system

Abstract

The system according to this embodiment aims to grasp the speaker's communication style and the audience's reactions in real time during online meetings and provide appropriate feedback. [Solution] The system according to the embodiment comprises an intonation detection unit, a visualization unit, an expression detection unit, a display unit, a summarization unit, and a feedback unit. The intonation detection unit detects the speaker's intonation and pitch. The visualization unit visualizes the information detected by the intonation detection unit. The expression detection unit detects the facial expressions of the audience. The display unit displays the information detected by the expression detection unit. The summarization unit records a summary and important points during the presentation. The feedback unit provides feedback on the information recorded by the summarization unit.

Description

Technical Field

[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, including 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

[0007] The system according to this embodiment can grasp the speaker's communication style and the audience's reactions in real time during online meetings and provide appropriate feedback. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied 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) An autonomous AI agent system according to an embodiment of the present invention is a system that provides consistent support in online meetings, from preparation to delivery and feedback of presentations. This autonomous AI agent system provides real-time feedback from the stage when the user is preparing presentation materials. During the presentation, it detects the speaker's intonation and pitch and visualizes how the message is being received by overlaying transparent layers such as "passionate = red" and "calm = blue" on the screen. It also detects the speaking speed and displays a periodic waveform, allowing the presenter to control the progress of the presentation. Furthermore, it detects the level of interest from the audience's camera expressions and displays the level of interest by displaying an expression mark at the edge of the screen, visualizing how much attention the audience is receiving. The autonomous AI agent is always running in the background, recording summaries and important points during the presentation in real time and providing feedback to the speaker. It also automatically records audience questions and comments and pops up candidate answers as needed. Furthermore, it performs real-time sentiment analysis of the audience and provides feedback to the presenter. It immediately notifies the presenter if interest is waning or, conversely, if the audience is captivated, and provides flexible support. This allows the presenter to objectively evaluate their presentation and make adjustments as needed. This allows autonomous AI agent systems to improve the quality of presentations.

[0029] The autonomous AI agent system according to this embodiment includes an intonation detection unit, a visualization unit, an expression detection unit, a display unit, a summarization unit, and a feedback unit. The intonation detection unit detects the speaker's intonation and intonation. The intonation detection unit detects intonation and intonation by analyzing, for example, the pitch, volume, and rhythm of the voice. The intonation detection unit can, for example, take a voice signal as input and detect intonation and intonation using a voice analysis algorithm. The intonation detection unit can, for example, input the speaker's voice data into a generating AI, and the generating AI can analyze the voice data to detect intonation and intonation. The visualization unit performs visualization based on the information detected by the intonation detection unit. The visualization unit visually conveys the speaker's intonation and intonation by, for example, overlaying a transparent layer on the screen. The visualization unit can perform visualization using, for example, red or blue colors. The visualization unit can dynamically change the color and shape of the transparent layer according to the speaker's intonation and intonation. The facial expression detection unit detects the facial expressions of the audience. For example, the facial expression detection unit uses a camera to capture the audience's facial expressions and detects them using a facial expression recognition algorithm. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the data to detect expressions. For example, the facial expression detection unit can detect changes in the audience's facial expressions in real time. The display unit displays information based on the information detected by the facial expression detection unit. For example, the display unit displays facial expression marks at the edge of the screen. For example, the display unit can dynamically change the type and position of the facial expression marks according to the audience's facial expressions. For example, the display unit can input the audience's facial expression data into a generating AI, which can analyze the data to determine the display content. The summarization unit records summaries and important points during the presentation. For example, the summarization unit analyzes the content of the presentation in real time and generates a summary. For example, the summarization unit can input the audio data of the presentation into a generating AI, which can analyze the audio data to generate a summary. For example, the summarization unit can automatically extract and record important points of the presentation.The feedback unit provides feedback on the information recorded by the summarization unit. For example, the feedback unit provides the speaker with a summary generated by the summarization unit. For example, the feedback unit notifies the speaker of key points extracted by the summarization unit. For example, the feedback unit automatically records audience questions and comments and pops up suggested answers as needed. For example, the feedback unit performs real-time sentiment analysis of the audience and provides feedback to the presenter. In this way, the autonomous AI agent system according to the embodiment can improve the quality of the presentation.

[0030] The intonation detection unit detects the speaker's intonation and intonation. For example, it detects intonation and intonation by analyzing the pitch, volume, and rhythm of the speech. Specifically, it digitizes the speech signal and performs frequency analysis to analyze changes in pitch and volume in detail. This allows for a more accurate understanding of the speaker's emotions and intentions. The intonation detection unit can, for example, take a speech signal as input and detect intonation and intonation using a speech analysis algorithm. The speech analysis algorithm analyzes the speech signal using, for example, Fourier transforms and Mel-frequency cepstrum coefficients (MFCCs) to extract features. This allows for highly accurate capture of the speaker's speech characteristics. The intonation detection unit can, for example, input speaker speech data into a generating AI, which then analyzes the speech data to detect intonation and intonation. The generating AI, for example, uses a deep learning-based speech recognition model to learn intonation and intonation patterns from the speech data. This allows for highly accurate analysis of the speaker's emotions and intentions and provides real-time feedback.

[0031] The visualization unit performs visualization based on information detected by the intonation detection unit. For example, the visualization unit visually conveys the speaker's intonation and intonation by overlaying a transparent layer on the screen. Specifically, it dynamically changes the color and shape of the transparent layer in response to changes in intonation. For example, it changes to red when the speaker's voice rises and to blue when their voice falls. Furthermore, the transparency and shape of the transparent layer can be changed according to the strength of the intonation. The visualization unit can use colors such as red and blue for visualization, making it easier for the audience to visually understand the speaker's emotions and intentions. The visualization unit can dynamically change the color and shape of the transparent layer in response to the speaker's intonation and intonation, enabling the real-time visual conveyance of the speaker's emotions and intentions, thereby enhancing the effectiveness of the presentation. Additionally, the visualization unit can automatically generate visualization patterns based on data from the intonation detection unit. This allows for the provision of optimal visualizations tailored to the speaker's intonation and intonation.

[0032] The facial expression detection unit detects the facial expressions of the audience. For example, the facial expression detection unit uses a camera to capture the audience's facial expressions and detects them using a facial expression recognition algorithm. Specifically, it takes image data captured by the camera as input and extracts facial feature points. This allows for real-time detection of changes in the audience's facial expressions. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the data and detect expressions. The generating AI, for example, uses a deep learning-based facial expression recognition model to learn emotional patterns from the facial expression data. This allows for high-precision analysis of the audience's emotions and reactions and provides real-time feedback. For example, the facial expression detection unit can detect changes in the audience's facial expressions in real time. This allows the speaker to grasp the audience's reactions in real time and adjust the progress of the presentation. Furthermore, the facial expression detection unit can use multiple cameras to capture the audience's facial expressions from multiple angles. This allows for more accurate detection of the audience's facial expressions and enhances the effectiveness of the presentation.

[0033] The display unit displays information based on the information detected by the facial expression detection unit. For example, the display unit displays facial expression marks at the edge of the screen. Specifically, it displays facial expression marks such as smiles, surprise, and confusion according to the audience's facial expressions. This allows the speaker to visually grasp the audience's reactions. For example, the display unit can dynamically change the type and position of the facial expression marks according to the audience's facial expressions. This allows the speaker to grasp the audience's reactions in real time and adjust the progress of the presentation. For example, the display unit can input the audience's facial expression data into a generating AI, which analyzes the facial expression data and determines the display content. For example, the generating AI uses a facial expression recognition model using deep learning to learn emotional patterns from the facial expression data. This allows it to analyze the audience's emotions and reactions with high accuracy and update the display content in real time. Furthermore, the display unit can automatically adjust the display content according to the audience's reactions. This allows the speaker to grasp the audience's reactions in real time and improve the effectiveness of the presentation.

[0034] The summarization unit records summaries and key points during a presentation. For example, the summarization unit analyzes the presentation content in real time and generates a summary. Specifically, it takes the presentation's audio data as input and converts it into text data using a speech recognition algorithm. This allows the presentation content to be recorded in text format. The summarization unit can, for example, input the presentation's audio data into a generation AI, which then analyzes the audio data and generates a summary. The generation AI, for example, uses natural language processing technology to extract key points from the audio data and generate a summary. This allows the presentation content to be summarized concisely. The summarization unit can, for example, automatically extract and record key points from a presentation. This allows the speaker to conduct the presentation smoothly. Furthermore, the summarization unit can analyze the presentation content in real time and generate a summary. This allows the speaker to conduct the presentation smoothly.

[0035] The feedback unit provides feedback on the information recorded by the summarization unit. For example, the feedback unit provides the speaker with a summary generated by the summarization unit. Specifically, it displays the summary on the screen so that the speaker can review it. This allows the speaker to conduct the presentation smoothly. The feedback unit notifies the speaker of key points extracted by the summarization unit. This allows the speaker to conduct the presentation smoothly. The feedback unit automatically records audience questions and comments and pops up suggested answers as needed. This allows the speaker to respond quickly to audience questions and comments. The feedback unit performs real-time sentiment analysis of the audience and provides feedback to the presenter. This allows the speaker to understand the audience's reactions in real time and conduct the presentation smoothly. Furthermore, the feedback unit can facilitate the smooth progress of the presentation based on the information recorded by the summarization unit. This allows the speaker to conduct the presentation smoothly.

[0036] The intonation detection unit can detect the speaker's intonation and intonation and transmit that information to the visualization unit. The intonation detection unit can detect intonation and intonation by analyzing, for example, the pitch, volume, and rhythm of the voice. The intonation detection unit can, for example, take a voice signal as input and detect intonation and intonation using a voice analysis algorithm. The intonation detection unit can, for example, input the speaker's voice data into a generation AI, which then analyzes the voice data to detect intonation and intonation. As a result, the accuracy of the visualization is improved when the intonation detection unit detects the speaker's intonation and intonation and transmits that information to the visualization unit.

[0037] The visualization unit can overlay a transparent layer onto the screen based on information transmitted by the intonation detection unit. For example, the visualization unit can visually convey the speaker's intonation and intonation by overlaying the transparent layer onto the screen. The visualization unit can perform visualization using colors such as red or blue. For example, the visualization unit can dynamically change the color and shape of the transparent layer according to the speaker's intonation and intonation. This allows the visualization unit to visually convey the speaker's intonation and intonation by overlaying the transparent layer onto the screen. Some or all of the above processing in the visualization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the visualization unit can input information transmitted by the intonation detection unit into a generation AI, and the generation AI can determine the color and shape of the transparent layer.

[0038] The facial expression detection unit can detect the facial expressions of the audience and transmit that information to the display unit. For example, the facial expression detection unit can capture the facial expressions of the audience using a camera and detect them using a facial expression recognition algorithm. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the facial expression data to detect expressions. For example, the facial expression detection unit can detect changes in the audience's facial expressions in real time. As a result, by detecting the audience's facial expressions and transmitting that information to the display unit, the audience's reactions can be understood in real time. Some or all of the above processing in the facial expression detection unit may be performed using a generating AI, or without using a generating AI. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the facial expression data to detect expressions.

[0039] The display unit can display an expression mark at the edge of the screen based on the information transmitted by the expression detection unit. For example, the display unit can display an expression mark at the edge of the screen. The display unit can dynamically change the type and position of the expression mark according to the audience's expressions. This allows the display unit to visually grasp the audience's level of interest by displaying an expression mark at the edge of the screen. Some or all of the above processing in the display unit may be performed using a generation AI, or not. For example, the display unit can input the information transmitted by the expression detection unit into a generation AI, which can then determine the type and position of the expression mark.

[0040] The summarization unit can record summaries and key points during a presentation and send that information to the feedback unit. The summarization unit can, for example, analyze the content of a presentation in real time and generate a summary. The summarization unit can, for example, input the audio data of a presentation into a generating AI, which can then analyze the audio data and generate a summary. The summarization unit can, for example, automatically extract and record key points of a presentation. This allows for an efficient understanding of the presentation content by having the summarization unit record summaries and key points during the presentation and send that information to the feedback unit. Some or all of the above-described processes in the summarization unit may be performed using a generating AI, or they may be performed without a generating AI. For example, the summarization unit can input the audio data of a presentation into a generating AI, which can then analyze the audio data and generate a summary.

[0041] The feedback unit can provide feedback to the speaker based on the information transmitted by the summarization unit. For example, the feedback unit provides the speaker with a summary generated by the summarization unit. For example, the feedback unit notifies the speaker of key points extracted by the summarization unit. This allows the speaker to understand areas for improvement in their presentation in real time by providing feedback from the feedback unit. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the information transmitted by the summarization unit into a generative AI, which can then determine the content of the feedback.

[0042] The feedback unit can automatically record audience questions and comments and pop up suggested answers as needed. For example, the feedback unit can record audience questions and comments in real time. For example, the feedback unit can analyze the content of questions and comments and present appropriate suggested answers. This streamlines question handling during presentations by allowing the feedback unit to automatically record audience questions and comments and pop up suggested answers as needed. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input audience questions and comments into a generative AI, which can then present appropriate suggested answers.

[0043] The feedback unit can perform real-time sentiment analysis of the audience and provide feedback to the presenter. For example, the feedback unit can analyze the audience's facial expressions and audio data to estimate their emotions. The feedback unit can analyze the audience's emotions in real time using, for example, an emotion estimation algorithm. This improves the quality of the presentation by allowing the feedback unit to perform real-time sentiment analysis of the audience and provide feedback to the presenter. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input audience facial expressions and audio data into a generative AI, which can then estimate the emotions.

[0044] The intonation detection unit can analyze the speaker's past presentation data and learn patterns of intonation change. For example, the intonation detection unit collects the speaker's past presentation data, and the AI ​​learns patterns of intonation change. For example, the intonation detection unit analyzes the speaker's past presentation data and extracts specific intonation patterns. As a result, the detection accuracy is improved by the intonation detection unit analyzing the speaker's past presentation data and learning patterns of intonation change. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intonation detection unit can input the speaker's past presentation data into a generative AI, and the generative AI can learn patterns of intonation change.

[0045] The intonation detection unit can optimize its detection algorithm based on the speaker's language and cultural background when detecting intonation. For example, the intonation detection unit applies a detection algorithm that takes into account the characteristics of intonation based on the speaker's native language. For example, the intonation detection unit adjusts its algorithm to appropriately detect changes in intonation based on the speaker's cultural background. This improves detection accuracy by optimizing the detection algorithm based on the speaker's language and cultural background. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intonation detection unit can input data about the speaker's language and cultural background into a generative AI, which can then optimize the detection algorithm.

[0046] The intonation detection unit can improve its detection accuracy by using the speaker's gestures and body language in conjunction with intonation detection. For example, the intonation detection unit can detect the speaker's hand movements and posture and associate them with changes in intonation. For example, the intonation detection unit can detect the speaker's facial expressions and associate them with changes in intonation. As a result, the intonation detection unit can improve its detection accuracy by using the speaker's gestures and body language in conjunction with intonation detection, thereby detecting changes in intonation more accurately. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intonation detection unit can input data on the speaker's gestures and body language into a generative AI, which can then improve the detection accuracy.

[0047] The intonation detection unit can analyze changes in the speaker's voice tone and pitch in real time when detecting intonation. For example, the intonation detection unit analyzes changes in the speaker's voice tone in real time and identifies changes in intonation. For example, the intonation detection unit analyzes changes in the speaker's voice pitch in real time and identifies changes in intonation. As a result, the intonation detection unit can accurately detect changes in intonation by analyzing changes in the speaker's voice tone and pitch in real time. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generating AI, or without a generating AI. For example, the intonation detection unit can input data on the speaker's voice tone and pitch into a generating AI, which can then analyze it in real time.

[0048] The visualization unit can apply different visualization methods depending on the content of the presentation during visualization. For example, if the content of the presentation is technical, the visualization unit will use graphs and charts for visualization. For example, if the content of the presentation is emotional, the visualization unit will use images and videos for visualization. This improves the effectiveness of the visualization by allowing the visualization unit to apply the most appropriate visualization method for the content of the presentation. Some or all of the above processing in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data about the content of the presentation into a generative AI, which can then determine the most appropriate visualization method.

[0049] The visualization unit can dynamically change the visualization in real time, reflecting the audience's reactions. For example, if the audience shows interest, the visualization unit brightens the colors of the visualization. For example, if the audience is bored, the visualization unit changes the content of the visualization. This allows the visualization unit to dynamically change the visualization in response to the audience's reactions, thereby enhancing the effectiveness of the presentation. Some or all of the above-described processes in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data on the audience's reactions into the generative AI, which can then dynamically change the content of the visualization.

[0050] The visualization unit can perform visualizations in conjunction with the content of the presentation slides. For example, the visualization unit can change the color and shape of the visualization according to the content of the slides. For example, the visualization unit can add data related to the content of the slides to the visualization. This enhances the effectiveness of the visualization by having the visualization unit perform visualizations in conjunction with the content of the presentation slides. Some or all of the above-described processes in the visualization unit may be performed using, for example, a generating AI, or without a generating AI. For example, the visualization unit can input data related to the slide content into a generating AI, and the generating AI can determine the content of the visualization.

[0051] The visualization unit can change the visualization effect according to the intensity of the speaker's voice during visualization. For example, if the speaker's voice is strong, the visualization unit will emphasize the visualization effect. For example, if the speaker's voice is weak, the visualization unit will tone down the visualization effect. In this way, the visualization unit can enhance the effect of visualization by changing the visualization effect according to the intensity of the speaker's voice. Some or all of the above processing in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data regarding the intensity of the speaker's voice into a generative AI, and the generative AI can determine the visualization effect.

[0052] The facial expression detection unit can analyze past facial expression data of the audience and learn patterns of facial expression changes. For example, the facial expression detection unit collects past facial expression data of the audience, and the AI ​​learns patterns of facial expression changes. For example, the facial expression detection unit analyzes past facial expression data of the audience and extracts specific facial expression patterns. As a result, the accuracy of facial expression detection is improved by the facial expression detection unit analyzing past facial expression data of the audience and learning patterns of facial expression changes. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input past facial expression data of the audience into a generative AI, and the generative AI can learn patterns of facial expression changes.

[0053] The facial expression detection unit can optimize its detection algorithm based on attribute information such as the audience's age and gender when detecting facial expressions. For example, the facial expression detection unit applies a detection algorithm that takes facial features into account based on the audience's age. For example, the facial expression detection unit adjusts its algorithm to appropriately detect changes in facial expressions based on the audience's gender. As a result, the accuracy of facial expression detection is improved by the facial expression detection unit optimizing its detection algorithm based on attribute information such as the audience's age and gender. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input data on the audience's age and gender into a generative AI, which can then optimize the detection algorithm.

[0054] The facial expression detection unit can improve its detection accuracy by using the audience's body movements and posture in conjunction with facial expression detection. For example, the facial expression detection unit can detect the audience's body movements and associate them with changes in facial expression. For example, the facial expression detection unit can detect the audience's posture and associate it with changes in facial expression. By improving the accuracy of facial expression detection by using the audience's body movements and posture in conjunction with facial expression detection, the facial expression detection unit can more accurately detect changes in facial expression. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input data on the audience's body movements and posture into a generative AI, which can then detect changes in facial expression.

[0055] The facial expression detection unit can analyze changes in facial expressions by using the audience's voice responses in conjunction with facial expression detection. For example, the facial expression detection unit can detect the audience's voice responses and associate them with changes in facial expressions. For example, the facial expression detection unit can analyze the audience's voice tone and associate it with changes in facial expressions. This allows the facial expression detection unit to more accurately detect changes in facial expressions by using the audience's voice responses in conjunction with facial expression detection. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input data on the audience's voice responses into a generative AI, which can then analyze changes in facial expressions.

[0056] The display unit can dynamically change its display content according to the progress of the presentation. For example, the display unit updates its display content in real time in accordance with the progress of the presentation. For example, the display unit highlights important points according to the progress of the presentation. In this way, the effectiveness of the presentation can be enhanced by the display unit dynamically changing its display content according to the progress of the presentation. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data about the progress of the presentation into the generative AI, and the generative AI can dynamically change the display content.

[0057] The display unit can change the emphasis of the display according to the audience's level of interest during display. For example, if the audience is interested, the display unit increases the emphasis of the display. For example, if the audience is bored, the display unit decreases the emphasis of the display. In this way, the display unit can enhance the effectiveness of the presentation by changing the emphasis of the display according to the audience's level of interest. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data on the audience's level of interest into a generative AI, and the generative AI can determine the emphasis of the display.

[0058] The display unit can display information in conjunction with the content of the presentation slides. For example, the display unit can change its display content according to the content of the slides. For example, the display unit can display information related to the content of the slides. By having the display unit display information in conjunction with the content of the presentation slides, the effectiveness of the presentation can be enhanced. Some or all of the above-described processes in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input data related to the slide content into a generation AI, and the generation AI can determine the display content.

[0059] The display unit can change its display effects in response to the audience's reactions during display. For example, if the audience shows interest, the display unit will emphasize the display effects. For example, if the audience is bored, the display unit will tone down the display effects. In this way, the effectiveness of the presentation can be enhanced by the display unit changing the display effects in response to the audience's reactions. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data on the audience's reactions into a generative AI, which can then determine the display effects.

[0060] The summarization unit can adjust the level of detail in the summary based on the importance of the presentation. For example, the summarization unit will highlight the key points of the presentation. The summarization unit will adjust the level of detail in the summary according to the importance of the presentation. This improves the accuracy of the summary by allowing the summarization unit to adjust the level of detail based on the importance of the presentation. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data on the importance of the presentation into a generative AI, which can then determine the level of detail in the summary.

[0061] The summarization unit can apply different summarization algorithms depending on the presentation category during the summarization process. For example, in the case of a technical presentation, the summarization unit applies a technical summarization algorithm. For example, in the case of an emotional presentation, the summarization unit applies an emotional summarization algorithm. This improves the accuracy of the summary by allowing the summarization unit to apply the most appropriate summarization algorithm for the presentation category. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data about the presentation category into a generative AI, which can then determine the most appropriate summarization algorithm.

[0062] The summarization unit can determine the priority of the summary according to the progress of the presentation. For example, the summarization unit updates the priority of the summary in real time in accordance with the progress of the presentation. For example, the summarization unit prioritizes summarizing important points according to the progress of the presentation. This improves the accuracy of the summary by having the summarization unit determine the priority of the summary according to the progress of the presentation. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data on the progress of the presentation into the generative AI, and the generative AI can determine the priority of the summary.

[0063] The summarization unit can improve the accuracy of its summary by referring to relevant materials from the presentation during the summarization process. For example, the summarization unit can refer to relevant materials from the presentation to improve the accuracy of the summary. For example, the summarization unit can supplement the content of the summary based on relevant materials from the presentation. As a result, the content of the summary becomes more accurate as the summarization unit improves its accuracy by referring to relevant materials from the presentation. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data about relevant materials from the presentation into a generative AI, and the generative AI can determine the content of the summary.

[0064] The feedback unit can adjust the timing of feedback according to the progress of the presentation. For example, the feedback unit can adjust the timing of feedback in real time in accordance with the progress of the presentation. For example, the feedback unit can provide feedback at important points according to the progress of the presentation. This improves the accuracy of feedback by allowing the feedback unit to adjust the timing of feedback according to the progress of the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data about the progress of the presentation into a generative AI, and the generative AI can determine the timing of the feedback.

[0065] The feedback unit can adjust the level of detail in the feedback based on the importance of the presentation. For example, the feedback unit may highlight key points of the presentation when providing feedback. The feedback unit adjusts the level of detail in the feedback according to the importance of the presentation. This improves the accuracy of the feedback by allowing the feedback unit to adjust the level of detail based on the importance of the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data on the importance of the presentation into a generative AI, which can then determine the level of detail in the feedback.

[0066] The feedback unit can improve the accuracy of its feedback by referring to relevant materials in the presentation. For example, the feedback unit can refer to relevant materials in the presentation to improve the accuracy of its feedback. For example, the feedback unit can supplement the content of its feedback based on relevant materials in the presentation. As a result, the content of the feedback becomes more accurate as the feedback unit improves the accuracy of its feedback by referring to relevant materials in the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data related to the relevant materials in the presentation into a generative AI, and the generative AI can determine the content of the feedback.

[0067] The feedback unit can dynamically change the content of the feedback during the feedback process according to the progress of the presentation. For example, the feedback unit changes the content of the feedback in real time in accordance with the progress of the presentation. For example, the feedback unit changes the content of the feedback at important points according to the progress of the presentation. This improves the accuracy of the feedback by allowing the feedback unit to dynamically change the content of the feedback according to the progress of the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data about the progress of the presentation into a generative AI, and the generative AI can determine the content of the feedback.

[0068] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0069] The autonomous AI agent system can evaluate the user's slide design during the presentation preparation phase and suggest visual improvements. For example, if the slide layout is difficult to read, it can suggest a more effective layout. If the color combination is inappropriate, it can suggest a more visually appealing color combination. If the font size or style is inappropriate, it can suggest a more readable font size or style. This allows users to improve the visual quality of their presentations.

[0070] The autonomous AI agent system can detect a speaker's gestures during a presentation and evaluate their appropriateness. For example, if a speaker uses their hands to explain something, the system can evaluate whether those gestures are appropriate. It can also detect whether the speaker is making eye contact and evaluate the appropriateness of their gaze. Furthermore, it can detect whether the speaker's posture is appropriate and evaluate its appropriateness. This allows speakers to improve their gestures and posture, leading to more effective presentations.

[0071] An autonomous AI agent system can suggest interactive elements to capture the audience's attention during a presentation. For example, it can insert quizzes or surveys to engage the audience, ask questions and collect answers in real time, and dynamically modify the presentation content based on audience responses. This helps maintain audience engagement and enhances the effectiveness of the presentation.

[0072] An autonomous AI agent system can evaluate a user's performance after a presentation and provide feedback on areas for improvement. For example, it can assess whether the speaker's speaking speed is appropriate, whether their intonation and intonation are appropriate, and whether their gestures and posture are appropriate. This allows users to improve their presentation skills.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The intonation detection unit detects the speaker's intonation and intonation. The intonation detection unit detects intonation and intonation by analyzing the pitch, volume, rhythm, etc., of the voice. For example, it can take a voice signal as input and use a voice analysis algorithm to detect intonation and intonation. Alternatively, the speaker's voice data can be input to a generating AI, which then analyzes the voice data to detect intonation and intonation. Step 2: The visualization unit performs visualization based on the information detected by the intonation detection unit. The visualization unit visually conveys the speaker's intonation and intonation by overlaying a transparent layer on the screen. For example, visualization can be performed using red or blue colors, and the color and shape of the transparent layer can be dynamically changed according to the speaker's intonation and intonation. Step 3: The facial expression detection unit detects the audience's facial expressions. The facial expression detection unit uses a camera to capture the audience's facial expressions and detects them using a facial expression recognition algorithm. For example, the audience's facial expression data can be input into a generating AI, which then analyzes the data to detect expressions. Furthermore, changes in the audience's facial expressions can be detected in real time. Step 4: The display unit displays information based on the information detected by the facial expression detection unit. The display unit displays facial expression marks at the edge of the screen. For example, the type and position of the facial expression marks can be dynamically changed according to the audience's facial expressions. In addition, the audience's facial expression data can be input into a generating AI, which analyzes the facial expression data to determine the display content. Step 5: The summarization unit records summaries and key points from the presentation. The summarization unit analyzes the presentation content in real time and generates a summary. For example, the audio data of the presentation can be input into the generation AI, which analyzes the audio data and generates a summary. It can also automatically extract and record key points from the presentation. Step 6: The feedback unit provides feedback on the information recorded by the summarization unit. The feedback unit provides the speaker with the summary generated by the summarization unit. For example, it notifies the speaker of the key points extracted by the summarization unit. It can also automatically record audience questions and comments and pop up suggested answers as needed. Furthermore, it can perform real-time sentiment analysis of the audience and provide feedback to the presenter.

[0075] (Example of form 2) An autonomous AI agent system according to an embodiment of the present invention is a system that provides consistent support in online meetings, from preparation to delivery and feedback of presentations. This autonomous AI agent system provides real-time feedback from the stage when the user is preparing presentation materials. During the presentation, it detects the speaker's intonation and pitch and visualizes how the message is being received by overlaying transparent layers such as "passionate = red" and "calm = blue" on the screen. It also detects the speaking speed and displays a periodic waveform, allowing the presenter to control the progress of the presentation. Furthermore, it detects the level of interest from the audience's camera expressions and displays the level of interest by displaying an expression mark at the edge of the screen, visualizing how much attention the audience is receiving. The autonomous AI agent is always running in the background, recording summaries and important points during the presentation in real time and providing feedback to the speaker. It also automatically records audience questions and comments and pops up candidate answers as needed. Furthermore, it performs real-time sentiment analysis of the audience and provides feedback to the presenter. It immediately notifies the presenter if interest is waning or, conversely, if the audience is captivated, and provides flexible support. This allows the presenter to objectively evaluate their presentation and make adjustments as needed. This allows autonomous AI agent systems to improve the quality of presentations.

[0076] The autonomous AI agent system according to this embodiment includes an intonation detection unit, a visualization unit, an expression detection unit, a display unit, a summarization unit, and a feedback unit. The intonation detection unit detects the speaker's intonation and intonation. The intonation detection unit detects intonation and intonation by analyzing, for example, the pitch, volume, and rhythm of the voice. The intonation detection unit can, for example, take a voice signal as input and detect intonation and intonation using a voice analysis algorithm. The intonation detection unit can, for example, input the speaker's voice data into a generating AI, and the generating AI can analyze the voice data to detect intonation and intonation. The visualization unit performs visualization based on the information detected by the intonation detection unit. The visualization unit visually conveys the speaker's intonation and intonation by, for example, overlaying a transparent layer on the screen. The visualization unit can perform visualization using, for example, red or blue colors. The visualization unit can dynamically change the color and shape of the transparent layer according to the speaker's intonation and intonation. The facial expression detection unit detects the facial expressions of the audience. For example, the facial expression detection unit uses a camera to capture the audience's facial expressions and detects them using a facial expression recognition algorithm. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the data to detect expressions. For example, the facial expression detection unit can detect changes in the audience's facial expressions in real time. The display unit displays information based on the information detected by the facial expression detection unit. For example, the display unit displays facial expression marks at the edge of the screen. For example, the display unit can dynamically change the type and position of the facial expression marks according to the audience's facial expressions. For example, the display unit can input the audience's facial expression data into a generating AI, which can analyze the data to determine the display content. The summarization unit records summaries and important points during the presentation. For example, the summarization unit analyzes the content of the presentation in real time and generates a summary. For example, the summarization unit can input the audio data of the presentation into a generating AI, which can analyze the audio data to generate a summary. For example, the summarization unit can automatically extract and record important points of the presentation.The feedback unit provides feedback on the information recorded by the summarization unit. For example, the feedback unit provides the speaker with a summary generated by the summarization unit. For example, the feedback unit notifies the speaker of key points extracted by the summarization unit. For example, the feedback unit automatically records audience questions and comments and pops up suggested answers as needed. For example, the feedback unit performs real-time sentiment analysis of the audience and provides feedback to the presenter. In this way, the autonomous AI agent system according to the embodiment can improve the quality of the presentation.

[0077] The intonation detection unit detects the speaker's intonation and intonation. For example, it detects intonation and intonation by analyzing the pitch, volume, and rhythm of the speech. Specifically, it digitizes the speech signal and performs frequency analysis to analyze changes in pitch and volume in detail. This allows for a more accurate understanding of the speaker's emotions and intentions. The intonation detection unit can, for example, take a speech signal as input and detect intonation and intonation using a speech analysis algorithm. The speech analysis algorithm analyzes the speech signal using, for example, Fourier transforms and Mel-frequency cepstrum coefficients (MFCCs) to extract features. This allows for highly accurate capture of the speaker's speech characteristics. The intonation detection unit can, for example, input speaker speech data into a generating AI, which then analyzes the speech data to detect intonation and intonation. The generating AI, for example, uses a deep learning-based speech recognition model to learn intonation and intonation patterns from the speech data. This allows for highly accurate analysis of the speaker's emotions and intentions and provides real-time feedback.

[0078] The visualization unit performs visualization based on information detected by the intonation detection unit. For example, the visualization unit visually conveys the speaker's intonation and intonation by overlaying a transparent layer on the screen. Specifically, it dynamically changes the color and shape of the transparent layer in response to changes in intonation. For example, it changes to red when the speaker's voice rises and to blue when their voice falls. Furthermore, the transparency and shape of the transparent layer can be changed according to the strength of the intonation. The visualization unit can use colors such as red and blue for visualization, making it easier for the audience to visually understand the speaker's emotions and intentions. The visualization unit can dynamically change the color and shape of the transparent layer in response to the speaker's intonation and intonation, enabling the real-time visual conveyance of the speaker's emotions and intentions, thereby enhancing the effectiveness of the presentation. Additionally, the visualization unit can automatically generate visualization patterns based on data from the intonation detection unit. This allows for the provision of optimal visualizations tailored to the speaker's intonation and intonation.

[0079] The facial expression detection unit detects the facial expressions of the audience. For example, the facial expression detection unit uses a camera to capture the audience's facial expressions and detects them using a facial expression recognition algorithm. Specifically, it takes image data captured by the camera as input and extracts facial feature points. This allows for real-time detection of changes in the audience's facial expressions. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the data and detect expressions. The generating AI, for example, uses a deep learning-based facial expression recognition model to learn emotional patterns from the facial expression data. This allows for high-precision analysis of the audience's emotions and reactions and provides real-time feedback. For example, the facial expression detection unit can detect changes in the audience's facial expressions in real time. This allows the speaker to grasp the audience's reactions in real time and adjust the progress of the presentation. Furthermore, the facial expression detection unit can use multiple cameras to capture the audience's facial expressions from multiple angles. This allows for more accurate detection of the audience's facial expressions and enhances the effectiveness of the presentation.

[0080] The display unit displays information based on the information detected by the facial expression detection unit. For example, the display unit displays facial expression marks at the edge of the screen. Specifically, it displays facial expression marks such as smiles, surprise, and confusion according to the audience's facial expressions. This allows the speaker to visually grasp the audience's reactions. For example, the display unit can dynamically change the type and position of the facial expression marks according to the audience's facial expressions. This allows the speaker to grasp the audience's reactions in real time and adjust the progress of the presentation. For example, the display unit can input the audience's facial expression data into a generating AI, which analyzes the facial expression data and determines the display content. For example, the generating AI uses a facial expression recognition model using deep learning to learn emotional patterns from the facial expression data. This allows it to analyze the audience's emotions and reactions with high accuracy and update the display content in real time. Furthermore, the display unit can automatically adjust the display content according to the audience's reactions. This allows the speaker to grasp the audience's reactions in real time and improve the effectiveness of the presentation.

[0081] The summarization unit records summaries and key points during a presentation. For example, the summarization unit analyzes the presentation content in real time and generates a summary. Specifically, it takes the presentation's audio data as input and converts it into text data using a speech recognition algorithm. This allows the presentation content to be recorded in text format. The summarization unit can, for example, input the presentation's audio data into a generation AI, which then analyzes the audio data and generates a summary. The generation AI, for example, uses natural language processing technology to extract key points from the audio data and generate a summary. This allows the presentation content to be summarized concisely. The summarization unit can, for example, automatically extract and record key points from a presentation. This allows the speaker to conduct the presentation smoothly. Furthermore, the summarization unit can analyze the presentation content in real time and generate a summary. This allows the speaker to conduct the presentation smoothly.

[0082] The feedback unit provides feedback on the information recorded by the summarization unit. For example, the feedback unit provides the speaker with a summary generated by the summarization unit. Specifically, it displays the summary on the screen so that the speaker can review it. This allows the speaker to conduct the presentation smoothly. The feedback unit notifies the speaker of key points extracted by the summarization unit. This allows the speaker to conduct the presentation smoothly. The feedback unit automatically records audience questions and comments and pops up suggested answers as needed. This allows the speaker to respond quickly to audience questions and comments. The feedback unit performs real-time sentiment analysis of the audience and provides feedback to the presenter. This allows the speaker to understand the audience's reactions in real time and conduct the presentation smoothly. Furthermore, the feedback unit can facilitate the smooth progress of the presentation based on the information recorded by the summarization unit. This allows the speaker to conduct the presentation smoothly.

[0083] The intonation detection unit can detect the speaker's intonation and intonation and transmit that information to the visualization unit. The intonation detection unit can detect intonation and intonation by analyzing, for example, the pitch, volume, and rhythm of the voice. The intonation detection unit can, for example, take a voice signal as input and detect intonation and intonation using a voice analysis algorithm. The intonation detection unit can, for example, input the speaker's voice data into a generation AI, which then analyzes the voice data to detect intonation and intonation. As a result, the accuracy of the visualization is improved when the intonation detection unit detects the speaker's intonation and intonation and transmits that information to the visualization unit.

[0084] The visualization unit can overlay a transparent layer onto the screen based on information transmitted by the intonation detection unit. For example, the visualization unit can visually convey the speaker's intonation and intonation by overlaying the transparent layer onto the screen. The visualization unit can perform visualization using colors such as red or blue. For example, the visualization unit can dynamically change the color and shape of the transparent layer according to the speaker's intonation and intonation. This allows the visualization unit to visually convey the speaker's intonation and intonation by overlaying the transparent layer onto the screen. Some or all of the above processing in the visualization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the visualization unit can input information transmitted by the intonation detection unit into a generation AI, and the generation AI can determine the color and shape of the transparent layer.

[0085] The facial expression detection unit can detect the facial expressions of the audience and transmit that information to the display unit. For example, the facial expression detection unit can capture the facial expressions of the audience using a camera and detect them using a facial expression recognition algorithm. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the facial expression data to detect expressions. For example, the facial expression detection unit can detect changes in the audience's facial expressions in real time. As a result, by detecting the audience's facial expressions and transmitting that information to the display unit, the audience's reactions can be understood in real time. Some or all of the above processing in the facial expression detection unit may be performed using a generating AI, or without using a generating AI. For example, the facial expression detection unit can input the audience's facial expression data into a generating AI, which can analyze the facial expression data to detect expressions.

[0086] The display unit can display an expression mark at the edge of the screen based on the information transmitted by the expression detection unit. For example, the display unit can display an expression mark at the edge of the screen. The display unit can dynamically change the type and position of the expression mark according to the audience's expressions. This allows the display unit to visually grasp the audience's level of interest by displaying an expression mark at the edge of the screen. Some or all of the above processing in the display unit may be performed using a generation AI, or not. For example, the display unit can input the information transmitted by the expression detection unit into a generation AI, which can then determine the type and position of the expression mark.

[0087] The summarization unit can record summaries and key points during a presentation and send that information to the feedback unit. The summarization unit can, for example, analyze the content of a presentation in real time and generate a summary. The summarization unit can, for example, input the audio data of a presentation into a generating AI, which can then analyze the audio data and generate a summary. The summarization unit can, for example, automatically extract and record key points of a presentation. This allows for an efficient understanding of the presentation content by having the summarization unit record summaries and key points during the presentation and send that information to the feedback unit. Some or all of the above-described processes in the summarization unit may be performed using a generating AI, or they may be performed without a generating AI. For example, the summarization unit can input the audio data of a presentation into a generating AI, which can then analyze the audio data and generate a summary.

[0088] The feedback unit can provide feedback to the speaker based on the information transmitted by the summarization unit. For example, the feedback unit provides the speaker with a summary generated by the summarization unit. For example, the feedback unit notifies the speaker of key points extracted by the summarization unit. This allows the speaker to understand areas for improvement in their presentation in real time by providing feedback from the feedback unit. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input the information transmitted by the summarization unit into a generative AI, which can then determine the content of the feedback.

[0089] The feedback unit can automatically record audience questions and comments and pop up suggested answers as needed. For example, the feedback unit can record audience questions and comments in real time. For example, the feedback unit can analyze the content of questions and comments and present appropriate suggested answers. This streamlines question handling during presentations by allowing the feedback unit to automatically record audience questions and comments and pop up suggested answers as needed. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input audience questions and comments into a generative AI, which can then present appropriate suggested answers.

[0090] The feedback unit can perform real-time sentiment analysis of the audience and provide feedback to the presenter. For example, the feedback unit can analyze the audience's facial expressions and audio data to estimate their emotions. The feedback unit can analyze the audience's emotions in real time using, for example, an emotion estimation algorithm. This improves the quality of the presentation by allowing the feedback unit to perform real-time sentiment analysis of the audience and provide feedback to the presenter. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input audience facial expressions and audio data into a generative AI, which can then estimate the emotions.

[0091] The intonation detection unit can estimate the speaker's emotions and adjust the accuracy of intonation detection based on the estimated emotions. For example, the intonation detection unit analyzes the speaker's voice data and estimates the emotions. For example, the intonation detection unit analyzes the speaker's emotions in real time using an emotion estimation algorithm. This improves detection accuracy by allowing the intonation detection unit to estimate the speaker's emotions and adjust the accuracy of intonation detection based on the estimated emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the intonation detection unit may be performed using a generative AI, or not using a generative AI. For example, the intonation detection unit can input the speaker's voice data into a generative AI, which can then estimate the emotions.

[0092] The intonation detection unit can analyze the speaker's past presentation data and learn patterns of intonation change. For example, the intonation detection unit collects the speaker's past presentation data, and the AI ​​learns patterns of intonation change. For example, the intonation detection unit analyzes the speaker's past presentation data and extracts specific intonation patterns. As a result, the detection accuracy is improved by the intonation detection unit analyzing the speaker's past presentation data and learning patterns of intonation change. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intonation detection unit can input the speaker's past presentation data into a generative AI, and the generative AI can learn patterns of intonation change.

[0093] The intonation detection unit can optimize its detection algorithm based on the speaker's language and cultural background when detecting intonation. For example, the intonation detection unit applies a detection algorithm that takes into account the characteristics of intonation based on the speaker's native language. For example, the intonation detection unit adjusts its algorithm to appropriately detect changes in intonation based on the speaker's cultural background. This improves detection accuracy by optimizing the detection algorithm based on the speaker's language and cultural background. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intonation detection unit can input data about the speaker's language and cultural background into a generative AI, which can then optimize the detection algorithm.

[0094] The intonation detection unit can estimate the speaker's emotions and identify emphasis in the intonation based on the estimated emotions. For example, the intonation detection unit analyzes the speaker's voice data and estimates the emotions. For example, the intonation detection unit analyzes the speaker's emotions in real time using an emotion estimation algorithm. This improves the accuracy of the visualization by allowing the intonation detection unit to estimate the speaker's emotions and identify emphasis in the intonation based on the estimated emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the intonation detection unit may be performed using a generative AI, or not using a generative AI. For example, the intonation detection unit can input the speaker's voice data into a generative AI, which can then estimate the emotions.

[0095] The intonation detection unit can improve its detection accuracy by using the speaker's gestures and body language in conjunction with intonation detection. For example, the intonation detection unit can detect the speaker's hand movements and posture and associate them with changes in intonation. For example, the intonation detection unit can detect the speaker's facial expressions and associate them with changes in intonation. As a result, the intonation detection unit can improve its detection accuracy by using the speaker's gestures and body language in conjunction with intonation detection, thereby detecting changes in intonation more accurately. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intonation detection unit can input data on the speaker's gestures and body language into a generative AI, which can then improve the detection accuracy.

[0096] The intonation detection unit can analyze changes in the speaker's voice tone and pitch in real time when detecting intonation. For example, the intonation detection unit analyzes changes in the speaker's voice tone in real time and identifies changes in intonation. For example, the intonation detection unit analyzes changes in the speaker's voice pitch in real time and identifies changes in intonation. As a result, the intonation detection unit can accurately detect changes in intonation by analyzing changes in the speaker's voice tone and pitch in real time. Some or all of the above processing in the intonation detection unit may be performed using, for example, a generating AI, or without a generating AI. For example, the intonation detection unit can input data on the speaker's voice tone and pitch into a generating AI, which can then analyze it in real time.

[0097] The visualization unit can estimate the speaker's emotions and adjust the color and shape of the visualization based on the estimated emotions. For example, if the speaker is excited, the visualization unit changes the color of the visualization to red. For example, if the speaker is calm, the visualization unit changes the color of the visualization to blue. This improves the effectiveness of the visualization by allowing the visualization unit to adjust the color and shape of the visualization based on the speaker's emotions. Some or all of the above processing in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data about the speaker's emotions into a generative AI, which can then determine the color and shape of the visualization.

[0098] The visualization unit can apply different visualization methods depending on the content of the presentation during visualization. For example, if the content of the presentation is technical, the visualization unit will use graphs and charts for visualization. For example, if the content of the presentation is emotional, the visualization unit will use images and videos for visualization. This improves the effectiveness of the visualization by allowing the visualization unit to apply the most appropriate visualization method for the content of the presentation. Some or all of the above processing in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data about the content of the presentation into a generative AI, which can then determine the most appropriate visualization method.

[0099] The visualization unit can dynamically change the visualization in real time, reflecting the audience's reactions. For example, if the audience shows interest, the visualization unit brightens the colors of the visualization. For example, if the audience is bored, the visualization unit changes the content of the visualization. This allows the visualization unit to dynamically change the visualization in response to the audience's reactions, thereby enhancing the effectiveness of the presentation. Some or all of the above-described processes in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data on the audience's reactions into the generative AI, which can then dynamically change the content of the visualization.

[0100] The visualization unit can estimate the speaker's emotions and adjust the transparency of the visualization based on the estimated emotions. For example, if the speaker is excited, the visualization unit will lower the transparency of the visualization to emphasize that emotion. For example, if the speaker is calm, the visualization unit will increase the transparency of the visualization to give a calm impression. In this way, the visualization unit can enhance the effect of the visualization by adjusting the transparency of the visualization based on the speaker's emotions. Some or all of the above processing in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data about the speaker's emotions into a generative AI, and the generative AI can determine the transparency of the visualization.

[0101] The visualization unit can perform visualizations in conjunction with the content of the presentation slides. For example, the visualization unit can change the color and shape of the visualization according to the content of the slides. For example, the visualization unit can add data related to the content of the slides to the visualization. This enhances the effectiveness of the visualization by having the visualization unit perform visualizations in conjunction with the content of the presentation slides. Some or all of the above-described processes in the visualization unit may be performed using, for example, a generating AI, or without a generating AI. For example, the visualization unit can input data related to the slide content into a generating AI, and the generating AI can determine the content of the visualization.

[0102] The visualization unit can change the visualization effect according to the intensity of the speaker's voice during visualization. For example, if the speaker's voice is strong, the visualization unit will emphasize the visualization effect. For example, if the speaker's voice is weak, the visualization unit will tone down the visualization effect. In this way, the visualization unit can enhance the effect of visualization by changing the visualization effect according to the intensity of the speaker's voice. Some or all of the above processing in the visualization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the visualization unit can input data regarding the intensity of the speaker's voice into a generative AI, and the generative AI can determine the visualization effect.

[0103] The facial expression detection unit can estimate the emotions of the audience and adjust the accuracy of facial expression detection based on the estimated emotions. For example, the facial expression detection unit analyzes the audience's facial expression data and estimates their emotions. For example, the facial expression detection unit analyzes the audience's emotions in real time using an emotion estimation algorithm. This improves the accuracy of facial expression detection by allowing the facial expression detection unit to adjust the accuracy of facial expression detection based on the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the facial expression detection unit may be performed using a generative AI, or not using a generative AI. For example, the facial expression detection unit can input the audience's facial expression data into a generative AI, which can then estimate the emotions.

[0104] The facial expression detection unit can analyze past facial expression data of the audience and learn patterns of facial expression changes. For example, the facial expression detection unit collects past facial expression data of the audience, and the AI ​​learns patterns of facial expression changes. For example, the facial expression detection unit analyzes past facial expression data of the audience and extracts specific facial expression patterns. As a result, the accuracy of facial expression detection is improved by the facial expression detection unit analyzing past facial expression data of the audience and learning patterns of facial expression changes. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input past facial expression data of the audience into a generative AI, and the generative AI can learn patterns of facial expression changes.

[0105] The facial expression detection unit can optimize its detection algorithm based on attribute information such as the audience's age and gender when detecting facial expressions. For example, the facial expression detection unit applies a detection algorithm that takes facial features into account based on the audience's age. For example, the facial expression detection unit adjusts its algorithm to appropriately detect changes in facial expressions based on the audience's gender. As a result, the accuracy of facial expression detection is improved by the facial expression detection unit optimizing its detection algorithm based on attribute information such as the audience's age and gender. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input data on the audience's age and gender into a generative AI, which can then optimize the detection algorithm.

[0106] The facial expression detection unit can estimate the emotions of the audience and display changes in facial expressions in real time based on the estimated emotions. For example, the facial expression detection unit analyzes the audience's facial expression data and estimates their emotions. For example, the facial expression detection unit analyzes the audience's emotions in real time using an emotion estimation algorithm. This enhances the effectiveness of the presentation by allowing the facial expression detection unit to display changes in facial expressions in real time based on the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the facial expression detection unit may be performed using a generative AI, or not using a generative AI. For example, the facial expression detection unit can input the audience's facial expression data into a generative AI, which can then estimate the emotions.

[0107] The facial expression detection unit can improve its detection accuracy by using the audience's body movements and posture in conjunction with facial expression detection. For example, the facial expression detection unit can detect the audience's body movements and associate them with changes in facial expression. For example, the facial expression detection unit can detect the audience's posture and associate it with changes in facial expression. By improving the accuracy of facial expression detection by using the audience's body movements and posture in conjunction with facial expression detection, the facial expression detection unit can more accurately detect changes in facial expression. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input data on the audience's body movements and posture into a generative AI, which can then detect changes in facial expression.

[0108] The facial expression detection unit can analyze changes in facial expressions by using the audience's voice responses in conjunction with facial expression detection. For example, the facial expression detection unit can detect the audience's voice responses and associate them with changes in facial expressions. For example, the facial expression detection unit can analyze the audience's voice tone and associate it with changes in facial expressions. This allows the facial expression detection unit to more accurately detect changes in facial expressions by using the audience's voice responses in conjunction with facial expression detection. Some or all of the above processing in the facial expression detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression detection unit can input data on the audience's voice responses into a generative AI, which can then analyze changes in facial expressions.

[0109] The display unit can estimate the audience's emotions and adjust the displayed content based on those emotions. For example, if the audience is excited, the display unit will emphasize the displayed content. For example, if the audience is calm, the display unit will make the displayed content more subdued. In this way, the display unit can enhance the effectiveness of the presentation by adjusting the displayed content based on the audience's emotions. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data about the audience's emotions into a generative AI, which can then determine the displayed content.

[0110] The display unit can dynamically change its display content according to the progress of the presentation. For example, the display unit updates its display content in real time in accordance with the progress of the presentation. For example, the display unit highlights important points according to the progress of the presentation. In this way, the effectiveness of the presentation can be enhanced by the display unit dynamically changing its display content according to the progress of the presentation. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data about the progress of the presentation into the generative AI, and the generative AI can dynamically change the display content.

[0111] The display unit can change the emphasis of the display according to the audience's level of interest during display. For example, if the audience is interested, the display unit increases the emphasis of the display. For example, if the audience is bored, the display unit decreases the emphasis of the display. In this way, the display unit can enhance the effectiveness of the presentation by changing the emphasis of the display according to the audience's level of interest. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data on the audience's level of interest into a generative AI, and the generative AI can determine the emphasis of the display.

[0112] The display unit can estimate the audience's emotions and adjust the timing of the display based on the estimated emotions. For example, if the audience is excited, the display unit will advance the timing of the display. For example, if the audience is calm, the display unit will delay the timing of the display. This allows the display unit to enhance the effectiveness of the presentation by adjusting the timing of the display based on the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 display unit may be performed using a generative AI, or not using a generative AI. For example, the display unit can input data about the audience's emotions into a generative AI, which can then determine the timing of the display.

[0113] The display unit can display information in conjunction with the content of the presentation slides. For example, the display unit can change its display content according to the content of the slides. For example, the display unit can display information related to the content of the slides. By having the display unit display information in conjunction with the content of the presentation slides, the effectiveness of the presentation can be enhanced. Some or all of the above-described processes in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input data related to the slide content into a generation AI, and the generation AI can determine the display content.

[0114] The display unit can change its display effects in response to the audience's reactions during display. For example, if the audience shows interest, the display unit will emphasize the display effects. For example, if the audience is bored, the display unit will tone down the display effects. In this way, the effectiveness of the presentation can be enhanced by the display unit changing the display effects in response to the audience's reactions. Some or all of the above processing in the display unit may be performed using, for example, a generative AI, or without a generative AI. For example, the display unit can input data on the audience's reactions into a generative AI, which can then determine the display effects.

[0115] The summarization unit can estimate the speaker's emotions during a presentation and adjust the content of the summary based on the estimated emotions. For example, the summarization unit analyzes the speaker's voice data to estimate emotions. The summarization unit analyzes the speaker's emotions in real time using, for example, an emotion estimation algorithm. This improves the accuracy of the summary by allowing the summarization unit to adjust the content of the summary based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the summarization unit can input the speaker's voice data into a generative AI, which can then estimate emotions.

[0116] The summarization unit can adjust the level of detail in the summary based on the importance of the presentation. For example, the summarization unit will highlight the key points of the presentation. The summarization unit will adjust the level of detail in the summary according to the importance of the presentation. This improves the accuracy of the summary by allowing the summarization unit to adjust the level of detail based on the importance of the presentation. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data on the importance of the presentation into a generative AI, which can then determine the level of detail in the summary.

[0117] The summarization unit can apply different summarization algorithms depending on the presentation category during the summarization process. For example, in the case of a technical presentation, the summarization unit applies a technical summarization algorithm. For example, in the case of an emotional presentation, the summarization unit applies an emotional summarization algorithm. This improves the accuracy of the summary by allowing the summarization unit to apply the most appropriate summarization algorithm for the presentation category. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data about the presentation category into a generative AI, which can then determine the most appropriate summarization algorithm.

[0118] The summarization unit can estimate the speaker's emotions during a presentation and adjust the length of the summary based on the estimated emotions. For example, the summarization unit analyzes the speaker's voice data to estimate emotions. The summarization unit analyzes the speaker's emotions in real time, for example, using an emotion estimation algorithm. This improves the accuracy of the summary by allowing the summarization unit to adjust the length of the summary based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using a generative AI, or not using a generative AI. For example, the summarization unit can input the speaker's voice data into a generative AI, which can then estimate emotions.

[0119] The summarization unit can determine the priority of the summary according to the progress of the presentation. For example, the summarization unit updates the priority of the summary in real time in accordance with the progress of the presentation. For example, the summarization unit prioritizes summarizing important points according to the progress of the presentation. This improves the accuracy of the summary by having the summarization unit determine the priority of the summary according to the progress of the presentation. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data on the progress of the presentation into the generative AI, and the generative AI can determine the priority of the summary.

[0120] The summarization unit can improve the accuracy of its summary by referring to relevant materials from the presentation during the summarization process. For example, the summarization unit can refer to relevant materials from the presentation to improve the accuracy of the summary. For example, the summarization unit can supplement the content of the summary based on relevant materials from the presentation. As a result, the content of the summary becomes more accurate as the summarization unit improves its accuracy by referring to relevant materials from the presentation. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input data about relevant materials from the presentation into a generative AI, and the generative AI can determine the content of the summary.

[0121] The feedback unit can estimate the audience's emotions and adjust the content of the feedback based on the estimated emotions. For example, the feedback unit can analyze the audience's facial expression data to estimate emotions. The feedback unit can analyze the audience's emotions in real time using, for example, an emotion estimation algorithm. This improves the accuracy of the feedback by allowing the feedback unit to adjust the content of the feedback based on the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the audience's facial expression data into a generative AI, which can then estimate emotions.

[0122] The feedback unit can adjust the timing of feedback according to the progress of the presentation. For example, the feedback unit can adjust the timing of feedback in real time in accordance with the progress of the presentation. For example, the feedback unit can provide feedback at important points according to the progress of the presentation. This improves the accuracy of feedback by allowing the feedback unit to adjust the timing of feedback according to the progress of the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data about the progress of the presentation into a generative AI, and the generative AI can determine the timing of the feedback.

[0123] The feedback unit can adjust the level of detail in the feedback based on the importance of the presentation. For example, the feedback unit may highlight key points of the presentation when providing feedback. The feedback unit adjusts the level of detail in the feedback according to the importance of the presentation. This improves the accuracy of the feedback by allowing the feedback unit to adjust the level of detail based on the importance of the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data on the importance of the presentation into a generative AI, which can then determine the level of detail in the feedback.

[0124] The feedback unit can estimate the audience's emotions and determine the priority of feedback based on the estimated emotions. For example, the feedback unit can analyze the audience's facial expression data to estimate emotions. The feedback unit can analyze the audience's emotions in real time using, for example, an emotion estimation algorithm. This improves the accuracy of feedback by allowing the feedback unit to determine the priority of feedback based on the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the audience's facial expression data into a generative AI, which can then estimate emotions.

[0125] The feedback unit can improve the accuracy of its feedback by referring to relevant materials in the presentation. For example, the feedback unit can refer to relevant materials in the presentation to improve the accuracy of its feedback. For example, the feedback unit can supplement the content of its feedback based on relevant materials in the presentation. As a result, the content of the feedback becomes more accurate as the feedback unit improves the accuracy of its feedback by referring to relevant materials in the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data related to the relevant materials in the presentation into a generative AI, and the generative AI can determine the content of the feedback.

[0126] The feedback unit can dynamically change the content of the feedback during the feedback process according to the progress of the presentation. For example, the feedback unit changes the content of the feedback in real time in accordance with the progress of the presentation. For example, the feedback unit changes the content of the feedback at important points according to the progress of the presentation. This improves the accuracy of the feedback by allowing the feedback unit to dynamically change the content of the feedback according to the progress of the presentation. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the feedback unit can input data about the progress of the presentation into a generative AI, and the generative AI can determine the content of the feedback.

[0127] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0128] The autonomous AI agent system can evaluate the user's slide design during the presentation preparation phase and suggest visual improvements. For example, if the slide layout is difficult to read, it can suggest a more effective layout. If the color combination is inappropriate, it can suggest a more visually appealing color combination. If the font size or style is inappropriate, it can suggest a more readable font size or style. This allows users to improve the visual quality of their presentations.

[0129] The autonomous AI agent system can detect a speaker's gestures during a presentation and evaluate their appropriateness. For example, if a speaker uses their hands to explain something, the system can evaluate whether those gestures are appropriate. It can also detect whether the speaker is making eye contact and evaluate the appropriateness of their gaze. Furthermore, it can detect whether the speaker's posture is appropriate and evaluate its appropriateness. This allows speakers to improve their gestures and posture, leading to more effective presentations.

[0130] An autonomous AI agent system can suggest interactive elements to capture the audience's attention during a presentation. For example, it can insert quizzes or surveys to engage the audience, ask questions and collect answers in real time, and dynamically modify the presentation content based on audience responses. This helps maintain audience engagement and enhances the effectiveness of the presentation.

[0131] An autonomous AI agent system can evaluate a user's performance after a presentation and provide feedback on areas for improvement. For example, it can assess whether the speaker's speaking speed is appropriate, whether their intonation and intonation are appropriate, and whether their gestures and posture are appropriate. This allows users to improve their presentation skills.

[0132] An autonomous AI agent system can display the audience's level of interest in real time during a presentation and provide feedback to the speaker. For example, if the audience is interested, a green mark will appear on the screen. If the audience is bored, a red mark will appear on the screen. Based on the audience's level of interest, the system will suggest appropriate actions to the speaker. This allows the speaker to maintain the audience's interest and enhance the effectiveness of the presentation.

[0133] An autonomous AI agent system can estimate a speaker's emotions during a presentation and provide feedback based on those emotions. For example, if the speaker is nervous, it can offer advice on how to relax. If the speaker is excited, it can offer advice on how to calm down. If the speaker is confident, it can encourage them to continue. This allows speakers to control their emotions and deliver more effective presentations.

[0134] An autonomous AI agent system can estimate the audience's emotions during a presentation and dynamically modify the presentation content based on those emotions. For example, if the audience shows interest, it can add more detailed explanations; if they are bored, it can change the topic; and if they are confused, it can simplify the explanations. This allows the presentation content to be tailored to the audience's emotions, thereby enhancing the presentation's effectiveness.

[0135] The autonomous AI agent system can estimate the speaker's emotions during a presentation and adjust their intonation and intonation based on those estimates. For example, if the speaker is nervous, it can advise them to calm their intonation. If the speaker is excited, it can advise them to tone down their intonation. If the speaker is confident, it can encourage them to continue. This allows the speaker to adjust their intonation and intonation to match their emotions, resulting in a more effective presentation.

[0136] An autonomous AI agent system can estimate the audience's emotions during a presentation and suggest actions to engage them based on those emotions. For example, if the audience shows interest, it can add more detailed explanations; if they are bored, it can change the topic; and if they are confused, it can simplify the explanation. This allows the presentation content to be tailored to the audience's emotions, thereby enhancing the presentation's effectiveness.

[0137] An autonomous AI agent system can estimate a speaker's emotions during a presentation and evaluate their performance based on those emotions. For example, it can assess the impact of nervousness, excitement, or confidence. This allows speakers to understand how their emotions affect their presentations and identify areas for improvement.

[0138] The following briefly describes the processing flow for example form 2.

[0139] Step 1: The intonation detection unit detects the speaker's intonation and intonation. The intonation detection unit detects intonation and intonation by analyzing the pitch, volume, rhythm, etc., of the voice. For example, it can take a voice signal as input and use a voice analysis algorithm to detect intonation and intonation. Alternatively, the speaker's voice data can be input to a generating AI, which then analyzes the voice data to detect intonation and intonation. Step 2: The visualization unit performs visualization based on the information detected by the intonation detection unit. The visualization unit visually conveys the speaker's intonation and intonation by overlaying a transparent layer on the screen. For example, visualization can be performed using red or blue colors, and the color and shape of the transparent layer can be dynamically changed according to the speaker's intonation and intonation. Step 3: The facial expression detection unit detects the audience's facial expressions. The facial expression detection unit uses a camera to capture the audience's facial expressions and detects them using a facial expression recognition algorithm. For example, the audience's facial expression data can be input into a generating AI, which then analyzes the data to detect expressions. Furthermore, changes in the audience's facial expressions can be detected in real time. Step 4: The display unit displays information based on the information detected by the facial expression detection unit. The display unit displays facial expression marks at the edge of the screen. For example, the type and position of the facial expression marks can be dynamically changed according to the audience's facial expressions. In addition, the audience's facial expression data can be input into a generating AI, which analyzes the facial expression data to determine the display content. Step 5: The summarization unit records summaries and key points from the presentation. The summarization unit analyzes the presentation content in real time and generates a summary. For example, the audio data of the presentation can be input into the generation AI, which analyzes the audio data and generates a summary. It can also automatically extract and record key points from the presentation. Step 6: The feedback unit provides feedback on the information recorded by the summarization unit. The feedback unit provides the speaker with the summary generated by the summarization unit. For example, it notifies the speaker of the key points extracted by the summarization unit. It can also automatically record audience questions and comments and pop up suggested answers as needed. Furthermore, it can perform real-time sentiment analysis of the audience and provide feedback to the presenter.

[0140] 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.

[0141] 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 text generation AI, image generation AI, and multimodal generation AI. 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 with 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 from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts 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.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0142] 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.

[0143] Each of the multiple elements described above, including the intonation detection unit, visualization unit, facial expression detection unit, display unit, summarization unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the intonation detection unit is implemented by the processor 46 of the smart device 14 and analyzes the speaker's voice data to detect intonation and pitch. The visualization unit is implemented by the control unit 46A of the smart device 14 and overlays a transparent layer on the screen based on the information detected by the intonation detection unit. The facial expression detection unit, for example, uses the camera 42 of the smart device 14 to capture the facial expressions of the audience and detects them with the processor 46. The display unit is implemented by the display 40A of the smart device 14 and displays facial expression marks based on the information detected by the facial expression detection unit. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a summary by analyzing the content of the presentation in real time. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides the speaker with the summary and key points generated by the summarization unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0144] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] 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.

[0157] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0158] 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.

[0159] Each of the multiple elements described above, including the intonation detection unit, visualization unit, facial expression detection unit, display unit, summarization unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the intonation detection unit is implemented by the processor 46 of the smart glasses 214 and analyzes the speaker's voice data to detect intonation and intonation. The visualization unit is implemented by the control unit 46A of the smart glasses 214 and overlays a transparent layer on the screen based on the information detected by the intonation detection unit. The facial expression detection unit, for example, uses the camera 42 of the smart glasses 214 to capture the facial expressions of the audience and detects the expressions with the processor 46. The display unit is implemented by the display 40A of the smart glasses 214 and displays facial expression marks based on the information detected by the facial expression detection unit. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a summary by analyzing the content of the presentation in real time. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides the speaker with the summary and key points generated by the summarization unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0160] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the intonation detection unit, visualization unit, facial expression detection unit, display unit, summarization unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the intonation detection unit is implemented by the processor 46 of the headset terminal 314 and analyzes the speaker's voice data to detect intonation and pitch. The visualization unit is implemented by the control unit 46A of the headset terminal 314 and overlays a transparent layer on the screen based on the information detected by the intonation detection unit. The facial expression detection unit, for example, uses the camera 42 of the headset terminal 314 to capture the facial expressions of the audience and detects them with the processor 46. The display unit is implemented by the display 343 of the headset terminal 314 and displays facial expression marks based on the information detected by the facial expression detection unit. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the content of the presentation in real time to generate a summary. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides the speaker with the summary and key points generated by the summarization unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.).

[0189] 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.

[0190] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0191] 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.

[0192] Each of the multiple elements described above, including the intonation detection unit, visualization unit, facial expression detection unit, display unit, summarization unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the intonation detection unit is implemented by the processor 46 of the robot 414 and analyzes the speaker's voice data to detect intonation and pitch. The visualization unit is implemented by the control unit 46A of the robot 414 and overlays a transparent layer on the screen based on the information detected by the intonation detection unit. The facial expression detection unit, for example, uses the camera 42 of the robot 414 to capture the facial expressions of the audience and detects them with the processor 46. The display unit is implemented by the display 40A of the robot 414 and displays facial expression marks based on the information detected by the facial expression detection unit. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a summary by analyzing the content of the presentation in real time. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides the speaker with the summary and key points generated by the summarization unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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."

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] (Note 1) An intonation detection unit that detects the speaker's intonation and pitch, A visualization unit that visualizes information detected by the intonation detection unit, A facial expression detection unit that detects the facial expressions of the audience, A display unit that displays information based on the information detected by the facial expression detection unit, A summary section for recording summaries and key points during the presentation, The system includes a feedback unit that provides feedback on the information recorded by the summarization unit. A system characterized by the following features. (Note 2) The aforementioned intonation detection unit, It detects the speaker's intonation and intonation and transmits that information to the visualization unit. The system described in Appendix 1, characterized by the features described herein. (Note 3) The visualization unit is, Based on the information transmitted by the intonation detection unit, a transparent layer is overlaid on the screen. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned facial expression detection unit, It detects the facial expressions of the audience and transmits that information to the display unit. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned display unit is Based on the information transmitted by the facial expression detection unit, a facial expression mark is displayed at the edge of the screen. The system described in Appendix 1, characterized by the features described herein. (Note 6) The summary section above is, Record summaries and key points from the presentation and send that information to the feedback department. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned feedback unit is Based on the information transmitted by the summarization unit, provide feedback to the speaker. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned feedback unit is It automatically records audience questions and comments and pops up suggested answers as needed. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned feedback unit is It performs real-time sentiment analysis of the audience and provides feedback to the presenter. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned intonation detection unit, It estimates the speaker's emotions and adjusts the accuracy of intonation detection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned intonation detection unit, Analyze the speaker's past presentation data and learn patterns of intonation changes. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned intonation detection unit, When detecting intonation, the detection algorithm is optimized based on the speaker's language and cultural background. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned intonation detection unit, It estimates the speaker's emotions and identifies the emphasis in their intonation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned intonation detection unit, To improve the accuracy of intonation detection, use the speaker's gestures and body language in conjunction with the intonation detection process. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned intonation detection unit, When detecting intonation, the system analyzes changes in the speaker's voice tone and pitch in real time. The system described in Appendix 1, characterized by the features described herein. (Note 16) The visualization unit is, The system estimates the speaker's emotions and adjusts the visualization's colors and shapes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The visualization unit is, When creating visualizations, apply different visualization techniques depending on the content of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The visualization unit is, During visualization, the visualization dynamically changes in real time to reflect audience reactions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The visualization unit is, The system estimates the speaker's emotions and adjusts the transparency of the visualization based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The visualization unit is, When visualizing, the visualization should be synchronized with the content of the presentation slides. The system described in Appendix 1, characterized by the features described herein. (Note 21) The visualization unit is, During visualization, the visualization effect changes according to the intensity of the speaker's voice. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned facial expression detection unit, The system estimates the audience's emotions and adjusts the accuracy of facial expression detection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned facial expression detection unit, Analyze past facial expression data from the audience and learn patterns of facial expression changes. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned facial expression detection unit, When detecting facial expressions, the detection algorithm is optimized based on attribute information such as the audience's age and gender. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned facial expression detection unit, It estimates the audience's emotions and displays changes in facial expressions in real time based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned facial expression detection unit, When detecting facial expressions, the accuracy of the detection is improved by using the audience's body movements and posture in conjunction with the facial expressions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned facial expression detection unit, When detecting facial expressions, changes in facial expressions are analyzed in conjunction with the audience's voice responses. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned display unit is It estimates the audience's emotions and adjusts the displayed content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned display unit is When displayed, the content is dynamically changed according to the progress of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned display unit is When displayed, the emphasis of the display changes according to the audience's level of interest. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned display unit is It estimates the audience's emotions and adjusts the timing of the display based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned display unit is When displayed, it will be displayed in conjunction with the content of the presentation slides. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned display unit is When displayed, the display effect changes in response to the audience's reaction. The system described in Appendix 1, characterized by the features described herein. (Note 34) The summary section above is, The system estimates the speaker's emotions during the presentation and adjusts the content of the summary based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The summary section above is, When summarizing, adjust the level of detail in the summary based on the importance of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 36) The summary section above is, When summarizing, different summarization algorithms are applied depending on the category of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 37) The summary section above is, It estimates the speaker's emotions during a presentation and adjusts the length of the summary based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The summary section above is, When summarizing, prioritize the summaries according to the progress of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 39) The summary section above is, When summarizing, refer to relevant materials from the presentation to improve the accuracy of the summary. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned feedback unit is Estimate the audience's emotions and adjust the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned feedback unit is During feedback sessions, adjust the timing of feedback according to the progress of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned feedback unit is When providing feedback, adjust the level of detail based on the importance of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned feedback unit is Estimate the audience's emotions and prioritize feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned feedback unit is When giving feedback, refer to relevant materials from the presentation to improve the accuracy of the feedback. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned feedback unit is During feedback, the content of the feedback will dynamically change according to the progress of the presentation. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0212] 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. An intonation detection unit that detects the speaker's intonation and pitch, A visualization unit that visualizes information detected by the intonation detection unit, A facial expression detection unit that detects the facial expressions of the audience, A display unit that displays information based on the information detected by the facial expression detection unit, A summary section for recording summaries and key points during the presentation, The system includes a feedback unit that provides feedback on the information recorded by the summarization unit. A system characterized by the following features.

2. The aforementioned intonation detection unit, It detects the speaker's intonation and intonation and transmits that information to the visualization unit. The system according to feature 1.

3. The visualization unit, Based on the information transmitted by the intonation detection unit, a transparent layer is overlaid on the screen. The system according to feature 1.

4. The aforementioned facial expression detection unit, It detects the facial expressions of the audience and transmits that information to the display unit. The system according to feature 1.

5. The aforementioned display unit is Based on the information transmitted by the facial expression detection unit, a facial expression mark is displayed at the edge of the screen. The system according to feature 1.

6. The summary section above is, Record summaries and key points from the presentation and send that information to the feedback department. The system according to feature 1.

7. The aforementioned feedback unit is Based on the information transmitted by the summarization unit, provide feedback to the speaker. The system according to feature 1.

8. The aforementioned feedback unit is It automatically records audience questions and comments and pops up suggested answers as needed. The system according to feature 1.

Images