System

Abstract

An object of a system according to an embodiment is to check voice quality in real time in a remote conference tool and automatically correct the voice quality when the voice quality is poor.SOLUTION: A system includes a voice quality check unit and a voice correction unit. The voice quality check unit checks voice quality in real time. The voice correction unit automatically corrects the voice when the voice quality check unit determines that the voice quality is poor.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it is difficult to correct audio quality in real time when it deteriorates in remote conferencing tools, which can disrupt the smooth progress of the meeting.

[0005] The system according to the embodiment aims to check the audio quality in real time in a remote conference tool and automatically correct the audio quality if it is poor. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice quality check unit and a voice correction unit. The voice quality check unit checks the voice quality in real time. The voice correction unit automatically corrects the voice when the voice quality check unit determines that the voice quality is poor. [Effects of the Invention]

[0007] The system according to the embodiment can check the audio quality in a remote conference tool in real time and automatically correct it if the audio quality is poor. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example 1) The remote conference system according to an embodiment of the present invention uses AI to check audio quality in real time and automatically corrects it if the audio quality is poor. This allows the remote conference system to maintain high-quality audio at all times during remote conferences and online communications.

[0029] A remote conference system according to an embodiment includes a voice quality check unit and a voice correction unit. The voice quality check unit checks voice quality in real time. For example, the generation AI receives voice data as input and analyzes factors that affect voice quality, such as noise, echo, and uneven volume. The generation AI also detects problems such as choppy voice and excessive background noise. The generation AI outputs a voice quality evaluation score and a list of problems. The voice correction unit automatically corrects the voice if it determines that the voice quality is poor. For example, the generation AI corrects the voice using technologies such as noise reduction, echo cancellation, and automatic volume adjustment. The generation AI also performs processes such as removing background noise and complementing voice interruptions. As a result, the remote conference system according to an embodiment can consistently maintain high-quality voice during remote conferences and online communications.

[0030] The voice quality check unit can analyze voice data and analyze at least one of the following factors that affect voice quality: noise, echo, and uneven volume. In the voice quality check unit, for example, the generation AI analyzes speech content during a meeting in real time to identify important speech. For example, it prioritizes analysis of speech during a presentation or speech that is the key point of a discussion. The generation AI also strengthens noise reduction and echo cancellation for speech with high importance. For example, it provides particularly high-quality audio for speech from a presenter. The generation AI also dynamically adjusts voice quality check criteria based on the importance of the speech content. For example, if there are many important speeches, it increases the frequency of voice quality checks. This enables detailed analysis of voice quality.

[0031] The audio correction unit can correct audio using at least one of noise reduction, echo cancellation, and automatic volume adjustment. For example, the audio correction unit uses a generation AI to analyze the emotions of speech in real time and identify emotionally charged speech. For example, it prioritizes improving audio quality for emotionally charged speech, such as anger or joy. The generation AI also strengthens noise reduction and echo cancellation for emotionally charged speech. For example, it provides particularly high-quality audio for emotionally charged speech. The generation AI also dynamically adjusts the audio quality check criteria based on the emotions of speech. For example, if there are many emotionally charged speeches, it increases the frequency of audio quality checks. This enables automatic audio quality correction.

[0032] The voice quality check unit can generate a voice quality evaluation score or a list of problems and notify participants. In the voice quality check unit, for example, the generation AI analyzes the progress of the meeting in real time and changes the voice quality check criteria depending on the situation, such as during a presentation or discussion. The generation AI also adjusts the strength of noise reduction and echo cancellation depending on the progress of the meeting. For example, it provides particularly high-quality voice during presentations. The generation AI also dynamically adjusts the frequency of voice quality checks based on the progress of the meeting. For example, it increases the frequency of voice quality checks when important topics are being discussed. This makes it possible to notify participants of the voice quality evaluation results.

[0033] The audio quality check unit can store the audio quality evaluation score or a list of problems in a database and manage it as a history. In the audio quality check unit, for example, the generation AI simultaneously analyzes audio and video data and comprehensively evaluates the quality of both. For example, if the audio is choppy, it also checks the video frame rate. In addition, to comprehensively evaluate audio and video quality, the generation AI adjusts the video resolution and frame rate at the same time as noise reduction and echo cancellation. The generation AI also sets standards for comprehensively evaluating audio and video quality and checks them in real time. For example, if audio quality deteriorates, it simultaneously checks the video quality. This makes it possible to manage audio quality history.

[0034] The voice quality check unit can provide a function that enables customization of voice quality check or correction settings. In the voice quality check unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the voice quality check criteria according to the connection status. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of voice quality checks. For example, if the connection is unstable, the check frequency is increased. This allows customization of the voice quality check and correction settings.

[0035] The voice quality check unit analyzes the importance of each statement and prioritizes improving the voice quality of important statements. For example, the voice quality check unit uses a generation AI to analyze statements made during a meeting in real time and identify important statements. For example, it prioritizes analysis of statements made during a presentation or statements that are key points in a discussion. The generation AI also strengthens noise reduction and echo cancellation for statements of high importance. For example, it provides particularly high-quality voice for the presenter's statements. The generation AI also dynamically adjusts the voice quality check criteria based on the importance of the statement. For example, if there are many important statements, it increases the frequency of voice quality checks. This makes it possible to prioritize improving the voice quality of important statements.

[0036] The voice quality check unit can dynamically change the voice quality check criteria according to the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the voice quality check criteria according to the situation, such as during a presentation or discussion. The generation AI also adjusts the strength of noise reduction and echo cancellation according to the progress of the meeting. For example, it provides particularly high-quality voice during presentations. The generation AI also dynamically adjusts the frequency of voice quality checks based on the progress of the meeting. For example, if an important topic is being discussed, it will increase the frequency of voice quality checks. This makes it possible to dynamically change the voice quality check criteria according to the progress of the meeting.

[0037] The audio quality check section simultaneously checks video quality, enabling a comprehensive evaluation of audio and video quality. For example, the audio quality check section uses a generation AI to simultaneously analyze audio and video data and comprehensively evaluate the quality of both. For example, if the audio is choppy, the generation AI also checks the video frame rate. To comprehensively evaluate audio and video quality, the generation AI also adjusts the video resolution and frame rate while simultaneously implementing noise reduction and echo cancellation. The generation AI also sets standards for comprehensively evaluating audio and video quality and checks them in real time. For example, if audio quality deteriorates, the generation AI simultaneously checks video quality. This makes it possible to comprehensively evaluate audio and video quality.

[0038] The voice quality check unit can monitor the network connection status of participants in real time and adjust the voice quality check criteria according to the connection status. In the voice quality check unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the voice quality check criteria according to the connection status. For example, if the connection is unstable, the check criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of voice quality checks. For example, if the connection is unstable, the check frequency is increased. This makes it possible to adjust the voice quality check criteria according to the network connection status.

[0039] The audio correction unit analyzes the importance of speech content and can prioritize audio quality correction for important speech. For example, the generation AI analyzes speech content during a meeting in real time and identifies important speech. For example, it prioritizes correction of speech during a presentation or speech that is the key point of a discussion. The generation AI also strengthens noise reduction and echo cancellation for speech with high importance. For example, it provides particularly high-quality audio for speech from a presenter. The generation AI also dynamically adjusts the audio quality correction criteria based on the importance of speech content. For example, if there are many important speeches, it increases the frequency of audio quality correction. This makes it possible to prioritize audio quality correction for important speech.

[0040] The audio correction unit can dynamically change the audio quality correction standard depending on the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the audio quality correction standard depending on the situation, such as during a presentation or discussion. The generation AI also adjusts the strength of noise reduction and echo cancellation depending on the progress of the meeting. For example, it provides particularly high-quality audio during presentations. The generation AI also dynamically adjusts the frequency of audio quality correction based on the progress of the meeting. For example, it increases the frequency of audio quality correction when an important topic is being discussed. This makes it possible to dynamically change the audio quality correction standard depending on the progress of the meeting.

[0041] The audio correction unit simultaneously corrects video quality, enabling comprehensive correction of audio and video quality. For example, the generation AI analyzes audio and video data simultaneously and comprehensively corrects both qualities. For example, if the audio is choppy, it also adjusts the video frame rate. To comprehensively correct audio and video quality, the generation AI also adjusts the video resolution and frame rate at the same time as noise reduction and echo cancellation. The generation AI also sets standards for comprehensively correcting audio and video quality and performs corrections in real time. For example, if audio quality deteriorates, it simultaneously corrects video quality. This makes it possible to comprehensively correct audio and video quality.

[0042] The audio correction unit can monitor the network connection status of participants in real time and adjust the audio quality correction standards according to the connection status. In the audio correction unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the audio quality correction standards according to the connection status. For example, if the connection is unstable, the correction standards are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality audio is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of audio quality correction. For example, if the connection is unstable, the correction frequency is increased. This makes it possible to adjust the audio quality correction standards according to the network connection status.

[0043] When notifying a voice quality evaluation score or a list of problems, the voice quality check unit can analyze the importance of the content of statements and prioritize notifying important statements with evaluation scores. In the voice quality check unit, for example, the generation AI analyzes the content of statements made during a meeting in real time and identifies important statements. For example, it prioritizes notifying statements made during a presentation or statements that are key points in a discussion as evaluation scores. The generation AI also emphasizes and notifies voice quality evaluation scores for statements with high importance. For example, it provides a particularly high-quality voice evaluation score for statements made by a presenter. The generation AI also dynamically adjusts the notification criteria for the voice quality evaluation score based on the importance of the content of statements. For example, if there are many important statements, it increases the frequency of evaluation score notifications. This makes it possible to prioritize notifying voice quality evaluation scores for important statements.

[0044] When notifying the voice quality evaluation score or a list of problems, the voice quality check unit can dynamically change the notification criteria for the evaluation score according to the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the notification criteria for the voice quality evaluation score according to the situation, such as during a presentation or discussion. The generation AI also adjusts the notification frequency for the voice quality evaluation score according to the progress of the meeting. For example, it provides a particularly high-quality voice evaluation score during a presentation. The generation AI also dynamically adjusts the notification criteria for the voice quality evaluation score based on the progress of the meeting. For example, if an important topic is being discussed, it increases the notification frequency of the evaluation score. This makes it possible to dynamically change the notification criteria for the voice quality evaluation score according to the progress of the meeting.

[0045] When notifying the audio quality evaluation score, the audio quality check unit simultaneously notifies the video quality evaluation score, enabling a comprehensive evaluation of audio and video quality. For example, the audio quality check unit uses a generation AI to simultaneously analyze audio and video data and comprehensively evaluate the quality of both. For example, if the audio is choppy, it also checks the video frame rate. To comprehensively evaluate audio and video quality, the generation AI also adjusts the video resolution and frame rate while simultaneously implementing noise reduction and echo cancellation. The generation AI also sets standards for comprehensively evaluating audio and video quality and notifies the evaluation score in real time. For example, if audio quality deteriorates, it simultaneously evaluates video quality. This makes it possible to comprehensively evaluate audio and video quality.

[0046] When notifying the voice quality evaluation score, the voice quality check unit can monitor the participant's network connection status in real time and adjust the notification criteria for the evaluation score according to the connection status. In the voice quality check unit, for example, the generation AI monitors the participant's network connection status in real time and adjusts the notification criteria for the voice quality evaluation score according to the connection status. For example, if the connection is unstable, the notification criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, a high-quality voice evaluation score is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the notification frequency for the voice quality evaluation score. For example, if the connection is unstable, the notification frequency is increased. This makes it possible to adjust the notification criteria for the voice quality evaluation score according to the network connection status.

[0047] When providing advice for improvement, the voice quality check unit can analyze the importance of the content of comments and prioritize the provision of advice to important comments. In the voice quality check unit, for example, the generation AI analyzes the content of comments made during a meeting in real time and identifies important comments. For example, it prioritizes providing advice to comments made during a presentation or comments that are key points in a discussion. The generation AI also provides specific improvement advice to highly important comments. For example, it provides advice that is particularly effective for comments made by the presenter. The generation AI also dynamically adjusts the criteria for providing improvement advice based on the importance of the content of comments. For example, if there are many important comments, it increases the frequency of providing advice. This makes it possible to prioritize the provision of improvement advice to important comments.

[0048] When providing advice for improvement, the voice quality check unit can dynamically change the content of the advice depending on the progress of the meeting. For example, the generation AI in the voice quality check unit analyzes the progress of the meeting in real time and changes the content of the advice depending on the situation, such as during a presentation or discussion. The generation AI also provides specific improvement advice depending on the progress of the meeting. For example, it provides advice that is particularly effective during a presentation. The generation AI also dynamically adjusts the criteria for providing improvement advice based on the progress of the meeting. For example, it increases the frequency of providing advice when an important topic is being discussed. This makes it possible to dynamically change the content of the advice for improvement depending on the progress of the meeting.

[0049] When providing advice for improvement, the audio quality check unit simultaneously provides advice for improving video quality, enabling comprehensive improvements to audio and video quality. For example, the audio quality check unit uses a generation AI to simultaneously analyze audio and video data and provide advice for comprehensively improving the quality of both. For example, if the audio is choppy, the generation AI also adjusts the video frame rate. To comprehensively improve audio and video quality, the generation AI also adjusts the video resolution and frame rate while simultaneously implementing noise reduction and echo cancellation. The generation AI also sets standards for comprehensively improving audio and video quality and provides advice in real time. For example, if audio quality deteriorates, the video quality is also improved simultaneously. This makes it possible to provide advice for comprehensively improving audio and video quality.

[0050] When providing advice for improvement, the voice quality check unit can monitor the participant's network connection status in real time and adjust the content of the advice according to the connection status. In the voice quality check unit, for example, the generation AI monitors the participant's network connection status in real time and adjusts the content of the improvement advice according to the connection status. For example, if the connection is unstable, the content of the advice is relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of providing improvement advice. For example, if the connection is unstable, the frequency of providing advice is increased. This makes it possible to adjust the content of the improvement advice according to the network connection status.

[0051] When managing the voice quality history, the voice quality check unit can analyze the importance of the content of statements and prioritize saving the history of important statements. In the voice quality check unit, for example, the generation AI analyzes the content of statements made during a meeting in real time and identifies important statements. For example, it prioritizes saving statements made during a presentation or statements that are key points in a discussion as history. The generation AI also emphasizes and saves the voice quality history of statements that are highly important. For example, it saves particularly detailed history of statements made by the presenter. The generation AI also dynamically adjusts the voice quality history saving criteria based on the importance of the content of statements. For example, if there are many important statements, it increases the frequency of history saving. This makes it possible to prioritize saving the voice quality history of important statements.

[0052] When managing the voice quality history, the voice quality check unit can dynamically change the standard for saving the history depending on the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the standard for saving the voice quality history depending on the situation, such as during a presentation or discussion. The generation AI also adjusts the frequency of saving the voice quality history depending on the progress of the meeting. For example, it saves particularly detailed history during a presentation. The generation AI also dynamically adjusts the standard for saving the voice quality history based on the progress of the meeting. For example, it increases the frequency of saving history when an important topic is being discussed. This makes it possible to dynamically change the standard for saving the voice quality history depending on the progress of the meeting.

[0053] When managing audio quality history, the audio quality check unit simultaneously manages video quality history, enabling comprehensive management of audio and video quality. For example, the audio quality check unit allows the generation AI to simultaneously analyze audio and video data and save a history for comprehensive management of both qualities. For example, if the audio is choppy, the video frame rate is also recorded. In addition, the generation AI records the video resolution and frame rate at the same time as noise reduction and echo cancellation to comprehensively manage audio and video quality. The generation AI also sets standards for comprehensive management of audio and video quality and saves the history in real time. For example, if audio quality deteriorates, the video quality is also recorded at the same time. This makes it possible to save a history for comprehensive management of audio and video quality.

[0054] When managing the voice quality history, the voice quality check unit can monitor the network connection status of participants in real time and adjust the history storage criteria according to the connection status. In the voice quality check unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the voice quality history storage criteria according to the connection status. For example, if the connection is unstable, the storage criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, a high-quality voice history is stored. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency at which the voice quality history is stored. For example, if the connection is unstable, the storage frequency is increased. This makes it possible to adjust the voice quality history storage criteria according to the network connection status.

[0055] When providing customized voice quality settings, the voice quality check unit can analyze the importance of the speech content and prioritize the application of customized settings to important speech. In the voice quality check unit, for example, the generation AI analyzes speech content during a meeting in real time and identifies important speech. For example, the generation AI prioritizes the application of customized settings to speech during a presentation or speech that is the key point of a discussion. The generation AI also strengthens customized noise reduction and echo cancellation settings for speech with high importance. For example, it provides particularly high-quality audio for speech from the presenter. The generation AI also dynamically adjusts the criteria for customized settings based on the importance of the speech content. For example, if there are many important speeches, the frequency of customized settings is increased. This makes it possible to prioritize the application of customized voice quality settings to important speech.

[0056] When providing customized voice quality settings, the voice quality check unit can dynamically change the criteria for the customization settings according to the progress of the meeting. In the voice quality check unit, for example, the generation AI analyzes the progress of the meeting in real time and changes the criteria for the customization settings according to the situation, such as during a presentation or discussion. The generation AI also adjusts the customized settings for noise reduction and echo cancellation according to the progress of the meeting. For example, it provides particularly high-quality voice during presentations. The generation AI also dynamically adjusts the criteria for the customization settings based on the progress of the meeting. For example, if an important topic is being discussed, it increases the frequency of the customization settings. This makes it possible to dynamically change the criteria for the customized voice quality settings according to the progress of the meeting.

[0057] When providing customization settings for audio quality, the audio quality check unit simultaneously provides customization settings for video quality, allowing for comprehensive customization of audio and video quality. In the audio quality check unit, for example, the generation AI simultaneously analyzes audio and video data and provides settings for comprehensive customization of both quality. For example, if the audio is choppy, the generation AI also adjusts the video frame rate. To comprehensively customize audio and video quality, the generation AI also adjusts the video resolution and frame rate at the same time as noise reduction and echo cancellation. The generation AI also sets standards for comprehensive customization of audio and video quality and provides customization settings in real time. For example, if audio quality deteriorates, the video quality is also customized at the same time. This makes it possible to provide settings for comprehensive customization of audio and video quality.

[0058] When providing customized voice quality settings, the voice quality check unit can monitor the network connection status of the participant in real time and adjust the criteria for the customized voice quality settings according to the connection status. In the voice quality check unit, for example, the generation AI monitors the network connection status of the participant in real time and adjusts the criteria for the customized voice quality settings according to the connection status. For example, if the connection is unstable, the setting criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of the customized voice quality settings. For example, if the connection is unstable, the setting frequency is increased. This makes it possible to adjust the criteria for the customized voice quality settings according to the network connection status.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The remote conference system can further include a progress analyzer that analyzes the progress of the conference in real time. The progress analyzer can dynamically adjust the standards for checking and correcting audio quality according to the progress of the conference. For example, it can provide particularly high-quality audio during presentations and strengthen correction to prevent audio interruptions during discussions. The progress analyzer can also dynamically adjust the frequency of checking and correcting audio quality based on the progress of the conference. This makes it possible to provide optimal audio quality according to the progress of the conference.

[0061] The remote conference system may further include a connection monitoring unit that monitors the network connection status of participants in real time. The connection monitoring unit can dynamically adjust the audio quality check and correction standards according to the network connection status of participants. For example, the check standards can be relaxed when the connection is unstable, and high-quality audio can be provided when the connection is stable. The connection monitoring unit can also adjust the strength of noise reduction and echo cancellation based on the network connection status. This makes it possible to provide optimal audio quality according to the network connection status.

[0062] The remote conferencing system can also analyze audio and video data simultaneously to comprehensively evaluate the quality of both. For example, if the audio is choppy, it can also check the video frame rate and set a standard for comprehensively evaluating the audio and video quality. Furthermore, to comprehensively evaluate the audio and video quality, it can adjust the video resolution and frame rate at the same time as noise reduction and echo cancellation. This makes it possible to comprehensively evaluate the audio and video quality.

[0063] The remote conference system can also dynamically change the standard for correcting audio quality according to the progress of the conference. For example, it can provide particularly high-quality audio during presentations and strengthen correction to prevent audio interruptions during discussions. It can also dynamically adjust the frequency of audio quality correction based on the progress of the conference. This makes it possible to provide optimal audio quality according to the progress of the conference.

[0064] The remote conferencing system also notifies users of the audio quality evaluation score at the same time as notifying them of the video quality evaluation score, allowing for a comprehensive evaluation of audio and video quality. For example, if the audio is choppy, the system can also check the video frame rate and set standards for comprehensively evaluating audio and video quality. Furthermore, to comprehensively evaluate audio and video quality, the system can adjust the video resolution and frame rate at the same time as noise reduction and echo cancellation. This makes it possible to comprehensively evaluate audio and video quality.

[0065] The remote conferencing system can also monitor participants' network connection status in real time and adjust the notification criteria for the voice quality evaluation score according to the connection status. For example, it can relax the notification criteria if the connection is unstable and provide a high-quality voice evaluation score if the connection is stable. It can also adjust the strength of noise reduction and echo cancellation based on the network connection status. This makes it possible to provide an optimal voice quality evaluation score according to the network connection status.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The voice quality checker checks voice quality in real time. For example, the generation AI receives voice data as input and analyzes factors that affect voice quality, such as noise, echo, and uneven volume. The generation AI also detects problems such as choppy voice or excessive background noise. The generation AI outputs a voice quality evaluation score and a list of problems. Step 2: The audio correction unit automatically corrects the audio if it determines that the audio quality is poor. For example, the generation AI corrects the audio using techniques such as noise reduction, echo cancellation, and automatic volume adjustment. The generation AI also performs processes such as removing background noise and filling in gaps in the audio.

[0068] (Example 2) The remote conference system according to an embodiment of the present invention uses AI to check audio quality in real time and automatically corrects it if the audio quality is poor. This allows the remote conference system to maintain high-quality audio at all times during remote conferences and online communications.

[0069] A remote conference system according to an embodiment includes a voice quality check unit and a voice correction unit. The voice quality check unit checks voice quality in real time. For example, the generation AI receives voice data as input and analyzes factors that affect voice quality, such as noise, echo, and uneven volume. The generation AI also detects problems such as choppy voice and excessive background noise. The generation AI outputs a voice quality evaluation score and a list of problems. The voice correction unit automatically corrects the voice if it determines that the voice quality is poor. For example, the generation AI corrects the voice using technologies such as noise reduction, echo cancellation, and automatic volume adjustment. The generation AI also performs processes such as removing background noise and complementing voice interruptions. As a result, the remote conference system according to an embodiment can consistently maintain high-quality voice during remote conferences and online communications.

[0070] The voice quality check unit can analyze voice data and analyze at least one of the following factors that affect voice quality: noise, echo, and uneven volume. In the voice quality check unit, for example, the generation AI analyzes speech content during a meeting in real time to identify important speech. For example, it prioritizes analysis of speech during a presentation or speech that is the key point of a discussion. The generation AI also strengthens noise reduction and echo cancellation for speech with high importance. For example, it provides particularly high-quality audio for speech from a presenter. The generation AI also dynamically adjusts voice quality check criteria based on the importance of the speech content. For example, if there are many important speeches, it increases the frequency of voice quality checks. This enables detailed analysis of voice quality.

[0071] The audio correction unit can correct audio using at least one of noise reduction, echo cancellation, and automatic volume adjustment. For example, the audio correction unit uses a generation AI to analyze the emotions of speech in real time and identify emotionally charged speech. For example, it prioritizes improving audio quality for emotionally charged speech, such as anger or joy. The generation AI also strengthens noise reduction and echo cancellation for emotionally charged speech. For example, it provides particularly high-quality audio for emotionally charged speech. The generation AI also dynamically adjusts the audio quality check criteria based on the emotions of speech. For example, if there are many emotionally charged speeches, it increases the frequency of audio quality checks. This enables automatic audio quality correction.

[0072] The voice quality check unit can generate a voice quality evaluation score or a list of problems and notify participants. In the voice quality check unit, for example, the generation AI analyzes the progress of the meeting in real time and changes the voice quality check criteria depending on the situation, such as during a presentation or discussion. The generation AI also adjusts the strength of noise reduction and echo cancellation depending on the progress of the meeting. For example, it provides particularly high-quality voice during presentations. The generation AI also dynamically adjusts the frequency of voice quality checks based on the progress of the meeting. For example, it increases the frequency of voice quality checks when important topics are being discussed. This makes it possible to notify participants of the voice quality evaluation results.

[0073] The audio quality check unit can store the audio quality evaluation score or a list of problems in a database and manage it as a history. In the audio quality check unit, for example, the generation AI simultaneously analyzes audio and video data and comprehensively evaluates the quality of both. For example, if the audio is choppy, it also checks the video frame rate. In addition, to comprehensively evaluate audio and video quality, the generation AI adjusts the video resolution and frame rate at the same time as noise reduction and echo cancellation. The generation AI also sets standards for comprehensively evaluating audio and video quality and checks them in real time. For example, if audio quality deteriorates, it simultaneously checks the video quality. This makes it possible to manage audio quality history.

[0074] The voice quality check unit can provide a function that enables customization of voice quality check or correction settings. In the voice quality check unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the voice quality check criteria according to the connection status. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of voice quality checks. For example, if the connection is unstable, the check frequency is increased. This allows customization of the voice quality check and correction settings.

[0075] The voice quality check unit analyzes the importance of each statement and prioritizes improving the voice quality of important statements. For example, the voice quality check unit uses a generation AI to analyze statements made during a meeting in real time and identify important statements. For example, it prioritizes analysis of statements made during a presentation or statements that are key points in a discussion. The generation AI also strengthens noise reduction and echo cancellation for statements of high importance. For example, it provides particularly high-quality voice for the presenter's statements. The generation AI also dynamically adjusts the voice quality check criteria based on the importance of the statement. For example, if there are many important statements, it increases the frequency of voice quality checks. This makes it possible to prioritize improving the voice quality of important statements.

[0076] The voice quality check unit can estimate the emotion of a speech and prioritize improving voice quality for speech that expresses strong emotions. In the voice quality check unit, for example, the generation AI analyzes the emotion of a speech in real time and identifies speech that expresses strong emotions. For example, it prioritizes improving voice quality for speech that expresses strong emotions such as anger or joy. The generation AI also strengthens noise reduction and echo cancellation for speech that expresses strong emotions. For example, it provides particularly high-quality voice for speech that expresses strong emotions. The generation AI also dynamically adjusts the voice quality check criteria based on the emotion of the speech. For example, if there are many speeches that express strong emotions, it increases the frequency of voice quality checks. This makes it possible to prioritize improving voice quality for speech that expresses strong emotions.

[0077] The voice quality check unit can dynamically change the voice quality check criteria according to the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the voice quality check criteria according to the situation, such as during a presentation or discussion. The generation AI also adjusts the strength of noise reduction and echo cancellation according to the progress of the meeting. For example, it provides particularly high-quality voice during presentations. The generation AI also dynamically adjusts the frequency of voice quality checks based on the progress of the meeting. For example, if an important topic is being discussed, it will increase the frequency of voice quality checks. This makes it possible to dynamically change the voice quality check criteria according to the progress of the meeting.

[0078] The audio quality check section simultaneously checks video quality, enabling a comprehensive evaluation of audio and video quality. For example, the audio quality check section uses a generation AI to simultaneously analyze audio and video data and comprehensively evaluate the quality of both. For example, if the audio is choppy, the generation AI also checks the video frame rate. To comprehensively evaluate audio and video quality, the generation AI also adjusts the video resolution and frame rate while simultaneously implementing noise reduction and echo cancellation. The generation AI also sets standards for comprehensively evaluating audio and video quality and checks them in real time. For example, if audio quality deteriorates, the generation AI simultaneously checks video quality. This makes it possible to comprehensively evaluate audio and video quality.

[0079] The voice quality check unit can monitor the network connection status of participants in real time and adjust the voice quality check criteria according to the connection status. In the voice quality check unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the voice quality check criteria according to the connection status. For example, if the connection is unstable, the check criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of voice quality checks. For example, if the connection is unstable, the check frequency is increased. This makes it possible to adjust the voice quality check criteria according to the network connection status.

[0080] The voice quality check unit can estimate the emotions of participants and relax the voice quality check standards when the emotions are positive. In the voice quality check unit, for example, the generation AI analyzes the emotions of participants in real time and relaxes the voice quality check standards when the emotions are positive. For example, the check standards are relaxed when the emotions are excited. In addition, the generation AI adjusts the strength of noise reduction and echo cancellation when the emotions are positive. For example, the voice quality check standards are relaxed when the emotions are excited. In addition, the generation AI dynamically adjusts the frequency of voice quality checks based on the emotions of participants. For example, the check frequency is relaxed when the emotions are positive. This makes it possible to relax the voice quality check standards when the emotions are positive.

[0081] The audio correction unit analyzes the importance of speech content and can prioritize audio quality correction for important speech. For example, the generation AI analyzes speech content during a meeting in real time and identifies important speech. For example, it prioritizes correction of speech during a presentation or speech that is the key point of a discussion. The generation AI also strengthens noise reduction and echo cancellation for speech with high importance. For example, it provides particularly high-quality audio for speech from a presenter. The generation AI also dynamically adjusts the audio quality correction criteria based on the importance of speech content. For example, if there are many important speeches, it increases the frequency of audio quality correction. This makes it possible to prioritize audio quality correction for important speech.

[0082] The voice correction unit can estimate the emotion of a speech and prioritize voice quality correction for speech that expresses strong emotions. For example, the voice correction unit uses a generation AI to analyze the emotion of a speech in real time and identify speech that expresses strong emotions. For example, it prioritizes voice quality correction for speech that expresses strong emotions, such as anger or joy. The generation AI also strengthens noise reduction and echo cancellation for speech that expresses strong emotions. For example, it provides particularly high-quality voice for speech that expresses strong emotions. The generation AI also dynamically adjusts the voice quality correction criteria based on the emotion of the speech. For example, if there are many speeches that express strong emotions, it increases the frequency of voice quality correction. This makes it possible to prioritize voice quality correction for speech that expresses strong emotions.

[0083] The audio correction unit can dynamically change the audio quality correction standard depending on the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the audio quality correction standard depending on the situation, such as during a presentation or discussion. The generation AI also adjusts the strength of noise reduction and echo cancellation depending on the progress of the meeting. For example, it provides particularly high-quality audio during presentations. The generation AI also dynamically adjusts the frequency of audio quality correction based on the progress of the meeting. For example, it increases the frequency of audio quality correction when an important topic is being discussed. This makes it possible to dynamically change the audio quality correction standard depending on the progress of the meeting.

[0084] The audio correction unit simultaneously corrects video quality, enabling comprehensive correction of audio and video quality. For example, the generation AI analyzes audio and video data simultaneously and comprehensively corrects both qualities. For example, if the audio is choppy, it also adjusts the video frame rate. To comprehensively correct audio and video quality, the generation AI also adjusts the video resolution and frame rate at the same time as noise reduction and echo cancellation. The generation AI also sets standards for comprehensively correcting audio and video quality and performs corrections in real time. For example, if audio quality deteriorates, it simultaneously corrects video quality. This makes it possible to comprehensively correct audio and video quality.

[0085] The audio correction unit can monitor the network connection status of participants in real time and adjust the audio quality correction standards according to the connection status. In the audio correction unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the audio quality correction standards according to the connection status. For example, if the connection is unstable, the correction standards are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality audio is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of audio quality correction. For example, if the connection is unstable, the correction frequency is increased. This makes it possible to adjust the audio quality correction standards according to the network connection status.

[0086] The voice correction unit can estimate the emotions of participants and relax the voice quality correction standards when the emotions are positive. In the voice correction unit, for example, the generation AI analyzes the emotions of participants in real time and relaxes the voice quality correction standards when the emotions are positive. For example, the correction standards are relaxed when the emotions are excited. In addition, the generation AI adjusts the strength of noise reduction and echo cancellation when the emotions are positive. For example, the voice quality correction standards are relaxed when the emotions are excited. In addition, the generation AI dynamically adjusts the frequency of voice quality correction based on the emotions of participants. For example, the correction frequency is relaxed when the emotions are positive. This makes it possible to relax the voice quality correction standards when the emotions are positive.

[0087] When notifying a voice quality evaluation score or a list of problems, the voice quality check unit can analyze the importance of the content of statements and prioritize notifying important statements with evaluation scores. In the voice quality check unit, for example, the generation AI analyzes the content of statements made during a meeting in real time and identifies important statements. For example, it prioritizes notifying statements made during a presentation or statements that are key points in a discussion as evaluation scores. The generation AI also emphasizes and notifies voice quality evaluation scores for statements with high importance. For example, it provides a particularly high-quality voice evaluation score for statements made by a presenter. The generation AI also dynamically adjusts the notification criteria for the voice quality evaluation score based on the importance of the content of statements. For example, if there are many important statements, it increases the frequency of evaluation score notifications. This makes it possible to prioritize notifying voice quality evaluation scores for important statements.

[0088] When notifying a voice quality evaluation score or a list of problems, the voice quality check unit can estimate the emotion of the utterance and prioritize notifying evaluation scores for utterances with strong emotions. In the voice quality check unit, for example, the generation AI analyzes the emotion of the utterance in real time and identifies utterances with strong emotions. For example, it prioritizes notifying voice quality evaluation scores for utterances with strong emotions, such as anger or joy. The generation AI also emphasizes the voice quality evaluation score for utterances with strong emotions and notifies them. For example, it provides a particularly high-quality voice evaluation score for utterances with high emotions. The generation AI also dynamically adjusts the notification criteria for the voice quality evaluation score based on the emotion of the utterance. For example, if there are many utterances with strong emotions, it increases the frequency of notification of the evaluation score. This makes it possible to prioritize notifying voice quality evaluation scores for utterances with strong emotions.

[0089] When notifying the voice quality evaluation score or a list of problems, the voice quality check unit can dynamically change the notification criteria for the evaluation score according to the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the notification criteria for the voice quality evaluation score according to the situation, such as during a presentation or discussion. The generation AI also adjusts the notification frequency for the voice quality evaluation score according to the progress of the meeting. For example, it provides a particularly high-quality voice evaluation score during a presentation. The generation AI also dynamically adjusts the notification criteria for the voice quality evaluation score based on the progress of the meeting. For example, if an important topic is being discussed, it increases the notification frequency of the evaluation score. This makes it possible to dynamically change the notification criteria for the voice quality evaluation score according to the progress of the meeting.

[0090] When notifying the audio quality evaluation score, the audio quality check unit simultaneously notifies the video quality evaluation score, enabling a comprehensive evaluation of audio and video quality. For example, the audio quality check unit uses a generation AI to simultaneously analyze audio and video data and comprehensively evaluate the quality of both. For example, if the audio is choppy, it also checks the video frame rate. To comprehensively evaluate audio and video quality, the generation AI also adjusts the video resolution and frame rate while simultaneously implementing noise reduction and echo cancellation. The generation AI also sets standards for comprehensively evaluating audio and video quality and notifies the evaluation score in real time. For example, if audio quality deteriorates, it simultaneously evaluates video quality. This makes it possible to comprehensively evaluate audio and video quality.

[0091] When notifying the voice quality evaluation score, the voice quality check unit can monitor the participant's network connection status in real time and adjust the notification criteria for the evaluation score according to the connection status. In the voice quality check unit, for example, the generation AI monitors the participant's network connection status in real time and adjusts the notification criteria for the voice quality evaluation score according to the connection status. For example, if the connection is unstable, the notification criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, a high-quality voice evaluation score is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the notification frequency for the voice quality evaluation score. For example, if the connection is unstable, the notification frequency is increased. This makes it possible to adjust the notification criteria for the voice quality evaluation score according to the network connection status.

[0092] The voice quality check unit estimates the emotions of participants when notifying them of the voice quality evaluation score, and can relax the notification criteria for the evaluation score if the emotion is positive. In the voice quality check unit, for example, the generation AI analyzes the emotions of participants in real time, and relaxes the notification criteria for the voice quality evaluation score if the emotion is positive. For example, the notification criteria are relaxed if the emotion is excited. In addition, the generation AI adjusts the strength of noise reduction and echo cancellation if the emotion is positive. For example, the notification criteria for the voice quality evaluation score are relaxed if the emotion is excited. In addition, the generation AI dynamically adjusts the notification frequency for the voice quality evaluation score based on the participant's emotion. For example, the notification frequency is relaxed if the emotion is positive. This makes it possible to relax the notification criteria for the voice quality evaluation score if the emotion is positive.

[0093] When providing advice for improvement, the voice quality check unit can analyze the importance of the content of comments and prioritize the provision of advice to important comments. In the voice quality check unit, for example, the generation AI analyzes the content of comments made during a meeting in real time and identifies important comments. For example, it prioritizes providing advice to comments made during a presentation or comments that are key points in a discussion. The generation AI also provides specific improvement advice to highly important comments. For example, it provides advice that is particularly effective for comments made by the presenter. The generation AI also dynamically adjusts the criteria for providing improvement advice based on the importance of the content of comments. For example, if there are many important comments, it increases the frequency of providing advice. This makes it possible to prioritize the provision of improvement advice to important comments.

[0094] When providing advice for improvement, the voice quality check unit can estimate the emotion of a statement and prioritize providing advice to statements that contain strong emotions. In the voice quality check unit, for example, the generation AI analyzes the emotion of a statement in real time and identifies statements that contain strong emotions. For example, it prioritizes providing improvement advice to statements that contain strong emotions, such as anger or joy. The generation AI also provides specific improvement advice to statements that contain strong emotions. For example, it provides advice that is particularly effective for statements that contain strong emotions. The generation AI also dynamically adjusts the criteria for providing improvement advice based on the emotion of the statement. For example, if there are many statements that contain strong emotions, it increases the frequency of providing advice. This makes it possible to prioritize providing improvement advice to statements that contain strong emotions.

[0095] When providing advice for improvement, the voice quality check unit can dynamically change the content of the advice depending on the progress of the meeting. For example, the generation AI in the voice quality check unit analyzes the progress of the meeting in real time and changes the content of the advice depending on the situation, such as during a presentation or discussion. The generation AI also provides specific improvement advice depending on the progress of the meeting. For example, it provides advice that is particularly effective during a presentation. The generation AI also dynamically adjusts the criteria for providing improvement advice based on the progress of the meeting. For example, it increases the frequency of providing advice when an important topic is being discussed. This makes it possible to dynamically change the content of the advice for improvement depending on the progress of the meeting.

[0096] When providing advice for improvement, the audio quality check unit simultaneously provides advice for improving video quality, enabling comprehensive improvements to audio and video quality. For example, the audio quality check unit uses a generation AI to simultaneously analyze audio and video data and provide advice for comprehensively improving the quality of both. For example, if the audio is choppy, the generation AI also adjusts the video frame rate. To comprehensively improve audio and video quality, the generation AI also adjusts the video resolution and frame rate while simultaneously implementing noise reduction and echo cancellation. The generation AI also sets standards for comprehensively improving audio and video quality and provides advice in real time. For example, if audio quality deteriorates, the video quality is also improved simultaneously. This makes it possible to provide advice for comprehensively improving audio and video quality.

[0097] When providing advice for improvement, the voice quality check unit can monitor the participant's network connection status in real time and adjust the content of the advice according to the connection status. In the voice quality check unit, for example, the generation AI monitors the participant's network connection status in real time and adjusts the content of the improvement advice according to the connection status. For example, if the connection is unstable, the content of the advice is relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of providing improvement advice. For example, if the connection is unstable, the frequency of providing advice is increased. This makes it possible to adjust the content of the improvement advice according to the network connection status.

[0098] When providing advice for improvement, the voice quality check unit can estimate the participant's emotions and soften the content of the advice if the emotion is positive. In the voice quality check unit, for example, the generation AI analyzes the participant's emotions in real time and softens the content of the improvement advice if the emotion is positive. For example, the advice is softened if the emotion is excited. In addition, the generation AI adjusts the strength of noise reduction and echo cancellation if the emotion is positive. For example, the improvement advice is softened if the emotion is excited. In addition, the generation AI dynamically adjusts the frequency of providing improvement advice based on the participant's emotions. For example, the frequency of providing advice is softened if the emotion is positive. This makes it possible to soften the content of the improvement advice if the emotion is positive.

[0099] When managing the voice quality history, the voice quality check unit can analyze the importance of the content of statements and prioritize saving the history of important statements. In the voice quality check unit, for example, the generation AI analyzes the content of statements made during a meeting in real time and identifies important statements. For example, it prioritizes saving statements made during a presentation or statements that are key points in a discussion as history. The generation AI also emphasizes and saves the voice quality history of statements that are highly important. For example, it saves particularly detailed history of statements made by the presenter. The generation AI also dynamically adjusts the voice quality history saving criteria based on the importance of the content of statements. For example, if there are many important statements, it increases the frequency of history saving. This makes it possible to prioritize saving the voice quality history of important statements.

[0100] When managing the voice quality history, the voice quality check unit can estimate the emotion of a speech and prioritize saving the history of speech that expresses strong emotions. In the voice quality check unit, for example, the generation AI analyzes the emotion of a speech in real time and identifies speech that expresses strong emotions. For example, the voice quality check unit prioritizes saving the voice quality history of speech that expresses strong emotions, such as anger or joy. The generation AI also emphasizes and saves the voice quality history of speech that expresses strong emotions. For example, it saves particularly detailed history for speech that expresses strong emotions. The generation AI also dynamically adjusts the voice quality history saving criteria based on the emotion of the speech. For example, if there are many speeches that express strong emotions, it increases the frequency of history saving. This makes it possible to prioritize saving the voice quality history of speech that expresses strong emotions.

[0101] When managing the voice quality history, the voice quality check unit can dynamically change the standard for saving the history depending on the progress of the meeting. For example, the generation AI analyzes the progress of the meeting in real time and changes the standard for saving the voice quality history depending on the situation, such as during a presentation or discussion. The generation AI also adjusts the frequency of saving the voice quality history depending on the progress of the meeting. For example, it saves particularly detailed history during a presentation. The generation AI also dynamically adjusts the standard for saving the voice quality history based on the progress of the meeting. For example, it increases the frequency of saving history when an important topic is being discussed. This makes it possible to dynamically change the standard for saving the voice quality history depending on the progress of the meeting.

[0102] When managing audio quality history, the audio quality check unit simultaneously manages video quality history, enabling comprehensive management of audio and video quality. For example, the audio quality check unit allows the generation AI to simultaneously analyze audio and video data and save a history for comprehensive management of both qualities. For example, if the audio is choppy, the video frame rate is also recorded. In addition, the generation AI records the video resolution and frame rate at the same time as noise reduction and echo cancellation to comprehensively manage audio and video quality. The generation AI also sets standards for comprehensive management of audio and video quality and saves the history in real time. For example, if audio quality deteriorates, the video quality is also recorded at the same time. This makes it possible to save a history for comprehensive management of audio and video quality.

[0103] When managing the voice quality history, the voice quality check unit can monitor the network connection status of participants in real time and adjust the history storage criteria according to the connection status. In the voice quality check unit, for example, the generation AI monitors the network connection status of participants in real time and adjusts the voice quality history storage criteria according to the connection status. For example, if the connection is unstable, the storage criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, a high-quality voice history is stored. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency at which the voice quality history is stored. For example, if the connection is unstable, the storage frequency is increased. This makes it possible to adjust the voice quality history storage criteria according to the network connection status.

[0104] When managing the voice quality history, the voice quality check unit can estimate the participant's emotions and relax the history storage standards if the emotions are positive. In the voice quality check unit, for example, the generation AI analyzes the participant's emotions in real time and relaxes the voice quality history storage standards if the emotions are positive. For example, the storage standards are relaxed if the emotions are excited. In addition, the generation AI adjusts the strength of noise reduction and echo cancellation if the emotions are positive. For example, the voice quality history storage standards are relaxed if the emotions are excited. In addition, the generation AI dynamically adjusts the frequency of voice quality history storage based on the participant's emotions. For example, the storage frequency is relaxed if the emotions are positive. This makes it possible to relax the voice quality history storage standards if the emotions are positive.

[0105] When providing customized voice quality settings, the voice quality check unit can analyze the importance of the speech content and prioritize the application of customized settings to important speech. In the voice quality check unit, for example, the generation AI analyzes speech content during a meeting in real time and identifies important speech. For example, the generation AI prioritizes the application of customized settings to speech during a presentation or speech that is the key point of a discussion. The generation AI also strengthens customized noise reduction and echo cancellation settings for speech with high importance. For example, it provides particularly high-quality audio for speech from the presenter. The generation AI also dynamically adjusts the criteria for customized settings based on the importance of the speech content. For example, if there are many important speeches, the frequency of customized settings is increased. This makes it possible to prioritize the application of customized voice quality settings to important speech.

[0106] When providing customized voice quality settings, the voice quality check unit can estimate the emotion of the speech and prioritize applying customized settings to speech with strong emotions. In the voice quality check unit, for example, the generation AI analyzes the emotion of the speech in real time and identifies speech with strong emotions. For example, the voice quality check unit prioritizes applying customized settings to speech with strong emotions, such as anger or joy. The generation AI also strengthens customized noise reduction and echo cancellation settings for speech with strong emotions. For example, it provides particularly high-quality voice for speech with strong emotions. The generation AI also dynamically adjusts the criteria for customized settings based on the emotion of the speech. For example, if there are many speeches with strong emotions, it increases the frequency of customized settings. This makes it possible to prioritize applying customized voice quality settings to speech with strong emotions.

[0107] When providing customized voice quality settings, the voice quality check unit can dynamically change the criteria for the customization settings according to the progress of the meeting. In the voice quality check unit, for example, the generation AI analyzes the progress of the meeting in real time and changes the criteria for the customization settings according to the situation, such as during a presentation or discussion. The generation AI also adjusts the customized settings for noise reduction and echo cancellation according to the progress of the meeting. For example, it provides particularly high-quality voice during presentations. The generation AI also dynamically adjusts the criteria for the customization settings based on the progress of the meeting. For example, if an important topic is being discussed, it increases the frequency of the customization settings. This makes it possible to dynamically change the criteria for the customized voice quality settings according to the progress of the meeting.

[0108] When providing customization settings for audio quality, the audio quality check unit simultaneously provides customization settings for video quality, allowing for comprehensive customization of audio and video quality. In the audio quality check unit, for example, the generation AI simultaneously analyzes audio and video data and provides settings for comprehensive customization of both quality. For example, if the audio is choppy, the generation AI also adjusts the video frame rate. To comprehensively customize audio and video quality, the generation AI also adjusts the video resolution and frame rate at the same time as noise reduction and echo cancellation. The generation AI also sets standards for comprehensive customization of audio and video quality and provides customization settings in real time. For example, if audio quality deteriorates, the video quality is also customized at the same time. This makes it possible to provide settings for comprehensive customization of audio and video quality.

[0109] When providing customized voice quality settings, the voice quality check unit can monitor the network connection status of the participant in real time and adjust the criteria for the customized voice quality settings according to the connection status. In the voice quality check unit, for example, the generation AI monitors the network connection status of the participant in real time and adjusts the criteria for the customized voice quality settings according to the connection status. For example, if the connection is unstable, the setting criteria are relaxed. The generation AI also adjusts the strength of noise reduction and echo cancellation based on the network connection status. For example, if the connection is stable, high-quality voice is provided. The generation AI also analyzes the network connection status in real time and dynamically adjusts the frequency of the customized voice quality settings. For example, if the connection is unstable, the setting frequency is increased. This makes it possible to adjust the criteria for the customized voice quality settings according to the network connection status.

[0110] When providing customization settings for voice quality, the voice quality check unit can estimate the emotions of the participant and relax the standards for the customization settings if the emotions are positive. In the voice quality check unit, for example, the generation AI analyzes the emotions of the participant in real time and relaxes the standards for the customization settings for voice quality if the emotions are positive. For example, the setting standards are relaxed if the emotions are excited. Furthermore, the generation AI adjusts the strength of noise reduction and echo cancellation if the emotions are positive. For example, the standards for the customization settings for voice quality are relaxed if the emotions are excited. Furthermore, the generation AI dynamically adjusts the frequency of the customization settings for voice quality based on the emotions of the participant. For example, the setting frequency is relaxed if the emotions are positive. This makes it possible to relax the standards for the customization settings for voice quality if the emotions are positive.

[0111] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0112] The remote conference system can further include a progress analyzer that analyzes the progress of the conference in real time. The progress analyzer can dynamically adjust the standards for checking and correcting audio quality according to the progress of the conference. For example, it can provide particularly high-quality audio during presentations and strengthen correction to prevent audio interruptions during discussions. The progress analyzer can also dynamically adjust the frequency of checking and correcting audio quality based on the progress of the conference. This makes it possible to provide optimal audio quality according to the progress of the conference.

[0113] The remote conference system may further include a connection monitoring unit that monitors the network connection status of participants in real time. The connection monitoring unit can dynamically adjust the audio quality check and correction standards according to the network connection status of participants. For example, the check standards can be relaxed when the connection is unstable, and high-quality audio can be provided when the connection is stable. The connection monitoring unit can also adjust the strength of noise reduction and echo cancellation based on the network connection status. This makes it possible to provide optimal audio quality according to the network connection status.

[0114] The remote conferencing system can also estimate the emotions of participants and prioritize improving the voice quality for emotionally charged speech. For example, it can strengthen noise reduction and echo cancellation for emotionally charged speech such as anger or joy. It can also dynamically adjust the voice quality check and correction criteria for emotionally charged speech. This makes it possible to provide particularly high-quality voice for emotionally charged speech.

[0115] The remote conferencing system can also analyze audio and video data simultaneously to comprehensively evaluate the quality of both. For example, if the audio is choppy, it can also check the video frame rate and set a standard for comprehensively evaluating the audio and video quality. Furthermore, to comprehensively evaluate the audio and video quality, it can adjust the video resolution and frame rate at the same time as noise reduction and echo cancellation. This makes it possible to comprehensively evaluate the audio and video quality.

[0116] The remote conferencing system can further estimate the emotions of participants and relax the voice quality check criteria when the emotion is positive. For example, the check criteria can be relaxed when the emotion is high, and the strength of noise reduction and echo cancellation can be adjusted when the emotion is positive. Also, the frequency of voice quality checks can be relaxed when the emotion is positive. This makes it possible to relax the voice quality check criteria when the emotion is positive.

[0117] The remote conference system can also dynamically change the standard for correcting audio quality according to the progress of the conference. For example, it can provide particularly high-quality audio during presentations and strengthen correction to prevent audio interruptions during discussions. It can also dynamically adjust the frequency of audio quality correction based on the progress of the conference. This makes it possible to provide optimal audio quality according to the progress of the conference.

[0118] The remote conferencing system can also estimate the emotions of participants and prioritize voice quality correction for emotionally charged speech. For example, it can strengthen noise reduction and echo cancellation for emotionally charged speech such as anger or joy. It can also dynamically adjust voice quality correction standards for emotionally charged speech. This makes it possible to provide particularly high-quality voice for emotionally charged speech.

[0119] The remote conferencing system also notifies users of the audio quality evaluation score at the same time as notifying them of the video quality evaluation score, allowing for a comprehensive evaluation of audio and video quality. For example, if the audio is choppy, the system can also check the video frame rate and set standards for comprehensively evaluating audio and video quality. Furthermore, to comprehensively evaluate audio and video quality, the system can adjust the video resolution and frame rate at the same time as noise reduction and echo cancellation. This makes it possible to comprehensively evaluate audio and video quality.

[0120] The remote conference system can further estimate the emotions of participants and prioritize the notification of speech quality evaluation scores for emotionally charged utterances. For example, speech quality evaluation scores can be emphasized for emotionally charged utterances such as anger or joy. Furthermore, the notification criteria for speech quality evaluation scores can be dynamically adjusted for emotionally charged utterances. This makes it possible to provide particularly high-quality speech evaluation scores for emotionally charged utterances.

[0121] The remote conferencing system can also monitor participants' network connection status in real time and adjust the notification criteria for the voice quality evaluation score according to the connection status. For example, it can relax the notification criteria if the connection is unstable and provide a high-quality voice evaluation score if the connection is stable. It can also adjust the strength of noise reduction and echo cancellation based on the network connection status. This makes it possible to provide an optimal voice quality evaluation score according to the network connection status.

[0122] The processing flow of the second embodiment will be briefly explained below.

[0123] Step 1: The voice quality checker checks voice quality in real time. For example, the generation AI receives voice data as input and analyzes factors that affect voice quality, such as noise, echo, and uneven volume. The generation AI also detects problems such as choppy voice or excessive background noise. The generation AI outputs a voice quality evaluation score and a list of problems. Step 2: The audio correction unit automatically corrects the audio if it determines that the audio quality is poor. For example, the generation AI corrects the audio using techniques such as noise reduction, echo cancellation, and automatic volume adjustment. The generation AI also performs processes such as removing background noise and filling in gaps in the audio.

[0124] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0125] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0144] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0158] 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.

[0159] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0164] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0165] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0171] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0172] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0174] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0175] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0176] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0177] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0178] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0179] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0180] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0181] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0182] 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.

[0183] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0184] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0185] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0186] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0187] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0188] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0189] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0190] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A voice quality check unit that checks voice quality in real time; an audio correction unit that automatically corrects the audio when the audio quality check unit determines that the audio quality is poor; A system characterized by:

2. The voice quality check unit Analyzing the audio data to analyze at least one of noise, echo, and volume non-uniformity as a factor affecting audio quality 2. The system of claim 1.

3. The audio correction unit Enhance the audio using at least one of the following technologies: noise reduction, echo cancellation, and automatic volume adjustment.

2. The system of claim 1.

4. The voice quality check unit generating an evaluation score or a list of issues with the voice quality and notifying the participants; 2. The system of claim 1.

5. The voice quality check unit The evaluation score or the list of problems of the voice quality is stored in a database and managed as a history.

2. The system of claim 1.

Images