system

Abstract

The system according to this embodiment aims to improve presentation skills and achieve effective communication. [Solution] The system according to the embodiment comprises a shooting unit, a identification unit, a generation unit, a provision unit, and a simulation unit. The shooting unit shoots a video of the presentation. The identification unit analyzes the video shot by the shooting unit and identifies areas for improvement. The generation unit generates a revised presentation video based on the areas for improvement identified by the identification unit. The provision unit provides the revised video generated by the generation unit as feedback. The simulation unit simulates the question and answer session.

Description

Technical Field

[0006] , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that feedback and simulation for improving presentation skills are not sufficiently performed due to time and frequency constraints.

[0005] The system according to the embodiment aims to achieve improvement in presentation skills and effective communication.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a shooting unit, a selection unit, a generation unit, a provision unit, and a simulation unit. The shooting unit shoots a video of the presentation. The selection unit analyzes the video shot by the shooting unit and identifies areas for improvement. The generation unit generates a revised presentation video based on the areas for improvement identified by the selection unit. The provision unit provides the revised video generated by the generation unit as feedback. The simulation unit simulates the question and answer session. [Effects of the Invention]

[0007] The system according to this embodiment can improve presentation skills and enable effective communication. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The presentation support system according to an embodiment of the present invention is a system that utilizes generative AI to provide an environment in which young employees can improve their presentation skills and receive feedback, overcoming the constraints of time and the number of attempts, in order to address the presentation challenges they face. This presentation support system records a video of the presentation, and the generative AI analyzes the video to identify areas for improvement. Next, the generative AI generates a revised presentation video and provides feedback. Furthermore, it uses prompts to conduct a realistic simulation of the Q&A session. This system allows young employees to improve their skills and receive feedback over the constraints of time and the number of attempts, supporting the improvement of their presentation skills and the realization of effective communication. For example, a video of a presentation is recorded. A young employee records their presentation using a smartphone or camera. This video is input into the generative AI. Next, the generative AI analyzes the input video and identifies areas for improvement. The generative AI analyzes the content of the presentation, the speaking style, the design of the slides, etc., and suggests specific areas for improvement. For example, it may point out that the speaking speed is too fast or the text on the slides is too small. The generative AI generates a revised presentation video based on the identified areas for improvement. For example, the speaking speed can be adjusted, or the slide design can be improved. This revised video is then provided to the junior employee as feedback. Furthermore, a Q&A simulation is conducted. The generating AI uses prompts to simulate a realistic Q&A session. For example, it generates questions about the presentation content, and the junior employee answers them. This simulation allows the junior employee to prepare for the actual presentation. This system allows junior employees to improve themselves and receive feedback beyond the constraints of time and frequency. For example, they can practice their presentations during their free time, such as evenings or weekends, and receive feedback from the generating AI. This supports the improvement of presentation skills and the realization of effective communication. In this way, the presentation support system enables junior employees to improve their presentation skills and achieve effective communication.

[0029] The presentation support system according to this embodiment comprises a shooting unit, an identification unit, a generation unit, a provision unit, and a simulation unit. The shooting unit shoots a video of the presentation. The video of the presentation includes, but is not limited to, business presentations and academic presentations. The shooting unit shoots the video of the presentation using, for example, a smartphone or camera. The shooting unit can also adjust the resolution and frame rate of the video. For example, the shooting unit can shoot a video in 4K resolution and set the frame rate to 60fps. The identification unit uses generation AI to analyze the video shot by the shooting unit and identify areas for improvement. For example, the identification unit analyzes the content of the presentation, the speaking style, and the design of the slides, and suggests specific areas for improvement. For example, the identification unit may point out that the speaking speed is too fast or the text on the slides is too small. The identification unit can also use generation AI to analyze the content of the presentation and extract important points. For example, the identification unit receives a prompt from the generation AI saying, "Please summarize the main points of this presentation," extracts the main points, and suggests areas for improvement. The generation unit generates a revised presentation video based on the improvements identified by the identification unit. For example, the generation unit may adjust the speaking speed or improve the slide design. The generation unit can also edit the presentation video using the generation AI. For example, the generation unit receives a prompt from the generation AI saying, "Please adjust the speaking speed," and generates a video with the speaking speed adjusted. The delivery unit provides the revised video generated by the generation unit as feedback. For example, the delivery unit provides the revised presentation video to junior employees as feedback. The delivery unit can also customize the content of the feedback using the generation AI. For example, the delivery unit receives a prompt from the generation AI saying, "Please provide feedback on areas for improvement in this presentation," and provides feedback. The simulation unit uses the generation AI to simulate a question-and-answer session. For example, the simulation unit uses prompts to simulate a realistic question-and-answer session.For example, the simulation unit receives a prompt from the generating AI saying, "Generate questions about this presentation," and generates questions. This allows the presentation support system according to this embodiment to enable young employees to improve their presentation skills and achieve effective communication.

[0030] The specific unit can analyze the content or delivery of a presentation, the design of the slides, and suggest areas for improvement. For example, the unit can analyze the content of a presentation and extract key points. For instance, the unit might receive a prompt from the generating AI saying, "Summarize the main points of this presentation," and then extract the points and suggest areas for improvement. The unit can also analyze the delivery and suggest areas for improvement, such as adjusting the speaking speed and tone. For example, if the speaking speed is too fast, the unit will suggest adjusting it to an appropriate speed. The unit can also analyze the design of the slides and suggest areas for improvement, such as font size and color usage. For example, if the font on the slides is too small, the unit will suggest increasing the font size. By providing specific areas for improvement, the quality of the presentation can be enhanced. Some or all of the above processing in the specific unit is performed using the generating AI. For example, the unit inputs a video of the presentation into the generating AI, which then analyzes the video and suggests areas for improvement.

[0031] The generation unit can adjust the speaking speed. For example, the generation unit adjusts the speaking speed in a presentation video. For instance, if the speaking speed is too fast, the generation unit adjusts it to an appropriate speed. It can also adjust the speaking speed to be faster if it is too slow. The generation unit uses a generation AI to receive prompts to adjust the speaking speed and adjusts it to an appropriate speed. For example, the generation unit receives a prompt from the generation AI saying "Please adjust the speaking speed" and generates a video with the speaking speed adjusted. This makes it possible to create presentations that are easier for the listener to understand by adjusting the speaking speed. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a presentation video into the generation AI, which adjusts the speaking speed and generates a revised video.

[0032] The generation unit can improve the design of slides. For example, the generation unit can improve the design of presentation slides. For example, the generation unit can adjust the font size and color scheme of the slides. The generation unit can also change the layout of the slides. The generation unit uses a generation AI to receive prompts for improving the slide design and improves it to an appropriate design. For example, the generation unit receives a prompt from the generation AI saying "Please improve the slide design" and generates a video with the improved slide design. This makes it possible to create a visually appealing presentation by improving the slide design. Some or all of the above processes in the generation unit are performed using the generation AI. For example, the generation unit inputs the presentation slides into the generation AI, and the generation AI improves the slide design and generates a revised video.

[0033] The simulation unit can perform realistic question-and-answer simulations using prompts. For example, the simulation unit can generate questions related to the content of a presentation. For instance, the simulation unit's generating AI receives the prompt "Generate questions about this presentation" and generates questions. The simulation unit can also simulate a junior employee answering the generated questions. For example, the simulation unit's generating AI receives the prompt "Answer this question" and simulates a junior employee answering. This allows for realistic question-and-answer simulations, preparing for actual presentations. Some or all of the above processes in the simulation unit are performed using the generating AI. For example, the simulation unit inputs the content of the presentation into the generating AI, which then generates questions and performs the simulation.

[0034] The service provider can provide employees with the revised presentation video as feedback. For example, the service provider can provide the revised presentation video as feedback to junior employees. The service provider can also customize the content of the feedback using generative AI. For example, the service provider can have the generative AI receive a prompt such as "Please provide feedback on how to improve this presentation" and then provide the feedback. This promotes self-improvement by providing the revised presentation video as feedback. Some or all of the above processes in the service provider are performed using generative AI. For example, the service provider inputs the revised presentation video into the generative AI, and the generative AI generates and provides the feedback.

[0035] The camera unit can automatically adjust the optimal shooting angle and lighting during shooting by referring to the user's past presentation history. For example, the camera unit can automatically set the shooting angle that the user previously preferred. For example, the camera unit analyzes the user's past presentation videos to identify the optimal shooting angle. The camera unit can also reproduce the lighting settings that the user has used in the past. For example, the camera unit analyzes the user's past presentation videos to identify the optimal lighting settings. The camera unit can also suggest the most effective shooting settings based on the user's past presentation history. For example, the camera unit analyzes the user's past presentation videos to suggest the optimal shooting settings. This allows the camera unit to automatically select the optimal shooting settings by referring to past presentation history. Some or all of the above processes in the camera unit are performed using a generative AI. For example, the camera unit inputs the user's past presentation videos into the generative AI, which identifies and automatically adjusts the optimal shooting settings.

[0036] The recording unit can analyze the user's current ambient sound during recording and automatically remove noise. For example, the recording unit can analyze ambient noise in real time and perform noise cancellation. For example, the recording unit analyzes ambient sound and removes noise using noise cancellation technology. The recording unit can also emphasize the user's voice and suppress background noise. For example, the recording unit analyzes ambient sound and performs filtering to emphasize the user's voice. The recording unit can also analyze ambient sound and automatically adjust the optimal microphone settings. For example, the recording unit analyzes ambient sound, identifies the optimal microphone settings, and automatically adjusts them. This allows for recording presentations with clear audio by analyzing ambient sound and removing noise. Some or all of the above processing in the recording unit is performed using generative AI. For example, the recording unit inputs ambient sound data into the generative AI, which removes noise and sets the optimal audio settings.

[0037] The shooting unit can select the optimal shooting settings based on the user's geographical location information during shooting. For example, when shooting outdoors, the shooting unit can select settings that make the most of natural light. For example, the shooting unit analyzes the user's geographical location information and identifies shooting settings that make the most of natural light. The shooting unit can also optimize artificial lighting when shooting indoors. For example, the shooting unit analyzes the user's geographical location information and identifies settings to optimize artificial lighting. The shooting unit can also automatically adjust sound settings according to a specific location. For example, the shooting unit analyzes the user's geographical location information, identifies the optimal sound settings, and automatically adjusts them. In this way, the optimal shooting settings can be selected by considering geographical location information. Some or all of the above processing in the shooting unit is performed using a generative AI. For example, the shooting unit inputs the user's geographical location information into the generative AI, which identifies the optimal shooting settings and automatically adjusts them.

[0038] The photography team can analyze the user's social media activity during filming and suggest relevant presentation content. For example, the photography team can suggest presentation themes based on the user's past posts. For example, the photography team analyzes the user's social media activity and identifies presentation themes based on past posts. The photography team can also analyze the interests of the user's followers and suggest relevant content. For example, the photography team analyzes the user's social media activity and identifies presentation content based on the interests of their followers. The photography team can also suggest content that reflects trends based on the user's social media activity. For example, the photography team analyzes the user's social media activity and identifies presentation content that reflects trends. In this way, by analyzing social media activity, relevant presentation content can be suggested. Some or all of the above processing in the photography team is performed using generative AI. For example, the photography team inputs the user's social media activity data into the generative AI, which then identifies and suggests relevant presentation content.

[0039] The specific unit can analyze the content of a presentation and identify areas for improvement by comparing it to past successful examples. For example, the specific unit can analyze the speaking speed and tone by comparing it to past successful presentations. For example, the specific unit can analyze videos of past successful examples to identify the speaking speed and tone. The specific unit can also identify areas for improvement by comparing it to the slide design of successful examples. For example, the specific unit can analyze the slide design of past successful examples to identify areas for improvement. The specific unit can also identify areas for improvement in content by comparing it to the structure of successful examples. For example, the specific unit can analyze the structure of past successful examples to identify areas for improvement in content. In this way, specific areas for improvement can be identified by comparing it to past successful examples. Some or all of the above processing in the specific unit is performed using a generative AI. For example, the specific unit inputs data from past successful examples into the generative AI, which then compares and identifies areas for improvement.

[0040] The specific unit can analyze a presentation's delivery and suggest improvements based on the tone or intonation of the voice. For example, the unit can analyze the user's speaking speed and suggest an appropriate speed. For instance, it can analyze the user's voice data and, if the speaking speed is too fast, advise adjusting to an appropriate speed. The unit can also analyze the user's voice tone and suggest a more effective tone. For example, it can analyze the user's voice data and, if the voice tone is monotonous, advise adding intonation. The unit can also analyze the user's intonation and suggest an intonation that is easier for the listener to understand. For example, it can analyze the user's voice data and, if the intonation is insufficient, advise adding appropriate intonation. This allows the unit to suggest improvements to delivery that are more effective by considering the tone and intonation of the voice. Some or all of the above processing in the specific unit is performed using a generative AI. For example, the unit inputs the user's voice data into the generative AI, which analyzes the tone and intonation of the voice and suggests improvements.

[0041] The specific unit can analyze the content of a presentation and suggest improvements based on the user's industry-specific terminology or trends. For example, the specific unit can analyze whether industry-specific terminology is being used appropriately and suggest improvements. For instance, the specific unit analyzes the user's presentation content and, if industry-specific terminology is not being used appropriately, it will point out the need to use appropriate terminology. The specific unit can also suggest content that reflects the latest industry trends. For example, the specific unit analyzes the user's presentation content and, if the latest industry trends are not reflected, it will point out the need to reflect the trends. The specific unit can also compare the presentation to industry best practices and suggest improvements. For example, the specific unit analyzes the user's presentation content and identifies areas for improvement by comparing it to industry best practices. This allows for the suggestion of more appropriate improvements by considering industry-specific terminology and trends. Some or all of the above processing in the specific unit is performed using a generative AI. For example, the specific unit inputs the user's presentation content into the generative AI, which analyzes industry-specific terminology and trends and suggests improvements.

[0042] The specific unit can analyze presentation slide designs and suggest improvements that reflect the latest design trends. For example, the unit can propose slide designs that reflect the latest design trends. For example, the unit can analyze the user's slide design and suggest designs that reflect the latest design trends. The unit can also suggest slide color schemes and fonts that match the latest trends. For example, the unit can analyze the user's slide design and, if the color scheme or fonts are outdated, suggest changes that match the latest trends. The unit can also improve slide layouts based on the latest design trends. For example, the unit can analyze the user's slide design and, if the layout is outdated, improve it based on the latest trends. This makes it possible to create visually appealing slide designs that reflect the latest design trends. Some or all of the above processing in the specific unit is performed using a generation AI. For example, the unit inputs the user's slide design into the generation AI, which analyzes the latest design trends and suggests improvements.

[0043] The generation unit can customize the generated edited video to reflect the user's past presentation style. For example, the generation unit can reflect the speaking style and tone the user has used in the past. For example, the generation unit analyzes the user's past presentation videos to identify and reflect the speaking style and tone. The generation unit can also reproduce slide designs preferred by the user. For example, the generation unit analyzes the user's past presentation videos to identify and reproduce slide designs. Furthermore, the generation unit can make optimal corrections based on the user's past presentation style. For example, the generation unit analyzes the user's past presentation videos to identify and make optimal corrections. In this way, by reflecting past presentation styles, the generation unit can provide the user with the most suitable edited video. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's past presentation videos into the generation AI, which analyzes the style and generates the edited video.

[0044] The generation unit can generate corrected videos based on the user's industry-specific presentation style. For example, the generation unit can generate videos that reflect industry-specific terminology and trends. For instance, it can analyze the user's industry-specific presentation content and generate videos that reflect terminology and trends. The generation unit can also generate videos that incorporate industry best practices. For example, it can analyze the user's industry-specific presentation content and generate videos that incorporate best practices. The generation unit can also reflect a presentation style tailored to the characteristics of the industry. For example, it can analyze the user's industry-specific presentation content and reflect a style tailored to the characteristics. This allows for the provision of more appropriate corrected videos by considering industry-specific presentation styles. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's industry-specific presentation content into the generation AI, which analyzes the style and generates the corrected video.

[0045] The generation unit can select the optimal style when generating a corrected video, taking into account the user's geographical location information. For example, the generation unit can select a style that reflects the culture and customs of the user's region. For example, the generation unit analyzes the user's geographical location information and identifies a style that reflects the culture and customs of that region. The generation unit can also select appropriate backgrounds and effects based on the user's geographical location. For example, the generation unit analyzes the user's geographical location information and identifies the optimal backgrounds and effects. The generation unit can also select a style that reflects region-specific trends. For example, the generation unit analyzes the user's geographical location information and identifies a style that reflects region-specific trends. In this way, by considering geographical location information, it is possible to provide a corrected video with the optimal style. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's geographical location information into the generation AI, and the generation AI identifies the optimal style and generates the corrected video.

[0046] The generation unit can analyze the user's social media activity and reflect relevant content when generating edited videos. For example, the generation unit can select a theme for the edited video based on content the user has previously posted. For example, the generation unit analyzes the user's social media activity and identifies a theme for the edited video based on past posts. The generation unit can also analyze the interests of the user's followers and reflect relevant content. For example, the generation unit analyzes the user's social media activity and identifies the content of the edited video based on the interests of the followers. The generation unit can also select content that reflects trends from the user's social media activity. For example, the generation unit analyzes the user's social media activity and identifies the content of the edited video that reflects trends. In this way, by analyzing social media activity, it is possible to provide edited videos that reflect relevant content. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's social media activity data into the generation AI, which identifies relevant content and generates the edited video.

[0047] The service provider can select the optimal method of providing feedback by referring to the user's past feedback history. For example, the service provider can reproduce feedback formats that the user has preferred in the past. For example, the service provider can analyze the user's past feedback history, identify preferred feedback formats, and reproduce them. The service provider can also select the most effective method of providing feedback from the user's past feedback history. For example, the service provider can analyze the user's past feedback history and identify the optimal method of providing feedback. The service provider can also provide feedback at the optimal timing based on the user's past feedback history. For example, the service provider can analyze the user's past feedback history, identify the optimal timing, and provide feedback. In this way, the service provider can select the optimal method of providing feedback by referring to past feedback history. Some or all of the above processes in the service provider are performed using a generative AI. For example, the service provider inputs the user's past feedback history into the generative AI, which identifies the optimal method of providing feedback and provides it.

[0048] The service provider can customize the feedback provided based on the user's current learning status. For example, the service provider can provide appropriate feedback according to the user's current learning progress. For example, the service provider can analyze the user's learning progress and provide feedback accordingly. The service provider can also analyze the user's learning situation and provide optimal feedback. For example, the service provider can analyze the user's learning situation, identify and provide the optimal feedback. The service provider can also provide customized feedback tailored to the user's learning goals. For example, the service provider can analyze the user's learning goals and provide feedback tailored to those goals. This allows for the provision of more appropriate feedback by considering the current learning situation. Some or all of the above processing in the service provider is performed using a generative AI. For example, the service provider inputs the user's learning status data into the generative AI, which then identifies and provides the optimal feedback.

[0049] The service provider can select the optimal method of providing feedback based on the user's geographical location. For example, the service provider can provide feedback that reflects the culture and customs of the user's region. For example, the service provider can analyze the user's geographical location and identify feedback that reflects the culture and customs of that region. The service provider can also select an appropriate feedback format based on the user's geographical location. For example, the service provider can analyze the user's geographical location and identify the optimal feedback format. The service provider can also provide feedback that reflects region-specific trends. For example, the service provider can analyze the user's geographical location and identify feedback that reflects region-specific trends. This allows the service provider to provide optimal feedback by considering geographical location. Some or all of the above processing in the service provider is performed using a generative AI. For example, the service provider inputs the user's geographical location into the generative AI, which then identifies and provides the optimal feedback format.

[0050] The service provider can analyze the user's social media activity and reflect relevant content when providing feedback. For example, the service provider can select feedback themes based on the user's past posts. For example, the service provider analyzes the user's social media activity and identifies feedback themes based on past posts. The service provider can also analyze the interests of the user's followers and reflect relevant content. For example, the service provider analyzes the user's social media activity and identifies feedback content based on the interests of followers. The service provider can also select content that reflects trends from the user's social media activity. For example, the service provider analyzes the user's social media activity and identifies feedback content that reflects trends. In this way, by analyzing social media activity, it is possible to provide feedback that reflects relevant content. Some or all of the above processing in the service provider is performed using a generative AI. For example, the service provider inputs the user's social media activity data into the generative AI, which identifies relevant content and provides feedback.

[0051] The simulation unit can provide realistic simulations by referring to past question-and-answer data when performing question-and-answer simulations. For example, the simulation unit can generate realistic questions based on past question-and-answer data. For example, the simulation unit can analyze past question-and-answer data, identify and generate realistic questions. The simulation unit can also select the most effective questions from past question-and-answer data. For example, the simulation unit can analyze past question-and-answer data, identify and select the most effective questions. The simulation unit can also provide realistic simulations by analyzing past question-and-answer data. For example, the simulation unit can analyze past question-and-answer data and generate questions to provide realistic simulations. In this way, realistic simulations can be provided by referring to past question-and-answer data. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs past question-and-answer data into the generation AI, and the generation AI analyzes the data to generate realistic questions.

[0052] The simulation unit can perform Q&A simulations that reflect the user's industry-specific questions. For example, the simulation unit can generate questions using industry-specific terminology. For instance, it can analyze the user's industry-specific presentation content and generate questions that reflect that terminology. The simulation unit can also generate questions that reflect industry trends. For example, it can analyze the user's industry-specific presentation content and generate questions that reflect those trends. Furthermore, the simulation unit can generate questions based on industry best practices. For example, it can analyze the user's industry-specific presentation content and generate questions based on best practices. By reflecting industry-specific questions, it can provide more appropriate Q&A simulations. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs the user's industry-specific presentation content into the generation AI, which then generates questions and performs the simulation.

[0053] The simulation unit can select the most appropriate questions based on the user's geographical location when simulating question-and-answer sessions. For example, the simulation unit can ask questions that reflect the culture and customs of the user's region. For instance, the simulation unit analyzes the user's geographical location and generates questions that reflect the culture and customs of that region. The simulation unit can also select appropriate questions based on the user's geographical location. For example, the simulation unit analyzes the user's geographical location and identifies and selects the most appropriate questions. The simulation unit can also ask questions that reflect region-specific trends. For example, the simulation unit analyzes the user's geographical location and generates questions that reflect region-specific trends. This allows the system to provide optimal questions by considering geographical location. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs the user's geographical location into the generation AI, which then identifies and generates the most appropriate questions.

[0054] The simulation unit can analyze a user's social media activity and reflect relevant questions when conducting a Q&A simulation. For example, the simulation unit can generate questions based on content the user has previously posted. For example, the simulation unit analyzes the user's social media activity and identifies and generates questions based on past posts. The simulation unit can also analyze the interests of the user's followers and reflect relevant questions. For example, the simulation unit analyzes the user's social media activity and identifies and generates questions based on the interests of their followers. The simulation unit can also generate questions that reflect trends from the user's social media activity. For example, the simulation unit analyzes the user's social media activity and identifies and generates questions that reflect trends. In this way, relevant questions can be provided by analyzing social media activity. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs the user's social media activity data into the generation AI, which then identifies and generates relevant questions.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The presentation support system may also include a voice analysis unit. This unit can analyze the tone and intonation of the user's voice and provide advice to enhance the effectiveness of the presentation. For example, if the voice analysis unit is monotonous, it may suggest adding more intonation. It can also suggest a more effective tone if the user's voice tone is inappropriate. Furthermore, if the voice analysis unit is inappropriate, it may suggest adjusting the volume. This allows the user to deliver a more effective presentation.

[0057] The generation unit can customize the generated edited video to reflect the user's past presentation style. For example, it can reflect the speaking style and tone the user has used in the past. It can also reproduce slide designs that the user preferred. Furthermore, it can make optimal corrections based on the user's past presentation style. In this way, by reflecting past presentation styles, it can provide the user with an edited video that is best suited to their needs.

[0058] The simulation unit can perform Q&A simulations that reflect the user's industry-specific questions. For example, it can generate questions using industry-specific terminology. It can also generate questions that reflect industry trends. Furthermore, it can generate questions based on industry best practices. By reflecting industry-specific questions, it can provide more appropriate Q&A simulations.

[0059] The feedback delivery system can select the optimal method of delivery by referring to the user's past feedback history. For example, it can reproduce a feedback format that the user previously preferred. It can also select the most effective method of delivery from the user's past feedback history. Furthermore, it can deliver feedback at the optimal timing based on the user's past feedback history. In this way, the optimal method of delivery can be selected by referring to past feedback history.

[0060] The feedback system can customize the feedback provided based on the user's current learning status. For example, it can provide appropriate feedback according to the user's current learning progress. It can also analyze the user's learning status and provide optimal feedback. Furthermore, it can provide customized feedback tailored to the user's learning goals. This allows for more appropriate feedback by taking the current learning status into consideration.

[0061] The simulation unit can select the most appropriate questions based on the user's geographical location when conducting question-and-answer simulations. For example, it can ask questions that reflect the culture and customs of the user's region. It can also select appropriate questions based on the user's geographical location. Furthermore, it can ask questions that reflect region-specific trends. In this way, by considering geographical location information, the system can provide the most optimal questions.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The filming team films the presentation video. Presentation videos include business presentations and academic presentations. The filming team can film the video using a smartphone or camera and adjust the resolution and frame rate. For example, they can film the video in 4K resolution and set the frame rate to 60fps. Step 2: The identification unit uses generation AI to analyze the video shot by the shooting unit and identify areas for improvement. The identification unit analyzes the content, speaking style, and slide design of the presentation and suggests specific areas for improvement. For example, it may point out that the speaking speed is too fast or the font size on the slides is too small. The identification unit can also analyze the content of the presentation and extract key points. Step 3: The generation unit generates a revised presentation video based on the improvements identified by the identification unit. The generation unit adjusts the speaking speed and improves the slide design. The generation unit can also edit the presentation video using the generation AI. For example, it can generate a video with adjusted speaking speed. Step 4: The provisioning department provides the revised video generated by the generation department as feedback. The provisioning department provides the revised presentation video to the junior employee as feedback. The provisioning department can also customize the content of the feedback using the generation AI. Step 5: The simulation unit uses a generative AI to simulate a question-and-answer session. The simulation unit uses prompts to simulate a realistic question-and-answer session. For example, the generative AI receives the prompt "Generate questions about this presentation" and generates questions.

[0064] (Example of form 2) The presentation support system according to an embodiment of the present invention is a system that utilizes generative AI to provide an environment in which young employees can improve their presentation skills and receive feedback, overcoming the constraints of time and the number of attempts, in order to address the presentation challenges they face. This presentation support system records a video of the presentation, and the generative AI analyzes the video to identify areas for improvement. Next, the generative AI generates a revised presentation video and provides feedback. Furthermore, it uses prompts to conduct a realistic simulation of the Q&A session. This system allows young employees to improve their skills and receive feedback over the constraints of time and the number of attempts, supporting the improvement of their presentation skills and the realization of effective communication. For example, a video of a presentation is recorded. A young employee records their presentation using a smartphone or camera. This video is input into the generative AI. Next, the generative AI analyzes the input video and identifies areas for improvement. The generative AI analyzes the content of the presentation, the speaking style, the design of the slides, etc., and suggests specific areas for improvement. For example, it may point out that the speaking speed is too fast or the text on the slides is too small. The generative AI generates a revised presentation video based on the identified areas for improvement. For example, the speaking speed can be adjusted, or the slide design can be improved. This revised video is then provided to the junior employee as feedback. Furthermore, a Q&A simulation is conducted. The generating AI uses prompts to simulate a realistic Q&A session. For example, it generates questions about the presentation content, and the junior employee answers them. This simulation allows the junior employee to prepare for the actual presentation. This system allows junior employees to improve themselves and receive feedback beyond the constraints of time and frequency. For example, they can practice their presentations during their free time, such as evenings or weekends, and receive feedback from the generating AI. This supports the improvement of presentation skills and the realization of effective communication. In this way, the presentation support system enables junior employees to improve their presentation skills and achieve effective communication.

[0065] The presentation support system according to this embodiment comprises a shooting unit, an identification unit, a generation unit, a provision unit, and a simulation unit. The shooting unit shoots a video of the presentation. The video of the presentation includes, but is not limited to, business presentations and academic presentations. The shooting unit shoots the video of the presentation using, for example, a smartphone or camera. The shooting unit can also adjust the resolution and frame rate of the video. For example, the shooting unit can shoot a video in 4K resolution and set the frame rate to 60fps. The identification unit uses generation AI to analyze the video shot by the shooting unit and identify areas for improvement. For example, the identification unit analyzes the content of the presentation, the speaking style, and the design of the slides, and suggests specific areas for improvement. For example, the identification unit may point out that the speaking speed is too fast or the text on the slides is too small. The identification unit can also use generation AI to analyze the content of the presentation and extract important points. For example, the identification unit receives a prompt from the generation AI saying, "Please summarize the main points of this presentation," extracts the main points, and suggests areas for improvement. The generation unit generates a revised presentation video based on the improvements identified by the identification unit. For example, the generation unit may adjust the speaking speed or improve the slide design. The generation unit can also edit the presentation video using the generation AI. For example, the generation unit receives a prompt from the generation AI saying, "Please adjust the speaking speed," and generates a video with the speaking speed adjusted. The delivery unit provides the revised video generated by the generation unit as feedback. For example, the delivery unit provides the revised presentation video to junior employees as feedback. The delivery unit can also customize the content of the feedback using the generation AI. For example, the delivery unit receives a prompt from the generation AI saying, "Please provide feedback on areas for improvement in this presentation," and provides feedback. The simulation unit uses the generation AI to simulate a question-and-answer session. For example, the simulation unit uses prompts to simulate a realistic question-and-answer session.For example, the simulation unit receives a prompt from the generating AI saying, "Generate questions about this presentation," and generates questions. This allows the presentation support system according to this embodiment to enable young employees to improve their presentation skills and achieve effective communication.

[0066] The specific unit can analyze the content or delivery of a presentation, the design of the slides, and suggest areas for improvement. For example, the unit can analyze the content of a presentation and extract key points. For instance, the unit might receive a prompt from the generating AI saying, "Summarize the main points of this presentation," and then extract the points and suggest areas for improvement. The unit can also analyze the delivery and suggest areas for improvement, such as adjusting the speaking speed and tone. For example, if the speaking speed is too fast, the unit will suggest adjusting it to an appropriate speed. The unit can also analyze the design of the slides and suggest areas for improvement, such as font size and color usage. For example, if the font on the slides is too small, the unit will suggest increasing the font size. By providing specific areas for improvement, the quality of the presentation can be enhanced. Some or all of the above processing in the specific unit is performed using the generating AI. For example, the unit inputs a video of the presentation into the generating AI, which then analyzes the video and suggests areas for improvement.

[0067] The generation unit can adjust the speaking speed. For example, the generation unit adjusts the speaking speed in a presentation video. For instance, if the speaking speed is too fast, the generation unit adjusts it to an appropriate speed. It can also adjust the speaking speed to be faster if it is too slow. The generation unit uses a generation AI to receive prompts to adjust the speaking speed and adjusts it to an appropriate speed. For example, the generation unit receives a prompt from the generation AI saying "Please adjust the speaking speed" and generates a video with the speaking speed adjusted. This makes it possible to create presentations that are easier for the listener to understand by adjusting the speaking speed. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs a presentation video into the generation AI, which adjusts the speaking speed and generates a revised video.

[0068] The generation unit can improve the design of slides. For example, the generation unit can improve the design of presentation slides. For example, the generation unit can adjust the font size and color scheme of the slides. The generation unit can also change the layout of the slides. The generation unit uses a generation AI to receive prompts for improving the slide design and improves it to an appropriate design. For example, the generation unit receives a prompt from the generation AI saying "Please improve the slide design" and generates a video with the improved slide design. This makes it possible to create a visually appealing presentation by improving the slide design. Some or all of the above processes in the generation unit are performed using the generation AI. For example, the generation unit inputs the presentation slides into the generation AI, and the generation AI improves the slide design and generates a revised video.

[0069] The simulation unit can perform realistic question-and-answer simulations using prompts. For example, the simulation unit can generate questions related to the content of a presentation. For instance, the simulation unit's generating AI receives the prompt "Generate questions about this presentation" and generates questions. The simulation unit can also simulate a junior employee answering the generated questions. For example, the simulation unit's generating AI receives the prompt "Answer this question" and simulates a junior employee answering. This allows for realistic question-and-answer simulations, preparing for actual presentations. Some or all of the above processes in the simulation unit are performed using the generating AI. For example, the simulation unit inputs the content of the presentation into the generating AI, which then generates questions and performs the simulation.

[0070] The service provider can provide employees with the revised presentation video as feedback. For example, the service provider can provide the revised presentation video as feedback to junior employees. The service provider can also customize the content of the feedback using generative AI. For example, the service provider can have the generative AI receive a prompt such as "Please provide feedback on how to improve this presentation" and then provide the feedback. This promotes self-improvement by providing the revised presentation video as feedback. Some or all of the above processes in the service provider are performed using generative AI. For example, the service provider inputs the revised presentation video into the generative AI, and the generative AI generates and provides the feedback.

[0071] The camera unit can estimate the user's emotions and adjust the timing of filming based on the estimated emotions. For example, if the user is nervous, the camera unit will wait until the user relaxes before starting filming. For example, the camera unit will analyze the user's facial expressions and, if it determines that the user is nervous, will wait until the user relaxes. The camera unit can also continue filming if the user is concentrating, in order to maintain their concentration. For example, the camera unit will analyze the user's facial expressions and, if it determines that the user is concentrating, will continue filming. The camera unit can also take a break before resuming filming if the user is tired. For example, the camera unit will analyze the user's facial expressions and, if it determines that the user is tired, will take a break. By adjusting the timing of filming according to the user's emotions, it is possible to film more natural presentation videos. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the camera unit is performed using generative AI. For example, the shooting unit inputs the user's facial expression data into a generating AI, which estimates the emotion and adjusts the timing of the shot.

[0072] The camera unit can automatically adjust the optimal shooting angle and lighting during shooting by referring to the user's past presentation history. For example, the camera unit can automatically set the shooting angle that the user previously preferred. For example, the camera unit analyzes the user's past presentation videos to identify the optimal shooting angle. The camera unit can also reproduce the lighting settings that the user has used in the past. For example, the camera unit analyzes the user's past presentation videos to identify the optimal lighting settings. The camera unit can also suggest the most effective shooting settings based on the user's past presentation history. For example, the camera unit analyzes the user's past presentation videos to suggest the optimal shooting settings. This allows the camera unit to automatically select the optimal shooting settings by referring to past presentation history. Some or all of the above processes in the camera unit are performed using a generative AI. For example, the camera unit inputs the user's past presentation videos into the generative AI, which identifies and automatically adjusts the optimal shooting settings.

[0073] The recording unit can analyze the user's current ambient sound during recording and automatically remove noise. For example, the recording unit can analyze ambient noise in real time and perform noise cancellation. For example, the recording unit analyzes ambient sound and removes noise using noise cancellation technology. The recording unit can also emphasize the user's voice and suppress background noise. For example, the recording unit analyzes ambient sound and performs filtering to emphasize the user's voice. The recording unit can also analyze ambient sound and automatically adjust the optimal microphone settings. For example, the recording unit analyzes ambient sound, identifies the optimal microphone settings, and automatically adjusts them. This allows for recording presentations with clear audio by analyzing ambient sound and removing noise. Some or all of the above processing in the recording unit is performed using generative AI. For example, the recording unit inputs ambient sound data into the generative AI, which removes noise and sets the optimal audio settings.

[0074] The shooting unit can estimate the user's emotions and determine shooting priorities based on the estimated emotions. For example, if the user is tense, the shooting unit will prioritize other tasks until the user relaxes. For example, the shooting unit will analyze the user's facial expressions and, if it determines that the user is tense, will prioritize other tasks. The shooting unit can also prioritize shooting if the user is focused, leveraging that focus. For example, the shooting unit will analyze the user's facial expressions and, if it determines that the user is focused, will prioritize shooting. The shooting unit can also prioritize rest and postpone shooting if the user is tired. For example, the shooting unit will analyze the user's facial expressions and, if it determines that the user is tired, will prioritize rest. In this way, by determining shooting priorities according to the user's emotions, shooting can be performed at the optimal timing. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the shooting unit is performed using generative AI. For example, the shooting unit inputs the user's facial expression data into a generating AI, which estimates the emotions and determines the priority of shooting.

[0075] The shooting unit can select the optimal shooting settings based on the user's geographical location information during shooting. For example, when shooting outdoors, the shooting unit can select settings that make the most of natural light. For example, the shooting unit analyzes the user's geographical location information and identifies shooting settings that make the most of natural light. The shooting unit can also optimize artificial lighting when shooting indoors. For example, the shooting unit analyzes the user's geographical location information and identifies settings to optimize artificial lighting. The shooting unit can also automatically adjust sound settings according to a specific location. For example, the shooting unit analyzes the user's geographical location information, identifies the optimal sound settings, and automatically adjusts them. In this way, the optimal shooting settings can be selected by considering geographical location information. Some or all of the above processing in the shooting unit is performed using a generative AI. For example, the shooting unit inputs the user's geographical location information into the generative AI, which identifies the optimal shooting settings and automatically adjusts them.

[0076] The photography team can analyze the user's social media activity during filming and suggest relevant presentation content. For example, the photography team can suggest presentation themes based on the user's past posts. For example, the photography team analyzes the user's social media activity and identifies presentation themes based on past posts. The photography team can also analyze the interests of the user's followers and suggest relevant content. For example, the photography team analyzes the user's social media activity and identifies presentation content based on the interests of their followers. The photography team can also suggest content that reflects trends based on the user's social media activity. For example, the photography team analyzes the user's social media activity and identifies presentation content that reflects trends. In this way, by analyzing social media activity, relevant presentation content can be suggested. Some or all of the above processing in the photography team is performed using generative AI. For example, the photography team inputs the user's social media activity data into the generative AI, which then identifies and suggests relevant presentation content.

[0077] The specific unit can estimate the user's emotions and adjust the method of presenting improvement suggestions based on the estimated emotions. For example, if the user is nervous, the specific unit may present improvement suggestions in gentle language. For example, if the specific unit analyzes the user's facial expression and determines that the user is nervous, it may present improvement suggestions in gentle language. The specific unit can also present detailed improvement suggestions if the user is relaxed. For example, if the specific unit analyzes the user's facial expression and determines that the user is relaxed, it may present detailed improvement suggestions. The specific unit can also present concise improvement suggestions if the user is in a hurry. For example, if the specific unit analyzes the user's facial expression and determines that the user is in a hurry, it may present concise improvement suggestions. By adjusting the method of presenting improvement suggestions according to the user's emotions, more effective feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the specific unit is performed using generative AI. For example, a specific unit inputs the user's facial expression data into a generating AI, which then estimates the emotion and adjusts the method of suggesting improvements.

[0078] The specific unit can analyze the content of a presentation and identify areas for improvement by comparing it to past successful examples. For example, the specific unit can analyze the speaking speed and tone by comparing it to past successful presentations. For example, the specific unit can analyze videos of past successful examples to identify the speaking speed and tone. The specific unit can also identify areas for improvement by comparing it to the slide design of successful examples. For example, the specific unit can analyze the slide design of past successful examples to identify areas for improvement. The specific unit can also identify areas for improvement in content by comparing it to the structure of successful examples. For example, the specific unit can analyze the structure of past successful examples to identify areas for improvement in content. In this way, specific areas for improvement can be identified by comparing it to past successful examples. Some or all of the above processing in the specific unit is performed using a generative AI. For example, the specific unit inputs data from past successful examples into the generative AI, which then compares and identifies areas for improvement.

[0079] The specific unit can analyze a presentation's delivery and suggest improvements based on the tone or intonation of the voice. For example, the unit can analyze the user's speaking speed and suggest an appropriate speed. For instance, it can analyze the user's voice data and, if the speaking speed is too fast, advise adjusting to an appropriate speed. The unit can also analyze the user's voice tone and suggest a more effective tone. For example, it can analyze the user's voice data and, if the voice tone is monotonous, advise adding intonation. The unit can also analyze the user's intonation and suggest an intonation that is easier for the listener to understand. For example, it can analyze the user's voice data and, if the intonation is insufficient, advise adding appropriate intonation. This allows the unit to suggest improvements to delivery that are more effective by considering the tone and intonation of the voice. Some or all of the above processing in the specific unit is performed using a generative AI. For example, the unit inputs the user's voice data into the generative AI, which analyzes the tone and intonation of the voice and suggests improvements.

[0080] The system can estimate the user's emotions and prioritize improvements based on those emotions. For example, if the user is tense, the system will suggest simple improvements first. For instance, it can analyze the user's facial expressions and, if it determines the user is tense, prioritize suggesting simple improvements. Similarly, if the user is relaxed, the system can prioritize suggesting detailed improvements. For example, it can analyze the user's facial expressions and, if it determines the user is relaxed, prioritize suggesting detailed improvements. Furthermore, if the user is in a hurry, the system can prioritize suggesting important improvements. For example, it can analyze the user's facial expressions and, if it determines the user is in a hurry, prioritize suggesting important improvements. This allows for effective improvements by prioritizing improvements according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the specific unit are performed using a generating AI. For example, the specific unit inputs the user's facial expression data into the generating AI, which estimates the emotions and determines the priority of areas for improvement.

[0081] The specific unit can analyze the content of a presentation and suggest improvements based on the user's industry-specific terminology or trends. For example, the specific unit can analyze whether industry-specific terminology is being used appropriately and suggest improvements. For instance, the specific unit analyzes the user's presentation content and, if industry-specific terminology is not being used appropriately, it will point out the need to use appropriate terminology. The specific unit can also suggest content that reflects the latest industry trends. For example, the specific unit analyzes the user's presentation content and, if the latest industry trends are not reflected, it will point out the need to reflect the trends. The specific unit can also compare the presentation to industry best practices and suggest improvements. For example, the specific unit analyzes the user's presentation content and identifies areas for improvement by comparing it to industry best practices. This allows for the suggestion of more appropriate improvements by considering industry-specific terminology and trends. Some or all of the above processing in the specific unit is performed using a generative AI. For example, the specific unit inputs the user's presentation content into the generative AI, which analyzes industry-specific terminology and trends and suggests improvements.

[0082] The specific unit can analyze presentation slide designs and suggest improvements that reflect the latest design trends. For example, the unit can propose slide designs that reflect the latest design trends. For example, the unit can analyze the user's slide design and suggest designs that reflect the latest design trends. The unit can also suggest slide color schemes and fonts that match the latest trends. For example, the unit can analyze the user's slide design and, if the color scheme or fonts are outdated, suggest changes that match the latest trends. The unit can also improve slide layouts based on the latest design trends. For example, the unit can analyze the user's slide design and, if the layout is outdated, improve it based on the latest trends. This makes it possible to create visually appealing slide designs that reflect the latest design trends. Some or all of the above processing in the specific unit is performed using a generation AI. For example, the unit inputs the user's slide design into the generation AI, which analyzes the latest design trends and suggests improvements.

[0083] The generation unit can estimate the user's emotions and adjust the method of generating the modified video based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a video that progresses at a leisurely pace. For example, if the generation unit analyzes the user's facial expressions and determines that the user is relaxed, it will generate a video that progresses at a leisurely pace. The generation unit can also generate a video that emphasizes the shortest route if the user is in a hurry. For example, if the generation unit analyzes the user's facial expressions and determines that the user is in a hurry, it will generate a video that emphasizes the shortest route. The generation unit can also generate a video with visually stimulating effects if the user is excited. For example, if the generation unit analyzes the user's facial expressions and determines that the user is excited, it will generate a video with visually stimulating effects. In this way, by adjusting the method of generating the modified video according to the user's emotions, a more effective modified video can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's facial expression data into the generation AI, which estimates the emotion and adjusts the method for generating the corrected video.

[0084] The generation unit can customize the generated edited video to reflect the user's past presentation style. For example, the generation unit can reflect the speaking style and tone the user has used in the past. For example, the generation unit analyzes the user's past presentation videos to identify and reflect the speaking style and tone. The generation unit can also reproduce slide designs preferred by the user. For example, the generation unit analyzes the user's past presentation videos to identify and reproduce slide designs. Furthermore, the generation unit can make optimal corrections based on the user's past presentation style. For example, the generation unit analyzes the user's past presentation videos to identify and make optimal corrections. In this way, by reflecting past presentation styles, the generation unit can provide the user with the most suitable edited video. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's past presentation videos into the generation AI, which analyzes the style and generates the edited video.

[0085] The generation unit can generate corrected videos based on the user's industry-specific presentation style. For example, the generation unit can generate videos that reflect industry-specific terminology and trends. For instance, it can analyze the user's industry-specific presentation content and generate videos that reflect terminology and trends. The generation unit can also generate videos that incorporate industry best practices. For example, it can analyze the user's industry-specific presentation content and generate videos that incorporate best practices. The generation unit can also reflect a presentation style tailored to the characteristics of the industry. For example, it can analyze the user's industry-specific presentation content and reflect a style tailored to the characteristics. This allows for the provision of more appropriate corrected videos by considering industry-specific presentation styles. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's industry-specific presentation content into the generation AI, which analyzes the style and generates the corrected video.

[0086] The generation unit can estimate the user's emotions and determine the priority of edited videos based on the estimated emotions. For example, if the user is nervous, the generation unit will prioritize simple edits. For example, if the generation unit analyzes the user's facial expressions and determines that the user is nervous, it will prioritize simple edits. The generation unit can also prioritize detailed edits if the user is relaxed. For example, if the generation unit analyzes the user's facial expressions and determines that the user is relaxed, it will prioritize detailed edits. The generation unit can also prioritize important edits if the user is in a hurry. For example, if the generation unit analyzes the user's facial expressions and determines that the user is in a hurry, it will prioritize important edits. This allows for effective editing by prioritizing edited videos according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's facial expression data into the generation AI, which estimates the emotions and determines the priority of the corrected videos.

[0087] The generation unit can select the optimal style when generating a corrected video, taking into account the user's geographical location information. For example, the generation unit can select a style that reflects the culture and customs of the user's region. For example, the generation unit analyzes the user's geographical location information and identifies a style that reflects the culture and customs of that region. The generation unit can also select appropriate backgrounds and effects based on the user's geographical location. For example, the generation unit analyzes the user's geographical location information and identifies the optimal backgrounds and effects. The generation unit can also select a style that reflects region-specific trends. For example, the generation unit analyzes the user's geographical location information and identifies a style that reflects region-specific trends. In this way, by considering geographical location information, it is possible to provide a corrected video with the optimal style. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's geographical location information into the generation AI, and the generation AI identifies the optimal style and generates the corrected video.

[0088] The generation unit can analyze the user's social media activity and reflect relevant content when generating edited videos. For example, the generation unit can select a theme for the edited video based on content the user has previously posted. For example, the generation unit analyzes the user's social media activity and identifies a theme for the edited video based on past posts. The generation unit can also analyze the interests of the user's followers and reflect relevant content. For example, the generation unit analyzes the user's social media activity and identifies the content of the edited video based on the interests of the followers. The generation unit can also select content that reflects trends from the user's social media activity. For example, the generation unit analyzes the user's social media activity and identifies the content of the edited video that reflects trends. In this way, by analyzing social media activity, it is possible to provide edited videos that reflect relevant content. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the user's social media activity data into the generation AI, which identifies relevant content and generates the edited video.

[0089] The service provider can estimate the user's emotions and adjust the method of providing feedback based on the estimated emotions. For example, if the user is nervous, the service provider can provide feedback in gentle language. For example, the service provider can analyze the user's facial expressions and, if it determines that the user is nervous, provide feedback in gentle language. The service provider can also provide detailed feedback if the user is relaxed. For example, the service provider can analyze the user's facial expressions and, if it determines that the user is relaxed, provide detailed feedback. The service provider can also provide concise feedback if the user is in a hurry. For example, the service provider can analyze the user's facial expressions and, if it determines that the user is in a hurry, provide concise feedback. In this way, by adjusting the method of providing feedback according to the user's emotions, more effective feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider is performed using generative AI. For example, the service provider inputs the user's facial expression data into a generating AI, which then estimates the emotion and adjusts the method of providing feedback.

[0090] The service provider can select the optimal method of providing feedback by referring to the user's past feedback history. For example, the service provider can reproduce feedback formats that the user has preferred in the past. For example, the service provider can analyze the user's past feedback history, identify preferred feedback formats, and reproduce them. The service provider can also select the most effective method of providing feedback from the user's past feedback history. For example, the service provider can analyze the user's past feedback history and identify the optimal method of providing feedback. The service provider can also provide feedback at the optimal timing based on the user's past feedback history. For example, the service provider can analyze the user's past feedback history, identify the optimal timing, and provide feedback. In this way, the service provider can select the optimal method of providing feedback by referring to past feedback history. Some or all of the above processes in the service provider are performed using a generative AI. For example, the service provider inputs the user's past feedback history into the generative AI, which identifies the optimal method of providing feedback and provides it.

[0091] The service provider can customize the feedback provided based on the user's current learning status. For example, the service provider can provide appropriate feedback according to the user's current learning progress. For example, the service provider can analyze the user's learning progress and provide feedback accordingly. The service provider can also analyze the user's learning situation and provide optimal feedback. For example, the service provider can analyze the user's learning situation, identify and provide the optimal feedback. The service provider can also provide customized feedback tailored to the user's learning goals. For example, the service provider can analyze the user's learning goals and provide feedback tailored to those goals. This allows for the provision of more appropriate feedback by considering the current learning situation. Some or all of the above processing in the service provider is performed using a generative AI. For example, the service provider inputs the user's learning status data into the generative AI, which then identifies and provides the optimal feedback.

[0092] The service provider can estimate the user's emotions and prioritize feedback based on those emotions. For example, if the user is nervous, the service provider will prioritize providing simple feedback. For instance, if the service provider analyzes the user's facial expressions and determines that the user is nervous, it will prioritize providing simple feedback. The service provider can also prioritize providing detailed feedback if the user is relaxed. For instance, if the service provider analyzes the user's facial expressions and determines that the user is relaxed, it will prioritize providing detailed feedback. The service provider can also prioritize providing important feedback if the user is in a hurry. For instance, if the service provider analyzes the user's facial expressions and determines that the user is in a hurry, it will prioritize providing important feedback. This allows for effective feedback by prioritizing feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the service provider is performed using generative AI. For example, the service provider inputs the user's facial expression data into a generating AI, which then estimates the emotion and determines the priority of the feedback.

[0093] The service provider can select the optimal method of providing feedback based on the user's geographical location. For example, the service provider can provide feedback that reflects the culture and customs of the user's region. For example, the service provider can analyze the user's geographical location and identify feedback that reflects the culture and customs of that region. The service provider can also select an appropriate feedback format based on the user's geographical location. For example, the service provider can analyze the user's geographical location and identify the optimal feedback format. The service provider can also provide feedback that reflects region-specific trends. For example, the service provider can analyze the user's geographical location and identify feedback that reflects region-specific trends. This allows the service provider to provide optimal feedback by considering geographical location. Some or all of the above processing in the service provider is performed using a generative AI. For example, the service provider inputs the user's geographical location into the generative AI, which then identifies and provides the optimal feedback format.

[0094] The service provider can analyze the user's social media activity and reflect relevant content when providing feedback. For example, the service provider can select feedback themes based on the user's past posts. For example, the service provider analyzes the user's social media activity and identifies feedback themes based on past posts. The service provider can also analyze the interests of the user's followers and reflect relevant content. For example, the service provider analyzes the user's social media activity and identifies feedback content based on the interests of followers. The service provider can also select content that reflects trends from the user's social media activity. For example, the service provider analyzes the user's social media activity and identifies feedback content that reflects trends. In this way, by analyzing social media activity, it is possible to provide feedback that reflects relevant content. Some or all of the above processing in the service provider is performed using a generative AI. For example, the service provider inputs the user's social media activity data into the generative AI, which identifies relevant content and provides feedback.

[0095] The simulation unit can estimate the user's emotions and adjust the question-and-answer simulation method based on the estimated emotions. For example, if the user is nervous, the simulation unit can start with gentle questions. For example, the simulation unit can analyze the user's facial expressions and, if it determines that the user is nervous, generate gentle questions. The simulation unit can also ask detailed questions if the user is relaxed. For example, the simulation unit can analyze the user's facial expressions and, if it determines that the user is relaxed, generate detailed questions. The simulation unit can also ask concise questions if the user is in a hurry. For example, the simulation unit can analyze the user's facial expressions and, if it determines that the user is in a hurry, generate concise questions. By adjusting the question-and-answer simulation method according to the user's emotions, a more effective simulation can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the simulation unit is performed using generative AI. For example, the simulation unit inputs the user's facial expression data into a generating AI, which estimates the emotions and adjusts the question-and-answer simulation method.

[0096] The simulation unit can provide realistic simulations by referring to past question-and-answer data when performing question-and-answer simulations. For example, the simulation unit can generate realistic questions based on past question-and-answer data. For example, the simulation unit can analyze past question-and-answer data, identify and generate realistic questions. The simulation unit can also select the most effective questions from past question-and-answer data. For example, the simulation unit can analyze past question-and-answer data, identify and select the most effective questions. The simulation unit can also provide realistic simulations by analyzing past question-and-answer data. For example, the simulation unit can analyze past question-and-answer data and generate questions to provide realistic simulations. In this way, realistic simulations can be provided by referring to past question-and-answer data. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs past question-and-answer data into the generation AI, and the generation AI analyzes the data to generate realistic questions.

[0097] The simulation unit can perform Q&A simulations that reflect the user's industry-specific questions. For example, the simulation unit can generate questions using industry-specific terminology. For instance, it can analyze the user's industry-specific presentation content and generate questions that reflect that terminology. The simulation unit can also generate questions that reflect industry trends. For example, it can analyze the user's industry-specific presentation content and generate questions that reflect those trends. Furthermore, the simulation unit can generate questions based on industry best practices. For example, it can analyze the user's industry-specific presentation content and generate questions based on best practices. By reflecting industry-specific questions, it can provide more appropriate Q&A simulations. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs the user's industry-specific presentation content into the generation AI, which then generates questions and performs the simulation.

[0098] The simulation unit can estimate the user's emotions and determine the priority of questions and answers based on the estimated emotions. For example, if the user is nervous, the simulation unit will prioritize simple questions. For example, if the simulation unit analyzes the user's facial expressions and determines that the user is nervous, it will prioritize simple questions. The simulation unit can also prioritize detailed questions if the user is relaxed. For example, if the simulation unit analyzes the user's facial expressions and determines that the user is relaxed, it will prioritize detailed questions. The simulation unit can also prioritize important questions if the user is in a hurry. For example, if the simulation unit analyzes the user's facial expressions and determines that the user is in a hurry, it will prioritize important questions. This allows for effective question and answer sessions by determining the priority of questions and answers according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the simulation unit is performed using generative AI. For example, the simulation unit inputs the user's facial expression data into a generating AI, which then estimates the emotions and determines the priority of questions and answers.

[0099] The simulation unit can select the most appropriate questions based on the user's geographical location when simulating question-and-answer sessions. For example, the simulation unit can ask questions that reflect the culture and customs of the user's region. For instance, the simulation unit analyzes the user's geographical location and generates questions that reflect the culture and customs of that region. The simulation unit can also select appropriate questions based on the user's geographical location. For example, the simulation unit analyzes the user's geographical location and identifies and selects the most appropriate questions. The simulation unit can also ask questions that reflect region-specific trends. For example, the simulation unit analyzes the user's geographical location and generates questions that reflect region-specific trends. This allows the system to provide optimal questions by considering geographical location. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs the user's geographical location into the generation AI, which then identifies and generates the most appropriate questions.

[0100] The simulation unit can analyze a user's social media activity and reflect relevant questions when conducting a Q&A simulation. For example, the simulation unit can generate questions based on content the user has previously posted. For example, the simulation unit analyzes the user's social media activity and identifies and generates questions based on past posts. The simulation unit can also analyze the interests of the user's followers and reflect relevant questions. For example, the simulation unit analyzes the user's social media activity and identifies and generates questions based on the interests of their followers. The simulation unit can also generate questions that reflect trends from the user's social media activity. For example, the simulation unit analyzes the user's social media activity and identifies and generates questions that reflect trends. In this way, relevant questions can be provided by analyzing social media activity. Some or all of the above processing in the simulation unit is performed using a generation AI. For example, the simulation unit inputs the user's social media activity data into the generation AI, which then identifies and generates relevant questions. === Hard Collateral 1-1 === Each of the multiple elements described above, including the shooting unit, identification unit, generation unit, provision unit, and simulation unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the shooting unit uses the camera 42 of the smart device 14 to shoot a video of the presentation. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the shot video using generation AI to identify areas for improvement. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a revised presentation video based on the identified areas for improvement. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the generated revised video to the junior employee as feedback. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs a question-and-answer simulation using generation AI. === Hard Collateral 1-2 === Each of the multiple elements described above, including the shooting unit, identification unit, generation unit, provision unit, and simulation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the shooting unit uses the camera 42 of the smart glasses 214 to shoot a video of the presentation. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the shot video using a generation AI and identifies areas for improvement. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates a revised presentation video based on the identified areas for improvement. The provision unit is implemented by the control unit 46A of the smart glasses 214, which provides the generated revised video to the junior employee as feedback. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses a generation AI to simulate a question-and-answer session. === Hard Collateral 1-3 === Each of the multiple elements described above, including the shooting unit, identification unit, generation unit, provision unit, and simulation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the shooting unit uses the camera 42 of the headset terminal 314 to shoot a video of the presentation. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the shot video using a generation AI and identifies areas for improvement. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates a revised presentation video based on the identified areas for improvement. The provision unit is implemented by the control unit 46A of the headset terminal 314, which provides the generated revised video to the junior employee as feedback. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses a generation AI to simulate a question-and-answer session. === Hard Collateral 1-4 === Each of the multiple elements described above, including the shooting unit, identification unit, generation unit, provision unit, and simulation unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the shooting unit uses the camera 42 of the robot 414 to shoot a video of the presentation. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the shot video using a generation AI and identifies areas for improvement. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates a revised presentation video based on the identified areas for improvement. The provision unit is implemented by the control unit 46A of the robot 414, which provides the generated revised video to the junior employee as feedback. The simulation unit is implemented by the identification processing unit 290 of the data processing unit 12, which uses a generation AI to simulate a question-and-answer session.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The presentation support system may also include a voice analysis unit. This unit can analyze the tone and intonation of the user's voice and provide advice to enhance the effectiveness of the presentation. For example, if the voice analysis unit is monotonous, it may suggest adding more intonation. It can also suggest a more effective tone if the user's voice tone is inappropriate. Furthermore, if the voice analysis unit is inappropriate, it may suggest adjusting the volume. This allows the user to deliver a more effective presentation.

[0103] A specific unit can estimate the user's emotions and adjust the way suggestions for improvement are presented based on those emotions. For example, if the user is nervous, suggestions for improvement may be presented in gentle language. If the user is relaxed, detailed suggestions for improvement may be presented. If the user is in a hurry, concise suggestions for improvement may be presented. By adjusting the way suggestions for improvement are presented according to the user's emotions, more effective feedback can be provided.

[0104] The generation unit can customize the generated edited video to reflect the user's past presentation style. For example, it can reflect the speaking style and tone the user has used in the past. It can also reproduce slide designs that the user preferred. Furthermore, it can make optimal corrections based on the user's past presentation style. In this way, by reflecting past presentation styles, it can provide the user with an edited video that is best suited to their needs.

[0105] The generation unit can estimate the user's emotions and adjust the method of generating the modified video based on those emotions. For example, if the user is relaxed, it can generate a video that progresses at a leisurely pace. If the user is in a hurry, it can generate a video that emphasizes the shortest route. If the user is excited, it can generate a video with visually stimulating effects. By adjusting the method of generating the modified video according to the user's emotions, it is possible to provide a more effective modified video.

[0106] The simulation unit can perform Q&A simulations that reflect the user's industry-specific questions. For example, it can generate questions using industry-specific terminology. It can also generate questions that reflect industry trends. Furthermore, it can generate questions based on industry best practices. By reflecting industry-specific questions, it can provide more appropriate Q&A simulations.

[0107] The feedback system can estimate the user's emotions and adjust the feedback delivery method based on those estimates. For example, if the user is nervous, it can provide feedback in gentle language. If the user is relaxed, it can provide detailed feedback. If the user is in a hurry, it can provide concise feedback. By adjusting the feedback delivery method according to the user's emotions, it is possible to provide more effective feedback.

[0108] The feedback delivery system can select the optimal method of delivery by referring to the user's past feedback history. For example, it can reproduce a feedback format that the user previously preferred. It can also select the most effective method of delivery from the user's past feedback history. Furthermore, it can deliver feedback at the optimal timing based on the user's past feedback history. In this way, the optimal method of delivery can be selected by referring to past feedback history.

[0109] The feedback system can customize the feedback provided based on the user's current learning status. For example, it can provide appropriate feedback according to the user's current learning progress. It can also analyze the user's learning status and provide optimal feedback. Furthermore, it can provide customized feedback tailored to the user's learning goals. This allows for more appropriate feedback by taking the current learning status into consideration.

[0110] The simulation unit can estimate the user's emotions and determine the priority of questions and answers based on those emotions. For example, if the user is nervous, simple questions can be prioritized. If the user is relaxed, more detailed questions can be prioritized. Also, if the user is in a hurry, important questions can be prioritized. This allows for more effective question-and-answer sessions by prioritizing questions according to the user's emotions.

[0111] The simulation unit can select the most appropriate questions based on the user's geographical location when conducting question-and-answer simulations. For example, it can ask questions that reflect the culture and customs of the user's region. It can also select appropriate questions based on the user's geographical location. Furthermore, it can ask questions that reflect region-specific trends. In this way, by considering geographical location information, the system can provide the most optimal questions.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The filming team films the presentation video. Presentation videos include business presentations and academic presentations. The filming team can film the video using a smartphone or camera and adjust the resolution and frame rate. For example, they can film the video in 4K resolution and set the frame rate to 60fps. Step 2: The identification unit uses generation AI to analyze the video shot by the shooting unit and identify areas for improvement. The identification unit analyzes the content, speaking style, and slide design of the presentation and suggests specific areas for improvement. For example, it may point out that the speaking speed is too fast or the font size on the slides is too small. The identification unit can also analyze the content of the presentation and extract key points. Step 3: The generation unit generates a revised presentation video based on the improvements identified by the identification unit. The generation unit adjusts the speaking speed and improves the slide design. The generation unit can also edit the presentation video using the generation AI. For example, it can generate a video with adjusted speaking speed. Step 4: The provisioning department provides the revised video generated by the generation department as feedback. The provisioning department provides the revised presentation video to the junior employee as feedback. The provisioning department can also customize the content of the feedback using the generation AI. Step 5: The simulation unit uses a generative AI to simulate a question-and-answer session. The simulation unit uses prompts to simulate a realistic question-and-answer session. For example, the generative AI receives the prompt "Generate questions about this presentation" and generates questions.

[0114] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0115] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0116] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0117] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] As shown in Figure 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.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0126] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0127] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0130] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0142] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0143] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0144] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0158] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0159] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0160] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0161] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0163] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0165] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0167] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0168] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0169] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0170] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0171] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0172] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0173] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0174] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0175] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0176] 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.

[0177] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0178] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0179] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0180] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0181] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0182] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0183] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0184] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0185] [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The filming department, which shoots the presentation video, An identification unit analyzes the video captured by the aforementioned shooting unit and identifies areas for improvement, A generation unit that generates a revised presentation video based on the improvements identified by the aforementioned specific unit, A providing unit that provides the corrected video generated by the generation unit as feedback, It includes a simulation unit that simulates question and answer sessions. A system characterized by the following features.

2. The specified part is, Analyze the content or delivery style of the presentation, as well as the slide design, and suggest areas for improvement. The system according to feature 1.

3. The generating unit is Adjust speaking speed The system according to feature 1.

4. The generating unit is Improve the design of your slides The system according to feature 1.

5. The aforementioned simulation unit, Use prompts to simulate a realistic question-and-answer session. The system according to feature 1.

6. The aforementioned supply unit is, Provide employees with feedback on the revised presentation video. The system according to feature 1.

7. The aforementioned imaging unit is It estimates the user's emotions and adjusts the timing of the photo shoot based on those emotions. The system according to feature 1.

8. The aforementioned imaging unit is During shooting, the system automatically adjusts the optimal shooting angle and lighting by referencing the user's past presentation history. The system according to feature 1.

Images