[0050] The operation device 15 is an input device that accepts operations by the user U. For example, an operator operated by the user U or a touch panel that detects contact by the user U is used as the operation device 15. In the first embodiment, the user U inputs various information by operating the operation device 15. Specifically, the user U inputs, for example, information for setting the task faced by the first character (for example, attributes of students and difficulty level) and an input utterance for solving the task of the first character through the operation device 15. The user U inputs an input utterance from the perspective of a teacher in charge of the class of the student (first character).

[0051] The information input by the user U is transmitted from the communication device 13 to the information processing device 20. The information transmitted to the information processing device 20 may be the information itself input by the user U, or may be some data including the information input by the user U. In the first embodiment, since the generation unit 211 is an interactive language model, a prompt including the information input by the user U is transmitted to the information processing device 20. For example, when the user U inputs an input utterance, a prompt instructing the information processing device 20 to generate a reply utterance to the input utterance of the user U may be transmitted to the information processing device 20.

[0052] 5 is a block diagram illustrating an example of the functional configuration of the control device 11 of the terminal device 10. The control device 11 executes a program stored in the storage device 12 to realize a plurality of functions (an acquisition unit 111, a presentation unit 112) for the user U to perform an interview simulation.

[0053] The acquisition unit 111 acquires various pieces of information input by the user U through the operation device 15. Specifically, the acquisition unit 111 acquires various pieces of information input by the user U by accepting them.

[0054] First, the acquisition unit 111 acquires information required for setting the interview simulation (hereinafter referred to as "setting information"). The setting information is, for example, information required for setting a task for the first character (the attribute of the first character in the first embodiment) and the difficulty level of the simulation.

[0055] Secondly, the acquisition unit 111 acquires an input utterance. That is, the acquisition unit 111 functions as an element that acquires a response (input utterance) input by the user U to the first character, which is the subject of the interview, in order to solve the problem set for the first character. Various information (e.g., setting information and input utterance) acquired by the acquisition unit 111 is transmitted from the communication device 13 to the information processing device 20.

[0056] The presentation unit 112 presents various types of information to the user U. Specifically, the presentation unit 112 presents various types of information to the user U by displaying them on the display device 14. However, the presentation of information by the presentation unit 112 is not limited to presentation by display, and may be presentation by audio, for example.

[0057] First, the presenting unit 112 presents a task that the generating unit 211 of the information processing device 20 has set for the first character under a set theme. In the first embodiment, an episode including the task is presented to the user U along with the task and a theme (set theme) corresponding to the task. Note that it is also possible that any one or two of the task, set theme, and episode are not presented.

[0058] Secondly, the presentation unit 112 presents the reply comment generated by the generation unit 211 in response to the input comment to the user U. In other words, the presentation unit 112 functions as an element that presents to the user U the reaction of the first character, which is generated by the generation unit 211 in response to the response acquired by the acquisition unit 111.

[0059] The process of the simulation system 100 executing an interview simulation (hereinafter referred to as "interview process") will be described in detail with reference to Figures 6 and 7. Figure 6 is a flowchart showing a specific procedure of the interview process executed by the simulation system 100.

[0060] 7 is an example of an image G displayed on the display device 14 of the terminal device 10 during the interview process. In the first embodiment, since the generation unit 211 is configured with an interactive large-scale language model, the interview simulation progresses by interactively exchanging information generated by the information processing device 20 (the generation unit 211) with information input by the user U. The image G displayed by the display device 14 shows an area Ta (Ta1, Ta2, ...) indicating information transmitted from the information processing device 20 to the terminal device 10, and an area Tb (Tb1, Tb2, ...) indicating information input by the user U to the terminal device 10.

[0061] The interview process in Fig. 6 is started when the terminal device 10 (acquisition unit 111) receives a start instruction from the user U (SA1). Upon receiving the instruction to start the interview simulation from the user U, the terminal device 10 (acquisition unit 111) transmits information (hereinafter referred to as "start information") for instructing the information processing device 20 to start the interview simulation (SA2). Details of the start information will be described later.

[0062] When the information processing device 20 receives the start information from the terminal device 10, it notifies the terminal device 10 that the interview simulation has started (SA3). Specifically, information notifying the user U that the interview simulation has started (for example, the information shown in area Ta1 in FIG. 7) is transmitted to the terminal device 10.

[0063] When notified that the interview simulation has started, the terminal device 10 (presentation unit 112) presents to the user U information that prompts the user U to input information (hereinafter referred to as "setting information") for setting the issues the student (first character) is facing. As illustrated in area Ta1 of Fig. 7, the setting information is, for example, the type of the student's school (an example of an attribute) and the difficulty level of the interview simulation.

[0064] The user U inputs setting information by operating the operation device 15. As illustrated in area Tb1 of Fig. 7, the type of school (junior high school) and the difficulty level (difficult) are input. The acquisition unit 111 accepts the setting information input by the user U (SA4) and transmits it to the information processing device 20 (SA5).

[0065] The information processing device 20 (generation unit 211) sets a task for the first character according to the setting information (school type, difficulty level) from the terminal device 10, and generates an episode including the task (SA6). In the first embodiment, a task corresponding to one of a plurality of themes (set theme) associated with the school type specified by the user U is set for the first character, and an episode including the task is generated.

[0066] One of the multiple themes illustrated in Fig. 3 is selected by the generation unit 211 as the set theme. The episode generated by the generation unit 211 may directly or indirectly include an assignment corresponding to the set theme. An episode that indirectly includes an assignment is, for example, a case where the episode includes an assignment that is a modified version of the assignment. The information processing device 20 then transmits the set theme, the assignment, and the episode to the terminal device 10 (SA7). A configuration in which the set theme and the assignment are not transmitted may also be adopted.

[0067] The terminal device 10 (presentation unit 112) presents the episode transmitted from the information processing device 20 to the user U (SA8). The area Ta2 in FIG. 7 illustrates an example in which a set theme "smartphone addiction", a task corresponding to the theme "addiction and access to inappropriate content", and an episode including the task "Taro Tanaka, a junior high school student, is of concern..." are presented. In addition to the episode, the purpose of the interview (for example, a sentence such as "The purpose is to solve Taro's problem of smartphone addiction, encourage healthy smartphone use, and improve his school life") may be presented to the user U.

[0068] As illustrated in area Tb2 of FIG. 7, the user U inputs an input utterance for solving the task set for the first character by operating the operating device 15. The input utterance is a utterance that is spoken to the first character (student) in order to solve the task. The terminal device 10 (acquisition unit 111) acquires the input utterance input by the user U by accepting it (SA9). Then, the acquisition unit 111 transmits the input utterance to the information processing device 20 (SA10).

[0069] The information processing device 20 (generation unit 211) generates a reaction (reply statement) of the first character in response to the input statement transmitted from the terminal device 10 (SA11). That is, a reply statement that the student who is addressed with the input statement can make is generated. In the first embodiment, the reply statement is generated according to the difficulty level set by the user U. The information processing device 20 transmits the reply statement to the terminal device 10 (SA12).

[0070] The terminal device 10 (presentation unit 112) presents the reply message transmitted by the information processing device 20 to the user U (SA13). Specifically, the terminal device 10 causes the display device 14 to display the reply message, as illustrated in the area Ta3 in FIG.

[0071] The user U further inputs an input utterance in response to the reply utterance, as illustrated in the area Tb3 of FIG. 7. When the input utterance is input, the process returns to step SA9, and SA10-SA12 are further executed, and the reply utterance is displayed in step SA13, as illustrated in the area Ta4 of FIG. 7. Toward the solution of the problem, the process of SA9-SA13 (a round trip between the input utterance and the reply utterance) is repeatedly executed. That is, the acquisition unit 111 acquires an input utterance further input by the user U in response to the reply utterance presented by the presentation unit 112, and the presentation unit 112 presents to the user U a reply utterance generated by the generation unit 211 every time an input utterance is input by the user U. The input utterance includes various utterances for guiding the student toward the solution of the problem, such as questions to the student, specific suggestions, contents of empathy or agreement, and contents of caution.

[0072] The time to end the interview simulation is arbitrary, but in the first embodiment, the interview simulation ends when the generation unit 211 determines that the interview has ended. The generation unit 211 determines that the interview has ended, for example, when an instruction to end the interview is received from the user U, when a pre-set time limit is reached, or when the generation unit 211 determines that the problem has been solved.

[0073] An example of start information for instructing the start of an interview simulation in the first embodiment will be described below. In the first embodiment, as described above, since the generation unit 211 is an interactive language model, the start information is information corresponding to an instruction sentence (prompt). The start information is information that instructs the generation unit 211 on the overall flow from the start to the end of the interview simulation (e.g., steps SA3-SA13) so that the generation unit 211 proceeds with the interview simulation.

[0074] The start information includes, for example, the following information P1-P5. Note that since the generation unit 211 of the first embodiment is a large-scale language model, the information P1-P5 is shown in a natural language.

[0075] Information P1 is information that indicates role 1 of the generation unit 211. Role 1 is a role of setting a task for the first character under a predetermined theme. Role 1 in the first embodiment is a role of setting a task for the first character (student) and generating an episode including the task. Specifically, information P1 is as follows.

[0076] [P1: Information instructing role 1 of the generation unit 211] You create episodes that include assignments according to the type (attributes) of your school. The theme of the episode (task) can be chosen from the following themes (Information P4).

[0077] Information P2 is information that indicates role 2 of the generation unit 211. Role 2 is to control (execute) the first character (student). In other words, it is a role to generate reply comments. Information P2 also includes information that indicates that the student's reaction (reply comment) will change depending on the difficulty level of the simulation. Specifically, information P2 is as follows:

[0078] [P2: Information instructing role 2 of the generation unit 211] You will play the role of a student attending a three-way conference. If the difficulty level is easy, listen to the advice. If the difficulty level is normal, there will be at least one rebuttal. If the level of difficulty is high, they are not easily convinced. They distrust schools and teachers.

[0079] The information P3 is information indicating the role of the user U (player). The information P3 in the first embodiment is information indicating that the user U plays the role of a teacher. In other words, the information P3 can be said to be information indicating the relationship of the user U to the first character (student). Specifically, the information P3 is as follows:

[0080] [P3: Information indicating the player's role] As a class teacher, the player participates in interviews with students to solve the episode's problems. The players are in control of instruction.

[0081] The information P4 is information indicating a theme and a task. Specifically, as illustrated in FIG. 3, the information includes a plurality of themes prepared in advance for each of a plurality of attributes and a task set for each of the themes.

[0082] The information P5 is information indicating the rules of the interview simulation. For example, the information P5 includes information instructing the start and end of the interview simulation and information instructing the lines to be presented to the user U first when starting the interview simulation. Specifically, the information P5 is as follows.

[0083] [Information P5: Information showing the rules of the interview simulation] The interview simulation begins with the player inputting the student's attributes (school type) and ends when the player inputs that the interview is over. The homeroom teacher's lines are written by the player, not by you. It begins with the following line: "Now, let's begin the interview simulation. Please specify the type of school you will be responsible for and the level of difficulty. If there are no specifications, we will proceed as is."

[0084] However, the information included in the start information is not limited to the above information P1-P5. For example, the start information may include information instructing the generation unit 211 to present a hint for the input utterance in response to an instruction from the user U.

[0085] It is preferable that the start information transmitted to the information processing device 20 is not presented to the user U (i.e., is not displayed on the display device 14). It is possible to prevent the start information from being presented to the user U by, for example, setting an API (Application Programming Interface).

[0086] As can be understood from the above description, in the first embodiment, an interview simulation can be executed in which a reply statement from the first character is obtained in response to an input statement input by the user U to solve a task set for the first character. Therefore, compared to an interview simulation with a character with no task set, interview skills in an interview aimed at solving a task can be improved.

[0087] In addition, in the first embodiment, one of a plurality of tasks prepared in advance is set for the first character, so that the interviewing ability can be improved in order to solve a variety of tasks.

[0088] According to the configuration of the first embodiment in which a task corresponding to any one of a plurality of themes is set for the first character, it is possible to simulate an interview with the first character to which a task according to the theme is set, and the user U can easily understand the type of task. Note that it is also possible to associate a plurality of tasks with each theme in Fig. 3. When a theme is selected, one of the tasks corresponding to the theme is selected according to an instruction from the user U or by the generation unit 211.

[0089] The configuration of the first embodiment in which the generation unit 211 generates a reply comment every time an input comment is input by the user U has the advantage that an interview simulation can be performed based on an actual conversation.

[0090] In the first embodiment, the first character is a school student character, and the user U inputs an input statement to solve a problem from the perspective of the student's teacher, thereby enabling an interview simulation to be performed with a student with a problem as the interview subject.

[0091] According to the configuration of the first embodiment in which attributes of a first character are set and a task corresponding to the attributes is set for the first character, there is an advantage that a task that reflects the characteristics of the attributes can be set for the first character.

[0092] In the first embodiment, the reply utterance generated by the generation unit 211 changes according to the difficulty level set for the interview simulation, so that an interview simulation can be performed assuming a variety of interview partners (interviewees).

[0093] According to the configuration of the first embodiment in which start information (prompt) is sent to the generation unit 211 when an instruction to start an interview simulation is received from user U, for example, user U does not need to perform an operation to send the start information separately from the start instruction, and it is possible for user U to send the start information to the generation unit 211 without being aware of it.

[0094] In the first embodiment, the start information includes information P1 that instructs the generation unit 211 to set a task for the first character, information P2 that instructs the generation unit 211 to control (execute) the first character, and information P3 that indicates the role of the user U, so that there is an advantage that the information P1-P3 required to start the interview simulation can be transmitted to the generation unit 211 all at once.

[0095] Because an episode including a task set for the first character is presented to the user U, it is possible to perform an interview simulation that more closely resembles an actual interview, compared to a configuration in which an episode is not presented to the user U. However, the first embodiment also includes a configuration in which the task itself is presented without presenting an episode.

[0096] <Second embodiment> A second embodiment of the present invention will be described. Note that, in each of the following exemplary embodiments, for elements whose functions are similar to those of the first embodiment, the reference numerals used in the description of the first embodiment will be used and detailed descriptions of each will be omitted as appropriate.

[0097] In the first embodiment, a configuration is illustrated for executing an interview simulation assuming a two-way interview between user U and a first character, while in the second embodiment, a configuration is illustrated for executing an interview simulation assuming a three-way interview between user U, a first character, and a second character.

[0098] The first character is a student character as in the first embodiment, the second character is a guardian character of the student, and the user U is a homeroom teacher.

[0099] The generation unit 211 of the information processing device 20 sets tasks for the first character (generates episodes) and controls the first character, as in the first embodiment. Furthermore, the generation unit 211 of the second embodiment executes (controls) the second character.

[0100] Specifically, the generation unit 211 controls the second character by generating the behavior (utterances, attitudes, facial expressions, etc.) of the second character. The generation unit 211 in the second embodiment generates a reaction of the second character (parent) in response to an input response (input utterance) input by the user U to the first character (student) to solve a problem. In the following explanation, a case will be exemplified in which the reaction of the second character generated in response to the input utterance is a utterance (hereinafter referred to as a "related utterance"), similar to the case of the first character.

[0101] In the second embodiment, a case is exemplified where the related utterances generated by the generation unit 211 change according to the difficulty level set for the interview simulation. The difficulty level set for the interview simulation is as described in the first embodiment. For example, when the difficulty level is set to "easy", a straightforward related utterance is generated for the input utterance, when the difficulty level is set to "difficult", the input utterance is not easily accepted and rebellious related utterances are repeatedly generated, and when the difficulty level is set to "normal", a rebellious related utterance is generated at least once. In other words, the difficulty level set for the simulation can be said to be the difficulty level of the second character (guardian).

[0102] The input utterance made by the user U to solve the problem of the first character may be addressed to both the first character and the second character, or to either one of them. In the second embodiment, a configuration is exemplified in which the function to control the first character and the function to control the second character are realized by a common element (generative model), but the function to control the first character and the function to control the second character may be configured by separate elements. In other words, the generation unit 211 may be configured by a plurality of elements.

[0103] The presentation unit 112 of the terminal device 10 in the second embodiment presents to the user U not only the reply comment of the first character, but also the related comment of the second character.

[0104] The start information of the second embodiment includes the following information P6 in addition to the above-mentioned information P1-P5. Information P6 is information instructing role 3 of the generation unit 211. Role 3 is to control (execute) the second character (guardian). In other words, role 3 is the role of generating related comments. Information P6 also includes information instructing that the guardian's reaction (related comments) will change depending on the difficulty level of the simulation. Specifically, information P6 is as follows.

[0105] [Information P6: Information instructing role 3 of the generation unit 211] You will act as the parent attending the three-way conference. If the difficulty level is easy, listen to the advice. If the difficulty level is normal, there will be at least one rebuttal. If the level of difficulty is high, they are not easily convinced. They distrust schools and teachers.

[0106] Steps SA1-SA9 in Fig. 6 are executed in the second embodiment in the same way as in the first embodiment. In the second embodiment, in step SA11, the generation unit 211 generates related comments along with a reply message. Then, in step SA12, the reply message and the related messages are sent to the terminal device 10, and in step SA13, the reply message and the related messages are presented to the user U. As in the first embodiment, the processes of SA9-SA13 (going back and forth between the input message and the reply message and related messages) are executed repeatedly to solve the problem.

[0107] In step SA11, it is not essential to generate both a reply message and a related message in response to an input message, and there are cases where only one of them is generated.

[0108] Fig. 8 is a drawing corresponding to Fig. 7 and is an example of an image G according to the second embodiment. Areas Ta1, Ta2 and areas Tb1, Tb2 are the same as those in Fig. 7. As exemplified by area Ta3 in Fig. 8, in the second embodiment, a reply comment by a student and a related comment by a guardian in response to an input comment are displayed.

[0109] As can be understood from the above explanation, in the second embodiment, the user U is presented with the first character's reply statement to the input statement and the related statement with the second character, so that a simulation of a three-way meeting including the first character (e.g., a student) and the second character (e.g., a parent) can be performed.

[0110] In the second embodiment, the second character is a guardian character, but the second character may be any character related to the first character. The second character may be, for example, a guardian, or various characters such as a person related to the student's school (e.g., a grade head or a life guidance director), a counselor, or an expert in a specific field (e.g., education or law). In particular, by performing an interview simulation in which a grade head or a life guidance director participates in addition to a student and a guardian, a highly accurate interview simulation based on an actual school interview becomes possible, and the user U's interview ability can be improved.

[0111] In the first embodiment, a two-person interview is assumed, and in the second embodiment, a three-person interview is assumed, but the interview simulation may be an interview with four or more people. For example, by having the generation unit 211 control the above-mentioned various characters in addition to the students and guardians, an interview simulation with four or more people is possible.

[0112] The start information includes information for instructing the generation unit 211 to control each character. For example, when the generation unit 211 executes the character of a head teacher of the grade, the start information includes the following information P7, and when the generation unit 211 executes the character of a head teacher of student guidance, the start information includes the following information P8.

[0113] The information P7 is information instructing the role 4 of the generation unit 211. The role 4 is to control (execute) the third character (head teacher of the grade). For example, information instructing to take measures to assist the user U (class teacher) is included. Specifically, the information P7 is as follows:

[0114] [Information P7: Information instructing role 4 of the generation unit 211] You are the head teacher for the grade to which the player's homeroom teacher belongs. They oversee the players' instruction with a warm heart and help them when students or parents make clear deviations from the law. The player takes the initiative, so everyone else is basically silent.

[0115] The information P8 is information instructing the role 5 of the generating unit 211. The role 5 is to control (execute) the fourth character (the head teacher of student guidance). The information P8 includes, for example, information instructing to take measures to assist the user (the class teacher). Specifically, the information P8 is as follows:

[0116] [Information P8: Information instructing role 5 of the generation unit 211] You are the head of student guidance at the school where the player's homeroom teacher works. They oversee the players' instruction with a warm heart and assist them when students or parents make obvious legal deviations. The player takes the initiative, so everyone else is basically silent.

[0117] The user U may be allowed to arbitrarily select a character to participate in the interview from among a plurality of characters (for example, a student, a guardian, a head of the grade, and a head of life guidance).

[0118] <Third embodiment> In the third embodiment, a configuration in which a function for evaluating input comments of a user U is added to the simulation system 100 in the first embodiment will be illustrated.

[0119] The generation unit 211 of the third embodiment generates an evaluation based on a predetermined evaluation criterion for the input utterance of the user U, in addition to the same functions as those of the first embodiment. The appropriateness of the content of the input utterance is evaluated based on the evaluation criterion. In other words, the user can understand from the evaluation whether the interview was appropriate for solving the problem or not.

[0120] An example of the evaluation criteria used in a simulation of an interview aimed at providing life guidance or student guidance will be described below. In the third embodiment, an example is shown in which an input utterance is evaluated by giving a score (out of 100 points) based on the evaluation criteria.

[0121] The evaluation criteria in the third embodiment are composed of, for example, the following items 1-10. The following evaluation criteria were created based on the Student Guidance Guidelines (Ministry of Education, Culture, Sports, Science and Technology) revised in December 2022. However, the evaluation criteria used in the third embodiment are not limited to the following examples and may be changed as appropriate depending on the type of interview (purpose of the interview).

[0122] [Evaluation criteria (maximum 100 points)] <Item 1> Anti-bullying measures (12 points): Do you notice the signs of bullying and respond appropriately? <Item 2> Response to violent acts (10 points): When a violent act occurs, do you respond immediately and appropriately? <Item 3> Prevention and response to juvenile delinquency (10 points): Are you able to detect students' delinquent tendencies and problem behaviors early and respond appropriately? <Item 4> Responding to students with diverse backgrounds (12 points): Are students with diverse backgrounds, such as disabilities and sexual minorities, being appropriately accommodated? <Item 5> Communication skills (12 points): Are you able to communicate effectively, clarify issues, and make them understood by students and parents? <Item 6> Problem-solving ability (11 points): Can you provide appropriate solutions to specific problems (bullying, poor academic performance, etc.)? <Item 7> Leadership and instruction (8 points): Can you provide direction and guidance to students and parents? <Item 8> Situational awareness and adaptability (8 points): Are you able to respond appropriately according to the flow of the interview and the reactions of the participants? <Item 9> Ability to explain specialized knowledge and educational policies (8 points): Can you clearly explain specialized knowledge about education and the school's educational policies? <Item 10> Quality of education and mental care of students (9 points): Is attention paid not only to academics but also to mental care of students?

[0123] The generation unit 211 evaluates (gives a score to) the input utterance based on the above evaluation criteria. In the third embodiment, the evaluation is made comprehensively by taking into account the sequence of all input utterances from the first input utterance input by the user U to the last input utterance. However, the present invention also includes a configuration in which evaluation is made for each input utterance.

[0124] Specifically, the generation unit 211, for example, specifies a score for each of the above items, and generates the total score for each item as an evaluation of the input utterance (i.e., the response of user U). However, the specific method of evaluating the input utterance based on the evaluation criteria is not limited to the above examples. Furthermore, the evaluation of the input utterance is not limited to a score, and may be, for example, a configuration in which the evaluation is indicated in one of a number of stages (e.g., very good, good, average, poor) or a configuration in which the evaluation is indicated by a comment. Note that the start information according to the third embodiment includes information instructing the generation unit 211 to evaluate the input utterance based on the evaluation criteria.

[0125] The presentation unit 112 of the terminal device 10 in the third embodiment has the same functions as those in the first embodiment, and in addition presents to the user U an evaluation generated for a response (input utterance) input by the user U.

[0126] Fig. 9 is a flowchart of an example of an interview process according to the third embodiment. As illustrated in Fig. 9, the interview process of the third embodiment includes steps SA14-SA17 in addition to SA1-SA13 in Fig. 6.

[0127] Fig. 10 is an example of an image G displayed on the display device 14 of the terminal device 10 when performing the interview process according to the third embodiment. Similar to Fig. 7, image G shows an area Ta (Ta1, Ta2, ...) indicating information transmitted from the information processing device 20 to the terminal device 10, and an area Tb (Tb1, Tb2, ...) indicating information input by the user U to the terminal device 10.

[0128] Steps SA1-SA13 are executed in the same manner as in the first embodiment. Note that, like in the first embodiment, the process of SA9-SA13 (the back and forth between the input message and the reply message) is executed repeatedly. After the back and forth between the input message and the reply message is repeated, the user U checks the last reply message and inputs an instruction to end the interview as illustrated in the area Tb5 of Fig. 10, and the instruction to end the interview is sent to the information processing device 20 (SA14).

[0129] Next, the generating unit 211 of the information processing device 20 generates an evaluation (score) for the input utterances (a series of input utterances from the first input utterance to the last input utterance) based on the evaluation criteria (SA15). The evaluation generated by the generating unit 211 is transmitted to the terminal device 10 (SA16). Then, the evaluation is presented to the user U (SA17). In the third embodiment, as illustrated in the area Ta5 of FIG. 10, a case is illustrated in which the user U is presented with a score for each item of the evaluation criteria, comments for each item (e.g., good points and points to be improved), and an overall comment (overall evaluation) along with the total score for multiple items of the evaluation criteria. That is, the evaluation of the input utterance is not limited to the total score for multiple items of the evaluation criteria, but may be the score or comment for each item.

[0130] In FIG. 9, the generating unit 211 generates an evaluation when the user U instructs the end of the interview. However, the generating unit 211 may also generate an evaluation when the generating unit 211 determines that the interview is over (for example, when a preset time limit is reached or when the generating unit 211 determines that the problem has been solved). Therefore, after steps SA9 and SA10 (i.e., after the last input utterance input by the user U), an evaluation may be generated in step SA15 based on the input utterance without performing steps SA11-SA14. In addition, when the user U instructs to generate an evaluation, the generating unit 211 may generate an evaluation based on the input utterances up to that point. As explained above, an evaluation may be generated at any point in steps SA9-SA13, and the interview simulation may end.

[0131] As can be understood from the above description, in the third embodiment, an evaluation is generated for the user U's response (input utterance), so that the user U can judge whether his / her response is appropriate or not. Note that in the second embodiment and other forms, a configuration that adds a function for evaluating input utterances can naturally be adopted.

[0132] <Modification> The above-mentioned exemplary embodiments can be modified in various ways. Specific modified embodiments are exemplified below. Two or more embodiments selected from the following examples can be appropriately combined.

[0133] (1) In each of the above-described embodiments, the generation unit 211 is configured to include one large-scale language model, but the generation unit 211 may be configured to include multiple elements. For example, in the first embodiment, the generation unit 211 may be configured to include a generation model that controls the first character and a generation model that sets a task for the first character (generates an episode including the task). That is, the configuration of the generation model is arbitrary, and the generation unit 211 may be configured to include, for example, multiple elements that are independent of each other. Similarly, in the second and third embodiments, multiple functions of the generation unit 211 may be realized by separate elements.

[0134] (2) In the above embodiment, a statement (input statement) is exemplified as a response input by the user U to the first character, but the response is not limited to a statement. The response may be, for example, an attitude, facial expression, or action. Similarly, the reaction of the first character generated in response to the response is not limited to a statement, and may be an attitude, facial expression, or action. The attitude, facial expression, or action is displayed in the image G as, for example, a character string (for example, "Student: Sulking"). Note that, when an avatar of the first character can be displayed, the attitude, facial expression, or action of the avatar may be controlled. The same applies to characters other than the first character executed by the generation unit 211.

[0135] (3) The generation unit 211 may be constructed with a generation model other than a language model. For example, a generation model that learns the relationship between an input utterance and a reply utterance by machine learning may be used as the generation unit 211. In addition, it is not essential that the generation unit 211 is constructed with a generation model. For example, a method is also adopted in which the generation unit 211 generates a reply utterance candidate that is associated with an input utterance candidate similar to an input utterance input by the user U as a reply utterance to be presented to the user U by using a data table in which a plurality of input utterance candidates prepared in advance are associated with reply utterance candidates and registered. In addition, in the second embodiment, related utterance candidates are also registered in the data table. In addition, the generation unit 211 may be configured to generate an episode using a data table in which each assignment is associated with an episode prepared in advance. However, according to a configuration in which the generation unit 211 is constructed with an interactive large-scale language model, there are advantages in that the specific processing of the interview process can be easily changed by changing the content of the start information (prompt) and that reply utterances of various contents can be generated.

[0136] (4) The first character is not limited to a student character, and may be, for example, a subordinate or a patient character. When the first character is a subordinate, the user U inputs an input utterance from the perspective of a superior, and when the first character is a patient, the user U inputs an input utterance from the perspective of a medical professional. In other words, it is possible to simulate not only interviews at school, but also interviews at the workplace or hospital.

[0137] (5) In the above embodiment, the type of school is exemplified as an attribute of the first character (student), but the attribute is not limited to the type of school. For example, various information related to students such as grade, school characteristics, personality, gender, family structure, and club activities are assumed as attributes of students. In addition, the type of attribute to be set is appropriately changed according to the first character. For example, if the first character is a subordinate, examples of attributes include career, years of employment, job content, and department, and if the first character is a patient, examples of attributes include current medical history and past medical history.

[0138] (6) In the above embodiment, the user U specifies the setting information (for example, attributes and difficulty level), but the generation unit 211 may select the setting information as desired. Upon receiving a start instruction from the user U, the generation unit 211 sets a task corresponding to, for example, a randomly selected attribute, and generates an episode. That is, the processes of steps SA4 and SA5 in FIG. 6 may be omitted.

[0139] (7) In each of the above-mentioned embodiments, for example, a plurality of themes corresponding to attributes designated by the user U may be presented to the user U, and the user U may select one of the presented themes to designate a set theme. Note that the generation unit 211 may present to the user U a plurality of themes corresponding to attributes arbitrarily selected by the user U.

[0140] (8) In each of the above-mentioned embodiments, a task is set for the first character under a predetermined theme (set theme), but it is not essential to set a task under a predetermined theme. For example, the generation unit 211 may be configured to set any one of a plurality of tasks associated with attributes for the first character (i.e., the theme in FIG. 3 is omitted).

[0141] Furthermore, if the generation unit 211 is a large-scale language model, it is also possible to generate tasks (episodes) without preparing multiple themes and tasks in advance. In the above configuration, the information P4 (information indicating the theme and task) may be omitted from the start information. Note that the information P5 of the start information may include information that, for example, when setting information is input from the user U, sets a task (episode) according to the setting information, and when the setting information is not input, the generation unit 211 arbitrarily sets a task.

[0142] (9) In the above embodiment, the theme selected by the generation unit 211 from a plurality of themes is set as the set theme, but the theme selected by the user U from a plurality of themes may also be set as the set theme. The user U may also specify a task to be set for the first character. The generation unit 211 sets the task specified by the user U for the first character, and generates an episode including the task.

[0143] (10) In the third embodiment, a configuration in which the generation unit 211 generates an evaluation based on the law and a configuration in which the generation unit 211 generates advice to the user U based on the law are also adopted. In the above configuration, for example, the start information includes information P9 instructing the role 6 of the generation unit 211. Role 6 is to control (execute) a lawyer character. The information P9 includes, for example, information instructing the user to take measures to assist the user U (classroom teacher), information instructing that the evaluation method changes depending on the difficulty level of the simulation, information instructing to give advice to the player based on the law, and information indicating the law. Note that the generation unit 211 may generate advice based on the law for the first character and present the advice to the user U.

[0144] [Information P9: Information instructing role 6 of the generation unit 211] As a professional lawyer, you provide legal justification for what the player says during your evaluation. Please indicate the appropriate clause from the following bills related to student life guidance. Also, if they ask for hints, please point them to this law, show them the relevant articles, and advise them on the direction of instruction. Unless a serious problem arises, I won't give advice until asked, but I will offer advice after the interview is over. When the difficulty level is easy to normal, the player's counseling style is evaluated. At the normal to hard difficulty level, players will be rewarded for standing firm on behalf of their students, acting in accordance with the law, coordinating with authorities such as the police, and taking disciplinary action. <Laws and regulations related to student life guidance> #To protect students: School education law Child Welfare Act Act on the Welfare and Protection of Children's Rights Act on Prevention of Sexual Exploitation of Children and Protection of Child Victims Basic Act on the Healthy Development of Youth School Health and Safety Act Youth Protection and Development Ordinance (varies by prefecture and municipality) Act on the Protection of Personal Information Copyright Law Law Concerning the Prohibition of Unauthorized Computer Access Basic law on education Basic Act on Support for Living and Employment of Persons with Disabilities Act on the Prevention of Bullying in Schools (Protection of Children and Students) #Student Discipline-related matters: civil law criminal law Gambling and Public Racing Law road traffic law Narcotics and Psychotropic Substances Control Act Telecommunications Business Act (related to internet use) Act on Prevention of Bullying in Schools (Disciplinary Aspects of Students) Laws concerning the Prohibition of Smoking by Minors (Disciplinary Aspects of Children and Students) Law Concerning Prohibition of Underage Drinking (Disciplinary Aspects of Students) #Related to disciplinary action against parents of students: Laws prohibiting smoking among minors (Parental Disciplinary Aspects) Laws Concerning Prohibition of Underage Drinking (Parental Disciplinary Aspects) Child Abuse Prevention Act (Disciplinary Aspects of Parents) #Related to obligations and responsibilities for teachers' omissions: Child Abuse Prevention Act School Education Act (part concerning teachers' duties and responsibilities) Basic Act on the Healthy Development of Youth (Part Concerning the Role of Teachers) Act on the Prevention of Bullying in Schools (Part concerning the Duties and Responsibilities of Teachers)

[0145] (11) In the third embodiment, the generation unit 211 is also configured to generate an evaluation from the perspective of an expert in student guidance or educational counseling. In the above configuration, for example, the start information includes information P10 that indicates role 7 of the generation unit 211. Role 7 is to control (execute) a character of an expert in student guidance or educational counseling. The information P10 includes information that instructs the generation of an evaluation based on evaluation criteria as an expert in student guidance or educational counseling. Specifically, the information P10 is as follows:

[0146] [Information P10: Information instructing role 7 of the generation unit 211] After the interview is over, please evaluate the player's response (input utterances) as an expert in student guidance and educational counseling. At that time, please give it a score using the evaluation criteria and present it.

[0147] (12) The evaluation criteria used in the third embodiment are arbitrary as described above, and may be changed as appropriate depending on the type of consultation. For example, the following evaluation criteria are used in an interview to solve a student's worries (problems) in educational counseling. The following evaluation criteria are created, for example, based on publicly issued information on educational counseling (for example, information issued by the Ministry of Education, Culture, Sports, Science and Technology or prefectures).

[0148] [Evaluation criteria (maximum 100 points)] Expertise and Understanding (15 points): Able to understand and appropriately apply basic theories and approaches in educational counselling. Counselling skills (15 points): Able to use basic counselling skills such as listening, questioning and responding appropriately. Ethics and confidentiality (20 points): Are you able to adhere to ethical guidelines and protect student confidentiality? Relationship building skills (10 points): Are you able to build trusting relationships with students? Goal setting and progress management (10 points): Can you work with students to set clear goals and manage their progress effectively? Multicultural Awareness and Accommodation (5 points): Are you able to accommodate and support students from different backgrounds? Effective Referrals (5 points): Are you able to provide appropriate referrals when needed? Self-Awareness and Self-Reflection (10 points): Are you able to recognize your strengths and weaknesses and pursue ongoing professional growth? Communication (5 points): Are you able to maintain clear and effective communication? Records and documentation (5 points): Are appropriate records of consultations kept and relevant documentation available where required?

[0149] (13) Although the interview process is progressed by display on the display device 14, the interview process may be progressed by voice, for example. When the interview process is progressed by voice, for example, the information shown in the area Ta (Ta1, Ta2, ...) and the information shown in the area Tb (Tb1, Tb2, ...) in the image G of Fig. 7 are presented to the user U by voice.

[0150] (14) A configuration is also adopted in which an input utterance that will receive the highest rating (full marks) based on the evaluation criteria is generated in response to an instruction from user U and presented to user U.

[0151] (15) In each of the above-described embodiments, the information processing device 20 is a server device, but the functions of the information processing device 20 (e.g., the generation unit 211) may be installed in the terminal device 10 of the user U. Also, some of the functions of the information processing device 20 (e.g., some of the functions of the generation unit 211) may be installed in the terminal device 10. As can be understood from the above explanation, the simulation system 100 may be a single device or a computer system composed of multiple devices.

[0152] (16) The simulation system 100 according to the above-mentioned embodiment is realized by the cooperation of a computer (specifically, a control device) and a program. The program according to the above-mentioned embodiment can be provided in a form stored in a computer-readable recording medium and installed in the computer. The recording medium is, for example, a non-transitory recording medium, and is exemplified by an optical recording medium (optical disk) such as a CD-ROM, but may include any known type of recording medium such as a semiconductor recording medium or a magnetic recording medium. Note that a non-transitory recording medium includes any recording medium except for a transient, propagating signal, and does not exclude a volatile recording medium. It is also possible to provide the program to the computer in the form of distribution via a communication network.

[0153] (17) The present invention can also be specified as a method for executing a simulation of an interview, the method being realized by a computer system that acquires a response input by a user to a first character who is the subject of the interview in order to solve a problem set for the first character, and presents to the user a reaction of the first character that is generated in response to the response acquired by the acquisition unit. The present invention can also be specified as a method for executing a simulation of an interview, the method being realized by a computer system that acquires a response of the first character that is generated in response to the response input by a user to the first character in order to solve a problem set for the first character who is the subject of the interview, and presents to the user a reaction of the first character that is generated in response to the response acquired by the acquisition unit. It is also specified as a computer-implemented generation method. [Explanation of symbols]

[0154] 10: Terminal device 11: Control device 12:Storage device 13: Communication equipment 14:Display device 15: Operating device 20: Information processing device 21: Control device 22: Storage device 23: Communication equipment 100: Simulation system 111: Acquisition Department 112: Presentation part 211 :Generation part 300: Communication network U:User

Claims

1. An apparatus for executing a simulation of an interview, comprising: an acquisition unit that acquires a response input by a user to a first character in order to solve a problem set for the first character that is the subject of the interview; a presentation unit that presents to the user a reaction of the first character, the reaction being generated by a generation unit in response to the response acquired by the acquisition unit; A terminal device comprising:

2. The acquisition unit further acquires a response input by the user in response to the reaction presented by the presentation unit, The presentation unit presents the reaction generated by the generation unit to the user every time the user inputs the response. The terminal device of claim 1.

3. The presentation unit presents to the user an evaluation generated based on a predetermined evaluation criterion for the response input by the user. The terminal device of claim 1.

4. The task is one of a number of tasks prepared in advance. The terminal device of claim 1.

5. the first character is a character of a student at a school; The acquisition unit acquires the response input by the user from the standpoint of the teacher of the student. The terminal device of claim 1.

6. The presentation unit presents to the user a reaction of a second character related to the first character, the reaction being generated by the generation unit in response to the response acquired by the acquisition unit. The terminal device of claim 1.

7. An attribute of the first character is set; The generation unit sets the task according to the attribute to the first character. The terminal device of claim 1.

8. A task corresponding to any one of a plurality of themes prepared in advance is set for the first character. The terminal device of claim 1.

9. The reaction generated by the generator varies depending on the difficulty level set for the simulation. The terminal device of claim 1.

10. The generator is an interactive large-scale language model. The terminal device of claim 1.

11. When the acquisition unit receives an instruction to start the simulation from the user, the acquisition unit transmits a prompt to start the simulation to the generation unit. The terminal device of claim 10.

12. The prompt may include: Information instructing the generation unit to set a problem faced by the first character; information instructing the generation unit to control the first character; and information indicating the role of the user. The terminal device of claim 11.

13. The generation unit generates an episode including the task, The presentation unit presents the episode to the user. The terminal device of claim 1.

14. An apparatus for executing a simulation of an interview, comprising: A generation unit generates a response of the first character in response to a response input by a user to the first character in order to solve a problem set for the first character that is the subject of the interview. Information processing device.

15. A system for executing a simulation of an interview, comprising: an acquisition unit that acquires a response input by a user to a first character in order to solve a problem set for the first character that is the subject of the interview; a generation unit that generates a reaction of the first character in response to the response acquired by the acquisition unit; a presentation unit that presents the reaction generated by the generation unit to the user; A simulation system comprising:

16. 1. A method for conducting a simulation of an interview, comprising: acquiring a response input by a user to a first character that is a subject of the interview in order to solve a problem set for the first character; Presenting to the user a reaction of the first character, the reaction being generated in response to the acquired response. A simulation method implemented by a computer system.

17. A program for executing a simulation of an interview, an acquisition unit that acquires a response input by a user to a first character in order to solve a problem set for the first character that is the subject of the interview; and a presentation unit that presents to the user a reaction of the first character that is generated in response to the response acquired by the acquisition unit; A program that causes a computer system to function as a

Images