system

Abstract

The system according to this embodiment aims to understand the emotions of participants in an online meeting and provide real-time visual feedback. [Solution] The system according to this embodiment comprises an image analysis unit, a voice analysis unit, and a feedback unit. The image analysis unit analyzes the participant's image to recognize emotions. The voice analysis unit analyzes the voice tone based on the emotions recognized by the image analysis unit. The feedback unit provides visual feedback in a color-coded frame based on the emotions analyzed by the voice analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to grasp the feelings of participants in an online meeting and real-time feedback cannot be obtained.

[0005] The system according to the embodiment aims to grasp the feelings of participants in an online meeting and provide visual feedback in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image analysis unit, a voice analysis unit, and a feedback unit. The image analysis unit analyzes the participant's image to recognize emotions. The voice analysis unit analyzes the voice tone based on the emotions recognized by the image analysis unit. The feedback unit provides visual feedback using color-coded frames based on the emotions analyzed by the voice analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can grasp the emotions of participants in an online meeting and provide real-time visual 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 controls 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 online meeting system according to an embodiment of the present invention is a system that provides participant emotion recognition and real-time feedback. This online meeting system solves the problem that in conventional online meetings it is difficult to grasp participants' emotions and feedback cannot be obtained in real time, which tends to make presentations one-way. To solve this problem, the system provides emotion recognition technology using image analysis, emotion judgment using voice tone analysis, and visual feedback using color-coded frames. First, the online meeting system recognizes emotions from facial expressions by analyzing the participant's image. For example, AI analyzes expressions such as smiles, surprise, and anger to determine emotions. The online meeting system also determines emotions by analyzing the participant's voice tone. For example, it analyzes emotions from voice tone, volume, and speed. As a result, the online meeting system can instantly grasp the emotional state of the participants. Next, based on the results of emotion recognition, the online meeting system provides visual feedback using color-coded frames. For example, a green frame when the participant is smiling, a yellow frame when they are surprised, and a red frame when they are angry, changing the color of the frame according to the emotion. As a result, the presenter can check the emotional state of the participants in real time. Furthermore, the online meeting system enables interactive meetings based on emotion recognition and feedback. For example, if a participant is surprised, the presenter can add a more detailed explanation, allowing for responses tailored to the participant's reaction. This improves the interactivity of the meeting and increases participant satisfaction. This system is particularly intended for use in business settings, such as presentation specialists in large corporations, professionals working in remote work environments, and individuals who value reactions and emotions. The EmotionTrackAI agent analyzes participants' images and voices during online meetings, and can grasp the emotional state of all participants in real time with dynamically changing frame colors based on their emotions. This visualizes the emotions of the meeting and provides an innovative experience. As a result, the online meeting system can recognize participants' emotions in real time and provide visual feedback, enabling interactive meetings.

[0029] The online meeting system according to this embodiment comprises an image analysis unit, an audio analysis unit, and a feedback unit. The image analysis unit analyzes images of participants to recognize emotions. The image analysis unit recognizes emotions by, for example, analyzing facial expressions. For example, the image analysis unit uses AI to analyze expressions such as smiles, surprise, and anger to determine emotions. The image analysis unit can recognize emotions by, for example, using a facial expression analysis algorithm to analyze the movement of facial muscles. The image analysis unit can also recognize emotions from facial expressions using machine learning algorithms. For example, the image analysis unit can analyze facial expressions with high accuracy and recognize emotions using deep learning. The audio analysis unit analyzes voice tone based on the emotions recognized by the image analysis unit. The audio analysis unit determines emotions by, for example, analyzing the voice tone of participants. For example, the audio analysis unit analyzes emotions from voice tone, volume, speed, etc. The audio analysis unit can determine emotions by, for example, using voice feature extraction technology to analyze voice tone. The audio analysis unit can also determine emotions from voice tone using an acoustic model. For example, the voice analysis unit can analyze features such as tone, volume, and speed of a voice using an acoustic model to determine emotion. The feedback unit provides visual feedback using color-coded frames based on the emotion analyzed by the voice analysis unit. The feedback unit can, for example, change the frame color according to emotion. For example, the feedback unit can change the frame color according to emotion, such as a green frame if the participant is smiling, a yellow frame if they are surprised, and a red frame if they are angry. The feedback unit can, for example, set color selection criteria and change the frame color according to emotion. The feedback unit can also adjust the timing of the feedback and change the frame color according to emotion. For example, the feedback unit can recognize emotions in real time and change the frame color immediately. As a result, the online meeting system according to this embodiment can realize interactive meetings by recognizing participants' emotions in real time and providing visual feedback.

[0030] The image analysis unit analyzes participants' images to recognize emotions. For example, it recognizes emotions by analyzing facial expressions. Specifically, the image analysis unit processes participants' facial images acquired through the camera in real time and analyzes the movement of facial muscles. This involves detecting the movement of various parts of the face (e.g., eyes, mouth, eyebrows) and analyzing the patterns of these movements to identify emotions such as smiles, surprise, and anger. The image analysis unit utilizes deep learning-based facial recognition algorithms and performs highly accurate emotion recognition using models pre-trained on a vast dataset. For example, it uses a convolutional neural network (CNN) to extract facial features and classify emotions based on these features. Furthermore, the image analysis unit can also use a combination of recurrent neural networks (RNNs) and long-term short-term memory (LSTM) networks to account for temporal changes. This allows it to capture subtle changes and continuous movements of facial expressions, enabling more accurate emotion recognition. In addition, the image analysis unit can apply data augmentation techniques and normalization methods to perform robust analysis against external factors such as lighting conditions and camera angles. This enables stable emotion recognition in various environments.

[0031] The voice analysis unit analyzes voice tone based on the emotions recognized by the image analysis unit. For example, the voice analysis unit determines emotions by analyzing the participant's voice tone. Specifically, the voice analysis unit processes voice data acquired through the microphone in real time and extracts voice features such as tone, volume, speed, pitch, and intonation. This uses acoustic features such as Mel-frequency cepstrum coefficients (MFCCs), pitch, and energy. Based on these features, the voice analysis unit uses machine learning models to classify the emotions of the voice. For example, it uses algorithms such as support vector machines (SVMs), random forests, and deep neural networks (DNNs) to analyze voice data and identify emotions. Furthermore, the voice analysis unit can also determine emotions from voice tone using acoustic models. For example, acoustic models can use recurrent neural networks (RNNs) or long-term short-term memory (LSTM) networks to take into account the temporal changes in voice data. This allows for capturing continuous changes in voice and patterns of intonation, enabling more accurate emotion recognition. Furthermore, the voice analysis unit can minimize the effects of environmental and background noise by applying noise reduction and voice enhancement technologies, enabling the analysis of clear voice data. As a result, the voice analysis unit can achieve stable emotion recognition even in various environments.

[0032] The feedback unit provides visual feedback using color-coded frames based on emotions analyzed by the voice analysis unit. For example, the feedback unit changes the frame color according to emotion. Specifically, it changes the color of each participant's frame displayed on the meeting screen to reflect the participant's emotional state in real time. For example, a green frame might indicate a smile, a yellow frame a surprised person, and a red frame an angry person. The feedback unit can set color selection criteria and change the frame color according to emotion. For example, it can change the intensity of the color according to the strength of the emotion, allowing for a more detailed visual representation of emotional changes. Furthermore, the feedback unit can adjust the timing of feedback and change the frame color according to emotion. For example, it can recognize emotions in real time and instantly change the frame color. This allows participants to immediately see how their emotions are being perceived and respond appropriately according to the meeting's progress. Additionally, the feedback unit records emotional changes as a history for later reference, which can be used for meeting review and analysis. For example, by reviewing the history of emotional changes after a meeting and analyzing when and what emotions were expressed, it's possible to identify areas for improvement in the meeting. This allows the feedback department to recognize participants' emotions in real time and provide visual feedback, thereby enabling more interactive meetings.

[0033] The image analysis unit can analyze the facial expressions of participants and recognize their emotions. For example, the image analysis unit can recognize emotions by analyzing facial expressions. For example, the image analysis unit can use AI to analyze expressions such as smiles, surprise, and anger and determine the emotion. For example, the image analysis unit can use a facial expression analysis algorithm to analyze the movement of facial muscles and recognize emotions. The image analysis unit can also use machine learning algorithms to recognize emotions from facial expressions. For example, the image analysis unit can use deep learning to analyze facial expressions with high accuracy and recognize emotions. As a result, by analyzing facial expressions, the emotions of participants can be accurately recognized. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input the participant's facial expression data into a generative AI and have the generative AI perform emotion recognition.

[0034] The voice analysis unit can analyze the participant's voice tone to determine their emotions. For example, the voice analysis unit can determine emotions by analyzing the participant's voice tone. For example, the voice analysis unit can analyze emotions from the tone, volume, and speed of the voice. For example, the voice analysis unit can analyze the voice tone and determine emotions using voice feature extraction technology. The voice analysis unit can also determine emotions from the voice tone using an acoustic model. For example, the voice analysis unit can analyze features such as the tone, volume, and speed of the voice using an acoustic model and determine emotions. This allows for accurate determination of the participant's emotions by analyzing their voice tone. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input the participant's voice data into a generative AI and have the generative AI perform the emotion determination.

[0035] The feedback unit can change the frame color according to emotion. For example, the feedback unit can change the frame color according to emotion, such as a green frame when the participant is smiling, a yellow frame when they are surprised, and a red frame when they are angry. The feedback unit can set color selection criteria and change the frame color according to emotion. The feedback unit can also adjust the timing of the feedback and change the frame color according to emotion. For example, the feedback unit can recognize emotions in real time and change the frame color immediately. This allows for visual emotional feedback by changing the frame color according to emotion. 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 result of emotion recognition into a generative AI and have the generative AI perform the color coding of the feedback.

[0036] The feedback unit may include an interactive unit that responds to participants' reactions. The feedback unit, for example, responds to participants' reactions. For example, if a participant is surprised, the feedback unit can respond in a way that the presenter can provide a more detailed explanation. The feedback unit may include an interactive unit that can respond to participants' reactions. For example, the interactive unit can analyze participants' reactions in real time and take appropriate action. This enables interactive meetings by responding to participants' reactions. Some or all of the above processing in the feedback unit may be performed using, for example, generative AI, or without generative AI. For example, the feedback unit can input participant reaction data into a generative AI and have the generative AI perform interactive responses.

[0037] The image analysis unit can improve the accuracy of image analysis by considering the orientation of the participant's face and lighting conditions during image analysis. For example, the image analysis unit can detect the orientation of the participant's face and improve the accuracy of the analysis if the participant is facing forward. For example, if the lighting conditions are dark, the image analysis unit can improve the accuracy of the analysis by correcting the brightness of the image. For example, if the participant's face is partially obscured, the image analysis unit will focus on analyzing the unobscured portion. This improves the accuracy of the analysis by considering the orientation of the face and lighting conditions. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input data on the orientation of the participant's face and lighting conditions into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0038] The image analysis unit can improve the accuracy of emotion recognition by considering the participant's background information during image analysis. For example, if the participant's background is bright, the image analysis unit can enhance the facial contours to improve analysis accuracy. For example, if the participant's background is complex, the image analysis unit can extract the facial region to improve analysis accuracy. For example, if the participant's background is moving, the image analysis unit can track facial movements to improve analysis accuracy. In this way, the accuracy of emotion recognition is improved by considering background information. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input the participant's background information into a generative AI and have the generative AI perform the improvement of emotion recognition accuracy.

[0039] The image analysis unit can perform filtering during image analysis to eliminate the influence of participants' clothing and accessories. For example, if the color of a participant's clothing is similar to the color of their face, the image analysis unit can enhance the facial area to improve analysis accuracy. For example, if a participant is wearing glasses, the image analysis unit can remove the reflection from the glasses to improve analysis accuracy. For example, if a participant is wearing a hat, the image analysis unit can eliminate the influence of the hat to improve analysis accuracy. In this way, analysis accuracy is improved by eliminating the influence of clothing and accessories. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input data on the participant's clothing and accessories into a generative AI and have the generative AI perform the filtering.

[0040] The voice analysis unit can improve the accuracy of its analysis by taking into account changes in the participant's speaking speed and volume during voice analysis. For example, the voice analysis unit increases the accuracy of voice analysis when the participant speaks quickly. For example, the voice analysis unit adjusts the accuracy of voice analysis when the participant's volume is loud. For example, the voice analysis unit analyzes changes in the participant's speaking speed and volume in real time to improve accuracy. This improves the accuracy of the analysis by taking into account changes in speaking speed and volume. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input data on the participant's speaking speed and volume into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0041] The audio analysis unit can perform filtering to remove background noise from participants during audio analysis. For example, the audio analysis unit can remove background noise contained in the participant's voice in real time. For example, the audio analysis unit can filter out noise in a specific frequency band contained in the participant's voice. For example, the audio analysis unit can analyze ambient sounds contained in the participant's voice and remove them as noise. By removing background noise, the accuracy of the analysis is improved. Some or all of the above processing in the audio analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the audio analysis unit can input the participant's voice data into a generative AI and have the generative AI perform background noise removal.

[0042] The voice analysis unit can improve the accuracy of emotion judgment by taking into account the influence of the participant's language and dialect during voice analysis. For example, the voice analysis unit adjusts the parameters of voice analysis according to the language used by the participant. For example, the voice analysis unit learns voice patterns specific to the participant's dialect to improve analysis accuracy. For example, the voice analysis unit analyzes the influence of the participant's language and dialect in real time to improve the accuracy of emotion judgment. As a result, the accuracy of emotion judgment is improved by taking into account the influence of language and dialect. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input data on the participant's language and dialect into a generative AI and have the generative AI perform the improvement of emotion judgment accuracy.

[0043] The feedback unit can learn from the participant's past response data and select the optimal feedback method during the feedback process. For example, the feedback unit can learn from the participant's past response data and select the optimal color-coding feedback method. For example, the feedback unit can learn from the participant's past response data and provide feedback at the optimal timing. For example, the feedback unit can learn from the participant's past response data and select the optimal feedback content. In this way, the optimal feedback method can be selected by learning from past response data. Some or all of the above processes in the feedback unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the feedback unit can input the participant's past response data into a generative AI and have the generative AI select the optimal feedback method.

[0044] The feedback unit can customize the design of the feedback, taking into account the participant's visual preferences. For example, the feedback unit can customize the color of the feedback according to the participant's visual preferences. For example, the feedback unit can customize the shape of the feedback according to the participant's visual preferences. For example, the feedback unit can customize the animation of the feedback according to the participant's visual preferences. This improves participant satisfaction by providing feedback designs that match their visual preferences. 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 participant's visual preference data into a generative AI and have the generative AI perform the customization of the feedback design.

[0045] The feedback unit can select the optimal display method when providing feedback, taking into account the participant's device information. For example, if the participant is using a smartphone, the feedback unit will select the optimal display method. For example, if the participant is using a tablet, the feedback unit will select the optimal display method. For example, if the participant is using a desktop computer, the feedback unit will select the optimal display method. By providing the optimal display method according to the device information, the visual burden can be reduced. 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 participant's device information into a generative AI and have the generative AI select the optimal display method.

[0046] The feedback unit can perform filtering during feedback to reduce the visual burden on participants. For example, the feedback unit can reduce the visual burden by adjusting the color of the feedback. For example, the feedback unit can reduce the visual burden by adjusting the brightness of the feedback. For example, the feedback unit can reduce the visual burden by adjusting the display time of the feedback. This reduces the visual burden and improves participant comfort. 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 participant visual burden data into a generative AI and have the generative AI perform the filtering.

[0047] The interactive unit can learn from the participant's past response data during interaction and select the optimal response method. For example, the interactive unit can learn from the participant's past response data and select the optimal timing for asking questions. For example, the interactive unit can learn from the participant's past response data and select the optimal method of explanation. For example, the interactive unit can learn from the participant's past response data and select the optimal interactive response method. In this way, the optimal response method can be selected by learning from past response data. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input the participant's past response data into a generative AI and have the generative AI select the optimal response method.

[0048] The interactive unit can customize its responses during interaction, taking into account the participant's current situation and interests. For example, the interactive unit customizes the optimal response according to the participant's current situation. For example, the interactive unit customizes the optimal response according to the participant's interests. For example, the interactive unit analyzes the participant's situation and interests in real time and customizes its responses. This improves participant satisfaction by providing responses that are tailored to their situation and interests. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input data on the participant's current situation and interests into a generative AI and have the generative AI perform the customization of the responses.

[0049] The interactive unit can select the optimal response method during interaction, taking into account the participant's device information. For example, if the participant is using a smartphone, the interactive unit will select the optimal response method. For example, if the participant is using a tablet, the interactive unit will select the optimal response method. For example, if the participant is using a desktop computer, the interactive unit will select the optimal response method. This improves participant comfort by providing the optimal response method according to device information. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input the participant's device information into a generative AI and have the generative AI select the optimal response method.

[0050] The interactive unit can analyze participants' responses in real time during interaction and immediately change its response. For example, the interactive unit analyzes participants' responses in real time and immediately changes its response. For example, the interactive unit immediately changes the content of questions in response to participants' responses. For example, the interactive unit immediately changes the content of explanations in response to participants' responses. This enables appropriate responses by analyzing responses in real time and immediately changing the response. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input participant response data into a generative AI and have the generative AI immediately change the response.

[0051] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0052] Online meeting systems can learn from participants' past meeting data and select the optimal meeting format. For example, they can learn from participants' past meeting data to select the optimal pace, content, and timing. This allows them to select the most effective meeting format by learning from past meeting data.

[0053] Online meeting systems can select the optimal meeting format by considering participants' device information. For example, if a participant is using a smartphone, the system can select the optimal format. If a participant is using a tablet, the system can select the optimal format. If a participant is using a desktop computer, the system can select the optimal format. This improves participant comfort by providing the most suitable meeting format based on device information.

[0054] Online meeting systems can customize the meeting design to take participants' visual preferences into account. For example, they can customize the meeting's colors, shape, and animations according to participants' visual preferences. This improves participant satisfaction by providing a meeting design that suits their visual preferences.

[0055] Online meeting systems can adjust the meeting flow by taking into account participants' background information. For example, if a participant's background is bright, the meeting can proceed smoothly. If a participant's background is complex, the meeting can proceed slowly. If a participant's background is moving, the meeting can proceed quickly. By providing a meeting flow that is tailored to background information, participant comfort is improved.

[0056] Online meeting systems can perform filtering to eliminate the influence of participants' clothing and accessories. For example, if a participant's clothing color is similar to their face color, the facial area can be emphasized to improve analysis accuracy. If a participant is wearing glasses, the reflection from the glasses can be removed to improve analysis accuracy. If a participant is wearing a hat, the influence of the hat can be eliminated to improve analysis accuracy. In this way, the accuracy of the analysis is improved by eliminating the influence of clothing and accessories.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The image analysis unit analyzes the participant's image to recognize emotions. For example, it can recognize emotions by analyzing facial expressions. The image analysis unit can use facial expression analysis algorithms and machine learning algorithms to analyze the movement of facial muscles and recognize emotions. It can also use deep learning to analyze facial expressions with high accuracy and recognize emotions. Step 2: The voice analysis unit analyzes the voice tone based on the emotions recognized by the image analysis unit. For example, it determines emotions by analyzing the participant's voice tone. The voice analysis unit analyzes emotions from the tone, volume, and speed of the voice. Voice feature extraction technology and acoustic models can be used to analyze voice tone and determine emotions. Step 3: The feedback unit provides visual feedback using color-coded frames based on the emotions analyzed by the voice analysis unit. For example, the frame color can change according to the emotion. A green frame if the participant is smiling, a yellow frame if they are surprised, a red frame if they are angry, and so on. The feedback unit can set color selection criteria and change the frame color according to the emotion. It can also recognize emotions in real time and change the frame color instantly.

[0059] (Example of form 2) An online meeting system according to an embodiment of the present invention is a system that provides participant emotion recognition and real-time feedback. This online meeting system solves the problem that in conventional online meetings it is difficult to grasp participants' emotions and feedback cannot be obtained in real time, which tends to make presentations one-way. To solve this problem, the system provides emotion recognition technology using image analysis, emotion judgment using voice tone analysis, and visual feedback using color-coded frames. First, the online meeting system recognizes emotions from facial expressions by analyzing the participant's image. For example, AI analyzes expressions such as smiles, surprise, and anger to determine emotions. The online meeting system also determines emotions by analyzing the participant's voice tone. For example, it analyzes emotions from voice tone, volume, and speed. As a result, the online meeting system can instantly grasp the emotional state of the participants. Next, based on the results of emotion recognition, the online meeting system provides visual feedback using color-coded frames. For example, a green frame when the participant is smiling, a yellow frame when they are surprised, and a red frame when they are angry, changing the color of the frame according to the emotion. As a result, the presenter can check the emotional state of the participants in real time. Furthermore, the online meeting system enables interactive meetings based on emotion recognition and feedback. For example, if a participant is surprised, the presenter can add a more detailed explanation, allowing for responses tailored to the participant's reaction. This improves the interactivity of the meeting and increases participant satisfaction. This system is particularly intended for use in business settings, such as presentation specialists in large corporations, professionals working in remote work environments, and individuals who value reactions and emotions. The EmotionTrackAI agent analyzes participants' images and voices during online meetings, and can grasp the emotional state of all participants in real time with dynamically changing frame colors based on their emotions. This visualizes the emotions of the meeting and provides an innovative experience. As a result, the online meeting system can recognize participants' emotions in real time and provide visual feedback, enabling interactive meetings.

[0060] The online meeting system according to this embodiment comprises an image analysis unit, an audio analysis unit, and a feedback unit. The image analysis unit analyzes images of participants to recognize emotions. The image analysis unit recognizes emotions by, for example, analyzing facial expressions. For example, the image analysis unit uses AI to analyze expressions such as smiles, surprise, and anger to determine emotions. The image analysis unit can recognize emotions by, for example, using a facial expression analysis algorithm to analyze the movement of facial muscles. The image analysis unit can also recognize emotions from facial expressions using machine learning algorithms. For example, the image analysis unit can analyze facial expressions with high accuracy and recognize emotions using deep learning. The audio analysis unit analyzes voice tone based on the emotions recognized by the image analysis unit. The audio analysis unit determines emotions by, for example, analyzing the voice tone of participants. For example, the audio analysis unit analyzes emotions from voice tone, volume, speed, etc. The audio analysis unit can determine emotions by, for example, using voice feature extraction technology to analyze voice tone. The audio analysis unit can also determine emotions from voice tone using an acoustic model. For example, the voice analysis unit can analyze features such as tone, volume, and speed of a voice using an acoustic model to determine emotion. The feedback unit provides visual feedback using color-coded frames based on the emotion analyzed by the voice analysis unit. The feedback unit can, for example, change the frame color according to emotion. For example, the feedback unit can change the frame color according to emotion, such as a green frame if the participant is smiling, a yellow frame if they are surprised, and a red frame if they are angry. The feedback unit can, for example, set color selection criteria and change the frame color according to emotion. The feedback unit can also adjust the timing of the feedback and change the frame color according to emotion. For example, the feedback unit can recognize emotions in real time and change the frame color immediately. As a result, the online meeting system according to this embodiment can realize interactive meetings by recognizing participants' emotions in real time and providing visual feedback.

[0061] The image analysis unit analyzes participants' images to recognize emotions. For example, it recognizes emotions by analyzing facial expressions. Specifically, the image analysis unit processes participants' facial images acquired through the camera in real time and analyzes the movement of facial muscles. This involves detecting the movement of various parts of the face (e.g., eyes, mouth, eyebrows) and analyzing the patterns of these movements to identify emotions such as smiles, surprise, and anger. The image analysis unit utilizes deep learning-based facial recognition algorithms and performs highly accurate emotion recognition using models pre-trained on a vast dataset. For example, it uses a convolutional neural network (CNN) to extract facial features and classify emotions based on these features. Furthermore, the image analysis unit can also use a combination of recurrent neural networks (RNNs) and long-term short-term memory (LSTM) networks to account for temporal changes. This allows it to capture subtle changes and continuous movements of facial expressions, enabling more accurate emotion recognition. In addition, the image analysis unit can apply data augmentation techniques and normalization methods to perform robust analysis against external factors such as lighting conditions and camera angles. This enables stable emotion recognition in various environments.

[0062] The voice analysis unit analyzes voice tone based on the emotions recognized by the image analysis unit. For example, the voice analysis unit determines emotions by analyzing the participant's voice tone. Specifically, the voice analysis unit processes voice data acquired through the microphone in real time and extracts voice features such as tone, volume, speed, pitch, and intonation. This uses acoustic features such as Mel-frequency cepstrum coefficients (MFCCs), pitch, and energy. Based on these features, the voice analysis unit uses machine learning models to classify the emotions of the voice. For example, it uses algorithms such as support vector machines (SVMs), random forests, and deep neural networks (DNNs) to analyze voice data and identify emotions. Furthermore, the voice analysis unit can also determine emotions from voice tone using acoustic models. For example, acoustic models can use recurrent neural networks (RNNs) or long-term short-term memory (LSTM) networks to take into account the temporal changes in voice data. This allows for capturing continuous changes in voice and patterns of intonation, enabling more accurate emotion recognition. Furthermore, the voice analysis unit can minimize the effects of environmental and background noise by applying noise reduction and voice enhancement technologies, enabling the analysis of clear voice data. As a result, the voice analysis unit can achieve stable emotion recognition even in various environments.

[0063] The feedback unit provides visual feedback using color-coded frames based on emotions analyzed by the voice analysis unit. For example, the feedback unit changes the frame color according to emotion. Specifically, it changes the color of each participant's frame displayed on the meeting screen to reflect the participant's emotional state in real time. For example, a green frame might indicate a smile, a yellow frame a surprised person, and a red frame an angry person. The feedback unit can set color selection criteria and change the frame color according to emotion. For example, it can change the intensity of the color according to the strength of the emotion, allowing for a more detailed visual representation of emotional changes. Furthermore, the feedback unit can adjust the timing of feedback and change the frame color according to emotion. For example, it can recognize emotions in real time and instantly change the frame color. This allows participants to immediately see how their emotions are being perceived and respond appropriately according to the meeting's progress. Additionally, the feedback unit records emotional changes as a history for later reference, which can be used for meeting review and analysis. For example, by reviewing the history of emotional changes after a meeting and analyzing when and what emotions were expressed, it's possible to identify areas for improvement in the meeting. This allows the feedback department to recognize participants' emotions in real time and provide visual feedback, thereby enabling more interactive meetings.

[0064] The image analysis unit can analyze the facial expressions of participants and recognize their emotions. For example, the image analysis unit can recognize emotions by analyzing facial expressions. For example, the image analysis unit can use AI to analyze expressions such as smiles, surprise, and anger and determine the emotion. For example, the image analysis unit can use a facial expression analysis algorithm to analyze the movement of facial muscles and recognize emotions. The image analysis unit can also use machine learning algorithms to recognize emotions from facial expressions. For example, the image analysis unit can use deep learning to analyze facial expressions with high accuracy and recognize emotions. As a result, by analyzing facial expressions, the emotions of participants can be accurately recognized. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input the participant's facial expression data into a generative AI and have the generative AI perform emotion recognition.

[0065] The voice analysis unit can analyze the participant's voice tone to determine their emotions. For example, the voice analysis unit can determine emotions by analyzing the participant's voice tone. For example, the voice analysis unit can analyze emotions from the tone, volume, and speed of the voice. For example, the voice analysis unit can analyze the voice tone and determine emotions using voice feature extraction technology. The voice analysis unit can also determine emotions from the voice tone using an acoustic model. For example, the voice analysis unit can analyze features such as the tone, volume, and speed of the voice using an acoustic model and determine emotions. This allows for accurate determination of the participant's emotions by analyzing their voice tone. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input the participant's voice data into a generative AI and have the generative AI perform the emotion determination.

[0066] The feedback unit can change the frame color according to emotion. For example, the feedback unit can change the frame color according to emotion, such as a green frame when the participant is smiling, a yellow frame when they are surprised, and a red frame when they are angry. The feedback unit can set color selection criteria and change the frame color according to emotion. The feedback unit can also adjust the timing of the feedback and change the frame color according to emotion. For example, the feedback unit can recognize emotions in real time and change the frame color immediately. This allows for visual emotional feedback by changing the frame color according to emotion. 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 result of emotion recognition into a generative AI and have the generative AI perform the color coding of the feedback.

[0067] The feedback unit may include an interactive unit that responds to participants' reactions. The feedback unit, for example, responds to participants' reactions. For example, if a participant is surprised, the feedback unit can respond in a way that the presenter can provide a more detailed explanation. The feedback unit may include an interactive unit that can respond to participants' reactions. For example, the interactive unit can analyze participants' reactions in real time and take appropriate action. This enables interactive meetings by responding to participants' reactions. Some or all of the above processing in the feedback unit may be performed using, for example, generative AI, or without generative AI. For example, the feedback unit can input participant reaction data into a generative AI and have the generative AI perform interactive responses.

[0068] The image analysis unit can estimate the participant's emotions and dynamically adjust the accuracy of the image analysis based on the estimated emotions. For example, if the participant is smiling, the image analysis unit can increase the accuracy of the image analysis to capture detailed changes in facial expression. For example, if the participant is surprised, the image analysis unit can increase the frequency of analysis to capture instantaneous changes in facial expression. For example, if the participant is angry, the image analysis unit can adjust the accuracy of the analysis to capture subtle changes in facial expression. In this way, the accuracy of the analysis is improved by adjusting the accuracy of the image analysis based on 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-described processes in the image analysis unit may be performed using a generative AI, or not using a generative AI. For example, the image analysis unit can input the participant's emotion data into a generative AI and have the generative AI perform the adjustment of the image analysis accuracy.

[0069] The image analysis unit can learn from the participant's past facial expression data and generate individual emotion recognition models. For example, the image analysis unit can learn from the participant's past smile data and generate an individual smile recognition model. For example, the image analysis unit can learn from the participant's past surprise data and generate an individual surprise recognition model. For example, the image analysis unit can learn from the participant's past anger data and generate an individual anger recognition model. In this way, individual emotion recognition models can be generated by learning from past facial expression data. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input the participant's past facial expression data into a generative AI and have the generative AI perform the generation of individual emotion recognition models.

[0070] The image analysis unit can improve the accuracy of image analysis by considering the orientation of the participant's face and lighting conditions during image analysis. For example, the image analysis unit can detect the orientation of the participant's face and improve the accuracy of the analysis if the participant is facing forward. For example, if the lighting conditions are dark, the image analysis unit can improve the accuracy of the analysis by correcting the brightness of the image. For example, if the participant's face is partially obscured, the image analysis unit will focus on analyzing the unobscured portion. This improves the accuracy of the analysis by considering the orientation of the face and lighting conditions. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input data on the orientation of the participant's face and lighting conditions into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0071] The image analysis unit can estimate the participant's emotions and adjust the frequency of image analysis based on the estimated emotions. For example, if the participant is smiling, the image analysis unit can reduce the frequency of image analysis to save resources. For example, if the participant is surprised, the image analysis unit can increase the frequency of image analysis to capture instantaneous changes in facial expression. For example, if the participant is angry, the image analysis unit can adjust the frequency of image analysis to capture subtle changes in facial expression. This allows for resource saving by adjusting the frequency of image analysis based on emotions. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input the participant's emotion data into a generative AI and have the generative AI perform the adjustment of the image analysis frequency.

[0072] The image analysis unit can improve the accuracy of emotion recognition by considering the participant's background information during image analysis. For example, if the participant's background is bright, the image analysis unit can enhance the facial contours to improve analysis accuracy. For example, if the participant's background is complex, the image analysis unit can extract the facial region to improve analysis accuracy. For example, if the participant's background is moving, the image analysis unit can track facial movements to improve analysis accuracy. In this way, the accuracy of emotion recognition is improved by considering background information. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image analysis unit can input the participant's background information into a generative AI and have the generative AI perform the improvement of emotion recognition accuracy.

[0073] The image analysis unit can perform filtering during image analysis to eliminate the influence of participants' clothing and accessories. For example, if the color of a participant's clothing is similar to the color of their face, the image analysis unit can enhance the facial area to improve analysis accuracy. For example, if a participant is wearing glasses, the image analysis unit can remove the reflection from the glasses to improve analysis accuracy. For example, if a participant is wearing a hat, the image analysis unit can eliminate the influence of the hat to improve analysis accuracy. In this way, analysis accuracy is improved by eliminating the influence of clothing and accessories. Some or all of the above processing in the image analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the image analysis unit can input data on the participant's clothing and accessories into a generative AI and have the generative AI perform the filtering.

[0074] The voice analysis unit can estimate the participant's emotions and dynamically adjust the voice analysis parameters based on the estimated emotions. For example, if the participant is relaxed, the voice analysis unit will set the voice analysis parameters loosely. For example, if the participant is tense, the voice analysis unit will set the voice analysis parameters strictly. For example, if the participant is excited, the voice analysis unit will dynamically adjust the voice analysis parameters. By adjusting the voice analysis parameters based on emotions, the accuracy of the analysis is improved. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input the participant's emotion data into a generative AI and have the generative AI perform the voice analysis parameter adjustments.

[0075] The voice analysis unit can learn from the participant's past voice data and generate individual emotion judgment models. For example, the voice analysis unit can learn from the participant's past voice data and generate an individual relaxation emotion judgment model. For example, the voice analysis unit can learn from the participant's past voice data and generate an individual tension emotion judgment model. For example, the voice analysis unit can learn from the participant's past voice data and generate an individual excitement emotion judgment model. In this way, individual emotion judgment models can be generated by learning from past voice data. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the voice analysis unit can input the participant's past voice data into a generative AI and have the generative AI perform the generation of individual emotion judgment models.

[0076] The voice analysis unit can improve the accuracy of its analysis by taking into account changes in the participant's speaking speed and volume during voice analysis. For example, the voice analysis unit increases the accuracy of voice analysis when the participant speaks quickly. For example, the voice analysis unit adjusts the accuracy of voice analysis when the participant's volume is loud. For example, the voice analysis unit analyzes changes in the participant's speaking speed and volume in real time to improve accuracy. This improves the accuracy of the analysis by taking into account changes in speaking speed and volume. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input data on the participant's speaking speed and volume into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0077] The voice analysis unit can estimate the participant's emotions and adjust the frequency of voice analysis based on the estimated emotions. For example, if the participant is relaxed, the voice analysis unit can reduce the frequency of voice analysis to save resources. For example, if the participant is tense, the voice analysis unit can increase the frequency of voice analysis to perform a more detailed analysis. For example, if the participant is excited, the voice analysis unit can dynamically adjust the frequency of voice analysis. This allows for resource savings by adjusting the frequency of voice analysis based on emotions. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input the participant's emotion data into a generative AI and have the generative AI perform the adjustment of the voice analysis frequency.

[0078] The audio analysis unit can perform filtering to remove background noise from participants during audio analysis. For example, the audio analysis unit can remove background noise contained in the participant's voice in real time. For example, the audio analysis unit can filter out noise in a specific frequency band contained in the participant's voice. For example, the audio analysis unit can analyze ambient sounds contained in the participant's voice and remove them as noise. By removing background noise, the accuracy of the analysis is improved. Some or all of the above processing in the audio analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the audio analysis unit can input the participant's voice data into a generative AI and have the generative AI perform background noise removal.

[0079] The voice analysis unit can improve the accuracy of emotion judgment by taking into account the influence of the participant's language and dialect during voice analysis. For example, the voice analysis unit adjusts the parameters of voice analysis according to the language used by the participant. For example, the voice analysis unit learns voice patterns specific to the participant's dialect to improve analysis accuracy. For example, the voice analysis unit analyzes the influence of the participant's language and dialect in real time to improve the accuracy of emotion judgment. As a result, the accuracy of emotion judgment is improved by taking into account the influence of language and dialect. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the voice analysis unit can input data on the participant's language and dialect into a generative AI and have the generative AI perform the improvement of emotion judgment accuracy.

[0080] The feedback unit can estimate the participant's emotions and dynamically adjust the color coding of the feedback based on the estimated emotions. For example, if the participant is smiling, the feedback unit dynamically adjusts the color of the feedback to green. For example, if the participant is surprised, the feedback unit dynamically adjusts the color of the feedback to yellow. For example, if the participant is angry, the feedback unit dynamically adjusts the color of the feedback to red. In this way, by adjusting the color coding of the feedback based on emotions, emotions can be visually conveyed as feedback. 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 participant's emotion data into a generative AI and have the generative AI perform the color coding of the feedback.

[0081] The feedback unit can learn from the participant's past response data and select the optimal feedback method during the feedback process. For example, the feedback unit can learn from the participant's past response data and select the optimal color-coding feedback method. For example, the feedback unit can learn from the participant's past response data and provide feedback at the optimal timing. For example, the feedback unit can learn from the participant's past response data and select the optimal feedback content. In this way, the optimal feedback method can be selected by learning from past response data. Some or all of the above processes in the feedback unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the feedback unit can input the participant's past response data into a generative AI and have the generative AI select the optimal feedback method.

[0082] The feedback unit can customize the design of the feedback, taking into account the participant's visual preferences. For example, the feedback unit can customize the color of the feedback according to the participant's visual preferences. For example, the feedback unit can customize the shape of the feedback according to the participant's visual preferences. For example, the feedback unit can customize the animation of the feedback according to the participant's visual preferences. This improves participant satisfaction by providing feedback designs that match their visual preferences. 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 participant's visual preference data into a generative AI and have the generative AI perform the customization of the feedback design.

[0083] The feedback unit can estimate the participant's emotions and adjust the timing of the feedback display based on the estimated emotions. For example, if the participant is smiling, the feedback unit will delay the timing of the feedback display. For example, if the participant is surprised, the feedback unit will speed up the timing of the feedback display. For example, if the participant is angry, the feedback unit will dynamically adjust the timing of the feedback display. This allows feedback to be provided at the appropriate time by adjusting the timing of the feedback display based on emotions. 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 participant's emotion data into a generative AI and have the generative AI execute the timing of the feedback display.

[0084] The feedback unit can select the optimal display method when providing feedback, taking into account the participant's device information. For example, if the participant is using a smartphone, the feedback unit will select the optimal display method. For example, if the participant is using a tablet, the feedback unit will select the optimal display method. For example, if the participant is using a desktop computer, the feedback unit will select the optimal display method. By providing the optimal display method according to the device information, the visual burden can be reduced. 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 participant's device information into a generative AI and have the generative AI select the optimal display method.

[0085] The feedback unit can perform filtering during feedback to reduce the visual burden on participants. For example, the feedback unit can reduce the visual burden by adjusting the color of the feedback. For example, the feedback unit can reduce the visual burden by adjusting the brightness of the feedback. For example, the feedback unit can reduce the visual burden by adjusting the display time of the feedback. This reduces the visual burden and improves participant comfort. 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 participant visual burden data into a generative AI and have the generative AI perform the filtering.

[0086] The interactive unit can estimate the participant's emotions and dynamically adjust its interactive response based on those emotions. For example, if the participant is smiling, the interactive unit will adjust its interactive response to be more relaxed. For example, if the participant is surprised, the interactive unit will adjust its interactive response to include a more detailed explanation. For example, if the participant is angry, the interactive unit will adjust its interactive response to be calm and composed. This allows for appropriate responses by adjusting the interactive response based on emotions. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input the participant's emotional data into a generative AI and have the generative AI perform the adjustment of the interactive response.

[0087] The interactive unit can learn from the participant's past response data during interaction and select the optimal response method. For example, the interactive unit can learn from the participant's past response data and select the optimal timing for asking questions. For example, the interactive unit can learn from the participant's past response data and select the optimal method of explanation. For example, the interactive unit can learn from the participant's past response data and select the optimal interactive response method. In this way, the optimal response method can be selected by learning from past response data. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input the participant's past response data into a generative AI and have the generative AI select the optimal response method.

[0088] The interactive unit can customize its responses during interaction, taking into account the participant's current situation and interests. For example, the interactive unit customizes the optimal response according to the participant's current situation. For example, the interactive unit customizes the optimal response according to the participant's interests. For example, the interactive unit analyzes the participant's situation and interests in real time and customizes its responses. This improves participant satisfaction by providing responses that are tailored to their situation and interests. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input data on the participant's current situation and interests into a generative AI and have the generative AI perform the customization of the responses.

[0089] The interactive unit can estimate the participant's emotions and adjust the frequency of interactive responses based on the estimated emotions. For example, if the participant is smiling, the interactive unit will decrease the frequency of interactive responses. For example, if the participant is surprised, the interactive unit will increase the frequency of interactive responses. For example, if the participant is angry, the interactive unit will dynamically adjust the frequency of interactive responses. This allows for responses at an appropriate frequency by adjusting the frequency of interactive responses based on emotions. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input the participant's emotion data into a generative AI and have the generative AI perform the adjustment of the frequency of interactive responses.

[0090] The interactive unit can select the optimal response method during interaction, taking into account the participant's device information. For example, if the participant is using a smartphone, the interactive unit will select the optimal response method. For example, if the participant is using a tablet, the interactive unit will select the optimal response method. For example, if the participant is using a desktop computer, the interactive unit will select the optimal response method. This improves participant comfort by providing the optimal response method according to device information. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input the participant's device information into a generative AI and have the generative AI select the optimal response method.

[0091] The interactive unit can analyze participants' responses in real time during interaction and immediately change its response. For example, the interactive unit analyzes participants' responses in real time and immediately changes its response. For example, the interactive unit immediately changes the content of questions in response to participants' responses. For example, the interactive unit immediately changes the content of explanations in response to participants' responses. This enables appropriate responses by analyzing responses in real time and immediately changing the response. Some or all of the above processing in the interactive unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interactive unit can input participant response data into a generative AI and have the generative AI immediately change the response.

[0092] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0093] Online meeting systems can estimate participants' emotions and dynamically adjust the meeting's pace based on those estimates. For example, if participants are relaxed, the meeting can proceed smoothly. If participants are tense, the meeting can proceed slowly. If participants are excited, the meeting can proceed quickly. This improves participant comfort by adjusting the meeting pace based on emotions.

[0094] Online meeting systems can estimate participants' emotions and dynamically adjust the meeting content based on those estimates. For example, if participants are relaxed, the meeting content can be adjusted to be more relaxed. If participants are tense, the content can be adjusted to include more detailed explanations. If participants are excited, the meeting content can be moved quickly. By adjusting the meeting content based on emotions, participant satisfaction can be improved.

[0095] Online meeting systems can estimate participants' emotions and dynamically adjust the interactivity of the meeting based on those estimates. For example, if participants are relaxed, interactivity can be increased; if they are tense, interactivity can be decreased; and if they are excited, interactivity can be dynamically adjusted. This improves participant comfort by adjusting interactivity based on emotions.

[0096] Online meeting systems can estimate participants' emotions and dynamically adjust meeting feedback based on those estimates. For example, if a participant is relaxed, the feedback can be adjusted to be more relaxed. If a participant is tense, the feedback can be adjusted to include more detailed explanations. If a participant is excited, the feedback can be delivered quickly. This adjustment of feedback based on emotions improves participant satisfaction.

[0097] Online meeting systems can estimate participants' emotions and dynamically adjust the meeting timing based on those estimates. For example, if participants are relaxed, the meeting can be delayed. If participants are tense, the meeting can be brought forward. If participants are excited, the meeting timing can be dynamically adjusted. This improves participant comfort by adjusting the meeting timing based on emotions.

[0098] Online meeting systems can learn from participants' past meeting data and select the optimal meeting format. For example, they can learn from participants' past meeting data to select the optimal pace, content, and timing. This allows them to select the most effective meeting format by learning from past meeting data.

[0099] Online meeting systems can select the optimal meeting format by considering participants' device information. For example, if a participant is using a smartphone, the system can select the optimal format. If a participant is using a tablet, the system can select the optimal format. If a participant is using a desktop computer, the system can select the optimal format. This improves participant comfort by providing the most suitable meeting format based on device information.

[0100] Online meeting systems can customize the meeting design to take participants' visual preferences into account. For example, they can customize the meeting's colors, shape, and animations according to participants' visual preferences. This improves participant satisfaction by providing a meeting design that suits their visual preferences.

[0101] Online meeting systems can adjust the meeting flow by taking into account participants' background information. For example, if a participant's background is bright, the meeting can proceed smoothly. If a participant's background is complex, the meeting can proceed slowly. If a participant's background is moving, the meeting can proceed quickly. By providing a meeting flow that is tailored to background information, participant comfort is improved.

[0102] Online meeting systems can perform filtering to eliminate the influence of participants' clothing and accessories. For example, if a participant's clothing color is similar to their face color, the facial area can be emphasized to improve analysis accuracy. If a participant is wearing glasses, the reflection from the glasses can be removed to improve analysis accuracy. If a participant is wearing a hat, the influence of the hat can be eliminated to improve analysis accuracy. In this way, the accuracy of the analysis is improved by eliminating the influence of clothing and accessories.

[0103] The following briefly describes the processing flow for example form 2.

[0104] Step 1: The image analysis unit analyzes the participant's image to recognize emotions. For example, it can recognize emotions by analyzing facial expressions. The image analysis unit can use facial expression analysis algorithms and machine learning algorithms to analyze the movement of facial muscles and recognize emotions. It can also use deep learning to analyze facial expressions with high accuracy and recognize emotions. Step 2: The voice analysis unit analyzes the voice tone based on the emotions recognized by the image analysis unit. For example, it determines emotions by analyzing the participant's voice tone. The voice analysis unit analyzes emotions from the tone, volume, and speed of the voice. Voice feature extraction technology and acoustic models can be used to analyze voice tone and determine emotions. Step 3: The feedback unit provides visual feedback using color-coded frames based on the emotions analyzed by the voice analysis unit. For example, the frame color can change according to the emotion. A green frame if the participant is smiling, a yellow frame if they are surprised, a red frame if they are angry, and so on. The feedback unit can set color selection criteria and change the frame color according to the emotion. It can also recognize emotions in real time and change the frame color instantly.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] Each of the multiple elements described above, including the image analysis unit, voice analysis unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the image analysis unit acquires an image of the participant using the camera 42 of the smart device 14 and recognizes emotions by analyzing facial expressions with the specific processing unit 290 of the data processing unit 12. The voice analysis unit acquires the participant's voice using the microphone 38B of the smart device 14 and determines emotions by analyzing the voice tone with the specific processing unit 290 of the data processing unit 12. The feedback unit provides visual feedback using color-coded frames with the display 40A of the smart device 14. 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.

[0109] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] Each of the multiple elements described above, including the image analysis unit, voice analysis unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the image analysis unit acquires an image of the participant using the camera 42 of the smart glasses 214 and recognizes emotions by analyzing facial expressions with the identification processing unit 290 of the data processing unit 12. The voice analysis unit acquires the participant's voice using the microphone 238 of the smart glasses 214 and determines emotions by analyzing the voice tone with the identification processing unit 290 of the data processing unit 12. The feedback unit provides visual feedback using color-coded frames with the display of the smart glasses 214. 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.

[0125] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the image analysis unit, voice analysis unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the image analysis unit acquires an image of the participant using the camera 42 of the headset terminal 314 and recognizes emotions by analyzing facial expressions with the identification processing unit 290 of the data processing unit 12. The voice analysis unit acquires the participant's voice using the microphone 238 of the headset terminal 314 and determines emotions by analyzing the voice tone with the identification processing unit 290 of the data processing unit 12. The feedback unit provides visual feedback using color-coded frames with the display 343 of the headset terminal 314. 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.

[0141] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] Each of the multiple elements described above, including the image analysis unit, voice analysis unit, and feedback unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the image analysis unit acquires an image of the participant using the camera 42 of the robot 414 and recognizes emotions by analyzing facial expressions with the specific processing unit 290 of the data processing unit 12. The voice analysis unit acquires the participant's voice using the microphone 238 of the robot 414 and determines emotions by analyzing the voice tone with the specific processing unit 290 of the data processing unit 12. The feedback unit provides visual feedback using color-coded frames with the display of the robot 414. 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] (Note 1) The image analysis unit analyzes the participants' images to recognize their emotions, A voice analysis unit analyzes voice tone based on the emotions recognized by the image analysis unit, A feedback unit provides visual feedback using color-coded frames based on the emotions analyzed by the aforementioned voice analysis unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned image analysis unit, The system analyzes participants' facial expressions to recognize their emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned voice analysis unit, Analyze the participant's voice tone to determine their emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned feedback unit is The frame color changes according to the emotion. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback unit is It features an interactive section that responds to participants' reactions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned image analysis unit, It estimates the emotions of the participants and dynamically adjusts the accuracy of image analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned image analysis unit, The system learns from participants' past facial expression data and generates individual emotion recognition models. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned image analysis unit, During image analysis, the accuracy of the analysis is improved by taking into account the orientation of the participants' faces and lighting conditions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned image analysis unit, The system estimates the participants' emotions and adjusts the frequency of image analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned image analysis unit, When analyzing images, we improve the accuracy of emotion recognition by considering the participant's background information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned image analysis unit, During image analysis, filtering is performed to eliminate the influence of participants' clothing and accessories. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned voice analysis unit, The system estimates the participants' emotions and dynamically adjusts the parameters of the voice analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned voice analysis unit, The system learns from participants' past audio data and generates individualized emotion judgment models. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned voice analysis unit, During voice analysis, the accuracy of the analysis is improved by taking into account changes in the participant's speaking speed and volume. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned voice analysis unit, The system estimates the participants' emotions and adjusts the frequency of voice analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned voice analysis unit, During audio analysis, filtering is performed to remove background noise from participants. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned voice analysis unit, During voice analysis, we improve the accuracy of emotion judgments by taking into account the influence of participants' language and dialect. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned feedback unit is It estimates the participants' emotions and dynamically adjusts the color coding of feedback based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback unit is During feedback sessions, the system learns from participants' past response data to select the optimal feedback method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned feedback unit is When providing feedback, customize the feedback design to take into account the participants' visual preferences. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned feedback unit is The system estimates the participant's emotions and adjusts the timing of feedback display based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned feedback unit is During the feedback process, the optimal display method will be selected, taking into account the participant's device information. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned feedback unit is When providing feedback, filters are used to reduce the visual burden on participants. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned interactive unit is It estimates the emotions of participants and dynamically adjusts interactive responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned interactive unit is During interaction, the system learns from participants' past response data and selects the optimal response method. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned interactive unit is During interactive sessions, the response is customized to take into account the participant's current situation and interests. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned interactive unit is The system estimates the participants' emotions and adjusts the frequency of interactive responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned interactive unit is During interactive sessions, the system selects the optimal response method by considering the participant's device information. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned interactive unit is During interactive sessions, participant responses are analyzed in real time, and responses are immediately modified. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The image analysis unit analyzes the participants' images to recognize their emotions, A voice analysis unit analyzes voice tone based on the emotions recognized by the image analysis unit, The system includes a feedback unit that provides visual feedback using color-coded frames based on the emotions analyzed by the voice analysis unit. A system characterized by the following features.

2. The aforementioned image analysis unit, The system analyzes participants' facial expressions to recognize their emotions. The system according to feature 1.

3. The aforementioned voice analysis unit, Analyze the participant's voice tone to determine their emotions. The system according to feature 1.

4. The aforementioned feedback unit is The frame color changes according to the emotion. The system according to feature 1.

5. The aforementioned feedback unit is It features an interactive section that responds to participants' reactions. The system according to feature 1.

6. The aforementioned image analysis unit, It estimates the emotions of the participants and dynamically adjusts the accuracy of image analysis based on the estimated emotions. The system according to feature 1.

7. The aforementioned image analysis unit, The system learns from participants' past facial expression data and generates individual emotion recognition models. The system according to feature 1.

8. The aforementioned image analysis unit, During image analysis, the accuracy of the analysis is improved by taking into account the orientation of the participants' faces and lighting conditions. The system according to feature 1.

9. The aforementioned image analysis unit, The system estimates the participants' emotions and adjusts the frequency of image analysis based on the estimated emotions. The system according to feature 1.

10. The aforementioned image analysis unit, When analyzing images, we improve the accuracy of emotion recognition by considering the participant's background information. The system according to feature 1.

Images