system

Abstract

The system according to this embodiment aims to evaluate presentations in real time and propose improvement measures. [Solution] The system according to the embodiment comprises an audio analysis unit, a video analysis unit, a structural evaluation unit, and a custom feedback unit. The audio analysis unit analyzes the audio of the presentation. The video analysis unit analyzes the video of the presentation based on the results analyzed by the audio analysis unit. The structural evaluation unit evaluates the structure of the presentation based on the results analyzed by the video analysis unit. The custom feedback unit makes individual improvement suggestions based on the results evaluated by the structural evaluation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that feedback for improving the presentation ability is insufficient and the opportunity for practice is limited.

[0005] The system according to the embodiment aims to evaluate a presentation in real time and propose improvement measures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an audio analysis unit, a video analysis unit, a structural evaluation unit, and a custom feedback unit. The audio analysis unit analyzes the audio of the presentation. The video analysis unit analyzes the video of the presentation based on the results analyzed by the audio analysis unit. The structural evaluation unit evaluates the structure of the presentation based on the results analyzed by the video analysis unit. The custom feedback unit makes individual improvement suggestions based on the results evaluated by the structural evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can evaluate presentations in real time and suggest improvements. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The presentation skills improvement system according to an embodiment of the present invention is a mechanism for improving presentation skills using an AI agent. When a user gives a presentation, the AI ​​agent analyzes the audio and video in real time and immediately proposes improvements to the presentation based on the analysis results. This mechanism allows users to improve their presentation skills to a higher quality. For example, when a user gives a presentation, the AI ​​agent analyzes the audio and video in real time. For instance, the audio analysis evaluates word choice and clarity of pronunciation, while the video analysis evaluates the optimization of gestures, eye gaze, and posture. This allows for a detailed analysis of each element of the presentation. Next, based on the analysis results, the AI ​​agent immediately proposes improvements to the presentation. For example, based on the audio analysis results, it suggests improvements to word choice and pronunciation, and based on the video analysis results, it suggests improvements to gestures, eye gaze, and posture. It can also evaluate the logical structure of the presentation and suggest improvements to the logical flow and structure. Furthermore, the presentation skills improvement system provides customized feedback to make individual improvement suggestions. For example, it can suggest training focused on specific skills to effectively improve the user's presentation skills. This system allows users to continuously improve their presentation skills. By receiving real-time feedback, it can combine self-assessment with peer evaluation and provide a personalized learning path powered by AI. This enables more persuasive presentations, which can contribute to improved performance and strengthen corporate branding. For example, corporate presenters can use this system to improve the quality of their presentations and significantly impact the company's image. Furthermore, for presenters who have limited opportunities to objectively understand their shortcomings, the real-time evaluation and improvement suggestions from the AI ​​agent are extremely beneficial.In this way, by using AI agents, companies can provide presenters with innovative growth opportunities and increase corporate value through limitless ways of communication. This invention is extremely useful as an effective tool for acquiring new presentation skills in the digital age. As a result, the presentation skills improvement system can effectively improve the presentation abilities of users.

[0029] The presentation ability improvement system according to this embodiment comprises an audio analysis unit, a video analysis unit, a structure evaluation unit, and a custom feedback unit. The audio analysis unit analyzes the audio of the presentation. The audio analysis unit analyzes the audio data using, for example, speech recognition technology and evaluates word choice and clarity of pronunciation. The audio analysis unit can, for example, extract audio features and evaluate the use of appropriate vocabulary and clarity of pronunciation. The audio analysis unit can also, for example, detect the presence or absence of audio distortion and evaluate audio quality. The video analysis unit analyzes the video of the presentation based on the results analyzed by the audio analysis unit. The video analysis unit analyzes the video data using, for example, image recognition technology and evaluates the optimization of gestures, gaze, and posture. The video analysis unit can, for example, extract video features and evaluate the appropriateness of hand movements and direction of gaze. The video analysis unit can also, for example, evaluate the appropriateness of standing posture and body movements. The structure evaluation unit evaluates the structure of the presentation based on the results analyzed by the video analysis unit. The structure evaluation unit evaluates the logical flow of the presentation using, for example, a logical structure analysis method. The structural evaluation unit can, for example, evaluate the appropriateness of the flow of information and the consistency of the logic. The structural evaluation unit can also, for example, evaluate the relationships between the components of a presentation. The custom feedback unit makes individual improvement suggestions based on the results evaluated by the structural evaluation unit. The custom feedback unit can, for example, suggest training that focuses on specific skills to effectively improve the user's presentation ability. The custom feedback unit can, for example, provide real-time feedback so that the user can immediately grasp areas for improvement. The custom feedback unit can, for example, combine self-evaluation and peer evaluation to provide more objective and effective feedback. The custom feedback unit can, for example, provide a personalized learning path to support effective learning tailored to the user's individual needs. As a result, the presentation ability improvement system according to the embodiment can effectively improve the user's presentation ability.

[0030] The audio analysis unit analyzes the audio of a presentation. For example, it uses speech recognition technology to analyze audio data and evaluate word choice and pronunciation clarity. Specifically, the audio analysis unit collects audio data in real time and converts it into text using a speech recognition engine. Based on this text data, it evaluates the diversity and appropriateness of the vocabulary used. It also extracts audio features and analyzes parameters such as pitch, rhythm, and stress to evaluate pronunciation clarity and emotional expression. Furthermore, the audio analysis unit detects the presence or absence of distortion and noise in the audio, evaluating audio quality. This allows users to understand their own pronunciation and speaking habits and clearly identify areas for improvement. The audio analysis unit can perform more accurate evaluations by using AI to analyze audio data and learn the user's speaking patterns and characteristics. For example, if a user tends to repeatedly use certain words, it will point this out and encourage the use of more appropriate vocabulary. The audio analysis unit is also designed to support different languages ​​and accents, enabling it to provide effective feedback to a global user base. This allows the voice analysis unit to play a crucial role in improving the user's presentation skills.

[0031] The video analysis unit analyzes the presentation video based on the results analyzed by the audio analysis unit. For example, the video analysis unit uses image recognition technology to analyze video data and evaluate the optimization of gestures, eye movements, and posture. Specifically, the video analysis unit uses cameras to collect video of the user during the presentation in real time and analyzes gestures and eye movements using image recognition algorithms. For example, it evaluates the appropriateness of hand movements and the direction of eye movements, providing advice to help the user effectively convey their message to the audience. The video analysis unit also evaluates the appropriateness of the user's posture and body movements, pointing out areas for improvement in posture and movements during the presentation. Furthermore, the video analysis unit analyzes the user's facial expressions and emotional expressions, providing feedback to enhance the impact of the presentation. For example, it evaluates the frequency of smiles and eye contact, providing advice to facilitate smoother communication with the audience. By using AI to analyze video data and learning the user's movement and facial expression patterns, the video analysis unit can perform more accurate evaluations. This allows the video analysis unit to play a crucial role in comprehensively improving the user's presentation skills.

[0032] The Structural Evaluation Unit evaluates the structure of a presentation based on the results analyzed by the Video Analysis Unit. For example, the Structural Evaluation Unit evaluates the logical flow of a presentation using methods for analyzing logical structure. Specifically, the Structural Evaluation Unit analyzes the presentation slides and script to evaluate the flow of information and logical consistency. For example, it evaluates whether each section of the presentation is appropriately related and whether the information is logically developed. The Structural Evaluation Unit can also evaluate the relationships between the components of the presentation and confirm whether important points are clearly communicated. Furthermore, the Structural Evaluation Unit can use AI to learn from past presentation data and extract patterns of effective presentations, thereby providing users with specific improvement suggestions. For example, it can evaluate whether the introduction of the presentation is effective in attracting the audience's attention and whether the conclusion is clear, and point out areas for improvement. In this way, the Structural Evaluation Unit can play an important role in improving the logical flow of the user's presentation and achieving more effective presentations.

[0033] The Custom Feedback Unit provides individual improvement suggestions based on the results evaluated by the Structural Evaluation Unit. For example, the Custom Feedback Unit proposes training that focuses on specific skills, effectively improving the user's presentation abilities. Specifically, based on the user's evaluation results, the Custom Feedback Unit provides training plans tailored to individual needs, such as improving pronunciation, optimizing gestures, and strengthening logical structure. The Custom Feedback Unit also provides real-time feedback, allowing users to immediately understand areas for improvement. For example, it displays the results of audio and video analysis in real time during a presentation, allowing users to make corrections on the spot. Furthermore, the Custom Feedback Unit can combine self-evaluation and peer evaluation to provide more objective and effective feedback. For example, it can compare the user's own evaluation with the results analyzed by AI to clarify areas for improvement. The Custom Feedback Unit also provides personalized learning paths, supporting effective learning tailored to the user's individual needs. In this way, the Custom Feedback Unit can play a crucial role in comprehensively improving the user's presentation abilities.

[0034] The speech analysis unit can evaluate word choice and pronunciation clarity. For example, the speech analysis unit can analyze speech data using speech recognition technology and evaluate the use of appropriate vocabulary. The speech analysis unit can also evaluate pronunciation clarity and detect the presence or absence of speech distortion. The speech analysis unit can also extract speech features and evaluate speech quality. This allows the speech analysis unit to improve the speech quality of a presentation by evaluating word choice and pronunciation clarity. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech analysis unit can input speech data into a generative AI, which can then analyze the speech data and evaluate word choice and pronunciation clarity.

[0035] The video analysis unit can evaluate the optimization of gestures, gaze, and posture. For example, the video analysis unit can analyze video data using image recognition technology to evaluate the appropriateness of hand movements. For example, the video analysis unit can evaluate the direction of gaze and assess the appropriateness of gaze movement. For example, the video analysis unit can evaluate the appropriateness of standing posture and body movements. As a result, the video analysis unit can improve the visual elements of a presentation by evaluating the optimization of gestures, gaze, and posture. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input video data into a generative AI, and the generative AI can analyze the video data to evaluate the optimization of gestures, gaze, and posture.

[0036] The structural evaluation unit can evaluate the logical structure of a presentation. For example, the structural evaluation unit evaluates the logical flow of a presentation using a method for analyzing logical structure. The structural evaluation unit can also evaluate the appropriateness of the flow of information and the logical consistency. The structural evaluation unit can also evaluate the relationships between the components of a presentation. In this way, the structural evaluation unit can improve the logical flow of a presentation by evaluating its logical structure. Some or all of the above-described processes in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input the components of a presentation into a generative AI, and the generative AI can evaluate the relationships between the components to evaluate the logical structure of the presentation.

[0037] The custom feedback unit can suggest training that focuses on specific skills. For example, to improve a user's presentation skills, the custom feedback unit can suggest training that focuses on speaking skills. For example, the custom feedback unit can also suggest training that focuses on visual presentation skills. For example, the custom feedback unit can also suggest training that focuses on logical structuring skills. In this way, the custom feedback unit can effectively improve a user's presentation skills by suggesting training that focuses on specific skills. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the custom feedback unit can input the user's presentation data into a generative AI, and the generative AI can suggest training that focuses on specific skills.

[0038] The custom feedback unit can provide feedback in real time. For example, it can provide feedback in real time while the user is giving a presentation. The custom feedback unit can adjust the timing of the feedback so that the user can immediately grasp areas for improvement. The custom feedback unit can also appropriately adjust the content of the feedback so that the user can effectively understand areas for improvement. As a result, by providing feedback in real time, the custom feedback unit allows the user to immediately grasp areas for improvement and improve their presentation skills. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the custom feedback unit can input the user's presentation data into a generative AI, and the generative AI can provide feedback in real time.

[0039] The custom feedback unit can integrate self-assessment and peer assessment. For example, the custom feedback unit can integrate the results of a user's self-assessment with the assessments made by others to provide comprehensive feedback. For example, the custom feedback unit can compare items from self-assessment and items from peer assessment to clarify the points of agreement and disagreement in the assessments. For example, the custom feedback unit can also specifically indicate the user's strengths and areas for improvement based on the results of self-assessment and peer assessment. In this way, the custom feedback unit can provide more objective and effective feedback by integrating self-assessment and peer assessment. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the custom feedback unit can input self-assessment and peer assessment data into a generative AI, and the generative AI can integrate the evaluation results and provide feedback.

[0040] The custom feedback unit can provide personalized learning paths. For example, the custom feedback unit can design individual learning paths to improve a user's presentation skills. For example, the custom feedback unit can manage a user's learning progress and suggest the next learning step at the appropriate time. For example, the custom feedback unit can customize learning content according to the user's needs to support effective learning. In this way, by providing personalized learning paths, the custom feedback unit can support effective learning tailored to the user's individual needs. Some or all of the above processing in the custom feedback unit may be performed using, for example, generative AI, or without generative AI. For example, the custom feedback unit can input user learning data into a generative AI, which can then design and provide a personalized learning path.

[0041] The voice analysis unit can select the optimal voice analysis method by referring to the user's past presentation history during voice analysis. For example, the voice analysis unit can select the optimal analysis method based on the voice analysis algorithm the user has used in the past. For example, the voice analysis unit can also select an analysis method that emphasizes specific voice characteristics from the user's past presentation history. For example, the voice analysis unit can analyze the user's past presentation history and select the most effective voice analysis method. This allows for the selection of the optimal voice analysis method and improvement of analysis accuracy by referring to the user's past presentation history. 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 user's past presentation history data into a generative AI, which can then select the optimal voice analysis method.

[0042] The speech analysis unit can apply different speech analysis algorithms depending on the content of the presentation during speech analysis. For example, in the case of a technical presentation, the speech analysis unit can apply a speech analysis algorithm that emphasizes the pronunciation of technical terms. For example, in the case of an emotional presentation, the speech analysis unit can also apply a speech analysis algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the speech analysis unit can also apply a speech analysis algorithm that emphasizes clear pronunciation. This improves the accuracy of the analysis by applying a speech analysis algorithm appropriate to the content of the presentation. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech analysis unit can input the content data of the presentation into a generative AI, and the generative AI can apply a speech analysis algorithm appropriate to the content.

[0043] The voice analysis unit can evaluate the accent and intonation of a voice based on the user's geographical background during voice analysis. For example, if the user has an accent from a different region, the voice analysis unit will take that accent into consideration during the analysis. For example, if the user speaks multiple languages, the voice analysis unit can also evaluate the intonation of each language. For example, if the user has pronunciation characteristics from a specific region, the voice analysis unit can also take those characteristics into consideration during the analysis. This improves the accuracy of the analysis by evaluating the accent and intonation of a voice based on the user's geographical background. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the voice analysis unit can input the user's geographical background data into a generative AI, and the generative AI can evaluate the accent and intonation of the voice.

[0044] The voice analysis unit can analyze the user's social media activity and evaluate relevant voice characteristics during voice analysis. For example, the voice analysis unit can evaluate voice characteristics based on the language used by the user on social media. The voice analysis unit can also analyze the content of the user's social media posts and evaluate relevant voice characteristics. The voice analysis unit can also evaluate voice characteristics based on the frequency of the user's social media activity. This allows for the evaluation of relevant voice characteristics and improvement of analysis accuracy by analyzing the user's social media activity. 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 user's social media activity data into a generative AI, which can then evaluate the voice characteristics.

[0045] The video analysis unit can select the optimal video analysis method by referring to the user's past video history during video analysis. For example, the video analysis unit can select the optimal analysis method based on video analysis algorithms previously used by the user. For example, the video analysis unit can also select an analysis method that emphasizes specific video characteristics from the user's past video history. For example, the video analysis unit can analyze the user's past video history and select the most effective video analysis method. This allows for the selection of the optimal video analysis method and improvement of analysis accuracy by referring to the user's past video history. Some or all of the above-described processes in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input the user's past video history data into a generative AI, which can then select the optimal video analysis method.

[0046] The video analysis unit can apply different video analysis algorithms depending on the content of the presentation during video analysis. For example, in the case of a technical presentation, the video analysis unit can apply a video analysis algorithm that emphasizes professional gestures. For example, in the case of an emotional presentation, the video analysis unit can also apply a video analysis algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the video analysis unit can also apply a video analysis algorithm that emphasizes visual clarity. By applying a video analysis algorithm appropriate to the content of the presentation, the accuracy of the analysis can be improved. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input presentation content data into a generative AI, and the generative AI can apply a video analysis algorithm appropriate to the content.

[0047] The video analysis unit can evaluate the background and environment of a video based on the user's geographical background during video analysis. For example, if the user has a different regional background, the video analysis unit will take that background into consideration during the analysis. For example, if the user speaks multiple languages, the video analysis unit can also evaluate the background of each language. For example, if the user has video characteristics specific to a particular region, the video analysis unit can also take those characteristics into consideration during the analysis. This improves the accuracy of the analysis by evaluating the background and environment of the video based on the user's geographical background. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the video analysis unit can input the user's geographical background data into a generative AI, and the generative AI can evaluate the background and environment of the video.

[0048] The video analysis unit can analyze the user's social media activity and evaluate relevant video characteristics during video analysis. For example, the video analysis unit can evaluate video characteristics based on the video style used by the user on social media. The video analysis unit can also analyze the content of the user's social media posts and evaluate relevant video characteristics. The video analysis unit can also evaluate video characteristics based on the frequency of the user's social media activity. This allows for the evaluation of relevant video characteristics and improvement of analysis accuracy by analyzing the user's social media activity. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input the user's social media activity data into a generative AI, which can then evaluate the video characteristics.

[0049] The structural evaluation unit can select the optimal structural evaluation method by referring to the user's past presentation history during structural evaluation. For example, the structural evaluation unit can select the optimal evaluation method based on the structural evaluation algorithm previously used by the user. For example, the structural evaluation unit can also select an evaluation method that emphasizes specific structural characteristics from the user's past presentation history. For example, the structural evaluation unit can analyze the user's past presentation history and select the most effective structural evaluation method. This allows for the selection of the optimal structural evaluation method and improvement of evaluation accuracy by referring to the user's past presentation history. Some or all of the above processing in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input the user's past presentation history data into a generative AI, which can then select the optimal structural evaluation method.

[0050] The structural evaluation unit can apply different structural evaluation algorithms depending on the content of the presentation during structural evaluation. For example, in the case of a technical presentation, the structural evaluation unit applies a structural evaluation algorithm that emphasizes logical flow. For example, in the case of an emotional presentation, the structural evaluation unit can also apply a structural evaluation algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the structural evaluation unit can also apply a structural evaluation algorithm that emphasizes clear explanation. By applying a structural evaluation algorithm appropriate to the content of the presentation, the evaluation accuracy can be improved. Some or all of the above processing in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input presentation content data into a generative AI, and the generative AI can apply a structural evaluation algorithm appropriate to the content.

[0051] The structural evaluation unit can evaluate the content of a presentation based on the user's geographical background during structural evaluation. For example, if the user has a different regional background, the structural evaluation unit will take that background into consideration during the evaluation. For example, if the user speaks multiple languages, the structural evaluation unit can also evaluate the background of each language. For example, if the user has presentation characteristics specific to a particular region, the structural evaluation unit can also take those characteristics into consideration during the evaluation. This improves the accuracy of the evaluation by evaluating the content of the presentation based on the user's geographical background. Some or all of the above processing in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input the user's geographical background data into a generative AI, and the generative AI can evaluate the content of the presentation.

[0052] The structure evaluation unit can analyze the user's social media activity and evaluate relevant structural characteristics during structure evaluation. For example, the structure evaluation unit can evaluate structural characteristics based on the presentation style used by the user on social media. The structure evaluation unit can also analyze the content of the user's social media posts and evaluate relevant structural characteristics. The structure evaluation unit can also evaluate structural characteristics based on the frequency of the user's social media activity. This allows for the evaluation of relevant structural characteristics and improvement of evaluation accuracy by analyzing the user's social media activity. Some or all of the above processing in the structure evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structure evaluation unit can input the user's social media activity data into a generative AI, which can then evaluate the structural characteristics.

[0053] The custom feedback unit can select the optimal feedback method by referring to the user's past feedback history when providing custom feedback. For example, the custom feedback unit can select the optimal feedback method based on feedback the user has received in the past. For example, the custom feedback unit can also select a method to emphasize specific feedback characteristics from the user's past feedback history. For example, the custom feedback unit can analyze the user's past feedback history and select the most effective feedback method. This allows for the selection of the optimal feedback method and improvement of feedback accuracy by referring to the user's past feedback history. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input the user's past feedback history data into a generative AI, which can then select the optimal feedback method.

[0054] The custom feedback unit can apply different feedback algorithms depending on the content of the presentation when providing custom feedback. For example, in the case of a technical presentation, the custom feedback unit can apply an algorithm that provides expert feedback. For example, in the case of an emotional presentation, the custom feedback unit can also apply a feedback algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the custom feedback unit can also apply a feedback algorithm that emphasizes clear explanation. This improves the accuracy of feedback by applying a feedback algorithm that is appropriate to the content of the presentation. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input presentation content data into a generative AI, and the generative AI can apply a feedback algorithm appropriate to the content.

[0055] The custom feedback unit can adjust the content of feedback based on the user's geographical background when providing custom feedback. For example, if the user has a different regional background, the custom feedback unit will take that background into consideration when providing feedback. For example, if the user speaks multiple languages, the custom feedback unit can also take the background of each language into consideration when providing feedback. For example, if the user has feedback characteristics specific to a particular region, the custom feedback unit can also take those characteristics into consideration when providing feedback. By adjusting the content of feedback based on the user's geographical background, the accuracy of the feedback can be improved. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input the user's geographical background data into a generative AI, and the generative AI can adjust the content of the feedback.

[0056] The custom feedback unit can analyze the user's social media activity and provide relevant feedback when providing custom feedback. For example, the custom feedback unit can provide feedback based on the language the user uses on social media. The custom feedback unit can also analyze the content of the user's social media posts and provide relevant feedback. The custom feedback unit can also provide feedback based on the frequency of the user's social media activity. This allows for the provision of relevant feedback and improved feedback accuracy by analyzing the user's social media activity. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input the user's social media activity data into a generative AI, which can then provide relevant feedback.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The presentation skills improvement system can analyze a user's past presentation data and provide an optimal training plan. For example, it can create a training plan that focuses on specific skills based on data from past presentations. It can also provide a training plan to strengthen areas where the user has struggled in the past. Furthermore, it can monitor the user's progress in real time and adjust the training plan as needed. This allows for the use of the user's past data to provide effective training tailored to individual needs.

[0059] The presentation skills improvement system can analyze a user's presentation style and suggest the most suitable presentation tools. For example, if a user prefers visual presentations, the system will suggest tools that heavily utilize graphics and visual aids. If a user prioritizes audio, the system can also suggest audio enhancement tools. Furthermore, if a user prefers interactive presentations, the system can suggest interactive tools. In this way, by suggesting the most suitable tools according to the user's presentation style, the quality of presentations can be improved.

[0060] The presentation skills improvement system allows users to save their presentation data to the cloud and share it with other users. For example, users can upload presentations they have created to the cloud, and other users can view those presentations and provide feedback. Users can also improve their own presentations by referring to presentations by other users. Furthermore, collaborative editing of presentations can be performed on the cloud, allowing multiple users to create presentations together. In this way, the quality of presentations can be improved by saving presentation data to the cloud and sharing it with other users.

[0061] The presentation skills improvement system can analyze a user's presentation data and suggest an optimal presentation schedule. For example, it can suggest the optimal presentation time based on data from the user's past presentations. It can also analyze the time slots of successful presentations in the past and suggest presenting during those times. Furthermore, it can suggest an optimal presentation schedule considering the user's schedule. In this way, by utilizing the user's presentation data to suggest an optimal presentation schedule, the success rate of presentations can be improved.

[0062] The presentation skills improvement system can analyze a user's presentation data and suggest the optimal presentation template. For example, it can suggest the best template based on the user's past presentations. It can also analyze templates from successful past presentations and suggest those templates. Furthermore, it can suggest the best template according to the content of the user's presentation. In this way, by utilizing the user's presentation data and suggesting the optimal presentation template, the quality of presentations can be improved.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The audio analysis unit analyzes the audio of the presentation. For example, it analyzes the audio data using speech recognition technology to evaluate word choice and pronunciation clarity. It can extract audio features and evaluate the appropriate use of vocabulary and pronunciation clarity. It can also detect the presence or absence of audio distortion and evaluate audio quality. Step 2: The video analysis unit analyzes the presentation video based on the results analyzed by the audio analysis unit. For example, it uses image recognition technology to analyze the video data and evaluate the optimization of gestures, gaze, and posture. It can extract video features and evaluate the appropriateness of hand movements and the direction of gaze. It can also evaluate the appropriateness of standing posture and body movements. Step 3: The structural evaluation unit evaluates the structure of the presentation based on the results analyzed by the video analysis unit. For example, it evaluates the logical flow of the presentation using a logical structure analysis method. It can evaluate the appropriateness of the information flow and the consistency of the logic. It can also evaluate the relationships between the components of the presentation. Step 4: The Custom Feedback Department makes individual improvement suggestions based on the results evaluated by the Structural Evaluation Department. For example, it may suggest training focused on specific skills to effectively improve the user's presentation abilities. It provides real-time feedback so that users can immediately understand areas for improvement. It can combine self-assessment and peer assessment to provide more objective and effective feedback. It provides personalized learning paths to support effective learning tailored to the user's individual needs.

[0065] (Example of form 2) The presentation skills improvement system according to an embodiment of the present invention is a mechanism for improving presentation skills using an AI agent. When a user gives a presentation, the AI ​​agent analyzes the audio and video in real time and immediately proposes improvements to the presentation based on the analysis results. This mechanism allows users to improve their presentation skills to a higher quality. For example, when a user gives a presentation, the AI ​​agent analyzes the audio and video in real time. For instance, the audio analysis evaluates word choice and clarity of pronunciation, while the video analysis evaluates the optimization of gestures, eye gaze, and posture. This allows for a detailed analysis of each element of the presentation. Next, based on the analysis results, the AI ​​agent immediately proposes improvements to the presentation. For example, based on the audio analysis results, it suggests improvements to word choice and pronunciation, and based on the video analysis results, it suggests improvements to gestures, eye gaze, and posture. It can also evaluate the logical structure of the presentation and suggest improvements to the logical flow and structure. Furthermore, the presentation skills improvement system provides customized feedback to make individual improvement suggestions. For example, it can suggest training focused on specific skills to effectively improve the user's presentation skills. This system allows users to continuously improve their presentation skills. By receiving real-time feedback, it can combine self-assessment with peer evaluation and provide a personalized learning path powered by AI. This enables more persuasive presentations, which can contribute to improved performance and strengthen corporate branding. For example, corporate presenters can use this system to improve the quality of their presentations and significantly impact the company's image. Furthermore, for presenters who have limited opportunities to objectively understand their shortcomings, the real-time evaluation and improvement suggestions from the AI ​​agent are extremely beneficial.In this way, by using AI agents, companies can provide presenters with innovative growth opportunities and increase corporate value through limitless ways of communication. This invention is extremely useful as an effective tool for acquiring new presentation skills in the digital age. As a result, the presentation skills improvement system can effectively improve the presentation abilities of users.

[0066] The presentation ability improvement system according to this embodiment comprises an audio analysis unit, a video analysis unit, a structure evaluation unit, and a custom feedback unit. The audio analysis unit analyzes the audio of the presentation. The audio analysis unit analyzes the audio data using, for example, speech recognition technology and evaluates word choice and clarity of pronunciation. The audio analysis unit can, for example, extract audio features and evaluate the use of appropriate vocabulary and clarity of pronunciation. The audio analysis unit can also, for example, detect the presence or absence of audio distortion and evaluate audio quality. The video analysis unit analyzes the video of the presentation based on the results analyzed by the audio analysis unit. The video analysis unit analyzes the video data using, for example, image recognition technology and evaluates the optimization of gestures, gaze, and posture. The video analysis unit can, for example, extract video features and evaluate the appropriateness of hand movements and direction of gaze. The video analysis unit can also, for example, evaluate the appropriateness of standing posture and body movements. The structure evaluation unit evaluates the structure of the presentation based on the results analyzed by the video analysis unit. The structure evaluation unit evaluates the logical flow of the presentation using, for example, a logical structure analysis method. The structural evaluation unit can, for example, evaluate the appropriateness of the flow of information and the consistency of the logic. The structural evaluation unit can also, for example, evaluate the relationships between the components of a presentation. The custom feedback unit makes individual improvement suggestions based on the results evaluated by the structural evaluation unit. The custom feedback unit can, for example, suggest training that focuses on specific skills to effectively improve the user's presentation ability. The custom feedback unit can, for example, provide real-time feedback so that the user can immediately grasp areas for improvement. The custom feedback unit can, for example, combine self-evaluation and peer evaluation to provide more objective and effective feedback. The custom feedback unit can, for example, provide a personalized learning path to support effective learning tailored to the user's individual needs. As a result, the presentation ability improvement system according to the embodiment can effectively improve the user's presentation ability.

[0067] The audio analysis unit analyzes the audio of a presentation. For example, it uses speech recognition technology to analyze audio data and evaluate word choice and pronunciation clarity. Specifically, the audio analysis unit collects audio data in real time and converts it into text using a speech recognition engine. Based on this text data, it evaluates the diversity and appropriateness of the vocabulary used. It also extracts audio features and analyzes parameters such as pitch, rhythm, and stress to evaluate pronunciation clarity and emotional expression. Furthermore, the audio analysis unit detects the presence or absence of distortion and noise in the audio, evaluating audio quality. This allows users to understand their own pronunciation and speaking habits and clearly identify areas for improvement. The audio analysis unit can perform more accurate evaluations by using AI to analyze audio data and learn the user's speaking patterns and characteristics. For example, if a user tends to repeatedly use certain words, it will point this out and encourage the use of more appropriate vocabulary. The audio analysis unit is also designed to support different languages ​​and accents, enabling it to provide effective feedback to a global user base. This allows the voice analysis unit to play a crucial role in improving the user's presentation skills.

[0068] The video analysis unit analyzes the presentation video based on the results analyzed by the audio analysis unit. For example, the video analysis unit uses image recognition technology to analyze video data and evaluate the optimization of gestures, eye movements, and posture. Specifically, the video analysis unit uses cameras to collect video of the user during the presentation in real time and analyzes gestures and eye movements using image recognition algorithms. For example, it evaluates the appropriateness of hand movements and the direction of eye movements, providing advice to help the user effectively convey their message to the audience. The video analysis unit also evaluates the appropriateness of the user's posture and body movements, pointing out areas for improvement in posture and movements during the presentation. Furthermore, the video analysis unit analyzes the user's facial expressions and emotional expressions, providing feedback to enhance the impact of the presentation. For example, it evaluates the frequency of smiles and eye contact, providing advice to facilitate smoother communication with the audience. By using AI to analyze video data and learning the user's movement and facial expression patterns, the video analysis unit can perform more accurate evaluations. This allows the video analysis unit to play a crucial role in comprehensively improving the user's presentation skills.

[0069] The Structural Evaluation Unit evaluates the structure of a presentation based on the results analyzed by the Video Analysis Unit. For example, the Structural Evaluation Unit evaluates the logical flow of a presentation using methods for analyzing logical structure. Specifically, the Structural Evaluation Unit analyzes the presentation slides and script to evaluate the flow of information and logical consistency. For example, it evaluates whether each section of the presentation is appropriately related and whether the information is logically developed. The Structural Evaluation Unit can also evaluate the relationships between the components of the presentation and confirm whether important points are clearly communicated. Furthermore, the Structural Evaluation Unit can use AI to learn from past presentation data and extract patterns of effective presentations, thereby providing users with specific improvement suggestions. For example, it can evaluate whether the introduction of the presentation is effective in attracting the audience's attention and whether the conclusion is clear, and point out areas for improvement. In this way, the Structural Evaluation Unit can play an important role in improving the logical flow of the user's presentation and achieving more effective presentations.

[0070] The Custom Feedback Unit provides individual improvement suggestions based on the results evaluated by the Structural Evaluation Unit. For example, the Custom Feedback Unit proposes training that focuses on specific skills, effectively improving the user's presentation abilities. Specifically, based on the user's evaluation results, the Custom Feedback Unit provides training plans tailored to individual needs, such as improving pronunciation, optimizing gestures, and strengthening logical structure. The Custom Feedback Unit also provides real-time feedback, allowing users to immediately understand areas for improvement. For example, it displays the results of audio and video analysis in real time during a presentation, allowing users to make corrections on the spot. Furthermore, the Custom Feedback Unit can combine self-evaluation and peer evaluation to provide more objective and effective feedback. For example, it can compare the user's own evaluation with the results analyzed by AI to clarify areas for improvement. The Custom Feedback Unit also provides personalized learning paths, supporting effective learning tailored to the user's individual needs. In this way, the Custom Feedback Unit can play a crucial role in comprehensively improving the user's presentation abilities.

[0071] The speech analysis unit can evaluate word choice and pronunciation clarity. For example, the speech analysis unit can analyze speech data using speech recognition technology and evaluate the use of appropriate vocabulary. The speech analysis unit can also evaluate pronunciation clarity and detect the presence or absence of speech distortion. The speech analysis unit can also extract speech features and evaluate speech quality. This allows the speech analysis unit to improve the speech quality of a presentation by evaluating word choice and pronunciation clarity. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech analysis unit can input speech data into a generative AI, which can then analyze the speech data and evaluate word choice and pronunciation clarity.

[0072] The video analysis unit can evaluate the optimization of gestures, gaze, and posture. For example, the video analysis unit can analyze video data using image recognition technology to evaluate the appropriateness of hand movements. For example, the video analysis unit can evaluate the direction of gaze and assess the appropriateness of gaze movement. For example, the video analysis unit can evaluate the appropriateness of standing posture and body movements. As a result, the video analysis unit can improve the visual elements of a presentation by evaluating the optimization of gestures, gaze, and posture. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input video data into a generative AI, and the generative AI can analyze the video data to evaluate the optimization of gestures, gaze, and posture.

[0073] The structural evaluation unit can evaluate the logical structure of a presentation. For example, the structural evaluation unit evaluates the logical flow of a presentation using a method for analyzing logical structure. The structural evaluation unit can also evaluate the appropriateness of the flow of information and the logical consistency. The structural evaluation unit can also evaluate the relationships between the components of a presentation. In this way, the structural evaluation unit can improve the logical flow of a presentation by evaluating its logical structure. Some or all of the above-described processes in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input the components of a presentation into a generative AI, and the generative AI can evaluate the relationships between the components to evaluate the logical structure of the presentation.

[0074] The custom feedback unit can suggest training that focuses on specific skills. For example, to improve a user's presentation skills, the custom feedback unit can suggest training that focuses on speaking skills. For example, the custom feedback unit can also suggest training that focuses on visual presentation skills. For example, the custom feedback unit can also suggest training that focuses on logical structuring skills. In this way, the custom feedback unit can effectively improve a user's presentation skills by suggesting training that focuses on specific skills. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the custom feedback unit can input the user's presentation data into a generative AI, and the generative AI can suggest training that focuses on specific skills.

[0075] The custom feedback unit can provide feedback in real time. For example, it can provide feedback in real time while the user is giving a presentation. The custom feedback unit can adjust the timing of the feedback so that the user can immediately grasp areas for improvement. The custom feedback unit can also appropriately adjust the content of the feedback so that the user can effectively understand areas for improvement. As a result, by providing feedback in real time, the custom feedback unit allows the user to immediately grasp areas for improvement and improve their presentation skills. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the custom feedback unit can input the user's presentation data into a generative AI, and the generative AI can provide feedback in real time.

[0076] The custom feedback unit can integrate self-assessment and peer assessment. For example, the custom feedback unit can integrate the results of a user's self-assessment with the assessments made by others to provide comprehensive feedback. For example, the custom feedback unit can compare items from self-assessment and items from peer assessment to clarify the points of agreement and disagreement in the assessments. For example, the custom feedback unit can also specifically indicate the user's strengths and areas for improvement based on the results of self-assessment and peer assessment. In this way, the custom feedback unit can provide more objective and effective feedback by integrating self-assessment and peer assessment. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the custom feedback unit can input self-assessment and peer assessment data into a generative AI, and the generative AI can integrate the evaluation results and provide feedback.

[0077] The custom feedback unit can provide personalized learning paths. For example, the custom feedback unit can design individual learning paths to improve a user's presentation skills. For example, the custom feedback unit can manage a user's learning progress and suggest the next learning step at the appropriate time. For example, the custom feedback unit can customize learning content according to the user's needs to support effective learning. In this way, by providing personalized learning paths, the custom feedback unit can support effective learning tailored to the user's individual needs. Some or all of the above processing in the custom feedback unit may be performed using, for example, generative AI, or without generative AI. For example, the custom feedback unit can input user learning data into a generative AI, which can then design and provide a personalized learning path.

[0078] The voice analysis unit can estimate the user's emotions and adjust the tone and tempo of the voice based on the estimated emotions. For example, if the user is nervous, the voice analysis unit can adjust the tone of the voice to be calmer. For example, if the user is excited, the voice analysis unit can also adjust the tempo of the voice to be faster. For example, if the user is relaxed, the voice analysis unit can also adjust the tone of the voice to be softer. By adjusting the tone and tempo of the voice according to the user's emotions, more effective presentations become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice analysis unit may be performed using a generative AI, or not using a generative AI. For example, the voice analysis unit can input voice data into a generative AI, which can analyze the voice data to estimate the user's emotions and adjust the tone and tempo of the voice.

[0079] The voice analysis unit can select the optimal voice analysis method by referring to the user's past presentation history during voice analysis. For example, the voice analysis unit can select the optimal analysis method based on the voice analysis algorithm the user has used in the past. For example, the voice analysis unit can also select an analysis method that emphasizes specific voice characteristics from the user's past presentation history. For example, the voice analysis unit can analyze the user's past presentation history and select the most effective voice analysis method. This allows for the selection of the optimal voice analysis method and improvement of analysis accuracy by referring to the user's past presentation history. 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 user's past presentation history data into a generative AI, which can then select the optimal voice analysis method.

[0080] The speech analysis unit can apply different speech analysis algorithms depending on the content of the presentation during speech analysis. For example, in the case of a technical presentation, the speech analysis unit can apply a speech analysis algorithm that emphasizes the pronunciation of technical terms. For example, in the case of an emotional presentation, the speech analysis unit can also apply a speech analysis algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the speech analysis unit can also apply a speech analysis algorithm that emphasizes clear pronunciation. This improves the accuracy of the analysis by applying a speech analysis algorithm appropriate to the content of the presentation. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the speech analysis unit can input the content data of the presentation into a generative AI, and the generative AI can apply a speech analysis algorithm appropriate to the content.

[0081] The voice analysis unit can estimate the user's emotions and adjust the volume of the voice based on the estimated emotions. For example, if the user is nervous, the voice analysis unit can adjust the volume to be lower. For example, if the user is excited, the voice analysis unit can also adjust the volume to be more emphasized. For example, if the user is relaxed, the voice analysis unit can also adjust the volume to be softer. By adjusting the volume of the voice according to the user's emotions, a more effective presentation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice analysis unit may be performed using a generative AI, or not using a generative AI. For example, the voice analysis unit can input voice data into a generative AI, which can analyze the voice data to estimate the user's emotions and adjust the volume of the voice.

[0082] The voice analysis unit can evaluate the accent and intonation of a voice based on the user's geographical background during voice analysis. For example, if the user has an accent from a different region, the voice analysis unit will take that accent into consideration during the analysis. For example, if the user speaks multiple languages, the voice analysis unit can also evaluate the intonation of each language. For example, if the user has pronunciation characteristics from a specific region, the voice analysis unit can also take those characteristics into consideration during the analysis. This improves the accuracy of the analysis by evaluating the accent and intonation of a voice based on the user's geographical background. Some or all of the above processing in the voice analysis unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the voice analysis unit can input the user's geographical background data into a generative AI, and the generative AI can evaluate the accent and intonation of the voice.

[0083] The voice analysis unit can analyze the user's social media activity and evaluate relevant voice characteristics during voice analysis. For example, the voice analysis unit can evaluate voice characteristics based on the language used by the user on social media. The voice analysis unit can also analyze the content of the user's social media posts and evaluate relevant voice characteristics. The voice analysis unit can also evaluate voice characteristics based on the frequency of the user's social media activity. This allows for the evaluation of relevant voice characteristics and improvement of analysis accuracy by analyzing the user's social media activity. 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 user's social media activity data into a generative AI, which can then evaluate the voice characteristics.

[0084] The video analysis unit can estimate the user's emotions and adjust gestures and eye movements based on the estimated emotions. For example, if the user is nervous, the video analysis unit can adjust gestures to be more subdued. If the user is excited, the video analysis unit can adjust gestures to be more exaggerated. If the user is relaxed, the video analysis unit can adjust eye movements to be more natural. By adjusting gestures and eye movements according to the user's emotions, a more effective presentation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the video analysis unit may be performed using a generative AI, or not using a generative AI. For example, the video analysis unit can input video data into a generative AI, which can analyze the video data to estimate the user's emotions and adjust gestures and eye movements accordingly.

[0085] The video analysis unit can select the optimal video analysis method by referring to the user's past video history during video analysis. For example, the video analysis unit can select the optimal analysis method based on video analysis algorithms previously used by the user. For example, the video analysis unit can also select an analysis method that emphasizes specific video characteristics from the user's past video history. For example, the video analysis unit can analyze the user's past video history and select the most effective video analysis method. This allows for the selection of the optimal video analysis method and improvement of analysis accuracy by referring to the user's past video history. Some or all of the above-described processes in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input the user's past video history data into a generative AI, which can then select the optimal video analysis method.

[0086] The video analysis unit can apply different video analysis algorithms depending on the content of the presentation during video analysis. For example, in the case of a technical presentation, the video analysis unit can apply a video analysis algorithm that emphasizes professional gestures. For example, in the case of an emotional presentation, the video analysis unit can also apply a video analysis algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the video analysis unit can also apply a video analysis algorithm that emphasizes visual clarity. By applying a video analysis algorithm appropriate to the content of the presentation, the accuracy of the analysis can be improved. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input presentation content data into a generative AI, and the generative AI can apply a video analysis algorithm appropriate to the content.

[0087] The video analysis unit can estimate the user's emotions and adjust the brightness and contrast of the video based on the estimated emotions. For example, if the user is nervous, the video analysis unit can adjust the brightness to make it calmer. For example, if the user is excited, the video analysis unit can also adjust the contrast to make it more prominent. For example, if the user is relaxed, the video analysis unit can also adjust the brightness to make it softer. By adjusting the brightness and contrast of the video according to the user's emotions, a more effective presentation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the video analysis unit may be performed using a generative AI, or not using a generative AI. For example, the video analysis unit can input video data into a generative AI, which can analyze the video data to estimate the user's emotions and adjust the brightness and contrast of the video.

[0088] The video analysis unit can evaluate the background and environment of a video based on the user's geographical background during video analysis. For example, if the user has a different regional background, the video analysis unit will take that background into consideration during the analysis. For example, if the user speaks multiple languages, the video analysis unit can also evaluate the background of each language. For example, if the user has video characteristics specific to a particular region, the video analysis unit can also take those characteristics into consideration during the analysis. This improves the accuracy of the analysis by evaluating the background and environment of the video based on the user's geographical background. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the video analysis unit can input the user's geographical background data into a generative AI, and the generative AI can evaluate the background and environment of the video.

[0089] The video analysis unit can analyze the user's social media activity and evaluate relevant video characteristics during video analysis. For example, the video analysis unit can evaluate video characteristics based on the video style used by the user on social media. The video analysis unit can also analyze the content of the user's social media posts and evaluate relevant video characteristics. The video analysis unit can also evaluate video characteristics based on the frequency of the user's social media activity. This allows for the evaluation of relevant video characteristics and improvement of analysis accuracy by analyzing the user's social media activity. Some or all of the above processing in the video analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the video analysis unit can input the user's social media activity data into a generative AI, which can then evaluate the video characteristics.

[0090] The structure evaluation unit can estimate the user's emotions and adjust the presentation structure based on the estimated emotions. For example, if the user is nervous, the structure evaluation unit can adjust the presentation structure to be simpler. For example, if the user is excited, the structure evaluation unit can also adjust the presentation structure to be more dynamic. For example, if the user is relaxed, the structure evaluation unit can also adjust the presentation structure to be more flexible. By adjusting the presentation structure according to the user's emotions, a more effective presentation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the structure evaluation unit may be performed using a generative AI, or not using a generative AI. For example, the structure evaluation unit can input presentation structure data into a generative AI, which can analyze the structure data to estimate the user's emotions and adjust the presentation structure.

[0091] The structural evaluation unit can select the optimal structural evaluation method by referring to the user's past presentation history during structural evaluation. For example, the structural evaluation unit can select the optimal evaluation method based on the structural evaluation algorithm previously used by the user. For example, the structural evaluation unit can also select an evaluation method that emphasizes specific structural characteristics from the user's past presentation history. For example, the structural evaluation unit can analyze the user's past presentation history and select the most effective structural evaluation method. This allows for the selection of the optimal structural evaluation method and improvement of evaluation accuracy by referring to the user's past presentation history. Some or all of the above processing in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input the user's past presentation history data into a generative AI, which can then select the optimal structural evaluation method.

[0092] The structural evaluation unit can apply different structural evaluation algorithms depending on the content of the presentation during structural evaluation. For example, in the case of a technical presentation, the structural evaluation unit applies a structural evaluation algorithm that emphasizes logical flow. For example, in the case of an emotional presentation, the structural evaluation unit can also apply a structural evaluation algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the structural evaluation unit can also apply a structural evaluation algorithm that emphasizes clear explanation. By applying a structural evaluation algorithm appropriate to the content of the presentation, the evaluation accuracy can be improved. Some or all of the above processing in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input presentation content data into a generative AI, and the generative AI can apply a structural evaluation algorithm appropriate to the content.

[0093] The structure evaluation unit can estimate the user's emotions and adjust the slide order of the presentation based on the estimated user emotions. For example, if the user is nervous, the structure evaluation unit may adjust the slide order to be simpler. For example, if the user is excited, the structure evaluation unit may also adjust the slide order to be more dynamic. For example, if the user is relaxed, the structure evaluation unit may also adjust the slide order to be more flexible. By adjusting the slide order of the presentation according to the user's emotions, a more effective presentation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the structure evaluation unit may be performed using a generative AI, or not using a generative AI. For example, the structure evaluation unit can input slide order data to a generative AI, and the generative AI can adjust the slide order.

[0094] The structural evaluation unit can evaluate the content of a presentation based on the user's geographical background during structural evaluation. For example, if the user has a different regional background, the structural evaluation unit will take that background into consideration during the evaluation. For example, if the user speaks multiple languages, the structural evaluation unit can also evaluate the background of each language. For example, if the user has presentation characteristics specific to a particular region, the structural evaluation unit can also take those characteristics into consideration during the evaluation. This improves the accuracy of the evaluation by evaluating the content of the presentation based on the user's geographical background. Some or all of the above processing in the structural evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structural evaluation unit can input the user's geographical background data into a generative AI, and the generative AI can evaluate the content of the presentation.

[0095] The structure evaluation unit can analyze the user's social media activity and evaluate relevant structural characteristics during structure evaluation. For example, the structure evaluation unit can evaluate structural characteristics based on the presentation style used by the user on social media. The structure evaluation unit can also analyze the content of the user's social media posts and evaluate relevant structural characteristics. The structure evaluation unit can also evaluate structural characteristics based on the frequency of the user's social media activity. This allows for the evaluation of relevant structural characteristics and improvement of evaluation accuracy by analyzing the user's social media activity. Some or all of the above processing in the structure evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the structure evaluation unit can input the user's social media activity data into a generative AI, which can then evaluate the structural characteristics.

[0096] The custom feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the user is nervous, the custom feedback unit can provide feedback in a gentle tone. If the user is excited, the custom feedback unit can also provide feedback that emphasizes specific areas for improvement. If the user is relaxed, the custom feedback unit can also provide detailed feedback. This allows for more effective feedback by adjusting the content of the feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the custom feedback unit may be performed using a generative AI, or not using a generative AI. For example, the custom feedback unit can input feedback data into a generative AI, which can then adjust the content of the feedback.

[0097] The custom feedback unit can select the optimal feedback method by referring to the user's past feedback history when providing custom feedback. For example, the custom feedback unit can select the optimal feedback method based on feedback the user has received in the past. For example, the custom feedback unit can also select a method to emphasize specific feedback characteristics from the user's past feedback history. For example, the custom feedback unit can analyze the user's past feedback history and select the most effective feedback method. This allows for the selection of the optimal feedback method and improvement of feedback accuracy by referring to the user's past feedback history. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input the user's past feedback history data into a generative AI, which can then select the optimal feedback method.

[0098] The custom feedback unit can apply different feedback algorithms depending on the content of the presentation when providing custom feedback. For example, in the case of a technical presentation, the custom feedback unit can apply an algorithm that provides expert feedback. For example, in the case of an emotional presentation, the custom feedback unit can also apply a feedback algorithm that emphasizes emotional expression. For example, in the case of an educational presentation, the custom feedback unit can also apply a feedback algorithm that emphasizes clear explanation. This improves the accuracy of feedback by applying a feedback algorithm that is appropriate to the content of the presentation. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input presentation content data into a generative AI, and the generative AI can apply a feedback algorithm appropriate to the content.

[0099] The custom feedback unit can estimate the user's emotions and prioritize feedback based on those emotions. For example, if the user is tense, the custom feedback unit may prioritize feedback on important areas for improvement. If the user is excited, the custom feedback unit may prioritize feedback on detailed areas for improvement. If the user is relaxed, the custom feedback unit may prioritize feedback on overall areas for improvement. This allows for more effective feedback by prioritizing feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the custom feedback unit may be performed using a generative AI, or not. For example, the custom feedback unit can input feedback data into a generative AI, which can then determine the priority of the feedback.

[0100] The custom feedback unit can adjust the content of feedback based on the user's geographical background when providing custom feedback. For example, if the user has a different regional background, the custom feedback unit will take that background into consideration when providing feedback. For example, if the user speaks multiple languages, the custom feedback unit can also take the background of each language into consideration when providing feedback. For example, if the user has feedback characteristics specific to a particular region, the custom feedback unit can also take those characteristics into consideration when providing feedback. By adjusting the content of feedback based on the user's geographical background, the accuracy of the feedback can be improved. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input the user's geographical background data into a generative AI, and the generative AI can adjust the content of the feedback.

[0101] The custom feedback unit can analyze the user's social media activity and provide relevant feedback when providing custom feedback. For example, the custom feedback unit can provide feedback based on the language the user uses on social media. The custom feedback unit can also analyze the content of the user's social media posts and provide relevant feedback. The custom feedback unit can also provide feedback based on the frequency of the user's social media activity. This allows for the provision of relevant feedback and improved feedback accuracy by analyzing the user's social media activity. Some or all of the above processing in the custom feedback unit may be performed using, for example, a generative AI, or without a generative AI. For example, the custom feedback unit can input the user's social media activity data into a generative AI, which can then provide relevant feedback.

[0102] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0103] The presentation skills enhancement system can estimate the user's emotions and dynamically adjust the presentation content based on those emotions. For example, if the user is nervous, the system can simplify the presentation and focus on key points. If the user is excited, the system can make the presentation more detailed and provide additional information. If the user is relaxed, the system can flexibly adjust the presentation content and even add interactive elements. This allows for more effective presentations by dynamically adjusting the content according to the user's emotions.

[0104] The presentation skills improvement system can analyze a user's past presentation data and provide an optimal training plan. For example, it can create a training plan that focuses on specific skills based on data from past presentations. It can also provide a training plan to strengthen areas where the user has struggled in the past. Furthermore, it can monitor the user's progress in real time and adjust the training plan as needed. This allows for the use of the user's past data to provide effective training tailored to individual needs.

[0105] The presentation skills enhancement system can estimate the user's emotions and adjust the presentation tempo based on those emotions. For example, if the user is nervous, the system will slow down the presentation tempo to allow the user to speak calmly. If the user is excited, the system can speed up the presentation tempo to support an energetic presentation. If the user is relaxed, the system can adjust the presentation tempo to a natural rhythm. This allows for more effective presentations by adjusting the presentation tempo according to the user's emotions.

[0106] The presentation skills improvement system can analyze a user's presentation style and suggest the most suitable presentation tools. For example, if a user prefers visual presentations, the system will suggest tools that heavily utilize graphics and visual aids. If a user prioritizes audio, the system can also suggest audio enhancement tools. Furthermore, if a user prefers interactive presentations, the system can suggest interactive tools. In this way, by suggesting the most suitable tools according to the user's presentation style, the quality of presentations can be improved.

[0107] The presentation skills enhancement system can estimate the user's emotions and adjust the visual effects of the presentation based on those emotions. For example, if the user is nervous, the system will tone down the visual effects to allow the user to focus on the content of the presentation. If the user is excited, the system can also emphasize the visual effects to create a greater visual impact. If the user is relaxed, the system can soften the visual effects to create a relaxed atmosphere. This allows for more effective presentations by adjusting visual effects according to the user's emotions.

[0108] The presentation skills improvement system allows users to save their presentation data to the cloud and share it with other users. For example, users can upload presentations they have created to the cloud, and other users can view those presentations and provide feedback. Users can also improve their own presentations by referring to presentations by other users. Furthermore, collaborative editing of presentations can be performed on the cloud, allowing multiple users to create presentations together. In this way, the quality of presentations can be improved by saving presentation data to the cloud and sharing it with other users.

[0109] The presentation skills enhancement system can estimate the user's emotions and select music for the presentation based on those emotions. For example, if the user is nervous, the system will select relaxing music. If the user is excited, the system can select energetic music. If the user is relaxed, the system can select calming music. By selecting music according to the user's emotions, a more effective presentation becomes possible.

[0110] The presentation skills improvement system can analyze a user's presentation data and suggest an optimal presentation schedule. For example, it can suggest the optimal presentation time based on data from the user's past presentations. It can also analyze the time slots of successful presentations in the past and suggest presenting during those times. Furthermore, it can suggest an optimal presentation schedule considering the user's schedule. In this way, by utilizing the user's presentation data to suggest an optimal presentation schedule, the success rate of presentations can be improved.

[0111] The presentation skills enhancement system can estimate the user's emotions and dynamically change the presentation background based on those emotions. For example, if the user is nervous, the system will select a calm background. If the user is excited, the system may select a lively background. If the user is relaxed, the system may select a soft background. This allows for more effective presentations by dynamically changing the presentation background according to the user's emotions.

[0112] The presentation skills improvement system can analyze a user's presentation data and suggest the optimal presentation template. For example, it can suggest the best template based on the user's past presentations. It can also analyze templates from successful past presentations and suggest those templates. Furthermore, it can suggest the best template according to the content of the user's presentation. In this way, by utilizing the user's presentation data and suggesting the optimal presentation template, the quality of presentations can be improved.

[0113] The following briefly describes the processing flow for example form 2.

[0114] Step 1: The audio analysis unit analyzes the audio of the presentation. For example, it analyzes the audio data using speech recognition technology to evaluate word choice and pronunciation clarity. It can extract audio features and evaluate the appropriate use of vocabulary and pronunciation clarity. It can also detect the presence or absence of audio distortion and evaluate audio quality. Step 2: The video analysis unit analyzes the presentation video based on the results analyzed by the audio analysis unit. For example, it uses image recognition technology to analyze the video data and evaluate the optimization of gestures, gaze, and posture. It can extract video features and evaluate the appropriateness of hand movements and the direction of gaze. It can also evaluate the appropriateness of standing posture and body movements. Step 3: The structural evaluation unit evaluates the structure of the presentation based on the results analyzed by the video analysis unit. For example, it evaluates the logical flow of the presentation using a logical structure analysis method. It can evaluate the appropriateness of the information flow and the consistency of the logic. It can also evaluate the relationships between the components of the presentation. Step 4: The Custom Feedback Department makes individual improvement suggestions based on the results evaluated by the Structural Evaluation Department. For example, it may suggest training focused on specific skills to effectively improve the user's presentation abilities. It provides real-time feedback so that users can immediately understand areas for improvement. It can combine self-assessment and peer assessment to provide more objective and effective feedback. It provides personalized learning paths to support effective learning tailored to the user's individual needs.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Each of the multiple elements described above, including the voice analysis unit, video analysis unit, structural evaluation unit, and custom feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the voice analysis unit is implemented by the processor 46 of the smart device 14 and analyzes voice data to evaluate word choice and clarity of pronunciation. The video analysis unit uses the camera 42 of the smart device 14 to analyze video data and evaluate the optimization of gestures, gaze, and posture. The structural evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the logical flow and structure of the presentation. The custom feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes individual improvement suggestions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0119] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the voice analysis unit, video analysis unit, structural evaluation unit, and custom feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the voice analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes voice data to evaluate word choice and clarity of pronunciation. The video analysis unit uses the camera 42 of the smart glasses 214 to analyze video data and evaluate the optimization of gestures, gaze, and posture. The structural evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the logical flow and structure of the presentation. The custom feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes individual improvement suggestions. 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.

[0135] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the voice analysis unit, video analysis unit, structural evaluation unit, and custom feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the voice analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes voice data to evaluate word choice and pronunciation clarity. The video analysis unit uses the camera 42 of the headset terminal 314 to analyze video data and evaluate the optimization of gestures, gaze, and posture. The structural evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the logical flow and structure of the presentation. The custom feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes individual improvement suggestions. 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.

[0151] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] Each of the multiple elements described above, including the voice analysis unit, video analysis unit, structural evaluation unit, and custom feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the voice analysis unit is implemented by the processor 46 of the robot 414 and analyzes voice data to evaluate word choice and clarity of pronunciation. The video analysis unit uses the camera 42 of the robot 414 to analyze video data and evaluate the optimization of gestures, gaze, and posture. The structural evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the logical flow and structure of the presentation. The custom feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes individual improvement suggestions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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."

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] (Note 1) The audio analysis unit analyzes the audio of the presentation, A video analysis unit analyzes the presentation video based on the results analyzed by the aforementioned audio analysis unit, A structural evaluation unit evaluates the structure of the presentation based on the results of the video analysis unit, The system includes a custom feedback unit that provides individual improvement suggestions based on the results evaluated by the structural evaluation unit. A system characterized by the following features. (Note 2) The aforementioned voice analysis unit, We evaluate word choice and clarity of pronunciation. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned video analysis unit, Evaluating the optimization of gestures, eye gaze, and posture. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned structural evaluation unit is Evaluate the logical structure of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 5) The custom feedback unit described above is: We propose training that focuses on specific skills. The system described in Appendix 1, characterized by the features described herein. (Note 6) The custom feedback unit described above is: Provide real-time feedback The system described in Appendix 1, characterized by the features described herein. (Note 7) The custom feedback unit described above is: Integrating self-evaluation with evaluation by others The system described in Appendix 1, characterized by the features described herein. (Note 8) The custom feedback unit described above is: Provides personalized learning paths The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned voice analysis unit, It estimates the user's emotions and adjusts the tone and tempo of the voice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned voice analysis unit, During voice analysis, the system selects the optimal voice analysis method by referring to the user's past presentation history. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned voice analysis unit, During audio analysis, different audio analysis algorithms are applied depending on the content of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned voice analysis unit, It estimates the user's emotions and adjusts the volume of the voice based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned voice analysis unit, During voice analysis, the system evaluates the accent and intonation of the voice based on the user's geographical background. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned voice analysis unit, During voice analysis, the system analyzes the user's social media activity and evaluates relevant voice characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned video analysis unit, It estimates the user's emotions and adjusts gestures and eye movements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned video analysis unit, During video analysis, the system selects the optimal video analysis method by referring to the user's past video history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned video analysis unit, During video analysis, different video analysis algorithms are applied depending on the content of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned video analysis unit, It estimates the user's emotions and adjusts the brightness and contrast of the video based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned video analysis unit, During video analysis, the background and environment of the video are evaluated based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned video analysis unit, During video analysis, we analyze the user's social media activity and evaluate relevant video characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned structural evaluation unit is It estimates the user's emotions and adjusts the presentation structure based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned structural evaluation unit is During structural evaluation, the optimal structural evaluation method is selected by referring to the user's past presentation history. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned structural evaluation unit is During structural evaluation, different structural evaluation algorithms are applied depending on the content of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned structural evaluation unit is It estimates the user's emotions and adjusts the presentation slide order based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned structural evaluation unit is During structural evaluation, the content of the presentation is evaluated based on the user's geographical background. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned structural evaluation unit is During structural evaluation, we analyze users' social media activity and evaluate the relevant structural characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 27) The custom feedback unit described above is: It estimates the user's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The custom feedback unit described above is: When providing custom feedback, the system will refer to the user's past feedback history to select the most suitable feedback method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The custom feedback unit described above is: When providing custom feedback, different feedback algorithms are applied depending on the content of the presentation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The custom feedback unit described above is: It estimates the user's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The custom feedback unit described above is: When providing custom feedback, the content of the feedback will be adjusted based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 32) The custom feedback unit described above is: When providing custom feedback, we analyze the user's social media activity and provide relevant feedback. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0187] 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 audio analysis unit analyzes the audio of the presentation, A video analysis unit analyzes the presentation video based on the results analyzed by the aforementioned audio analysis unit, A structural evaluation unit evaluates the structure of the presentation based on the results of the video analysis unit, The system includes a custom feedback unit that provides individual improvement suggestions based on the results evaluated by the structural evaluation unit. A system characterized by the following features.

2. The aforementioned voice analysis unit, We evaluate word choice and clarity of pronunciation. The system according to feature 1.

3. The aforementioned video analysis unit, Evaluating the optimization of gestures, eye gaze, and posture. The system according to feature 1.

4. The aforementioned structural evaluation unit is Evaluate the logical structure of the presentation. The system according to feature 1.

5. The custom feedback unit is, We propose training that focuses on specific skills. The system according to feature 1.

6. The custom feedback unit is, Provide real-time feedback The system according to feature 1.

7. The custom feedback unit is, Integrating self-evaluation with evaluation by others The system according to feature 1.

8. The custom feedback unit is, Provides personalized learning paths The system according to feature 1.

Images