System

Abstract

An object of the system according to the embodiment is to comprehensively support preparation to execution of a presentation.SOLUTION: A system includes a reception part, a generation part, a check part, a feedback part, and a follow part. The reception unit receives a presentation situation. The generation unit generates an avatar based on the information received by the reception unit. A check part automatically generates base materials on the basis of the avatar generated by the generation part and checks the appropriateness of design and expression. The feedback part practices the presentation based on the material generated by the check part, and feeds back the result. The follow-up unit performs follow-up at the time of presentation based on the feedback provided by the feedback unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there are many issues when preparing and delivering presentations, such as nervousness, difficulty in creating materials, and responding to questions, and there is room for improvement.

[0005] The system according to the embodiment aims to provide comprehensive support for presentations, from preparation to execution. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, a check unit, a feedback unit, and a follow-up unit. The reception unit receives information about the presentation situation. The generation unit generates an avatar based on the information received by the reception unit. The check unit automatically generates base materials based on the avatar generated by the generation unit and checks the appropriateness of the design and expression. The feedback unit practices the presentation based on the materials generated by the check unit and provides feedback on the results. The follow-up unit follows up during the presentation based on the feedback provided by the feedback unit. [Effects of the Invention]

[0007] The system according to the embodiment can comprehensively support the entire process from preparation to execution of a presentation. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A presentation support system according to an embodiment of the present invention accepts a presentation situation, generates an avatar using a generation AI, automatically generates base materials, checks the appropriateness of the design and expression, conducts a practice presentation, provides feedback on the results, and provides follow-up support during the presentation. The presentation support system inputs the presentation situation as a prompt, generates an avatar appropriate for the presentation's audience, automatically generates base materials, and checks the appropriateness of the design and expression. Furthermore, the presentation support system conducts a practice presentation and provides feedback based on the results. Finally, the presentation support system provides follow-up support during the presentation, such as easing tension, checking time allocation, and interpreting the intent of questions. For example, if the presentation is for an executive and the purpose is to propose a new product, the presentation support system inputs information such as the presentation time limit of 30 minutes and the audience's high level of knowledge. This information is input into the generation AI. The generation AI then generates an avatar appropriate for the presentation's audience. For example, an executive avatar is generated for an executive-level presentation, and a superior avatar is generated for a superior-level presentation. This makes presentation practice more realistic. The generative AI automatically generates base materials and checks the appropriateness of the design and expression of the created materials. For example, the generative AI automatically generates the design of presentation materials and checks whether the expression is appropriate and for any violations. This results in the creation of high-quality presentation materials. The system practices the presentation and provides feedback based on the results. For example, the generative AI practices the presentation, points out the consistency between the materials and the statements, points out any unclear parts, and generates possible FAQs. This improves the quality of the presentation. Finally, the presentation support system provides advice to ease tension during the presentation, checks time allocation, interprets the intent of questions, and supports appropriate responses. This increases the success rate of the presentation. In this way, the presentation support system can improve the quality of presentations. For example, it supports the entire process from presentation preparation to the actual presentation, reducing the burden on the presenter. It also allows presenters to know specific areas for improvement in their presentations, increasing the success rate of their presentations.

[0029] A presentation support system according to an embodiment includes a reception unit, a generation unit, a check unit, a feedback unit, and a follow-up unit. The reception unit receives information about the presentation status. Examples of the presentation status include, but are not limited to, the recipient, purpose, presentation time, recipient's knowledge level, and industry. For example, if the recipient is an executive and the purpose is to propose a new product, the reception unit receives information such as, for example, a 30-minute presentation time and a high recipient's knowledge level. The generation unit uses a generation AI to generate an avatar based on the information received by the reception unit. Examples of the avatar generated include, but are not limited to, an executive avatar for an executive-level recipient and a superior avatar for a superior-level recipient. The generation unit generates the avatar using, for example, deep learning technology. The check unit uses the generation AI to automatically generate base materials based on the avatars generated by the generation unit and checks the appropriateness of the design and expression. The check unit, for example, automatically generates the design of the presentation materials using the generation AI and checks whether the expression is appropriate and whether there are any violations. The feedback unit uses the generation AI to practice a presentation based on the materials generated by the check unit and provides feedback on the results. For example, the feedback unit has the generation AI practice a presentation, point out the consistency between the materials and statements, point out any unclear parts, and generate expected FAQs. The follow-up unit uses the generation AI to provide follow-up during the presentation based on the feedback provided by the feedback unit. For example, the follow-up unit provides advice to help the generation AI ease tension during the presentation, checks time allocation, and interprets the intent of questions to support appropriate responses. This enables the presentation support system according to the embodiment to provide comprehensive support for improving the quality of presentations.

[0030] The reception unit can receive information about the recipient of the presentation, the purpose, the presentation time, the recipient's knowledge level, and the industry. The recipient of the presentation may include, but is not limited to, an executive, a superior, a colleague, a customer, etc. For example, if the recipient of the presentation is an executive, the reception unit receives the recipient's position and expertise. The purpose of the presentation may include, but is not limited to, a new product proposal, a performance report, education, information provision, etc. For example, if the purpose of the presentation is to propose a new product, the reception unit receives the proposal content and goals. The presentation time may include, but is not limited to, 10 minutes, 30 minutes, or 1 hour. For example, if the presentation time is 30 minutes, the reception unit receives the time limit. The recipient's knowledge level may include, but is not limited to, a beginner, intermediate, or expert. For example, if the recipient's knowledge level is high, the reception unit receives the recipient's range of expertise. The industry may include, but is not limited to, an IT industry, a medical industry, an education industry, etc. For example, if the person giving the presentation is a medical industry expert, the reception unit receives information related to that industry. This allows the reception of information appropriate to the situation of the presentation.

[0031] The generation unit can generate an avatar according to the presentation recipient using the generation AI. The generated avatars include, but are not limited to, executives, superiors, colleagues, and customers. The generation unit generates the avatar using deep learning technology, for example. For example, the generation AI generates an executive avatar for an executive-level presentation recipient, and generates a superior avatar for a superior-level presentation recipient. The generation AI can also generate realistic avatars using, for example, a generative artificial network (GAN). For example, the generation AI learns the characteristics of the presentation recipient and generates an avatar based on those characteristics. This makes presentation practice more realistic. Some or all of the above-described processing in the generation unit can be performed using the generation AI. For example, the generation unit can input information about the presentation recipient into the generation AI and have the generation AI generate an avatar.

[0032] The checking unit can automatically generate base materials using the generation AI and check the appropriateness of the design and expression. Examples of base materials include, but are not limited to, slides, text, and images. For example, the checking unit automatically generates presentation material designs using the generation AI and checks whether the expressions are appropriate and whether there are any violations. For example, the generation AI checks the design using an algorithm that evaluates visual beauty and information transmission. For example, the generation AI can use natural language processing technology to evaluate whether the content of the presentation materials is appropriate. For example, the generation AI can use image recognition technology to evaluate whether the expressions in the presentation materials are appropriate. This results in the creation of high-quality presentation materials. Some or all of the above-described processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the generated base materials into the generation AI and have the generation AI check the appropriateness of the design and expression.

[0033] The feedback unit can have the generation AI practice a presentation, point out the consistency between the materials and the statements, point out any difficult-to-understand parts, and generate expected FAQs. For example, the feedback unit has the generation AI practice a presentation and evaluate the consistency between the materials and the statements. The generation AI can use natural language processing technology, for example, to evaluate whether the content of the presentation matches the materials. The generation AI can also use speech recognition technology, for example, to evaluate whether the statements in the presentation match the materials. For example, the feedback unit has the generation AI practice a presentation and point out any difficult-to-understand parts. The generation AI can use natural language processing technology, for example, to identify parts of the presentation content that are difficult to understand. The generation AI can also use speech recognition technology, for example, to identify parts of the statements in the presentation that are difficult to understand. For example, the feedback unit has the generation AI practice a presentation and generate expected FAQs. The generation AI can generate FAQs based on past question data, for example. The generation AI can also generate FAQs based on simulation results, for example. This improves the quality of the presentation. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the results of a presentation practice into the generation AI and have the generation AI generate feedback.

[0034] The follow-up unit can provide the generation AI with advice to relieve tension during a presentation, check time allocation, and interpret the intent of the question to support the response. For example, the follow-up unit allows the generation AI to provide advice to relieve tension during a presentation. The generation AI can, for example, suggest breathing or relaxation techniques. The generation AI can also provide audio guidance to relieve tension during a presentation. For example, the follow-up unit allows the generation AI to check time allocation during a presentation. The generation AI can, for example, monitor the progress of the presentation using a timer. The generation AI can, for example, check the time allocation for each slide. For example, the follow-up unit allows the generation AI to interpret the intent of a question during a presentation and support the response. The generation AI can, for example, analyze the background of the question and the purpose of the questioner. The generation AI can, for example, interpret the intent of the question and suggest an appropriate response. This increases the success rate of the presentation. Some or all of the above-mentioned processes in the follow-up unit are performed using the generation AI. For example, the follow-up unit can input the situation during the presentation into the generation AI and have the generation AI execute the follow-up.

[0035] The reception unit can analyze past reaction data of the other party to the presentation and select the optimal information reception method. For example, the reception unit prioritizes information reception methods to which the other party to the presentation has responded favorably in the past. For example, the reception unit avoids information reception methods to which the other party to the presentation has responded negatively in the past. For example, the reception unit customizes the optimal information reception method based on the other party's past reaction data. This makes it possible to select the optimal information reception method according to the other party to the presentation. Analysis of past reaction data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and suggest the optimal information reception method. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input past reaction data into the generation AI and have the generation AI select the information reception method.

[0036] The reception unit can adjust the level of detail of the information to be accepted depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the reception unit accepts detailed technical information. For example, if the purpose of the presentation is a simple report, the reception unit accepts only an outline. For example, if the purpose of the presentation is education, the reception unit sets the level of detail of the information to be accepted to a medium level. This allows the level of detail of the information to be adjusted depending on the purpose of the presentation. The adjustment of the level of detail of the information is performed, for example, using a generation AI. The generation AI can suggest the level of detail of the information to be accepted depending on the purpose of the presentation. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the level of detail of the information.

[0037] The reception unit can filter the information to be received based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the reception unit will prioritize receiving specialized information. For example, if the other person receiving the presentation is a beginner, the reception unit will prioritize receiving basic information. For example, the reception unit adjusts the level of detail of the information according to the knowledge level of the other person receiving the presentation. This makes it possible to filter the information according to the knowledge level of the other person receiving the presentation. The filtering of the information is performed using, for example, a generation AI. The generation AI can suggest filtering of the information to be received based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input the knowledge level of the other person receiving the presentation into the generation AI and have the generation AI perform information filtering.

[0038] The reception unit can prioritize receiving highly relevant information taking into account the geographical location information of the recipient. For example, if the recipient is in a specific region, the reception unit prioritizes receiving information related to that region. For example, if the recipient is in a different region, the reception unit filters information related to that region. For example, the reception unit selects optimal information based on the geographical location information of the recipient. This makes it possible to receive highly relevant information based on the geographical location information of the recipient. The geographical location information is acquired using, for example, a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographical location information of the recipient. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input the geographical location information of the recipient to the generation AI and have the generation AI select the information.

[0039] The reception unit can analyze the social media activity of the other party receiving the presentation and receive related information. For example, the reception unit preferentially receives information related to topics in which the other party has shown interest on social media. For example, the reception unit analyzes the content of the other party's social media posts and filters the related information. For example, the reception unit receives related information by referring to the activity of the other party's friends on social media. This makes it possible to receive related information based on the other party's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify related information. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the social media activity of the other party to the generation AI and have the generation AI select the information.

[0040] The reception unit can customize the information reception method by reflecting the past feedback of the other person receiving the presentation. For example, the reception unit prioritizes information reception methods for which the other person receiving the presentation has given favorable feedback in the past. For example, the reception unit avoids information reception methods for which the other person receiving the presentation has given negative feedback in the past. For example, the reception unit customizes the optimal information reception method based on the other person receiving the presentation's past feedback. This allows the information reception method to be customized based on the other person receiving the presentation's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal information reception method. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input the other person receiving the presentation's past feedback into the generation AI and have the generation AI customize the information reception method.

[0041] The generation unit can analyze past reaction data of the presentation partner and select the optimal avatar generation method. For example, the generation unit prioritizes avatar expression methods to which the presentation partner has previously responded favorably. For example, the generation unit avoids avatar expression methods to which the presentation partner has previously responded negatively. For example, the generation unit customizes the optimal avatar generation method based on the presentation partner's past reaction data. This allows the selection of the optimal avatar generation method according to the presentation partner. The analysis of past reaction data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and propose the optimal avatar generation method. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input past reaction data into the generation AI and have the generation AI select the avatar generation method.

[0042] The generation unit can adjust the level of detail of the avatar depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the generation unit generates a detailed avatar. For example, if the purpose of the presentation is to make a simple report, the generation unit generates a simple avatar. For example, if the purpose of the presentation is to educate, the generation unit generates an avatar with a medium level of detail. This allows the level of detail of the avatar to be adjusted depending on the purpose of the presentation. The adjustment of the level of detail of the avatar is performed using, for example, a generation AI. The generation AI can suggest the level of detail of the avatar depending on the purpose of the presentation. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the purpose of the presentation into the generation AI and cause the generation AI to adjust the level of detail of the avatar.

[0043] The generation unit can customize the expression of the avatar based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the generation unit generates an avatar with a professional expression. For example, if the other person receiving the presentation is a beginner, the generation unit generates an avatar with a basic expression. For example, the generation unit adjusts the expression of the avatar according to the knowledge level of the other person receiving the presentation. This allows the expression of the avatar to be customized according to the knowledge level of the other person receiving the presentation. The customization of the avatar expression is performed using, for example, a generation AI. The generation AI can suggest an expression of the avatar based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the knowledge level of the other person receiving the presentation into the generation AI and cause the generation AI to customize the expression of the avatar.

[0044] The generation unit can prioritize generating highly relevant avatars by taking into account the geographic location information of the other person receiving the presentation. For example, if the other person receiving the presentation is in a specific region, the generation unit prioritizes generating avatars related to that region. For example, if the other person receiving the presentation is in a different region, the generation unit filters avatars related to that region. For example, the generation unit selects the optimal avatar based on the geographic location information of the other person receiving the presentation. This makes it possible to generate highly relevant avatars based on the geographic location information of the other person receiving the presentation. The geographic location information is acquired using, for example, a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographic location information of the other person receiving the presentation. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the geographic location information of the other person receiving the presentation to the generation AI and have the generation AI select an avatar.

[0045] The generation unit can analyze the social media activity of the person receiving the presentation and generate a relevant avatar. For example, the generation unit prioritizes generating avatars related to topics in which the person receiving the presentation has shown interest on social media. For example, the generation unit analyzes the content of the person receiving the presentation's social media posts and filters out relevant avatars. For example, the generation unit generates relevant avatars by referring to the activity of the person receiving the presentation's friends on social media. This makes it possible to generate relevant avatars based on the person receiving the presentation's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant avatars. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the social media activity of the person receiving the presentation into the generation AI and have the generation AI select an avatar.

[0046] The generation unit can customize the avatar generation method by reflecting the past feedback of the other presenter. For example, the generation unit prioritizes an avatar expression method for which the other presenter has given favorable feedback in the past. For example, the generation unit avoids an avatar expression method for which the other presenter has given negative feedback in the past. For example, the generation unit customizes an optimal avatar generation method based on the past feedback of the other presenter. This allows the avatar generation method to be customized based on the past feedback of the other presenter. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and propose an optimal avatar generation method. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the past feedback of the other presenter into the generation AI and cause the generation AI to customize the avatar generation method.

[0047] The checking unit can analyze past evaluation data of the presentation materials and select the optimal checking method. For example, the checking unit prioritizes checking methods that have received high evaluations for presentation materials in the past. For example, the checking unit avoids checking methods that have received low evaluations for presentation materials in the past. For example, the checking unit customizes the optimal checking method based on the past evaluation data of the presentation materials. This allows the optimal checking method to be selected based on the past evaluation data of the presentation materials. Analysis of the past evaluation data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and propose the optimal checking method. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input past evaluation data of the presentation materials into the generation AI and have the generation AI select the checking method.

[0048] The checking unit can adjust the check items of the materials depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the checking unit prioritizes technical check items. For example, if the purpose of the presentation is a simple report, the checking unit prioritizes summary check items. For example, if the purpose of the presentation is education, the checking unit prioritizes educational check items. This allows the check items of the materials to be adjusted depending on the purpose of the presentation. The adjustment of the check items is performed using, for example, a generation AI. The generation AI can suggest check items depending on the purpose of the presentation. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the check items.

[0049] The checking unit can customize the expression of the material based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the checking unit prioritizes specialized expression. For example, if the other person receiving the presentation is a beginner, the checking unit prioritizes basic expression. For example, the checking unit adjusts the expression of the material according to the knowledge level of the other person receiving the presentation. This allows the expression of the material to be customized according to the knowledge level of the other person receiving the presentation. Customization of the expression of the material is performed using, for example, a generation AI. The generation AI can suggest an expression of the material based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the knowledge level of the other person receiving the presentation into the generation AI and cause the generation AI to customize the expression of the material.

[0050] The checking unit can prioritize checking highly relevant materials by taking into account the geographic location information of the recipient. For example, if the recipient is in a specific region, the checking unit prioritizes checking materials related to that region. For example, if the recipient is in a different region, the checking unit filters materials related to that region. For example, the checking unit selects the most appropriate materials based on the geographic location information of the recipient. This makes it possible to check highly relevant materials based on the geographic location information of the recipient. The geographic location information is obtained, for example, using a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographic location information of the recipient. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the geographic location information of the recipient to the generation AI and have the generation AI select materials.

[0051] The checking unit can analyze the social media activity of the recipient and check relevant materials. For example, the checking unit prioritizes checking materials related to topics that the recipient has shown interest in on social media. For example, the checking unit analyzes the content of the recipient's social media posts and filters out relevant materials. For example, the checking unit checks relevant materials by referring to the activity of the recipient's friends on social media. This makes it possible to check relevant materials based on the recipient's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant materials. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the recipient's social media activity into the generation AI and have the generation AI select materials.

[0052] The checking unit can customize the method for checking materials by reflecting past feedback from the other party to the presentation. For example, the checking unit prioritizes checking methods for which the other party to the presentation has given favorable feedback in the past. For example, the checking unit avoids checking methods for which the other party to the presentation has given negative feedback in the past. For example, the checking unit customizes the optimal checking method based on the other party to the presentation's past feedback. This allows the method for checking materials to be customized based on the other party to the presentation's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal checking method. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input past feedback from the other party to the generation AI and have the generation AI customize the checking method.

[0053] The feedback unit can analyze past data of presentation practice results and select the optimal feedback method. For example, the feedback unit prioritizes feedback methods that have received high marks in the past for presentation practice results. For example, the feedback unit avoids feedback methods that have received low marks in the past for presentation practice results. For example, the feedback unit customizes the optimal feedback method based on the past data of presentation practice results. This allows the optimal feedback method to be selected based on the past data of presentation practice results. Analysis of the past data is performed using, for example, a generation AI. The generation AI can analyze past practice results and feedback comments and suggest the optimal feedback method. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input past data of presentation practice results into the generation AI and have the generation AI select the feedback method.

[0054] The feedback unit can adjust the level of detail of the feedback depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the feedback unit provides detailed feedback. For example, if the purpose of the presentation is a simple report, the feedback unit provides summary feedback. For example, if the purpose of the presentation is education, the feedback unit provides educational feedback. This makes it possible to adjust the level of detail of the feedback depending on the purpose of the presentation. The adjustment of the level of detail of the feedback is performed, for example, using a generation AI. The generation AI can suggest the level of detail of the feedback depending on the purpose of the presentation. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the purpose of the presentation to the generation AI and cause the generation AI to adjust the level of detail of the feedback.

[0055] The feedback unit can customize the content of the feedback based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the feedback unit provides specialized feedback. For example, if the other person receiving the presentation is a beginner, the feedback unit provides basic feedback. For example, the feedback unit adjusts the content of the feedback according to the knowledge level of the other person receiving the presentation. This makes it possible to customize the content of the feedback according to the knowledge level of the other person receiving the presentation. Customization of the content of the feedback is performed, for example, using a generation AI. The generation AI can suggest the content of the feedback based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the knowledge level of the other person receiving the presentation into the generation AI and cause the generation AI to customize the content of the feedback.

[0056] The feedback unit can prioritize providing highly relevant feedback by taking into account the geographic location information of the other person receiving the presentation. For example, if the other person receiving the presentation is in a specific region, the feedback unit prioritizes providing feedback related to that region. For example, if the other person receiving the presentation is in a different region, the feedback unit filters feedback related to that region. For example, the feedback unit selects optimal feedback based on the geographic location information of the other person receiving the presentation. This makes it possible to provide highly relevant feedback based on the geographic location information of the other person receiving the presentation. The geographic location information is obtained using, for example, a generation AI. The generation AI can analyze GPS data or an IP address to identify the geographic location information of the other person receiving the presentation. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the geographic location information of the other person receiving the presentation to the generation AI and cause the generation AI to select feedback.

[0057] The feedback unit can analyze the social media activity of the recipient and provide relevant feedback. For example, the feedback unit can prioritize providing feedback related to topics in which the recipient has shown interest on social media. For example, the feedback unit can analyze the content of the recipient's social media posts and filter relevant feedback. For example, the feedback unit can provide relevant feedback by referring to the activity of the recipient's friends on social media. This makes it possible to provide relevant feedback based on the recipient's social media activity. The analysis of social media activity can be performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant feedback. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the recipient's social media activity into the generation AI and have the generation AI select feedback.

[0058] The feedback unit can customize the feedback method by reflecting the other person's past feedback. For example, the feedback unit prioritizes methods for which the other person has given positive feedback in the past. For example, the feedback unit avoids methods for which the other person has given negative feedback in the past. The feedback unit customizes the optimal feedback method based on the other person's past feedback, for example. This allows the feedback method to be customized based on the other person's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal feedback method. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the other person's past feedback into the generation AI and have the generation AI customize the feedback method.

[0059] The follow-up unit can analyze past reaction data during the presentation and select the optimal follow-up method. For example, the follow-up unit prioritizes follow-up methods that have shown favorable reactions based on past reaction data during the presentation. For example, the follow-up unit avoids follow-up methods that have shown negative reactions based on past reaction data during the presentation. For example, the follow-up unit customizes the optimal follow-up method based on past reaction data during the presentation. This allows the optimal follow-up method to be selected based on past reaction data during the presentation. Analysis of past reaction data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and suggest the optimal follow-up method. Some or all of the above-mentioned processing in the follow-up unit can be performed using the generation AI. For example, the follow-up unit can input past reaction data during the presentation into the generation AI and have the generation AI select a follow-up method.

[0060] The follow-up unit can adjust the level of detail in the follow-up depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the follow-up unit provides detailed follow-up. For example, if the purpose of the presentation is a simple report, the follow-up unit provides summary follow-up. For example, if the purpose of the presentation is education, the follow-up unit provides educational follow-up. This makes it possible to adjust the level of detail in the follow-up depending on the purpose of the presentation. The adjustment of the level of detail in the follow-up is performed, for example, using a generation AI. The generation AI can suggest the level of detail in the follow-up depending on the purpose of the presentation. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the level of detail in the follow-up.

[0061] The follow-up unit can customize the content of the follow-up based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the follow-up unit provides professional follow-up. For example, if the other person receiving the presentation is a beginner, the follow-up unit provides basic follow-up. For example, the follow-up unit adjusts the content of the follow-up according to the knowledge level of the other person receiving the presentation. This makes it possible to customize the content of the follow-up according to the knowledge level of the other person receiving the presentation. Customization of the content of the follow-up is performed using, for example, a generation AI. The generation AI can suggest content of the follow-up based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the knowledge level of the other person receiving the presentation into the generation AI and have the generation AI customize the content of the follow-up.

[0062] The follow-up unit can prioritize providing highly relevant follows by taking into account the geographical location information of the other person receiving the presentation. For example, if the other person receiving the presentation is in a specific region, the follow-up unit prioritizes providing follows related to that region. For example, if the other person receiving the presentation is in a different region, the follow-up unit filters follows related to that region. For example, the follow-up unit selects the optimal follow-up based on the geographical location information of the other person receiving the presentation. This makes it possible to provide highly relevant follows based on the geographical location information of the other person receiving the presentation. The geographical location information is acquired using, for example, a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographical location information of the other person receiving the presentation. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the geographical location information of the other person receiving the presentation to the generation AI and have the generation AI select the follow-up.

[0063] The following unit can analyze the social media activity of the recipient and provide relevant follows. For example, the following unit prioritizes providing follows related to topics in which the recipient has shown interest on social media. For example, the following unit analyzes the content of the recipient's social media posts and filters out relevant follows. For example, the following unit provides relevant follows by referring to the activity of the recipient's friends on social media. This makes it possible to provide relevant follows based on the recipient's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant follows. Some or all of the above-mentioned processing in the following unit is performed using the generation AI. For example, the following unit can input the recipient's social media activity into the generation AI and have the generation AI select follows.

[0064] The follow-up unit can customize the follow-up method by reflecting the past feedback of the other person receiving the presentation. For example, the follow-up unit prioritizes follow-up methods for which the other person receiving the presentation has given favorable feedback in the past. For example, the follow-up unit avoids follow-up methods for which the other person receiving the presentation has given negative feedback in the past. For example, the follow-up unit customizes the optimal follow-up method based on the other person receiving the presentation's past feedback. This allows the follow-up method to be customized based on the other person receiving the presentation's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal follow-up method. Some or all of the above-mentioned processing in the follow-up unit can be performed using the generation AI. For example, the follow-up unit can input the other person receiving the presentation's past feedback into the generation AI and have the generation AI customize the follow-up method.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The reception unit can adjust the format and content of the information it accepts, taking into account the cultural background of the recipient. For example, if the recipient belongs to a different culture, it uses expressions and examples appropriate to that culture. For example, if the recipient belongs to an Asian culture, the reception unit prioritizes accepting examples and expressions common in Asian cultures. For example, if the recipient belongs to a Western culture, the reception unit prioritizes accepting examples and expressions common in Western cultures. This makes it possible to accept information according to the recipient's cultural background. Consideration of cultural background is performed, for example, using a generation AI. The generation AI can suggest an appropriate format and content of information based on the recipient's cultural background. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the recipient's cultural background into the generation AI and have the generation AI adjust the format and content of the information.

[0067] The generation unit can customize the avatar's clothing and accessories based on the occupation and position of the person giving the presentation. For example, if the person giving the presentation is a medical professional, the generation unit generates an avatar wearing a medical lab coat and holding a stethoscope. For example, if the person giving the presentation is a businessman, the generation unit generates an avatar wearing a suit and tie. For example, if the person giving the presentation is an engineer, the generation unit generates an avatar wearing work clothes and holding tools. This makes it possible to customize the avatar according to the occupation and position of the person giving the presentation. The customization of the avatar's clothing and accessories is performed using, for example, a generation AI. The generation AI can suggest appropriate clothing and accessories based on the occupation and position of the person giving the presentation. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the occupation and position of the person giving the presentation into the generation AI and cause the generation AI to customize the avatar's clothing and accessories.

[0068] The checking unit can adjust the design of the presentation materials using color psychology to enhance the visual elements of the materials. For example, if the purpose of the presentation is to persuade, the checking unit can make extensive use of blue, which conveys a sense of trust. For example, if the purpose of the presentation is to educate, the checking unit can make extensive use of green, which promotes concentration. For example, if the purpose of the presentation is to convey urgency, the checking unit can make extensive use of red, which attracts attention. This makes it possible to enhance the visual elements according to the purpose of the presentation. The application of color psychology is performed, for example, using a generation AI. The generation AI can suggest appropriate colors based on the purpose of the presentation. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the colors.

[0069] The reception unit can analyze the past purchasing history of the person receiving the presentation and select the optimal information reception method. For example, the reception unit can prioritize information related to products that the person receiving the presentation has purchased in the past. For example, if the person receiving the presentation has a negative reaction to a product that they have purchased in the past, the reception unit can avoid information related to that product. The reception unit can customize the optimal information reception method based on the person receiving the presentation's past purchasing history. This makes it possible to select the optimal information reception method according to the person receiving the presentation's purchasing history. The analysis of the past purchasing history is performed using, for example, a generation AI. The generation AI can analyze past purchasing data and suggest the optimal information reception method. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the past purchasing history into the generation AI and have the generation AI select the information reception method.

[0070] The generation unit can customize the avatar's background and props based on the hobbies and interests of the person receiving the presentation. For example, if the person receiving the presentation likes sports, the generation unit generates an avatar with a sports-related background and props. For example, if the person receiving the presentation likes music, the generation unit generates an avatar with an instrument or music-related props. For example, if the person receiving the presentation likes traveling, the generation unit generates an avatar with a travel-related background and props. This makes it possible to customize the avatar according to the person receiving the presentation's hobbies and interests. The customization of the avatar's background and props is performed using, for example, a generation AI. The generation AI can suggest appropriate backgrounds and props based on the person receiving the presentation's hobbies and interests. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the person receiving the presentation's hobbies and interests into the generation AI and cause the generation AI to customize the avatar's background and props.

[0071] The checking unit can adjust the design of the presentation materials using visual storytelling techniques to enhance the visual elements of the materials. For example, if the purpose of the presentation is persuasive, the checking unit can use visual storytelling to emphasize the logical flow. For example, if the purpose of the presentation is educational, the checking unit can use visual storytelling to enhance the learning effect. For example, if the purpose of the presentation is to provide information, the checking unit can use visual storytelling to smooth the transmission of information. This makes it possible to enhance the visual elements according to the purpose of the presentation. The application of visual storytelling is performed, for example, using a generation AI. The generation AI can suggest appropriate visual storytelling techniques based on the purpose of the presentation. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the purpose of the presentation into the generation AI and cause the generation AI to adjust the visual storytelling.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The reception unit receives the presentation status. The presentation status includes, for example, the person being presented to, the purpose, the presentation time, the knowledge level of the person being presented to, the industry, etc. Specifically, if the person being presented to is an executive and the purpose is to propose a new product, the reception unit receives information such as the presentation time being 30 minutes and the knowledge level of the person being presented to being high. Step 2: The generation unit uses the generation AI to generate an avatar based on the information received by the reception unit. The generated avatars include, for example, an executive avatar for an executive-level presentation partner, a superior avatar for a superior-level presentation partner, etc. The generation AI generates the avatar using deep learning technology. Step 3: The Checking Department uses the Generation AI to automatically generate base materials based on the avatar generated by the Generation Department, and checks the appropriateness of the design and expression. The Generation AI automatically generates the design of presentation materials, and checks whether the expression is appropriate and there are no violations. Step 4: The feedback department uses the generation AI to practice the presentation based on the materials generated by the checking department and provides feedback on the results. The generation AI practices the presentation, points out any consistency between the materials and the statements, and identifies any unclear parts, generating anticipated FAQs. Step 5: The Follow-up section uses the Generative AI to provide follow-up during the presentation based on the feedback provided by the Feedback section. The Generative AI provides advice to ease tension during the presentation, checks time allocation, and interprets the intent of questions to support appropriate responses.

[0074] (Example 2) A presentation support system according to an embodiment of the present invention accepts a presentation situation, generates an avatar using a generation AI, automatically generates base materials, checks the appropriateness of the design and expression, conducts a practice presentation, provides feedback on the results, and provides follow-up support during the presentation. The presentation support system inputs the presentation situation as a prompt, generates an avatar appropriate for the presentation's audience, automatically generates base materials, and checks the appropriateness of the design and expression. Furthermore, the presentation support system conducts a practice presentation and provides feedback based on the results. Finally, the presentation support system provides follow-up support during the presentation, such as easing tension, checking time allocation, and interpreting the intent of questions. For example, if the presentation is for an executive and the purpose is to propose a new product, the presentation support system inputs information such as the presentation time limit of 30 minutes and the audience's high level of knowledge. This information is input into the generation AI. The generation AI then generates an avatar appropriate for the presentation's audience. For example, an executive avatar is generated for an executive-level presentation, and a superior avatar is generated for a superior-level presentation. This makes presentation practice more realistic. The generative AI automatically generates base materials and checks the appropriateness of the design and expression of the created materials. For example, the generative AI automatically generates the design of presentation materials and checks whether the expression is appropriate and for any violations. This results in the creation of high-quality presentation materials. The system practices the presentation and provides feedback based on the results. For example, the generative AI practices the presentation, points out the consistency between the materials and the statements, points out any unclear parts, and generates possible FAQs. This improves the quality of the presentation. Finally, the presentation support system provides advice to ease tension during the presentation, checks time allocation, interprets the intent of questions, and supports appropriate responses. This increases the success rate of the presentation. In this way, the presentation support system can improve the quality of presentations. For example, it supports the entire process from presentation preparation to the actual presentation, reducing the burden on the presenter. It also allows presenters to know specific areas for improvement in their presentations, increasing the success rate of their presentations.

[0075] A presentation support system according to an embodiment includes a reception unit, a generation unit, a check unit, a feedback unit, and a follow-up unit. The reception unit receives information about the presentation status. Examples of the presentation status include, but are not limited to, the recipient, purpose, presentation time, recipient's knowledge level, and industry. For example, if the recipient is an executive and the purpose is to propose a new product, the reception unit receives information such as, for example, a 30-minute presentation time and a high recipient's knowledge level. The generation unit uses a generation AI to generate an avatar based on the information received by the reception unit. Examples of the avatar generated include, but are not limited to, an executive avatar for an executive-level recipient and a superior avatar for a superior-level recipient. The generation unit generates the avatar using, for example, deep learning technology. The check unit uses the generation AI to automatically generate base materials based on the avatars generated by the generation unit and checks the appropriateness of the design and expression. The check unit, for example, automatically generates the design of the presentation materials using the generation AI and checks whether the expression is appropriate and whether there are any violations. The feedback unit uses the generation AI to practice a presentation based on the materials generated by the check unit and provides feedback on the results. For example, the feedback unit has the generation AI practice a presentation, point out the consistency between the materials and statements, point out any unclear parts, and generate expected FAQs. The follow-up unit uses the generation AI to provide follow-up during the presentation based on the feedback provided by the feedback unit. For example, the follow-up unit provides advice to help the generation AI ease tension during the presentation, checks time allocation, and interprets the intent of questions to support appropriate responses. This enables the presentation support system according to the embodiment to provide comprehensive support for improving the quality of presentations.

[0076] The reception unit can receive information about the recipient of the presentation, the purpose, the presentation time, the recipient's knowledge level, and the industry. The recipient of the presentation may include, but is not limited to, an executive, a superior, a colleague, a customer, etc. For example, if the recipient of the presentation is an executive, the reception unit receives the recipient's position and expertise. The purpose of the presentation may include, but is not limited to, a new product proposal, a performance report, education, information provision, etc. For example, if the purpose of the presentation is to propose a new product, the reception unit receives the proposal content and goals. The presentation time may include, but is not limited to, 10 minutes, 30 minutes, or 1 hour. For example, if the presentation time is 30 minutes, the reception unit receives the time limit. The recipient's knowledge level may include, but is not limited to, a beginner, intermediate, or expert. For example, if the recipient's knowledge level is high, the reception unit receives the recipient's range of expertise. The industry may include, but is not limited to, an IT industry, a medical industry, an education industry, etc. For example, if the person giving the presentation is a medical industry expert, the reception unit receives information related to that industry. This allows the reception of information appropriate to the situation of the presentation.

[0077] The generation unit can generate an avatar according to the presentation recipient using the generation AI. The generated avatars include, but are not limited to, executives, superiors, colleagues, and customers. The generation unit generates the avatar using deep learning technology, for example. For example, the generation AI generates an executive avatar for an executive-level presentation recipient, and generates a superior avatar for a superior-level presentation recipient. The generation AI can also generate realistic avatars using, for example, a generative artificial network (GAN). For example, the generation AI learns the characteristics of the presentation recipient and generates an avatar based on those characteristics. This makes presentation practice more realistic. Some or all of the above-described processing in the generation unit can be performed using the generation AI. For example, the generation unit can input information about the presentation recipient into the generation AI and have the generation AI generate an avatar.

[0078] The checking unit can automatically generate base materials using the generation AI and check the appropriateness of the design and expression. Examples of base materials include, but are not limited to, slides, text, and images. For example, the checking unit automatically generates presentation material designs using the generation AI and checks whether the expressions are appropriate and whether there are any violations. For example, the generation AI checks the design using an algorithm that evaluates visual beauty and information transmission. For example, the generation AI can use natural language processing technology to evaluate whether the content of the presentation materials is appropriate. For example, the generation AI can use image recognition technology to evaluate whether the expressions in the presentation materials are appropriate. This results in the creation of high-quality presentation materials. Some or all of the above-described processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the generated base materials into the generation AI and have the generation AI check the appropriateness of the design and expression.

[0079] The feedback unit can have the generation AI practice a presentation, point out the consistency between the materials and the statements, point out any difficult-to-understand parts, and generate expected FAQs. For example, the feedback unit has the generation AI practice a presentation and evaluate the consistency between the materials and the statements. The generation AI can use natural language processing technology, for example, to evaluate whether the content of the presentation matches the materials. The generation AI can also use speech recognition technology, for example, to evaluate whether the statements in the presentation match the materials. For example, the feedback unit has the generation AI practice a presentation and point out any difficult-to-understand parts. The generation AI can use natural language processing technology, for example, to identify parts of the presentation content that are difficult to understand. The generation AI can also use speech recognition technology, for example, to identify parts of the statements in the presentation that are difficult to understand. For example, the feedback unit has the generation AI practice a presentation and generate expected FAQs. The generation AI can generate FAQs based on past question data, for example. The generation AI can also generate FAQs based on simulation results, for example. This improves the quality of the presentation. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the results of a presentation practice into the generation AI and have the generation AI generate feedback.

[0080] The follow-up unit can provide the generation AI with advice to relieve tension during a presentation, check time allocation, and interpret the intent of the question to support the response. For example, the follow-up unit allows the generation AI to provide advice to relieve tension during a presentation. The generation AI can, for example, suggest breathing or relaxation techniques. The generation AI can also provide audio guidance to relieve tension during a presentation. For example, the follow-up unit allows the generation AI to check time allocation during a presentation. The generation AI can, for example, monitor the progress of the presentation using a timer. The generation AI can, for example, check the time allocation for each slide. For example, the follow-up unit allows the generation AI to interpret the intent of a question during a presentation and support the response. The generation AI can, for example, analyze the background of the question and the purpose of the questioner. The generation AI can, for example, interpret the intent of the question and suggest an appropriate response. This increases the success rate of the presentation. Some or all of the above-mentioned processes in the follow-up unit are performed using the generation AI. For example, the follow-up unit can input the situation during the presentation into the generation AI and have the generation AI execute the follow-up.

[0081] The reception unit can estimate the user's emotions and adjust the timing for accepting information about the presentation status based on the estimated user emotions. For example, if the user is nervous, the reception unit allows the user time to relax before accepting information about the presentation status. For example, if the user is impatient, the reception unit quickly accepts information about the presentation status. For example, if the user is relaxed, the reception unit takes time to accept detailed information. This allows information to be accepted at an appropriate time depending on the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the user's facial expression data into the generation AI and have the generation AI execute emotion estimation.

[0082] The reception unit can analyze past reaction data of the other party to the presentation and select the optimal information reception method. For example, the reception unit prioritizes information reception methods to which the other party to the presentation has responded favorably in the past. For example, the reception unit avoids information reception methods to which the other party to the presentation has responded negatively in the past. For example, the reception unit customizes the optimal information reception method based on the other party's past reaction data. This makes it possible to select the optimal information reception method according to the other party to the presentation. Analysis of past reaction data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and suggest the optimal information reception method. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input past reaction data into the generation AI and have the generation AI select the information reception method.

[0083] The reception unit can adjust the level of detail of the information to be accepted depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the reception unit accepts detailed technical information. For example, if the purpose of the presentation is a simple report, the reception unit accepts only an outline. For example, if the purpose of the presentation is education, the reception unit sets the level of detail of the information to be accepted to a medium level. This allows the level of detail of the information to be adjusted depending on the purpose of the presentation. The adjustment of the level of detail of the information is performed, for example, using a generation AI. The generation AI can suggest the level of detail of the information to be accepted depending on the purpose of the presentation. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the level of detail of the information.

[0084] The reception unit can filter the information to be received based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the reception unit will prioritize receiving specialized information. For example, if the other person receiving the presentation is a beginner, the reception unit will prioritize receiving basic information. For example, the reception unit adjusts the level of detail of the information according to the knowledge level of the other person receiving the presentation. This makes it possible to filter the information according to the knowledge level of the other person receiving the presentation. The filtering of the information is performed using, for example, a generation AI. The generation AI can suggest filtering of the information to be received based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input the knowledge level of the other person receiving the presentation into the generation AI and have the generation AI perform information filtering.

[0085] The reception unit can estimate the user's emotions and determine the priority of information to be received based on the estimated user emotions. For example, if the user is nervous, the reception unit prioritizes receiving important information. For example, if the user is relaxed, the reception unit prioritizes receiving detailed information. For example, if the user is impatient, the reception unit prioritizes receiving information that can be processed quickly. This allows the priority of information to be determined according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the user's facial expression data into the generation AI and have the generation AI execute emotion estimation.

[0086] The reception unit can prioritize receiving highly relevant information taking into account the geographical location information of the recipient. For example, if the recipient is in a specific region, the reception unit prioritizes receiving information related to that region. For example, if the recipient is in a different region, the reception unit filters information related to that region. For example, the reception unit selects optimal information based on the geographical location information of the recipient. This makes it possible to receive highly relevant information based on the geographical location information of the recipient. The geographical location information is acquired using, for example, a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographical location information of the recipient. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input the geographical location information of the recipient to the generation AI and have the generation AI select the information.

[0087] The reception unit can analyze the social media activity of the other party receiving the presentation and receive related information. For example, the reception unit preferentially receives information related to topics in which the other party has shown interest on social media. For example, the reception unit analyzes the content of the other party's social media posts and filters the related information. For example, the reception unit receives related information by referring to the activity of the other party's friends on social media. This makes it possible to receive related information based on the other party's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify related information. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the social media activity of the other party to the generation AI and have the generation AI select the information.

[0088] The reception unit can customize the information reception method by reflecting the past feedback of the other person receiving the presentation. For example, the reception unit prioritizes information reception methods for which the other person receiving the presentation has given favorable feedback in the past. For example, the reception unit avoids information reception methods for which the other person receiving the presentation has given negative feedback in the past. For example, the reception unit customizes the optimal information reception method based on the other person receiving the presentation's past feedback. This allows the information reception method to be customized based on the other person receiving the presentation's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal information reception method. Some or all of the above-mentioned processing in the reception unit can be performed using the generation AI. For example, the reception unit can input the other person receiving the presentation's past feedback into the generation AI and have the generation AI customize the information reception method.

[0089] The generation unit can estimate the user's emotions and adjust the avatar's expression style based on the estimated user's emotions. For example, if the user is nervous, the generation unit generates an avatar with a relaxed expression. For example, if the user is relaxed, the generation unit generates an avatar with a cheerful expression. For example, if the user is impatient, the generation unit generates an avatar with a calm expression. This allows the avatar's expression style to be adjusted according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0090] The generation unit can analyze past reaction data of the presentation partner and select the optimal avatar generation method. For example, the generation unit prioritizes avatar expression methods to which the presentation partner has previously responded favorably. For example, the generation unit avoids avatar expression methods to which the presentation partner has previously responded negatively. For example, the generation unit customizes the optimal avatar generation method based on the presentation partner's past reaction data. This allows the selection of the optimal avatar generation method according to the presentation partner. The analysis of past reaction data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and propose the optimal avatar generation method. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input past reaction data into the generation AI and have the generation AI select the avatar generation method.

[0091] The generation unit can adjust the level of detail of the avatar depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the generation unit generates a detailed avatar. For example, if the purpose of the presentation is to make a simple report, the generation unit generates a simple avatar. For example, if the purpose of the presentation is to educate, the generation unit generates an avatar with a medium level of detail. This allows the level of detail of the avatar to be adjusted depending on the purpose of the presentation. The adjustment of the level of detail of the avatar is performed using, for example, a generation AI. The generation AI can suggest the level of detail of the avatar depending on the purpose of the presentation. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the purpose of the presentation into the generation AI and cause the generation AI to adjust the level of detail of the avatar.

[0092] The generation unit can customize the expression of the avatar based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the generation unit generates an avatar with a professional expression. For example, if the other person receiving the presentation is a beginner, the generation unit generates an avatar with a basic expression. For example, the generation unit adjusts the expression of the avatar according to the knowledge level of the other person receiving the presentation. This allows the expression of the avatar to be customized according to the knowledge level of the other person receiving the presentation. The customization of the avatar expression is performed using, for example, a generation AI. The generation AI can suggest an expression of the avatar based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the knowledge level of the other person receiving the presentation into the generation AI and cause the generation AI to customize the expression of the avatar.

[0093] The generation unit can estimate the user's emotions and determine the order in which avatars are generated based on the estimated user emotions. For example, if the user is nervous, the generation unit prioritizes generating avatars with a relaxed expression. For example, if the user is relaxed, the generation unit prioritizes generating avatars with a cheerful expression. For example, if the user is anxious, the generation unit prioritizes generating avatars with a calm expression. This allows the generation order of avatars to be determined according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit is performed using the generation AI. For example, the generation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0094] The generation unit can prioritize generating highly relevant avatars by taking into account the geographic location information of the other person receiving the presentation. For example, if the other person receiving the presentation is in a specific region, the generation unit prioritizes generating avatars related to that region. For example, if the other person receiving the presentation is in a different region, the generation unit filters avatars related to that region. For example, the generation unit selects the optimal avatar based on the geographic location information of the other person receiving the presentation. This makes it possible to generate highly relevant avatars based on the geographic location information of the other person receiving the presentation. The geographic location information is acquired using, for example, a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographic location information of the other person receiving the presentation. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the geographic location information of the other person receiving the presentation to the generation AI and have the generation AI select an avatar.

[0095] The generation unit can analyze the social media activity of the person receiving the presentation and generate a relevant avatar. For example, the generation unit prioritizes generating avatars related to topics in which the person receiving the presentation has shown interest on social media. For example, the generation unit analyzes the content of the person receiving the presentation's social media posts and filters out relevant avatars. For example, the generation unit generates relevant avatars by referring to the activity of the person receiving the presentation's friends on social media. This makes it possible to generate relevant avatars based on the person receiving the presentation's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant avatars. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the social media activity of the person receiving the presentation into the generation AI and have the generation AI select an avatar.

[0096] The generation unit can customize the avatar generation method by reflecting the past feedback of the other presenter. For example, the generation unit prioritizes an avatar expression method for which the other presenter has given favorable feedback in the past. For example, the generation unit avoids an avatar expression method for which the other presenter has given negative feedback in the past. For example, the generation unit customizes an optimal avatar generation method based on the past feedback of the other presenter. This allows the avatar generation method to be customized based on the past feedback of the other presenter. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and propose an optimal avatar generation method. Some or all of the above-mentioned processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the past feedback of the other presenter into the generation AI and cause the generation AI to customize the avatar generation method.

[0097] The check unit can estimate the user's emotions and adjust the method of checking the materials based on the estimated user emotions. For example, if the user is nervous, the check unit provides a simple checklist. For example, if the user is relaxed, the check unit provides a detailed checklist. For example, if the user is impatient, the check unit provides a quick check method. This allows the method of checking the materials to be adjusted according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the check unit is performed using the generation AI. For example, the check unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0098] The checking unit can analyze past evaluation data of the presentation materials and select the optimal checking method. For example, the checking unit prioritizes checking methods that have received high evaluations for presentation materials in the past. For example, the checking unit avoids checking methods that have received low evaluations for presentation materials in the past. For example, the checking unit customizes the optimal checking method based on the past evaluation data of the presentation materials. This allows the optimal checking method to be selected based on the past evaluation data of the presentation materials. Analysis of the past evaluation data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and propose the optimal checking method. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input past evaluation data of the presentation materials into the generation AI and have the generation AI select the checking method.

[0099] The checking unit can adjust the check items of the materials depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the checking unit prioritizes technical check items. For example, if the purpose of the presentation is a simple report, the checking unit prioritizes summary check items. For example, if the purpose of the presentation is education, the checking unit prioritizes educational check items. This allows the check items of the materials to be adjusted depending on the purpose of the presentation. The adjustment of the check items is performed using, for example, a generation AI. The generation AI can suggest check items depending on the purpose of the presentation. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the check items.

[0100] The checking unit can customize the expression of the material based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the checking unit prioritizes specialized expression. For example, if the other person receiving the presentation is a beginner, the checking unit prioritizes basic expression. For example, the checking unit adjusts the expression of the material according to the knowledge level of the other person receiving the presentation. This allows the expression of the material to be customized according to the knowledge level of the other person receiving the presentation. Customization of the expression of the material is performed using, for example, a generation AI. The generation AI can suggest an expression of the material based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the knowledge level of the other person receiving the presentation into the generation AI and cause the generation AI to customize the expression of the material.

[0101] The checking unit can estimate the user's emotions and determine the order in which to check the materials based on the estimated user emotions. For example, if the user is nervous, the checking unit prioritizes checking important items. For example, if the user is relaxed, the checking unit prioritizes checking detailed items. For example, if the user is impatient, the checking unit prioritizes items that can be checked quickly. This makes it possible to determine the order in which to check the materials according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0102] The checking unit can prioritize checking highly relevant materials by taking into account the geographic location information of the recipient. For example, if the recipient is in a specific region, the checking unit prioritizes checking materials related to that region. For example, if the recipient is in a different region, the checking unit filters materials related to that region. For example, the checking unit selects the most appropriate materials based on the geographic location information of the recipient. This makes it possible to check highly relevant materials based on the geographic location information of the recipient. The geographic location information is obtained, for example, using a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographic location information of the recipient. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the geographic location information of the recipient to the generation AI and have the generation AI select materials.

[0103] The checking unit can analyze the social media activity of the recipient and check relevant materials. For example, the checking unit prioritizes checking materials related to topics that the recipient has shown interest in on social media. For example, the checking unit analyzes the content of the recipient's social media posts and filters out relevant materials. For example, the checking unit checks relevant materials by referring to the activity of the recipient's friends on social media. This makes it possible to check relevant materials based on the recipient's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant materials. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the recipient's social media activity into the generation AI and have the generation AI select materials.

[0104] The checking unit can customize the method for checking materials by reflecting past feedback from the other party to the presentation. For example, the checking unit prioritizes checking methods for which the other party to the presentation has given favorable feedback in the past. For example, the checking unit avoids checking methods for which the other party to the presentation has given negative feedback in the past. For example, the checking unit customizes the optimal checking method based on the other party to the presentation's past feedback. This allows the method for checking materials to be customized based on the other party to the presentation's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal checking method. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input past feedback from the other party to the generation AI and have the generation AI customize the checking method.

[0105] The feedback unit can estimate the user's emotion and adjust the way the feedback is expressed based on the estimated user's emotion. For example, if the user is nervous, the feedback unit provides feedback in a relaxed manner. For example, if the user is relaxed, the feedback unit provides detailed feedback. For example, if the user is impatient, the feedback unit provides quick feedback. This makes it possible to adjust the way the feedback is expressed according to the user's emotion. The estimation of the user's emotion is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0106] The feedback unit can analyze past data of presentation practice results and select the optimal feedback method. For example, the feedback unit prioritizes feedback methods that have received high marks in the past for presentation practice results. For example, the feedback unit avoids feedback methods that have received low marks in the past for presentation practice results. For example, the feedback unit customizes the optimal feedback method based on the past data of presentation practice results. This allows the optimal feedback method to be selected based on the past data of presentation practice results. Analysis of the past data is performed using, for example, a generation AI. The generation AI can analyze past practice results and feedback comments and suggest the optimal feedback method. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input past data of presentation practice results into the generation AI and have the generation AI select the feedback method.

[0107] The feedback unit can adjust the level of detail of the feedback depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the feedback unit provides detailed feedback. For example, if the purpose of the presentation is a simple report, the feedback unit provides summary feedback. For example, if the purpose of the presentation is education, the feedback unit provides educational feedback. This makes it possible to adjust the level of detail of the feedback depending on the purpose of the presentation. The adjustment of the level of detail of the feedback is performed, for example, using a generation AI. The generation AI can suggest the level of detail of the feedback depending on the purpose of the presentation. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the purpose of the presentation to the generation AI and cause the generation AI to adjust the level of detail of the feedback.

[0108] The feedback unit can customize the content of the feedback based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the feedback unit provides specialized feedback. For example, if the other person receiving the presentation is a beginner, the feedback unit provides basic feedback. For example, the feedback unit adjusts the content of the feedback according to the knowledge level of the other person receiving the presentation. This makes it possible to customize the content of the feedback according to the knowledge level of the other person receiving the presentation. Customization of the content of the feedback is performed, for example, using a generation AI. The generation AI can suggest the content of the feedback based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the knowledge level of the other person receiving the presentation into the generation AI and cause the generation AI to customize the content of the feedback.

[0109] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated user's emotions. For example, if the user is nervous, the feedback unit prioritizes providing important feedback. For example, if the user is relaxed, the feedback unit prioritizes providing detailed feedback. For example, if the user is impatient, the feedback unit prioritizes feedback that can be provided quickly. This makes it possible to determine the priority of feedback according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0110] The feedback unit can prioritize providing highly relevant feedback by taking into account the geographic location information of the other person receiving the presentation. For example, if the other person receiving the presentation is in a specific region, the feedback unit prioritizes providing feedback related to that region. For example, if the other person receiving the presentation is in a different region, the feedback unit filters feedback related to that region. For example, the feedback unit selects optimal feedback based on the geographic location information of the other person receiving the presentation. This makes it possible to provide highly relevant feedback based on the geographic location information of the other person receiving the presentation. The geographic location information is obtained using, for example, a generation AI. The generation AI can analyze GPS data or an IP address to identify the geographic location information of the other person receiving the presentation. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the geographic location information of the other person receiving the presentation to the generation AI and cause the generation AI to select feedback.

[0111] The feedback unit can analyze the social media activity of the recipient and provide relevant feedback. For example, the feedback unit can prioritize providing feedback related to topics in which the recipient has shown interest on social media. For example, the feedback unit can analyze the content of the recipient's social media posts and filter relevant feedback. For example, the feedback unit can provide relevant feedback by referring to the activity of the recipient's friends on social media. This makes it possible to provide relevant feedback based on the recipient's social media activity. The analysis of social media activity can be performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant feedback. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the recipient's social media activity into the generation AI and have the generation AI select feedback.

[0112] The feedback unit can customize the feedback method by reflecting the other person's past feedback. For example, the feedback unit prioritizes methods for which the other person has given positive feedback in the past. For example, the feedback unit avoids methods for which the other person has given negative feedback in the past. The feedback unit customizes the optimal feedback method based on the other person's past feedback, for example. This allows the feedback method to be customized based on the other person's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal feedback method. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the other person's past feedback into the generation AI and have the generation AI customize the feedback method.

[0113] The follow-up unit can estimate the user's emotions and adjust the follow-up method based on the estimated user's emotions. For example, if the user is nervous, the follow-up unit provides advice to relax. For example, if the user is relaxed, the follow-up unit provides detailed follow-up. For example, if the user is impatient, the follow-up unit provides quick follow-up. This makes it possible to adjust the follow-up method according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0114] The follow-up unit can analyze past reaction data during the presentation and select the optimal follow-up method. For example, the follow-up unit prioritizes follow-up methods that have shown favorable reactions based on past reaction data during the presentation. For example, the follow-up unit avoids follow-up methods that have shown negative reactions based on past reaction data during the presentation. For example, the follow-up unit customizes the optimal follow-up method based on past reaction data during the presentation. This allows the optimal follow-up method to be selected based on past reaction data during the presentation. Analysis of past reaction data is performed using, for example, a generation AI. The generation AI can analyze past survey results and feedback comments and suggest the optimal follow-up method. Some or all of the above-mentioned processing in the follow-up unit can be performed using the generation AI. For example, the follow-up unit can input past reaction data during the presentation into the generation AI and have the generation AI select a follow-up method.

[0115] The follow-up unit can adjust the level of detail in the follow-up depending on the purpose of the presentation. For example, if the purpose of the presentation is to propose a new product, the follow-up unit provides detailed follow-up. For example, if the purpose of the presentation is a simple report, the follow-up unit provides summary follow-up. For example, if the purpose of the presentation is education, the follow-up unit provides educational follow-up. This makes it possible to adjust the level of detail in the follow-up depending on the purpose of the presentation. The adjustment of the level of detail in the follow-up is performed, for example, using a generation AI. The generation AI can suggest the level of detail in the follow-up depending on the purpose of the presentation. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the level of detail in the follow-up.

[0116] The follow-up unit can customize the content of the follow-up based on the knowledge level of the other person receiving the presentation. For example, if the other person receiving the presentation is an expert, the follow-up unit provides professional follow-up. For example, if the other person receiving the presentation is a beginner, the follow-up unit provides basic follow-up. For example, the follow-up unit adjusts the content of the follow-up according to the knowledge level of the other person receiving the presentation. This makes it possible to customize the content of the follow-up according to the knowledge level of the other person receiving the presentation. Customization of the content of the follow-up is performed using, for example, a generation AI. The generation AI can suggest content of the follow-up based on the knowledge level of the other person receiving the presentation. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the knowledge level of the other person receiving the presentation into the generation AI and have the generation AI customize the content of the follow-up.

[0117] The follow-up unit can estimate the user's emotions and determine the priority of follow-ups based on the estimated user's emotions. For example, if the user is nervous, the follow-up unit prioritizes providing important follow-ups. For example, if the user is relaxed, the follow-up unit prioritizes providing detailed follow-ups. For example, if the user is impatient, the follow-up unit prioritizes follow-ups that can be provided quickly. This makes it possible to determine the priority of follow-ups according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0118] The follow-up unit can prioritize providing highly relevant follows by taking into account the geographical location information of the other person receiving the presentation. For example, if the other person receiving the presentation is in a specific region, the follow-up unit prioritizes providing follows related to that region. For example, if the other person receiving the presentation is in a different region, the follow-up unit filters follows related to that region. For example, the follow-up unit selects the optimal follow-up based on the geographical location information of the other person receiving the presentation. This makes it possible to provide highly relevant follows based on the geographical location information of the other person receiving the presentation. The geographical location information is acquired using, for example, a generation AI. The generation AI can analyze GPS data or IP addresses to identify the geographical location information of the other person receiving the presentation. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the geographical location information of the other person receiving the presentation to the generation AI and have the generation AI select the follow-up.

[0119] The following unit can analyze the social media activity of the recipient and provide relevant follows. For example, the following unit prioritizes providing follows related to topics in which the recipient has shown interest on social media. For example, the following unit analyzes the content of the recipient's social media posts and filters out relevant follows. For example, the following unit provides relevant follows by referring to the activity of the recipient's friends on social media. This makes it possible to provide relevant follows based on the recipient's social media activity. The analysis of social media activity is performed using, for example, a generation AI. The generation AI can analyze the content of social media posts and the number of followers to identify relevant follows. Some or all of the above-mentioned processing in the following unit is performed using the generation AI. For example, the following unit can input the recipient's social media activity into the generation AI and have the generation AI select follows.

[0120] The follow-up unit can customize the follow-up method by reflecting the past feedback of the other person receiving the presentation. For example, the follow-up unit prioritizes follow-up methods for which the other person receiving the presentation has given favorable feedback in the past. For example, the follow-up unit avoids follow-up methods for which the other person receiving the presentation has given negative feedback in the past. For example, the follow-up unit customizes the optimal follow-up method based on the other person receiving the presentation's past feedback. This allows the follow-up method to be customized based on the other person receiving the presentation's past feedback. Analysis of past feedback is performed using, for example, a generation AI. The generation AI can analyze past survey results and comments and suggest the optimal follow-up method. Some or all of the above-mentioned processing in the follow-up unit can be performed using the generation AI. For example, the follow-up unit can input the other person receiving the presentation's past feedback into the generation AI and have the generation AI customize the follow-up method. === Hard Collateral 1-1 === Each of the multiple elements including the above-described reception unit, generation unit, check unit, feedback unit, and follow-up unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by at least one of the smart device 14 and the data processing device 12. For example, the reception unit can receive the presentation status via the control unit 46A of the smart device 14. For example, the generation unit generates an avatar using a generation AI via the specific processing unit 290 of the data processing device 12. For example, the check unit automatically generates base materials based on the avatar generated by the specific processing unit 290 of the data processing device 12 and checks the appropriateness of the design and expression. For example, the feedback unit provides feedback on the results of the presentation practice via the control unit 46A of the smart device 14. For example, the follow-up unit provides follow-up during the presentation via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-described reception unit, generation unit, check unit, feedback unit, and follow-up unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can receive the presentation status via the control unit 46A of the smart glasses 214. For example, the generation unit generates an avatar using a generation AI via the specific processing unit 290 of the data processing device 12. For example, the check unit automatically generates base materials based on the avatar generated by the specific processing unit 290 of the data processing device 12 and checks the appropriateness of the design and expression. For example, the feedback unit provides feedback on the results of the presentation practice via the control unit 46A of the smart glasses 214. For example, the follow-up unit provides follow-up during the presentation via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-described reception unit, generation unit, check unit, feedback unit, and follow-up unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit can receive the presentation status via the control unit 46A of the headset-type terminal 314. For example, the generation unit generates an avatar using a generation AI via the specific processing unit 290 of the data processing device 12. For example, the check unit automatically generates base materials based on the avatar generated by the specific processing unit 290 of the data processing device 12 and checks the appropriateness of the design and expression. For example, the feedback unit provides feedback on the results of the presentation practice via the control unit 46A of the headset-type terminal 314. For example, the follow-up unit provides follow-up during the presentation via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-described reception unit, generation unit, check unit, feedback unit, and follow-up unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can receive the presentation status via the control unit 46A of the robot 414. For example, the generation unit generates an avatar using a generation AI via the specific processing unit 290 of the data processing device 12. For example, the check unit automatically generates base materials based on the avatar generated by the specific processing unit 290 of the data processing device 12 and checks the appropriateness of the design and expression. For example, the feedback unit provides feedback on the results of the presentation practice via the control unit 46A of the robot 414. For example, the follow-up unit provides follow-up during the presentation via the specific processing unit 290 of the data processing device 12.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] The reception unit can adjust the format and content of the information it accepts, taking into account the cultural background of the recipient. For example, if the recipient belongs to a different culture, it uses expressions and examples appropriate to that culture. For example, if the recipient belongs to an Asian culture, the reception unit prioritizes accepting examples and expressions common in Asian cultures. For example, if the recipient belongs to a Western culture, the reception unit prioritizes accepting examples and expressions common in Western cultures. This makes it possible to accept information according to the recipient's cultural background. Consideration of cultural background is performed, for example, using a generation AI. The generation AI can suggest an appropriate format and content of information based on the recipient's cultural background. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the recipient's cultural background into the generation AI and have the generation AI adjust the format and content of the information.

[0123] The generation unit can customize the avatar's clothing and accessories based on the occupation and position of the person giving the presentation. For example, if the person giving the presentation is a medical professional, the generation unit generates an avatar wearing a medical lab coat and holding a stethoscope. For example, if the person giving the presentation is a businessman, the generation unit generates an avatar wearing a suit and tie. For example, if the person giving the presentation is an engineer, the generation unit generates an avatar wearing work clothes and holding tools. This makes it possible to customize the avatar according to the occupation and position of the person giving the presentation. The customization of the avatar's clothing and accessories is performed using, for example, a generation AI. The generation AI can suggest appropriate clothing and accessories based on the occupation and position of the person giving the presentation. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the occupation and position of the person giving the presentation into the generation AI and cause the generation AI to customize the avatar's clothing and accessories.

[0124] The checking unit can adjust the design of the presentation materials using color psychology to enhance the visual elements of the materials. For example, if the purpose of the presentation is to persuade, the checking unit can make extensive use of blue, which conveys a sense of trust. For example, if the purpose of the presentation is to educate, the checking unit can make extensive use of green, which promotes concentration. For example, if the purpose of the presentation is to convey urgency, the checking unit can make extensive use of red, which attracts attention. This makes it possible to enhance the visual elements according to the purpose of the presentation. The application of color psychology is performed, for example, using a generation AI. The generation AI can suggest appropriate colors based on the purpose of the presentation. Some or all of the above-mentioned processing in the checking unit is performed using the generation AI. For example, the checking unit can input the purpose of the presentation into the generation AI and have the generation AI adjust the colors.

[0125] The feedback unit can estimate the user's emotions and adjust the timing of feedback based on the estimated user emotions. For example, if the user is nervous, the feedback unit provides feedback after allowing the user time to relax. For example, if the user is relaxed, the feedback unit provides detailed feedback immediately. For example, if the user is impatient, the feedback unit provides feedback quickly. This makes it possible to adjust the timing of feedback according to the user's emotions. The estimation of the user's emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the feedback unit is performed using the generation AI. For example, the feedback unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0126] The follow-up unit can monitor the user's emotions during a presentation in real time and provide follow-up at the appropriate time. For example, if the user is nervous, it immediately provides advice to relax. For example, if the user is relaxed, the follow-up unit provides detailed follow-up. For example, if the user is impatient, the follow-up unit provides quick follow-up. This enables real-time follow-up according to the user's emotions during a presentation. Monitoring of the user's emotions is realized using an emotion estimation function, for example, with an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the user's facial expression data into the generation AI and have the generation AI monitor the emotions.

[0127] The reception unit can analyze the past purchasing history of the person receiving the presentation and select the optimal information reception method. For example, the reception unit can prioritize information related to products that the person receiving the presentation has purchased in the past. For example, if the person receiving the presentation has a negative reaction to a product that they have purchased in the past, the reception unit can avoid information related to that product. The reception unit can customize the optimal information reception method based on the person receiving the presentation's past purchasing history. This makes it possible to select the optimal information reception method according to the person receiving the presentation's purchasing history. The analysis of the past purchasing history is performed using, for example, a generation AI. The generation AI can analyze past purchasing data and suggest the optimal information reception method. Some or all of the above-mentioned processing in the reception unit is performed using the generation AI. For example, the reception unit can input the past purchasing history into the generation AI and have the generation AI select the information reception method.

[0128] The generation unit can customize the avatar's background and props based on the hobbies and interests of the person receiving the presentation. For example, if the person receiving the presentation likes sports, the generation unit generates an avatar with a sports-related background and props. For example, if the person receiving the presentation likes music, the generation unit generates an avatar with an instrument or music-related props. For example, if the person receiving the presentation likes traveling, the generation unit generates an avatar with a travel-related background and props. This makes it possible to customize the avatar according to the person receiving the presentation's hobbies and interests. The customization of the avatar's background and props is performed using, for example, a generation AI. The generation AI can suggest appropriate backgrounds and props based on the person receiving the presentation's hobbies and interests. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input the person receiving the presentation's hobbies and interests into the generation AI and cause the generation AI to customize the avatar's background and props.

[0129] The checking unit can adjust the design of the presentation materials using visual storytelling techniques to enhance the visual elements of the materials. For example, if the purpose of the presentation is persuasive, the checking unit can use visual storytelling to emphasize the logical flow. For example, if the purpose of the presentation is educational, the checking unit can use visual storytelling to enhance the learning effect. For example, if the purpose of the presentation is to provide information, the checking unit can use visual storytelling to smooth the transmission of information. This makes it possible to enhance the visual elements according to the purpose of the presentation. The application of visual storytelling is performed, for example, using a generation AI. The generation AI can suggest appropriate visual storytelling techniques based on the purpose of the presentation. Some or all of the above-mentioned processing in the checking unit can be performed using the generation AI. For example, the checking unit can input the purpose of the presentation into the generation AI and cause the generation AI to adjust the visual storytelling.

[0130] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated user's emotions. For example, if the user is nervous, the feedback unit can prioritize providing positive feedback. For example, if the user is relaxed, the feedback unit can provide feedback including detailed suggestions for improvement. For example, if the user is impatient, the feedback unit can provide feedback that is easy to understand quickly. This allows the content of the feedback to be adjusted according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the feedback unit can be performed using the generation AI. For example, the feedback unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0131] The follow-up unit can monitor the user's emotions during a presentation in real time and provide follow-up at the appropriate time. For example, if the user is nervous, it immediately provides advice to relax. For example, if the user is relaxed, the follow-up unit provides detailed follow-up. For example, if the user is impatient, the follow-up unit provides quick follow-up. This enables real-time follow-up according to the user's emotions during a presentation. Monitoring of the user's emotions is realized using an emotion estimation function, for example, with an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the follow-up unit is performed using the generation AI. For example, the follow-up unit can input the user's facial expression data into the generation AI and have the generation AI monitor the emotions.

[0132] The processing flow of the second embodiment will be briefly explained below.

[0133] Step 1: The reception unit receives the presentation status. The presentation status includes, for example, the person being presented to, the purpose, the presentation time, the knowledge level of the person being presented to, the industry, etc. Specifically, if the person being presented to is an executive and the purpose is to propose a new product, the reception unit receives information such as the presentation time being 30 minutes and the knowledge level of the person being presented to being high. Step 2: The generation unit uses the generation AI to generate an avatar based on the information received by the reception unit. The generated avatars include, for example, an executive avatar for an executive-level presentation partner, a superior avatar for a superior-level presentation partner, etc. The generation AI generates the avatar using deep learning technology. Step 3: The Checking Department uses the Generation AI to automatically generate base materials based on the avatar generated by the Generation Department, and checks the appropriateness of the design and expression. The Generation AI automatically generates the design of presentation materials, and checks whether the expression is appropriate and there are no violations. Step 4: The feedback department uses the generation AI to practice the presentation based on the materials generated by the checking department and provides feedback on the results. The generation AI practices the presentation, points out any consistency between the materials and the statements, and identifies any unclear parts, generating anticipated FAQs. Step 5: The Follow-up section uses the Generative AI to provide follow-up during the presentation based on the feedback provided by the Feedback section. The Generative AI provides advice to ease tension during the presentation, checks time allocation, and interprets the intent of questions to support appropriate responses.

[0134] 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.

[0135] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] 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.

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

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. 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 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.

[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 (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).

[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] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0185] 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.

[0186] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Explanation of symbols]

[0206] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception section for receiving information on the presentation status; a generation unit that generates an avatar based on the information received by the reception unit; a check unit that automatically generates base materials based on the avatars generated by the generation unit and checks the appropriateness of the design and expression; a feedback unit that practices the presentation based on the materials generated by the checking unit and provides feedback on the results; a follow-up unit that follows up during the presentation based on the feedback provided by the feedback unit. A system characterized by:

2. The reception unit Accept information about the audience, purpose, presentation time, audience's knowledge level, and industry 2. The system of claim 1.

3. The generation unit Generative AI generates an avatar suited to the person you are presenting to.

2. The system of claim 1.

4. The checking unit Automatically generate base materials using generative AI and check the appropriateness of the design and expression 2. The system of claim 1.

5. The feedback unit Practice presentations using generative AI, point out consistency between materials and statements, and identify difficult-to-understand parts, and generate anticipated FAQs.

2. The system of claim 1.

6. The follow section is Generative AI provides advice to ease tension during presentations, checks time allocation, and interprets questions to support responses.

2. The system of claim 1.

7. The reception unit Estimate the user's emotions and adjust the timing of receiving information about the presentation situation based on the estimated user emotions.

2. The system of claim 1.

8. The reception unit Analyze past reaction data from presentation recipients and select the optimal method for receiving information 2. The system of claim 1.

9. The reception unit Adjust the level of detail you accept depending on the purpose of your presentation.

2. The system of claim 1.

10. The reception unit Filter the information you accept based on the knowledge level of the people you are presenting to.

2. The system of claim 1.

Images