system

Abstract

We provide the system. [Solution] A speech recognition means for identifying the statements of multiple participants in a meeting, Monitoring means for monitoring the frequency and duration of speech identified by the speech recognition means, A means of adjusting speaking opportunities among participants based on the monitoring results of speaking frequency and duration, A feedback mechanism that provides feedback after the meeting based on the results of the monitoring mechanism, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a hybrid meeting where in-person participants and remote participants are mixed, there is a problem that remote participants have difficulty obtaining speaking opportunities. Also, the inequality of speaking opportunities reduces the efficiency of the meeting and becomes a factor hindering constructive discussions. Against this background, there is a need for a method to smoothly adjust the frequency and timing of speaking and provide a place where all participants can speak equally.

Means for Solving the Problems

[0005] This invention proposes a system that uses speech recognition means to identify the voices of multiple participants in a meeting and monitors the frequency and duration of each participant's speech. Based on the obtained monitoring data, this system adjusts the speaking opportunities among participants and corrects imbalances. Furthermore, it provides feedback to participants after the meeting based on the monitoring results, indicating areas for improvement for the next meeting. In particular, by including notification means to encourage remote participants to speak and priority resetting means to reset the priority of speaking, the system achieves equalization of speaking opportunities.

[0006] "Speech recognition means" refers to technology that converts participants' speech from audio data into text data and identifies who made the statement.

[0007] "Monitoring measures" refer to a function for recording and analyzing the speaking time and frequency of each participant during a meeting.

[0008] "Adjustment means" refers to a device or program that controls the distribution of speaking opportunities among participants to an equal degree, based on data obtained by monitoring means.

[0009] A "feedback mechanism" is a function that, after a meeting, provides participants with the data they entered based on the monitoring results, either visually or numerically, and indicates areas for improvement for future meetings.

[0010] "Notification methods" refer to technologies used to inform remote participants when it is time to speak and to send information to encourage them to participate.

[0011] The "priority resetting mechanism" is a function that adjusts the order and timing of participants' speeches in real time to ensure equal opportunities for them to speak. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, a communication I / F (Interface) with a reference number is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system for maximizing the efficiency of hybrid meetings with a mix of in-person and remote participants. This system uses AI technology to appropriately control and adjust participant participation, thereby providing all participants with equal opportunities to speak.

[0034] The server collects audio data from all participants during the meeting in real time and uses speech recognition technology to convert each participant's statements into text data. This allows for clear identification of the content of the statements and the speaker. Speech analysis is used to monitor and record the frequency and duration of statements.

[0035] The terminal acquires audio data locally and transmits it to the server. This ensures that remote participants can smoothly provide audio data. It also displays support information to ensure equal opportunities for participation and provides feedback to participants.

[0036] Users are prompted to speak when they receive notifications, and they can adjust the timing of their contributions. Notifications and feedback from the server serve as reference information for users to participate more efficiently in future meetings.

[0037] As a concrete example, during a meeting, the server analyzes the audio data and detects that remote participant A is speaking infrequently. In this case, the server sends a notification to participant A via their terminal prompting them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether everyone has had an equal opportunity to speak. After the meeting ends, the server generates feedback based on the accumulated speaking data and presents it to the participants. This enables efficient and fair hybrid meetings.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server collects audio data from all participants in real time as soon as the meeting starts. Each time audio input is made, the data is temporarily stored and prepared to be sent to the speech recognition process.

[0041] Step 2:

[0042] The device captures audio from the user's microphone and sends the stream data to the server. During this process, the audio data is encoded into a predetermined format and configured to minimize data latency.

[0043] Step 3:

[0044] The server uses speech recognition technology to convert audio data into text and identify the user who made the statement. This allows the server to track which participant spoke in real time and record the content of their speech.

[0045] Step 4:

[0046] The server uses analytical data to update the speaking status for each participant, monitoring the frequency and duration of each participant's contributions. This includes the start time, end time, and total duration of each contribution.

[0047] Step 5:

[0048] Based on monitoring results, the server executes adjustment logic when it detects an imbalance in opportunities to speak. For example, if a remote participant is not speaking, it prepares a notification to encourage them to speak.

[0049] Step 6:

[0050] The terminal receives instructions from the server and displays a notification to the user prompting them to speak. The notification is presented to the user visually or audibly, informing them of the appropriate time to speak.

[0051] Step 7:

[0052] The user receives a notification from their device, recognizes the need to speak, and speaks at the appropriate time. This spoken information is then sent back to the server via the device, and the monitoring data is updated.

[0053] Step 8:

[0054] At the end of the meeting, the server compiles all the accumulated speech data and generates feedback for each participant. The feedback includes information such as speaking time, frequency, and balance, and indicates areas for improvement for the next meeting.

[0055] Step 9:

[0056] The terminal displays feedback provided by the server to the user. Based on this feedback, the user can analyze how they participated and use that information to prepare for the next meeting.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In hybrid meetings, there is a challenge in ensuring that both in-person and remote participants have an equal opportunity to speak. Traditional systems have difficulty balancing the participation of all participants in audio collection and analysis, resulting in some participants' opinions not being adequately reflected in the overall meeting. Furthermore, remote participants, in particular, tend to miss opportunities to speak due to physical constraints. This leads to a situation where not all participants can effectively contribute to the conversation, resulting in a decline in the quality of the meeting.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes a data processing means for inputting participants' voices into an information processing device and identifying the content of their speech; an analysis means for accumulating the speech information obtained by the data processing means and detecting the frequency and duration of speeches; and an opportunity adjustment means for equalizing participation opportunities based on the detected speech information. This makes it possible for all participants to have a fair opportunity to speak, thereby improving the overall quality of the meeting.

[0062] An "information processing device" is a device that receives audio data and analyzes and processes the statements made by participants.

[0063] A "data processing means" is an element that has the function of converting audio information input by participants into text data and identifying the content of what was said.

[0064] "Analysis means" refers to a mechanism for detecting the frequency and timing of statements based on text data and for analyzing statement information.

[0065] An "opportunity adjustment mechanism" is a device or function that adjusts the frequency and timing of speeches to provide equal opportunities for participants to speak.

[0066] A "response generation means" is a function that generates notifications and feedback to encourage participants' actions.

[0067] "Communication means" is a term that refers to communication technologies and devices used to transmit information to participants.

[0068] The "order setting mechanism" is a function that dynamically restructures the priority of speeches in real time and adjusts opportunities for speaking within a meeting.

[0069] The hybrid meeting system in this invention can improve meeting efficiency by equalizing speaking opportunities in meetings with a mix of in-person and remote participants. This system is implemented through the following configuration and operation.

[0070] The server receives audio data from all participants in real time during the meeting and uses speech recognition technology to convert each participant's statements into text data. A typical cloud-based speech recognition service is likely to be used for this purpose. The converted text data is recorded in a database on the server and used to track the frequency and duration of speeches.

[0071] The terminal is responsible for acquiring audio data from remote participants' local environments and sending it to the server. The terminal is equipped with a function to display the feedback and information prompting participation to the participants. This makes it possible to quickly prompt the next action if an imbalance in speaking opportunities is detected.

[0072] Users receive notifications and feedback from their devices and adjust their speaking timing accordingly. If a user is notified that they have not spoken enough, they can make an effort to speak more to contribute to the meeting's agenda.

[0073] As a concrete example, suppose the server analyzes audio data during a meeting and determines that participant A is speaking less than other participants. In this case, the server sends a notification to participant A via their terminal to encourage them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether all participants had an equal opportunity to speak.

[0074] An example of a prompt would be, "How can an AI conferencing system improve the balance of participation?" Using this prompt, a generative AI model can make suggestions for equalizing speaking opportunities.

[0075] In this way, by ensuring equal opportunities for participation through the system, it is expected that all participants can contribute effectively to the meeting, thereby improving the quality and efficiency of the meeting.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server receives audio data from all participants at the start of the meeting. The input is an audio stream from microphones and communication applications. The server collects this audio data in real time and configures the network appropriately for high-speed and high-precision processing. The output is an aggregate of the audio data.

[0079] Step 2:

[0080] The server sends the received audio data to the speech recognition engine. The input is the audio data aggregated in step 1. The speech recognition engine converts the data into text data and identifies each utterance and speaker. The output is the identified text data.

[0081] Step 3:

[0082] The server analyzes text data and monitors the frequency and duration of each participant's speech. The input is the text data obtained in step 2. The server records this speech information in a database and analyzes the bias in speech patterns for each participant. The output is speech frequency and speech duration information for each participant.

[0083] Step 4:

[0084] The server generates notifications prompting remote participants to speak based on the analysis results. The input is the speech frequency and speech time information obtained in step 3. The output is the specific notification content for participants who need to adjust their participation.

[0085] Step 5:

[0086] The terminal displays notifications to remote participants and encourages them to speak. The input is the notification content sent from the server in step 4. The terminal displays the notification on the screen or alerts the user with an audio alert. The output is visual or auditory feedback to the participants.

[0087] Step 6:

[0088] The user receives a notification from their device and adjusts the timing of their speech. The input is the feedback provided in step 5. The user uses this feedback to deliver their speech. The output is new audio data sent to the server.

[0089] Step 7:

[0090] After the meeting ends, the server analyzes all the accumulated data and provides feedback to the participants. The input consists of the collected speech data and its analysis results. The server notifies participants of areas for improvement for the next meeting and trends in their behavior. The output is a feedback report.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In factory production environments, it is essential to properly coordinate communication between machines and workers to ensure a smooth workflow. However, currently, machines may not receive instructions accurately and completely, leading to decreased work efficiency. Furthermore, unequal opportunities for communication between machines and workers can result in wasted movements and misunderstandings, hindering productivity.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for monitoring the frequency and duration of voices identified by a voice recognition device, means for adjusting voice opportunities, and a feedback function that provides information based on the monitoring results. This facilitates smooth communication between the machine and the operator, enabling improved work efficiency and reduced misunderstandings.

[0096] A "speech recognition device" is a device that converts speech, such as conversations and instructions, into digital data to identify the speaker and the content of the speech.

[0097] The "monitoring function" is a function that tracks and analyzes the frequency and duration of voice data obtained by the voice recognition device.

[0098] The "adjustment function" is a function that uses data obtained from the monitoring function to distribute speaking opportunities equally among participants.

[0099] The "feedback function" is a feature that provides participants with information based on the analysis of audio data after a meeting or task is completed, to help them improve and increase efficiency.

[0100] "Production environment" refers to the physical and functional space where work is carried out in a manufacturing site such as a factory.

[0101] "Collaboration function" refers to a function that optimizes communication between machines and human workers in order to work together efficiently.

[0102] A "notification function" is a function that transmits necessary information and instructions to machines and workers at the appropriate time.

[0103] The "priority resetting function" is a feature that re-evaluates the importance of information needed for communication and work during operation and determines the appropriate processing order.

[0104] The system for implementing this invention optimizes voice communication between machines and workers in a factory production environment. The server uses a high-performance voice recognition device to collect voice data in real time during the production process and converts it into text using voice recognition technology. It utilizes open-source NLTK libraries and other tools to analyze the voice data and identify the content and frequency of each utterance.

[0105] The terminal acquires audio data through microphones and speakers installed within the factory and transmits it to the server in real time. This enables smooth communication between machines and workers and provides information to adjust the timing and content of communication.

[0106] Users, i.e., factory workers, can communicate more effectively with machines based on notifications from the server. For example, if a worker is giving too many instructions, the system will notify the worker that "the instructions have already been received," preventing unnecessary duplication of instructions. Conversely, if a machine lacks information, it will prompt the worker to provide the missing information.

[0107] As a concrete example, in a production line, if worker A instructs a machine to attach a part, but the voice recognition device determines the instruction is excessive, the server can notify worker A and advise them to refrain from giving unnecessary instructions. This allows the work to proceed efficiently without disrupting the production flow.

[0108] Examples of prompts for the generating AI model include, "Please tell me how to design a system that analyzes voice communication between machines and workers in a factory and achieves optimal communication."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server receives audio data from within the factory, transmitted from terminals. This input data is then converted into text using an open-source speech recognition library. The resulting text data serves as basic information for recording the content of each utterance.

[0112] Step 2:

[0113] The server analyzes the transcribed audio data and uses the NLTK library to identify the frequency and speaker of each utterance. Based on this analysis, it re-evaluates the importance and priority of each utterance and prepares data for adjustment.

[0114] Step 3:

[0115] Based on the analysis results, the server resets the priority of each message and makes adjustments to provide the machine with the necessary information at the appropriate time. The adjustment results are stored as notification data.

[0116] Step 4:

[0117] The terminal receives notification data from the server and transmits necessary instructions and information to the machine and worker via speaker. This process helps maintain a smooth workflow.

[0118] Step 5:

[0119] Based on the information provided by the terminal, the user confirms the work details and adjusts communication with the machine as needed. This helps maintain an efficient work environment.

[0120] Step 6:

[0121] The server generates feedback from the collected speech data after the work is completed, providing information to help improve future processes. This feedback serves as reference material for each worker and manager.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a system for streamlining meetings in both in-person and remote environments. In addition to an adjustment function that ensures equal speaking opportunities for all participants, it incorporates an emotion engine. This emotion engine allows for real-time analysis of each participant's emotional state, which can be used to facilitate the meeting.

[0124] The server analyzes the audio data collected during the meeting and uses speech recognition technology to transcribe the spoken content into text. Simultaneously, it uses an emotion engine to identify the speaker's emotional tone from the audio. This makes it possible to analyze and record the emotional state of each participant as they speak.

[0125] The terminal captures voice input from the user and sends it to the server. Terminals, especially those for remote participants, provide real-time feedback based on sentiment analysis results. This feedback is presented through visual cues and audio, allowing users to understand their own emotional state.

[0126] Users receive notifications powered by an emotion engine, which helps them adjust when and how they should speak. If the system determines that a user's emotional state is unbalanced, a notification encouraging relaxation is sent through the device. This feature allows users to express themselves more appropriately.

[0127] As a concrete example, consider a scenario where the server detects an increase in participant B's stress level based on their tone of voice during a meeting. In this case, the emotion engine analyzes the information and sends a notification to B's terminal suggesting a break. By allowing B to take an appropriate rest, stress levels are reduced, and the quality of the discussion improves. Thus, the introduction of the emotion engine makes it possible to conduct meetings in a way that maintains the emotional balance of all participants, not just by equalizing speaking opportunities.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server initiates the audio data collection process at the start of the meeting. It receives audio streams from all participants and prepares the data by sending it to the speech recognition module and emotion engine.

[0131] Step 2:

[0132] The device acquires audio data through the microphone when the user speaks and sends it to the server in real time. The data is compressed during transmission to ensure efficient transfer to the server.

[0133] Step 3:

[0134] The server uses a speech recognition module to convert the audio data into text and identify the speaker. Simultaneously, an emotion engine analyzes the emotional tone from the audio, determining and recording the emotional category, such as positive, negative, or neutral.

[0135] Step 4:

[0136] The server uses speech recognition and sentiment analysis results to monitor each participant's speaking frequency, duration, and emotional state. Based on this, it collects data to adjust the balance between speaking opportunities and emotions.

[0137] Step 5:

[0138] The server executes adjustment logic if it determines that opportunities to speak are unequal or if a particular emotional tone is repeated. If necessary, it prepares notifications to encourage remote participants to speak or to encourage relaxation.

[0139] Step 6:

[0140] The device receives instructions from the server and notifies the user of notifications to encourage them to speak or to take actions aimed at improving their emotions. Notifications are displayed in the form of pop-ups or voice messages.

[0141] Step 7:

[0142] Users can view emotion-based notifications from their devices and take necessary actions. For example, if prompted to relax, they can take a break as appropriate.

[0143] Step 8:

[0144] At the end of the meeting, the server compiles all monitoring data. It generates a feedback report on each participant's speaking frequency, duration, and emotional state, and provides each participant with suggestions for emotional improvement.

[0145] Step 9:

[0146] The device displays the generated feedback report to the user. The user can use this feedback to reflect on their participation and emotional management, and utilize it to prepare for future meetings.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] In meetings, imbalances in opportunities for participation and emotional well-being among participants often occur, which can impair the effectiveness and efficiency of the meeting. Furthermore, remote participants, in particular, may find it difficult to get opportunities to speak, leading to decreased motivation and incomplete information transmission. It is necessary to address these imbalances and improve the quality of meetings.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes voice analysis means for identifying speech, monitoring means for monitoring the frequency and duration of speech, and emotion engine means for identifying emotional states and providing feedback. This makes it possible to provide all participants with equal opportunities to speak while understanding the emotional states of participants in real time. This can streamline the progress of meetings and improve participants' willingness to communicate.

[0152] "Voice analysis means" refers to a technical means for identifying the statements of multiple participants in a meeting and converting the audio data into text.

[0153] "Monitoring means" refers to technical means that have the function of monitoring the frequency and duration of speech identified by the speech analysis means.

[0154] "Adjustment means" refers to technical means for adjusting opportunities for participants to speak based on the results of monitoring by monitoring means.

[0155] "Information provision means" refers to the means of providing feedback after a meeting has concluded, based on the results of monitoring.

[0156] An "emotion engine" is a technology that identifies the speaker's emotional state from audio data and provides real-time feedback based on that emotion.

[0157] "Notification means" refers to technical means for sending notifications to remote participants via communication devices to prompt them to speak.

[0158] A "priority setting means" is a technical means for automatically setting the priority of speeches based on data obtained by monitoring means, thereby providing equal opportunities for speaking.

[0159] To implement this invention, a system having the following components is required: a server and voice analysis means for collecting and analyzing the voice of each participant. This voice analysis means has the technology to convert voice data into text using a voice recognition engine and has high-precision natural language processing capabilities. Furthermore, the server is equipped with an emotion engine means to identify the emotional state of the participants from the voice data. This emotion engine identifies emotional tones using a voice analysis algorithm and generates appropriate feedback in real time.

[0160] The terminal is responsible for capturing voice input from the user and sending it to the server. To enable real-time transmission of voice data, the terminal uses a high-sensitivity microphone and noise-canceling technology. In particular, terminals for remote participants provide visual or audio feedback based on sentiment analysis results from the server.

[0161] On the other hand, users can receive feedback from their devices, understand their own emotional state, and adjust the timing and content of their statements. The feedback provided to users is designed to support effective communication by taking into account the emotional balance of the participants.

[0162] As a concrete example, consider a scenario where a server detects an increase in stress levels from a participant's voice tone during a meeting. The emotion engine immediately analyzes this information and sends a notification to the participant's device encouraging them to relax. As a result, the participant can expect to reduce their stress levels and improve the quality of the conversation.

[0163] An example of a prompt for a generative AI model is: "Describe a system that understands the emotional state of participants during a meeting and provides appropriate feedback. Please also mention specific features, benefits, and the hardware and software used."

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The terminal captures participants' voice input in real time. This is done using a high-sensitivity microphone and noise-canceling technology. The input voice data is processed to reduce ambient noise for clarity and immediately sent to the server. The output is processed voice data that is transferred to the server.

[0167] Step 2:

[0168] The server receives audio data sent from the terminal and converts it into text using a speech recognition engine. The input is audio data, which is converted into text data including technical terms and proper nouns using natural language processing technology. The output is the transcribed speech.

[0169] Step 3:

[0170] The server inputs the transcribed data and the original audio data into the emotion engine to identify the speaker's emotional tone. The input consists of the text of the speech and its vocal characteristics, which the speech analysis algorithm classifies into emotional categories such as joy or anger. The output is data indicating the emotional state.

[0171] Step 4:

[0172] The server generates appropriate feedback based on the emotional state and sends that information to the terminal. The input is the identified emotional state, and the corresponding feedback is generated as text or voice. The output is the feedback data sent to the terminal.

[0173] Step 5:

[0174] The device presents the user with feedback received from the server. The input is feedback data, provided to the user as visual indicators or audio. The device's actions include displaying information on the screen or playing audio notifications. The output is feedback that the user sees or hears.

[0175] Step 6:

[0176] The user adjusts their statements based on feedback from the device. The input is feedback information provided by the device, which the user uses to consider the timing and content of their next statement. The output is the user's speaking behavior. Specifically, the user uses the feedback to relax or to facilitate their speech.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0179] In brick-and-mortar stores, it can be difficult for employees to quickly and accurately grasp a customer's emotional state, potentially resulting in an unsatisfactory customer experience. Furthermore, a lack of information necessary for employees to provide personalized service to customers is a significant problem.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes a speech recognition means for identifying customer statements, an emotion analysis means for analyzing emotional states from transcribed statements and video, and a presentation means for providing real-time feedback based on the analyzed emotional state. This enables employees to grasp the customer's emotional state in real time and provide more appropriate and personalized responses.

[0182] "Speech recognition means" is a technology that receives audio data of a conversation as input and converts its content into text data.

[0183] "Monitoring means" refers to technology that measures the frequency and duration of speech content obtained by speech recognition means and evaluates the fairness of opportunities to speak.

[0184] "Adjustment means" refers to devices or software that have the function of adjusting opportunities for participants to speak based on information obtained from monitoring means.

[0185] A "feedback method" is a technique for analyzing data accumulated after a meeting and providing participants with suggestions for improvement and advice.

[0186] "Emotional analysis methods" are technologies that derive emotional tones from audio and video data and evaluate the emotional state of participants in real time.

[0187] "Presentation means" refers to devices or methods for conveying information to the user visually or audibly based on the analysis results.

[0188] "Notification methods" refer to technologies that send information to remote participants to encourage them to speak.

[0189] A "priority resetting mechanism" is a technology that re-evaluates the importance of each statement in real time and appropriately allocates speaking opportunities according to the situation.

[0190] The system used to implement this invention uses a wearable device, such as smart glasses, as its primary hardware. These smart glasses are equipped with a microphone and camera for capturing the customer's voice and video. They also include communication capabilities for real-time data processing via a connection to a cloud server.

[0191] The server uses speech recognition software (e.g., Google® Cloud Speech-to-Text) to convert audio data sent from smart glasses into text data. The text and video data are then analyzed for emotional tone and state using an emotion analysis API (e.g., Amazon Comprehend or Microsoft® Azure® Emotion API). The analysis results identify whether the customer is experiencing positive or negative emotions.

[0192] The device (smart glasses) provides specific feedback to the store staff based on analysis results received from the server. For example, if the customer shows interest, it displays a message encouraging further product introductions. Conversely, if the customer has lost interest, it suggests alternative customer service methods or recommendations.

[0193] As a concrete example, consider customer service in a cafe. If, while introducing a new product, the customer shows a negative tone based on information detected by smart glasses, the system will immediately send feedback to the staff such as, "Let's try introducing another popular product."

[0194] Using a generative AI model, an example of a prompt message is, "Please consider what to do if you detect a customer's expression of disinterest while introducing a new product." Providing real-time feedback in this way can improve the customer experience.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server receives audio data transmitted from smart glasses. The input is customer audio data captured by the smart glasses' microphone. This audio data is converted into text data using Google Cloud Speech-to-Text. The output is the transcribed speech.

[0198] Step 2:

[0199] The server passes the text data obtained in Step 1 to the emotion analysis API. The input consists of the transcribed speech and video data showing the customer's facial expressions sent from smart glasses. Amazon Comprehend or Microsoft Azure Emotion API analyzes the customer's emotional tone from the audio and video. The output is data showing the analyzed emotional state.

[0200] Step 3:

[0201] The server sends the emotional state data analyzed in step 2 to the smart glasses. The input is the emotional state data, which is the result of the analysis. The output is what is displayed on the smart glasses as visual or audible feedback information.

[0202] Step 4:

[0203] The device (smart glasses) prompts the store clerk to take appropriate action based on feedback from the server. The input is the feedback information that is output in step 3. Specifically, it suggests further product introductions or changes in topic depending on the customer's mood. The output is the specific suggestion content displayed on the visual display.

[0204] Step 5:

[0205] The user (store clerk) receives information displayed on smart glasses and develops a service that responds to the customer's emotions. The input is the suggested content displayed on the smart glasses. The action involves explaining products or trying different approaches while observing the customer's reaction. The output is an improved customer experience.

[0206] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0207] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0208] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0212] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0213] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0214] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0215] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0216] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0217] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0218] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0219] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0220] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0221] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0222] This invention is a system for maximizing the efficiency of hybrid meetings with a mix of in-person and remote participants. This system uses AI technology to appropriately control and adjust participant participation, thereby providing all participants with equal opportunities to speak.

[0223] The server collects audio data from all participants during the meeting in real time and uses speech recognition technology to convert each participant's statements into text data. This allows for clear identification of the content of the statements and the speaker. Speech analysis is used to monitor and record the frequency and duration of statements.

[0224] The terminal acquires audio data locally and transmits it to the server. This ensures that remote participants can smoothly provide audio data. It also displays support information to ensure equal opportunities for participation and provides feedback to participants.

[0225] Users are prompted to speak when they receive notifications, and they can adjust the timing of their contributions. Notifications and feedback from the server serve as reference information for users to participate more efficiently in future meetings.

[0226] As a concrete example, during a meeting, the server analyzes the audio data and detects that remote participant A is speaking infrequently. In this case, the server sends a notification to participant A via their terminal prompting them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether everyone has had an equal opportunity to speak. After the meeting ends, the server generates feedback based on the accumulated speaking data and presents it to the participants. This enables efficient and fair hybrid meetings.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The server collects audio data from all participants in real time as soon as the meeting starts. Each time audio input is made, the data is temporarily stored and prepared to be sent to the speech recognition process.

[0230] Step 2:

[0231] The device captures audio from the user's microphone and sends the stream data to the server. During this process, the audio data is encoded into a predetermined format and configured to minimize data latency.

[0232] Step 3:

[0233] The server uses speech recognition technology to convert audio data into text and identify the user who made the statement. This allows the server to track which participant spoke in real time and record the content of their speech.

[0234] Step 4:

[0235] The server uses analytical data to update the speaking status for each participant, monitoring the frequency and duration of each participant's contributions. This includes the start time, end time, and total duration of each contribution.

[0236] Step 5:

[0237] Based on monitoring results, the server executes adjustment logic when it detects an imbalance in opportunities to speak. For example, if a remote participant is not speaking, it prepares a notification to encourage them to speak.

[0238] Step 6:

[0239] The terminal receives instructions from the server and displays a notification to the user prompting them to speak. The notification is presented to the user visually or audibly, informing them of the appropriate time to speak.

[0240] Step 7:

[0241] The user receives a notification from their device, recognizes the need to speak, and speaks at the appropriate time. This spoken information is then sent back to the server via the device, and the monitoring data is updated.

[0242] Step 8:

[0243] At the end of the meeting, the server compiles all the accumulated speech data and generates feedback for each participant. The feedback includes information such as speaking time, frequency, and balance, and indicates areas for improvement for the next meeting.

[0244] Step 9:

[0245] The terminal displays feedback provided by the server to the user. Based on this feedback, the user can analyze how they participated and use that information to prepare for the next meeting.

[0246] (Example 1)

[0247] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0248] In hybrid meetings, there is a challenge in ensuring that both in-person and remote participants have an equal opportunity to speak. Traditional systems have difficulty balancing the participation of all participants in audio collection and analysis, resulting in some participants' opinions not being adequately reflected in the overall meeting. Furthermore, remote participants, in particular, tend to miss opportunities to speak due to physical constraints. This leads to a situation where not all participants can effectively contribute to the conversation, resulting in a decline in the quality of the meeting.

[0249] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0250] In this invention, the server includes a data processing means for inputting participants' voices into an information processing device and identifying the content of their speech; an analysis means for accumulating the speech information obtained by the data processing means and detecting the frequency and duration of speeches; and an opportunity adjustment means for equalizing participation opportunities based on the detected speech information. This makes it possible for all participants to have a fair opportunity to speak, thereby improving the overall quality of the meeting.

[0251] An "information processing device" is a device that receives audio data and analyzes and processes the statements made by participants.

[0252] A "data processing means" is an element that has the function of converting audio information input by participants into text data and identifying the content of what was said.

[0253] "Analysis means" refers to a mechanism for detecting the frequency and timing of statements based on text data and for analyzing statement information.

[0254] An "opportunity adjustment mechanism" is a device or function that adjusts the frequency and timing of speeches to provide equal opportunities for participants to speak.

[0255] A "response generation means" is a function that generates notifications and feedback to encourage participants' actions.

[0256] "Communication means" is a term that refers to communication technologies and devices used to transmit information to participants.

[0257] The "order setting mechanism" is a function that dynamically restructures the priority of speeches in real time and adjusts opportunities for speaking within a meeting.

[0258] The hybrid meeting system in this invention can improve meeting efficiency by equalizing speaking opportunities in meetings with a mix of in-person and remote participants. This system is implemented through the following configuration and operation.

[0259] The server receives audio data from all participants in real time during the meeting and uses speech recognition technology to convert each participant's statements into text data. A typical cloud-based speech recognition service is likely to be used for this purpose. The converted text data is recorded in a database on the server and used to track the frequency and duration of speeches.

[0260] The terminal is responsible for acquiring audio data from remote participants' local environments and sending it to the server. The terminal is equipped with a function to display the feedback and information prompting participation to the participants. This makes it possible to quickly prompt the next action if an imbalance in speaking opportunities is detected.

[0261] Users receive notifications and feedback from their devices and adjust their speaking timing accordingly. If a user is notified that they have not spoken enough, they can make an effort to speak more to contribute to the meeting's agenda.

[0262] As a concrete example, suppose the server analyzes audio data during a meeting and determines that participant A is speaking less than other participants. In this case, the server sends a notification to participant A via their terminal to encourage them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether all participants had an equal opportunity to speak.

[0263] An example of a prompt would be, "How can an AI conferencing system improve the balance of participation?" Using this prompt, a generative AI model can make suggestions for equalizing speaking opportunities.

[0264] In this way, by ensuring equal opportunities for participation through the system, it is expected that all participants can contribute effectively to the meeting, thereby improving the quality and efficiency of the meeting.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The server receives audio data from all participants at the start of the meeting. The input is an audio stream from microphones and communication applications. The server collects this audio data in real time and configures the network appropriately for high-speed and high-precision processing. The output is an aggregate of the audio data.

[0268] Step 2:

[0269] The server sends the received audio data to the speech recognition engine. The input is the audio data aggregated in step 1. The speech recognition engine converts the data into text data and identifies each utterance and speaker. The output is the identified text data.

[0270] Step 3:

[0271] The server analyzes text data and monitors the frequency and duration of each participant's speech. The input is the text data obtained in step 2. The server records this speech information in a database and analyzes the bias in speech patterns for each participant. The output is speech frequency and speech duration information for each participant.

[0272] Step 4:

[0273] The server generates notifications prompting remote participants to speak based on the analysis results. The input is the speech frequency and speech time information obtained in step 3. The output is the specific notification content for participants who need to adjust their participation.

[0274] Step 5:

[0275] The terminal displays notifications to remote participants and encourages them to speak. The input is the notification content sent from the server in step 4. The terminal displays the notification on the screen or alerts the user with an audio alert. The output is visual or auditory feedback to the participants.

[0276] Step 6:

[0277] The user receives a notification from their device and adjusts the timing of their speech. The input is the feedback provided in step 5. The user uses this feedback to deliver their speech. The output is new audio data sent to the server.

[0278] Step 7:

[0279] After the meeting, the server analyzes all the accumulated data and provides feedback to the participants. The input is the speech data collected so far and the analysis results thereof. The server notifies the improvements for the next meeting and the trends of the participants' behaviors. The output is a feedback report.

[0280] (Application Example 1)

[0281] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0282] In the production environment of a factory, it is required to appropriately adjust the communication between machines and workers and smoothly advance the work flow. However, currently, machines may not receive instructions accurately, and the work efficiency may decrease. Also, when the speaking opportunities between machines and workers are unequal, useless operations and misunderstandings occur, which are factors hindering productivity.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0284] In this invention, the server includes means for monitoring the frequency and time of the voice identified by the voice recognition device, means for adjusting the voice opportunity, and a feedback function for providing information based on the monitoring results. Thereby, the communication between machines and workers becomes smooth, and it is possible to improve work efficiency and reduce misunderstandings.

[0285] The "voice recognition device" is a device for converting voices such as conversations and instructions into digital data and identifying the speaker and the content.

[0286] The "monitoring function" is a function for tracking and analyzing the frequency and time of the voice data obtained by the voice recognition device.

[0287] The "adjusting function" is a function for equally distributing the speaking opportunities among the participants based on the data obtained by the monitoring function.

[0288] The "feedback function" is a feature that provides participants with information based on the analysis of audio data after a meeting or task is completed, to help them improve and increase efficiency.

[0289] "Production environment" refers to the physical and functional space where work is carried out in a manufacturing site such as a factory.

[0290] "Collaboration function" refers to a function that optimizes communication between machines and human workers in order to work together efficiently.

[0291] A "notification function" is a function that transmits necessary information and instructions to machines and workers at the appropriate time.

[0292] The "priority resetting function" is a feature that re-evaluates the importance of information needed for communication and work during operation and determines the appropriate processing order.

[0293] The system for implementing this invention optimizes voice communication between machines and workers in a factory production environment. The server uses a high-performance voice recognition device to collect voice data in real time during the production process and converts it into text using voice recognition technology. It utilizes open-source NLTK libraries and other tools to analyze the voice data and identify the content and frequency of each utterance.

[0294] The terminal acquires audio data through microphones and speakers installed within the factory and transmits it to the server in real time. This enables smooth communication between machines and workers and provides information to adjust the timing and content of communication.

[0295] Users, i.e., factory workers, can communicate more effectively with machines based on notifications from the server. For example, if a worker is giving too many instructions, the system will notify the worker that "the instructions have already been received," preventing unnecessary duplication of instructions. Conversely, if a machine lacks information, it will prompt the worker to provide the missing information.

[0296] As a concrete example, in a production line, if worker A instructs a machine to attach a part, but the voice recognition device determines the instruction is excessive, the server can notify worker A and advise them to refrain from giving unnecessary instructions. This allows the work to proceed efficiently without disrupting the production flow.

[0297] Examples of prompts for the generating AI model include, "Please tell me how to design a system that analyzes voice communication between machines and workers in a factory and achieves optimal communication."

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server receives audio data from within the factory, transmitted from terminals. This input data is then converted into text using an open-source speech recognition library. The resulting text data serves as basic information for recording the content of each utterance.

[0301] Step 2:

[0302] The server analyzes the transcribed audio data and uses the NLTK library to identify the frequency and speaker of each utterance. Based on this analysis, it re-evaluates the importance and priority of each utterance and prepares data for adjustment.

[0303] Step 3:

[0304] Based on the analysis results, the server re - sets the priority of each statement and makes adjustments to provide the necessary information to the machine at an appropriate timing. The adjustment results are stored as notification data.

[0305] Step 4:

[0306] The terminal receives the notification data from the server and transmits the necessary instructions and information to the machine and the operator through the speaker. This process maintains the smooth flow of work.

[0307] Step 5:

[0308] Based on the information provided by the terminal, the user checks the work content and adjusts the communication with the machine as needed. This can maintain an efficient working environment.

[0309] Step 6:

[0310] After the work is completed, the server generates feedback from the aggregated statement data and provides information for use in future improvements. The feedback serves as a reference for each operator and administrator.

[0311] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0312] The present invention is a system for improving the efficiency of meetings in face - to - face and remote environments. In addition to the adjustment function for equalizing the speaking opportunities of participants, it incorporates an emotion engine. This emotion engine can analyze the emotional state of each participant in real - time and be used to facilitate the progress of the meeting.

[0313] The server analyzes the audio data collected during the meeting and uses speech recognition technology to transcribe the spoken content into text. Simultaneously, it uses an emotion engine to identify the speaker's emotional tone from the audio. This makes it possible to analyze and record the emotional state of each participant as they speak.

[0314] The terminal captures voice input from the user and sends it to the server. Terminals, especially those for remote participants, provide real-time feedback based on sentiment analysis results. This feedback is presented through visual cues and audio, allowing users to understand their own emotional state.

[0315] Users receive notifications powered by an emotion engine, which helps them adjust when and how they should speak. If the system determines that a user's emotional state is unbalanced, a notification encouraging relaxation is sent through the device. This feature allows users to express themselves more appropriately.

[0316] As a concrete example, consider a scenario where the server detects an increase in participant B's stress level based on their tone of voice during a meeting. In this case, the emotion engine analyzes the information and sends a notification to B's terminal suggesting a break. By allowing B to take an appropriate rest, stress levels are reduced, and the quality of the discussion improves. Thus, the introduction of the emotion engine makes it possible to conduct meetings in a way that maintains the emotional balance of all participants, not just by equalizing speaking opportunities.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The server initiates the audio data collection process at the start of the meeting. It receives audio streams from all participants and prepares the data by sending it to the speech recognition module and emotion engine.

[0320] Step 2:

[0321] The device acquires audio data through the microphone when the user speaks and sends it to the server in real time. The data is compressed during transmission to ensure efficient transfer to the server.

[0322] Step 3:

[0323] The server uses a speech recognition module to convert the audio data into text and identify the speaker. Simultaneously, an emotion engine analyzes the emotional tone from the audio, determining and recording the emotional category, such as positive, negative, or neutral.

[0324] Step 4:

[0325] The server uses speech recognition and sentiment analysis results to monitor each participant's speaking frequency, duration, and emotional state. Based on this, it collects data to adjust the balance between speaking opportunities and emotions.

[0326] Step 5:

[0327] The server executes adjustment logic if it determines that opportunities to speak are unequal or if a particular emotional tone is repeated. If necessary, it prepares notifications to encourage remote participants to speak or to encourage relaxation.

[0328] Step 6:

[0329] The device receives instructions from the server and notifies the user of notifications to encourage them to speak or to take actions aimed at improving their emotions. Notifications are displayed in the form of pop-ups or voice messages.

[0330] Step 7:

[0331] Users can view emotion-based notifications from their devices and take necessary actions. For example, if prompted to relax, they can take a break as appropriate.

[0332] Step 8:

[0333] At the end of the meeting, the server compiles all monitoring data. It generates a feedback report on each participant's speaking frequency, duration, and emotional state, and provides each participant with suggestions for emotional improvement.

[0334] Step 9:

[0335] The device displays the generated feedback report to the user. The user can use this feedback to reflect on their participation and emotional management, and utilize it to prepare for future meetings.

[0336] (Example 2)

[0337] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0338] In meetings, imbalances in opportunities for participation and emotional well-being among participants often occur, which can impair the effectiveness and efficiency of the meeting. Furthermore, remote participants, in particular, may find it difficult to get opportunities to speak, leading to decreased motivation and incomplete information transmission. It is necessary to address these imbalances and improve the quality of meetings.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes voice analysis means for identifying speech, monitoring means for monitoring the frequency and duration of speech, and emotion engine means for identifying emotional states and providing feedback. This makes it possible to provide all participants with equal opportunities to speak while understanding the emotional states of participants in real time. This can streamline the progress of meetings and improve participants' willingness to communicate.

[0341] "Voice analysis means" refers to a technical means for identifying the statements of multiple participants in a meeting and converting the audio data into text.

[0342] "Monitoring means" refers to technical means that have the function of monitoring the frequency and duration of speech identified by the speech analysis means.

[0343] "Adjustment means" refers to technical means for adjusting opportunities for participants to speak based on the results of monitoring by monitoring means.

[0344] "Information provision means" refers to the means of providing feedback after a meeting has concluded, based on the results of monitoring.

[0345] An "emotion engine" is a technology that identifies the speaker's emotional state from audio data and provides real-time feedback based on that emotion.

[0346] "Notification means" refers to technical means for sending notifications to remote participants via communication devices to prompt them to speak.

[0347] A "priority setting means" is a technical means for automatically setting the priority of speeches based on data obtained by monitoring means, thereby providing equal opportunities for speaking.

[0348] To implement this invention, a system having the following components is required: a server and voice analysis means for collecting and analyzing the voice of each participant. This voice analysis means has the technology to convert voice data into text using a voice recognition engine and has high-precision natural language processing capabilities. Furthermore, the server is equipped with an emotion engine means to identify the emotional state of the participants from the voice data. This emotion engine identifies emotional tones using a voice analysis algorithm and generates appropriate feedback in real time.

[0349] The terminal is responsible for capturing voice input from the user and sending it to the server. To enable real-time transmission of voice data, the terminal uses a high-sensitivity microphone and noise-canceling technology. In particular, terminals for remote participants provide visual or audio feedback based on sentiment analysis results from the server.

[0350] On the other hand, users can receive feedback from their devices, understand their own emotional state, and adjust the timing and content of their statements. The feedback provided to users is designed to support effective communication by taking into account the emotional balance of the participants.

[0351] As a concrete example, consider a scenario where a server detects an increase in stress levels from a participant's voice tone during a meeting. The emotion engine immediately analyzes this information and sends a notification to the participant's device encouraging them to relax. As a result, the participant can expect to reduce their stress levels and improve the quality of the conversation.

[0352] An example of a prompt for a generative AI model is: "Describe a system that understands the emotional state of participants during a meeting and provides appropriate feedback. Please also mention specific features, benefits, and the hardware and software used."

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] The terminal captures participants' voice input in real time. This is done using a high-sensitivity microphone and noise-canceling technology. The input voice data is processed to reduce ambient noise for clarity and immediately sent to the server. The output is processed voice data that is transferred to the server.

[0356] Step 2:

[0357] The server receives audio data sent from the terminal and converts it into text using a speech recognition engine. The input is audio data, which is converted into text data including technical terms and proper nouns using natural language processing technology. The output is the transcribed speech.

[0358] Step 3:

[0359] The server inputs the transcribed data and the original audio data into the emotion engine to identify the speaker's emotional tone. The input consists of the text of the speech and its vocal characteristics, which the speech analysis algorithm classifies into emotional categories such as joy or anger. The output is data indicating the emotional state.

[0360] Step 4:

[0361] The server generates appropriate feedback based on the emotional state and sends that information to the terminal. The input is the identified emotional state, and the corresponding feedback is generated as text or voice. The output is the feedback data sent to the terminal.

[0362] Step 5:

[0363] The device presents the user with feedback received from the server. The input is feedback data, provided to the user as visual indicators or audio. The device's actions include displaying information on the screen or playing audio notifications. The output is feedback that the user sees or hears.

[0364] Step 6:

[0365] The user adjusts their statements based on feedback from the device. The input is feedback information provided by the device, which the user uses to consider the timing and content of their next statement. The output is the user's speaking behavior. Specifically, the user uses the feedback to relax or to facilitate their speech.

[0366] (Application Example 2)

[0367] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0368] In brick-and-mortar stores, it can be difficult for employees to quickly and accurately grasp a customer's emotional state, potentially resulting in an unsatisfactory customer experience. Furthermore, a lack of information necessary for employees to provide personalized service to customers is a significant problem.

[0369] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0370] In this invention, the server includes a speech recognition means for identifying customer statements, an emotion analysis means for analyzing emotional states from transcribed statements and video, and a presentation means for providing real-time feedback based on the analyzed emotional state. This enables employees to grasp the customer's emotional state in real time and provide more appropriate and personalized responses.

[0371] "Speech recognition means" is a technology that receives audio data of a conversation as input and converts its content into text data.

[0372] "Monitoring means" refers to technology that measures the frequency and duration of speech content obtained by speech recognition means and evaluates the fairness of opportunities to speak.

[0373] "Adjustment means" refers to devices or software that have the function of adjusting opportunities for participants to speak based on information obtained from monitoring means.

[0374] A "feedback method" is a technique for analyzing data accumulated after a meeting and providing participants with suggestions for improvement and advice.

[0375] "Emotional analysis methods" are technologies that derive emotional tones from audio and video data and evaluate the emotional state of participants in real time.

[0376] "Presentation means" refers to devices or methods for conveying information to the user visually or audibly based on the analysis results.

[0377] "Notification methods" refer to technologies that send information to remote participants to encourage them to speak.

[0378] A "priority resetting mechanism" is a technology that re-evaluates the importance of each statement in real time and appropriately allocates speaking opportunities according to the situation.

[0379] The system used to implement this invention uses a wearable device, such as smart glasses, as its primary hardware. These smart glasses are equipped with a microphone and camera for capturing the customer's voice and video. They also include communication capabilities for real-time data processing via a connection to a cloud server.

[0380] The server uses speech recognition software (e.g., Google Cloud Speech-to-Text) to convert audio data sent from smart glasses into text data. The text and video data are then analyzed for emotional tone and state using an emotion analysis API (e.g., Amazon Comprehend or Microsoft Azure Emotion API). The analysis results identify whether the customer is experiencing positive or negative emotions.

[0381] The device (smart glasses) provides specific feedback to the store staff based on analysis results received from the server. For example, if the customer shows interest, it displays a message encouraging further product introductions. Conversely, if the customer has lost interest, it suggests alternative customer service methods or recommendations.

[0382] As a concrete example, consider customer service in a cafe. If, while introducing a new product, the customer shows a negative tone based on information detected by smart glasses, the system will immediately send feedback to the staff such as, "Let's try introducing another popular product."

[0383] Using a generative AI model, an example of a prompt message is, "Please consider what to do if you detect a customer's expression of disinterest while introducing a new product." Providing real-time feedback in this way can improve the customer experience.

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server receives audio data transmitted from smart glasses. The input is customer audio data captured by the smart glasses' microphone. This audio data is converted into text data using Google Cloud Speech-to-Text. The output is the transcribed speech.

[0387] Step 2:

[0388] The server passes the text data obtained in Step 1 to the emotion analysis API. The input consists of the transcribed speech and video data showing the customer's facial expressions sent from smart glasses. Amazon Comprehend or Microsoft Azure Emotion API analyzes the customer's emotional tone from the audio and video. The output is data showing the analyzed emotional state.

[0389] Step 3:

[0390] The server sends the emotional state data analyzed in step 2 to the smart glasses. The input is the emotional state data, which is the result of the analysis. The output is what is displayed on the smart glasses as visual or audible feedback information.

[0391] Step 4:

[0392] The device (smart glasses) prompts the store clerk to take appropriate action based on feedback from the server. The input is the feedback information that is output in step 3. Specifically, it suggests further product introductions or changes in topic depending on the customer's mood. The output is the specific suggestion content displayed on the visual display.

[0393] Step 5:

[0394] The user (store clerk) receives information displayed on smart glasses and develops a service that responds to the customer's emotions. The input is the suggested content displayed on the smart glasses. The action involves explaining products or trying different approaches while observing the customer's reaction. The output is an improved customer experience.

[0395] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0396] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0397] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0401] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0402] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0403] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0404] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0405] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0406] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0407] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0408] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0409] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0410] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0411] This invention is a system for maximizing the efficiency of hybrid meetings with a mix of in-person and remote participants. This system uses AI technology to appropriately control and adjust participant participation, thereby providing all participants with equal opportunities to speak.

[0412] The server collects audio data from all participants during the meeting in real time and uses speech recognition technology to convert each participant's statements into text data. This allows for clear identification of the content of the statements and the speaker. Speech analysis is used to monitor and record the frequency and duration of statements.

[0413] The terminal acquires audio data locally and transmits it to the server. This ensures that remote participants can smoothly provide audio data. It also displays support information to ensure equal opportunities for participation and provides feedback to participants.

[0414] Users are prompted to speak when they receive notifications, and they can adjust the timing of their contributions. Notifications and feedback from the server serve as reference information for users to participate more efficiently in future meetings.

[0415] As a concrete example, during a meeting, the server analyzes the audio data and detects that remote participant A is speaking infrequently. In this case, the server sends a notification to participant A via their terminal prompting them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether everyone has had an equal opportunity to speak. After the meeting ends, the server generates feedback based on the accumulated speaking data and presents it to the participants. This enables efficient and fair hybrid meetings.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The server collects audio data from all participants in real time as soon as the meeting starts. Each time audio input is made, the data is temporarily stored and prepared to be sent to the speech recognition process.

[0419] Step 2:

[0420] The device captures audio from the user's microphone and sends the stream data to the server. During this process, the audio data is encoded into a predetermined format and configured to minimize data latency.

[0421] Step 3:

[0422] The server uses speech recognition technology to convert audio data into text and identify the user who made the statement. This allows the server to track which participant spoke in real time and record the content of their speech.

[0423] Step 4:

[0424] The server uses analytical data to update the speaking status for each participant, monitoring the frequency and duration of each participant's contributions. This includes the start time, end time, and total duration of each contribution.

[0425] Step 5:

[0426] Based on monitoring results, the server executes adjustment logic when it detects an imbalance in opportunities to speak. For example, if a remote participant is not speaking, it prepares a notification to encourage them to speak.

[0427] Step 6:

[0428] The terminal receives instructions from the server and displays a notification to the user prompting them to speak. The notification is presented to the user visually or audibly, informing them of the appropriate time to speak.

[0429] Step 7:

[0430] The user receives a notification from their device, recognizes the need to speak, and speaks at the appropriate time. This spoken information is then sent back to the server via the device, and the monitoring data is updated.

[0431] Step 8:

[0432] At the end of the meeting, the server compiles all the accumulated speech data and generates feedback for each participant. The feedback includes information such as speaking time, frequency, and balance, and indicates areas for improvement for the next meeting.

[0433] Step 9:

[0434] The terminal displays feedback provided by the server to the user. Based on this feedback, the user can analyze how they participated and use that information to prepare for the next meeting.

[0435] (Example 1)

[0436] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0437] In hybrid meetings, there is a challenge in ensuring that both in-person and remote participants have an equal opportunity to speak. Traditional systems have difficulty balancing the participation of all participants in audio collection and analysis, resulting in some participants' opinions not being adequately reflected in the overall meeting. Furthermore, remote participants, in particular, tend to miss opportunities to speak due to physical constraints. This leads to a situation where not all participants can effectively contribute to the conversation, resulting in a decline in the quality of the meeting.

[0438] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0439] In this invention, the server includes a data processing means for inputting participants' voices into an information processing device and identifying the content of their speech; an analysis means for accumulating the speech information obtained by the data processing means and detecting the frequency and duration of speeches; and an opportunity adjustment means for equalizing participation opportunities based on the detected speech information. This makes it possible for all participants to have a fair opportunity to speak, thereby improving the overall quality of the meeting.

[0440] An "information processing device" is a device that receives audio data and analyzes and processes the statements made by participants.

[0441] A "data processing means" is an element that has the function of converting audio information input by participants into text data and identifying the content of what was said.

[0442] "Analysis means" refers to a mechanism for detecting the frequency and timing of statements based on text data and for analyzing statement information.

[0443] An "opportunity adjustment mechanism" is a device or function that adjusts the frequency and timing of speeches to provide equal opportunities for participants to speak.

[0444] A "response generation means" is a function that generates notifications and feedback to encourage participants' actions.

[0445] "Communication means" is a term that refers to communication technologies and devices used to transmit information to participants.

[0446] The "order setting mechanism" is a function that dynamically restructures the priority of speeches in real time and adjusts opportunities for speaking within a meeting.

[0447] The hybrid meeting system in this invention can improve meeting efficiency by equalizing speaking opportunities in meetings with a mix of in-person and remote participants. This system is implemented through the following configuration and operation.

[0448] The server receives audio data from all participants in real time during the meeting and uses speech recognition technology to convert each participant's statements into text data. A typical cloud-based speech recognition service is likely to be used for this purpose. The converted text data is recorded in a database on the server and used to track the frequency and duration of speeches.

[0449] The terminal is responsible for acquiring audio data from remote participants' local environments and sending it to the server. The terminal is equipped with a function to display the feedback and information prompting participation to the participants. This makes it possible to quickly prompt the next action if an imbalance in speaking opportunities is detected.

[0450] Users receive notifications and feedback from their devices and adjust their speaking timing accordingly. If a user is notified that they have not spoken enough, they can make an effort to speak more to contribute to the meeting's agenda.

[0451] As a concrete example, suppose the server analyzes audio data during a meeting and determines that participant A is speaking less than other participants. In this case, the server sends a notification to participant A via their terminal to encourage them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether all participants had an equal opportunity to speak.

[0452] An example of a prompt would be, "How can an AI conferencing system improve the balance of participation?" Using this prompt, a generative AI model can make suggestions for equalizing speaking opportunities.

[0453] In this way, by ensuring equal opportunities for participation through the system, it is expected that all participants can contribute effectively to the meeting, thereby improving the quality and efficiency of the meeting.

[0454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0455] Step 1:

[0456] The server receives audio data from all participants at the start of the meeting. The input is an audio stream from microphones and communication applications. The server collects this audio data in real time and configures the network appropriately for high-speed and high-precision processing. The output is an aggregate of the audio data.

[0457] Step 2:

[0458] The server sends the received audio data to the speech recognition engine. The input is the audio data aggregated in step 1. The speech recognition engine converts the data into text data and identifies each utterance and speaker. The output is the identified text data.

[0459] Step 3:

[0460] The server analyzes text data and monitors the frequency and duration of each participant's speech. The input is the text data obtained in step 2. The server records this speech information in a database and analyzes the bias in speech patterns for each participant. The output is speech frequency and speech duration information for each participant.

[0461] Step 4:

[0462] The server generates notifications prompting remote participants to speak based on the analysis results. The input is the speech frequency and speech time information obtained in step 3. The output is the specific notification content for participants who need to adjust their participation.

[0463] Step 5:

[0464] The terminal displays notifications to remote participants and encourages them to speak. The input is the notification content sent from the server in step 4. The terminal displays the notification on the screen or alerts the user with an audio alert. The output is visual or auditory feedback to the participants.

[0465] Step 6:

[0466] The user receives a notification from their device and adjusts the timing of their speech. The input is the feedback provided in step 5. The user uses this feedback to deliver their speech. The output is new audio data sent to the server.

[0467] Step 7:

[0468] After the meeting ends, the server analyzes all the accumulated data and provides feedback to the participants. The input consists of the collected speech data and its analysis results. The server notifies participants of areas for improvement for the next meeting and trends in their behavior. The output is a feedback report.

[0469] (Application Example 1)

[0470] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0471] In factory production environments, it is essential to properly coordinate communication between machines and workers to ensure a smooth workflow. However, currently, machines may not receive instructions accurately and completely, leading to decreased work efficiency. Furthermore, unequal opportunities for communication between machines and workers can result in wasted movements and misunderstandings, hindering productivity.

[0472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0473] In this invention, the server includes means for monitoring the frequency and duration of voices identified by a voice recognition device, means for adjusting voice opportunities, and a feedback function that provides information based on the monitoring results. This facilitates smooth communication between the machine and the operator, enabling improved work efficiency and reduced misunderstandings.

[0474] A "speech recognition device" is a device that converts speech, such as conversations and instructions, into digital data to identify the speaker and the content of the speech.

[0475] The "monitoring function" is a function that tracks and analyzes the frequency and duration of voice data obtained by the voice recognition device.

[0476] The "adjustment function" is a function that uses data obtained from the monitoring function to distribute speaking opportunities equally among participants.

[0477] The "feedback function" is a feature that provides participants with information based on the analysis of audio data after a meeting or task is completed, to help them improve and increase efficiency.

[0478] "Production environment" refers to the physical and functional space where work is carried out in a manufacturing site such as a factory.

[0479] "Collaboration function" refers to a function that optimizes communication between machines and human workers in order to work together efficiently.

[0480] A "notification function" is a function that transmits necessary information and instructions to machines and workers at the appropriate time.

[0481] The "priority resetting function" is a feature that re-evaluates the importance of information needed for communication and work during operation and determines the appropriate processing order.

[0482] The system for implementing this invention optimizes voice communication between machines and workers in a factory production environment. The server uses a high-performance voice recognition device to collect voice data in real time during the production process and converts it into text using voice recognition technology. It utilizes open-source NLTK libraries and other tools to analyze the voice data and identify the content and frequency of each utterance.

[0483] The terminal acquires audio data through microphones and speakers installed within the factory and transmits it to the server in real time. This enables smooth communication between machines and workers and provides information to adjust the timing and content of communication.

[0484] Users, i.e., factory workers, can communicate more effectively with machines based on notifications from the server. For example, if a worker is giving too many instructions, the system will notify the worker that "the instructions have already been received," preventing unnecessary duplication of instructions. Conversely, if a machine lacks information, it will prompt the worker to provide the missing information.

[0485] As a concrete example, in a production line, if worker A instructs a machine to attach a part, but the voice recognition device determines the instruction is excessive, the server can notify worker A and advise them to refrain from giving unnecessary instructions. This allows the work to proceed efficiently without disrupting the production flow.

[0486] Examples of prompts for the generating AI model include, "Please tell me how to design a system that analyzes voice communication between machines and workers in a factory and achieves optimal communication."

[0487] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0488] Step 1:

[0489] The server receives audio data from within the factory, transmitted from terminals. This input data is then converted into text using an open-source speech recognition library. The resulting text data serves as basic information for recording the content of each utterance.

[0490] Step 2:

[0491] The server analyzes the transcribed audio data and uses the NLTK library to identify the frequency and speaker of each utterance. Based on this analysis, it re-evaluates the importance and priority of each utterance and prepares data for adjustment.

[0492] Step 3:

[0493] Based on the analysis results, the server resets the priority of each message and makes adjustments to provide the machine with the necessary information at the appropriate time. The adjustment results are stored as notification data.

[0494] Step 4:

[0495] The terminal receives notification data from the server and transmits necessary instructions and information to the machine and worker via speaker. This process helps maintain a smooth workflow.

[0496] Step 5:

[0497] Based on the information provided by the terminal, the user confirms the work details and adjusts communication with the machine as needed. This helps maintain an efficient work environment.

[0498] Step 6:

[0499] The server generates feedback from the collected speech data after the work is completed, providing information to help improve future processes. This feedback serves as reference material for each worker and manager.

[0500] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0501] This invention is a system for streamlining meetings in both in-person and remote environments. In addition to an adjustment function that ensures equal speaking opportunities for all participants, it incorporates an emotion engine. This emotion engine allows for real-time analysis of each participant's emotional state, which can be used to facilitate the meeting.

[0502] The server analyzes the audio data collected during the meeting and uses speech recognition technology to transcribe the spoken content into text. Simultaneously, it uses an emotion engine to identify the speaker's emotional tone from the audio. This makes it possible to analyze and record the emotional state of each participant as they speak.

[0503] The terminal captures voice input from the user and sends it to the server. Terminals, especially those for remote participants, provide real-time feedback based on sentiment analysis results. This feedback is presented through visual cues and audio, allowing users to understand their own emotional state.

[0504] Users receive notifications powered by an emotion engine, which helps them adjust when and how they should speak. If the system determines that a user's emotional state is unbalanced, a notification encouraging relaxation is sent through the device. This feature allows users to express themselves more appropriately.

[0505] As a concrete example, consider a scenario where the server detects an increase in participant B's stress level based on their tone of voice during a meeting. In this case, the emotion engine analyzes the information and sends a notification to B's terminal suggesting a break. By allowing B to take an appropriate rest, stress levels are reduced, and the quality of the discussion improves. Thus, the introduction of the emotion engine makes it possible to conduct meetings in a way that maintains the emotional balance of all participants, not just by equalizing speaking opportunities.

[0506] The following describes the processing flow.

[0507] Step 1:

[0508] The server initiates the audio data collection process at the start of the meeting. It receives audio streams from all participants and prepares the data by sending it to the speech recognition module and emotion engine.

[0509] Step 2:

[0510] The device acquires audio data through the microphone when the user speaks and sends it to the server in real time. The data is compressed during transmission to ensure efficient transfer to the server.

[0511] Step 3:

[0512] The server uses a speech recognition module to convert the audio data into text and identify the speaker. Simultaneously, an emotion engine analyzes the emotional tone from the audio, determining and recording the emotional category, such as positive, negative, or neutral.

[0513] Step 4:

[0514] The server uses speech recognition and sentiment analysis results to monitor each participant's speaking frequency, duration, and emotional state. Based on this, it collects data to adjust the balance between speaking opportunities and emotions.

[0515] Step 5:

[0516] The server executes adjustment logic if it determines that opportunities to speak are unequal or if a particular emotional tone is repeated. If necessary, it prepares notifications to encourage remote participants to speak or to encourage relaxation.

[0517] Step 6:

[0518] The device receives instructions from the server and notifies the user of notifications to encourage them to speak or to take actions aimed at improving their emotions. Notifications are displayed in the form of pop-ups or voice messages.

[0519] Step 7:

[0520] Users can view emotion-based notifications from their devices and take necessary actions. For example, if prompted to relax, they can take a break as appropriate.

[0521] Step 8:

[0522] At the end of the meeting, the server compiles all monitoring data. It generates a feedback report on each participant's speaking frequency, duration, and emotional state, and provides each participant with suggestions for emotional improvement.

[0523] Step 9:

[0524] The device displays the generated feedback report to the user. The user can use this feedback to reflect on their participation and emotional management, and utilize it to prepare for future meetings.

[0525] (Example 2)

[0526] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0527] In meetings, imbalances in opportunities for participation and emotional well-being among participants often occur, which can impair the effectiveness and efficiency of the meeting. Furthermore, remote participants, in particular, may find it difficult to get opportunities to speak, leading to decreased motivation and incomplete information transmission. It is necessary to address these imbalances and improve the quality of meetings.

[0528] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0529] In this invention, the server includes voice analysis means for identifying speech, monitoring means for monitoring the frequency and duration of speech, and emotion engine means for identifying emotional states and providing feedback. This makes it possible to provide all participants with equal opportunities to speak while understanding the emotional states of participants in real time. This can streamline the progress of meetings and improve participants' willingness to communicate.

[0530] "Voice analysis means" refers to a technical means for identifying the statements of multiple participants in a meeting and converting the audio data into text.

[0531] "Monitoring means" refers to technical means that have the function of monitoring the frequency and duration of speech identified by the speech analysis means.

[0532] "Adjustment means" refers to technical means for adjusting opportunities for participants to speak based on the results of monitoring by monitoring means.

[0533] "Information provision means" refers to the means of providing feedback after a meeting has concluded, based on the results of monitoring.

[0534] An "emotion engine" is a technology that identifies the speaker's emotional state from audio data and provides real-time feedback based on that emotion.

[0535] "Notification means" refers to technical means for sending notifications to remote participants via communication devices to prompt them to speak.

[0536] A "priority setting means" is a technical means for automatically setting the priority of speeches based on data obtained by monitoring means, thereby providing equal opportunities for speaking.

[0537] To implement this invention, a system having the following components is required: a server and voice analysis means for collecting and analyzing the voice of each participant. This voice analysis means has the technology to convert voice data into text using a voice recognition engine and has high-precision natural language processing capabilities. Furthermore, the server is equipped with an emotion engine means to identify the emotional state of the participants from the voice data. This emotion engine identifies emotional tones using a voice analysis algorithm and generates appropriate feedback in real time.

[0538] The terminal is responsible for capturing voice input from the user and sending it to the server. To enable real-time transmission of voice data, the terminal uses a high-sensitivity microphone and noise-canceling technology. In particular, terminals for remote participants provide visual or audio feedback based on sentiment analysis results from the server.

[0539] On the other hand, users can receive feedback from their devices, understand their own emotional state, and adjust the timing and content of their statements. The feedback provided to users is designed to support effective communication by taking into account the emotional balance of the participants.

[0540] As a concrete example, consider a scenario where a server detects an increase in stress levels from a participant's voice tone during a meeting. The emotion engine immediately analyzes this information and sends a notification to the participant's device encouraging them to relax. As a result, the participant can expect to reduce their stress levels and improve the quality of the conversation.

[0541] An example of a prompt for a generative AI model is: "Describe a system that understands the emotional state of participants during a meeting and provides appropriate feedback. Please also mention specific features, benefits, and the hardware and software used."

[0542] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0543] Step 1:

[0544] The terminal captures participants' voice input in real time. This is done using a high-sensitivity microphone and noise-canceling technology. The input voice data is processed to reduce ambient noise for clarity and immediately sent to the server. The output is processed voice data that is transferred to the server.

[0545] Step 2:

[0546] The server receives audio data sent from the terminal and converts it into text using a speech recognition engine. The input is audio data, which is converted into text data including technical terms and proper nouns using natural language processing technology. The output is the transcribed speech.

[0547] Step 3:

[0548] The server inputs the transcribed data and the original audio data into the emotion engine to identify the speaker's emotional tone. The input consists of the text of the speech and its vocal characteristics, which the speech analysis algorithm classifies into emotional categories such as joy or anger. The output is data indicating the emotional state.

[0549] Step 4:

[0550] The server generates appropriate feedback based on the emotional state and sends that information to the terminal. The input is the identified emotional state, and the corresponding feedback is generated as text or voice. The output is the feedback data sent to the terminal.

[0551] Step 5:

[0552] The device presents the user with feedback received from the server. The input is feedback data, provided to the user as visual indicators or audio. The device's actions include displaying information on the screen or playing audio notifications. The output is feedback that the user sees or hears.

[0553] Step 6:

[0554] The user adjusts their statements based on feedback from the device. The input is feedback information provided by the device, which the user uses to consider the timing and content of their next statement. The output is the user's speaking behavior. Specifically, the user uses the feedback to relax or to facilitate their speech.

[0555] (Application Example 2)

[0556] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0557] In brick-and-mortar stores, it can be difficult for employees to quickly and accurately grasp a customer's emotional state, potentially resulting in an unsatisfactory customer experience. Furthermore, a lack of information necessary for employees to provide personalized service to customers is a significant problem.

[0558] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0559] In this invention, the server includes a speech recognition means for identifying customer statements, an emotion analysis means for analyzing emotional states from transcribed statements and video, and a presentation means for providing real-time feedback based on the analyzed emotional state. This enables employees to grasp the customer's emotional state in real time and provide more appropriate and personalized responses.

[0560] "Speech recognition means" is a technology that receives audio data of a conversation as input and converts its content into text data.

[0561] "Monitoring means" refers to technology that measures the frequency and duration of speech content obtained by speech recognition means and evaluates the fairness of opportunities to speak.

[0562] "Adjustment means" refers to devices or software that have the function of adjusting opportunities for participants to speak based on information obtained from monitoring means.

[0563] A "feedback method" is a technique for analyzing data accumulated after a meeting and providing participants with suggestions for improvement and advice.

[0564] "Emotional analysis methods" are technologies that derive emotional tones from audio and video data and evaluate the emotional state of participants in real time.

[0565] "Presentation means" refers to devices or methods for conveying information to the user visually or audibly based on the analysis results.

[0566] "Notification methods" refer to technologies that send information to remote participants to encourage them to speak.

[0567] A "priority resetting mechanism" is a technology that re-evaluates the importance of each statement in real time and appropriately allocates speaking opportunities according to the situation.

[0568] The system used to implement this invention uses a wearable device, such as smart glasses, as its primary hardware. These smart glasses are equipped with a microphone and camera for capturing the customer's voice and video. They also include communication capabilities for real-time data processing via a connection to a cloud server.

[0569] The server uses speech recognition software (e.g., Google Cloud Speech-to-Text) to convert audio data sent from smart glasses into text data. The text and video data are then analyzed for emotional tone and state using an emotion analysis API (e.g., Amazon Comprehend or Microsoft Azure Emotion API). The analysis results identify whether the customer is experiencing positive or negative emotions.

[0570] The device (smart glasses) provides specific feedback to the store staff based on analysis results received from the server. For example, if the customer shows interest, it displays a message encouraging further product introductions. Conversely, if the customer has lost interest, it suggests alternative customer service methods or recommendations.

[0571] As a concrete example, consider customer service in a cafe. If, while introducing a new product, the customer shows a negative tone based on information detected by smart glasses, the system will immediately send feedback to the staff such as, "Let's try introducing another popular product."

[0572] Using a generative AI model, an example of a prompt message is, "Please consider what to do if you detect a customer's expression of disinterest while introducing a new product." Providing real-time feedback in this way can improve the customer experience.

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The server receives audio data transmitted from smart glasses. The input is customer audio data captured by the smart glasses' microphone. This audio data is converted into text data using Google Cloud Speech-to-Text. The output is the transcribed speech.

[0576] Step 2:

[0577] The server passes the text data obtained in Step 1 to the emotion analysis API. The input consists of the transcribed speech and video data showing the customer's facial expressions sent from smart glasses. Amazon Comprehend or Microsoft Azure Emotion API analyzes the customer's emotional tone from the audio and video. The output is data showing the analyzed emotional state.

[0578] Step 3:

[0579] The server sends the emotional state data analyzed in step 2 to the smart glasses. The input is the emotional state data, which is the result of the analysis. The output is what is displayed on the smart glasses as visual or audible feedback information.

[0580] Step 4:

[0581] The device (smart glasses) prompts the store clerk to take appropriate action based on feedback from the server. The input is the feedback information that is output in step 3. Specifically, it suggests further product introductions or changes in topic depending on the customer's mood. The output is the specific suggestion content displayed on the visual display.

[0582] Step 5:

[0583] The user (store clerk) receives information displayed on smart glasses and develops a service that responds to the customer's emotions. The input is the suggested content displayed on the smart glasses. The action involves explaining products or trying different approaches while observing the customer's reaction. The output is an improved customer experience.

[0584] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0585] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0586] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0587] [Fourth Embodiment]

[0588] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0589] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0590] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0591] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0592] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0593] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0594] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0595] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0596] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0597] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0598] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0599] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0600] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0601] This invention is a system for maximizing the efficiency of hybrid meetings with a mix of in-person and remote participants. This system uses AI technology to appropriately control and adjust participant participation, thereby providing all participants with equal opportunities to speak.

[0602] The server collects audio data from all participants during the meeting in real time and uses speech recognition technology to convert each participant's statements into text data. This allows for clear identification of the content of the statements and the speaker. Speech analysis is used to monitor and record the frequency and duration of statements.

[0603] The terminal acquires audio data locally and transmits it to the server. This ensures that remote participants can smoothly provide audio data. It also displays support information to ensure equal opportunities for participation and provides feedback to participants.

[0604] Users are prompted to speak when they receive notifications, and they can adjust the timing of their contributions. Notifications and feedback from the server serve as reference information for users to participate more efficiently in future meetings.

[0605] As a concrete example, during a meeting, the server analyzes the audio data and detects that remote participant A is speaking infrequently. In this case, the server sends a notification to participant A via their terminal prompting them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether everyone has had an equal opportunity to speak. After the meeting ends, the server generates feedback based on the accumulated speaking data and presents it to the participants. This enables efficient and fair hybrid meetings.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The server collects audio data from all participants in real time as soon as the meeting starts. Each time audio input is made, the data is temporarily stored and prepared to be sent to the speech recognition process.

[0609] Step 2:

[0610] The device captures audio from the user's microphone and sends the stream data to the server. During this process, the audio data is encoded into a predetermined format and configured to minimize data latency.

[0611] Step 3:

[0612] The server uses speech recognition technology to convert audio data into text and identify the user who made the statement. This allows the server to track which participant spoke in real time and record the content of their speech.

[0613] Step 4:

[0614] The server uses analytical data to update the speaking status for each participant, monitoring the frequency and duration of each participant's contributions. This includes the start time, end time, and total duration of each contribution.

[0615] Step 5:

[0616] Based on monitoring results, the server executes adjustment logic when it detects an imbalance in opportunities to speak. For example, if a remote participant is not speaking, it prepares a notification to encourage them to speak.

[0617] Step 6:

[0618] The terminal receives instructions from the server and displays a notification to the user prompting them to speak. The notification is presented to the user visually or audibly, informing them of the appropriate time to speak.

[0619] Step 7:

[0620] The user receives a notification from their device, recognizes the need to speak, and speaks at the appropriate time. This spoken information is then sent back to the server via the device, and the monitoring data is updated.

[0621] Step 8:

[0622] At the end of the meeting, the server compiles all the accumulated speech data and generates feedback for each participant. The feedback includes information such as speaking time, frequency, and balance, and indicates areas for improvement for the next meeting.

[0623] Step 9:

[0624] The terminal displays feedback provided by the server to the user. Based on this feedback, the user can analyze how they participated and use that information to prepare for the next meeting.

[0625] (Example 1)

[0626] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0627] In hybrid meetings, there is a challenge in ensuring that both in-person and remote participants have an equal opportunity to speak. Traditional systems have difficulty balancing the participation of all participants in audio collection and analysis, resulting in some participants' opinions not being adequately reflected in the overall meeting. Furthermore, remote participants, in particular, tend to miss opportunities to speak due to physical constraints. This leads to a situation where not all participants can effectively contribute to the conversation, resulting in a decline in the quality of the meeting.

[0628] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0629] In this invention, the server includes a data processing means for inputting participants' voices into an information processing device and identifying the content of their speech; an analysis means for accumulating the speech information obtained by the data processing means and detecting the frequency and duration of speeches; and an opportunity adjustment means for equalizing participation opportunities based on the detected speech information. This makes it possible for all participants to have a fair opportunity to speak, thereby improving the overall quality of the meeting.

[0630] An "information processing device" is a device that receives audio data and analyzes and processes the statements made by participants.

[0631] A "data processing means" is an element that has the function of converting audio information input by participants into text data and identifying the content of what was said.

[0632] "Analysis means" refers to a mechanism for detecting the frequency and timing of statements based on text data and for analyzing statement information.

[0633] An "opportunity adjustment mechanism" is a device or function that adjusts the frequency and timing of speeches to provide equal opportunities for participants to speak.

[0634] A "response generation means" is a function that generates notifications and feedback to encourage participants' actions.

[0635] "Communication means" is a term that refers to communication technologies and devices used to transmit information to participants.

[0636] The "order setting mechanism" is a function that dynamically restructures the priority of speeches in real time and adjusts opportunities for speaking within a meeting.

[0637] The hybrid meeting system in this invention can improve meeting efficiency by equalizing speaking opportunities in meetings with a mix of in-person and remote participants. This system is implemented through the following configuration and operation.

[0638] The server receives audio data from all participants in real time during the meeting and uses speech recognition technology to convert each participant's statements into text data. A typical cloud-based speech recognition service is likely to be used for this purpose. The converted text data is recorded in a database on the server and used to track the frequency and duration of speeches.

[0639] The terminal is responsible for acquiring audio data from remote participants' local environments and sending it to the server. The terminal is equipped with a function to display the feedback and information prompting participation to the participants. This makes it possible to quickly prompt the next action if an imbalance in speaking opportunities is detected.

[0640] Users receive notifications and feedback from their devices and adjust their speaking timing accordingly. If a user is notified that they have not spoken enough, they can make an effort to speak more to contribute to the meeting's agenda.

[0641] As a concrete example, suppose the server analyzes audio data during a meeting and determines that participant A is speaking less than other participants. In this case, the server sends a notification to participant A via their terminal to encourage them to speak. When participant A speaks, the audio data is sent back to the server, and it is evaluated whether all participants had an equal opportunity to speak.

[0642] An example of a prompt would be, "How can an AI conferencing system improve the balance of participation?" Using this prompt, a generative AI model can make suggestions for equalizing speaking opportunities.

[0643] In this way, by ensuring equal opportunities for participation through the system, it is expected that all participants can contribute effectively to the meeting, thereby improving the quality and efficiency of the meeting.

[0644] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0645] Step 1:

[0646] The server receives audio data from all participants at the start of the meeting. The input is an audio stream from microphones and communication applications. The server collects this audio data in real time and configures the network appropriately for high-speed and high-precision processing. The output is an aggregate of the audio data.

[0647] Step 2:

[0648] The server sends the received audio data to the speech recognition engine. The input is the audio data aggregated in step 1. The speech recognition engine converts the data into text data and identifies each utterance and speaker. The output is the identified text data.

[0649] Step 3:

[0650] The server analyzes text data and monitors the frequency and duration of each participant's speech. The input is the text data obtained in step 2. The server records this speech information in a database and analyzes the bias in speech patterns for each participant. The output is speech frequency and speech duration information for each participant.

[0651] Step 4:

[0652] The server generates notifications prompting remote participants to speak based on the analysis results. The input is the speech frequency and speech time information obtained in step 3. The output is the specific notification content for participants who need to adjust their participation.

[0653] Step 5:

[0654] The terminal displays notifications to remote participants and encourages them to speak. The input is the notification content sent from the server in step 4. The terminal displays the notification on the screen or alerts the user with an audio alert. The output is visual or auditory feedback to the participants.

[0655] Step 6:

[0656] The user receives a notification from their device and adjusts the timing of their speech. The input is the feedback provided in step 5. The user uses this feedback to deliver their speech. The output is new audio data sent to the server.

[0657] Step 7:

[0658] After the meeting ends, the server analyzes all the accumulated data and provides feedback to the participants. The input consists of the collected speech data and its analysis results. The server notifies participants of areas for improvement for the next meeting and trends in their behavior. The output is a feedback report.

[0659] (Application Example 1)

[0660] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0661] In factory production environments, it is essential to properly coordinate communication between machines and workers to ensure a smooth workflow. However, currently, machines may not receive instructions accurately and completely, leading to decreased work efficiency. Furthermore, unequal opportunities for communication between machines and workers can result in wasted movements and misunderstandings, hindering productivity.

[0662] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0663] In this invention, the server includes means for monitoring the frequency and duration of voices identified by a voice recognition device, means for adjusting voice opportunities, and a feedback function that provides information based on the monitoring results. This facilitates smooth communication between the machine and the operator, enabling improved work efficiency and reduced misunderstandings.

[0664] A "speech recognition device" is a device that converts speech, such as conversations and instructions, into digital data to identify the speaker and the content of the speech.

[0665] The "monitoring function" is a function that tracks and analyzes the frequency and duration of voice data obtained by the voice recognition device.

[0666] The "adjustment function" is a function that uses data obtained from the monitoring function to distribute speaking opportunities equally among participants.

[0667] The "feedback function" is a feature that provides participants with information based on the analysis of audio data after a meeting or task is completed, to help them improve and increase efficiency.

[0668] "Production environment" refers to the physical and functional space where work is carried out in a manufacturing site such as a factory.

[0669] "Collaboration function" refers to a function that optimizes communication between machines and human workers in order to work together efficiently.

[0670] A "notification function" is a function that transmits necessary information and instructions to machines and workers at the appropriate time.

[0671] The "priority resetting function" is a feature that re-evaluates the importance of information needed for communication and work during operation and determines the appropriate processing order.

[0672] The system for implementing this invention optimizes voice communication between machines and workers in a factory production environment. The server uses a high-performance voice recognition device to collect voice data in real time during the production process and converts it into text using voice recognition technology. It utilizes open-source NLTK libraries and other tools to analyze the voice data and identify the content and frequency of each utterance.

[0673] The terminal acquires audio data through microphones and speakers installed within the factory and transmits it to the server in real time. This enables smooth communication between machines and workers and provides information to adjust the timing and content of communication.

[0674] Users, i.e., factory workers, can communicate more effectively with machines based on notifications from the server. For example, if a worker is giving too many instructions, the system will notify the worker that "the instructions have already been received," preventing unnecessary duplication of instructions. Conversely, if a machine lacks information, it will prompt the worker to provide the missing information.

[0675] As a concrete example, in a production line, if worker A instructs a machine to attach a part, but the voice recognition device determines the instruction is excessive, the server can notify worker A and advise them to refrain from giving unnecessary instructions. This allows the work to proceed efficiently without disrupting the production flow.

[0676] Examples of prompts for the generating AI model include, "Please tell me how to design a system that analyzes voice communication between machines and workers in a factory and achieves optimal communication."

[0677] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0678] Step 1:

[0679] The server receives audio data from within the factory, transmitted from terminals. This input data is then converted into text using an open-source speech recognition library. The resulting text data serves as basic information for recording the content of each utterance.

[0680] Step 2:

[0681] The server analyzes the transcribed audio data and uses the NLTK library to identify the frequency and speaker of each utterance. Based on this analysis, it re-evaluates the importance and priority of each utterance and prepares data for adjustment.

[0682] Step 3:

[0683] Based on the analysis results, the server resets the priority of each message and makes adjustments to provide the machine with the necessary information at the appropriate time. The adjustment results are stored as notification data.

[0684] Step 4:

[0685] The terminal receives notification data from the server and transmits necessary instructions and information to the machine and worker via speaker. This process helps maintain a smooth workflow.

[0686] Step 5:

[0687] Based on the information provided by the terminal, the user confirms the work details and adjusts communication with the machine as needed. This helps maintain an efficient work environment.

[0688] Step 6:

[0689] The server generates feedback from the collected speech data after the work is completed, providing information to help improve future processes. This feedback serves as reference material for each worker and manager.

[0690] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0691] This invention is a system for streamlining meetings in both in-person and remote environments. In addition to an adjustment function that ensures equal speaking opportunities for all participants, it incorporates an emotion engine. This emotion engine allows for real-time analysis of each participant's emotional state, which can be used to facilitate the meeting.

[0692] The server analyzes the audio data collected during the meeting and uses speech recognition technology to transcribe the spoken content into text. Simultaneously, it uses an emotion engine to identify the speaker's emotional tone from the audio. This makes it possible to analyze and record the emotional state of each participant as they speak.

[0693] The terminal captures voice input from the user and sends it to the server. Terminals, especially those for remote participants, provide real-time feedback based on sentiment analysis results. This feedback is presented through visual cues and audio, allowing users to understand their own emotional state.

[0694] Users receive notifications powered by an emotion engine, which helps them adjust when and how they should speak. If the system determines that a user's emotional state is unbalanced, a notification encouraging relaxation is sent through the device. This feature allows users to express themselves more appropriately.

[0695] As a concrete example, consider a scenario where the server detects an increase in participant B's stress level based on their tone of voice during a meeting. In this case, the emotion engine analyzes the information and sends a notification to B's terminal suggesting a break. By allowing B to take an appropriate rest, stress levels are reduced, and the quality of the discussion improves. Thus, the introduction of the emotion engine makes it possible to conduct meetings in a way that maintains the emotional balance of all participants, not just by equalizing speaking opportunities.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] The server initiates the audio data collection process at the start of the meeting. It receives audio streams from all participants and prepares the data by sending it to the speech recognition module and emotion engine.

[0699] Step 2:

[0700] The device acquires audio data through the microphone when the user speaks and sends it to the server in real time. The data is compressed during transmission to ensure efficient transfer to the server.

[0701] Step 3:

[0702] The server uses a speech recognition module to convert the audio data into text and identify the speaker. Simultaneously, an emotion engine analyzes the emotional tone from the audio, determining and recording the emotional category, such as positive, negative, or neutral.

[0703] Step 4:

[0704] The server uses speech recognition and sentiment analysis results to monitor each participant's speaking frequency, duration, and emotional state. Based on this, it collects data to adjust the balance between speaking opportunities and emotions.

[0705] Step 5:

[0706] The server executes adjustment logic if it determines that opportunities to speak are unequal or if a particular emotional tone is repeated. If necessary, it prepares notifications to encourage remote participants to speak or to encourage relaxation.

[0707] Step 6:

[0708] The device receives instructions from the server and notifies the user of notifications to encourage them to speak or to take actions aimed at improving their emotions. Notifications are displayed in the form of pop-ups or voice messages.

[0709] Step 7:

[0710] Users can view emotion-based notifications from their devices and take necessary actions. For example, if prompted to relax, they can take a break as appropriate.

[0711] Step 8:

[0712] At the end of the meeting, the server compiles all monitoring data. It generates a feedback report on each participant's speaking frequency, duration, and emotional state, and provides each participant with suggestions for emotional improvement.

[0713] Step 9:

[0714] The device displays the generated feedback report to the user. The user can use this feedback to reflect on their participation and emotional management, and utilize it to prepare for future meetings.

[0715] (Example 2)

[0716] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0717] In meetings, imbalances in opportunities for participation and emotional well-being among participants often occur, which can impair the effectiveness and efficiency of the meeting. Furthermore, remote participants, in particular, may find it difficult to get opportunities to speak, leading to decreased motivation and incomplete information transmission. It is necessary to address these imbalances and improve the quality of meetings.

[0718] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0719] In this invention, the server includes voice analysis means for identifying speech, monitoring means for monitoring the frequency and duration of speech, and emotion engine means for identifying emotional states and providing feedback. This makes it possible to provide all participants with equal opportunities to speak while understanding the emotional states of participants in real time. This can streamline the progress of meetings and improve participants' willingness to communicate.

[0720] "Voice analysis means" refers to a technical means for identifying the statements of multiple participants in a meeting and converting the audio data into text.

[0721] "Monitoring means" refers to technical means that have the function of monitoring the frequency and duration of speech identified by the speech analysis means.

[0722] "Adjustment means" refers to technical means for adjusting opportunities for participants to speak based on the results of monitoring by monitoring means.

[0723] "Information provision means" refers to the means of providing feedback after a meeting has concluded, based on the results of monitoring.

[0724] An "emotion engine" is a technology that identifies the speaker's emotional state from audio data and provides real-time feedback based on that emotion.

[0725] "Notification means" refers to technical means for sending notifications to remote participants via communication devices to prompt them to speak.

[0726] A "priority setting means" is a technical means for automatically setting the priority of speeches based on data obtained by monitoring means, thereby providing equal opportunities for speaking.

[0727] To implement this invention, a system having the following components is required: a server and voice analysis means for collecting and analyzing the voice of each participant. This voice analysis means has the technology to convert voice data into text using a voice recognition engine and has high-precision natural language processing capabilities. Furthermore, the server is equipped with an emotion engine means to identify the emotional state of the participants from the voice data. This emotion engine identifies emotional tones using a voice analysis algorithm and generates appropriate feedback in real time.

[0728] The terminal is responsible for capturing voice input from the user and sending it to the server. To enable real-time transmission of voice data, the terminal uses a high-sensitivity microphone and noise-canceling technology. In particular, terminals for remote participants provide visual or audio feedback based on sentiment analysis results from the server.

[0729] On the other hand, users can receive feedback from their devices, understand their own emotional state, and adjust the timing and content of their statements. The feedback provided to users is designed to support effective communication by taking into account the emotional balance of the participants.

[0730] As a concrete example, consider a scenario where a server detects an increase in stress levels from a participant's voice tone during a meeting. The emotion engine immediately analyzes this information and sends a notification to the participant's device encouraging them to relax. As a result, the participant can expect to reduce their stress levels and improve the quality of the conversation.

[0731] An example of a prompt for a generative AI model is: "Describe a system that understands the emotional state of participants during a meeting and provides appropriate feedback. Please also mention specific features, benefits, and the hardware and software used."

[0732] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0733] Step 1:

[0734] The terminal captures participants' voice input in real time. This is done using a high-sensitivity microphone and noise-canceling technology. The input voice data is processed to reduce ambient noise for clarity and immediately sent to the server. The output is processed voice data that is transferred to the server.

[0735] Step 2:

[0736] The server receives audio data sent from the terminal and converts it into text using a speech recognition engine. The input is audio data, which is converted into text data including technical terms and proper nouns using natural language processing technology. The output is the transcribed speech.

[0737] Step 3:

[0738] The server inputs the transcribed data and the original audio data into the emotion engine to identify the speaker's emotional tone. The input consists of the text of the speech and its vocal characteristics, which the speech analysis algorithm classifies into emotional categories such as joy or anger. The output is data indicating the emotional state.

[0739] Step 4:

[0740] The server generates appropriate feedback based on the emotional state and sends that information to the terminal. The input is the identified emotional state, and the corresponding feedback is generated as text or voice. The output is the feedback data sent to the terminal.

[0741] Step 5:

[0742] The device presents the user with feedback received from the server. The input is feedback data, provided to the user as visual indicators or audio. The device's actions include displaying information on the screen or playing audio notifications. The output is feedback that the user sees or hears.

[0743] Step 6:

[0744] The user adjusts their statements based on feedback from the device. The input is feedback information provided by the device, which the user uses to consider the timing and content of their next statement. The output is the user's speaking behavior. Specifically, the user uses the feedback to relax or to facilitate their speech.

[0745] (Application Example 2)

[0746] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0747] In brick-and-mortar stores, it can be difficult for employees to quickly and accurately grasp a customer's emotional state, potentially resulting in an unsatisfactory customer experience. Furthermore, a lack of information necessary for employees to provide personalized service to customers is a significant problem.

[0748] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0749] In this invention, the server includes a speech recognition means for identifying customer statements, an emotion analysis means for analyzing emotional states from transcribed statements and video, and a presentation means for providing real-time feedback based on the analyzed emotional state. This enables employees to grasp the customer's emotional state in real time and provide more appropriate and personalized responses.

[0750] "Speech recognition means" is a technology that receives audio data of a conversation as input and converts its content into text data.

[0751] "Monitoring means" refers to technology that measures the frequency and duration of speech content obtained by speech recognition means and evaluates the fairness of opportunities to speak.

[0752] "Adjustment means" refers to devices or software that have the function of adjusting opportunities for participants to speak based on information obtained from monitoring means.

[0753] A "feedback method" is a technique for analyzing data accumulated after a meeting and providing participants with suggestions for improvement and advice.

[0754] "Emotional analysis methods" are technologies that derive emotional tones from audio and video data and evaluate the emotional state of participants in real time.

[0755] "Presentation means" refers to devices or methods for conveying information to the user visually or audibly based on the analysis results.

[0756] "Notification methods" refer to technologies that send information to remote participants to encourage them to speak.

[0757] A "priority resetting mechanism" is a technology that re-evaluates the importance of each statement in real time and appropriately allocates speaking opportunities according to the situation.

[0758] The system used to implement this invention uses a wearable device, such as smart glasses, as its primary hardware. These smart glasses are equipped with a microphone and camera for capturing the customer's voice and video. They also include communication capabilities for real-time data processing via a connection to a cloud server.

[0759] The server uses speech recognition software (e.g., Google Cloud Speech-to-Text) to convert audio data sent from smart glasses into text data. The text and video data are then analyzed for emotional tone and state using an emotion analysis API (e.g., Amazon Comprehend or Microsoft Azure Emotion API). The analysis results identify whether the customer is experiencing positive or negative emotions.

[0760] The device (smart glasses) provides specific feedback to the store staff based on analysis results received from the server. For example, if the customer shows interest, it displays a message encouraging further product introductions. Conversely, if the customer has lost interest, it suggests alternative customer service methods or recommendations.

[0761] As a concrete example, consider customer service in a cafe. If, while introducing a new product, the customer shows a negative tone based on information detected by smart glasses, the system will immediately send feedback to the staff such as, "Let's try introducing another popular product."

[0762] Using a generative AI model, an example of a prompt message is, "Please consider what to do if you detect a customer's expression of disinterest while introducing a new product." Providing real-time feedback in this way can improve the customer experience.

[0763] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0764] Step 1:

[0765] The server receives audio data transmitted from smart glasses. The input is customer audio data captured by the smart glasses' microphone. This audio data is converted into text data using Google Cloud Speech-to-Text. The output is the transcribed speech.

[0766] Step 2:

[0767] The server passes the text data obtained in Step 1 to the emotion analysis API. The input consists of the transcribed speech and video data showing the customer's facial expressions sent from smart glasses. Amazon Comprehend or Microsoft Azure Emotion API analyzes the customer's emotional tone from the audio and video. The output is data showing the analyzed emotional state.

[0768] Step 3:

[0769] The server sends the emotional state data analyzed in step 2 to the smart glasses. The input is the emotional state data, which is the result of the analysis. The output is what is displayed on the smart glasses as visual or audible feedback information.

[0770] Step 4:

[0771] The device (smart glasses) prompts the store clerk to take appropriate action based on feedback from the server. The input is the feedback information that is output in step 3. Specifically, it suggests further product introductions or changes in topic depending on the customer's mood. The output is the specific suggestion content displayed on the visual display.

[0772] Step 5:

[0773] The user (store clerk) receives information displayed on smart glasses and develops a service that responds to the customer's emotions. The input is the suggested content displayed on the smart glasses. The action involves explaining products or trying different approaches while observing the customer's reaction. The output is an improved customer experience.

[0774] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0775] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0776] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0777] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0778] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0779] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0780] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0781] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0782] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0783] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0784] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0785] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0786] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0787] 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.

[0788] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0789] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0790] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0791] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0792] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0793] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0794] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0795] The following is further disclosed regarding the embodiments described above.

[0796] (Claim 1)

[0797] A speech recognition means for identifying the statements of multiple participants in a meeting,

[0798] Monitoring means for monitoring the frequency and duration of speech identified by the speech recognition means,

[0799] A means of adjusting speaking opportunities among participants based on the monitoring results of speaking frequency and duration,

[0800] A feedback mechanism that provides feedback after the meeting based on the results of the monitoring mechanism,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the coordination means has a notification means for sending a notification to a remote participant prompting them to speak.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the monitoring means has a priority resetting means for resetting the priority of speeches in real time and providing equal opportunities for speech.

[0806] "Example 1"

[0807] (Claim 1)

[0808] A data processing means that inputs the voice of a participant into an information processing device and identifies the content of the speech,

[0809] The data processing means provides for storing the speech information obtained and for analyzing the frequency and duration of speeches,

[0810] Based on the detected statement information, an opportunity adjustment mechanism is provided to ensure equal opportunities for participation,

[0811] Based on the results of the opportunity adjustment means, the information presentation device includes a response generation means that encourages participants to improve their behavior,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The opportunity coordination means includes a communication means for encouraging remote participants to speak. The system according to claim 1.

[0815] (Claim 3)

[0816] The analysis means has a sequence setting means for dynamically reconstructing speaking priority and ensuring equal speaking opportunities. The system according to claim 1.

[0817] "Application Example 1"

[0818] (Claim 1)

[0819] A speech recognition device and means for identifying the voices of multiple participants in a meeting.

[0820] A monitoring function and means for monitoring the frequency and duration of voices identified by the voice recognition device,

[0821] A function and means for adjusting audio opportunities among participants based on monitoring results of audio frequency and duration.

[0822] A feedback function and means to provide information after the meeting, based on the results of the monitoring function.

[0823] A collaborative function and means to optimize communication between power equipment and workers in a production environment.

[0824] A notification function and means for providing timely notifications and instructions to the power unit.

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the adjustment function has a notification device for sending a notification prompting a remote participant to speak.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the monitoring function has a priority resetting function for resetting voice priority during operation and providing uniform voice opportunities.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] A voice analysis means for identifying the statements of numerous participants in a meeting,

[0833] A monitoring means for monitoring the frequency and duration of utterances identified by the voice analysis means,

[0834] A means for adjusting speaking opportunities among participants based on the monitoring results of speaking frequency and duration,

[0835] Based on the results of the monitoring measures, an information provision method is provided to give feedback after the meeting has ended.

[0836] An emotion engine means that identifies the speaker's emotional state from audio data and provides feedback in real time based on that emotion,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, wherein the coordination means has a notification means for sending a notification prompting a remote participant to speak via a communication device.

[0840] (Claim 3)

[0841] The system according to claim 1, wherein the monitoring means has a priority setting means for automatically setting the priority of speeches and providing equal opportunities for speech.

[0842] "Application example 2 when combining with an emotional engine"

[0843] (Claim 1)

[0844] A speech recognition means for identifying the statements of multiple participants in a meeting,

[0845] Monitoring means for monitoring the frequency and duration of speech identified by the speech recognition means,

[0846] A means of adjusting speaking opportunities among participants based on the monitoring results of speaking frequency and duration,

[0847] A feedback mechanism that provides feedback after the meeting based on the results of the monitoring mechanism,

[0848] A means of analyzing participants' emotional states by transcribing their speech into text and analyzing their emotional state from audio and video,

[0849] A presentation means that provides real-time feedback based on the analyzed emotional state,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, wherein the adjustment means has a notification means for sending notifications to remote participants prompting them to speak, and the system has a support means for responding to customer interactions in the store based on sentiment analysis results.

[0853] (Claim 3)

[0854] The system according to claim 1, wherein the monitoring means has a priority resetting means for resetting the priority of speech in real time and providing equal opportunities for speech, and further has a means for optimizing emotional balance through emotion analysis. [Explanation of Symbols]

[0855] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A speech recognition means for identifying the statements of multiple participants in a meeting, Monitoring means for monitoring the frequency and duration of speech identified by the speech recognition means, A means of adjusting opportunities for participants to speak based on the monitoring results of the frequency and duration of their speech, A feedback mechanism that provides feedback after the meeting based on the results of the monitoring mechanism, A system that includes this.

2. The system according to claim 1, wherein the coordination means has a notification means for sending a notification to a remote participant prompting them to speak.

3. The system according to claim 1, wherein the monitoring means has a priority resetting means for resetting the priority of speeches in real time and providing equal opportunities for speech.

Images