system

Abstract

The system according to the embodiment aims to efficiently conduct a seminar and respond to questions from participants. [Solution] A system according to an embodiment includes a seminar proceeding unit, a question receiving unit, an answer providing unit, and a learning unit. The seminar proceeding unit proceeds with the seminar. The question receiving unit receives questions from participants. The answer providing unit provides answers based on the questions received by the question receiving unit. The learning unit learns and updates the answers provided by the answer providing unit.

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 relies on manual labor to conduct seminars and respond to questions from participants, making efficient management difficult.

[0005] The system according to the embodiment aims to efficiently conduct a seminar and respond to questions from participants. [Means for solving the problem]

[0006] The system according to the embodiment includes a seminar proceeding unit, a question receiving unit, an answer providing unit, and a learning unit. The seminar proceeding unit proceeds with the seminar. The question receiving unit receives questions from participants. The answer providing unit provides answers based on the questions received by the question receiving unit. The learning unit learns and updates the answers provided by the answer providing unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently conduct a seminar and respond to questions from participants. [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 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 seminar system according to an embodiment of the present invention is a system that uses a robot as a lecturer in smartphone seminars. In this seminar system, the robot plays the role of seminar manager, facilitator, and lecturer, delivering speeches and projecting materials. The robot also answers questions, concerns, and inquiries from participants. The robot learns from participants' questions and constantly upgrades itself to accommodate new questions and replies. For example, a seminar system may first include a "seminar progress unit" for the robot to conduct the seminar, delivering speeches and projecting materials. Next, a "question reception unit" is provided to accept questions from participants, and an "answer provision unit" is provided to recognize questions and provide appropriate answers. Furthermore, a "learning unit" is provided for the robot to learn questions and upgrade itself. This learning unit accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. This allows the robot to constantly provide the latest information, improving participant satisfaction. This allows the seminar system to provide a system that integrates seminar progress, question reception, answer provision, learning, and upgrades.

[0029] A seminar system according to an embodiment includes a seminar facilitator, a question receiver, an answer provider, and a learning unit. The seminar facilitator uses a robot to deliver oral presentations and project materials. For example, the robot greets participants at the start of the seminar and explains the purpose and content of the seminar. The robot can also project presentation materials onto a projector or screen to provide participants with visual information. Furthermore, the robot can monitor participants' responses during the seminar and adjust the pace and content as needed. The question receiver recognizes questions from participants. For example, the question receiver can recognize participants' oral questions using voice recognition technology. The question receiver can also receive questions via text input or a tablet device. Furthermore, the question receiver can analyze participants' facial expressions and gestures to recognize non-verbal questions and doubts. The answer provider provides appropriate answers based on the questions received by the question receiver. For example, the answer provider can provide appropriate answers by referencing a pre-prepared FAQ database. The answer provider can also generate customized answers to participants' questions using a generative AI. Furthermore, the answer providing unit can adjust the tone and expression of the answer, taking into account the emotions and reactions of the participants. The learning unit accumulates questions from participants in a database and uses AI to learn how to respond to new questions and tactics. For example, the learning unit can analyze question data from participants and identify frequently asked questions and new question patterns. The learning unit can also use a generation AI to learn variations in tactics and answers, thereby improving the accuracy of the answer providing unit. Furthermore, the learning unit can evaluate the performance of the entire system based on participant feedback and identify areas for improvement. As a result, the seminar system according to the embodiment can provide a system that integrates seminar progress, question acceptance, answer provision, learning, and version upgrades.

[0030] The seminar facilitator can use a robot to conduct the seminar verbally or by projecting materials. For example, the robot may greet participants at the start of the seminar and explain the purpose and content of the seminar. The robot can also project presentation materials onto a projector or screen to provide participants with visual information. For example, the robot may display slides sequentially and emphasize important points. The robot can also monitor participants' reactions as the seminar progresses and adjust the pace and content as necessary. For example, the robot may repeat explanations or provide additional examples to help participants understand. This allows the robot to conduct the seminar efficiently. Some or all of the above-mentioned processes in the seminar facilitator may be performed using, or without, AI. For example, the seminar facilitator can input the robot's actions and speech content into an AI model and have the AI ​​execute the optimal seminar method.

[0031] The question reception unit can recognize questions from participants. The question reception unit can recognize verbal questions from participants using, for example, voice recognition technology. For example, the question reception unit can collect participants' utterances through a microphone and convert them into text using voice recognition software. The question reception unit can also receive questions via text input or a tablet device. For example, a participant inputs a question into a tablet device, and the question reception unit analyzes the text data. The question reception unit can also analyze participants' facial expressions and gestures to recognize non-verbal questions and doubts. For example, a camera can capture a participant's facial expression and an expression recognition algorithm can estimate their emotions. This allows for accurate recognition of questions from participants and appropriate responses. Some or all of the above-described processing in the question reception unit can be performed using, for example, AI, or without AI. For example, the question reception unit can input voice data or image data into an AI model and have the AI ​​recognize the question.

[0032] The answer providing unit can provide an appropriate answer based on the question received by the question receiving unit. The answer providing unit, for example, refers to a pre-prepared FAQ database to provide an appropriate answer. For example, the answer providing unit extracts keywords from the question and searches the FAQ database for related answers. The answer providing unit can also use a generation AI to generate a customized answer to the participant's question. For example, the generation AI understands the context of the question and generates an appropriate answer. The answer providing unit can also adjust the tone and expression of the answer by taking into account the participant's emotions and reactions. For example, if the participant is nervous, the answer can be provided in a gentle tone. This provides an appropriate answer to the question, thereby resolving the participant's doubts. Some or all of the above-mentioned processing in the answer providing unit may be performed using, or without, AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​generate an optimal answer.

[0033] The learning unit can accumulate questions from participants in a database and use AI to learn how to respond to new questions or replies. For example, the learning unit can analyze question data from participants to identify frequently occurring questions and new question patterns. For example, the learning unit can cluster the question data and group similar questions. The learning unit can also use a generation AI to learn replies and answer variations to improve the accuracy of the answer providing unit. For example, the generation AI can learn from past question-answer pairs and generate appropriate responses to new questions. The learning unit can also evaluate the overall performance of the system based on participant feedback and identify areas for improvement. For example, the learning unit can evaluate participant satisfaction and the accuracy of answers to help improve the system. This allows AI-based learning to always provide the latest information and improve participant satisfaction. Some or all of the above-described processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input question data into an AI model and have the AI ​​execute a learning algorithm.

[0034] The seminar facilitator can analyze participants' reactions in real time and dynamically change the content of the seminar as it proceeds. For example, if a participant's reaction is good, the seminar facilitator can skip the planned content and move on to the next topic. For example, the robot can analyze participants' facial expressions and voice to detect whether they are reacting well. Furthermore, if a participant's reaction is poor, the seminar facilitator can provide additional explanations or examples to deepen understanding. For example, the robot can analyze participants' gaze and posture to detect whether they are reacting poorly. Furthermore, if participants' reactions are divided, the seminar facilitator can collect opinions and adjust the content of the seminar based on the majority opinion. For example, the robot can collect participants' opinions in real time and dynamically change the content of the seminar. This maximizes the effectiveness of the seminar by dynamically changing the content of the seminar according to participants' reactions. Some or all of the above-described processing in the seminar facilitator can be performed using, or without, AI. For example, the seminar facilitator can input participant reaction data into an AI model and have the AI ​​change the content of the seminar.

[0035] The seminar facilitator can refer to the participant's past participation history when conducting a seminar and provide individually customized seminars. For example, the seminar facilitator provides new, non-duplicate information based on the content of seminars the participant has previously attended. For example, the robot retrieves the participant's past participation history from a database and avoids duplicate content. The seminar facilitator can also emphasize topics of particular interest to the participant based on the participant's past participation history. For example, the robot identifies a topic of interest to the participant and provides information related to that topic. The seminar facilitator can also set a progression speed according to the participant's level of understanding based on the participant's past participation history. For example, the robot evaluates the participant's level of understanding and adjusts the progression speed. This improves participant satisfaction by providing customized seminars based on the participant's past participation history. Some or all of the above-described processing by the seminar facilitator may be performed using, or without, AI. For example, the seminar facilitator can input the participant's historical data into an AI model and have the AI ​​execute customized seminars.

[0036] The seminar facilitator can use region-specific cases and data based on the participants' geographic location information when conducting the seminar. For example, if the participants are from a specific region, the seminar facilitator can introduce case studies related to that region. For example, the robot acquires the participants' geographic location information and searches a database for case studies related to that region. The seminar facilitator can also use region-specific data to provide explanations based on the participants' geographic location information. For example, the robot references regional statistical data and case studies and provides them to the participants. The seminar facilitator can also introduce case studies related to each region in a balanced manner if the participants are from different regions. For example, the robot collects data related to multiple regions and presents it in a balanced manner. This allows the use of region-specific cases and data to provide more relevant information to participants. Some or all of the above-described processing in the seminar facilitator can be performed using, for example, AI, or without AI. For example, the seminar facilitator can input geographic location data into an AI model and have the AI ​​select region-specific cases and data.

[0037] The seminar facilitator can analyze participants' social media activities and incorporate relevant topics into the seminar. For example, the seminar facilitator can incorporate topics that participants have shown interest in on social media into the seminar. For example, a robot can analyze participants' social media activities and identify topics of interest. The seminar facilitator can also analyze participants' social media activities and provide content that matches trends. For example, a robot can analyze social media posts and identify trends. The seminar facilitator can also customize the content of the seminar based on information shared by participants on social media. For example, a robot can collect information shared by participants and reflect it in the content of the seminar. In this way, by analyzing participants' social media activities, content that matches trends can be provided. Some or all of the above-mentioned processing in the seminar facilitator can be performed using, for example, AI, or without AI. For example, the seminar facilitator can input social media data into an AI model and have the AI ​​select relevant topics.

[0038] When accepting a question, the question accepting unit can suggest an appropriate question format by referring to the participant's past question history. For example, the question accepting unit may prioritize suggesting question formats that the participant has used in the past. For example, the robot may retrieve the participant's past question history from a database and suggest similar question formats. The question accepting unit may also recommend a specific question format based on the participant's past question history. For example, the robot may analyze past question data to identify the optimal question format. The question accepting unit may also automatically set a question format that the participant has frequently used in the past. For example, the robot may automatically select the most frequently used question format based on the participant's question history. This improves the quality of questions by suggesting an appropriate question format based on the past question history. Some or all of the above-described processing in the question accepting unit may be performed using, or without, AI. For example, the question accepting unit may input question history data into an AI model and have the AI ​​execute the question format suggestion.

[0039] When accepting questions, the question accepting unit can filter questions based on the participant's current areas of interest. For example, the question accepting unit prioritizes accepting questions related to topics in which the participant is currently interested. For example, the robot identifies the participant's areas of interest from survey results or past questions and prioritizes related questions. The question accepting unit can also filter related questions based on the participant's current areas of interest. For example, the robot extracts questions related to the areas of interest using keyword matching or category classification. The question accepting unit can also automatically display questions related to the areas in which the participant is interested. For example, the robot automatically lists related questions based on the participant's areas of interest. In this way, by filtering questions based on the participant's current areas of interest, it is possible to prioritize accepting highly relevant questions. Some or all of the above-described processing in the question accepting unit may be performed using, for example, AI, or may be performed without using AI. For example, the question accepting unit can input area of ​​interest data into an AI model and have the AI ​​perform question filtering.

[0040] When accepting questions, the question acceptance unit can prioritize highly relevant questions based on the geographical location information of the participants. For example, if a participant is participating from a specific region, the question acceptance unit prioritizes questions related to that region. For example, the robot acquires the participant's geographical location information and searches a database for questions related to that region. The question acceptance unit can also prioritize region-specific questions based on the participant's geographical location information. For example, the robot references region-specific data and prioritizes relevant questions. Furthermore, if participants are participating from different regions, the question acceptance unit can accept questions related to each region in a balanced manner. For example, the robot collects questions related to multiple regions and processes them in a balanced manner. This enables more appropriate response to questions by prioritizing highly relevant questions based on the geographical location information. Some or all of the above-described processing in the question acceptance unit may be performed using, or without, AI. For example, the question acceptance unit may input geographical location data into an AI model and have the AI ​​determine the priority of questions.

[0041] The question receiving unit can analyze the participants' social media activities when receiving questions and receive relevant questions. For example, the question receiving unit can prioritize questions related to topics in which the participants are interested on social media. For example, the robot can analyze the participants' social media activities and identify topics of interest. The question receiving unit can also analyze the participants' social media activities and receive questions that match trends. For example, the robot can analyze social media posts to identify trends. The question receiving unit can also receive related questions based on information shared by the participants on social media. For example, the robot can collect information shared by the participants and list related questions. In this way, by analyzing social media activities, questions that match trends can be received. Some or all of the above-described processing in the question receiving unit can be performed using, for example, AI, or can be performed without using AI. For example, the question receiving unit can input social media data into an AI model and have the AI ​​select relevant questions.

[0042] When providing an answer, the answer providing unit can adjust the level of detail of the answer based on the importance of the question. For example, the answer providing unit provides a detailed answer to a question of high importance. For example, the robot evaluates the impact and urgency of the question and generates a detailed answer. The answer providing unit can also provide a concise answer to a question of low importance. For example, the robot evaluates the importance of the question and generates a concise answer. The answer providing unit can also gradually adjust the level of detail of the answer according to the importance. For example, the robot adjusts the length and specificity of the answer based on the importance of the question. In this way, by adjusting the level of detail of the answer according to the importance of the question, a more appropriate answer can be provided. Some or all of the above-mentioned processing in the answer providing unit may be performed using, or without, AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​adjust the level of detail of the answer.

[0043] When providing an answer, the answer providing unit can apply different answer algorithms depending on the category of the question. For example, the answer providing unit applies a specialized answer algorithm to a technical question. For example, the robot identifies a technical question and generates an answer using a specialized algorithm. The answer providing unit can also apply a simple answer algorithm to a general question. For example, the robot identifies a general question and generates an answer using a simple algorithm. The answer providing unit can also select an optimal answer algorithm depending on the category. For example, the robot classifies the question category and selects an optimal algorithm. This allows for providing a more appropriate answer by applying the optimal answer algorithm depending on the question category. Some or all of the above-mentioned processing in the answer providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​select an answer algorithm.

[0044] When providing an answer, the answer providing unit can determine the priority of the answers based on the time of submission of the question. For example, the answer providing unit prioritizes answers to questions submitted earlier. For example, the robot evaluates the submission date and time of the question and prioritizes questions submitted earlier. The answer providing unit can also prioritize answers to questions with high urgency. For example, the robot evaluates the urgency of the question and prioritizes questions with high urgency. The answer providing unit can also gradually adjust the priority of the answers depending on the time of submission. For example, the robot adjusts the priority of the answers based on the time of submission of the question. This enables faster answers by determining the priority of the answers based on the time of submission of the question. Some or all of the above-mentioned processing in the answer providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​determine the priority of the answers.

[0045] When providing answers, the answer providing unit can adjust the order of answers based on the relevance of the questions. For example, the answer providing unit prioritizes answers to highly relevant questions. For example, the robot evaluates the content and category of the questions and prioritizes highly relevant questions. The answer providing unit can also postpone less relevant questions. For example, the robot evaluates the relevance of questions and postpones less relevant questions. The answer providing unit can also gradually adjust the order of answers according to the relevance of the questions. For example, the robot adjusts the order of answers based on the relevance of the questions. In this way, by adjusting the order of answers based on the relevance of the questions, more appropriate answers can be provided. Some or all of the above-described processing in the answer providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​adjust the order of answers.

[0046] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on the past learning data. For example, the robot retrieves past learning data from a database and selects an optimal algorithm. The learning unit can also analyze the past learning data and improve the learning algorithm. For example, the robot analyzes the past learning data and adjusts algorithm parameters. The learning unit can also adjust the learning algorithm parameters by referring to the past learning data. For example, the robot optimizes the algorithm parameters based on the past learning data. This improves learning accuracy by optimizing the learning algorithm by referring to the past learning data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input learning data into an AI model and cause AI to optimize the algorithm.

[0047] During learning, the learning unit can customize the learning content by referring to the participant's past question history. The learning unit, for example, prioritizes learning related learning content based on the participant's past question history. For example, the robot retrieves the participant's past question history from a database and selects related learning content. The learning unit can also analyze the participant's past question history to customize the learning content. For example, the robot analyzes past question data and identifies the optimal learning content. The learning unit can also determine the priority of the learning content by referring to the participant's past question history. For example, the robot sets the priority of the learning content based on the participant's past question history. This enables more effective learning by customizing the learning content based on the participant's past question history. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input question history data into an AI model and have the AI ​​customize the learning content.

[0048] During learning, the learning unit can weight the learning data based on the time when the question was submitted. For example, the learning unit prioritizes learning and weights recently submitted questions more highly. For example, the robot evaluates the submission date and time of questions and prioritizes recent questions. The learning unit can also lower the weight of older questions and prioritize the latest information. For example, the robot evaluates the submission date and time of questions and lower the weight of older questions. The learning unit can also gradually adjust the weighting of the learning data according to the submission date and time. For example, the robot adjusts the weighting of the learning data based on the submission date and time of questions. In this way, by weighting the learning data based on the submission date and time of questions, the latest information can be prioritized for learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input question data into an AI model and have the AI ​​perform weighting of the learning data.

[0049] During learning, the learning unit can learn region-specific questions based on the participants' geographical location information. For example, if a participant is from a specific region, the learning unit prioritizes learning questions related to that region. For example, the robot acquires the participants' geographical location information and searches a database for questions related to that region. The learning unit can also learn region-specific data based on the participants' geographical location information. For example, the robot refers to statistical data and case studies for the region to learn related questions. Furthermore, if participants are from different regions, the learning unit can learn questions related to each region in a balanced manner. For example, the robot collects data related to multiple regions and learns in a balanced manner. This allows the robot to learn region-specific questions based on geographical location information, thereby providing more relevant information. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit may input geographical location data into an AI model and cause the AI ​​to learn region-specific questions.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The seminar moderator can refer to the participant's past learning history and provide individually customized progress. For example, it can provide new information that does not overlap with the content of seminars the participant has previously attended. It can also emphasize topics of particular interest to the participant based on the participant's past learning history. It can also set the progress speed according to the participant's level of understanding. This allows for customized progress based on the participant's past learning history, thereby improving participant satisfaction.

[0052] The answer providing unit can adjust the level of detail of the answer based on the importance of the question. For example, a detailed answer can be provided for a question of high importance. A concise answer can also be provided for a question of low importance. Furthermore, the level of detail of the answer can be adjusted in stages depending on the importance. In this way, by adjusting the level of detail of the answer depending on the importance of the question, a more appropriate answer can be provided.

[0053] The seminar facilitator can use region-specific case studies and data based on the participants' geographic location information. For example, if participants are from a specific region, case studies related to that region can be introduced. Region-specific data can also be used for explanations. Furthermore, if participants are from different regions, case studies related to each region can be introduced in a balanced manner. This allows the use of region-specific case studies and data to provide more relevant information to participants.

[0054] The question reception unit can analyze the social media activity of participants and receive relevant questions. For example, it can prioritize questions related to topics that participants are interested in on social media. It can also analyze social media activity and receive questions that match trends. It can also receive questions that are related to information shared by participants on social media. In this way, it is possible to receive questions that match trends by analyzing social media activity.

[0055] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. For example, it can select the optimal learning algorithm based on the past learning data. It can also analyze the past learning data and improve the learning algorithm. Furthermore, it can also adjust the parameters of the learning algorithm by referring to the past learning data. In this way, the accuracy of learning is improved by optimizing the learning algorithm by referring to the past learning data.

[0056] During learning, the learning unit can weight the learning data based on the time of question submission. For example, recently submitted questions can be given priority in learning and weighted higher. Older questions can also be weighted lower and the most recent information given priority. Furthermore, the weighting of the learning data can be adjusted in stages depending on the time of submission. In this way, by weighting the learning data based on the time of question submission, the most recent information can be given priority in learning.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The seminar moderator uses the robot to deliver speeches and project materials. For example, the robot greets participants at the start of the seminar and explains the seminar's purpose and content. The robot can also project presentation materials onto a projector or screen to provide participants with visual information. Furthermore, the robot can monitor participants' reactions as the seminar progresses and adjust the pace and content as necessary. Step 2: The question reception unit recognizes questions from participants. For example, the question reception unit can recognize verbal questions from participants using voice recognition technology. The question reception unit can also receive questions entered via text or a tablet device. Furthermore, the question reception unit can analyze participants' facial expressions and gestures to recognize non-verbal questions and doubts. Step 3: The answer providing unit provides an appropriate answer based on the question received by the question receiving unit. For example, the answer providing unit can refer to a pre-prepared FAQ database to provide an appropriate answer. The answer providing unit can also use a generation AI to generate a customized answer to the participant's question. Furthermore, the answer providing unit can adjust the tone and expression of the answer taking into account the participant's emotions and reactions. Step 4: The learning unit accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. For example, the learning unit can analyze question data from participants and identify frequently asked questions and new question patterns. The learning unit can also use generative AI to learn variations in replies and answers, improving the accuracy of the answer providing unit. Furthermore, the learning unit can evaluate the performance of the entire system based on participant feedback and identify areas for improvement.

[0059] (Example 2) A seminar system according to an embodiment of the present invention is a system that uses a robot as a lecturer in smartphone seminars. In this seminar system, the robot plays the role of seminar manager, facilitator, and lecturer, delivering speeches and projecting materials. The robot also answers questions, concerns, and inquiries from participants. The robot learns from participants' questions and constantly upgrades itself to accommodate new questions and replies. For example, a seminar system may first include a "seminar progress unit" for the robot to conduct the seminar, delivering speeches and projecting materials. Next, a "question reception unit" is provided to accept questions from participants, and an "answer provision unit" is provided to recognize questions and provide appropriate answers. Furthermore, a "learning unit" is provided for the robot to learn questions and upgrade itself. This learning unit accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. This allows the robot to constantly provide the latest information, improving participant satisfaction. This allows the seminar system to provide a system that integrates seminar progress, question reception, answer provision, learning, and upgrades.

[0060] A seminar system according to an embodiment includes a seminar facilitator, a question receiver, an answer provider, and a learning unit. The seminar facilitator uses a robot to deliver oral presentations and project materials. For example, the robot greets participants at the start of the seminar and explains the purpose and content of the seminar. The robot can also project presentation materials onto a projector or screen to provide participants with visual information. Furthermore, the robot can monitor participants' responses during the seminar and adjust the pace and content as needed. The question receiver recognizes questions from participants. For example, the question receiver can recognize participants' oral questions using voice recognition technology. The question receiver can also receive questions via text input or a tablet device. Furthermore, the question receiver can analyze participants' facial expressions and gestures to recognize non-verbal questions and doubts. The answer provider provides appropriate answers based on the questions received by the question receiver. For example, the answer provider can provide appropriate answers by referencing a pre-prepared FAQ database. The answer provider can also generate customized answers to participants' questions using a generative AI. Furthermore, the answer providing unit can adjust the tone and expression of the answer, taking into account the emotions and reactions of the participants. The learning unit accumulates questions from participants in a database and uses AI to learn how to respond to new questions and tactics. For example, the learning unit can analyze question data from participants and identify frequently asked questions and new question patterns. The learning unit can also use a generation AI to learn variations in tactics and answers, thereby improving the accuracy of the answer providing unit. Furthermore, the learning unit can evaluate the performance of the entire system based on participant feedback and identify areas for improvement. As a result, the seminar system according to the embodiment can provide a system that integrates seminar progress, question acceptance, answer provision, learning, and version upgrades.

[0061] The seminar facilitator can use a robot to conduct the seminar verbally or by projecting materials. For example, the robot may greet participants at the start of the seminar and explain the purpose and content of the seminar. The robot can also project presentation materials onto a projector or screen to provide participants with visual information. For example, the robot may display slides sequentially and emphasize important points. The robot can also monitor participants' reactions as the seminar progresses and adjust the pace and content as necessary. For example, the robot may repeat explanations or provide additional examples to help participants understand. This allows the robot to conduct the seminar efficiently. Some or all of the above-mentioned processes in the seminar facilitator may be performed using, or without, AI. For example, the seminar facilitator can input the robot's actions and speech content into an AI model and have the AI ​​execute the optimal seminar method.

[0062] The question reception unit can recognize questions from participants. The question reception unit can recognize verbal questions from participants using, for example, voice recognition technology. For example, the question reception unit can collect participants' utterances through a microphone and convert them into text using voice recognition software. The question reception unit can also receive questions via text input or a tablet device. For example, a participant inputs a question into a tablet device, and the question reception unit analyzes the text data. The question reception unit can also analyze participants' facial expressions and gestures to recognize non-verbal questions and doubts. For example, a camera can capture a participant's facial expression and an expression recognition algorithm can estimate their emotions. This allows for accurate recognition of questions from participants and appropriate responses. Some or all of the above-described processing in the question reception unit can be performed using, for example, AI, or without AI. For example, the question reception unit can input voice data or image data into an AI model and have the AI ​​recognize the question.

[0063] The answer providing unit can provide an appropriate answer based on the question received by the question receiving unit. The answer providing unit, for example, refers to a pre-prepared FAQ database to provide an appropriate answer. For example, the answer providing unit extracts keywords from the question and searches the FAQ database for related answers. The answer providing unit can also use a generation AI to generate a customized answer to the participant's question. For example, the generation AI understands the context of the question and generates an appropriate answer. The answer providing unit can also adjust the tone and expression of the answer by taking into account the participant's emotions and reactions. For example, if the participant is nervous, the answer can be provided in a gentle tone. This provides an appropriate answer to the question, thereby resolving the participant's doubts. Some or all of the above-mentioned processing in the answer providing unit may be performed using, or without, AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​generate an optimal answer.

[0064] The learning unit can accumulate questions from participants in a database and use AI to learn how to respond to new questions or replies. For example, the learning unit can analyze question data from participants to identify frequently occurring questions and new question patterns. For example, the learning unit can cluster the question data and group similar questions. The learning unit can also use a generation AI to learn replies and answer variations to improve the accuracy of the answer providing unit. For example, the generation AI can learn from past question-answer pairs and generate appropriate responses to new questions. The learning unit can also evaluate the overall performance of the system based on participant feedback and identify areas for improvement. For example, the learning unit can evaluate participant satisfaction and the accuracy of answers to help improve the system. This allows AI-based learning to always provide the latest information and improve participant satisfaction. Some or all of the above-described processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input question data into an AI model and have the AI ​​execute a learning algorithm.

[0065] The seminar facilitator can estimate the emotions of the participants and adjust the pace of the seminar based on the estimated emotions. For example, if a participant is excited, the seminar facilitator can speed up the seminar to keep the pace at a good pace. For example, the robot can analyze the participants' facial expressions and voices to detect their excited state. Furthermore, if a participant is bored, the seminar facilitator can slow down the pace of the seminar and provide more detailed explanations. For example, the robot can analyze the participants' gaze and posture to detect their boredom. Furthermore, if a participant is nervous, the seminar facilitator can slow down the pace of the seminar to allow them to relax. For example, the robot can measure the participants' heart rate and electrodermal activity with sensors to detect their nervous state. This allows for more effective seminar management by adjusting the pace of the seminar according to the participants' emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing by the seminar facilitator may be performed using AI, or may be performed without AI. For example, the seminar facilitator may input participants' emotional data into an AI model and have the AI ​​adjust the progress of the seminar.

[0066] The seminar facilitator can analyze participants' reactions in real time and dynamically change the content of the seminar as it proceeds. For example, if a participant's reaction is good, the seminar facilitator can skip the planned content and move on to the next topic. For example, the robot can analyze participants' facial expressions and voice to detect whether they are reacting well. Furthermore, if a participant's reaction is poor, the seminar facilitator can provide additional explanations or examples to deepen understanding. For example, the robot can analyze participants' gaze and posture to detect whether they are reacting poorly. Furthermore, if participants' reactions are divided, the seminar facilitator can collect opinions and adjust the content of the seminar based on the majority opinion. For example, the robot can collect participants' opinions in real time and dynamically change the content of the seminar. This maximizes the effectiveness of the seminar by dynamically changing the content of the seminar according to participants' reactions. Some or all of the above-described processing in the seminar facilitator can be performed using, or without, AI. For example, the seminar facilitator can input participant reaction data into an AI model and have the AI ​​change the content of the seminar.

[0067] The seminar facilitator can refer to the participant's past participation history when conducting a seminar and provide individually customized seminars. For example, the seminar facilitator provides new, non-duplicate information based on the content of seminars the participant has previously attended. For example, the robot retrieves the participant's past participation history from a database and avoids duplicate content. The seminar facilitator can also emphasize topics of particular interest to the participant based on the participant's past participation history. For example, the robot identifies a topic of interest to the participant and provides information related to that topic. The seminar facilitator can also set a progression speed according to the participant's level of understanding based on the participant's past participation history. For example, the robot evaluates the participant's level of understanding and adjusts the progression speed. This improves participant satisfaction by providing customized seminars based on the participant's past participation history. Some or all of the above-described processing by the seminar facilitator may be performed using, or without, AI. For example, the seminar facilitator can input the participant's historical data into an AI model and have the AI ​​execute customized seminars.

[0068] The seminar facilitator can estimate the emotions of participants and adjust the order of material projection based on the estimated emotions of the participants. For example, if a participant is excited, the seminar facilitator can project materials that attract their interest first. For example, the robot can analyze the participant's facial expressions and voice to detect their excited state. Furthermore, if a participant is bored, the seminar facilitator can project important materials first to attract their attention. For example, the robot can analyze the participant's gaze and posture to detect their boredom. Furthermore, if a participant is nervous, the seminar facilitator can project materials that will help them relax first. For example, the robot can measure the participant's heart rate and electrodermal activity using sensors to detect their nervous state. This allows for more effective seminar management by adjusting the order of material projection according to the participant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-mentioned processes in the seminar facilitator may be performed using AI or without AI. For example, the seminar facilitator may input participants' emotional data into an AI model and have the AI ​​determine the order in which materials are projected.

[0069] The seminar facilitator can use region-specific cases and data based on the participants' geographic location information when conducting the seminar. For example, if the participants are from a specific region, the seminar facilitator can introduce case studies related to that region. For example, the robot acquires the participants' geographic location information and searches a database for case studies related to that region. The seminar facilitator can also use region-specific data to provide explanations based on the participants' geographic location information. For example, the robot references regional statistical data and case studies and provides them to the participants. The seminar facilitator can also introduce case studies related to each region in a balanced manner if the participants are from different regions. For example, the robot collects data related to multiple regions and presents it in a balanced manner. This allows the use of region-specific cases and data to provide more relevant information to participants. Some or all of the above-described processing in the seminar facilitator can be performed using, for example, AI, or without AI. For example, the seminar facilitator can input geographic location data into an AI model and have the AI ​​select region-specific cases and data.

[0070] The seminar facilitator can analyze participants' social media activities and incorporate relevant topics into the seminar. For example, the seminar facilitator can incorporate topics that participants have shown interest in on social media into the seminar. For example, a robot can analyze participants' social media activities and identify topics of interest. The seminar facilitator can also analyze participants' social media activities and provide content that matches trends. For example, a robot can analyze social media posts and identify trends. The seminar facilitator can also customize the content of the seminar based on information shared by participants on social media. For example, a robot can collect information shared by participants and reflect it in the content of the seminar. In this way, by analyzing participants' social media activities, content that matches trends can be provided. Some or all of the above-mentioned processing in the seminar facilitator can be performed using, for example, AI, or without AI. For example, the seminar facilitator can input social media data into an AI model and have the AI ​​select relevant topics.

[0071] The question receiving unit can estimate the emotions of participants and adjust the method of accepting questions based on the estimated emotions of the participants. For example, if a participant is nervous, the question receiving unit can provide a simple question format to make it easier for the participant to ask a question. For example, the robot can analyze the participant's facial expressions and voice to detect a state of nervousness. Furthermore, if a participant is relaxed, the question receiving unit can provide a detailed question format to encourage deeper questions. For example, the robot can analyze the participant's posture and gaze to detect a state of relaxation. Furthermore, if a participant is excited, the question receiving unit can provide an interface that immediately accepts questions. For example, the robot can analyze the participant's voice and facial expressions to detect a state of excitement. This allows for more appropriate question acceptance by adjusting the method of accepting questions according to the participant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can 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 question receiving unit can be performed using, for example, AI, or without AI. For example, the question reception unit can input emotional data into an AI model and have the AI ​​adjust the question reception method.

[0072] When accepting a question, the question accepting unit can suggest an appropriate question format by referring to the participant's past question history. For example, the question accepting unit may prioritize suggesting question formats that the participant has used in the past. For example, the robot may retrieve the participant's past question history from a database and suggest similar question formats. The question accepting unit may also recommend a specific question format based on the participant's past question history. For example, the robot may analyze past question data to identify the optimal question format. The question accepting unit may also automatically set a question format that the participant has frequently used in the past. For example, the robot may automatically select the most frequently used question format based on the participant's question history. This improves the quality of questions by suggesting an appropriate question format based on the past question history. Some or all of the above-described processing in the question accepting unit may be performed using, or without, AI. For example, the question accepting unit may input question history data into an AI model and have the AI ​​execute the question format suggestion.

[0073] When accepting questions, the question accepting unit can filter questions based on the participant's current areas of interest. For example, the question accepting unit prioritizes accepting questions related to topics in which the participant is currently interested. For example, the robot identifies the participant's areas of interest from survey results or past questions and prioritizes related questions. The question accepting unit can also filter related questions based on the participant's current areas of interest. For example, the robot extracts questions related to the areas of interest using keyword matching or category classification. The question accepting unit can also automatically display questions related to the areas in which the participant is interested. For example, the robot automatically lists related questions based on the participant's areas of interest. In this way, by filtering questions based on the participant's current areas of interest, it is possible to prioritize accepting highly relevant questions. Some or all of the above-described processing in the question accepting unit may be performed using, for example, AI, or may be performed without using AI. For example, the question accepting unit can input area of ​​interest data into an AI model and have the AI ​​perform question filtering.

[0074] The question receiving unit can estimate the emotions of participants and prioritize questions based on the estimated emotions. For example, if a participant is nervous, the question receiving unit prioritizes the question. For example, the robot analyzes the participant's facial expressions and voice to detect a nervous state. Furthermore, if a participant is relaxed, the question receiving unit can treat the question equally with other questions. For example, the robot analyzes the participant's posture and gaze to detect a relaxed state. Furthermore, if a participant is excited, the question receiving unit can quickly process the question. For example, the robot analyzes the participant's voice and facial expressions to detect an excited state. This enables more appropriate question responses by prioritizing questions according to the participant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can 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 question receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the question receiving unit can input emotional data into an AI model and have the AI ​​determine the priority of questions.

[0075] When accepting questions, the question acceptance unit can prioritize highly relevant questions based on the geographical location information of the participants. For example, if a participant is participating from a specific region, the question acceptance unit prioritizes questions related to that region. For example, the robot acquires the participant's geographical location information and searches a database for questions related to that region. The question acceptance unit can also prioritize region-specific questions based on the participant's geographical location information. For example, the robot references region-specific data and prioritizes relevant questions. Furthermore, if participants are participating from different regions, the question acceptance unit can accept questions related to each region in a balanced manner. For example, the robot collects questions related to multiple regions and processes them in a balanced manner. This enables more appropriate response to questions by prioritizing highly relevant questions based on the geographical location information. Some or all of the above-described processing in the question acceptance unit may be performed using, or without, AI. For example, the question acceptance unit may input geographical location data into an AI model and have the AI ​​determine the priority of questions.

[0076] The question receiving unit can analyze the participants' social media activities when receiving questions and receive relevant questions. For example, the question receiving unit can prioritize questions related to topics in which the participants are interested on social media. For example, the robot can analyze the participants' social media activities and identify topics of interest. The question receiving unit can also analyze the participants' social media activities and receive questions that match trends. For example, the robot can analyze social media posts to identify trends. The question receiving unit can also receive related questions based on information shared by the participants on social media. For example, the robot can collect information shared by the participants and list related questions. In this way, by analyzing social media activities, questions that match trends can be received. Some or all of the above-described processing in the question receiving unit can be performed using, for example, AI, or can be performed without using AI. For example, the question receiving unit can input social media data into an AI model and have the AI ​​select relevant questions.

[0077] The answer providing unit can estimate the participant's emotions and adjust the way the answer is expressed based on the estimated participant's emotions. For example, if the participant is nervous, the answer providing unit can provide an answer in a gentle tone. For example, the robot can analyze the participant's facial expressions and voice to detect a state of tension. Furthermore, if the participant is relaxed, the answer providing unit can provide an answer with a detailed explanation. For example, the robot can analyze the participant's posture and gaze to detect a relaxed state. Furthermore, if the participant is excited, the answer providing unit can provide a concise and clear answer. For example, the robot can analyze the participant's voice and facial expressions to detect an excited state. This allows the robot to adjust the way the answer is expressed based on the participant's emotions, thereby providing a more appropriate answer. Emotion estimation is achieved 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., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answer providing unit can be performed, for example, using AI, or without AI. For example, the answer providing unit can input emotional data into an AI model and have the AI ​​adjust the way the answer is expressed.

[0078] When providing an answer, the answer providing unit can adjust the level of detail of the answer based on the importance of the question. For example, the answer providing unit provides a detailed answer to a question of high importance. For example, the robot evaluates the impact and urgency of the question and generates a detailed answer. The answer providing unit can also provide a concise answer to a question of low importance. For example, the robot evaluates the importance of the question and generates a concise answer. The answer providing unit can also gradually adjust the level of detail of the answer according to the importance. For example, the robot adjusts the length and specificity of the answer based on the importance of the question. In this way, by adjusting the level of detail of the answer according to the importance of the question, a more appropriate answer can be provided. Some or all of the above-mentioned processing in the answer providing unit may be performed using, or without, AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​adjust the level of detail of the answer.

[0079] When providing an answer, the answer providing unit can apply different answer algorithms depending on the category of the question. For example, the answer providing unit applies a specialized answer algorithm to a technical question. For example, the robot identifies a technical question and generates an answer using a specialized algorithm. The answer providing unit can also apply a simple answer algorithm to a general question. For example, the robot identifies a general question and generates an answer using a simple algorithm. The answer providing unit can also select an optimal answer algorithm depending on the category. For example, the robot classifies the question category and selects an optimal algorithm. This allows for providing a more appropriate answer by applying the optimal answer algorithm depending on the question category. Some or all of the above-mentioned processing in the answer providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​select an answer algorithm.

[0080] The answer providing unit can estimate the participant's emotions and adjust the length of the answer based on the estimated participant's emotions. For example, if a participant is nervous, the answer providing unit can provide a short, to-the-point answer. For example, the robot can analyze the participant's facial expressions and voice to detect a state of nervousness. Furthermore, if a participant is relaxed, the answer providing unit can provide a longer answer with detailed explanations. For example, the robot can analyze the participant's posture and gaze to detect a state of relaxation. Furthermore, if a participant is excited, the answer providing unit can provide a concise and clear answer. For example, the robot can analyze the participant's voice and facial expressions to detect a state of excitement. This allows the robot to adjust the length of the answer according to the participant's emotions, thereby providing a more appropriate answer. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 answer providing unit can be performed, for example, using AI, or without AI. For example, the answer providing unit can input emotional data into an AI model and have the AI ​​adjust the length of the answer.

[0081] When providing an answer, the answer providing unit can determine the priority of the answers based on the time of submission of the question. For example, the answer providing unit prioritizes answers to questions submitted earlier. For example, the robot evaluates the submission date and time of the question and prioritizes questions submitted earlier. The answer providing unit can also prioritize answers to questions with high urgency. For example, the robot evaluates the urgency of the question and prioritizes questions with high urgency. The answer providing unit can also gradually adjust the priority of the answers depending on the time of submission. For example, the robot adjusts the priority of the answers based on the time of submission of the question. This enables faster answers by determining the priority of the answers based on the time of submission of the question. Some or all of the above-mentioned processing in the answer providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​determine the priority of the answers.

[0082] When providing answers, the answer providing unit can adjust the order of answers based on the relevance of the questions. For example, the answer providing unit prioritizes answers to highly relevant questions. For example, the robot evaluates the content and category of the questions and prioritizes highly relevant questions. The answer providing unit can also postpone less relevant questions. For example, the robot evaluates the relevance of questions and postpones less relevant questions. The answer providing unit can also gradually adjust the order of answers according to the relevance of the questions. For example, the robot adjusts the order of answers based on the relevance of the questions. In this way, by adjusting the order of answers based on the relevance of the questions, more appropriate answers can be provided. Some or all of the above-described processing in the answer providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer providing unit can input question data into an AI model and have the AI ​​adjust the order of answers.

[0083] The learning unit can estimate the emotions of participants and select training data based on the estimated emotions of the participants. For example, if a participant is excited, the learning unit prioritizes learning data that attracts their interest. For example, the robot analyzes the participant's facial expressions and voice to detect their excited state. Furthermore, if a participant is relaxed, the learning unit can also learn detailed data. For example, the robot analyzes the participant's posture and gaze to detect their relaxed state. Furthermore, if a participant is nervous, the learning unit can also learn concise, to-the-point data. For example, the robot measures the participant's heart rate and electrodermal activity with a sensor to detect their nervous state. This enables more effective learning by selecting training data based on the participant's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or without AI. For example, the learning unit can input emotional data into an AI model and have the AI ​​select the learning data.

[0084] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on the past learning data. For example, the robot retrieves past learning data from a database and selects an optimal algorithm. The learning unit can also analyze the past learning data and improve the learning algorithm. For example, the robot analyzes the past learning data and adjusts algorithm parameters. The learning unit can also adjust the learning algorithm parameters by referring to the past learning data. For example, the robot optimizes the algorithm parameters based on the past learning data. This improves learning accuracy by optimizing the learning algorithm by referring to the past learning data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input learning data into an AI model and cause AI to optimize the algorithm.

[0085] During learning, the learning unit can customize the learning content by referring to the participant's past question history. The learning unit, for example, prioritizes learning related learning content based on the participant's past question history. For example, the robot retrieves the participant's past question history from a database and selects related learning content. The learning unit can also analyze the participant's past question history to customize the learning content. For example, the robot analyzes past question data and identifies the optimal learning content. The learning unit can also determine the priority of the learning content by referring to the participant's past question history. For example, the robot sets the priority of the learning content based on the participant's past question history. This enables more effective learning by customizing the learning content based on the participant's past question history. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input question history data into an AI model and have the AI ​​customize the learning content.

[0086] The learning unit can estimate the emotions of the participants and adjust the frequency of learning based on the estimated emotions of the participants. For example, the learning unit increases the frequency of learning when the participants are excited. For example, the robot analyzes the participants' facial expressions and voices to detect an excited state. The learning unit can also normalize the frequency of learning when the participants are relaxed. For example, the robot analyzes the participants' posture and gaze to detect a relaxed state. The learning unit can also reduce the frequency of learning when the participants are nervous. For example, the robot measures the participants' heart rate and electrodermal activity with sensors to detect a nervous state. This enables more effective learning by adjusting the frequency of learning based on the participants' emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI can be 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-mentioned processing in the learning unit may be performed using, for example, AI, or without AI. For example, the learning unit can input emotional data into an AI model and have the AI ​​adjust the learning frequency.

[0087] During learning, the learning unit can weight the learning data based on the time when the question was submitted. For example, the learning unit prioritizes learning and weights recently submitted questions more highly. For example, the robot evaluates the submission date and time of questions and prioritizes recent questions. The learning unit can also lower the weight of older questions and prioritize the latest information. For example, the robot evaluates the submission date and time of questions and lower the weight of older questions. The learning unit can also gradually adjust the weighting of the learning data according to the submission date and time. For example, the robot adjusts the weighting of the learning data based on the submission date and time of questions. In this way, by weighting the learning data based on the submission date and time of questions, the latest information can be prioritized for learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input question data into an AI model and have the AI ​​perform weighting of the learning data.

[0088] During learning, the learning unit can learn region-specific questions based on the participants' geographical location information. For example, if a participant is from a specific region, the learning unit prioritizes learning questions related to that region. For example, the robot acquires the participants' geographical location information and searches a database for questions related to that region. The learning unit can also learn region-specific data based on the participants' geographical location information. For example, the robot refers to statistical data and case studies for the region to learn related questions. Furthermore, if participants are from different regions, the learning unit can learn questions related to each region in a balanced manner. For example, the robot collects data related to multiple regions and learns in a balanced manner. This allows the robot to learn region-specific questions based on geographical location information, thereby providing more relevant information. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit may input geographical location data into an AI model and cause the AI ​​to learn region-specific questions. === Hard Collateral 1-1 === Each of the multiple elements including the seminar proceeding unit, question receiving unit, answer providing unit, and learning 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 seminar proceeding unit is realized by the control unit 46A of the smart device 14, and a robot performs oral presentations and project materials. The question receiving unit recognizes participants' questions using the microphone 38B of the smart device 14 or a tablet terminal. The answer providing unit is realized by the specific processing unit 290 of the data processing device 12, and provides appropriate answers using an FAQ database and a generation AI. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. === Hard Collateral 1-2 === Each of the multiple elements, including the seminar proceeding unit, question receiving unit, answer providing unit, and learning unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the seminar proceeding unit is realized by the control unit 46A of the smart glasses 214, and a robot performs oral presentations and material projections. The question receiving unit recognizes participants' questions using the microphone 238 of the smart glasses 214 or a tablet terminal. The answer providing unit is realized by the specific processing unit 290 of the data processing device 12, and provides appropriate answers using an FAQ database and a generation AI. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. === Hard Collateral 1-3 === Each of the multiple elements including the seminar facilitator, question receiver, answer provider, and learning unit described above is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the seminar facilitator is realized by the control unit 46A of the headset terminal 314, and a robot performs oral presentations and project materials. The question receiver recognizes participants' questions using the microphone 238 of the headset terminal 314 or a tablet terminal. The answer provider is realized by the specific processing unit 290 of the data processing device 12, and provides appropriate answers using an FAQ database and a generation AI. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. === Hard Collateral 1-4 === Each of the multiple elements including the seminar facilitator, question receiver, answer provider, and learning unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the seminar facilitator is realized by the control unit 46A of the robot 414, and the robot performs oral presentations and material projections. The question receiver recognizes participants' questions using the microphone 238 of the robot 414 or a tablet terminal. The answer provider is realized by the specific processing unit 290 of the data processing device 12, and provides appropriate answers using an FAQ database and a generation AI. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The seminar moderator can refer to the participant's past learning history and provide individually customized progress. For example, it can provide new information that does not overlap with the content of seminars the participant has previously attended. It can also emphasize topics of particular interest to the participant based on the participant's past learning history. It can also set the progress speed according to the participant's level of understanding. This allows for customized progress based on the participant's past learning history, thereby improving participant satisfaction.

[0091] The question accepting unit can estimate the emotions of the participants and adjust the method of accepting questions based on the estimated emotions of the participants. For example, if a participant is nervous, a simple question format can be provided to make it easier for them to ask questions. If a participant is relaxed, a detailed question format can be provided to encourage them to ask deeper questions. Furthermore, if a participant is excited, an interface that accepts questions immediately can be provided. This allows for more appropriate question acceptance by adjusting the method of accepting questions according to the emotions of the participants.

[0092] The answer providing unit can adjust the level of detail of the answer based on the importance of the question. For example, a detailed answer can be provided for a question of high importance. A concise answer can also be provided for a question of low importance. Furthermore, the level of detail of the answer can be adjusted in stages depending on the importance. In this way, by adjusting the level of detail of the answer depending on the importance of the question, a more appropriate answer can be provided.

[0093] The learning unit can estimate the emotions of participants and select learning data based on the estimated emotions of participants. For example, if participants are excited, it can prioritize learning data that catches their interest. If participants are relaxed, it can also learn detailed data. Furthermore, if participants are nervous, it can also learn concise data that focuses on the main points. This allows for more effective learning by selecting learning data based on participants' emotions.

[0094] The seminar facilitator can use region-specific case studies and data based on the participants' geographic location information. For example, if participants are from a specific region, case studies related to that region can be introduced. Region-specific data can also be used for explanations. Furthermore, if participants are from different regions, case studies related to each region can be introduced in a balanced manner. This allows the use of region-specific case studies and data to provide more relevant information to participants.

[0095] The question reception unit can analyze the social media activity of participants and receive relevant questions. For example, it can prioritize questions related to topics that participants are interested in on social media. It can also analyze social media activity and receive questions that match trends. It can also receive questions that are related to information shared by participants on social media. In this way, it is possible to receive questions that match trends by analyzing social media activity.

[0096] The answer providing unit can estimate the emotion of the participant and adjust the way the answer is expressed based on the estimated emotion of the participant. For example, if the participant is nervous, the answer can be provided in a gentle tone. If the participant is relaxed, the answer can be provided with detailed explanations. Furthermore, if the participant is excited, the answer can be provided in a concise and clear manner. In this way, by adjusting the way the answer is expressed according to the emotion of the participant, more appropriate answers can be provided.

[0097] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. For example, it can select the optimal learning algorithm based on the past learning data. It can also analyze the past learning data and improve the learning algorithm. Furthermore, it can also adjust the parameters of the learning algorithm by referring to the past learning data. In this way, the accuracy of learning is improved by optimizing the learning algorithm by referring to the past learning data.

[0098] The seminar management unit can estimate the emotions of the participants and adjust the order of material projection based on the estimated emotions of the participants. For example, if the participants are excited, it can project interesting materials first. If the participants are bored, it can project important materials first to attract their attention. Furthermore, if the participants are nervous, it can project materials that will help them relax first. This allows for more effective seminar management by adjusting the order of material projection according to the emotions of the participants.

[0099] During learning, the learning unit can weight the learning data based on the time of question submission. For example, recently submitted questions can be given priority in learning and weighted higher. Older questions can also be weighted lower and the most recent information given priority. Furthermore, the weighting of the learning data can be adjusted in stages depending on the time of submission. In this way, by weighting the learning data based on the time of question submission, the most recent information can be given priority in learning.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The seminar moderator uses the robot to deliver speeches and project materials. For example, the robot greets participants at the start of the seminar and explains the seminar's purpose and content. The robot can also project presentation materials onto a projector or screen to provide participants with visual information. Furthermore, the robot can monitor participants' reactions as the seminar progresses and adjust the pace and content as necessary. Step 2: The question reception unit recognizes questions from participants. For example, the question reception unit can recognize verbal questions from participants using voice recognition technology. The question reception unit can also receive questions entered via text or a tablet device. Furthermore, the question reception unit can analyze participants' facial expressions and gestures to recognize non-verbal questions and doubts. Step 3: The answer providing unit provides an appropriate answer based on the question received by the question receiving unit. For example, the answer providing unit can refer to a pre-prepared FAQ database to provide an appropriate answer. The answer providing unit can also use a generation AI to generate a customized answer to the participant's question. Furthermore, the answer providing unit can adjust the tone and expression of the answer taking into account the participant's emotions and reactions. Step 4: The learning unit accumulates questions from participants in a database and uses AI to learn how to respond to new questions and replies. For example, the learning unit can analyze question data from participants and identify frequently asked questions and new question patterns. The learning unit can also use generative AI to learn variations in replies and answers, improving the accuracy of the answer providing unit. Furthermore, the learning unit can evaluate the performance of the entire system based on participant feedback and identify areas for improvement.

[0102] 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.

[0103] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] 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.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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, in order to avoid confusion and to 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.

[0172] 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.

[0173] [Explanation of symbols]

[0174] 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. The seminar management team will conduct the seminar. a question reception section for receiving questions from participants; an answer providing unit that provides an answer based on the question received by the question receiving unit; a learning unit that learns and updates the answers provided by the answer providing unit. A system characterized by:

2. The seminar proceedings department: The robot will give a speech or project a document.

2. The system of claim 1.

3. The question receiving unit Acknowledge questions from participants 2. The system of claim 1.

4. The answer providing unit Providing an appropriate answer based on the question received by the question receiving unit 2. The system of claim 1.

5. The learning unit Questions from participants are stored in a database, and AI is used to learn how to respond to new questions or counter-narratives.

2. The system of claim 1.

6. The seminar proceedings department: Estimate participants' emotions and adjust the pace of the seminar based on the estimated emotions of the participants.

2. The system of claim 1.

7. The seminar proceedings department: As the seminar progresses, participants' reactions are analyzed in real time and the content of the seminar is dynamically changed.

2. The system of claim 1.

8. The seminar proceedings department: When conducting a seminar, refer to the participant's past participation history to conduct an individually customized seminar.

2. The system of claim 1.

9. The seminar proceedings department: Estimate participants' emotions and adjust the order of material projections based on the estimated emotions of participants.

2. The system of claim 1.

10. The seminar proceedings department: Use local examples and data based on participants' geographic locations during seminars 2. The system of claim 1.

Images