system

Abstract

We provide the system. [Solution] Means for acquiring audio data, Means for converting the aforementioned audio data into text data, A means for translating the aforementioned text data into multiple different languages, A means for generating a meeting summary from the translated text data, A means for automatically extracting issues and action items from the aforementioned summary, Means for notifying and displaying the aforementioned summary, issues, and action items to the user, 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 a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need to solve the problems of delayed information sharing due to the time-consuming creation of meeting minutes in a meeting, the occurrence of manual errors, and the inability to handle international cases due to the difficulty of multilingual support. In the conventional method, manually creating meeting minutes after the meeting and translating between multiple languages requires time, which hinders efficient international communication.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for acquiring audio data, means for converting audio data into text data, means for translating text data into multiple different languages, means for generating a meeting summary from the translated text data, means for automatically extracting issues and action items from the summary, and means for notifying and displaying the summary, issues, and action items to the user. By creating accurate and rapid meeting minutes based on audio data and supporting multiple languages, it enables faster information sharing and efficient management of international matters.

[0006] "Audio data" refers to signals, including human voices, collected through microphones during meetings, conversations, and other similar events.

[0007] "Text data" refers to text information converted from speech, and is information expressed in natural language.

[0008] Translation is the process of converting text expressed in one language into another language.

[0009] "Summarization" is the act of extracting important information from a long text and expressing it in a shortened form.

[0010] "Issues" refer to specific problems or situations that need to be resolved in a meeting.

[0011] "Action items" refer to the specific tasks or steps that should be taken next to solve a problem.

[0012] A "notification" is a message or alert sent to a user to inform them of information.

[0013] "Display" refers to the act of drawing information on a device screen so that the user can visually confirm it. [Brief explanation of the drawing]

[0014] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] [[ID=,45]] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the labeled processor (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.

[0018] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the labeled storage 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.

[0020] In the following embodiments, the labeled communication I / F (Interface) 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.

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a voice translation meeting minutes generation system that enables efficient information management of meetings and important conversations. This system allows users to acquire information in real time during meetings and facilitates information sharing in multiple languages.

[0036] First, the user starts a meeting through their device. The device's microphone captures audio data and sends it to the server. As soon as the server receives the audio data, it converts it into text data using a highly accurate speech recognition engine. This conversion ensures that every word is accurately transcribed into text.

[0037] The converted text data is passed to the translation engine on the server. The server then translates the text into the specified language. Even when users speak different languages, the translated meeting minutes ensure that all participants understand the same information.

[0038] Furthermore, the server automatically generates a summary from the translated text. This summary extracts the key points to grasp the overall flow of the meeting, helping users quickly review the meeting content.

[0039] The server also picks out issues and action items from the summary information and automatically generates them in list format. This list clarifies the next steps to be addressed in the meeting and helps users manage tasks efficiently.

[0040] This information is displayed as a notification on the user's device. Based on this, the user follows up on tasks and shares information with collaborators as needed. This clarifies important decisions made in meetings and the next steps, ensuring smooth project progress.

[0041] As a concrete example, in international conferences of multinational corporations, this system allows participants speaking different languages ​​to understand the meeting minutes in real time. This enables faster decision-making and more efficient information sharing. Furthermore, because the system automatically extracts issues and actions, delays and human errors in operations can be minimized.

[0042] This invention makes it possible to shorten meeting times, maintain the accuracy of information, and manage projects across multiple languages.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user inputs the meeting audio using the device's microphone. The device then begins to acquire this audio data as a digital signal in real time.

[0046] Step 2:

[0047] The terminal appropriately compresses the acquired digital audio data and sends it to the server using a protocol that minimizes latency.

[0048] Step 3:

[0049] The server inputs the received audio data into the speech recognition engine. This engine uses advanced algorithms to convert the audio into text data. By removing noise and enabling speaker identification, it achieves highly accurate text conversion.

[0050] Step 4:

[0051] The server formats the generated text data, correcting grammatical errors and redundancies. The formatted data is stored in a database and made accessible later.

[0052] Step 5:

[0053] The server passes the formatted text data to the translation engine, which then performs the translation process for the specified languages. This translation accurately reproduces the content of the meeting in other languages ​​while preserving the original nuances.

[0054] Step 6:

[0055] The server generates a summary from the translated text data. Using natural language processing, it extracts key keywords and points and compiles a concise summary of the meeting.

[0056] Step 7:

[0057] The server then extracts issues and action items from the summary information and automatically creates them in list format. This list is then ready to be used in conjunction with the task management system.

[0058] Step 8:

[0059] The terminal receives summaries, translated texts, and task lists sent from the server and notifies the user. The user uses this information to review the meeting content and determine the next steps.

[0060] Step 9:

[0061] Users proceed with follow-up tasks based on the generated action list via their devices. By checking the progress of tasks and sharing information with team members, they facilitate the implementation of decisions made in meetings.

[0062] (Example 1)

[0063] 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."

[0064] In today's business environment, meetings frequently used by multinational corporations and global teams require rapid and accurate information transfer among participants who speak different languages. Furthermore, post-meeting minutes and the clarification of next steps are time-consuming and prone to human error. There is a need to solve these problems and provide a system that efficiently manages and shares information in multiple languages.

[0065] 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.

[0066] In this invention, the server includes means for acquiring audio information, means for converting the audio information into document data, and means for converting the document data into multiple different languages. This enables all participants using different languages ​​to quickly and accurately understand the meeting content and grasp important discussions and conclusions in real time.

[0067] "Audio information" refers to data of human speech and sounds emitted during meetings and other similar events.

[0068] "Document data" refers to text-based data that represents audio information using characters.

[0069] "Conversion" refers to the process of changing data from one format to another. In this context, it refers to converting audio information into document data or converting document data into another language.

[0070] "Key points" refer to the main content of a meeting, such as particularly noteworthy discussions or decisions.

[0071] "Work details" refers to the action plan decided at the meeting and the specific tasks based on it.

[0072] "Action guidelines" refer to instructions or policies that should be implemented based on the outcome of a meeting.

[0073] "Users" refer to people who use this system to participate in meetings or receive information.

[0074] This invention relates to a speech translation meeting minutes generation system for efficiently managing information in multilingual meetings. To implement this system, terminals, servers, and network elements connecting them are used.

[0075] The user initiates a meeting using a terminal. This terminal is equipped with a microphone and is responsible for capturing audio information during the meeting. The captured audio information is transmitted from the terminal to the server via the internet. To ensure data security, it is appropriate to use the SSL / TLS protocol for communication.

[0076] The server converts received audio information into document data using an advanced speech recognition engine. Specific speech recognition engines available include Google® Speech-to-Text API and Microsoft® Azure® Speech Service. This conversion ensures that every word spoken is accurately transcribed into text.

[0077] The obtained document data is then passed to a translation engine. Using the Google Translate API or DeepL API, rapid and accurate multilingual translation is performed. This ensures that participants speaking different languages ​​can obtain consistent information.

[0078] Next, the server uses the translated document data to apply natural language processing techniques to summarize the key points of the meeting. Generative AI models such as OpenAI's GPT model are used for summary generation, enabling efficient extraction of meeting key points and quick information comprehension.

[0079] Furthermore, the server extracts work content and action guidelines from this summary. It utilizes machine learning algorithms to effectively identify tasks and instructions from the document data.

[0080] After the information is processed, the server sends it to the terminal, making it available to the user. Based on the information displayed on their terminal, the user can efficiently review meeting content and share information with other participants. This system significantly improves the smooth running of meetings and the efficiency of project management.

[0081] A concrete example of using this system is an international conference where multiple languages ​​are spoken. Meeting minutes and summaries, automatically translated via the server, allow all participants to quickly grasp the key points of the meeting and make efficient decisions.

[0082] Example of a prompt:

[0083] "Please record today's meeting and create minutes and summaries translated into English, French, and Chinese. Next, please list the identified issues and action plans."

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The user starts a meeting on their device. At this time, the device's microphone acquires audio information from the meeting in real time. The input is an audio signal, and the output is digitized audio data. The device temporarily stores the acquired audio data.

[0087] Step 2:

[0088] The terminal sends the acquired audio data to the server. Here, the terminal encrypts the audio data using the SSL / TLS protocol and sends it to the server over the internet. The input is digital audio data, and the output is secure data transmission to the server.

[0089] Step 3:

[0090] The server inputs the received audio data into the speech recognition engine. Specifically, the Google Speech-to-Text API is used for speech recognition. The input is digital audio data, and the data is processed to output document data. This output is a string representation of the meeting's spoken content.

[0091] Step 4:

[0092] The server passes document data to the translation engine, which then translates it into the specified language. It uses the DeepL API to achieve highly accurate translations. The input is document data, and the output is translated document data after data transformation.

[0093] Step 5:

[0094] The server processes translated document data and summarizes key meeting points. It automatically generates summaries using OpenAI's GPT model. The input is translated document data, and the output is a condensed meeting summary.

[0095] Step 6:

[0096] The server automatically extracts action plans and work instructions from the meeting summary. Here, a machine learning algorithm identifies tasks and directives from the summary. The input is the summary data, and the output is the extracted task list.

[0097] Step 7:

[0098] The server sends the generated translated documents, meeting summaries, and action plan lists to the terminal. The input is this various data, and the output is the distribution of information usable by the user. The terminal notifies the user of the information and displays it on the screen, facilitating post-meeting information access.

[0099] (Application Example 1)

[0100] 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."

[0101] To facilitate information sharing and rapid decision-making among multinational engineers in data centers, it is essential to translate meeting content into multiple languages ​​in real time and to quickly and accurately transmit critical information. In this context, there is a growing need for a system that efficiently manages meeting content and immediately extracts issues and solutions. Therefore, a method is needed to deepen understanding among engineers who speak different languages ​​and to quickly implement countermeasures.

[0102] 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.

[0103] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, means for translating text information into different languages, means for generating a summary from the translated text information, means for automatically extracting problems and countermeasures from the summary, means for informing and displaying the summary, problems, and countermeasures to the user, and means for enabling use in monitoring meetings in a data center. This enables rapid information transmission between different languages ​​and immediate problem resolution.

[0104] "Means for acquiring audio information" refers to devices or technologies for collecting audio emitted from speakers or sound sources.

[0105] "Means of converting to text information" refers to technologies or software that convert audio information into text format through digital processing.

[0106] "Means of translation into different languages" refers to technologies or systems for performing the process of accurately converting textual information written in one language into another language.

[0107] "Methods for generating summaries" refer to techniques that extract important information and key points from long texts and reconstruct that information in a short, condensed form.

[0108] "Methods for automatically extracting problems and countermeasures" refers to a process in which the system independently identifies and lists the issues and future countermeasures discussed within the summary.

[0109] "Means of informing and displaying to the user" refers to devices or interfaces that notify the user of extracted information and display it on a screen or device.

[0110] "Means to enable use in monitoring meetings in data centers" refers to a process that includes technologies and preset settings for effectively utilizing a meeting system in a data center environment.

[0111] The system that realizes this invention includes a mechanism that processes audio information in real time, translates it into different languages, generates summaries, and improves the efficiency of meetings in data centers.

[0112] The server acquires audio information from the terminals during meetings and converts that audio into text. Machine learning frameworks such as TENSORFLOW® are used for speech recognition to achieve highly accurate text conversion. This converted text information is then translated into multiple languages ​​using the Google Translate API.

[0113] From the translated text information, the server generates a meeting summary using a natural language processing model such as BERT. From the summarized information, it automatically extracts problems and proposed solutions, and lists them.

[0114] The user's device immediately displays a notification containing a summary, the problem, and the suggested solutions. This process enables rapid information sharing and collaborative problem-solving in monitoring meetings involving engineers from diverse cultural backgrounds.

[0115] As a concrete example, when a network failure occurs at a data center, engineers can use this system to hold an emergency meeting. The content of the discussion is translated and summarized in multiple languages ​​in real time and displayed simultaneously on each engineer's terminal, allowing the team to work together to develop a response plan.

[0116] An example of a prompt message could be: "Collect meeting audio in real time, immediately translate it into multiple languages, summarize the key points, and then display it as a notification to the technicians so they can use it for emergency response."

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The user's device acquires meeting audio information in real time from the microphone. The audio information is transmitted to the server in digital format. The input is raw audio data, and the output is digitized audio data.

[0120] Step 2:

[0121] The server converts received audio data into text information using a speech recognition engine based on TensorFlow. The input is digitized audio data, and the output is text information. This process analyzes the audio waveform and converts the speaker's utterance into text data.

[0122] Step 3:

[0123] The server translates text information into multiple specified languages ​​using the Google Translate API. The input is text information, and the output is the translated string. This step ensures that information is shared in a way that all participants, regardless of their language background, can understand.

[0124] Step 4:

[0125] The server generates a summary using the BERT model from translated text information. The input is the translated string, and the output is the summarized text. This model extracts the key points from a meeting and shortens the content.

[0126] Step 5:

[0127] The server automatically extracts problems and solutions from the summary and organizes them as a list. The input is the summarized text, and the output is a list of problems and solutions. This process uses natural language processing technology to clarify the core points of the meeting.

[0128] Step 6:

[0129] The user's terminal immediately displays a summary, problem, and countermeasures sent from the server as a notification on the screen. The input is the notification information from the server, and the output is the display on the terminal screen. In this step, technicians can immediately review the information and begin taking the necessary actions.

[0130] 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.

[0131] This invention provides a system that efficiently processes audio data from meetings and conversations, enabling multilingual translation and integration of emotional information. This system maximizes the effectiveness of meetings by generating useful meeting minutes from the audio data and further analyzing the emotional states of participants.

[0132] Users initiate a meeting through their terminal and transmit audio data using the microphone. This audio is acquired in real time by the terminal and sent to the server. The audio data received by the server is converted into text data by a speech recognition engine. During the conversion process, a noise reduction module operates to improve the quality of the audio signal.

[0133] This text data is further translated into multiple languages ​​specified by a translation engine on the server. The translated data can then be easily shared at international conferences, thus expanding the scope of the conference through multilingual support.

[0134] The server further analyzes the audio data using an emotion engine to identify each participant's emotional state. This allows the server to understand participants' emotional responses during the meeting and respond accordingly.

[0135] The generated text data is summarized using natural language processing techniques to extract the key points of the meeting. The summary facilitates smooth communication among participants and helps them grasp the important points.

[0136] The server also automatically extracts issues and action items from the summary and shares them with the user. This list helps participants clarify what actions they need to take next and efficiently plan their post-meeting schedule.

[0137] As a concrete example, using this system in meetings for international projects allows participants who speak different languages ​​to not only obtain the same information in real time, but also to visually understand each individual's emotional state. This enables appropriate responses when discussions become heated or when understanding difficulties arise, and facilitates smoother decision-making regarding project direction.

[0138] By implementing this system, meeting times can be significantly reduced while improving the accuracy of information and mutual understanding. Meeting minutes that include emotional information support more sophisticated decision-making that takes human factors into account.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The user starts a meeting and inputs audio data using the device's microphone. The device converts this audio data into a digital signal in real time and prepares to send it to the server.

[0142] Step 2:

[0143] The terminal compresses the audio data while performing noise reduction before sending it to the server. This improves data transfer efficiency while maintaining audio clarity.

[0144] Step 3:

[0145] The server inputs the received audio data into the speech recognition engine. The engine analyzes this data and converts it into highly accurate text data.

[0146] Step 4:

[0147] The server passes the text data to the emotion engine, which analyzes the intonation and speed of the speech to infer the participant's emotional state. Based on this analysis, it generates text data that includes emotional nuances.

[0148] Step 5:

[0149] The server simultaneously passes the text data to the translation engine, which translates it into the specified language. This enables real-time information sharing even in a multilingual environment.

[0150] Step 6:

[0151] The server passes the translated text data through a summarization engine, which uses natural language processing to extract key points. By shortening the summary, it enables quick understanding of the main points of the meeting.

[0152] Step 7:

[0153] The server extracts issues and action items from the generated summary information and automatically creates a list. These action items facilitate follow-up after meetings.

[0154] Step 8:

[0155] The terminal receives summaries, translation results, sentiment analysis results, and task lists sent from the server. The user reviews this information on the terminal to understand the overall picture of the meeting and the sentiments of the participants.

[0156] Step 9:

[0157] Users execute tasks and follow up based on action lists generated through their devices. This allows for the quick and reliable implementation of meeting conclusions and next steps.

[0158] (Example 2)

[0159] 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".

[0160] In modern international conferences and dialogues, it is essential for multilingual participants to share information accurately and in real time, and to communicate smoothly. However, in addition to multilingual translation, it is also necessary to consider the emotional reactions of participants, and there is a lack of technology to efficiently handle this. As a result, the effectiveness of meetings may not be fully realized, and problems may arise in important decision-making.

[0161] 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.

[0162] In this invention, the server includes means for acquiring audio information, means for converting the audio information into text information, and means for translating the text information into multiple different languages. This enables participants to understand information in multiple languages ​​in real time. The server also includes means for generating a meeting summary from the translated text information, means for automatically extracting issues and action items from the summary, and means for analyzing the audio information to identify the emotional state of the participants. This maximizes the effectiveness of the meeting and enables smooth important decision-making.

[0163] "Audio information" refers to data obtained by acquiring and recording conversations and voices as digital signals.

[0164] "Textual information" refers to data in text format that has been converted from audio information, and is information that humans can visually recognize.

[0165] Translation is the process of converting written information in one language into another language, facilitating communication between multiple languages.

[0166] "Summary generation" is the process of extracting key points and information from a large amount of textual data and presenting it in a concise format.

[0167] "Identifying issues and action items" is the process of identifying key issues and next steps from summarized information, thereby clarifying the actions to be taken after the meeting.

[0168] "Emotional state" refers to the result of evaluating participants' emotional responses and psychological state based on audio information.

[0169] "Visualization" is the process of visually representing extracted information and analysis results, and presenting them in a way that is easy for participants to understand.

[0170] This invention describes a system that efficiently processes audio information, enabling multilingual translation and sentiment analysis. First, the user starts a meeting using a terminal. A highly sensitive microphone is connected to the terminal, which records the user's speech as audio information in real time. This audio information is collected as a digital signal, works in conjunction with a noise filtering module, and is transmitted to a server as high-precision audio data.

[0171] The server converts received audio information into text using a speech recognition engine. At this stage, a model utilizing deep learning technology is used to improve the accuracy of speech recognition. The converted text information is then translated into the specified languages ​​by a multilingual translation engine within the server. This translation process employs natural language processing technology to ensure fast and accurate translation.

[0172] The translated text information is then passed to a summarization module to create a summary of the meeting content. This summary information is processed to highlight key points. The server also drives an emotion analysis engine by analyzing the intonation, speed, and volume of the speech to visualize the emotional state of each participant.

[0173] Furthermore, the system automatically extracts issues and action items from the generated summary and notifies the user of this information. As a result, each participant can clearly understand their next steps, making it easier to plan for the day after the meeting.

[0174] As a concrete example, consider the case where this system is adopted in an international project. Participants who speak different languages ​​will be able to understand information simultaneously, and adjustments as needed will be made efficiently. The introduction of this system will shorten meeting times and promote accuracy and mutual understanding of information.

[0175] An example of a prompt might be, "Please provide an overview of the meeting minutes generation system using real-time translation and sentiment analysis for international conferences." This prompt allows users to immediately obtain specific and actionable information that the system can provide.

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] The user starts a meeting using the terminal. The terminal acquires audio information through the microphone and instantly converts that data into a digital signal. The audio data is acquired as input by the terminal, and after audio signal processing, it generates clean audio data with noise removed as output.

[0179] Step 2:

[0180] The terminal sends the acquired clean audio data to the server via a security protocol. The audio data arrives at the server as input, and its integrity is verified. The server receives this data and prepares for the next process.

[0181] Step 3:

[0182] The server passes the received audio data to the speech recognition engine, which processes it to convert it into text. The input here is clean audio data, and the output is accurately transcribed text. Specifically, a deep learning model analyzes the audio and converts it into text format.

[0183] Step 4:

[0184] The server inputs textual information into a multilingual translation engine, which translates it in real time into multiple specified languages. The input is textual information, and the output is translated text in multiple languages. A machine translation algorithm generates the appropriate translation based on the context.

[0185] Step 5:

[0186] The server sends the translated text information to a summarization engine to create a meeting summary. The input is a set of translated texts, and the output is a concise and easy-to-understand summary. In this process, important topics are extracted through natural language processing.

[0187] Step 6:

[0188] The server then inputs the audio data into an emotion analysis engine to identify the participant's emotional state. The input is audio data, and the output is the analysis result indicating the emotional state. Here, the intonation and pitch of the voice are analyzed to determine the emotion.

[0189] Step 7:

[0190] The server notifies the user of the generated summary, issues, and action items. Input consists of the summary text and sentiment analysis results, while output is information displayed through the user interface. This allows the user to easily grasp the overall picture of the meeting and prepare for subsequent actions.

[0191] (Application Example 2)

[0192] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0193] In multilingual meetings and discussions, it is difficult for participants to smoothly understand information and appropriately grasp emotional responses. Traditional technologies handle translation, minute-taking, and sentiment analysis separately, lacking integrated support. As a result, efficient and smooth communication is hindered in international conferences and multicultural societies.

[0194] 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.

[0195] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, and means for translating into multiple different languages. This enables real-time information sharing and visualization of emotions even in a multilingual environment.

[0196] "Audio information" refers to data that represents sounds and voices as digital or analog signals.

[0197] "Text information" refers to data in which audio information has been converted into the form of characters and symbols.

[0198] Translation is the process of replacing words in one language with words in another while preserving their meaning.

[0199] A "summary" is a way of simplifying a vast amount of information and extracting the main points and content.

[0200] "Challenges" refer to problems that need to be solved or themes that need to be addressed.

[0201] An "action item" is a list of specific actions that should be taken to achieve a certain goal.

[0202] "User" refers to an individual or group that uses this system or service.

[0203] "Noise reduction" is the process of removing unwanted sounds and background noise from the target signal.

[0204] The "speaker" is the person who is actually speaking in a conversation or audio information.

[0205] "Emotional state" refers to a temporary state of a person's emotions or mood.

[0206] "Visualization" is the process of making information more understandable by visualizing it using images, infographics, and other visual aids.

[0207] To implement this invention, first, the user acquires voice information using a terminal at the start of a meeting or conversation. The voice is collected through the terminal's microphone. The acquired voice information is transmitted in real time to a server in the cloud. The server uses a speech recognition engine to convert the voice information into text information. This process uses speech recognition technology such as Google Speech-to-Text.

[0208] The server translates the converted text information into multiple specified languages ​​using tools such as Google Translate. It also uses an emotion analysis engine, such as IBM Watson® Tone Analyzer, to identify the emotional state of each participant from the text information. This visualizes the emotional information for the user, helping them understand the context of meetings and conversations.

[0209] Furthermore, the server utilizes natural language processing tools such as spaCy and NLTK to generate a summary from the translated text information. This summary includes key points and action items from the meeting. The summary results are also automatically extracted as issues and action items, notified to the user, and displayed on the screen.

[0210] As a concrete example, if a city hall holds a public briefing for a multinational population, this system can be used to provide real-time meeting minutes and sentiment analysis information in multiple languages. This allows for the collection of feedback that takes residents' feelings into account, enabling better service improvements.

[0211] An example of a prompt is, "Use the meeting audio data to perform multilingual translation and sentiment analysis, and visualize meeting minutes and sentiment states in real time." By using this prompt, the system initiates the necessary processing and supports smooth meetings and discussions.

[0212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0213] Step 1:

[0214] The user uses the device's microphone to capture audio information from meetings and conversations. This captured audio data is sent to the server in real time. The input is audio data, and the output is the data sent to the server. This process prepares the system for recording the content of conversations sequentially.

[0215] Step 2:

[0216] The server passes the received audio data to a speech recognition engine, which converts the audio into text. The input is audio data on the server, and the output is text data. Speech-to-text conversion is achieved by processing the data using speech recognition technologies such as Google Speech-to-Text.

[0217] Step 3:

[0218] The server passes the converted text information to a translation engine, which then translates it into the specified multiple languages. The input is the converted text information, and the output is multilingual text information. The translation process is performed using the Google Translate API. This operation makes it possible to share information with participants who speak different languages.

[0219] Step 4:

[0220] The server passes the translated text information to the sentiment analysis engine to identify each participant's emotional state. The input is the translated text information, and the output is the result of the emotional state analysis. Sentiment analysis techniques such as IBM Watson Tone Analyzer are used to extract emotional information. This clarifies the participants' emotional responses.

[0221] Step 5:

[0222] The server analyzes translated text information using natural language processing tools and generates a summary. The input is translated text information, and the output is summary information. Using tools like spaCy and NLTK, the text is analyzed to extract the main points of conversations and meetings. This process presents important information concisely.

[0223] Step 6:

[0224] The server automatically extracts issues and action items from the generated summary information and notifies the user. The input is summary information, and the output is a list of issues and action items. The program automatically extracts this information using conditional branching and pattern recognition, and displays it on the terminal. This process clarifies the actions needed after the meeting.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] [Second Embodiment]

[0229] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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".

[0241] This invention is a voice translation meeting minutes generation system that enables efficient information management of meetings and important conversations. This system allows users to acquire information in real time during meetings and facilitates information sharing in multiple languages.

[0242] First, the user starts a meeting through their device. The device's microphone captures audio data and sends it to the server. As soon as the server receives the audio data, it converts it into text data using a highly accurate speech recognition engine. This conversion ensures that every word is accurately transcribed into text.

[0243] The converted text data is passed to the translation engine on the server. The server then translates the text into the specified language. Even when users speak different languages, the translated meeting minutes ensure that all participants understand the same information.

[0244] Furthermore, the server automatically generates a summary from the translated text. This summary extracts the key points to grasp the overall flow of the meeting, helping users quickly review the meeting content.

[0245] The server also picks out issues and action items from the summary information and automatically generates them in list format. This list clarifies the next steps to be addressed in the meeting and helps users manage tasks efficiently.

[0246] This information is displayed as a notification on the user's device. Based on this, the user follows up on tasks and shares information with collaborators as needed. This clarifies important decisions made in meetings and the next steps, ensuring smooth project progress.

[0247] As a concrete example, in international conferences of multinational corporations, this system allows participants speaking different languages ​​to understand the meeting minutes in real time. This enables faster decision-making and more efficient information sharing. Furthermore, because the system automatically extracts issues and actions, delays and human errors in operations can be minimized.

[0248] This invention makes it possible to shorten meeting times, maintain the accuracy of information, and manage projects across multiple languages.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The user inputs the meeting audio using the device's microphone. The device then begins to acquire this audio data as a digital signal in real time.

[0252] Step 2:

[0253] The terminal appropriately compresses the acquired digital audio data and sends it to the server using a protocol that minimizes latency.

[0254] Step 3:

[0255] The server inputs the received audio data into the speech recognition engine. This engine uses advanced algorithms to convert the audio into text data. By removing noise and enabling speaker identification, it achieves highly accurate text conversion.

[0256] Step 4:

[0257] The server formats the generated text data, correcting grammatical errors and redundancies. The formatted data is stored in a database and made accessible later.

[0258] Step 5:

[0259] The server passes the formatted text data to the translation engine, which then performs the translation process for the specified languages. This translation accurately reproduces the content of the meeting in other languages ​​while preserving the original nuances.

[0260] Step 6:

[0261] The server generates a summary from the translated text data. Using natural language processing, it extracts key keywords and points and compiles a concise summary of the meeting.

[0262] Step 7:

[0263] The server then extracts issues and action items from the summary information and automatically creates them in list format. This list is then ready to be used in conjunction with the task management system.

[0264] Step 8:

[0265] The terminal receives summaries, translated texts, and task lists sent from the server and notifies the user. The user uses this information to review the meeting content and determine the next steps.

[0266] Step 9:

[0267] Users proceed with follow-up tasks based on the generated action list via their devices. By checking the progress of tasks and sharing information with team members, they facilitate the implementation of decisions made in meetings.

[0268] (Example 1)

[0269] 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."

[0270] In today's business environment, meetings frequently used by multinational corporations and global teams require rapid and accurate information transfer among participants who speak different languages. Furthermore, post-meeting minutes and the clarification of next steps are time-consuming and prone to human error. There is a need to solve these problems and provide a system that efficiently manages and shares information in multiple languages.

[0271] 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.

[0272] In this invention, the server includes means for acquiring audio information, means for converting the audio information into document data, and means for converting the document data into multiple different languages. This enables all participants using different languages ​​to quickly and accurately understand the meeting content and grasp important discussions and conclusions in real time.

[0273] "Audio information" refers to data of human speech and sounds emitted during meetings and other similar events.

[0274] "Document data" refers to text-based data that represents audio information using characters.

[0275] "Conversion" refers to the process of changing data from one format to another. In this context, it refers to converting audio information into document data or converting document data into another language.

[0276] "Key points" refer to the main content of a meeting, such as particularly noteworthy discussions or decisions.

[0277] "Work details" refers to the action plan decided at the meeting and the specific tasks based on it.

[0278] "Action guidelines" refer to instructions or policies that should be implemented based on the outcome of a meeting.

[0279] "Users" refer to people who use this system to participate in meetings or receive information.

[0280] This invention is a speech translation meeting minutes generation system for efficiently managing information in multilingual meetings. To implement this system, terminals, servers, and network elements connecting them are used.

[0281] The user starts a meeting using a terminal. This terminal is equipped with a microphone and serves to acquire the audio information during the meeting. The obtained audio information is sent from the terminal to the server via the Internet. For communication, it is suitable to use the SSL / TLS protocol to ensure data security.

[0282] The server converts the received audio information into document data using an advanced speech recognition engine. As specific speech recognition engines, Google Speech-to-Text API or Microsoft Azure Speech Service can be used. Through this conversion, each utterance is accurately transcribed into text.

[0283] The obtained document data is then passed to a translation engine. For translation, by using Google Translate API or DeepL API, rapid and accurate conversion between multiple languages is performed. This enables participants who speak different languages to obtain unified information.

[0284] Subsequently, the server applies natural language processing technology to summarize the key points of the meeting content using the translated document data. For summary generation, by using a generative AI model such as OpenAI's GPT model, the key points of the meeting can be efficiently extracted, enabling information grasping in a short time.

[0285] Furthermore, the server extracts the work content and action guidelines from this summary. By leveraging machine learning algorithms, tasks and instructions are effectively identified from the document data.

[0286] After the information is processed, the server sends it to the terminal for the user to access. Based on the information displayed on their own terminal, the user can efficiently review the meeting content and share information among participants. This system greatly improves the smooth progress of the meeting and the efficiency of project management.

[0287] A concrete example of using this system is an international conference where multiple languages ​​are spoken. Meeting minutes and summaries, automatically translated via the server, allow all participants to quickly grasp the key points of the meeting and make efficient decisions.

[0288] Example of a prompt:

[0289] "Please record today's meeting and create minutes and summaries translated into English, French, and Chinese. Next, please list the identified issues and action plans."

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] The user starts a meeting on their device. At this time, the device's microphone acquires audio information from the meeting in real time. The input is an audio signal, and the output is digitized audio data. The device temporarily stores the acquired audio data.

[0293] Step 2:

[0294] The terminal sends the acquired audio data to the server. Here, the terminal encrypts the audio data using the SSL / TLS protocol and sends it to the server over the internet. The input is digital audio data, and the output is secure data transmission to the server.

[0295] Step 3:

[0296] The server inputs the received audio data into the speech recognition engine. Specifically, the Google Speech-to-Text API is used for speech recognition. The input is digital audio data, and the data is processed to output document data. This output is a string representation of the meeting's spoken content.

[0297] Step 4:

[0298] The server passes document data to the translation engine, which then translates it into the specified language. It uses the DeepL API to achieve highly accurate translations. The input is document data, and the output is translated document data after data transformation.

[0299] Step 5:

[0300] The server processes translated document data and summarizes key meeting points. It automatically generates summaries using OpenAI's GPT model. The input is translated document data, and the output is a condensed meeting summary.

[0301] Step 6:

[0302] The server automatically extracts action plans and work instructions from the meeting summary. Here, a machine learning algorithm identifies tasks and directives from the summary. The input is the summary data, and the output is the extracted task list.

[0303] Step 7:

[0304] The server sends the generated translated documents, meeting summaries, and action plan lists to the terminal. The input is this various data, and the output is the distribution of information usable by the user. The terminal notifies the user of the information and displays it on the screen, facilitating post-meeting information access.

[0305] (Application Example 1)

[0306] 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 glasses 214 will be referred to as the "terminal."

[0307] In order to facilitate information sharing and speed up decision-making among multinational engineers in a data center, it is required to translate the content of meetings into multiple languages in real time and transmit important information quickly and accurately. In such a situation, there is an increasing need for a system that can efficiently manage the content of meetings and immediately extract issues and countermeasures. Therefore, a method is needed to deepen understanding among engineers who speak different languages and quickly take corresponding measures.

[0308] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0309] In this invention, the server includes means for acquiring voice information, means for converting voice information into character information, means for translating character information into different languages, means for generating a summary from the translated character information, means for automatically extracting problem points and countermeasure items from the summary, means for notifying and displaying the summary, problem points, and countermeasure items to the user, and means for enabling use in a monitoring meeting in a data center. Thereby, rapid information transmission between different languages and immediate problem solving become possible.

[0310] The "means for acquiring voice information" is a device or technology for collecting voices emitted from speakers or sound sources.

[0311] The "means for converting into character information" is a technology or software for converting voice information into text format by digital processing.

[0312] The "means for translating into different languages" is a technology or system for executing a process of accurately converting character information described in a specific language into another language.

[0313] The "means for generating a summary" is a technology for extracting important information and points from a long text and reconstructing the information in a condensed and shortened form.

[0314] "Methods for automatically extracting problems and countermeasures" refers to a process in which the system independently identifies and lists the issues and future countermeasures discussed within the summary.

[0315] "Means of informing and displaying to the user" refers to devices or interfaces that notify the user of extracted information and display it on a screen or device.

[0316] "Means to enable use in monitoring meetings in data centers" refers to a process that includes technologies and preset settings for effectively utilizing a meeting system in a data center environment.

[0317] The system that realizes this invention includes a mechanism that processes audio information in real time, translates it into different languages, generates summaries, and improves the efficiency of meetings in data centers.

[0318] The server acquires audio information from the terminals during meetings and converts that audio into text. Machine learning frameworks such as TensorFlow are used for speech recognition to achieve highly accurate text conversion. This converted text information is then translated into multiple languages ​​using the Google Translate API.

[0319] From the translated text information, the server generates a meeting summary using a natural language processing model such as BERT. From the summarized information, it automatically extracts problems and proposed solutions, and lists them.

[0320] The user's device immediately displays a notification containing a summary, the problem, and the suggested solutions. This process enables rapid information sharing and collaborative problem-solving in monitoring meetings involving engineers from diverse cultural backgrounds.

[0321] As a concrete example, when a network failure occurs at a data center, engineers can use this system to hold an emergency meeting. The content of the discussion is translated and summarized in multiple languages ​​in real time and displayed simultaneously on each engineer's terminal, allowing the team to work together to develop a response plan.

[0322] An example of a prompt message could be: "Collect meeting audio in real time, immediately translate it into multiple languages, summarize the key points, and then display it as a notification to the technicians so they can use it for emergency response."

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The user's device acquires meeting audio information in real time from the microphone. The audio information is transmitted to the server in digital format. The input is raw audio data, and the output is digitized audio data.

[0326] Step 2:

[0327] The server converts received audio data into text information using a speech recognition engine based on TensorFlow. The input is digitized audio data, and the output is text information. This process analyzes the audio waveform and converts the speaker's utterance into text data.

[0328] Step 3:

[0329] The server uses the Google Translate API to translate text information into multiple specified languages. The input is text information, and the output is the translated string. This step ensures that information is shared in a way that is understandable to all participants using different languages.

[0330] Step 4:

[0331] The server generates a summary using the BERT model from translated text information. The input is the translated string, and the output is the summarized text. This model extracts the key points from a meeting and shortens the content.

[0332] Step 5:

[0333] The server automatically extracts problems and solutions from the summary and organizes them as a list. The input is the summarized text, and the output is a list of problems and solutions. This process uses natural language processing technology to clarify the core points of the meeting.

[0334] Step 6:

[0335] The user's terminal immediately displays a summary, problem, and countermeasures sent from the server as a notification on the screen. The input is the notification information from the server, and the output is the display on the terminal screen. In this step, technicians can immediately review the information and begin taking the necessary actions.

[0336] 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.

[0337] This invention provides a system that efficiently processes audio data from meetings and conversations, enabling multilingual translation and integration of emotional information. This system maximizes the effectiveness of meetings by generating useful meeting minutes from the audio data and further analyzing the emotional states of participants.

[0338] Users initiate a meeting through their terminal and transmit audio data using the microphone. This audio is acquired in real time by the terminal and sent to the server. The audio data received by the server is converted into text data by a speech recognition engine. During the conversion process, a noise reduction module operates to improve the quality of the audio signal.

[0339] This text data is further translated into multiple languages ​​specified by a translation engine on the server. The translated data can then be easily shared at international conferences, thus expanding the scope of the conference through multilingual support.

[0340] The server further analyzes the audio data using an emotion engine to identify each participant's emotional state. This allows the server to understand participants' emotional responses during the meeting and respond accordingly.

[0341] The generated text data is summarized using natural language processing techniques to extract the key points of the meeting. The summary facilitates smooth communication among participants and helps them grasp the important points.

[0342] The server also automatically extracts issues and action items from the summary and shares them with the user. This list helps participants clarify what actions they need to take next and efficiently plan their post-meeting schedule.

[0343] As a concrete example, using this system in meetings for international projects allows participants who speak different languages ​​to not only obtain the same information in real time, but also to visually understand each individual's emotional state. This enables appropriate responses when discussions become heated or when understanding difficulties arise, and facilitates smoother decision-making regarding project direction.

[0344] By implementing this system, meeting times can be significantly reduced while improving the accuracy of information and mutual understanding. Meeting minutes that include emotional information support more sophisticated decision-making that takes human factors into account.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] The user starts a meeting and inputs audio data using the device's microphone. The device converts this audio data into a digital signal in real time and prepares to send it to the server.

[0348] Step 2:

[0349] The terminal compresses the audio data while performing noise reduction before sending it to the server. This improves data transfer efficiency while maintaining audio clarity.

[0350] Step 3:

[0351] The server inputs the received audio data into the speech recognition engine. The engine analyzes this data and converts it into highly accurate text data.

[0352] Step 4:

[0353] The server passes the text data to the emotion engine, which analyzes the intonation and speed of the speech to infer the participant's emotional state. Based on this analysis, it generates text data that includes emotional nuances.

[0354] Step 5:

[0355] The server simultaneously passes the text data to the translation engine, which translates it into the specified language. This enables real-time information sharing even in a multilingual environment.

[0356] Step 6:

[0357] The server passes the translated text data through a summarization engine, which uses natural language processing to extract key points. By shortening the summary, it enables quick understanding of the main points of the meeting.

[0358] Step 7:

[0359] The server extracts issues and action items from the generated summary information and automatically creates a list. These action items facilitate follow-up after meetings.

[0360] Step 8:

[0361] The terminal receives summaries, translation results, sentiment analysis results, and task lists sent from the server. The user reviews this information on the terminal to understand the overall picture of the meeting and the sentiments of the participants.

[0362] Step 9:

[0363] Users execute tasks and follow up based on action lists generated through their devices. This allows for the quick and reliable implementation of meeting conclusions and next steps.

[0364] (Example 2)

[0365] 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".

[0366] In modern international conferences and dialogues, it is essential for multilingual participants to share information accurately and in real time, and to communicate smoothly. However, in addition to multilingual translation, it is also necessary to consider the emotional reactions of participants, and there is a lack of technology to efficiently handle this. As a result, the effectiveness of meetings may not be fully realized, and problems may arise in important decision-making.

[0367] 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.

[0368] In this invention, the server includes means for acquiring audio information, means for converting the audio information into text information, and means for translating the text information into multiple different languages. This enables participants to understand information in multiple languages ​​in real time. The server also includes means for generating a meeting summary from the translated text information, means for automatically extracting issues and action items from the summary, and means for analyzing the audio information to identify the emotional state of the participants. This maximizes the effectiveness of the meeting and enables smooth important decision-making.

[0369] "Audio information" refers to data obtained by acquiring and recording conversations and voices as digital signals.

[0370] "Textual information" refers to data in text format that has been converted from audio information, and is information that humans can visually recognize.

[0371] Translation is the process of converting written information in one language into another language, facilitating communication between multiple languages.

[0372] "Summary generation" is the process of extracting key points and information from a large amount of textual data and presenting it in a concise format.

[0373] "Identifying issues and action items" is the process of identifying key issues and next steps from summarized information, thereby clarifying the actions to be taken after the meeting.

[0374] "Emotional state" refers to the result of evaluating participants' emotional responses and psychological state based on audio information.

[0375] "Visualization" is the process of visually representing extracted information and analysis results, and presenting them in a way that is easy for participants to understand.

[0376] This invention describes a system that efficiently processes audio information, enabling multilingual translation and sentiment analysis. First, the user starts a meeting using a terminal. A highly sensitive microphone is connected to the terminal, which records the user's speech as audio information in real time. This audio information is collected as a digital signal, works in conjunction with a noise filtering module, and is transmitted to a server as high-precision audio data.

[0377] The server converts received audio information into text using a speech recognition engine. At this stage, a model utilizing deep learning technology is used to improve the accuracy of speech recognition. The converted text information is then translated into the specified languages ​​by a multilingual translation engine within the server. This translation process employs natural language processing technology to ensure fast and accurate translation.

[0378] The translated text information is then passed to a summarization module to create a summary of the meeting content. This summary information is processed to highlight key points. The server also drives an emotion analysis engine by analyzing the intonation, speed, and volume of the speech to visualize the emotional state of each participant.

[0379] Furthermore, the system automatically extracts issues and action items from the generated summary and notifies the user of this information. As a result, each participant can clearly understand their next steps, making it easier to plan for the day after the meeting.

[0380] As a concrete example, consider the case where this system is adopted in an international project. Participants who speak different languages ​​will be able to understand information simultaneously, and adjustments as needed will be made efficiently. The introduction of this system will shorten meeting times and promote accuracy and mutual understanding of information.

[0381] An example of a prompt might be, "Please provide an overview of the meeting minutes generation system using real-time translation and sentiment analysis for international conferences." This prompt allows users to immediately obtain specific and actionable information that the system can provide.

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The user starts a meeting using the terminal. The terminal acquires audio information through the microphone and instantly converts that data into a digital signal. The audio data is acquired as input by the terminal, and after audio signal processing, it generates clean audio data with noise removed as output.

[0385] Step 2:

[0386] The terminal sends the acquired clean audio data to the server via a security protocol. The audio data arrives at the server as input, and its integrity is verified. The server receives this data and prepares for the next process.

[0387] Step 3:

[0388] The server passes the received audio data to the speech recognition engine, which processes it to convert it into text. The input here is clean audio data, and the output is accurately transcribed text. Specifically, a deep learning model analyzes the audio and converts it into text format.

[0389] Step 4:

[0390] The server inputs textual information into a multilingual translation engine, which translates it in real time into multiple specified languages. The input is textual information, and the output is translated text in multiple languages. A machine translation algorithm generates the appropriate translation based on the context.

[0391] Step 5:

[0392] The server sends the translated text information to a summarization engine to create a meeting summary. The input is a set of translated texts, and the output is a concise and easy-to-understand summary. In this process, important topics are extracted through natural language processing.

[0393] Step 6:

[0394] The server then inputs the audio data into an emotion analysis engine to identify the participant's emotional state. The input is audio data, and the output is the analysis result indicating the emotional state. Here, the intonation and pitch of the voice are analyzed to determine the emotion.

[0395] Step 7:

[0396] The server notifies the user of the generated summary, issues, and action items. Input consists of the summary text and sentiment analysis results, while output is information displayed through the user interface. This allows the user to easily grasp the overall picture of the meeting and prepare for subsequent actions.

[0397] (Application Example 2)

[0398] 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."

[0399] In multilingual meetings and discussions, it is difficult for participants to smoothly understand information and appropriately grasp emotional responses. Traditional technologies handle translation, minute-taking, and sentiment analysis separately, lacking integrated support. As a result, efficient and smooth communication is hindered in international conferences and multicultural societies.

[0400] 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.

[0401] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, and means for translating into multiple different languages. This enables real-time information sharing and visualization of emotions even in a multilingual environment.

[0402] "Audio information" refers to data that represents sounds and voices as digital or analog signals.

[0403] "Text information" refers to data in which audio information has been converted into the form of characters and symbols.

[0404] Translation is the process of replacing words in one language with words in another while preserving their meaning.

[0405] A "summary" is a way of simplifying a vast amount of information and extracting the main points and content.

[0406] "Challenges" refer to problems that need to be solved or themes that need to be addressed.

[0407] An "action item" is a list of specific actions that should be taken to achieve a certain goal.

[0408] "User" refers to an individual or group that uses this system or service.

[0409] "Noise reduction" is the process of removing unwanted sounds and background noise from the target signal.

[0410] The "speaker" is the person who is actually speaking in a conversation or audio information.

[0411] "Emotional state" refers to a temporary state of a person's emotions or mood.

[0412] "Visualization" is the process of making information more understandable by visualizing it using images, infographics, and other visual aids.

[0413] To implement this invention, first, the user acquires voice information using a terminal at the start of a meeting or conversation. The voice is collected through the terminal's microphone. The acquired voice information is transmitted in real time to a server in the cloud. The server uses a speech recognition engine to convert the voice information into text information. This process uses speech recognition technology such as Google Speech-to-Text.

[0414] The server translates the converted text information into multiple specified languages ​​using tools such as Google Translate. It also uses a sentiment analysis engine, such as IBM Watson Tone Analyzer, to identify the emotional state of each participant from the text information. This visualizes the emotional information for the user, helping them understand the context of meetings and conversations.

[0415] Furthermore, the server utilizes natural language processing tools such as spaCy and NLTK to generate a summary from the translated text information. This summary includes key points and action items from the meeting. The summary results are also automatically extracted as issues and action items, notified to the user, and displayed on the screen.

[0416] As a concrete example, if a city hall holds a public briefing for a multinational population, this system can be used to provide real-time meeting minutes and sentiment analysis information in multiple languages. This allows for the collection of feedback that takes residents' feelings into account, enabling better service improvements.

[0417] An example of a prompt is, "Use the meeting audio data to perform multilingual translation and sentiment analysis, and visualize meeting minutes and sentiment states in real time." By using this prompt, the system initiates the necessary processing and supports smooth meetings and discussions.

[0418] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0419] Step 1:

[0420] The user uses the device's microphone to capture audio information from meetings and conversations. This captured audio data is sent to the server in real time. The input is audio data, and the output is the data sent to the server. This process prepares the system for recording the content of conversations sequentially.

[0421] Step 2:

[0422] The server passes the received audio data to a speech recognition engine, which converts the audio into text. The input is audio data on the server, and the output is text data. Speech-to-text conversion is achieved by processing the data using speech recognition technologies such as Google Speech-to-Text.

[0423] Step 3:

[0424] The server passes the converted text information to a translation engine, which then translates it into the specified multiple languages. The input is the converted text information, and the output is multilingual text information. The translation process is performed using the Google Translate API. This operation makes it possible to share information with participants who speak different languages.

[0425] Step 4:

[0426] The server passes the translated text information to the sentiment analysis engine to identify each participant's emotional state. The input is the translated text information, and the output is the result of the emotional state analysis. Sentiment analysis techniques such as IBM Watson Tone Analyzer are used to extract emotional information. This clarifies the participants' emotional responses.

[0427] Step 5:

[0428] The server analyzes translated text information using natural language processing tools and generates a summary. The input is translated text information, and the output is summary information. Using tools like spaCy and NLTK, the text is analyzed to extract the main points of conversations and meetings. This process presents important information concisely.

[0429] Step 6:

[0430] The server automatically extracts issues and action items from the generated summary information and notifies the user. The input is summary information, and the output is a list of issues and action items. The program automatically extracts this information using conditional branching and pattern recognition, and displays it on the terminal. This process clarifies the actions needed after the meeting.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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".

[0447] This invention is a voice translation meeting minutes generation system that enables efficient information management of meetings and important conversations. This system allows users to acquire information in real time during meetings and facilitates information sharing in multiple languages.

[0448] First, the user starts a meeting through their device. The device's microphone captures audio data and sends it to the server. As soon as the server receives the audio data, it converts it into text data using a highly accurate speech recognition engine. This conversion ensures that every word is accurately transcribed into text.

[0449] The converted text data is passed to the translation engine on the server. The server then translates the text into the specified language. Even when users speak different languages, the translated meeting minutes ensure that all participants understand the same information.

[0450] Furthermore, the server automatically generates a summary from the translated text. This summary extracts the key points to grasp the overall flow of the meeting, helping users quickly review the meeting content.

[0451] The server also picks out issues and action items from the summary information and automatically generates them in list format. This list clarifies the next steps to be addressed in the meeting and helps users manage tasks efficiently.

[0452] This information is displayed as a notification on the user's device. Based on this, the user follows up on tasks and shares information with collaborators as needed. This clarifies important decisions made in meetings and the next steps, ensuring smooth project progress.

[0453] As a concrete example, in international conferences of multinational corporations, this system allows participants speaking different languages ​​to understand the meeting minutes in real time. This enables faster decision-making and more efficient information sharing. Furthermore, because the system automatically extracts issues and actions, delays and human errors in operations can be minimized.

[0454] This invention makes it possible to shorten meeting times, maintain the accuracy of information, and manage projects across multiple languages.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] The user inputs the meeting audio using the device's microphone. The device then begins to acquire this audio data as a digital signal in real time.

[0458] Step 2:

[0459] The terminal appropriately compresses the acquired digital audio data and sends it to the server using a protocol that minimizes latency.

[0460] Step 3:

[0461] The server inputs the received audio data into the speech recognition engine. This engine uses advanced algorithms to convert the audio into text data. By removing noise and enabling speaker identification, it achieves highly accurate text conversion.

[0462] Step 4:

[0463] The server formats the generated text data, correcting grammatical errors and redundancies. The formatted data is stored in a database and made accessible later.

[0464] Step 5:

[0465] The server passes the formatted text data to the translation engine, which then performs the translation process for the specified languages. This translation accurately reproduces the content of the meeting in other languages ​​while preserving the original nuances.

[0466] Step 6:

[0467] The server generates a summary from the translated text data. Using natural language processing, it extracts key keywords and points and compiles a concise summary of the meeting.

[0468] Step 7:

[0469] The server then extracts issues and action items from the summary information and automatically creates them in list format. This list is then ready to be used in conjunction with the task management system.

[0470] Step 8:

[0471] The terminal receives summaries, translated texts, and task lists sent from the server and notifies the user. The user uses this information to review the meeting content and determine the next steps.

[0472] Step 9:

[0473] Users proceed with follow-up tasks based on the generated action list via their devices. By checking the progress of tasks and sharing information with team members, they facilitate the implementation of decisions made in meetings.

[0474] (Example 1)

[0475] 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."

[0476] In today's business environment, meetings frequently used by multinational corporations and global teams require rapid and accurate information transfer among participants who speak different languages. Furthermore, post-meeting minutes and the clarification of next steps are time-consuming and prone to human error. There is a need to solve these problems and provide a system that efficiently manages and shares information in multiple languages.

[0477] 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.

[0478] In this invention, the server includes means for acquiring audio information, means for converting the audio information into document data, and means for converting the document data into multiple different languages. This enables all participants using different languages ​​to quickly and accurately understand the meeting content and grasp important discussions and conclusions in real time.

[0479] "Audio information" refers to data of human speech and sounds emitted during meetings and other similar events.

[0480] "Document data" refers to text-based data that represents audio information using characters.

[0481] "Conversion" refers to the process of changing data from one format to another. In this context, it refers to converting audio information into document data or converting document data into another language.

[0482] "Key points" refer to the main content of a meeting, such as particularly noteworthy discussions or decisions.

[0483] "Work details" refers to the action plan decided at the meeting and the specific tasks based on it.

[0484] "Action guidelines" refer to instructions or policies that should be implemented based on the outcome of a meeting.

[0485] "Users" refer to people who use this system to participate in meetings or receive information.

[0486] This invention is a speech translation meeting minutes generation system for efficiently managing information in multilingual meetings. To implement this system, terminals, servers, and network elements connecting them are used.

[0487] The user initiates a meeting using a terminal. This terminal is equipped with a microphone and is responsible for capturing audio information during the meeting. The captured audio information is transmitted from the terminal to the server via the internet. To ensure data security, it is appropriate to use the SSL / TLS protocol for communication.

[0488] The server converts the received audio information into document data using an advanced speech recognition engine. Specific speech recognition engines available include the Google Speech-to-Text API and Microsoft Azure Speech Service. This conversion ensures that every word spoken is accurately transcribed into text.

[0489] The obtained document data is then passed to a translation engine. Using the Google Translate API or DeepL API, rapid and accurate multilingual translation is performed. This ensures that participants speaking different languages ​​can obtain consistent information.

[0490] Next, the server uses the translated document data to apply natural language processing techniques to summarize the key points of the meeting. Generative AI models such as OpenAI's GPT model are used for summary generation, efficiently extracting the essential points of the meeting and enabling quick information comprehension.

[0491] Furthermore, the server extracts work content and action guidelines from this summary. It utilizes machine learning algorithms to effectively identify tasks and instructions from the document data.

[0492] After the information is processed, the server sends it to the terminal, making it available to the user. Based on the information displayed on their terminal, the user can efficiently review meeting content and share information with other participants. This system significantly improves the smooth running of meetings and the efficiency of project management.

[0493] A concrete example of using this system is an international conference where multiple languages ​​are spoken. Meeting minutes and summaries, automatically translated via the server, allow all participants to quickly grasp the key points of the meeting and make efficient decisions.

[0494] Example of a prompt:

[0495] "Please record today's meeting and create minutes and summaries translated into English, French, and Chinese. Next, please list the identified issues and action plans."

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] The user starts a meeting on their device. At this time, the device's microphone acquires audio information from the meeting in real time. The input is an audio signal, and the output is digitized audio data. The device temporarily stores the acquired audio data.

[0499] Step 2:

[0500] The terminal sends the acquired audio data to the server. Here, the terminal encrypts the audio data using the SSL / TLS protocol and sends it to the server over the internet. The input is digital audio data, and the output is secure data transmission to the server.

[0501] Step 3:

[0502] The server inputs the received audio data into the speech recognition engine. Specifically, the Google Speech-to-Text API is used for speech recognition. The input is digital audio data, and the data is processed to output document data. This output is a string representation of the meeting's spoken content.

[0503] Step 4:

[0504] The server passes document data to the translation engine, which then translates it into the specified language. It uses the DeepL API to achieve highly accurate translations. The input is document data, and the output is translated document data after data transformation.

[0505] Step 5:

[0506] The server processes translated document data and summarizes key meeting points. It automatically generates summaries using OpenAI's GPT model. The input is translated document data, and the output is a condensed meeting summary.

[0507] Step 6:

[0508] The server automatically extracts action plans and work instructions from the meeting summary. Here, a machine learning algorithm identifies tasks and directives from the summary. The input is the summary data, and the output is the extracted task list.

[0509] Step 7:

[0510] The server sends the generated translated documents, meeting summaries, and action plan lists to the terminal. The input is this various data, and the output is the distribution of information usable by the user. The terminal notifies the user of the information and displays it on the screen, facilitating post-meeting information access.

[0511] (Application Example 1)

[0512] 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."

[0513] To facilitate information sharing and rapid decision-making among multinational engineers in data centers, it is essential to translate meeting content into multiple languages ​​in real time and to quickly and accurately transmit critical information. In this context, there is a growing need for a system that efficiently manages meeting content and immediately extracts issues and solutions. Therefore, a method is needed to deepen understanding among engineers who speak different languages ​​and to quickly implement countermeasures.

[0514] 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.

[0515] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, means for translating text information into different languages, means for generating a summary from the translated text information, means for automatically extracting problems and countermeasures from the summary, means for informing and displaying the summary, problems, and countermeasures to the user, and means for enabling use in monitoring meetings in a data center. This enables rapid information transmission between different languages ​​and immediate problem resolution.

[0516] "Means for acquiring audio information" refers to devices or technologies for collecting audio emitted from speakers or sound sources.

[0517] "Means of converting to text information" refers to technologies or software that convert audio information into text format through digital processing.

[0518] "Means of translation into different languages" refers to technologies or systems for performing the process of accurately converting textual information written in one language into another language.

[0519] "Methods for generating summaries" refer to techniques that extract important information and key points from long texts and reconstruct that information in a short, condensed form.

[0520] "Methods for automatically extracting problems and countermeasures" refers to a process in which the system independently identifies and lists the issues and future countermeasures discussed within the summary.

[0521] "Means of informing and displaying to the user" refers to devices or interfaces that notify the user of extracted information and display it on a screen or device.

[0522] "Means to enable use in monitoring meetings in data centers" refers to a process that includes technologies and preset settings for effectively utilizing a meeting system in a data center environment.

[0523] The system that realizes this invention includes a mechanism that processes audio information in real time, translates it into different languages, generates summaries, and improves the efficiency of meetings in data centers.

[0524] The server acquires audio information from the terminals during meetings and converts that audio into text. Machine learning frameworks such as TensorFlow are used for speech recognition to achieve highly accurate text conversion. This converted text information is then translated into multiple languages ​​using the Google Translate API.

[0525] From the translated text information, the server generates a meeting summary using a natural language processing model such as BERT. From the summarized information, it automatically extracts problems and proposed solutions, and lists them.

[0526] The user's device immediately displays a notification containing a summary, the problem, and the suggested solutions. This process enables rapid information sharing and collaborative problem-solving in monitoring meetings involving engineers from diverse cultural backgrounds.

[0527] As a concrete example, when a network failure occurs at a data center, engineers can use this system to hold an emergency meeting. The content of the discussion is translated and summarized in multiple languages ​​in real time and displayed simultaneously on each engineer's terminal, allowing the team to work together to develop a response plan.

[0528] An example of a prompt message could be: "Collect meeting audio in real time, immediately translate it into multiple languages, summarize the key points, and then display it as a notification to the technicians so they can use it for emergency response."

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] The user's device acquires meeting audio information in real time from the microphone. The audio information is transmitted to the server in digital format. The input is raw audio data, and the output is digitized audio data.

[0532] Step 2:

[0533] The server converts received audio data into text information using a speech recognition engine based on TensorFlow. The input is digitized audio data, and the output is text information. This process analyzes the audio waveform and converts the speaker's utterance into text data.

[0534] Step 3:

[0535] The server uses the Google Translate API to translate text information into multiple specified languages. The input is text information, and the output is the translated string. This step ensures that information is shared in a way that is understandable to all participants using different languages.

[0536] Step 4:

[0537] The server generates a summary using the BERT model from translated text information. The input is the translated string, and the output is the summarized text. This model extracts the key points from a meeting and shortens the content.

[0538] Step 5:

[0539] The server automatically extracts problems and solutions from the summary and organizes them as a list. The input is the summarized text, and the output is a list of problems and solutions. This process uses natural language processing technology to clarify the core points of the meeting.

[0540] Step 6:

[0541] The user's terminal immediately displays a summary, problem, and countermeasures sent from the server as a notification on the screen. The input is the notification information from the server, and the output is the display on the terminal screen. In this step, technicians can immediately review the information and begin taking the necessary actions.

[0542] 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.

[0543] This invention provides a system that efficiently processes audio data from meetings and conversations, enabling multilingual translation and integration of emotional information. This system maximizes the effectiveness of meetings by generating useful meeting minutes from the audio data and further analyzing the emotional states of participants.

[0544] Users initiate a meeting through their terminal and transmit audio data using the microphone. This audio is acquired in real time by the terminal and sent to the server. The audio data received by the server is converted into text data by a speech recognition engine. During the conversion process, a noise reduction module operates to improve the quality of the audio signal.

[0545] This text data is further translated into multiple languages ​​specified by a translation engine on the server. The translated data can then be easily shared at international conferences, thus expanding the scope of the conference through multilingual support.

[0546] The server further analyzes the audio data using an emotion engine to identify each participant's emotional state. This allows the server to understand participants' emotional responses during the meeting and respond accordingly.

[0547] The generated text data is summarized using natural language processing techniques to extract the key points of the meeting. The summary facilitates smooth communication among participants and helps them grasp the important points.

[0548] The server also automatically extracts issues and action items from the summary and shares them with the user. This list helps participants clarify what actions they need to take next and efficiently plan their post-meeting schedule.

[0549] As a concrete example, using this system in meetings for international projects allows participants who speak different languages ​​to not only obtain the same information in real time, but also to visually understand each individual's emotional state. This enables appropriate responses when discussions become heated or when understanding difficulties arise, and facilitates smoother decision-making regarding project direction.

[0550] By implementing this system, meeting times can be significantly reduced while improving the accuracy of information and mutual understanding. Meeting minutes that include emotional information support more sophisticated decision-making that takes human factors into account.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] The user starts a meeting and inputs audio data using the device's microphone. The device converts this audio data into a digital signal in real time and prepares to send it to the server.

[0554] Step 2:

[0555] The terminal compresses the audio data while performing noise reduction before sending it to the server. This improves data transfer efficiency while maintaining audio clarity.

[0556] Step 3:

[0557] The server inputs the received audio data into the speech recognition engine. The engine analyzes this data and converts it into highly accurate text data.

[0558] Step 4:

[0559] The server passes the text data to the emotion engine, which analyzes the intonation and speed of the speech to infer the participant's emotional state. Based on this analysis, it generates text data that includes emotional nuances.

[0560] Step 5:

[0561] The server simultaneously passes the text data to the translation engine, which translates it into the specified language. This enables real-time information sharing even in a multilingual environment.

[0562] Step 6:

[0563] The server passes the translated text data through a summarization engine, which uses natural language processing to extract key points. By shortening the summary, it enables quick understanding of the main points of the meeting.

[0564] Step 7:

[0565] The server extracts issues and action items from the generated summary information and automatically creates a list. These action items facilitate follow-up after meetings.

[0566] Step 8:

[0567] The terminal receives summaries, translation results, sentiment analysis results, and task lists sent from the server. The user reviews this information on the terminal to understand the overall picture of the meeting and the sentiments of the participants.

[0568] Step 9:

[0569] Users execute tasks and follow up based on action lists generated through their devices. This allows for the quick and reliable implementation of meeting conclusions and next steps.

[0570] (Example 2)

[0571] 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."

[0572] In modern international conferences and dialogues, it is essential for multilingual participants to share information accurately and in real time, and to communicate smoothly. However, in addition to multilingual translation, it is also necessary to consider the emotional reactions of participants, and there is a lack of technology to efficiently handle this. As a result, the effectiveness of meetings may not be fully realized, and problems may arise in important decision-making.

[0573] 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.

[0574] In this invention, the server includes means for acquiring audio information, means for converting the audio information into text information, and means for translating the text information into multiple different languages. This enables participants to understand information in multiple languages ​​in real time. The server also includes means for generating a meeting summary from the translated text information, means for automatically extracting issues and action items from the summary, and means for analyzing the audio information to identify the emotional state of the participants. This maximizes the effectiveness of the meeting and enables smooth important decision-making.

[0575] "Audio information" refers to data obtained by acquiring and recording conversations and voices as digital signals.

[0576] "Textual information" refers to data in text format that has been converted from audio information, and is information that humans can visually recognize.

[0577] Translation is the process of converting written information in one language into another language, facilitating communication between multiple languages.

[0578] "Summary generation" is the process of extracting key points and information from a large amount of textual data and presenting it in a concise format.

[0579] "Identifying issues and action items" is the process of identifying key issues and next steps from summarized information, thereby clarifying the actions to be taken after the meeting.

[0580] "Emotional state" refers to the result of evaluating participants' emotional responses and psychological state based on audio information.

[0581] "Visualization" is the process of visually representing extracted information and analysis results, and presenting them in a way that is easy for participants to understand.

[0582] This invention describes a system that efficiently processes audio information, enabling multilingual translation and sentiment analysis. First, the user starts a meeting using a terminal. A highly sensitive microphone is connected to the terminal, which records the user's speech as audio information in real time. This audio information is collected as a digital signal, works in conjunction with a noise filtering module, and is transmitted to a server as high-precision audio data.

[0583] The server converts received audio information into text using a speech recognition engine. At this stage, a model utilizing deep learning technology is used to improve the accuracy of speech recognition. The converted text information is then translated into the specified languages ​​by a multilingual translation engine within the server. This translation process employs natural language processing technology to ensure fast and accurate translation.

[0584] The translated text information is then passed to a summarization module to create a summary of the meeting content. This summary information is processed to highlight key points. The server also drives an emotion analysis engine by analyzing the intonation, speed, and volume of the speech to visualize the emotional state of each participant.

[0585] Furthermore, the system automatically extracts issues and action items from the generated summary and notifies the user of this information. As a result, each participant can clearly understand their next steps, making it easier to plan for the day after the meeting.

[0586] As a concrete example, consider the case where this system is adopted in an international project. Participants who speak different languages ​​will be able to understand information simultaneously, and adjustments as needed will be made efficiently. The introduction of this system will shorten meeting times and promote accuracy and mutual understanding of information.

[0587] An example of a prompt might be, "Please provide an overview of the meeting minutes generation system using real-time translation and sentiment analysis for international conferences." This prompt allows users to immediately obtain specific and actionable information that the system can provide.

[0588] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0589] Step 1:

[0590] The user starts a meeting using the terminal. The terminal acquires audio information through the microphone and instantly converts that data into a digital signal. The audio data is acquired as input by the terminal, and after audio signal processing, it generates clean audio data with noise removed as output.

[0591] Step 2:

[0592] The terminal sends the acquired clean audio data to the server via a security protocol. The audio data arrives at the server as input, and its integrity is verified. The server receives this data and prepares for the next process.

[0593] Step 3:

[0594] The server passes the received audio data to the speech recognition engine, which processes it to convert it into text. The input here is clean audio data, and the output is accurately transcribed text. Specifically, a deep learning model analyzes the audio and converts it into text format.

[0595] Step 4:

[0596] The server inputs textual information into a multilingual translation engine, which translates it in real time into multiple specified languages. The input is textual information, and the output is translated text in multiple languages. A machine translation algorithm generates the appropriate translation based on the context.

[0597] Step 5:

[0598] The server sends the translated text information to a summarization engine to create a meeting summary. The input is a set of translated texts, and the output is a concise and easy-to-understand summary. In this process, important topics are extracted through natural language processing.

[0599] Step 6:

[0600] The server then inputs the audio data into an emotion analysis engine to identify the participant's emotional state. The input is audio data, and the output is the analysis result indicating the emotional state. Here, the intonation and pitch of the voice are analyzed to determine the emotion.

[0601] Step 7:

[0602] The server notifies the user of the generated summary, issues, and action items. Input consists of the summary text and sentiment analysis results, while output is information displayed through the user interface. This allows the user to easily grasp the overall picture of the meeting and prepare for subsequent actions.

[0603] (Application Example 2)

[0604] 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."

[0605] In multilingual meetings and discussions, it is difficult for participants to smoothly understand information and appropriately grasp emotional responses. Traditional technologies handle translation, minute-taking, and sentiment analysis separately, lacking integrated support. As a result, efficient and smooth communication is hindered in international conferences and multicultural societies.

[0606] 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.

[0607] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, and means for translating into multiple different languages. This enables real-time information sharing and visualization of emotions even in a multilingual environment.

[0608] "Audio information" refers to data that represents sounds and voices as digital or analog signals.

[0609] "Text information" refers to data in which audio information has been converted into the form of characters and symbols.

[0610] Translation is the process of replacing words in one language with words in another while preserving their meaning.

[0611] A "summary" is a way of simplifying a vast amount of information and extracting the main points and content.

[0612] "Challenges" refer to problems that need to be solved or themes that need to be addressed.

[0613] An "action item" is a list of specific actions that should be taken to achieve a certain goal.

[0614] "User" refers to an individual or group that uses this system or service.

[0615] "Noise reduction" is the process of removing unwanted sounds and background noise from the target signal.

[0616] The "speaker" is the person who is actually speaking in a conversation or audio information.

[0617] "Emotional state" refers to a temporary state of a person's emotions or mood.

[0618] "Visualization" is the process of making information more understandable by visualizing it using images, infographics, and other visual aids.

[0619] To implement this invention, first, the user acquires voice information using a terminal at the start of a meeting or conversation. The voice is collected through the terminal's microphone. The acquired voice information is transmitted in real time to a server in the cloud. The server uses a speech recognition engine to convert the voice information into text information. This process uses speech recognition technology such as Google Speech-to-Text.

[0620] The server translates the converted text information into multiple specified languages ​​using tools such as Google Translate. It also uses a sentiment analysis engine, such as IBM Watson Tone Analyzer, to identify the emotional state of each participant from the text information. This visualizes the emotional information for the user, helping them understand the context of meetings and conversations.

[0621] Furthermore, the server utilizes natural language processing tools such as spaCy and NLTK to generate a summary from the translated text information. This summary includes key points and action items from the meeting. The summary results are also automatically extracted as issues and action items, notified to the user, and displayed on the screen.

[0622] As a concrete example, if a city hall holds a public briefing for a multinational population, this system can be used to provide real-time meeting minutes and sentiment analysis information in multiple languages. This allows for the collection of feedback that takes residents' feelings into account, enabling better service improvements.

[0623] An example of a prompt is, "Use the meeting audio data to perform multilingual translation and sentiment analysis, and visualize meeting minutes and sentiment states in real time." By using this prompt, the system initiates the necessary processing and supports smooth meetings and discussions.

[0624] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0625] Step 1:

[0626] The user uses the device's microphone to capture audio information from meetings and conversations. This captured audio data is sent to the server in real time. The input is audio data, and the output is the data sent to the server. This process prepares the system for recording the content of conversations sequentially.

[0627] Step 2:

[0628] The server passes the received audio data to a speech recognition engine, which converts the audio into text. The input is audio data on the server, and the output is text data. Speech-to-text conversion is achieved by processing the data using speech recognition technologies such as Google Speech-to-Text.

[0629] Step 3:

[0630] The server passes the converted text information to a translation engine, which then translates it into the specified multiple languages. The input is the converted text information, and the output is multilingual text information. The translation process is performed using the Google Translate API. This operation makes it possible to share information with participants who speak different languages.

[0631] Step 4:

[0632] The server passes the translated text information to the sentiment analysis engine to identify each participant's emotional state. The input is the translated text information, and the output is the result of the emotional state analysis. Sentiment analysis techniques such as IBM Watson Tone Analyzer are used to extract emotional information. This clarifies the participants' emotional responses.

[0633] Step 5:

[0634] The server analyzes translated text information using natural language processing tools and generates a summary. The input is translated text information, and the output is summary information. Using tools like spaCy and NLTK, the text is analyzed to extract the main points of conversations and meetings. This process presents important information concisely.

[0635] Step 6:

[0636] The server automatically extracts issues and action items from the generated summary information and notifies the user. The input is summary information, and the output is a list of issues and action items. The program automatically extracts this information using conditional branching and pattern recognition, and displays it on the terminal. This process clarifies the actions needed after the meeting.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] [Fourth Embodiment]

[0641] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0642] 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.

[0643] 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).

[0644] 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.

[0645] 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.

[0646] 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).

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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".

[0654] This invention is a voice translation meeting minutes generation system that enables efficient information management of meetings and important conversations. This system allows users to acquire information in real time during meetings and facilitates information sharing in multiple languages.

[0655] First, the user starts a meeting through their device. The device's microphone captures audio data and sends it to the server. As soon as the server receives the audio data, it converts it into text data using a highly accurate speech recognition engine. This conversion ensures that every word is accurately transcribed into text.

[0656] The converted text data is passed to the translation engine on the server. The server then translates the text into the specified language. Even when users speak different languages, the translated meeting minutes ensure that all participants understand the same information.

[0657] Furthermore, the server automatically generates a summary from the translated text. This summary extracts the key points to grasp the overall flow of the meeting, helping users quickly review the meeting content.

[0658] The server also picks out issues and action items from the summary information and automatically generates them in list format. This list clarifies the next steps to be addressed in the meeting and helps users manage tasks efficiently.

[0659] This information is displayed as a notification on the user's device. Based on this, the user follows up on tasks and shares information with collaborators as needed. This clarifies important decisions made in meetings and the next steps, ensuring smooth project progress.

[0660] As a concrete example, in international conferences of multinational corporations, this system allows participants speaking different languages ​​to understand the meeting minutes in real time. This enables faster decision-making and more efficient information sharing. Furthermore, because the system automatically extracts issues and actions, delays and human errors in operations can be minimized.

[0661] This invention makes it possible to shorten meeting times, maintain the accuracy of information, and manage projects across multiple languages.

[0662] The following describes the processing flow.

[0663] Step 1:

[0664] The user inputs the meeting audio using the device's microphone. The device then begins to acquire this audio data as a digital signal in real time.

[0665] Step 2:

[0666] The terminal appropriately compresses the acquired digital audio data and sends it to the server using a protocol that minimizes latency.

[0667] Step 3:

[0668] The server inputs the received audio data into the speech recognition engine. This engine uses advanced algorithms to convert the audio into text data. By removing noise and enabling speaker identification, it achieves highly accurate text conversion.

[0669] Step 4:

[0670] The server formats the generated text data, correcting grammatical errors and redundancies. The formatted data is stored in a database and made accessible later.

[0671] Step 5:

[0672] The server passes the formatted text data to the translation engine, which then performs the translation process for the specified languages. This translation accurately reproduces the content of the meeting in other languages ​​while preserving the original nuances.

[0673] Step 6:

[0674] The server generates a summary from the translated text data. Using natural language processing, it extracts key keywords and points and compiles a concise summary of the meeting.

[0675] Step 7:

[0676] The server then extracts issues and action items from the summary information and automatically creates them in list format. This list is then ready to be used in conjunction with the task management system.

[0677] Step 8:

[0678] The terminal receives summaries, translated texts, and task lists sent from the server and notifies the user. The user uses this information to review the meeting content and determine the next steps.

[0679] Step 9:

[0680] Users proceed with follow-up tasks based on the generated action list via their devices. By checking the progress of tasks and sharing information with team members, they facilitate the implementation of decisions made in meetings.

[0681] (Example 1)

[0682] 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".

[0683] In today's business environment, meetings frequently used by multinational corporations and global teams require rapid and accurate information transfer among participants who speak different languages. Furthermore, post-meeting minutes and the clarification of next steps are time-consuming and prone to human error. There is a need to solve these problems and provide a system that efficiently manages and shares information in multiple languages.

[0684] 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.

[0685] In this invention, the server includes means for acquiring audio information, means for converting the audio information into document data, and means for converting the document data into multiple different languages. This enables all participants using different languages ​​to quickly and accurately understand the meeting content and grasp important discussions and conclusions in real time.

[0686] "Audio information" refers to data of human speech and sounds emitted during meetings and other similar events.

[0687] "Document data" refers to text-based data that represents audio information using characters.

[0688] "Conversion" refers to the process of changing data from one format to another. In this context, it refers to converting audio information into document data or converting document data into another language.

[0689] "Key points" refer to the main content of a meeting, such as particularly noteworthy discussions or decisions.

[0690] "Work details" refers to the action plan decided at the meeting and the specific tasks based on it.

[0691] "Action guidelines" refer to instructions or policies that should be implemented based on the outcome of a meeting.

[0692] "Users" refer to people who use this system to participate in meetings or receive information.

[0693] This invention is a speech translation meeting minutes generation system for efficiently managing information in multilingual meetings. To implement this system, terminals, servers, and network elements connecting them are used.

[0694] The user initiates a meeting using a terminal. This terminal is equipped with a microphone and is responsible for capturing audio information during the meeting. The captured audio information is transmitted from the terminal to the server via the internet. To ensure data security, it is appropriate to use the SSL / TLS protocol for communication.

[0695] The server converts received audio information into document data using an advanced speech recognition engine. Specific speech recognition engines available include the Google Speech-to-Text API and Microsoft Azure Speech Service. This conversion ensures that every word spoken is accurately transcribed into text.

[0696] The obtained document data is then passed to a translation engine. Using the Google Translate API or DeepL API, rapid and accurate multilingual translation is performed. This ensures that participants speaking different languages ​​can obtain consistent information.

[0697] Next, the server uses the translated document data to apply natural language processing techniques to summarize the key points of the meeting. Generative AI models such as OpenAI's GPT model are used for summary generation, efficiently extracting the essential points of the meeting and enabling quick information comprehension.

[0698] Furthermore, the server extracts work content and action guidelines from this summary. It utilizes machine learning algorithms to effectively identify tasks and instructions from the document data.

[0699] After the information is processed, the server sends it to the terminal, making it available to the user. Based on the information displayed on their terminal, the user can efficiently review meeting content and share information with other participants. This system significantly improves the smooth running of meetings and the efficiency of project management.

[0700] A concrete example of using this system is an international conference where multiple languages ​​are spoken. Meeting minutes and summaries, automatically translated via the server, allow all participants to quickly grasp the key points of the meeting and make efficient decisions.

[0701] Example of a prompt:

[0702] "Please record today's meeting and create minutes and summaries translated into English, French, and Chinese. Next, please list the identified issues and action plans."

[0703] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0704] Step 1:

[0705] The user starts a meeting on their device. At this time, the device's microphone acquires audio information from the meeting in real time. The input is an audio signal, and the output is digitized audio data. The device temporarily stores the acquired audio data.

[0706] Step 2:

[0707] The terminal sends the acquired audio data to the server. Here, the terminal encrypts the audio data using the SSL / TLS protocol and sends it to the server over the internet. The input is digital audio data, and the output is secure data transmission to the server.

[0708] Step 3:

[0709] The server inputs the received audio data into the speech recognition engine. Specifically, the Google Speech-to-Text API is used for speech recognition. The input is digital audio data, and the data is processed to output document data. This output is a string representation of the meeting's spoken content.

[0710] Step 4:

[0711] The server passes document data to the translation engine, which then translates it into the specified language. It uses the DeepL API to achieve highly accurate translations. The input is document data, and the output is translated document data after data transformation.

[0712] Step 5:

[0713] The server processes translated document data and summarizes key meeting points. It automatically generates summaries using OpenAI's GPT model. The input is translated document data, and the output is a condensed meeting summary.

[0714] Step 6:

[0715] The server automatically extracts action plans and work instructions from the meeting summary. Here, a machine learning algorithm identifies tasks and directives from the summary. The input is the summary data, and the output is the extracted task list.

[0716] Step 7:

[0717] The server sends the generated translated documents, meeting summaries, and action plan lists to the terminal. The input is this various data, and the output is the distribution of information usable by the user. The terminal notifies the user of the information and displays it on the screen, facilitating post-meeting information access.

[0718] (Application Example 1)

[0719] 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".

[0720] To facilitate information sharing and rapid decision-making among multinational engineers in data centers, it is essential to translate meeting content into multiple languages ​​in real time and to quickly and accurately transmit critical information. In this context, there is a growing need for a system that efficiently manages meeting content and immediately extracts issues and solutions. Therefore, a method is needed to deepen understanding among engineers who speak different languages ​​and to quickly implement countermeasures.

[0721] 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.

[0722] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, means for translating text information into different languages, means for generating a summary from the translated text information, means for automatically extracting problems and countermeasures from the summary, means for informing and displaying the summary, problems, and countermeasures to the user, and means for enabling use in monitoring meetings in a data center. This enables rapid information transmission between different languages ​​and immediate problem resolution.

[0723] "Means for acquiring audio information" refers to devices or technologies for collecting audio emitted from speakers or sound sources.

[0724] "Means of converting to text information" refers to technologies or software that convert audio information into text format through digital processing.

[0725] "Means of translation into different languages" refers to technologies or systems for performing the process of accurately converting textual information written in one language into another language.

[0726] "Methods for generating summaries" refer to techniques that extract important information and key points from long texts and reconstruct that information in a short, condensed form.

[0727] "Methods for automatically extracting problems and countermeasures" refers to a process in which the system independently identifies and lists the issues and future countermeasures discussed within the summary.

[0728] "Means of informing and displaying to the user" refers to devices or interfaces that notify the user of extracted information and display it on a screen or device.

[0729] "Means to enable use in monitoring meetings in data centers" refers to a process that includes technologies and preset settings for effectively utilizing a meeting system in a data center environment.

[0730] The system that realizes this invention includes a mechanism that processes audio information in real time, translates it into different languages, generates summaries, and improves the efficiency of meetings in data centers.

[0731] The server acquires audio information from the terminals during meetings and converts that audio into text. Machine learning frameworks such as TensorFlow are used for speech recognition to achieve highly accurate text conversion. This converted text information is then translated into multiple languages ​​using the Google Translate API.

[0732] From the translated text information, the server generates a meeting summary using a natural language processing model such as BERT. From the summarized information, it automatically extracts problems and proposed solutions, and lists them.

[0733] The user's device immediately displays a notification containing a summary, the problem, and the suggested solutions. This process enables rapid information sharing and collaborative problem-solving in monitoring meetings involving engineers from diverse cultural backgrounds.

[0734] As a concrete example, when a network failure occurs at a data center, engineers can use this system to hold an emergency meeting. The content of the discussion is translated and summarized in multiple languages ​​in real time and displayed simultaneously on each engineer's terminal, allowing the team to work together to develop a response plan.

[0735] An example of a prompt message could be: "Collect meeting audio in real time, immediately translate it into multiple languages, summarize the key points, and then display it as a notification to the technicians so they can use it for emergency response."

[0736] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0737] Step 1:

[0738] The user's device acquires meeting audio information in real time from the microphone. The audio information is transmitted to the server in digital format. The input is raw audio data, and the output is digitized audio data.

[0739] Step 2:

[0740] The server converts received audio data into text information using a speech recognition engine based on TensorFlow. The input is digitized audio data, and the output is text information. This process analyzes the audio waveform and converts the speaker's utterance into text data.

[0741] Step 3:

[0742] The server uses the Google Translate API to translate text information into multiple specified languages. The input is text information, and the output is the translated string. This step ensures that information is shared in a way that is understandable to all participants using different languages.

[0743] Step 4:

[0744] The server generates a summary using the BERT model from translated text information. The input is the translated string, and the output is the summarized text. This model extracts the key points from a meeting and shortens the content.

[0745] Step 5:

[0746] The server automatically extracts problems and solutions from the summary and organizes them as a list. The input is the summarized text, and the output is a list of problems and solutions. This process uses natural language processing technology to clarify the core points of the meeting.

[0747] Step 6:

[0748] The user's terminal immediately displays a summary, problem, and countermeasures sent from the server as a notification on the screen. The input is the notification information from the server, and the output is the display on the terminal screen. In this step, technicians can immediately review the information and begin taking the necessary actions.

[0749] 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.

[0750] This invention provides a system that efficiently processes audio data from meetings and conversations, enabling multilingual translation and integration of emotional information. This system maximizes the effectiveness of meetings by generating useful meeting minutes from the audio data and further analyzing the emotional states of participants.

[0751] Users initiate a meeting through their terminal and transmit audio data using the microphone. This audio is acquired in real time by the terminal and sent to the server. The audio data received by the server is converted into text data by a speech recognition engine. During the conversion process, a noise reduction module operates to improve the quality of the audio signal.

[0752] This text data is further translated into multiple languages ​​specified by a translation engine on the server. The translated data can then be easily shared at international conferences, thus expanding the scope of the conference through multilingual support.

[0753] The server further analyzes the audio data using an emotion engine to identify each participant's emotional state. This allows the server to understand participants' emotional responses during the meeting and respond accordingly.

[0754] The generated text data is summarized using natural language processing techniques to extract the key points of the meeting. The summary facilitates smooth communication among participants and helps them grasp the important points.

[0755] The server also automatically extracts issues and action items from the summary and shares them with the user. This list helps participants clarify what actions they need to take next and efficiently plan their post-meeting schedule.

[0756] As a concrete example, using this system in meetings for international projects allows participants who speak different languages ​​to not only obtain the same information in real time, but also to visually understand each individual's emotional state. This enables appropriate responses when discussions become heated or when understanding difficulties arise, and facilitates smoother decision-making regarding project direction.

[0757] By implementing this system, meeting times can be significantly reduced while improving the accuracy of information and mutual understanding. Meeting minutes that include emotional information support more sophisticated decision-making that takes human factors into account.

[0758] The following describes the processing flow.

[0759] Step 1:

[0760] The user starts a meeting and inputs audio data using the device's microphone. The device converts this audio data into a digital signal in real time and prepares to send it to the server.

[0761] Step 2:

[0762] The terminal compresses the audio data while performing noise reduction before sending it to the server. This improves data transfer efficiency while maintaining audio clarity.

[0763] Step 3:

[0764] The server inputs the received audio data into the speech recognition engine. The engine analyzes this data and converts it into highly accurate text data.

[0765] Step 4:

[0766] The server passes the text data to the emotion engine, which analyzes the intonation and speed of the speech to infer the participant's emotional state. Based on this analysis, it generates text data that includes emotional nuances.

[0767] Step 5:

[0768] The server simultaneously passes the text data to the translation engine, which translates it into the specified language. This enables real-time information sharing even in a multilingual environment.

[0769] Step 6:

[0770] The server passes the translated text data through a summarization engine, which uses natural language processing to extract key points. By shortening the summary, it enables quick understanding of the main points of the meeting.

[0771] Step 7:

[0772] The server extracts issues and action items from the generated summary information and automatically creates a list. These action items facilitate follow-up after meetings.

[0773] Step 8:

[0774] The terminal receives summaries, translation results, sentiment analysis results, and task lists sent from the server. The user reviews this information on the terminal to understand the overall picture of the meeting and the sentiments of the participants.

[0775] Step 9:

[0776] Users execute tasks and follow up based on action lists generated through their devices. This allows for the quick and reliable implementation of meeting conclusions and next steps.

[0777] (Example 2)

[0778] 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".

[0779] In modern international conferences and dialogues, it is essential for multilingual participants to share information accurately and in real time, and to communicate smoothly. However, in addition to multilingual translation, it is also necessary to consider the emotional reactions of participants, and there is a lack of technology to efficiently handle this. As a result, the effectiveness of meetings may not be fully realized, and problems may arise in important decision-making.

[0780] 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.

[0781] In this invention, the server includes means for acquiring audio information, means for converting the audio information into text information, and means for translating the text information into multiple different languages. This enables participants to understand information in multiple languages ​​in real time. The server also includes means for generating a meeting summary from the translated text information, means for automatically extracting issues and action items from the summary, and means for analyzing the audio information to identify the emotional state of the participants. This maximizes the effectiveness of the meeting and enables smooth important decision-making.

[0782] "Audio information" refers to data obtained by acquiring and recording conversations and voices as digital signals.

[0783] "Textual information" refers to data in text format that has been converted from audio information, and is information that humans can visually recognize.

[0784] Translation is the process of converting written information in one language into another language, facilitating communication between multiple languages.

[0785] "Summary generation" is the process of extracting key points and information from a large amount of textual data and presenting it in a concise format.

[0786] "Identifying issues and action items" is the process of identifying key issues and next steps from summarized information, thereby clarifying the actions to be taken after the meeting.

[0787] "Emotional state" refers to the result of evaluating participants' emotional responses and psychological state based on audio information.

[0788] "Visualization" is the process of visually representing extracted information and analysis results, and presenting them in a way that is easy for participants to understand.

[0789] This invention describes a system that efficiently processes audio information, enabling multilingual translation and sentiment analysis. First, the user starts a meeting using a terminal. A highly sensitive microphone is connected to the terminal, which records the user's speech as audio information in real time. This audio information is collected as a digital signal, works in conjunction with a noise filtering module, and is transmitted to a server as high-precision audio data.

[0790] The server converts received audio information into text using a speech recognition engine. At this stage, a model utilizing deep learning technology is used to improve the accuracy of speech recognition. The converted text information is then translated into the specified languages ​​by a multilingual translation engine within the server. This translation process employs natural language processing technology to ensure fast and accurate translation.

[0791] The translated text information is then passed to a summarization module to create a summary of the meeting content. This summary information is processed to highlight key points. The server also drives an emotion analysis engine by analyzing the intonation, speed, and volume of the speech to visualize the emotional state of each participant.

[0792] Furthermore, the system automatically extracts issues and action items from the generated summary and notifies the user of this information. As a result, each participant can clearly understand their next steps, making it easier to plan for the day after the meeting.

[0793] As a concrete example, consider the case where this system is adopted in an international project. Participants who speak different languages ​​will be able to understand information simultaneously, and adjustments as needed will be made efficiently. The introduction of this system will shorten meeting times and promote accuracy and mutual understanding of information.

[0794] An example of a prompt might be, "Please provide an overview of the meeting minutes generation system using real-time translation and sentiment analysis for international conferences." This prompt allows users to immediately obtain specific and actionable information that the system can provide.

[0795] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0796] Step 1:

[0797] The user starts a meeting using the terminal. The terminal acquires audio information through the microphone and instantly converts that data into a digital signal. The audio data is acquired as input by the terminal, and after audio signal processing, it generates clean audio data with noise removed as output.

[0798] Step 2:

[0799] The terminal sends the acquired clean audio data to the server via a security protocol. The audio data arrives at the server as input, and its integrity is verified. The server receives this data and prepares for the next process.

[0800] Step 3:

[0801] The server passes the received audio data to the speech recognition engine, which processes it to convert it into text. The input here is clean audio data, and the output is accurately transcribed text. Specifically, a deep learning model analyzes the audio and converts it into text format.

[0802] Step 4:

[0803] The server inputs textual information into a multilingual translation engine, which translates it in real time into multiple specified languages. The input is textual information, and the output is translated text in multiple languages. A machine translation algorithm generates the appropriate translation based on the context.

[0804] Step 5:

[0805] The server sends the translated text information to a summarization engine to create a meeting summary. The input is a set of translated texts, and the output is a concise and easy-to-understand summary. In this process, important topics are extracted through natural language processing.

[0806] Step 6:

[0807] The server then inputs the audio data into an emotion analysis engine to identify the participant's emotional state. The input is audio data, and the output is the analysis result indicating the emotional state. Here, the intonation and pitch of the voice are analyzed to determine the emotion.

[0808] Step 7:

[0809] The server notifies the user of the generated summary, issues, and action items. Input consists of the summary text and sentiment analysis results, while output is information displayed through the user interface. This allows the user to easily grasp the overall picture of the meeting and prepare for subsequent actions.

[0810] (Application Example 2)

[0811] 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".

[0812] In multilingual meetings and discussions, it is difficult for participants to smoothly understand information and appropriately grasp emotional responses. Traditional technologies handle translation, minute-taking, and sentiment analysis separately, lacking integrated support. As a result, efficient and smooth communication is hindered in international conferences and multicultural societies.

[0813] 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.

[0814] In this invention, the server includes means for acquiring audio information, means for converting audio information into text information, and means for translating into multiple different languages. This enables real-time information sharing and visualization of emotions even in a multilingual environment.

[0815] "Audio information" refers to data that represents sounds and voices as digital or analog signals.

[0816] "Text information" refers to data in which audio information has been converted into the form of characters and symbols.

[0817] Translation is the process of replacing words in one language with words in another while preserving their meaning.

[0818] A "summary" is a way of simplifying a vast amount of information and extracting the main points and content.

[0819] "Challenges" refer to problems that need to be solved or themes that need to be addressed.

[0820] An "action item" is a list of specific actions that should be taken to achieve a certain goal.

[0821] "User" refers to an individual or group that uses this system or service.

[0822] "Noise reduction" is the process of removing unwanted sounds and background noise from the target signal.

[0823] The "speaker" is the person who is actually speaking in a conversation or audio information.

[0824] "Emotional state" refers to a temporary state of a person's emotions or mood.

[0825] "Visualization" is the process of making information more understandable by visualizing it using images, infographics, and other visual aids.

[0826] To implement this invention, first, the user acquires voice information using a terminal at the start of a meeting or conversation. The voice is collected through the terminal's microphone. The acquired voice information is transmitted in real time to a server in the cloud. The server uses a speech recognition engine to convert the voice information into text information. This process uses speech recognition technology such as Google Speech-to-Text.

[0827] The server translates the converted text information into multiple specified languages ​​using tools such as Google Translate. It also uses a sentiment analysis engine, such as IBM Watson Tone Analyzer, to identify the emotional state of each participant from the text information. This visualizes the emotional information for the user, helping them understand the context of meetings and conversations.

[0828] Furthermore, the server utilizes natural language processing tools such as spaCy and NLTK to generate a summary from the translated text information. This summary includes key points and action items from the meeting. The summary results are also automatically extracted as issues and action items, notified to the user, and displayed on the screen.

[0829] As a concrete example, if a city hall holds a public briefing for a multinational population, this system can be used to provide real-time meeting minutes and sentiment analysis information in multiple languages. This allows for the collection of feedback that takes residents' feelings into account, enabling better service improvements.

[0830] An example of a prompt is, "Use the meeting audio data to perform multilingual translation and sentiment analysis, and visualize meeting minutes and sentiment states in real time." By using this prompt, the system initiates the necessary processing and supports smooth meetings and discussions.

[0831] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0832] Step 1:

[0833] The user uses the device's microphone to capture audio information from meetings and conversations. This captured audio data is sent to the server in real time. The input is audio data, and the output is the data sent to the server. This process prepares the system for recording the content of conversations sequentially.

[0834] Step 2:

[0835] The server passes the received audio data to a speech recognition engine, which converts the audio into text. The input is audio data on the server, and the output is text data. Speech-to-text conversion is achieved by processing the data using speech recognition technologies such as Google Speech-to-Text.

[0836] Step 3:

[0837] The server passes the converted text information to a translation engine, which then translates it into the specified multiple languages. The input is the converted text information, and the output is multilingual text information. The translation process is performed using the Google Translate API. This operation makes it possible to share information with participants who speak different languages.

[0838] Step 4:

[0839] The server passes the translated text information to the sentiment analysis engine to identify each participant's emotional state. The input is the translated text information, and the output is the result of the emotional state analysis. Sentiment analysis techniques such as IBM Watson Tone Analyzer are used to extract emotional information. This clarifies the participants' emotional responses.

[0840] Step 5:

[0841] The server analyzes translated text information using natural language processing tools and generates a summary. The input is translated text information, and the output is summary information. Using tools like spaCy and NLTK, the text is analyzed to extract the main points of conversations and meetings. This process presents important information concisely.

[0842] Step 6:

[0843] The server automatically extracts issues and action items from the generated summary information and notifies the user. The input is summary information, and the output is a list of issues and action items. The program automatically extracts this information using conditional branching and pattern recognition, and displays it on the terminal. This process clarifies the actions needed after the meeting.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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."

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0865] The following is further disclosed regarding the embodiments described above.

[0866] (Claim 1)

[0867] Means for acquiring audio data,

[0868] Means for converting the aforementioned audio data into text data,

[0869] A means for translating the aforementioned text data into multiple different languages,

[0870] A means for generating a meeting summary from the translated text data,

[0871] A means for automatically extracting issues and action items from the aforementioned summary,

[0872] Means for notifying and displaying the aforementioned summary, issues, and action items to the user,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, further comprising means for removing noise from audio data.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising means for identifying the speaker from the aforementioned character data.

[0878] "Example 1"

[0879] (Claim 1)

[0880] Means for acquiring audio information,

[0881] Means for converting the aforementioned audio information into document data,

[0882] Means for converting the aforementioned document data into multiple different languages,

[0883] A means for generating key points of a meeting from the converted document data,

[0884] A means for automatically extracting work content and action guidelines from the aforementioned key points,

[0885] Means for notifying and displaying the aforementioned important points, work content, and guidelines for action to users,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, further comprising means for removing interfering sounds from audio information.

[0889] (Claim 3)

[0890] The system according to claim 1, further comprising means for identifying the speaker from the document data.

[0891] "Application Example 1"

[0892] (Claim 1)

[0893] Means for acquiring audio information,

[0894] Means for converting the aforementioned audio information into text information,

[0895] A means for translating the aforementioned textual information into multiple different languages,

[0896] A means for generating a meeting summary from the translated text information,

[0897] A means for automatically extracting problems and countermeasures from the above summary,

[0898] A means of informing and displaying the aforementioned summary, problems, and countermeasures to the user,

[0899] A means to enable its use in monitoring meetings in data centers,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising means for removing noise from audio information.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising means for identifying the speaker from the aforementioned textual information.

[0905] "Example 2 of combining an emotion engine"

[0906] (Claim 1)

[0907] Means for acquiring audio information,

[0908] Means for converting the aforementioned audio information into text information,

[0909] A means for translating the aforementioned textual information into multiple different languages,

[0910] A means for generating a meeting summary from the translated text information,

[0911] A means for automatically extracting issues and action items from the aforementioned summary,

[0912] A means for analyzing the aforementioned audio information to identify the emotional state of the participant,

[0913] A means for notifying and displaying the aforementioned summary, issues, behavioral items, and emotional state to the user,

[0914] A means for visualizing the emotional state generated through the aforementioned system,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, further comprising means for removing noise from audio information.

[0918] (Claim 3)

[0919] The system according to claim 1, further comprising means for identifying the speaker from the aforementioned textual information.

[0920] "Application example 2 when combining with an emotional engine"

[0921] (Claim 1)

[0922] Means for acquiring audio information,

[0923] Means for converting the aforementioned audio information into text information,

[0924] A means for translating the aforementioned text information into multiple different languages,

[0925] A means for generating a summary of the dialogue from the translated text information,

[0926] A means for automatically extracting issues and action items from the aforementioned summary,

[0927] Means for notifying and displaying the aforementioned summary, issues, and action items to the user,

[0928] A means of analyzing emotional states in dialogue,

[0929] A means for visualizing and presenting the analyzed emotional state to the user,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, further comprising means for removing noise from audio information.

[0933] (Claim 3)

[0934] The system according to claim 1, further comprising means for identifying the speaker from the aforementioned text information. [Explanation of symbols]

[0935] 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. Means for acquiring audio data, Means for converting the aforementioned audio data into text data, A means for translating the aforementioned text data into multiple different languages, A means for generating a meeting summary from the translated text data, A means for automatically extracting issues and action items from the aforementioned summary, Means for notifying and displaying the aforementioned summary, issues, and action items to the user, A system that includes this.

2. The system according to claim 1, further comprising means for removing noise from audio data.

3. The system according to claim 1, further comprising means for identifying the speaker from the aforementioned character data.

Images