System

Abstract

An object of the system according to the embodiment is to improve the quality of an event by generating an unexpected question or an active question in a training session or an explanation meeting.SOLUTION: A system includes a unit for generating a question, an evaluation unit, and a unit for generating a question. The question generating unit generates a question in consideration of a persona. The evaluation unit evaluates validity of an answer to the question generated by the question generation unit. The question generating unit generates an active question when the number of questions from the participants is small.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to deal with unexpected questions during training sessions or information sessions, or when there are few active questions from participants.

[0005] The system according to the embodiment aims to generate unexpected questions and active questions during training sessions and information sessions, thereby improving the quality of the events. [Means for solving the problem]

[0006] A system according to an embodiment includes a question generating unit, an evaluation unit, and a question generating unit. The question generating unit generates questions taking personas into consideration. The evaluation unit evaluates the appropriateness of answers to the questions generated by the question generating unit. The question generating unit generates active questions when there are few questions from participants. [Effects of the Invention]

[0007] The system according to the embodiment can generate unexpected questions and active questions during training sessions and information sessions, thereby improving the quality of the events. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A training support platform according to an embodiment of the present invention is a system that utilizes a large-scale language model (LLM) to solve problems during rehearsals and actual events in training and talent acquisition, such as new employee training and company information sessions for students. The training support platform generates questions taking personas into consideration, evaluates the validity of answers to questions, and generates active questions when there are few questions from participants. For example, during rehearsals, the LLM generates questions taking personas into consideration and helps handle unexpected questions. Then, during the actual event, the LLM generates active questions even when there are few questions from participants, helping to create a lively event. The LLM also evaluates the validity of answers to questions and provides appropriate feedback. This contributes to the realization of a successful event. This training support platform can solve problems during rehearsals and actual events in training and talent acquisition, such as new employee training and company information sessions for students, and contribute to the realization of a successful event. For example, unexpected questions can be easily handled during rehearsals, and the LLM generates active questions even when there are few questions from participants during the actual event, helping to create a lively event. The LLM also evaluates the validity of answers to questions and provides appropriate feedback to improve the quality of answers.

[0029] A training support platform according to an embodiment includes a question generation unit, an evaluation unit, and a question generation unit. The question generation unit generates questions taking personas into consideration. Questions taking personas into consideration include, for example, factors such as age, occupation, and interests. For example, the question generation unit generates questions about a company's business operations and career paths for entry-level employees. The question generation unit can also generate questions about internships and the recruitment process for students. The question generation unit generates active questions when there are few questions from participants. For example, if participants do not ask questions, the question generation unit automatically generates questions to support the progress of the event. The evaluation unit evaluates the appropriateness of answers to the generated questions. Criteria for evaluating the appropriateness include, for example, accuracy, consistency, and relevance. For example, the evaluation unit evaluates whether answers to questions generated during a rehearsal are appropriate and points out areas for improvement as necessary. The evaluation unit can also provide appropriate feedback to improve the quality of the answers. This enables the training support platform according to an embodiment to generate questions taking personas into consideration, evaluate the appropriateness of answers, and generate active questions. For example, it makes it easier to handle unexpected questions during rehearsals, and even if there are few questions from participants during the actual event, the question generation unit will generate lively questions to help liven up the event.In addition, the evaluation unit will evaluate the validity of answers to questions and provide appropriate feedback, improving the quality of answers.

[0030] The question generation unit can generate questions taking into account the characteristics of new employees or students. The characteristics of new employees or students include, for example, years of experience, learning style, and field of expertise. For new employees, the question generation unit generates questions about the company's business operations and career paths. For students, the question generation unit can also generate questions about internships and the hiring process. This enables questions to be generated according to the characteristics of participants. Some or all of the above-described processing in the question generation unit may be performed using, or without, an LLM. For example, the question generation unit can input characteristic data of new employees or students into the LLM and have the LLM generate questions according to the characteristics.

[0031] The evaluation unit can evaluate the appropriateness of answers to generated questions and provide appropriate feedback. Appropriate feedback includes, for example, suggestions for improvement and specific advice. For example, the evaluation unit evaluates whether answers to questions generated during rehearsal are appropriate and suggests improvements as necessary. The evaluation unit can also provide appropriate feedback to improve the quality of the answers. This enables the evaluation of the appropriateness of answers and the provision of feedback. Some or all of the above-described processing in the evaluation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the evaluation unit can input the generated questions and their answers into an LLM and cause the LLM to evaluate the appropriateness of the answers and generate feedback.

[0032] The question generation unit can automatically generate questions when there are few questions from participants. Specific criteria for determining whether there are few questions include, for example, the number of questions within a certain period of time and the participants' reactions. For example, the question generation unit can automatically generate questions when participants do not ask questions, thereby supporting the progress of the event. The question generation unit can also monitor participants' reactions in real time and automatically generate questions when it determines that there are few questions. This enables active question generation even when there are few questions from participants. Some or all of the above-mentioned processing in the question generation unit may be performed using, or without, an LLM. For example, the question generation unit can input participant reaction data into an LLM and have the LLM execute automatic question generation.

[0033] The evaluation unit can evaluate the quality of answers to questions generated during rehearsal and suggest areas for improvement as necessary. Specific situations and conditions during rehearsal include, for example, a mock session, a pre-practice session, etc. The evaluation unit can evaluate, for example, whether answers to questions generated during rehearsal are appropriate and suggest areas for improvement as necessary. The evaluation unit can also provide appropriate feedback to improve the quality of the answers. This makes it possible to improve the quality of answers during rehearsal. Some or all of the above-described processing by the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input questions generated during rehearsal and their answers into an LLM, and cause the LLM to evaluate the quality of the answers and generate feedback.

[0034] The question generation unit can generate active questions to support the progress of the event. Specific methods and criteria for supporting the progress of the event include, for example, timekeeping and promoting discussion. The question generation unit, for example, generates active questions at appropriate times to ensure smooth progress of the event. The question generation unit can also generate questions that attract the interest of participants to promote discussion. This enables the generation of active questions to support the progress of the event. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input event progress status data into the LLM and cause the LLM to generate active questions.

[0035] When generating a question, the question generation unit can generate an appropriate question by referring to past event data. Past event data includes, for example, past question content, participant feedback, and the like. For example, the question generation unit generates a similar question based on questions that frequently appeared in past events. The question generation unit can also generate questions based on topics in which participants were interested in past events. The question generation unit can also generate improved questions by referring to feedback from past events. This makes it possible to generate optimal questions by referring to past event data. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input past event data into an LLM and cause the LLM to generate optimal questions.

[0036] When generating questions, the question generation unit can adjust the difficulty of the questions according to the expertise level of the participants. Expertise levels include, for example, beginner, intermediate, and advanced. For example, the question generation unit generates basic questions for beginners. The question generation unit can also generate applied questions for intermediate users. The question generation unit can also generate specialized questions for advanced users. This makes it possible to adjust the difficulty of questions according to the expertise level of the participants. Some or all of the above-mentioned processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input expertise level data of the participants into the LLM and cause the LLM to generate questions according to the difficulty level.

[0037] When generating questions, the question generation unit can select themes for the questions based on the interests and concerns of the participants. The question generation unit, for example, generates questions based on topics in which the participants are interested. The question generation unit can also generate questions based on themes in which the participants have previously shown interest. The question generation unit can also generate related questions by referring to the profile information of the participants. This makes it possible to select themes for questions based on the interests and concerns of the participants. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input the interest and concern data of the participants into the LLM and cause the LLM to generate questions based on the themes.

[0038] When generating a question, the question generation unit can analyze the participant's past question history and generate a unique question. The past question history includes, for example, the content of the question, frequency, and quality of the answer. The question generation unit, for example, generates a new question by avoiding questions previously asked by the participant. The question generation unit can also analyze the participant's past question history and generate a new but related question. The question generation unit can also generate a question based on a topic in which the participant previously showed interest but has not yet resolved. This makes it possible to analyze the participant's past question history and generate a unique question. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input the participant's past question history data into an LLM and cause the LLM to generate a unique question.

[0039] The question generation unit can generate relevant questions by taking into account the geographical location information of participants when generating questions. Geographical location information includes, for example, GPS data, IP addresses, etc. The question generation unit can generate questions related to the location of participants, for example. The question generation unit can also generate questions based on the characteristics of the participants' regions. The question generation unit can also generate relevant questions by taking into account the geographical background of participants. This makes it possible to generate questions that take into account the geographical location information of participants. Some or all of the above-described processing in the question generation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the question generation unit can input the geographical location information data of participants into an LLM and cause the LLM to generate relevant questions.

[0040] When generating questions, the question generation unit can analyze the participants' social media activities and generate relevant questions. Social media activities include, for example, the content of posts, the number of followers, and the engagement rate. The question generation unit can generate questions based on, for example, topics in which the participants have shown interest on social media. The question generation unit can also analyze the content of the participants' social media posts and generate relevant questions. The question generation unit can also generate relevant questions by referring to the activities of the participants' friends on social media. This makes it possible to generate questions based on the analysis of the participants' social media activities. Some or all of the above-described processing in the question generation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the question generation unit can input the participants' social media activity data into the LLM and cause the LLM to generate relevant questions.

[0041] When generating a question, the question generation unit can customize the question content by reflecting the participants' past feedback. Past feedback includes, for example, participants' evaluation comments, improvement suggestions, and the like. The question generation unit adjusts the question content based on, for example, feedback provided by participants in the past. The question generation unit can also analyze the participants' past feedback and generate questions that reflect improvements. The question generation unit can also generate more appropriate questions by referring to the participants' feedback. This makes it possible to customize the question content by reflecting the participants' past feedback. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input the participants' past feedback data into the LLM and cause the LLM to generate questions that reflect the feedback.

[0042] The evaluation unit can improve the accuracy of the evaluation by referring to past response data during evaluation. The past response data includes, for example, the content of the response, the evaluation results, and feedback. The evaluation unit can adjust the evaluation criteria, for example, based on the past response data. The evaluation unit can also analyze the past response data to improve the accuracy of the evaluation. The evaluation unit can also maintain the consistency of the evaluation by referring to the past response data. This makes it possible to improve the accuracy of the evaluation by referring to the past response data. Some or all of the above-mentioned processing in the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input the past response data into an LLM and have the LLM adjust the evaluation criteria.

[0043] During evaluation, the evaluation unit can adjust the level of detail of the feedback based on the content of the answer. The level of detail of the feedback includes, for example, the accuracy, relevance, and depth of the answer. For example, the evaluation unit provides brief feedback for a brief answer. The evaluation unit can also provide detailed feedback for a detailed answer. The evaluation unit can also adjust the level of detail of the feedback depending on the quality of the answer. This makes it possible to adjust the level of detail of the feedback based on the content of the answer. Some or all of the above-described processing in the evaluation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the evaluation unit can input content data of the answer into an LLM and cause the LLM to adjust the level of detail of the feedback.

[0044] During evaluation, the evaluation unit can apply different evaluation algorithms depending on the category of the answer. Answer categories include, for example, technical answers, business answers, and creative answers. For example, the evaluation unit applies a technical evaluation algorithm to technical answers. The evaluation unit can also apply a business evaluation algorithm to business-related answers. The evaluation unit can also apply a personnel evaluation algorithm to personnel-related answers. This makes it possible to apply an evaluation algorithm depending on the category of the answer. Some or all of the above-described processing in the evaluation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the evaluation unit can input answer category data into the LLM and cause the LLM to apply an evaluation algorithm depending on the category.

[0045] The evaluation unit can perform evaluations taking into account the attribute information of the answer submitter. The attribute information includes, for example, age, gender, occupation, and years of experience. For example, the evaluation unit can evaluate answers from entry-level employees, taking into account their lack of experience. The evaluation unit can also evaluate answers from students, taking into account their academic background. The evaluation unit can also evaluate answers from veteran employees, taking into account their experience. This enables evaluations that take into account the attribute information of the answer submitter. Some or all of the above-described processing by the evaluation unit can be performed using, or without, an LLM. For example, the evaluation unit can input attribute information data of the answer submitter into the LLM and have the LLM perform an evaluation based on the attribute information.

[0046] During evaluation, the evaluation unit can weight the evaluation based on the time of submission of the answer. The submission time includes, for example, the submission date and time, the submission deadline, and the submission frequency. For example, the evaluation unit can give a higher score to an answer submitted early. The evaluation unit can also give a lower score to an answer submitted just before the deadline. The evaluation unit can also adjust the weighting of the evaluation depending on the time of submission. This enables the weighting of the evaluation based on the time of submission of the answer. Some or all of the above-described processing in the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input data on the time of submission of the answer into the LLM and cause the LLM to weight the evaluation based on the time of submission.

[0047] During evaluation, the evaluation unit can improve the accuracy of the evaluation by referring to literature related to the answer. Examples of related literature include academic papers, technical reports, and industry news. For example, the evaluation unit can improve the accuracy of the evaluation by referring to literature related to the answer. The evaluation unit can also compare the content of the answer with related literature and perform the evaluation. The evaluation unit can also evaluate the validity of the answer based on the related literature. This makes it possible to improve the accuracy of the evaluation by referring to the literature related to the answer. Some or all of the above-described processing in the evaluation unit can be performed using, or without, an LLM. For example, the evaluation unit can input related literature data into the LLM and cause the LLM to improve the accuracy of the evaluation based on the literature.

[0048] The evaluation unit can perform the evaluation by taking into account the market value of the answer. Market value includes, for example, sales forecast, market share, and competitive analysis. For example, the evaluation unit can assign a high rating to an answer if it has practicality in the market. The evaluation unit can also assign a high rating to an answer if it is competitive in the market. The evaluation unit can also assign a high rating to an answer if it meets market demand. This enables evaluation that takes into account the market value of the answer. Some or all of the above-described processing in the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input market value data of the answer into the LLM and cause the LLM to perform an evaluation based on the market value.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The training support platform can further include a learning history reference unit that references the participant's past learning history. The learning history reference unit collects data such as past training content, grades, and feedback. This allows the question generation unit and evaluation unit to take appropriate measures based on the participant's past learning history. For example, for a participant who has struggled with a particular topic in the past, basic questions related to that topic can be generated. Also, for topics that have received high marks in the past, applied questions can be generated. Furthermore, based on past feedback, the evaluation unit can provide specific advice to encourage the participant's growth. This makes it possible to provide individualized support based on the participant's learning history.

[0051] The training support platform can further include a social media analysis unit that analyzes participants' social media activity. The social media analysis unit collects data such as participants' posted content, number of followers, and engagement rate. This allows the question generation unit and evaluation unit to take appropriate action based on participants' social media activity. For example, questions can be generated based on topics in which participants have shown interest on social media. Related questions can also be generated by analyzing participants' social media posts. Furthermore, related questions can be generated by taking into account the activities of participants' friends on social media. This makes it possible to generate questions based on an analysis of participants' social media activity.

[0052] The training support platform may further include a geographic information consideration unit that generates relevant questions by taking into account the geographic location information of participants. The geographic information consideration unit collects data such as GPS data and IP addresses. This allows the question generation unit to generate questions related to the location of the participants. For example, questions can be generated based on the characteristics of the participants' regions. Relevant questions can also be generated by taking into account the geographic background of the participants. Furthermore, the geographic information consideration unit can generate questions related to issues or interests specific to the region based on the participants' geographic location information. This makes it possible to generate questions that take into account the participants' geographic location information.

[0053] The training support platform can further include an expertise level adjustment unit that adjusts the difficulty of questions according to the expertise level of the participants. The expertise level adjustment unit collects data such as beginner, intermediate, and advanced. This allows the question generation unit to generate questions according to the expertise level of the participants. For example, basic questions can be generated for beginners, applied questions can be generated for intermediate learners, and specialized questions can be generated for advanced learners. This makes it possible to adjust the difficulty of questions according to the expertise level of the participants.

[0054] The training support platform may further include a question history analysis unit that analyzes participants' past question history and generates unique questions. The question history analysis unit collects data such as the content, frequency, and quality of answers of past questions. This allows the question generation unit to generate new questions based on the participants' past question history. For example, new questions can be generated that avoid questions previously asked by the participants. Also, the past question history of the participants can be analyzed to generate new but related questions. Furthermore, questions can be generated based on topics that the participants have shown interest in in the past but have not yet been resolved. This makes it possible to analyze the participants' past question history and generate unique questions.

[0055] The training support platform may further include a feedback reflection unit that customizes the content of questions by reflecting participants' past feedback. The feedback reflection unit collects data such as participants' evaluation comments and improvement suggestions. This allows the question generation unit to adjust the content of questions based on participants' past feedback. For example, the question content can be adjusted based on feedback provided by participants in the past. Furthermore, the past feedback of participants can be analyzed and questions that reflect improvements can be generated. Furthermore, more appropriate questions can be generated by referring to participants' feedback. This makes it possible to customize the content of questions by reflecting participants' past feedback.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The question generator generates questions taking into account the persona. Personas include factors such as age, occupation, and interests. For example, questions about the company's business operations and career paths are generated for new employees, while questions about internships and the recruitment process are generated for students. Step 2: The question generator generates active questions when there are few questions from participants. For example, if participants do not ask questions, the question generator automatically generates questions to support the progress of the event. Step 3: The evaluator evaluates the appropriateness of the answers to the questions generated. The evaluation of appropriateness includes criteria such as accuracy, consistency, and relevance. For example, the evaluator evaluates whether the answers to the questions generated during the rehearsal are appropriate and, if necessary, points out areas for improvement. The evaluator also provides appropriate feedback to improve the quality of the answers.

[0058] (Example 2) A training support platform according to an embodiment of the present invention is a system that utilizes a large-scale language model (LLM) to solve problems during rehearsals and actual events in training and talent acquisition, such as new employee training and company information sessions for students. The training support platform generates questions taking personas into consideration, evaluates the validity of answers to questions, and generates active questions when there are few questions from participants. For example, during rehearsals, the LLM generates questions taking personas into consideration and helps handle unexpected questions. Then, during the actual event, the LLM generates active questions even when there are few questions from participants, helping to create a lively event. The LLM also evaluates the validity of answers to questions and provides appropriate feedback. This contributes to the realization of a successful event. This training support platform can solve problems during rehearsals and actual events in training and talent acquisition, such as new employee training and company information sessions for students, and contribute to the realization of a successful event. For example, unexpected questions can be easily handled during rehearsals, and the LLM generates active questions even when there are few questions from participants during the actual event, helping to create a lively event. The LLM also evaluates the validity of answers to questions and provides appropriate feedback to improve the quality of answers.

[0059] A training support platform according to an embodiment includes a question generation unit, an evaluation unit, and a question generation unit. The question generation unit generates questions taking personas into consideration. Questions taking personas into consideration include, for example, factors such as age, occupation, and interests. For example, the question generation unit generates questions about a company's business operations and career paths for entry-level employees. The question generation unit can also generate questions about internships and the recruitment process for students. The question generation unit generates active questions when there are few questions from participants. For example, if participants do not ask questions, the question generation unit automatically generates questions to support the progress of the event. The evaluation unit evaluates the appropriateness of answers to the generated questions. Criteria for evaluating the appropriateness include, for example, accuracy, consistency, and relevance. For example, the evaluation unit evaluates whether answers to questions generated during a rehearsal are appropriate and points out areas for improvement as necessary. The evaluation unit can also provide appropriate feedback to improve the quality of the answers. This enables the training support platform according to an embodiment to generate questions taking personas into consideration, evaluate the appropriateness of answers, and generate active questions. For example, it makes it easier to handle unexpected questions during rehearsals, and even if there are few questions from participants during the actual event, the question generation unit will generate lively questions to help liven up the event.In addition, the evaluation unit will evaluate the validity of answers to questions and provide appropriate feedback, improving the quality of answers.

[0060] The question generation unit can generate questions taking into account the characteristics of new employees or students. The characteristics of new employees or students include, for example, years of experience, learning style, and field of expertise. For new employees, the question generation unit generates questions about the company's business operations and career paths. For students, the question generation unit can also generate questions about internships and the hiring process. This enables questions to be generated according to the characteristics of participants. Some or all of the above-described processing in the question generation unit may be performed using, or without, an LLM. For example, the question generation unit can input characteristic data of new employees or students into the LLM and have the LLM generate questions according to the characteristics.

[0061] The evaluation unit can evaluate the appropriateness of answers to generated questions and provide appropriate feedback. Appropriate feedback includes, for example, suggestions for improvement and specific advice. For example, the evaluation unit evaluates whether answers to questions generated during rehearsal are appropriate and suggests improvements as necessary. The evaluation unit can also provide appropriate feedback to improve the quality of the answers. This enables the evaluation of the appropriateness of answers and the provision of feedback. Some or all of the above-described processing in the evaluation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the evaluation unit can input the generated questions and their answers into an LLM and cause the LLM to evaluate the appropriateness of the answers and generate feedback.

[0062] The question generation unit can automatically generate questions when there are few questions from participants. Specific criteria for determining whether there are few questions include, for example, the number of questions within a certain period of time and the participants' reactions. For example, the question generation unit can automatically generate questions when participants do not ask questions, thereby supporting the progress of the event. The question generation unit can also monitor participants' reactions in real time and automatically generate questions when it determines that there are few questions. This enables active question generation even when there are few questions from participants. Some or all of the above-mentioned processing in the question generation unit may be performed using, or without, an LLM. For example, the question generation unit can input participant reaction data into an LLM and have the LLM execute automatic question generation.

[0063] The evaluation unit can evaluate the quality of answers to questions generated during rehearsal and suggest areas for improvement as necessary. Specific situations and conditions during rehearsal include, for example, a mock session, a pre-practice session, etc. The evaluation unit can evaluate, for example, whether answers to questions generated during rehearsal are appropriate and suggest areas for improvement as necessary. The evaluation unit can also provide appropriate feedback to improve the quality of the answers. This makes it possible to improve the quality of answers during rehearsal. Some or all of the above-described processing by the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input questions generated during rehearsal and their answers into an LLM, and cause the LLM to evaluate the quality of the answers and generate feedback.

[0064] The question generation unit can generate active questions to support the progress of the event. Specific methods and criteria for supporting the progress of the event include, for example, timekeeping and promoting discussion. The question generation unit, for example, generates active questions at appropriate times to ensure smooth progress of the event. The question generation unit can also generate questions that attract the interest of participants to promote discussion. This enables the generation of active questions to support the progress of the event. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input event progress status data into the LLM and cause the LLM to generate active questions.

[0065] The question generation unit can estimate the emotions of participants and adjust the content and timing of questions based on the estimated emotions. For example, if a participant is nervous, the question generation unit can generate simple questions to relax them. Furthermore, if a participant is excited, the question generation unit can generate detailed questions to pique their interest. Furthermore, if a participant is tired, the question generation unit can generate short and concise questions. This enables the content and timing of questions to be adjusted according to the emotions of the participants. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the question generation unit can be performed using, for example, an LLM, or without an LLM. For example, the question generation unit can input emotion data of participants into an LLM and cause the LLM to adjust the content and timing of questions based on their emotions.

[0066] When generating a question, the question generation unit can generate an appropriate question by referring to past event data. Past event data includes, for example, past question content, participant feedback, and the like. For example, the question generation unit generates a similar question based on questions that frequently appeared in past events. The question generation unit can also generate questions based on topics in which participants were interested in past events. The question generation unit can also generate improved questions by referring to feedback from past events. This makes it possible to generate optimal questions by referring to past event data. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input past event data into an LLM and cause the LLM to generate optimal questions.

[0067] When generating questions, the question generation unit can adjust the difficulty of the questions according to the expertise level of the participants. Expertise levels include, for example, beginner, intermediate, and advanced. For example, the question generation unit generates basic questions for beginners. The question generation unit can also generate applied questions for intermediate users. The question generation unit can also generate specialized questions for advanced users. This makes it possible to adjust the difficulty of questions according to the expertise level of the participants. Some or all of the above-mentioned processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input expertise level data of the participants into the LLM and cause the LLM to generate questions according to the difficulty level.

[0068] When generating questions, the question generation unit can select themes for the questions based on the interests and concerns of the participants. The question generation unit, for example, generates questions based on topics in which the participants are interested. The question generation unit can also generate questions based on themes in which the participants have previously shown interest. The question generation unit can also generate related questions by referring to the profile information of the participants. This makes it possible to select themes for questions based on the interests and concerns of the participants. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input the interest and concern data of the participants into the LLM and cause the LLM to generate questions based on the themes.

[0069] When generating a question, the question generation unit can analyze the participant's past question history and generate a unique question. The past question history includes, for example, the content of the question, frequency, and quality of the answer. The question generation unit, for example, generates a new question by avoiding questions previously asked by the participant. The question generation unit can also analyze the participant's past question history and generate a new but related question. The question generation unit can also generate a question based on a topic in which the participant previously showed interest but has not yet resolved. This makes it possible to analyze the participant's past question history and generate a unique question. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input the participant's past question history data into an LLM and cause the LLM to generate a unique question.

[0070] The question generation unit can estimate the emotions of participants and prioritize questions based on the estimated emotions. For example, if a participant is excited, the question generation unit can prioritize questions that pique their interest. Furthermore, if a participant is nervous, the question generation unit can prioritize questions that relax them. Furthermore, if a participant is tired, the question generation unit can prioritize questions that are easy to understand. This enables prioritization of questions based on participants' emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., an LLM) or a multimodal generation AI. Some or all of the above-described processing in the question generation unit can be performed using, for example, an LLM, or without an LLM. For example, the question generation unit can input participants' emotion data into an LLM and cause the LLM to prioritize questions based on their emotions.

[0071] The question generation unit can generate relevant questions by taking into account the geographical location information of participants when generating questions. Geographical location information includes, for example, GPS data, IP addresses, etc. The question generation unit can generate questions related to the location of participants, for example. The question generation unit can also generate questions based on the characteristics of the participants' regions. The question generation unit can also generate relevant questions by taking into account the geographical background of participants. This makes it possible to generate questions that take into account the geographical location information of participants. Some or all of the above-described processing in the question generation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the question generation unit can input the geographical location information data of participants into an LLM and cause the LLM to generate relevant questions.

[0072] When generating questions, the question generation unit can analyze the participants' social media activities and generate relevant questions. Social media activities include, for example, the content of posts, the number of followers, and the engagement rate. The question generation unit can generate questions based on, for example, topics in which the participants have shown interest on social media. The question generation unit can also analyze the content of the participants' social media posts and generate relevant questions. The question generation unit can also generate relevant questions by referring to the activities of the participants' friends on social media. This makes it possible to generate questions based on the analysis of the participants' social media activities. Some or all of the above-described processing in the question generation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the question generation unit can input the participants' social media activity data into the LLM and cause the LLM to generate relevant questions.

[0073] When generating a question, the question generation unit can customize the question content by reflecting the participants' past feedback. Past feedback includes, for example, participants' evaluation comments, improvement suggestions, and the like. The question generation unit adjusts the question content based on, for example, feedback provided by participants in the past. The question generation unit can also analyze the participants' past feedback and generate questions that reflect improvements. The question generation unit can also generate more appropriate questions by referring to the participants' feedback. This makes it possible to customize the question content by reflecting the participants' past feedback. Some or all of the above-described processing in the question generation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the question generation unit can input the participants' past feedback data into the LLM and cause the LLM to generate questions that reflect the feedback.

[0074] The evaluation unit can estimate the emotions of the participants and adjust the evaluation criteria for the answers based on the estimated emotions. For example, if the participant is nervous, the evaluation unit can apply gentle evaluation criteria. If the participant is relaxed, the evaluation unit can also apply strict evaluation criteria. If the participant is excited, the evaluation unit can also apply detailed evaluation criteria. This enables the adjustment of the evaluation criteria for the answers based on the participants' emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the evaluation unit can be performed using, for example, an LLM, or without an LLM. For example, the evaluation unit can input the participants' emotion data into an LLM and cause the LLM to adjust the evaluation criteria based on the emotions.

[0075] The evaluation unit can improve the accuracy of the evaluation by referring to past response data during evaluation. The past response data includes, for example, the content of the response, the evaluation results, and feedback. The evaluation unit can adjust the evaluation criteria, for example, based on the past response data. The evaluation unit can also analyze the past response data to improve the accuracy of the evaluation. The evaluation unit can also maintain the consistency of the evaluation by referring to the past response data. This makes it possible to improve the accuracy of the evaluation by referring to the past response data. Some or all of the above-mentioned processing in the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input the past response data into an LLM and have the LLM adjust the evaluation criteria.

[0076] During evaluation, the evaluation unit can adjust the level of detail of the feedback based on the content of the answer. The level of detail of the feedback includes, for example, the accuracy, relevance, and depth of the answer. For example, the evaluation unit provides brief feedback for a brief answer. The evaluation unit can also provide detailed feedback for a detailed answer. The evaluation unit can also adjust the level of detail of the feedback depending on the quality of the answer. This makes it possible to adjust the level of detail of the feedback based on the content of the answer. Some or all of the above-described processing in the evaluation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the evaluation unit can input content data of the answer into an LLM and cause the LLM to adjust the level of detail of the feedback.

[0077] During evaluation, the evaluation unit can apply different evaluation algorithms depending on the category of the answer. Answer categories include, for example, technical answers, business answers, and creative answers. For example, the evaluation unit applies a technical evaluation algorithm to technical answers. The evaluation unit can also apply a business evaluation algorithm to business-related answers. The evaluation unit can also apply a personnel evaluation algorithm to personnel-related answers. This makes it possible to apply an evaluation algorithm depending on the category of the answer. Some or all of the above-described processing in the evaluation unit may be performed using, for example, an LLM, or may be performed without using an LLM. For example, the evaluation unit can input answer category data into the LLM and cause the LLM to apply an evaluation algorithm depending on the category.

[0078] The evaluation unit can perform evaluations taking into account the attribute information of the answer submitter. The attribute information includes, for example, age, gender, occupation, and years of experience. For example, the evaluation unit can evaluate answers from entry-level employees, taking into account their lack of experience. The evaluation unit can also evaluate answers from students, taking into account their academic background. The evaluation unit can also evaluate answers from veteran employees, taking into account their experience. This enables evaluations that take into account the attribute information of the answer submitter. Some or all of the above-described processing by the evaluation unit can be performed using, or without, an LLM. For example, the evaluation unit can input attribute information data of the answer submitter into the LLM and have the LLM perform an evaluation based on the attribute information.

[0079] The evaluation unit can estimate the emotions of the participants and prioritize feedback based on the estimated emotions. For example, if a participant is nervous, the evaluation unit can prioritize providing relaxing feedback. Furthermore, if a participant is excited, the evaluation unit can prioritize detailed feedback. Furthermore, if a participant is tired, the evaluation unit can prioritize concise feedback. This enables prioritization of feedback based on the participants' emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the evaluation unit can be performed using, for example, an LLM, or without an LLM. For example, the evaluation unit can input emotion data of the participants into an LLM and cause the LLM to prioritize feedback based on emotions.

[0080] During evaluation, the evaluation unit can weight the evaluation based on the time of submission of the answer. The submission time includes, for example, the submission date and time, the submission deadline, and the submission frequency. For example, the evaluation unit can give a higher score to an answer submitted early. The evaluation unit can also give a lower score to an answer submitted just before the deadline. The evaluation unit can also adjust the weighting of the evaluation depending on the time of submission. This enables the weighting of the evaluation based on the time of submission of the answer. Some or all of the above-described processing in the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input data on the time of submission of the answer into the LLM and cause the LLM to weight the evaluation based on the time of submission.

[0081] During evaluation, the evaluation unit can improve the accuracy of the evaluation by referring to literature related to the answer. Examples of related literature include academic papers, technical reports, and industry news. For example, the evaluation unit can improve the accuracy of the evaluation by referring to literature related to the answer. The evaluation unit can also compare the content of the answer with related literature and perform the evaluation. The evaluation unit can also evaluate the validity of the answer based on the related literature. This makes it possible to improve the accuracy of the evaluation by referring to the literature related to the answer. Some or all of the above-described processing in the evaluation unit can be performed using, or without, an LLM. For example, the evaluation unit can input related literature data into the LLM and cause the LLM to improve the accuracy of the evaluation based on the literature.

[0082] The evaluation unit can perform the evaluation by taking into account the market value of the answer. Market value includes, for example, sales forecast, market share, and competitive analysis. For example, the evaluation unit can assign a high rating to an answer if it has practicality in the market. The evaluation unit can also assign a high rating to an answer if it is competitive in the market. The evaluation unit can also assign a high rating to an answer if it meets market demand. This enables evaluation that takes into account the market value of the answer. Some or all of the above-described processing in the evaluation unit can be performed using, for example, an LLM, or can be performed without using an LLM. For example, the evaluation unit can input market value data of the answer into the LLM and cause the LLM to perform an evaluation based on the market value. === Hard Collateral 1-1 === Each of the multiple elements including the question generation unit and the evaluation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, question generation taking personas into consideration is performed by the processor 46 of the smart device 14 or the processor 28 of the data processing device 12. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the validity of answers to the generated questions. For example, the evaluation unit evaluates the validity of the answers using an emotion identification model 59 stored in the storage 32 of the data processing device 12 and provides appropriate feedback. === Hard Collateral 1-2 === Each of the multiple elements including the question generator and evaluator described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the question generator is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, question generation taking into account the persona is performed by the processor 46 of the smart glasses 214 or the processor 28 of the data processing device 12. The evaluator is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the validity of an answer to the generated question. For example, the evaluator evaluates the validity of the answer using an emotion identification model 59 stored in the storage 32 of the data processing device 12 and provides appropriate feedback. === Hard Collateral 1-3 === Each of the multiple elements including the question generation unit and the evaluation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, question generation taking personas into consideration is performed by the processor 46 of the headset type terminal 314 or the processor 28 of the data processing device 12. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the appropriateness of answers to the generated questions. For example, the evaluation unit evaluates the appropriateness of the answers using an emotion identification model 59 stored in the storage 32 of the data processing device 12 and provides appropriate feedback. === Hard Collateral 1-4 === Each of the multiple elements including the question generation unit and the evaluation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the question generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, question generation taking personas into consideration is performed by the processor 46 of the robot 414 or the processor 28 of the data processing device 12. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the appropriateness of an answer to the generated question. For example, the evaluation unit evaluates the appropriateness of the answer using an emotion identification model 59 stored in the storage 32 of the data processing device 12, and provides appropriate feedback.

[0083] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0084] The training support platform may further include a biometric information acquisition unit that acquires real-time biometric information of participants. The biometric information acquisition unit collects data such as heart rate, electrodermal activity, and body temperature. This allows the participant's level of tension and concentration to be grasped in real time, and the question generation unit and evaluation unit can take appropriate measures based on that information. For example, if the heart rate is rising, the question generation unit can generate a simple question to help the participant relax. If the electrodermal activity is decreasing, the evaluation unit can determine that the participant is tired and provide concise feedback. Furthermore, if the body temperature is rising, the question generation unit can generate a detailed question that will attract the participant's attention. This enables flexible responses based on the participant's biometric information.

[0085] The training support platform can further include a learning history reference unit that references the participant's past learning history. The learning history reference unit collects data such as past training content, grades, and feedback. This allows the question generation unit and evaluation unit to take appropriate measures based on the participant's past learning history. For example, for a participant who has struggled with a particular topic in the past, basic questions related to that topic can be generated. Also, for topics that have received high marks in the past, applied questions can be generated. Furthermore, based on past feedback, the evaluation unit can provide specific advice to encourage the participant's growth. This makes it possible to provide individualized support based on the participant's learning history.

[0086] The training support platform can further include a social media analysis unit that analyzes participants' social media activity. The social media analysis unit collects data such as participants' posted content, number of followers, and engagement rate. This allows the question generation unit and evaluation unit to take appropriate action based on participants' social media activity. For example, questions can be generated based on topics in which participants have shown interest on social media. Related questions can also be generated by analyzing participants' social media posts. Furthermore, related questions can be generated by taking into account the activities of participants' friends on social media. This makes it possible to generate questions based on an analysis of participants' social media activity.

[0087] The training support platform may further include a feedback adjustment unit that estimates the participant's emotions and adjusts the content of the feedback based on the estimated emotions. For example, if the participant is nervous, the feedback adjustment unit may provide gentle feedback to help the participant relax. If the participant is excited, the feedback adjustment unit may provide detailed feedback. If the participant is tired, the feedback adjustment unit may provide brief feedback. This enables the content of the feedback to be adjusted based on the participant's emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the feedback adjustment unit may be performed using, for example, an LLM, or without an LLM. For example, the feedback adjustment unit may input the participant's emotion data into an LLM and cause the LLM to adjust the content of the feedback based on the emotion.

[0088] The training support platform may further include a geographic information consideration unit that generates relevant questions by taking into account the geographic location information of participants. The geographic information consideration unit collects data such as GPS data and IP addresses. This allows the question generation unit to generate questions related to the location of the participants. For example, questions can be generated based on the characteristics of the participants' regions. Relevant questions can also be generated by taking into account the geographic background of the participants. Furthermore, the geographic information consideration unit can generate questions related to issues or interests specific to the region based on the participants' geographic location information. This makes it possible to generate questions that take into account the participants' geographic location information.

[0089] The training support platform can further include an expertise level adjustment unit that adjusts the difficulty of questions according to the expertise level of the participants. The expertise level adjustment unit collects data such as beginner, intermediate, and advanced. This allows the question generation unit to generate questions according to the expertise level of the participants. For example, basic questions can be generated for beginners, applied questions can be generated for intermediate learners, and specialized questions can be generated for advanced learners. This makes it possible to adjust the difficulty of questions according to the expertise level of the participants.

[0090] The training support platform may further include a question prioritization unit that estimates participants' emotions and prioritizes questions based on the estimated emotions. For example, if a participant is excited, the question prioritization unit may prioritize questions that pique the participants' interest. Furthermore, if a participant is nervous, the question prioritization unit may prioritize questions that relax the participants. Furthermore, if a participant is tired, the question prioritization unit may prioritize questions that ease the participants' emotions. The emotion estimation may be achieved using, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the question prioritization unit may be performed using, for example, an LLM, or without an LLM. For example, the question prioritization unit may input participants' emotion data into an LLM and cause the LLM to prioritize questions based on their emotions.

[0091] The training support platform may further include a question history analysis unit that analyzes participants' past question history and generates unique questions. The question history analysis unit collects data such as the content, frequency, and quality of answers of past questions. This allows the question generation unit to generate new questions based on the participants' past question history. For example, new questions can be generated that avoid questions previously asked by the participants. Also, the past question history of the participants can be analyzed to generate new but related questions. Furthermore, questions can be generated based on topics that the participants have shown interest in in the past but have not yet been resolved. This makes it possible to analyze the participants' past question history and generate unique questions.

[0092] The training support platform may further include a feedback reflection unit that customizes the content of questions by reflecting participants' past feedback. The feedback reflection unit collects data such as participants' evaluation comments and improvement suggestions. This allows the question generation unit to adjust the content of questions based on participants' past feedback. For example, the question content can be adjusted based on feedback provided by participants in the past. Furthermore, the past feedback of participants can be analyzed and questions that reflect improvements can be generated. Furthermore, more appropriate questions can be generated by referring to participants' feedback. This makes it possible to customize the content of questions by reflecting participants' past feedback.

[0093] The training support platform may further include an evaluation criterion adjustment unit that estimates the participant's emotions and adjusts the evaluation criteria for the answers based on the estimated emotions. For example, the evaluation criterion adjustment unit may apply gentle evaluation criteria if the participant is nervous. Furthermore, it may apply strict evaluation criteria if the participant is relaxed. Furthermore, it may apply detailed evaluation criteria if the participant is excited. This enables the adjustment of the evaluation criteria for the answers based on the participant's emotions. The emotion estimation is realized, for example, using an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation criterion adjustment unit may be performed using, for example, an LLM, or without an LLM. For example, the evaluation criterion adjustment unit may input the participant's emotion data into an LLM and cause the LLM to adjust the evaluation criteria based on the emotion.

[0094] The processing flow of the second embodiment will be briefly explained below.

[0095] Step 1: The question generator generates questions taking into account the persona. Personas include factors such as age, occupation, and interests. For example, questions about the company's business operations and career paths are generated for new employees, while questions about internships and the recruitment process are generated for students. Step 2: The question generator generates active questions when there are few questions from participants. For example, if participants do not ask questions, the question generator automatically generates questions to support the progress of the event. Step 3: The evaluator evaluates the appropriateness of the answers to the questions generated. The evaluation of appropriateness includes criteria such as accuracy, consistency, and relevance. For example, the evaluator evaluates whether the answers to the questions generated during the rehearsal are appropriate and, if necessary, points out areas for improvement. The evaluator also provides appropriate feedback to improve the quality of the answers.

[0096] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0097] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0098] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0099] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0100] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0101] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0103] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0104] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0107] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0108] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0110] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0111] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0115] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0140] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0150] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0152] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0153] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0154] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0156] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0158] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0160] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0161] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0167] [Explanation of symbols]

[0168] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a persona-based question generation unit; an evaluation unit that evaluates the validity of answers to questions generated by the evaluation unit; a question generation unit that generates active questions when there are few questions from participants; Equipped with A system characterized by:

2. The question generation unit Generate questions taking into account the characteristics of new employees or students 2. The system of claim 1.

3. The evaluation unit Evaluate the validity of answers to generated questions and provide appropriate feedback 2. The system of claim 1.

4. The question generation unit Auto-generate questions when there are few questions from participants 2. The system of claim 1.

5. The evaluation unit Evaluate the quality of responses to questions generated during rehearsals and suggest improvements where necessary 2. The system of claim 1.

6. The question generation unit Generate lively questions to support the event 2. The system of claim 1.

7. The question generation unit Estimate participants' emotions and adjust the content and timing of questions based on those emotions 2. The system of claim 1.

8. The question generation unit When generating questions, refer to past event data to generate appropriate questions 2. The system of claim 1.

Images