system

Abstract

The system according to this embodiment aims to provide objective feedback in order to improve presentation skills. [Solution] The system according to the embodiment comprises a reception unit, an image recognition unit, a speech recognition unit, and a suggestion unit. The reception unit receives video and audio as input. The image recognition unit performs image recognition based on the video received by the reception unit. The speech recognition unit performs speech recognition based on the audio received by the reception unit. The suggestion unit generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to obtain objective feedback for improving presentation skills.

[0005] The system according to the embodiment aims to provide objective feedback for improving presentation skills.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an image recognition unit, a speech recognition unit, and a suggestion unit. The reception unit receives video and audio as input. The image recognition unit performs image recognition based on the video received by the reception unit. The speech recognition unit performs speech recognition based on the audio received by the reception unit. The suggestion unit generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide objective feedback to improve presentation skills. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The presentation checking system according to an embodiment of the present invention is a system that uses a generating AI to check presentations and improve skills. This presentation checking system accepts video and audio as input, and the generating AI performs image recognition and audio recognition. Next, it checks the gestures, posture, and eye movements based on the video and generates improvement suggestions. It also counts the number of unnecessary filler words, checks the timing of pauses, volume, and tone of voice based on the audio input. These check results are comprehensively evaluated to improve presentation skills. For example, the presentation checking system takes video as input, and the generating AI performs image recognition. At this time, it checks the presenter's gestures, posture, and eye movements. For example, it analyzes the timing of the presenter's hand movements, posture collapses, and direction of eye movements, and suggests areas for improvement. This allows the presenter to objectively understand and improve their own gestures and posture. Next, the presentation checking system takes audio as input, and the generating AI performs audio recognition. At this time, it counts the number of unnecessary filler words, checks the timing of pauses, volume, and tone of voice. For example, it counts the number of filler words like "um" and "uh" and suggests appropriate pauses, volume, and tone adjustments. This allows presenters to objectively understand and improve their speaking style. Furthermore, the presentation check system comprehensively evaluates the video and audio check results to improve presentation skills. For example, it evaluates the balance between gestures and voice volume and suggests areas for improvement. This allows presenters to improve their overall skills. This system enables not only young salespeople but also veteran salespeople to objectively analyze themselves and improve their presentation skills. For example, veteran salespeople can check their own presentations, understand areas for improvement, and deliver more effective presentations. In this way, the presentation check system helps improve presentation skills.

[0029] The presentation checking system according to this embodiment comprises a reception unit, an image recognition unit, a speech recognition unit, and a proposal unit. The reception unit receives video and audio as input. The video and audio include, but are not limited to, formats such as MP4, AVI, WAV, and MP3. The image recognition unit performs image recognition based on the video received by the reception unit. The image recognition unit performs image recognition using algorithms such as CNN (Convolutional Neural Network) and HOG (Histogram of Oriented Gradient). For example, the image recognition unit analyzes the presenter's gestures and body movements, checking hand movements and body orientation. The image recognition unit can also analyze the presenter's posture, checking standing and sitting postures. Furthermore, the image recognition unit can analyze the presenter's gaze, checking the direction and movement of their eyes. The speech recognition unit performs speech recognition based on the audio received by the reception unit. The speech recognition unit performs speech recognition using algorithms such as HMM (Hidden Markov Model) or DNN (Deep Neural Network). For example, the speech recognition unit counts the number of unnecessary filler words used by the presenter and checks for filler words such as "um" and "uh." The speech recognition unit can also analyze the presenter's pacing and check the length of pauses and breaks in speech. Furthermore, the speech recognition unit can analyze the volume of the presenter's voice and check the measured value in decibels (dB). The suggestion unit generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition unit. The suggestion unit suggests improvements to the presentation slide structure and speaking style, for example. In this way, the presentation check system according to the embodiment can help improve presentation skills.

[0030] The image recognition unit includes a gesture checking unit that checks the presenter's gestures and movements. The gesture checking unit checks the presenter's gestures and movements. For example, the gesture checking unit analyzes the timing of the presenter's hand movements and the orientation of their body, and checks the hand movements and body orientation. The gesture checking unit can also analyze the patterns of the presenter's hand movements and check the consistency and naturalness of the hand movements. Furthermore, the gesture checking unit can analyze the presenter's body orientation and posture and check the balance and stability of their body movements. This allows the system to check the presenter's gestures and movements and suggest improvements.

[0031] The image recognition unit includes a posture check unit that checks the presenter's posture. The posture check unit checks the presenter's posture. For example, the posture check unit analyzes the presenter's standing and sitting posture to check the stability and balance of their posture. The posture check unit can also analyze the degree of spinal straightness and shoulder position to check the correctness of their posture. Furthermore, the posture check unit can analyze the position of the presenter's body's center of gravity to check the stability of their posture. This allows the system to check the presenter's posture and suggest improvements.

[0032] The image recognition unit includes an eye-tracking unit that checks the presenter's gaze. The eye-tracking unit checks the presenter's gaze. For example, the eye-tracking unit analyzes the direction and movement of the presenter's gaze to check the consistency and naturalness of their gaze. The eye-tracking unit can also analyze the focus of the presenter's gaze to check where their eyes are directed. Furthermore, the eye-tracking unit can analyze the patterns of the presenter's gaze movements to check the consistency and naturalness of their gaze movements. This allows the system to check the presenter's gaze and suggest improvements.

[0033] The speech recognition unit includes a counting unit that counts the number of unnecessary filler words. The counting unit counts the number of times the presenter uses unnecessary filler words. For example, the counting unit counts the number of times filler words such as "um" and "uh" are used, and checks the frequency of filler words. The counting unit can also analyze the presenter's speaking patterns and check the frequency of filler words. Furthermore, the counting unit can analyze the rhythm of the presenter's speaking and check the timing of filler words. This allows the system to count the number of unnecessary filler words and provide suggestions for improvement.

[0034] The speech recognition unit includes a pause check unit that checks the timing of pauses. The pause check unit checks the presenter's timing. For example, the pause check unit analyzes the length of pauses and breaks in the presenter's speech to check the appropriateness of the pauses. The pause check unit can also analyze the rhythm of the presenter's speech to check the naturalness of the pauses. Furthermore, the pause check unit can analyze the flow of the presenter's speech to check the consistency of the pauses. This allows for checking the timing and making suggestions for improvement.

[0035] The speech recognition unit includes a voice checking unit that checks the volume of the voice. The voice checking unit checks the volume of the presenter's voice. For example, the voice checking unit analyzes the decibel (dB) measurement of the presenter's voice and checks the appropriateness of the volume. The voice checking unit can also analyze the intensity of the presenter's voice and check the balance of the volume. Furthermore, the voice checking unit can analyze the resonance of the presenter's voice and check the consistency of the volume. This allows for checking the volume and making suggestions for improvement.

[0036] The speech recognition unit includes a tone check unit that checks the tone. The tone check unit checks the presenter's tone. For example, the tone check unit analyzes the pitch and intonation of the presenter's voice to check the appropriateness of the tone. The tone check unit can also analyze the rhythm of the presenter's voice to check the naturalness of the tone. Furthermore, the tone check unit can analyze the volume of the presenter's voice to check the consistency of the tone. This allows for tone checking and suggestions for improvement.

[0037] The reception desk analyzes the user's past presentation history and selects the most suitable reception method. For example, the reception desk prioritizes suggesting reception methods the user has used in the past. It can also select the most efficient reception method based on the user's past presentation history. Furthermore, the reception desk can analyze the user's past presentation history and suggest the optimal reception timing. This allows for the selection of the most suitable reception method by analyzing the user's past presentation history.

[0038] The reception system filters video and audio submissions based on the user's current presentation status and areas of interest. For example, it prioritizes receiving highly relevant videos and audio based on the user's current presentation status. It can also filter relevant videos and audio based on the user's areas of interest. Furthermore, it can combine the user's current presentation status and areas of interest to receive the most relevant videos and audio. This allows for the reception of highly relevant data by filtering based on the user's current presentation status and areas of interest.

[0039] The reception desk prioritizes receiving highly relevant data when receiving video and audio, taking into account the user's geographical location. For example, the reception desk prioritizes receiving videos and audio related to the user's region based on the user's geographical location. The reception desk can also suggest the most suitable presentation method, taking into account the user's geographical location. Furthermore, the reception desk can filter and receive highly relevant data based on the user's geographical location. This allows for the priority of receiving highly relevant data by considering the user's geographical location.

[0040] The reception desk analyzes the user's social media activity and receives relevant data when receiving videos and audio. For example, the reception desk analyzes the user's social media activity and prioritizes receiving relevant videos and audio. The reception desk can also extract topics of high interest from the user's social media activity and receive relevant data. Furthermore, the reception desk can suggest the most suitable presentation method based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to prioritize the receipt of relevant data.

[0041] The image recognition unit optimizes its recognition algorithm by referencing the presenter's past behavior data during image recognition. For example, the image recognition unit selects the optimal recognition algorithm based on the presenter's past behavior data. The image recognition unit can also analyze the presenter's past behavior data to optimize the recognition algorithm. Furthermore, the image recognition unit can improve recognition accuracy by referencing the presenter's past behavior data. This allows for the optimization of the recognition algorithm and improvement of recognition accuracy by referencing the presenter's past behavior data.

[0042] The image recognition unit improves recognition accuracy based on the presenter's clothing and background during image recognition. For example, the image recognition unit adjusts the recognition algorithm based on the presenter's clothing. The image recognition unit can also improve recognition accuracy based on the presenter's background. Furthermore, the image recognition unit can select the optimal recognition algorithm by combining the presenter's clothing and background. This allows for more accurate recognition results by improving recognition accuracy based on the presenter's clothing and background.

[0043] The image recognition unit considers the presenter's geographical background when performing image recognition. For example, the image recognition unit adjusts its recognition algorithm based on the presenter's geographical background. It can also select the optimal recognition method by considering the presenter's geographical background. Furthermore, the image recognition unit can improve recognition accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve recognition accuracy.

[0044] The image recognition unit improves recognition accuracy by referring to the presenter's relevant literature during image recognition. For example, the image recognition unit optimizes the recognition algorithm by referring to the presenter's relevant literature. Furthermore, the image recognition unit can improve recognition accuracy based on the presenter's relevant literature. In addition, the image recognition unit can select the optimal recognition method by referring to the presenter's relevant literature. Thus, recognition accuracy can be improved by referring to the presenter's relevant literature.

[0045] The speech recognition unit optimizes its recognition algorithm by referencing the presenter's past audio data during speech recognition. For example, the speech recognition unit selects the optimal recognition algorithm based on the presenter's past audio data. The speech recognition unit can also analyze the presenter's past audio data to optimize the recognition algorithm. Furthermore, the speech recognition unit can improve recognition accuracy by referencing the presenter's past audio data. This allows for the optimization of the recognition algorithm and improvement of recognition accuracy by referencing the presenter's past audio data.

[0046] The speech recognition unit improves recognition accuracy based on the presenter's speaking style and accent during speech recognition. For example, the speech recognition unit adjusts the recognition algorithm based on the presenter's speaking style. It can also improve recognition accuracy by considering the presenter's accent. Furthermore, the speech recognition unit can select the optimal recognition algorithm by combining the presenter's speaking style and accent. This allows for more accurate recognition results by improving recognition accuracy based on the presenter's speaking style and accent.

[0047] The speech recognition unit takes the presenter's geographical background into consideration during speech recognition. For example, the speech recognition unit adjusts its recognition algorithm based on the presenter's geographical background. It can also select the optimal recognition method by considering the presenter's geographical background. Furthermore, the speech recognition unit can improve recognition accuracy based on the presenter's geographical background. Thus, recognition accuracy can be improved by considering the presenter's geographical background.

[0048] The speech recognition unit improves recognition accuracy by referring to the presenter's relevant literature during speech recognition. For example, the speech recognition unit optimizes the recognition algorithm by referring to the presenter's relevant literature. Furthermore, the speech recognition unit can improve recognition accuracy based on the presenter's relevant literature. In addition, the speech recognition unit can select the optimal recognition method by referring to the presenter's relevant literature. Thus, recognition accuracy can be improved by referring to the presenter's relevant literature.

[0049] The proposal generation system generates the optimal proposal by referencing the presenter's past improvement history. For example, the proposal generation system generates the optimal proposal based on the presenter's past improvement history. Furthermore, the proposal generation system can analyze the presenter's past improvement history to make effective proposals. In addition, the proposal generation system can customize the proposal content by referencing the presenter's past improvement history. This allows the system to generate the optimal proposal by referencing the presenter's past improvement history.

[0050] The proposal team customizes the proposal content based on the presenter's current presentation status when generating the proposal. For example, the proposal team analyzes the presenter's current presentation status and makes optimal improvement suggestions. The proposal team can also suggest specific improvements based on the presenter's current presentation status. Furthermore, the proposal team can make actionable suggestions considering the presenter's current presentation status. This allows for more appropriate suggestions to be made by customizing the proposal content based on the presenter's current presentation status.

[0051] The proposal generation system considers the presenter's geographical location to generate the most suitable proposal. For example, the system can make region-related proposals based on the presenter's geographical location. It can also propose the most suitable presentation method, taking the presenter's geographical location into consideration. Furthermore, it can make highly relevant proposals based on the presenter's geographical location. This allows the system to generate optimal proposals by considering the presenter's geographical location.

[0052] The proposal team analyzes the presenter's social media activity and adjusts the proposal content when generating it. For example, the proposal team analyzes the presenter's social media activity and makes relevant proposals. The proposal team can also extract themes of high interest from the presenter's social media activity and adjust the proposal content accordingly. Furthermore, the proposal team can make optimal proposals based on the presenter's social media activity. In this way, relevant proposals can be made by analyzing the presenter's social media activity.

[0053] The behavior check unit optimizes the check algorithm by referring to the presenter's past behavior data during the behavior check. For example, the behavior check unit selects the optimal check algorithm based on the presenter's past behavior data. The behavior check unit can also analyze the presenter's past behavior data and optimize the check algorithm. Furthermore, the behavior check unit can improve the check accuracy by referring to the presenter's past behavior data. In this way, by referring to the presenter's past behavior data, the check algorithm can be optimized and the check accuracy can be improved.

[0054] The behavior check unit considers the presenter's geographical background when performing behavior checks. For example, the behavior check unit adjusts the check algorithm based on the presenter's geographical background. It can also select the optimal check method considering the presenter's geographical background. Furthermore, the behavior check unit can improve check accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve check accuracy.

[0055] The posture checking unit optimizes the checking algorithm by referring to the presenter's past posture data during the posture check. For example, the posture checking unit selects the optimal checking algorithm based on the presenter's past posture data. The posture checking unit can also analyze the presenter's past posture data and optimize the checking algorithm. Furthermore, the posture checking unit can improve the checking accuracy by referring to the presenter's past posture data. In this way, by referring to the presenter's past posture data, the checking algorithm can be optimized and the checking accuracy can be improved.

[0056] The posture checking unit takes the presenter's geographical background into consideration when performing posture checks. For example, the posture checking unit adjusts the checking algorithm based on the presenter's geographical background. Furthermore, the posture checking unit can select the optimal checking method considering the presenter's geographical background. In addition, the posture checking unit can improve the accuracy of the check based on the presenter's geographical background. Thus, by considering the presenter's geographical background, the accuracy of the check can be improved.

[0057] The eye-tracking unit optimizes the checking algorithm by referring to the presenter's past eye-tracking data during eye-tracking. For example, the eye-tracking unit selects the optimal checking algorithm based on the presenter's past eye-tracking data. The eye-tracking unit can also analyze the presenter's past eye-tracking data and optimize the checking algorithm. Furthermore, the eye-tracking unit can improve checking accuracy by referring to the presenter's past eye-tracking data. In this way, by referring to the presenter's past eye-tracking data, the checking algorithm can be optimized and checking accuracy can be improved.

[0058] The eye-tracking unit considers the presenter's geographical background when performing eye-tracking checks. For example, the eye-tracking unit adjusts its checking algorithm based on the presenter's geographical background. It can also select the optimal checking method considering the presenter's geographical background. Furthermore, the eye-tracking unit can improve checking accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve checking accuracy.

[0059] The counting unit optimizes the counting algorithm by referring to the presenter's past transition phrase data during counting. For example, the counting unit selects the optimal counting algorithm based on the presenter's past transition phrase data. The counting unit can also analyze the presenter's past transition phrase data and optimize the counting algorithm. Furthermore, the counting unit can improve counting accuracy by referring to the presenter's past transition phrase data. In this way, by referring to the presenter's past transition phrase data, the counting algorithm can be optimized and counting accuracy can be improved.

[0060] The counting unit takes the presenter's geographical background into consideration when counting. For example, the counting unit adjusts the counting algorithm based on the presenter's geographical background. The counting unit can also select the optimal counting method considering the presenter's geographical background. Furthermore, the counting unit can improve counting accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve counting accuracy.

[0061] The pause check unit optimizes the check algorithm by referring to the presenter's past pause data during the pause check. For example, the pause check unit selects the optimal check algorithm based on the presenter's past pause data. The pause check unit can also analyze the presenter's past pause data and optimize the check algorithm. Furthermore, the pause check unit can improve the check accuracy by referring to the presenter's past pause data. In this way, by referring to the presenter's past pause data, the check algorithm can be optimized and the check accuracy can be improved.

[0062] The inter-check unit performs checks while considering the presenter's geographical background. For example, the inter-check unit adjusts the check algorithm based on the presenter's geographical background. Furthermore, the inter-check unit can select the optimal check method considering the presenter's geographical background. In addition, the inter-check unit can improve check accuracy based on the presenter's geographical background. Thus, by considering the presenter's geographical background, check accuracy can be improved.

[0063] The voice checking unit optimizes the checking algorithm by referring to the presenter's past voice data during the voice checking process. For example, the voice checking unit selects the optimal checking algorithm based on the presenter's past voice data. The voice checking unit can also analyze the presenter's past voice data and optimize the checking algorithm. Furthermore, the voice checking unit can improve the checking accuracy by referring to the presenter's past voice data. In this way, by referring to the presenter's past voice data, the checking algorithm can be optimized and the checking accuracy can be improved.

[0064] The voice checking unit takes the presenter's geographical background into consideration during the voice check. For example, the voice checking unit adjusts the checking algorithm based on the presenter's geographical background. Furthermore, the voice checking unit can select the optimal checking method considering the presenter's geographical background. In addition, the voice checking unit can improve the accuracy of the check based on the presenter's geographical background. Thus, by considering the presenter's geographical background, the accuracy of the check can be improved.

[0065] The tone check unit optimizes the check algorithm by referring to the presenter's past tone data during tone checking. For example, the tone check unit selects the optimal check algorithm based on the presenter's past tone data. The tone check unit can also analyze the presenter's past tone data and optimize the check algorithm. Furthermore, the tone check unit can improve check accuracy by referring to the presenter's past tone data. In this way, by referring to the presenter's past tone data, the check algorithm can be optimized and check accuracy can be improved.

[0066] The tone checking unit takes the presenter's geographical background into consideration during the tone checking process. For example, the tone checking unit adjusts the checking algorithm based on the presenter's geographical background. Furthermore, the tone checking unit can select the optimal checking method considering the presenter's geographical background. In addition, the tone checking unit can improve the checking accuracy based on the presenter's geographical background. Thus, by considering the presenter's geographical background, the checking accuracy can be improved.

[0067] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0068] The presentation checking system can also include a feedback unit. This feedback unit provides real-time feedback to the presenter. For example, if the speech recognition unit detects excessive use of filler words while the presenter is speaking, the feedback unit can immediately notify the presenter and encourage improvement. The feedback unit can also point out issues with the presenter's posture and eye contact in real time and encourage appropriate corrections. Furthermore, the feedback unit can provide real-time advice on adjusting the presenter's voice volume and tone. This allows the presenter to immediately identify areas for improvement and make corrections on the spot.

[0069] The presentation checking system can also include a data analysis unit. This unit analyzes the presenter's past presentation data to support long-term skill improvement. For example, it can track changes in the frequency of transitional phrases and pacing in the presenter's past presentations, showing trends for improvement. It can also analyze changes in the presenter's posture and eye contact, indicating which improvements were effective. Furthermore, it can track changes in the presenter's voice volume and tone, suggesting the optimal presentation style. This allows presenters to improve their skills over the long term.

[0070] The presentation checking system can also include a simulation unit. This unit provides a function that allows presenters to practice their presentations in a virtual environment. For example, the simulation unit can generate a virtual audience, allowing presenters to practice as if they were actually giving a presentation. The simulation unit can also check the presenter's gestures, posture, and eye contact in real time and provide feedback on areas for improvement. Furthermore, the simulation unit can analyze the presenter's voice and provide advice on the frequency of transitional words, pacing, and adjustments to voice volume and tone. This allows presenters to practice in an environment close to a real presentation and improve their skills.

[0071] The presentation checking system can also include an interactive section. This interactive section helps improve the presentation through dialogue between the presenter and the system. For example, when the presenter inputs a question, the system can provide appropriate advice. Furthermore, when the presenter consults the interactive section about a specific problem, the system can suggest concrete solutions. Additionally, when the presenter requests real-time feedback during practice, the system can respond immediately and point out areas for improvement. This allows the presenter to deliver a more effective presentation through interaction with the system.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The reception unit accepts video and audio as input. Video and audio include, but are not limited to, formats such as MP4, AVI, WAV, and MP3. Step 2: The image recognition unit performs image recognition based on the video received by the reception unit. The image recognition unit uses algorithms such as CNN (Convolutional Neural Network) and HOG (Histogram of Oriented Gradient) for image recognition. For example, it analyzes the presenter's gestures and body movements, checking hand movements and body orientation. It can also analyze the presenter's posture, checking standing and sitting positions. Furthermore, it can analyze the presenter's gaze, checking the direction and movement of their eyes. Step 3: The speech recognition unit performs speech recognition based on the audio received by the reception unit. The speech recognition unit uses algorithms such as HMM (Hidden Markov Model) or DNN (Deep Neural Network) for speech recognition. For example, it counts the number of times the presenter uses unnecessary filler words and checks for filler words such as "um" and "uh". It can also analyze the presenter's pacing and check the length of pauses and breaks in speech. Furthermore, it can analyze the volume of the presenter's voice and check the measured value in decibels (dB). Step 4: The suggestion unit generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition unit. The suggestion unit suggests improvements to the presentation slide structure and speaking style, for example. In this way, the presentation check system according to the embodiment can help improve presentation skills.

[0074] (Example of form 2) The presentation checking system according to an embodiment of the present invention is a system that uses a generating AI to check presentations and improve skills. This presentation checking system accepts video and audio as input, and the generating AI performs image recognition and audio recognition. Next, it checks the gestures, posture, and eye movements based on the video and generates improvement suggestions. It also counts the number of unnecessary filler words, checks the timing of pauses, volume, and tone of voice based on the audio input. These check results are comprehensively evaluated to improve presentation skills. For example, the presentation checking system takes video as input, and the generating AI performs image recognition. At this time, it checks the presenter's gestures, posture, and eye movements. For example, it analyzes the timing of the presenter's hand movements, posture collapses, and direction of eye movements, and suggests areas for improvement. This allows the presenter to objectively understand and improve their own gestures and posture. Next, the presentation checking system takes audio as input, and the generating AI performs audio recognition. At this time, it counts the number of unnecessary filler words, checks the timing of pauses, volume, and tone of voice. For example, it counts the number of filler words like "um" and "uh" and suggests appropriate pauses, volume, and tone adjustments. This allows presenters to objectively understand and improve their speaking style. Furthermore, the presentation check system comprehensively evaluates the video and audio check results to improve presentation skills. For example, it evaluates the balance between gestures and voice volume and suggests areas for improvement. This allows presenters to improve their overall skills. This system enables not only young salespeople but also veteran salespeople to objectively analyze themselves and improve their presentation skills. For example, veteran salespeople can check their own presentations, understand areas for improvement, and deliver more effective presentations. In this way, the presentation check system helps improve presentation skills.

[0075] The presentation checking system according to this embodiment comprises a reception unit, an image recognition unit, a speech recognition unit, and a proposal unit. The reception unit receives video and audio as input. The video and audio include, but are not limited to, formats such as MP4, AVI, WAV, and MP3. The image recognition unit performs image recognition based on the video received by the reception unit. The image recognition unit performs image recognition using algorithms such as CNN (Convolutional Neural Network) and HOG (Histogram of Oriented Gradient). For example, the image recognition unit analyzes the presenter's gestures and body movements, checking hand movements and body orientation. The image recognition unit can also analyze the presenter's posture, checking standing and sitting postures. Furthermore, the image recognition unit can analyze the presenter's gaze, checking the direction and movement of their eyes. The speech recognition unit performs speech recognition based on the audio received by the reception unit. The speech recognition unit performs speech recognition using algorithms such as HMM (Hidden Markov Model) or DNN (Deep Neural Network). For example, the speech recognition unit counts the number of unnecessary filler words used by the presenter and checks for filler words such as "um" and "uh." The speech recognition unit can also analyze the presenter's pacing and check the length of pauses and breaks in speech. Furthermore, the speech recognition unit can analyze the volume of the presenter's voice and check the measured value in decibels (dB). The suggestion unit generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition unit. The suggestion unit suggests improvements to the presentation slide structure and speaking style, for example. In this way, the presentation check system according to the embodiment can help improve presentation skills.

[0076] The image recognition unit includes a gesture checking unit that checks the presenter's gestures and movements. The gesture checking unit checks the presenter's gestures and movements. For example, the gesture checking unit analyzes the timing of the presenter's hand movements and the orientation of their body, and checks the hand movements and body orientation. The gesture checking unit can also analyze the patterns of the presenter's hand movements and check the consistency and naturalness of the hand movements. Furthermore, the gesture checking unit can analyze the presenter's body orientation and posture and check the balance and stability of their body movements. This allows the system to check the presenter's gestures and movements and suggest improvements.

[0077] The image recognition unit includes a posture check unit that checks the presenter's posture. The posture check unit checks the presenter's posture. For example, the posture check unit analyzes the presenter's standing and sitting posture to check the stability and balance of their posture. The posture check unit can also analyze the degree of spinal straightness and shoulder position to check the correctness of their posture. Furthermore, the posture check unit can analyze the position of the presenter's body's center of gravity to check the stability of their posture. This allows the system to check the presenter's posture and suggest improvements.

[0078] The image recognition unit includes an eye-tracking unit that checks the presenter's gaze. The eye-tracking unit checks the presenter's gaze. For example, the eye-tracking unit analyzes the direction and movement of the presenter's gaze to check the consistency and naturalness of their gaze. The eye-tracking unit can also analyze the focus of the presenter's gaze to check where their eyes are directed. Furthermore, the eye-tracking unit can analyze the patterns of the presenter's gaze movements to check the consistency and naturalness of their gaze movements. This allows the system to check the presenter's gaze and suggest improvements.

[0079] The speech recognition unit includes a counting unit that counts the number of unnecessary filler words. The counting unit counts the number of times the presenter uses unnecessary filler words. For example, the counting unit counts the number of times filler words such as "um" and "uh" are used, and checks the frequency of filler words. The counting unit can also analyze the presenter's speaking patterns and check the frequency of filler words. Furthermore, the counting unit can analyze the rhythm of the presenter's speaking and check the timing of filler words. This allows the system to count the number of unnecessary filler words and provide suggestions for improvement.

[0080] The speech recognition unit includes a pause check unit that checks the timing of pauses. The pause check unit checks the presenter's timing. For example, the pause check unit analyzes the length of pauses and breaks in the presenter's speech to check the appropriateness of the pauses. The pause check unit can also analyze the rhythm of the presenter's speech to check the naturalness of the pauses. Furthermore, the pause check unit can analyze the flow of the presenter's speech to check the consistency of the pauses. This allows for checking the timing and making suggestions for improvement.

[0081] The speech recognition unit includes a voice checking unit that checks the volume of the voice. The voice checking unit checks the volume of the presenter's voice. For example, the voice checking unit analyzes the decibel (dB) measurement of the presenter's voice and checks the appropriateness of the volume. The voice checking unit can also analyze the intensity of the presenter's voice and check the balance of the volume. Furthermore, the voice checking unit can analyze the resonance of the presenter's voice and check the consistency of the volume. This allows for checking the volume and making suggestions for improvement.

[0082] The speech recognition unit includes a tone check unit that checks the tone. The tone check unit checks the presenter's tone. For example, the tone check unit analyzes the pitch and intonation of the presenter's voice to check the appropriateness of the tone. The tone check unit can also analyze the rhythm of the presenter's voice to check the naturalness of the tone. Furthermore, the tone check unit can analyze the volume of the presenter's voice to check the consistency of the tone. This allows for tone checking and suggestions for improvement.

[0083] The reception desk estimates the user's emotions and adjusts the timing of video and audio reception based on the estimated emotions. For example, if the reception desk is nervous, it will delay the reception timing to allow the user to relax. Conversely, if the user is relaxed, the reception desk can start the reception immediately. Furthermore, if the user is in a hurry, the reception desk can speed up the reception timing. By adjusting the reception timing according to the user's emotions, video and audio can be received at a more appropriate time.

[0084] The reception desk analyzes the user's past presentation history and selects the most suitable reception method. For example, the reception desk prioritizes suggesting reception methods the user has used in the past. It can also select the most efficient reception method based on the user's past presentation history. Furthermore, the reception desk can analyze the user's past presentation history and suggest the optimal reception timing. This allows for the selection of the most suitable reception method by analyzing the user's past presentation history.

[0085] The reception system filters video and audio submissions based on the user's current presentation status and areas of interest. For example, it prioritizes receiving highly relevant videos and audio based on the user's current presentation status. It can also filter relevant videos and audio based on the user's areas of interest. Furthermore, it can combine the user's current presentation status and areas of interest to receive the most relevant videos and audio. This allows for the reception of highly relevant data by filtering based on the user's current presentation status and areas of interest.

[0086] The reception desk estimates the user's emotions and determines the priority of videos and audio to be received based on those estimated emotions. For example, if the user is feeling tense, the reception desk will prioritize videos and audio that promote relaxation. If the user is relaxed, the reception desk may also prioritize videos and audio that are highly effective for learning. Furthermore, if the user is in a hurry, the reception desk may prioritize videos and audio that are effective in a short amount of time. This allows for the prioritization of more relevant data by determining the priority of videos and audio according to the user's emotions.

[0087] The reception desk prioritizes receiving highly relevant data when receiving video and audio, taking into account the user's geographical location. For example, the reception desk prioritizes receiving videos and audio related to the user's region based on the user's geographical location. The reception desk can also suggest the most suitable presentation method, taking into account the user's geographical location. Furthermore, the reception desk can filter and receive highly relevant data based on the user's geographical location. This allows for the priority of receiving highly relevant data by considering the user's geographical location.

[0088] The reception desk analyzes the user's social media activity and receives relevant data when receiving videos and audio. For example, the reception desk analyzes the user's social media activity and prioritizes receiving relevant videos and audio. The reception desk can also extract topics of high interest from the user's social media activity and receive relevant data. Furthermore, the reception desk can suggest the most suitable presentation method based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to prioritize the receipt of relevant data.

[0089] The image recognition unit estimates the user's emotions and adjusts the accuracy of image recognition based on the estimated emotions. For example, if the user is tense, the image recognition unit will lower the accuracy of image recognition to help them relax. Conversely, if the user is relaxed, the image recognition unit can perform detailed image recognition. Furthermore, if the user is in a hurry, the image recognition unit can perform rapid image recognition. By adjusting the accuracy of image recognition according to the user's emotions, more appropriate recognition results can be obtained.

[0090] The image recognition unit optimizes its recognition algorithm by referencing the presenter's past behavior data during image recognition. For example, the image recognition unit selects the optimal recognition algorithm based on the presenter's past behavior data. The image recognition unit can also analyze the presenter's past behavior data to optimize the recognition algorithm. Furthermore, the image recognition unit can improve recognition accuracy by referencing the presenter's past behavior data. This allows for the optimization of the recognition algorithm and improvement of recognition accuracy by referencing the presenter's past behavior data.

[0091] The image recognition unit improves recognition accuracy based on the presenter's clothing and background during image recognition. For example, the image recognition unit adjusts the recognition algorithm based on the presenter's clothing. The image recognition unit can also improve recognition accuracy based on the presenter's background. Furthermore, the image recognition unit can select the optimal recognition algorithm by combining the presenter's clothing and background. This allows for more accurate recognition results by improving recognition accuracy based on the presenter's clothing and background.

[0092] The image recognition unit estimates the user's emotions and adjusts the order in which it displays the image recognition results based on the estimated emotions. For example, if the user is tense, the image recognition unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, it can prioritize displaying results that summarize the key points. By adjusting the order in which image recognition results are displayed according to the user's emotions, more appropriate results can be provided.

[0093] The image recognition unit considers the presenter's geographical background when performing image recognition. For example, the image recognition unit adjusts its recognition algorithm based on the presenter's geographical background. It can also select the optimal recognition method by considering the presenter's geographical background. Furthermore, the image recognition unit can improve recognition accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve recognition accuracy.

[0094] The image recognition unit improves recognition accuracy by referring to the presenter's relevant literature during image recognition. For example, the image recognition unit optimizes the recognition algorithm by referring to the presenter's relevant literature. Furthermore, the image recognition unit can improve recognition accuracy based on the presenter's relevant literature. In addition, the image recognition unit can select the optimal recognition method by referring to the presenter's relevant literature. Thus, recognition accuracy can be improved by referring to the presenter's relevant literature.

[0095] The speech recognition unit estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions. For example, if the user is tense, the speech recognition unit will loosen the accuracy of speech recognition to help them relax. Conversely, if the user is relaxed, the speech recognition unit can perform detailed speech recognition. Furthermore, if the user is in a hurry, the speech recognition unit can perform rapid speech recognition. In this way, by adjusting the accuracy of speech recognition according to the user's emotions, more appropriate recognition results can be obtained.

[0096] The speech recognition unit optimizes its recognition algorithm by referencing the presenter's past audio data during speech recognition. For example, the speech recognition unit selects the optimal recognition algorithm based on the presenter's past audio data. The speech recognition unit can also analyze the presenter's past audio data to optimize the recognition algorithm. Furthermore, the speech recognition unit can improve recognition accuracy by referencing the presenter's past audio data. This allows for the optimization of the recognition algorithm and improvement of recognition accuracy by referencing the presenter's past audio data.

[0097] The speech recognition unit improves recognition accuracy based on the presenter's speaking style and accent during speech recognition. For example, the speech recognition unit adjusts the recognition algorithm based on the presenter's speaking style. It can also improve recognition accuracy by considering the presenter's accent. Furthermore, the speech recognition unit can select the optimal recognition algorithm by combining the presenter's speaking style and accent. This allows for more accurate recognition results by improving recognition accuracy based on the presenter's speaking style and accent.

[0098] The speech recognition unit estimates the user's emotions and adjusts the order in which it displays the speech recognition results based on the estimated emotions. For example, if the user is tense, the speech recognition unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, it can prioritize displaying concise results. By adjusting the order in which speech recognition results are displayed according to the user's emotions, more appropriate results can be provided.

[0099] The speech recognition unit takes the presenter's geographical background into consideration during speech recognition. For example, the speech recognition unit adjusts its recognition algorithm based on the presenter's geographical background. It can also select the optimal recognition method by considering the presenter's geographical background. Furthermore, the speech recognition unit can improve recognition accuracy based on the presenter's geographical background. Thus, recognition accuracy can be improved by considering the presenter's geographical background.

[0100] The speech recognition unit improves recognition accuracy by referring to the presenter's relevant literature during speech recognition. For example, the speech recognition unit optimizes the recognition algorithm by referring to the presenter's relevant literature. Furthermore, the speech recognition unit can improve recognition accuracy based on the presenter's relevant literature. In addition, the speech recognition unit can select the optimal recognition method by referring to the presenter's relevant literature. Thus, recognition accuracy can be improved by referring to the presenter's relevant literature.

[0101] The suggestion department estimates the user's emotions and adjusts the content of improvement suggestions based on those estimates. For example, if the user is feeling stressed, the suggestion department will offer suggestions to help them relax. If the user is relaxed, the suggestion department can also offer more detailed improvement suggestions. Furthermore, if the user is in a hurry, the suggestion department can offer suggestions that can be implemented quickly. By adjusting the content of improvement suggestions according to the user's emotions, the department can provide more appropriate suggestions.

[0102] The proposal generation system generates the optimal proposal by referencing the presenter's past improvement history. For example, the proposal generation system generates the optimal proposal based on the presenter's past improvement history. Furthermore, the proposal generation system can analyze the presenter's past improvement history to make effective proposals. In addition, the proposal generation system can customize the proposal content by referencing the presenter's past improvement history. This allows the system to generate the optimal proposal by referencing the presenter's past improvement history.

[0103] The proposal team customizes the proposal content based on the presenter's current presentation status when generating the proposal. For example, the proposal team analyzes the presenter's current presentation status and makes optimal improvement suggestions. The proposal team can also suggest specific improvements based on the presenter's current presentation status. Furthermore, the proposal team can make actionable suggestions considering the presenter's current presentation status. This allows for more appropriate suggestions to be made by customizing the proposal content based on the presenter's current presentation status.

[0104] The suggestion function estimates the user's emotions and prioritizes suggestions based on those emotions. For example, if the user is feeling stressed, the suggestion function will prioritize suggestions that help them relax. If the user is relaxed, the suggestion function may also prioritize more detailed suggestions. Furthermore, if the user is in a hurry, the suggestion function may prioritize suggestions that can be implemented quickly. This allows for more appropriate suggestions to be made by prioritizing suggestions according to the user's emotions.

[0105] The proposal generation system considers the presenter's geographical location to generate the most suitable proposal. For example, the system can make region-related proposals based on the presenter's geographical location. It can also propose the most suitable presentation method, taking the presenter's geographical location into consideration. Furthermore, it can make highly relevant proposals based on the presenter's geographical location. This allows the system to generate optimal proposals by considering the presenter's geographical location.

[0106] The proposal team analyzes the presenter's social media activity and adjusts the proposal content when generating it. For example, the proposal team analyzes the presenter's social media activity and makes relevant proposals. The proposal team can also extract themes of high interest from the presenter's social media activity and adjust the proposal content accordingly. Furthermore, the proposal team can make optimal proposals based on the presenter's social media activity. In this way, relevant proposals can be made by analyzing the presenter's social media activity.

[0107] The behavior check unit estimates the user's emotions and adjusts the behavior check criteria based on the estimated emotions. For example, if the behavior check unit is tense, it will relax the behavior check criteria to help the user relax. Furthermore, if the user is relaxed, the behavior check unit can perform a more detailed behavior check. Additionally, if the user is in a hurry, the behavior check unit can perform a quick behavior check. This allows for more appropriate checks by adjusting the behavior check criteria according to the user's emotions.

[0108] The behavior check unit optimizes the check algorithm by referring to the presenter's past behavior data during the behavior check. For example, the behavior check unit selects the optimal check algorithm based on the presenter's past behavior data. The behavior check unit can also analyze the presenter's past behavior data and optimize the check algorithm. Furthermore, the behavior check unit can improve the check accuracy by referring to the presenter's past behavior data. In this way, by referring to the presenter's past behavior data, the check algorithm can be optimized and the check accuracy can be improved.

[0109] The behavior check unit estimates the user's emotions and adjusts the order in which the behavior check results are displayed based on the estimated emotions. For example, if the user is tense, the behavior check unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the behavior check unit can prioritize displaying concise results. By adjusting the order in which the behavior check results are displayed according to the user's emotions, more appropriate results can be provided.

[0110] The behavior check unit considers the presenter's geographical background when performing behavior checks. For example, the behavior check unit adjusts the check algorithm based on the presenter's geographical background. It can also select the optimal check method considering the presenter's geographical background. Furthermore, the behavior check unit can improve check accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve check accuracy.

[0111] The posture check unit estimates the user's emotions and adjusts the posture check criteria based on the estimated emotions. For example, if the user is tense, the posture check unit will relax the posture check criteria to help them relax. If the user is relaxed, the posture check unit can also perform a more detailed posture check. Furthermore, if the user is in a hurry, the posture check unit can perform a quick posture check. This allows for a more appropriate check by adjusting the posture check criteria according to the user's emotions.

[0112] The posture checking unit optimizes the checking algorithm by referring to the presenter's past posture data during the posture check. For example, the posture checking unit selects the optimal checking algorithm based on the presenter's past posture data. The posture checking unit can also analyze the presenter's past posture data and optimize the checking algorithm. Furthermore, the posture checking unit can improve the checking accuracy by referring to the presenter's past posture data. In this way, by referring to the presenter's past posture data, the checking algorithm can be optimized and the checking accuracy can be improved.

[0113] The posture check unit estimates the user's emotions and adjusts the order in which the posture check results are displayed based on the estimated emotions. For example, if the user is tense, the posture check unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the posture check unit can prioritize displaying concise results. By adjusting the order in which the posture check results are displayed according to the user's emotions, more appropriate results can be provided.

[0114] The posture checking unit takes the presenter's geographical background into consideration when performing posture checks. For example, the posture checking unit adjusts the checking algorithm based on the presenter's geographical background. Furthermore, the posture checking unit can select the optimal checking method considering the presenter's geographical background. In addition, the posture checking unit can improve the accuracy of the check based on the presenter's geographical background. Thus, by considering the presenter's geographical background, the accuracy of the check can be improved.

[0115] The eye-tracking unit estimates the user's emotions and adjusts the criteria for eye-tracking based on the estimated emotions. For example, if the user is tense, the eye-tracking unit will relax the criteria for eye-tracking to help them relax. Furthermore, if the user is relaxed, the eye-tracking unit can perform a more detailed eye-tracking check. Additionally, if the user is in a hurry, the eye-tracking unit can perform a quick eye-tracking check. This allows for more appropriate checks by adjusting the criteria for eye-tracking according to the user's emotions.

[0116] The eye-tracking unit optimizes the checking algorithm by referring to the presenter's past eye-tracking data during eye-tracking. For example, the eye-tracking unit selects the optimal checking algorithm based on the presenter's past eye-tracking data. The eye-tracking unit can also analyze the presenter's past eye-tracking data and optimize the checking algorithm. Furthermore, the eye-tracking unit can improve checking accuracy by referring to the presenter's past eye-tracking data. In this way, by referring to the presenter's past eye-tracking data, the checking algorithm can be optimized and checking accuracy can be improved.

[0117] The eye-tracking unit estimates the user's emotions and adjusts the order in which the eye-tracking results are displayed based on the estimated emotions. For example, if the user is tense, the eye-tracking unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the eye-tracking unit can prioritize displaying results that highlight the key points. By adjusting the order in which the eye-tracking results are displayed according to the user's emotions, more appropriate results can be provided.

[0118] The eye-tracking unit considers the presenter's geographical background when performing eye-tracking checks. For example, the eye-tracking unit adjusts its checking algorithm based on the presenter's geographical background. It can also select the optimal checking method considering the presenter's geographical background. Furthermore, the eye-tracking unit can improve checking accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve checking accuracy.

[0119] The counting unit estimates the user's emotions and adjusts the counting criteria for connecting words based on the estimated emotions. For example, if the user is tense, the counting unit will loosen the counting criteria to help them relax. It can also perform a more detailed count if the user is relaxed. Furthermore, if the user is in a hurry, the counting unit can perform a faster count. This allows for more appropriate counting by adjusting the counting criteria for connecting words according to the user's emotions.

[0120] The counting unit optimizes the counting algorithm by referring to the presenter's past transition phrase data during counting. For example, the counting unit selects the optimal counting algorithm based on the presenter's past transition phrase data. The counting unit can also analyze the presenter's past transition phrase data and optimize the counting algorithm. Furthermore, the counting unit can improve counting accuracy by referring to the presenter's past transition phrase data. In this way, by referring to the presenter's past transition phrase data, the counting algorithm can be optimized and counting accuracy can be improved.

[0121] The counting unit estimates the user's emotions and adjusts the order in which the counting results are displayed based on the estimated emotions. For example, if the user is feeling tense, the counting unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the counting unit can prioritize displaying concise results. By adjusting the order in which the counting results are displayed according to the user's emotions, more appropriate results can be provided.

[0122] The counting unit takes the presenter's geographical background into consideration when counting. For example, the counting unit adjusts the counting algorithm based on the presenter's geographical background. The counting unit can also select the optimal counting method considering the presenter's geographical background. Furthermore, the counting unit can improve counting accuracy based on the presenter's geographical background. Thus, considering the presenter's geographical background can improve counting accuracy.

[0123] The timing check unit estimates the user's emotions and adjusts the timing check criteria based on the estimated emotions. For example, if the timing check unit is tense, it will loosen the timing check criteria to help the user relax. Also, if the user is relaxed, the timing check unit can perform a more detailed timing check. Furthermore, if the user is in a hurry, the timing check unit can perform a quick timing check. In this way, by adjusting the timing check criteria according to the user's emotions, a more appropriate check can be performed.

[0124] The pause check unit optimizes the check algorithm by referring to the presenter's past pause data during the pause check. For example, the pause check unit selects the optimal check algorithm based on the presenter's past pause data. The pause check unit can also analyze the presenter's past pause data and optimize the check algorithm. Furthermore, the pause check unit can improve the check accuracy by referring to the presenter's past pause data. In this way, by referring to the presenter's past pause data, the check algorithm can be optimized and the check accuracy can be improved.

[0125] The interval check unit estimates the user's emotions and adjusts the order in which the interval check results are displayed based on the estimated emotions. For example, if the user is tense, the interval check unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the interval check unit can prioritize displaying concise results. By adjusting the order in which the interval check results are displayed according to the user's emotions, more appropriate results can be provided.

[0126] The inter-check unit performs checks while considering the presenter's geographical background. For example, the inter-check unit adjusts the check algorithm based on the presenter's geographical background. Furthermore, the inter-check unit can select the optimal check method considering the presenter's geographical background. In addition, the inter-check unit can improve check accuracy based on the presenter's geographical background. Thus, by considering the presenter's geographical background, check accuracy can be improved.

[0127] The voice checking unit estimates the user's emotions and adjusts the voice volume check criteria based on the estimated emotions. For example, if the user is nervous, the voice checking unit will loosen the voice volume check criteria to help them relax. Furthermore, if the user is relaxed, the voice checking unit can perform a more detailed voice volume check. Additionally, if the user is in a hurry, the voice checking unit can perform a quick voice volume check. This allows for a more appropriate check by adjusting the voice volume check criteria according to the user's emotions.

[0128] The voice checking unit optimizes the checking algorithm by referring to the presenter's past voice data during the voice checking process. For example, the voice checking unit selects the optimal checking algorithm based on the presenter's past voice data. The voice checking unit can also analyze the presenter's past voice data and optimize the checking algorithm. Furthermore, the voice checking unit can improve the checking accuracy by referring to the presenter's past voice data. In this way, by referring to the presenter's past voice data, the checking algorithm can be optimized and the checking accuracy can be improved.

[0129] The voice check unit estimates the user's emotions and adjusts the order in which the voice check results are displayed based on the estimated emotions. For example, if the user is tense, the voice check unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the voice check unit can prioritize displaying concise results. By adjusting the order in which the voice check results are displayed according to the user's emotions, more appropriate results can be provided.

[0130] The voice checking unit takes the presenter's geographical background into consideration during the voice check. For example, the voice checking unit adjusts the checking algorithm based on the presenter's geographical background. Furthermore, the voice checking unit can select the optimal checking method considering the presenter's geographical background. In addition, the voice checking unit can improve the accuracy of the check based on the presenter's geographical background. Thus, by considering the presenter's geographical background, the accuracy of the check can be improved.

[0131] The tone check unit estimates the user's emotions and adjusts the tone check criteria based on the estimated emotions. For example, if the user is tense, the tone check unit will loosen the tone check criteria to help them relax. If the user is relaxed, the tone check unit can also perform a more detailed tone check. Furthermore, if the user is in a hurry, the tone check unit can perform a quick tone check. This allows for a more appropriate check by adjusting the tone check criteria according to the user's emotions.

[0132] The tone check unit optimizes the check algorithm by referring to the presenter's past tone data during tone checking. For example, the tone check unit selects the optimal check algorithm based on the presenter's past tone data. The tone check unit can also analyze the presenter's past tone data and optimize the check algorithm. Furthermore, the tone check unit can improve check accuracy by referring to the presenter's past tone data. In this way, by referring to the presenter's past tone data, the check algorithm can be optimized and check accuracy can be improved.

[0133] The tone check unit estimates the user's emotions and adjusts the order in which the tone check results are displayed based on the estimated emotions. For example, if the user is tense, the tone check unit will prioritize displaying results that promote relaxation. It can also prioritize displaying detailed results if the user is relaxed. Furthermore, if the user is in a hurry, the tone check unit can prioritize displaying concise results. By adjusting the order in which the tone check results are displayed according to the user's emotions, more appropriate results can be provided.

[0134] The tone checking unit takes the presenter's geographical background into consideration during the tone checking process. For example, the tone checking unit adjusts the checking algorithm based on the presenter's geographical background. Furthermore, the tone checking unit can select the optimal checking method considering the presenter's geographical background. In addition, the tone checking unit can improve the checking accuracy based on the presenter's geographical background. Thus, by considering the presenter's geographical background, the checking accuracy can be improved. === Hard Collateral 1-1 === Each of the multiple elements described above, including the reception unit, image recognition unit, voice recognition unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives video and audio as input. The image recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's gestures, posture, and gaze. The voice recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's count of unnecessary filler words, pauses, volume, and tone. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates improvement suggestions based on the results obtained by the image recognition unit and the voice recognition unit. === Hard Collateral 1-2 === Each of the multiple elements described above, including the reception unit, image recognition unit, voice recognition unit, and suggestion unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives video and audio as input. The image recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's gestures, posture, and gaze. The voice recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's count of unnecessary filler words, pauses, volume, and tone. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates improvement suggestions based on the results obtained by the image recognition unit and the voice recognition unit. === Hard Collateral 1-3 === Each of the multiple elements described above, including the reception unit, image recognition unit, voice recognition unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives video and audio as input. The image recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's gestures, posture, and gaze. The voice recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's count of unnecessary filler words, pauses, volume, and tone. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates improvement suggestions based on the results obtained by the image recognition unit and the voice recognition unit. === Hard Collateral 1-4 === Each of the multiple elements described above, including the reception unit, image recognition unit, speech recognition unit, and proposal unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives video and audio as input. The image recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's gestures, posture, and gaze. The speech recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and checks the presenter's count of unnecessary filler words, pauses, volume, and tone. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition unit.

[0135] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0136] The presentation checking system can also include a feedback unit. This feedback unit provides real-time feedback to the presenter. For example, if the speech recognition unit detects excessive use of filler words while the presenter is speaking, the feedback unit can immediately notify the presenter and encourage improvement. The feedback unit can also point out issues with the presenter's posture and eye contact in real time and encourage appropriate corrections. Furthermore, the feedback unit can provide real-time advice on adjusting the presenter's voice volume and tone. This allows the presenter to immediately identify areas for improvement and make corrections on the spot.

[0137] The presentation checking system can also include a data analysis unit. This unit analyzes the presenter's past presentation data to support long-term skill improvement. For example, it can track changes in the frequency of transitional phrases and pacing in the presenter's past presentations, showing trends for improvement. It can also analyze changes in the presenter's posture and eye contact, indicating which improvements were effective. Furthermore, it can track changes in the presenter's voice volume and tone, suggesting the optimal presentation style. This allows presenters to improve their skills over the long term.

[0138] The presentation checking system can also include a simulation unit. This unit provides a function that allows presenters to practice their presentations in a virtual environment. For example, the simulation unit can generate a virtual audience, allowing presenters to practice as if they were actually giving a presentation. The simulation unit can also check the presenter's gestures, posture, and eye contact in real time and provide feedback on areas for improvement. Furthermore, the simulation unit can analyze the presenter's voice and provide advice on the frequency of transitional words, pacing, and adjustments to voice volume and tone. This allows presenters to practice in an environment close to a real presentation and improve their skills.

[0139] The presentation checking system can also be equipped with an emotion analysis unit. This unit analyzes the presenter's emotions in real time and evaluates the effectiveness of the presentation. For example, it can estimate the presenter's level of tension and confidence from their facial expressions and tone of voice, and provide feedback as the presentation progresses. It can also track changes in the presenter's emotions and identify where tension increased. Furthermore, based on the presenter's emotions, the unit can offer advice on relaxation and suggestions for building confidence. This allows presenters to understand their own emotions and deliver more effective presentations.

[0140] The presentation checking system can also include an interactive section. This interactive section helps improve the presentation through dialogue between the presenter and the system. For example, when the presenter inputs a question, the system can provide appropriate advice. Furthermore, when the presenter consults the interactive section about a specific problem, the system can suggest concrete solutions. Additionally, when the presenter requests real-time feedback during practice, the system can respond immediately and point out areas for improvement. This allows the presenter to deliver a more effective presentation through interaction with the system.

[0141] The presentation checking system can also be equipped with an emotion estimation unit. This unit estimates the presenter's emotions and adjusts the presentation based on the estimated emotions. For example, if the presenter is nervous, the emotion estimation unit can slow down the presentation to help them relax. Conversely, if the presenter is relaxed, the unit can speed up the presentation. Furthermore, if the presenter is in a hurry, the unit can speed up the presentation. This allows for more effective presentations by adjusting the presentation pace according to the presenter's emotions.

[0142] The presentation checking system can also include an emotional feedback unit. This unit estimates the presenter's emotions and provides feedback based on those estimates. For example, if the presenter is nervous, it can offer advice on how to relax. If the presenter is confident, it can offer specific suggestions for further improvement. Furthermore, if the presenter is anxious, it can suggest ways to calm down. This allows the presenter to receive feedback tailored to their emotions, enabling them to deliver more effective presentations.

[0143] The presentation checking system can also be equipped with an emotion monitoring unit. This unit monitors the presenter's emotions in real time and provides feedback as the presentation progresses. For example, it can estimate emotions from the presenter's facial expressions and tone of voice, and provide advice to relax if tension increases. It can also track changes in the presenter's emotions and identify when their confidence increased. Furthermore, the emotion monitoring unit can adjust the presentation based on the presenter's emotions. This allows the presenter to understand their emotions in real time and deliver a more effective presentation.

[0144] The presentation checking system can also be equipped with an emotion tracking unit. This unit tracks the presenter's emotions over the long term to help improve their presentation skills. For example, it can record changes in the presenter's emotions during past presentations and analyze the situations in which tension increased. It can also track the presenter's emotional changes and indicate what improvements were effective. Furthermore, based on the presenter's emotions, the emotion tracking unit can suggest the optimal presentation method. This allows presenters to understand their long-term emotional changes and deliver more effective presentations.

[0145] The presentation checking system can also be equipped with an emotional assistance unit. This unit estimates the presenter's emotions and provides support for the presentation based on those emotions. For example, if the presenter is nervous, the emotional assistance unit can play music to help them relax. If the presenter is confident, the unit can also provide specific advice for further improvement. Furthermore, if the presenter is anxious, the unit can suggest breathing techniques to help them calm down. This allows the presenter to receive support tailored to their emotions, enabling them to deliver a more effective presentation.

[0146] The following briefly describes the processing flow for example form 2.

[0147] Step 1: The reception unit accepts video and audio as input. Video and audio include, but are not limited to, formats such as MP4, AVI, WAV, and MP3. Step 2: The image recognition unit performs image recognition based on the video received by the reception unit. The image recognition unit uses algorithms such as CNN (Convolutional Neural Network) and HOG (Histogram of Oriented Gradient) for image recognition. For example, it analyzes the presenter's gestures and body movements, checking hand movements and body orientation. It can also analyze the presenter's posture, checking standing and sitting positions. Furthermore, it can analyze the presenter's gaze, checking the direction and movement of their eyes. Step 3: The speech recognition unit performs speech recognition based on the audio received by the reception unit. The speech recognition unit uses algorithms such as HMM (Hidden Markov Model) or DNN (Deep Neural Network) for speech recognition. For example, it counts the number of times the presenter uses unnecessary filler words and checks for filler words such as "um" and "uh". It can also analyze the presenter's pacing and check the length of pauses and breaks in speech. Furthermore, it can analyze the volume of the presenter's voice and check the measured value in decibels (dB). Step 4: The suggestion unit generates improvement suggestions based on the results obtained by the image recognition unit and the speech recognition unit. The suggestion unit suggests improvements to the presentation slide structure and speaking style, for example. In this way, the presentation check system according to the embodiment can help improve presentation skills.

[0148] 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.

[0149] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0150] 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.

[0151] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0152] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[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 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.

[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 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.

[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. 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 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.

[0167] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0168] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.).

[0180] 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.

[0181] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0182] 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.

[0183] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0184] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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).

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.).

[0197] 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.

[0198] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0199] 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.

[0200] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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."

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Explanation of Symbols]

[0220] 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. A reception desk that accepts video and audio as input, An image recognition unit that performs image recognition based on the video received by the aforementioned reception unit, A speech recognition unit that performs speech recognition based on the voice received by the reception unit, A proposal unit that generates improvement suggestions based on the results obtained from the image recognition unit and the speech recognition unit, , equipped A system characterized by the following features.

2. The image recognition unit, It includes a gesture checker to verify the presenter's body language and movements. The system according to feature 1.

3. The image recognition unit, It includes a posture check unit to monitor the presenter's posture. The system according to feature 1.

4. The image recognition unit, It features an eye-tracking unit to check the presenter's gaze. The system according to feature 1.

5. The aforementioned speech recognition unit, It includes a counting unit that counts the number of times unnecessary connecting words are used. The system according to feature 1.

6. The aforementioned speech recognition unit, It includes a timing check unit to check the timing of the intervals. The system according to feature 1.

7. The aforementioned speech recognition unit, It is equipped with a voice check unit to check the volume of your voice. The system according to feature 1.

8. The aforementioned speech recognition unit, It features a tone check section for checking the tone. The system according to feature 1.

Images