system

Abstract

Provide a system. 【Solution means】 Means for acquiring an audio signal in real time using an audio acquisition unit, Means for converting the acquired audio signal into text data using speech recognition technology, Means for extracting important information from the text data using natural language processing technology, Means for automatically generating an information record based on the extracted important information, Means for automatically generating a follow-up task from the generated information record, Means for managing the progress of the follow-up task in cooperation with a task management system, Means for analyzing in real time the instruction information in the driving environment and reflecting it in an automatic control system, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern business environment, there is a demand for improving the efficiency of meetings and the accuracy of follow - up work. However, many companies struggle with manual minutes creation and task management during increasing meetings, and the accompanying information leakage and work duplication are reducing business efficiency. Therefore, there is a need for a system that can automatically generate accurate minutes in real - time during a meeting and enable reliable follow - up after the meeting.

Means for Solving the Problems

[0005] This invention provides a system that acquires meeting audio in real time using an audio acquisition unit and converts it into text data using speech recognition technology. Furthermore, it employs natural language processing technology to extract important information from the text data and automatically generates meeting minutes based on this information. Follow-up tasks are automatically generated from the generated meeting minutes, and the accuracy of follow-up is improved by managing the progress of tasks in conjunction with a task management tool. In addition, by automatically assigning follow-up tasks to responsible persons based on the extracted important information, appropriate information distribution and business efficiency are achieved. Furthermore, delays and incomplete tasks are identified based on task progress management information, and relevant parties are notified, thereby supporting the smooth operation of business.

[0006] A "sound acquisition unit" is a device or system for acquiring audio generated during a meeting in real time.

[0007] "Speech recognition technology" is a technology that converts acquired speech data into text data, and by using this technology, it becomes possible to treat speech as text information.

[0008] "Text data" refers to data expressed in character form, converted using speech recognition technology.

[0009] Natural language processing technology is a technique that analyzes the content of text data and extracts important information. It is particularly used to identify the main points and topics of a conversation.

[0010] Meeting minutes are documents that summarize what was said during a meeting and record important points and decisions.

[0011] A "follow-up task" is a series of action items required based on the results of a meeting, with the aim of putting into action the decisions made at the meeting.

[0012] A "task management tool" is software or a platform used to track and manage the progress of follow-up tasks.

[0013] "Progress management information" refers to data that shows how far a task has progressed, and serves as a standard for evaluating the status and achievement of a task.

[0014] "Notification" refers to the act of promptly informing stakeholders of important information, such as the progress or delay status of a task. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] 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 combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is an embodiment of an integrated system that acquires meeting audio in real time, converts that audio into text data, and automatically extracts and manages important information. Specifically, it operates as follows:

[0037] First, the user activates the system at the start of the meeting. The activated terminal captures audio during the meeting using its built-in voice acquisition function or an external microphone device. The captured audio is then converted into text data by the terminal using speech recognition technology. The speech recognition technology is designed to handle a wide variety of audio data, enabling accurate text conversion.

[0038] Next, the server receives the text data and applies natural language processing technology. This extracts the important agenda items and decisions made during the meeting, and automatically generates meeting minutes based on this information. These minutes are clearly organized and easy to understand, helping to quickly grasp the overall picture of the meeting. Furthermore, they include action items and next steps that were pointed out during the meeting.

[0039] Next, the generated meeting minutes are analyzed by the server, and follow-up tasks are automatically created. These tasks are assigned to designated personnel. Task assignment is carried out in conjunction with task management tools used within the organization, and is smoothly reflected through APIs such as those of project management systems.

[0040] The server has the functionality to track these tasks and constantly monitor their progress. Progress information is notified to the person in charge via the task management tool platform, allowing them to immediately check the completion status of tasks and the percentage of incomplete tasks. In this way, information leaks and overlooked tasks are prevented, contributing to improved work efficiency.

[0041] As a concrete example, if the implementation schedule for a new feature changes during a product development meeting, users are immediately listed as a critical issue. This information is then reflected in subsequent follow-up tasks and assigned to the relevant development team members, resulting in transparent and efficient project management.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user activates the AI ​​agent at the start of the meeting. The terminal that receives the activation command prepares to activate its audio acquisition unit in order to acquire meeting audio.

[0045] Step 2:

[0046] The terminal records audio data collected during the meeting via an audio acquisition unit. The recorded audio data is prepared in real time for speech recognition technology and processed quickly.

[0047] Step 3:

[0048] The device inputs recorded audio data into speech recognition technology and converts it into text data. The speech recognition results are optimized for high accuracy, and the converted text data is saved locally.

[0049] Step 4:

[0050] The server receives text data and analyzes it using natural language processing technology. Through this analysis, important meeting topics, speaker information, action items, and other relevant details are automatically extracted.

[0051] Step 5:

[0052] The server automatically generates meeting minutes based on the analysis results. The generated minutes are presented in a well-organized format, clearly indicating the key points and decisions of the meeting, and are prepared for easy sharing with relevant parties.

[0053] Step 6:

[0054] The server generates follow-up tasks from the meeting minutes. These tasks include action items decided at the meeting and incorporate necessary assignee information. This clearly identifies which tasks should be assigned to which individuals.

[0055] Step 7:

[0056] The server integrates task information into the task management tool. Tasks are registered via the management tool's API, and a system is in place to monitor progress in real time. In case of failure or delay, the system is configured to quickly notify relevant parties.

[0057] Step 8:

[0058] Users can check task progress through task management tools and take corrective actions as needed. This monitoring function is used to maximize work efficiency and productivity.

[0059] (Example 1)

[0060] 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."

[0061] Efficient management of audio information during meetings is essential to prevent overlooking important information and delaying tasks. In particular, the failure to accurately record important content after meetings and the resulting inadequate management of follow-up tasks can hinder project progress.

[0062] 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.

[0063] In this invention, the server includes means for acquiring meeting audio in real time using a receiving device, means for converting the acquired audio into text information using a speech recognition method, and means for extracting important information from the text information using natural language processing technology. This makes it possible to accurately record the key points of a meeting and to automatically generate and manage follow-up tasks.

[0064] A "receiving device" is a hardware or software system for acquiring audio during a meeting in real time.

[0065] A "speech recognition method" is a technical technique that analyzes acquired speech data and converts it into text information.

[0066] "Natural language processing technology" is a field of computer science that extracts and analyzes important information from text.

[0067] "Text information" refers to character information converted from audio data using speech recognition methods.

[0068] "Important information" refers to the topics and action items necessary for decision-making and follow-up during a meeting.

[0069] A "record document" is a document that is automatically generated based on extracted key information and summarizes the main points of a meeting.

[0070] A "tracking task" is an action item derived from the generated record document that is necessary for the progress of the work.

[0071] "Progress management techniques" are techniques for monitoring and appropriately managing the completion status and progress of tasks.

[0072] A "related party" is any person or entity that is directly responsible for or may be affected by the progress of the generated tracking task.

[0073] This invention is an integrated system for the efficient acquisition, conversion, analysis, and management of conference audio. Its embodiments are described in detail below.

[0074] The user activates the system when starting a meeting. This allows the terminal to capture audio in real time during the meeting using its built-in microphone or an external microphone device. While a standard audio capture device is used for audio acquisition, a high-sensitivity microphone with noise-canceling capabilities can reduce ambient noise and capture clear audio.

[0075] The acquired audio data is processed on the device and converted into text information using speech recognition software such as Google® Speech-to-Text API or Amazon Transcribe. This speech recognition analyzes the audio information and outputs it as text, thereby achieving text conversion.

[0076] The generated text information is then sent to a server, where important information is extracted using natural language processing techniques. For example, by utilizing SpaCy, a Python library, contextual analysis can be performed to extract agenda items and important decisions.

[0077] Based on the extracted key information, the server automatically generates a record document. This document clarifies the key points of the meeting and serves as an important resource for scheduling appointments and reviewing decisions made later.

[0078] Furthermore, the server creates tracking tasks from the generated record documents, which are then properly managed by a progress management system that integrates with progress tracking technology. By utilizing APIs such as Asana and Trello, the generated tasks are smoothly reflected in these progress management tools and assigned to the responsible parties.

[0079] In this way, the server can constantly monitor progress and notify relevant parties if there are delays or incomplete tasks.

[0080] As a concrete example, the prompt "Extract important decisions from the following meeting minutes and create action items" is entered into the AI. This automatically extracts the critical information and suggests the next steps. This makes it easier to manage meeting content and allows subsequent actions to proceed efficiently.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The user activates the system at the start of the meeting. This action puts the terminal into a state where it can acquire audio during the meeting. The input is the audio signal acquired through the microphone device, and this signal is converted into digital audio data by the audio capture system inside the terminal. The output is audio data in digital format.

[0084] Step 2:

[0085] The device passes the acquired digital audio data to speech recognition software. This software analyzes the audio data using APIs such as the Google Speech-to-Text API and outputs it as text. The input is digital audio data, and the output is converted text information. Specifically, the process involves analyzing the pattern of the sound wave signal and converting it into a language structure.

[0086] Step 3:

[0087] The server receives text information sent from the terminal and extracts important information using natural language processing techniques. The input is text data related to a meeting, and the output is important information including agenda items and decisions. Specifically, the process involves identifying nouns and verbs within the text and analyzing the context of the sentences related to them.

[0088] Step 4:

[0089] The server automatically generates record documents based on the extracted key information. The input is the key information obtained in step 3, and the output is a well-organized meeting minutes-style document. In this process, the information is logically structured and output in a format that is easy to use for project progress and decision-making.

[0090] Step 5:

[0091] The server automatically generates tracking tasks from the generated record documents. The input is the action items contained in the meeting minutes, and the output is a list of tracking tasks. Specifically, it is a procedure to document tasks based on the necessary actions and instructions, and register them in the management system.

[0092] Step 6:

[0093] The server integrates with progress management technology to reflect generated tasks in related systems. The input is a list of tracked tasks, and the output is the status of their implementation in task management tools. This operation includes sending information via API and assigning tasks to assigned personnel.

[0094] Step 7:

[0095] The server monitors task progress in real time and notifies relevant parties as needed. Input is task progress data, and output is notifications to relevant parties. This process includes the ability to measure the degree of task completion and immediately notify if non-completion is suspected.

[0096] (Application Example 1)

[0097] 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."

[0098] In modern times, the development of autonomous driving technology has created a demand for driver assistance in vehicles. Efficiently acquiring instructions and safety-related information within autonomous vehicles and processing it in real time is crucial for safe driving and operational optimization. This invention aims to acquire such instruction information as voice, rapidly analyze it, and reflect it in the system.

[0099] 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.

[0100] In this invention, the server includes means for acquiring audio signals in real time using an audio acquisition unit, means for converting the acquired audio signals into text data using speech recognition technology, and means for analyzing instruction information in the driving environment in real time and reflecting it in the automatic control system. This enables efficient analysis of instruction information within an autonomous vehicle, allowing for safe and rapid driving control.

[0101] A "voice acquisition unit" is a device or system for acquiring voice signals in real time.

[0102] "Speech recognition technology" is a technology that converts acquired speech signals into text data.

[0103] "Natural language processing technology" is a technique for extracting and analyzing important information from text data.

[0104] "Information records" refer to documents or data that are automatically generated based on extracted important information.

[0105] A "follow-up task" is a subsequent task or instruction that is automatically generated from the generated information record.

[0106] A "task management system" is a system for monitoring and managing the progress of follow-up tasks.

[0107] "Driving environment" is a concept that refers to the surrounding conditions and circumstances while an autonomous vehicle is in motion.

[0108] "Instructional information" refers to commands and requests given verbally by drivers, passengers, etc.

[0109] An "automatic control system" is a system that automatically adjusts the vehicle's operation based on instruction information.

[0110] This system aims to effectively acquire and analyze instruction information within autonomous vehicles. The server uses a voice acquisition unit to acquire in-vehicle audio signals in real time. These acquired audio signals are then converted into text data using speech recognition technology.

[0111] The server applies natural language processing techniques to the converted text data to analyze important driving instructions. The instructions extracted through this analysis are then reflected in the automated control system in real time, ensuring proper vehicle control.

[0112] Users can instruct the system to change destinations or update driving information through simple voice commands. This improves driving efficiency and safety. For example, if a passenger instructs the system to change destinations by voice, the instruction is analyzed as text data, and the navigation system is quickly updated.

[0113] An example of a prompt message for a generated AI model might be: "Design a system that analyzes voice commands while driving and immediately reflects changes in the destination." This prompt message specifically describes the system's function and serves as a guide for realizing the necessary information processing while driving.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The terminal uses an audio acquisition unit to acquire audio signals from passengers and drivers in real time. The input is an audio signal, and the output is raw audio data. This audio data is acquired at a constant sampling rate and converted to a digital format for subsequent processing.

[0117] Step 2:

[0118] The server converts the acquired audio data into text data using speech recognition technology. The input is the audio data from step 1, and the output is parseable text data. This process uses a generative AI model in the speech recognition system to process the data to handle diverse pronunciations and noise.

[0119] Step 3:

[0120] The server analyzes the obtained text data using natural language processing technology and extracts the instruction information necessary for driving. The input is the text data from step 2, and the output is the instruction information. At this stage, keywords and context are analyzed from the text, and a generative AI model is used to evaluate the urgency and priority of the instructions.

[0121] Step 4:

[0122] The server reflects the extracted instruction information into the automatic control system and adjusts the vehicle's driving control. The input is the instruction information from step 3, and the output is the control command. In this process, the output is generated in a format compatible with the control system and immediately applied to the vehicle's operation.

[0123] Step 5:

[0124] The user can review system feedback as needed and provide additional instructions via voice. The input is the new voice instruction from the user, and the output is the voice data looped back to step 1 for reprocessing. This feedback loop allows for continuous optimization of the operating conditions.

[0125] 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.

[0126] This invention is a system that not only acquires meeting audio in real time and converts it into text data to extract important information, but also reads emotions from participants' voices and applies this information to the meeting recording and follow-up process. In this embodiment, the system operates as follows.

[0127] The user activates the system at the start of the meeting, and the terminal acquires the meeting audio in real time using the audio acquisition unit. The acquired audio data is converted into text data using speech recognition technology. This allows the content of the meeting to be quickly saved as text.

[0128] In addition, the server uses an emotion engine to analyze the user's emotions from the audio data. The emotion engine determines the participant's emotional state by analyzing the intonation, speed, and other parameters of the voice. The emotional information obtained here is incorporated into text data extracted using natural language processing techniques and reflected in the meeting minutes.

[0129] The server automatically generates meeting minutes with emotional information. In addition to the text data of what was said, these minutes record the emotional state at the time of the statement, which helps to understand the atmosphere of the meeting and the reactions of the participants.

[0130] Next, emotional information is also used to generate and prioritize follow-up tasks. Specifically, the server uses the user's emotional information to re-evaluate the urgency and importance of tasks and determine the need for follow-up. This automatically determines who should prioritize which tasks and assigns them to the appropriate personnel.

[0131] For example, if there is significant interest in feedback on a new product during a meeting, the server will use sentiment engine analysis of the participants to identify the high level of user interest in that product. As a result, it will prioritize tasks related to the new product, promptly notify those responsible, and support efficient project progress.

[0132] In this way, the system combines speech recognition and sentiment analysis to enhance meeting recording and subsequent business processes, enabling a dramatic improvement in corporate operational efficiency.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The user activates the system at the start of the meeting. This initiates the operation of the terminal, including the audio acquisition unit, and prepares it to acquire meeting audio in real time.

[0136] Step 2:

[0137] The terminal uses speech recognition technology to convert the audio collected from the meeting into text data. The audio data is then transcribed with high accuracy by the platform and immediately sent to the server.

[0138] Step 3:

[0139] The server applies natural language processing techniques to the received text data to extract the meeting summary and key points. During this process, the information is organized and prepared as the source data for the meeting record.

[0140] Step 4:

[0141] Simultaneously, the device uses an emotion engine to analyze the tone and pitch of the user's voice from the audio data and performs emotion queries. This identifies the emotional state behind each statement.

[0142] Step 5:

[0143] The server integrates the sentiment analysis results into the meeting minutes data. Sentimental information associated with each statement is added, making the reactions of each participant during the meeting clearer.

[0144] Step 6:

[0145] The server generates follow-up tasks using meeting minutes with sentiment information. Sentiment information influences the determination of task importance and priority, highlighting issues that require immediate attention from the user.

[0146] Step 7:

[0147] The server uses a task management tool to assign follow-up tasks to the appropriate personnel, and is configured to make tasks immediately visible. The system automatically optimizes the allocation based on each person's workload and interests.

[0148] Step 8:

[0149] After a meeting, users track the progress of their tasks through a task management tool. The system can evaluate their focus on priority tasks based on sentiment analysis, and revise countermeasures as needed.

[0150] (Example 2)

[0151] 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".

[0152] Modern business meetings involve the frequent exchange of large amounts of information, necessitating rapid and accurate recording of meeting content and follow-up based on participants' emotional states. However, traditional methods often involve manual transcription of speech and emotional analysis, which is time-consuming and labor-intensive, and results in inconsistent recording accuracy and follow-up quality. Therefore, it is crucial to achieve efficient meeting management and follow-up through automated speech conversion and the utilization of emotional information.

[0153] 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.

[0154] In this invention, the server includes means for acquiring meeting audio in real time using an acoustic acquisition device, means for converting the acquired audio into text data using speech recognition technology, and means for analyzing the emotional state of speakers from the audio data using emotion analysis technology. This makes it possible to automatically transcribe meeting audio information into text and quickly analyze the emotional state of participants. Furthermore, this information can be used to extract important information and automatically generate meeting minutes, and to automatically generate and prioritize follow-up tasks that reflect the emotional information. This leads to improved efficiency and quality of work.

[0155] An "acoustic acquisition device" is a device used to acquire sound as a digital signal in settings such as meetings.

[0156] "Voice recognition technology" is a technology that analyzes acquired voice data and automatically converts it into corresponding text data.

[0157] "Text data" refers to text information converted from speech, specifically a written record of the presentations given at a meeting.

[0158] "Emotional analysis technology" is a technology that analyzes voice data to determine the emotional state of the speaker.

[0159] "Meeting minutes" are documents that record the content of conversations during a meeting, including the emotional state of the participants at the time.

[0160] "Follow-up tasks" are the work or tasks that need to be done after a meeting, and are generated based on the meeting minutes.

[0161] A "business management device" is a device used to manage the progress and priorities of follow-up tasks and to inform relevant parties of the results.

[0162] This invention is a system that efficiently acquires audio information from meetings, transcribes it into text, and analyzes and records emotional information based on that text, thereby automatically generating and managing follow-up tasks.

[0163] The user activates the system at the start of the meeting. The hardware used is a terminal equipped with an audio acquisition device. The terminal acquires meeting audio in real time and converts it into text data using speech recognition technology. Software such as the Google Speech-to-Text API can be used for this speech recognition.

[0164] Next, the server uses emotion analysis technology to analyze the acquired audio data and determine the emotional state at the time of speaking. In this process, emotion analysis tools such as IBM Watson® Tone Analyzer are used to evaluate elements such as intonation and speed of speech and identify emotions.

[0165] The generated text data and emotional information are unified by the server and automatically compiled into meeting minutes. These minutes include detailed descriptions of what was said, along with the emotional state at the time, allowing for a clearer understanding of the participants' attitudes and reactions.

[0166] Furthermore, this sentiment information is also used to generate and prioritize follow-up tasks. Based on meeting minutes and sentiment states, the server evaluates the urgency and importance of tasks. This allows the task management system to assign tasks to the appropriate personnel, manage progress, and support an efficient post-meeting process.

[0167] For example, if a new service is discussed in a meeting and participants show high interest, the server can analyze their sentiment, prioritize related tasks, and quickly notify the appropriate person. This system allows companies to improve meeting productivity and prevent delays or inadequate follow-up.

[0168] An example of a prompt would be, "Please provide an overview of the follow-up tasks generated as a result of converting the meeting audio data to text and performing sentiment analysis."

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The user activates the system at the start of the meeting. Once activated, the system prepares to begin acquiring meeting audio. The input here is an acoustic acquisition device that receives the audio signal. The output is the real-time collection of meeting audio.

[0172] Step 2:

[0173] The terminal uses an acoustic acquisition device to capture conference audio in real time. In this step, the conference audio is converted into a digital signal for use in subsequent analysis steps. The input is continuous audio data from the acoustic acquisition device. The output is in the form of a digital audio signal, which is passed on to the next step.

[0174] Step 3:

[0175] The device uses speech recognition technology to convert acquired speech into text data. Specifically, it analyzes the speech signal using APIs such as the Google Speech-to-Text API and generates the corresponding text. The input is a digital speech signal, and the output is the spoken content as text data.

[0176] Step 4:

[0177] The server utilizes emotion analysis technology to analyze the speaker's emotional state from audio data. For example, it evaluates the intonation, speed, and volume of the speech to identify emotions. The input is a digital audio signal and corresponding text data, and the output is numerical or categorical information indicating the speaker's emotional state.

[0178] Step 5:

[0179] The server combines text data and sentiment information to automatically generate meeting minutes that reflect the participants' statements and emotional states. In this step, the meeting record is comprehensively documented. The input is text data and sentiment information, and the output is a documented meeting record.

[0180] Step 6:

[0181] The server automatically generates follow-up tasks and sets priorities based on the generated meeting minutes and sentiment states. Here, the urgency and importance of the tasks are re-evaluated, and preparations are made for managing their progress in conjunction with the task management system. The input is the meeting record document, and the output is a prioritized list of follow-up tasks.

[0182] Step 7:

[0183] The server uses a task management system to assign follow-up tasks to appropriate personnel and monitors and manages their progress. Specifically, it notifies personnel of task details through a notification system and collects progress data. The input is a list of follow-up tasks, and the output is management information related to the progress of the tasks.

[0184] (Application Example 2)

[0185] 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".

[0186] In modern workplaces and homes, information sharing through meetings and conversations is highly valued, but the quality of communication can decline if appropriate follow-up is not conducted with an understanding of participants' emotions. In this situation, there is a need to improve the efficiency and quality of communication by understanding emotional states and automating and managing follow-up tasks.

[0187] 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.

[0188] In this invention, the server includes means for acquiring acoustic information of a meeting in real time using an acoustic information acquisition unit, means for converting the acquired acoustic information into document data using acoustic recognition technology, and emotion analysis means for analyzing the emotional state of participants from the acoustic data. This enables the automated management of conversation recordings and prioritized follow-up tasks based on emotional states.

[0189] An "acoustic information acquisition unit" is a device or group of devices for acquiring acoustic information in real time.

[0190] "Acoustic recognition technology" is a technology for converting acquired acoustic information into document data.

[0191] "Natural language processing technology" is a technique used to extract important information from document data.

[0192] "Emotional analysis means" refers to a technology or device for analyzing the emotional state of participants from their acoustic data.

[0193] "Meeting minutes" are documents that record the content of meetings and gatherings, and include important information and emotional states.

[0194] "Follow-up tasks" refer to a series of tasks performed to implement and manage the decisions made at meetings and gatherings.

[0195] A "task management tool" is software or a system used to track and manage the progress of follow-up tasks.

[0196] To implement this invention, a consumer robot is first equipped with an acoustic information acquisition unit. This allows the robot to acquire ambient sounds and conversations in real time when a meeting begins in a user's home or office. Software implementing acoustic recognition technology runs within the terminal and converts the real-time acquired acoustic information into document data. Acoustic recognition technologies such as the Google Cloud Speech-to-Text API are used in this process.

[0197] The server receives the converted document data and extracts important information using natural language processing techniques. The accuracy of the extraction can be improved by utilizing libraries such as the Natural Language Toolkit (NLTK) and Tensorflow®.

[0198] Furthermore, as a means of emotion analysis, a system that analyzes participants' emotional states from acoustic data is operated on a server. This system analyzes the intonation and speed of the sounds to determine the emotional state. The generated emotional information is integrated with document data and reflected in the meeting minutes.

[0199] As a concrete example, during a family meeting at home, the robot can record each member's opinions and emotional state, and prioritize follow-up tasks for topics that show particularly high interest. Such a system facilitates smoother communication within the family and promotes decision-making.

[0200] Example of a prompt:

[0201] "Let's begin the meeting about our next family trip. Please have the robot record what we discussed today and pay particular attention to its emotional responses."

[0202] Thus, a specific embodiment of this invention is that consumer robots function as an important tool for improving the quality of communication.

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The terminal uses an acoustic information acquisition unit to record acoustic information of the meeting in real time. The input is ambient sound and conversation sounds, and the output is digital acoustic data. This acoustic data is sent to a server for further processing.

[0206] Step 2:

[0207] The server converts received acoustic data into document data using acoustic recognition technology. The input is digital acoustic data, and the output is document data in text format. It uses the Google Cloud Speech-to-Text API to analyze the acoustic waveform and convert it into word by word.

[0208] Step 3:

[0209] The server analyzes the generated document data using natural language processing techniques and extracts important information. The input is document data generated by speech recognition, and the output is important information such as key feedback and issues. Natural Language Toolkit (NLTK) is used for part-of-speech tagging and semantic analysis.

[0210] Step 4:

[0211] The server analyzes the emotional state of participants using sentiment analysis techniques based on the input acoustic data. The input is acoustic data, and the output is data indicating the emotional state for each statement. This uses machine learning models to evaluate changes in the speaker's tone and pace.

[0212] Step 5:

[0213] The server integrates the generated key information and emotional states to create meeting minutes. The input is key information and emotional states, and the output is a detailed meeting minute containing both. This meeting minute is then visualized for users and relevant parties.

[0214] Step 6:

[0215] Users review follow-up tasks based on meeting minutes and sentiment information, and prioritize tasks as needed. Input is meeting minutes, and output is task lists and priority settings. Notifications and task adjustments are handled through the user interface.

[0216] Step 7:

[0217] The server works in conjunction with the task management tool to monitor the progress of follow-up tasks and sends notifications of delays or incomplete tasks to relevant parties as needed. Inputs are progress status and completion data, while outputs are tracked task status and action instruction notifications. This is implemented using API integration with the task management platform.

[0218] 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.

[0219] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] This invention is an embodiment of an integrated system that acquires meeting audio in real time, converts that audio into text data, and automatically extracts and manages important information. Specifically, it operates as follows:

[0235] First, the user activates the system at the start of the meeting. The activated terminal captures audio during the meeting using its built-in voice acquisition function or an external microphone device. The captured audio is then converted into text data by the terminal using speech recognition technology. The speech recognition technology is designed to handle a wide variety of audio data, enabling accurate text conversion.

[0236] Next, the server receives the text data and applies natural language processing technology. This extracts the important agenda items and decisions made during the meeting, and automatically generates meeting minutes based on this information. These minutes are clearly organized and easy to understand, helping to quickly grasp the overall picture of the meeting. Furthermore, they include action items and next steps that were pointed out during the meeting.

[0237] Next, the generated meeting minutes are analyzed by the server, and follow-up tasks are automatically created. These tasks are assigned to designated personnel. Task assignment is carried out in conjunction with task management tools used within the organization, and is smoothly reflected through APIs such as those of project management systems.

[0238] The server has the functionality to track these tasks and constantly monitor their progress. Progress information is notified to the person in charge via the task management tool platform, allowing them to immediately check the completion status of tasks and the percentage of incomplete tasks. In this way, information leaks and overlooked tasks are prevented, contributing to improved work efficiency.

[0239] As a concrete example, if the implementation schedule for a new feature changes during a product development meeting, users are immediately listed as a critical issue. This information is then reflected in subsequent follow-up tasks and assigned to the relevant development team members, resulting in transparent and efficient project management.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The user activates the AI ​​agent at the start of the meeting. The terminal that receives the activation command prepares to activate its audio acquisition unit in order to acquire meeting audio.

[0243] Step 2:

[0244] The terminal records audio data collected during the meeting via an audio acquisition unit. The recorded audio data is prepared in real time for speech recognition technology and processed quickly.

[0245] Step 3:

[0246] The device inputs recorded audio data into speech recognition technology and converts it into text data. The speech recognition results are optimized for high accuracy, and the converted text data is saved locally.

[0247] Step 4:

[0248] The server receives text data and analyzes it using natural language processing technology. Through this analysis, important meeting topics, speaker information, action items, and other relevant details are automatically extracted.

[0249] Step 5:

[0250] The server automatically generates meeting minutes based on the analysis results. The generated minutes are presented in a well-organized format, clearly indicating the key points and decisions of the meeting, and are prepared for easy sharing with relevant parties.

[0251] Step 6:

[0252] The server generates follow-up tasks from the meeting minutes. These tasks include action items decided at the meeting and incorporate necessary assignee information. This clearly identifies which tasks should be assigned to which individuals.

[0253] Step 7:

[0254] The server integrates task information into the task management tool. Tasks are registered via the management tool's API, and a system is in place to monitor progress in real time. In case of failure or delay, the system is configured to quickly notify relevant parties.

[0255] Step 8:

[0256] Users can check task progress through task management tools and take corrective actions as needed. This monitoring function is used to maximize work efficiency and productivity.

[0257] (Example 1)

[0258] 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."

[0259] Efficient management of audio information during meetings is essential to prevent overlooking important information and delaying tasks. In particular, the failure to accurately record important content after meetings and the resulting inadequate management of follow-up tasks can hinder project progress.

[0260] 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.

[0261] In this invention, the server includes means for acquiring meeting audio in real time using a receiving device, means for converting the acquired audio into text information using a speech recognition method, and means for extracting important information from the text information using natural language processing technology. This makes it possible to accurately record the key points of a meeting and to automatically generate and manage follow-up tasks.

[0262] A "receiving device" is a hardware or software system for acquiring audio during a meeting in real time.

[0263] A "speech recognition method" is a technical technique that analyzes acquired speech data and converts it into text information.

[0264] "Natural language processing technology" is a field of computer science that extracts and analyzes important information from text.

[0265] "Text information" refers to character information converted from audio data using speech recognition methods.

[0266] "Important information" refers to the topics and action items necessary for decision-making and follow-up during a meeting.

[0267] A "record document" is a document that is automatically generated based on extracted key information and summarizes the main points of a meeting.

[0268] A "tracking task" is an action item derived from the generated record document that is necessary for the progress of the work.

[0269] "Progress management techniques" are techniques for monitoring and appropriately managing the completion status and progress of tasks.

[0270] A "related party" is any person or entity that is directly responsible for or may be affected by the progress of the generated tracking task.

[0271] This invention is an integrated system for the efficient acquisition, conversion, analysis, and management of conference audio. Its embodiments are described in detail below.

[0272] The user activates the system when starting a meeting. This allows the terminal to capture audio in real time during the meeting using its built-in microphone or an external microphone device. While a standard audio capture device is used for audio acquisition, a high-sensitivity microphone with noise-canceling capabilities can reduce ambient noise and capture clear audio.

[0273] The acquired audio data is processed on the device and converted into text information using speech recognition software such as the Google Speech-to-Text API or Amazon Transcribe. This speech recognition process analyzes the audio information and outputs it as text, thereby achieving text conversion.

[0274] The generated text information is then sent to a server, where important information is extracted using natural language processing techniques. For example, by utilizing SpaCy, a Python library, contextual analysis can be performed to extract agenda items and important decisions.

[0275] Based on the extracted key information, the server automatically generates a record document. This document clarifies the key points of the meeting and serves as an important resource for scheduling appointments and reviewing decisions made later.

[0276] Furthermore, the server creates tracking tasks from the generated record documents, which are then properly managed by a progress management system that integrates with progress tracking technology. By utilizing APIs such as Asana and Trello, the generated tasks are smoothly reflected in these progress management tools and assigned to the responsible parties.

[0277] In this way, the server can constantly monitor progress and notify relevant parties if there are delays or incomplete tasks.

[0278] As a concrete example, the prompt "Extract important decisions from the following meeting minutes and create action items" is entered into the AI. This automatically extracts the critical information and suggests the next steps. This makes it easier to manage meeting content and allows subsequent actions to proceed efficiently.

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The user starts the system at the beginning of the meeting. By this operation, the terminal enters a state of acquiring the audio during the meeting. The input is the audio signal acquired through the microphone device, and this signal undergoes an operation of being converted into digital audio data by the audio capture system inside the terminal. The output is the audio data in digital format.

[0282] Step 2:

[0283] The terminal passes the acquired digital audio data to the speech recognition software. This software uses, such as the Google Speech-to-Text API, to analyze the audio data and outputs it as a character string. The input is the audio data in digital format, and the output is the converted text information. The specific operation here is to analyze the pattern of the sound wave signal and perform the process of converting it into a language structure.

[0284] Step 3:

[0285] The server receives the text information sent from the terminal and extracts important information using natural language processing technology. The input is the text data related to the meeting, and the output is the important information including the topics and decisions. The specific operation includes identifying nouns and verbs in the text and analyzing the context of the sentences related to them.

[0286] Step 4:

[0287] The server automatically generates a record document based on the extracted important information. The input is the important information obtained in Step 3, and the output is a document in the format of minutes of the meeting. In this process, the information is logically structured and output in a format that is easy to use for the progress of the project and decision-making.

[0288] Step 5:

[0289] The server automatically generates tracking tasks from the generated record documents. The input is the action items contained in the meeting minutes, and the output is a list of tracking tasks. Specifically, it is a procedure to document tasks based on the necessary actions and instructions, and register them in the management system.

[0290] Step 6:

[0291] The server integrates with progress management technology to reflect generated tasks in related systems. The input is a list of tracked tasks, and the output is the status of their implementation in task management tools. This operation includes sending information via API and assigning tasks to assigned personnel.

[0292] Step 7:

[0293] The server monitors task progress in real time and notifies relevant parties as needed. Input is task progress data, and output is notifications to relevant parties. This process includes the ability to measure the degree of task completion and immediately notify if non-completion is suspected.

[0294] (Application Example 1)

[0295] 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."

[0296] In modern times, the development of autonomous driving technology has created a demand for driver assistance in vehicles. Efficiently acquiring instructions and safety-related information within autonomous vehicles and processing it in real time is crucial for safe driving and operational optimization. This invention aims to acquire such instruction information as voice, rapidly analyze it, and reflect it in the system.

[0297] 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.

[0298] In this invention, the server includes means for acquiring an audio signal in real time using an audio acquisition unit, means for converting the acquired audio signal into text data using speech recognition technology, and means for analyzing instruction information in the driving environment in real time and reflecting it in an automatic control system. Thereby, instruction information can be efficiently analyzed in an autonomous vehicle, enabling safe and rapid driving control.

[0299] The "audio acquisition unit" is a device or system for acquiring an audio signal in real time.

[0300] "Speech recognition technology" is a technology for converting an acquired audio signal into text data.

[0301] "Natural language processing technology" is a technology for extracting and analyzing important information from text data.

[0302] "Information recording" is a document or data automatically generated based on the extracted important information.

[0303] "Follow-up task" is a subsequent operation or instruction automatically generated from the generated information recording.

[0304] The "task management system" is a system for monitoring and managing the progress of follow-up tasks.

[0305] The "driving environment" is a concept referring to the surrounding situations and conditions during the driving of an autonomous vehicle.

[0306] "Instruction information" is information of commands or requests given by voice from a driver, passenger, etc.

[0307] The "automatic control system" is a system for automatically adjusting the operation of a vehicle based on instruction information.

[0308] This system aims to effectively acquire and analyze instruction information within autonomous vehicles. The server uses a voice acquisition unit to acquire in-vehicle audio signals in real time. These acquired audio signals are then converted into text data using speech recognition technology.

[0309] The server applies natural language processing techniques to the converted text data to analyze important driving instructions. The instructions extracted through this analysis are then reflected in the automated control system in real time, ensuring proper vehicle control.

[0310] Users can instruct the system to change destinations or update driving information through simple voice commands. This improves driving efficiency and safety. For example, if a passenger instructs the system to change destinations by voice, the instruction is analyzed as text data, and the navigation system is quickly updated.

[0311] An example of a prompt message for a generated AI model might be: "Design a system that analyzes voice commands while driving and immediately reflects changes in the destination." This prompt message specifically describes the system's function and serves as a guide for realizing the necessary information processing while driving.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The terminal uses an audio acquisition unit to acquire audio signals from passengers and drivers in real time. The input is an audio signal, and the output is raw audio data. This audio data is acquired at a constant sampling rate and converted to a digital format for subsequent processing.

[0315] Step 2:

[0316] The server converts the acquired audio data into text data using speech recognition technology. The input is the audio data from step 1, and the output is parseable text data. This process uses a generative AI model in the speech recognition system to process the data to handle diverse pronunciations and noise.

[0317] Step 3:

[0318] The server analyzes the obtained text data using natural language processing technology and extracts the instruction information necessary for driving. The input is the text data from step 2, and the output is the instruction information. At this stage, keywords and context are analyzed from the text, and a generative AI model is used to evaluate the urgency and priority of the instructions.

[0319] Step 4:

[0320] The server reflects the extracted instruction information into the automatic control system and adjusts the vehicle's driving control. The input is the instruction information from step 3, and the output is the control command. In this process, the output is generated in a format compatible with the control system and immediately applied to the vehicle's operation.

[0321] Step 5:

[0322] The user can review system feedback as needed and provide additional instructions via voice. The input is the new voice instruction from the user, and the output is the voice data looped back to step 1 for reprocessing. This feedback loop allows for continuous optimization of the operating conditions.

[0323] 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.

[0324] This invention is a system that not only acquires meeting audio in real time and converts it into text data to extract important information, but also reads emotions from participants' voices and applies this information to the meeting recording and follow-up process. In this embodiment, the system operates as follows.

[0325] The user activates the system at the start of the meeting, and the terminal acquires the meeting audio in real time using the audio acquisition unit. The acquired audio data is converted into text data using speech recognition technology. This allows the content of the meeting to be quickly saved as text.

[0326] In addition, the server uses an emotion engine to analyze the user's emotions from the audio data. The emotion engine determines the participant's emotional state by analyzing the intonation, speed, and other parameters of the voice. The emotional information obtained here is incorporated into text data extracted using natural language processing techniques and reflected in the meeting minutes.

[0327] The server automatically generates meeting minutes with emotional information. In addition to the text data of what was said, these minutes record the emotional state at the time of the statement, which helps to understand the atmosphere of the meeting and the reactions of the participants.

[0328] Next, emotional information is also used to generate and prioritize follow-up tasks. Specifically, the server uses the user's emotional information to re-evaluate the urgency and importance of tasks and determine the need for follow-up. This automatically determines who should prioritize which tasks and assigns them to the appropriate personnel.

[0329] For example, if there is significant interest in feedback on a new product during a meeting, the server will use sentiment engine analysis of the participants to identify the high level of user interest in that product. As a result, it will prioritize tasks related to the new product, promptly notify those responsible, and support efficient project progress.

[0330] In this way, the system combines speech recognition and sentiment analysis to enhance meeting recording and subsequent business processes, enabling a dramatic improvement in corporate operational efficiency.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] The user activates the system at the start of the meeting. This initiates the operation of the terminal, including the audio acquisition unit, and prepares it to acquire meeting audio in real time.

[0334] Step 2:

[0335] The terminal uses speech recognition technology to convert the audio collected from the meeting into text data. The audio data is then transcribed with high accuracy by the platform and immediately sent to the server.

[0336] Step 3:

[0337] The server applies natural language processing techniques to the received text data to extract the meeting summary and key points. During this process, the information is organized and prepared as the source data for the meeting record.

[0338] Step 4:

[0339] Simultaneously, the device uses an emotion engine to analyze the tone and pitch of the user's voice from the audio data and performs emotion queries. This identifies the emotional state behind each statement.

[0340] Step 5:

[0341] The server integrates the sentiment analysis results into the meeting minutes data. Sentimental information associated with each statement is added, making the reactions of each participant during the meeting clearer.

[0342] Step 6:

[0343] The server generates follow-up tasks using meeting minutes with sentiment information. Sentiment information influences the determination of task importance and priority, highlighting issues that require immediate attention from the user.

[0344] Step 7:

[0345] The server uses a task management tool to assign follow-up tasks to the appropriate personnel, and is configured to make tasks immediately visible. The system automatically optimizes the allocation based on each person's workload and interests.

[0346] Step 8:

[0347] After a meeting, users track the progress of their tasks through a task management tool. The system can evaluate their focus on priority tasks based on sentiment analysis, and revise countermeasures as needed.

[0348] (Example 2)

[0349] 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".

[0350] Modern business meetings involve the frequent exchange of large amounts of information, necessitating rapid and accurate recording of meeting content and follow-up based on participants' emotional states. However, traditional methods often involve manual transcription of speech and emotional analysis, which is time-consuming and labor-intensive, and results in inconsistent recording accuracy and follow-up quality. Therefore, it is crucial to achieve efficient meeting management and follow-up through automated speech conversion and the utilization of emotional information.

[0351] 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.

[0352] In this invention, the server includes means for acquiring meeting audio in real time using an acoustic acquisition device, means for converting the acquired audio into text data using speech recognition technology, and means for analyzing the emotional state of speakers from the audio data using emotion analysis technology. This makes it possible to automatically transcribe meeting audio information into text and quickly analyze the emotional state of participants. Furthermore, this information can be used to extract important information and automatically generate meeting minutes, and to automatically generate and prioritize follow-up tasks that reflect the emotional information. This leads to improved efficiency and quality of work.

[0353] An "acoustic acquisition device" is a device used to acquire sound as a digital signal in settings such as meetings.

[0354] "Voice recognition technology" is a technology that analyzes acquired voice data and automatically converts it into corresponding text data.

[0355] "Text data" refers to text information converted from speech, specifically a written record of the presentations given at a meeting.

[0356] "Emotional analysis technology" is a technology that analyzes voice data to determine the emotional state of the speaker.

[0357] "Meeting minutes" are documents that record the content of conversations during a meeting, including the emotional state of the participants at the time.

[0358] "Follow-up tasks" are the work or tasks that need to be done after a meeting, and are generated based on the meeting minutes.

[0359] A "business management device" is a device used to manage the progress and priorities of follow-up tasks and to inform relevant parties of the results.

[0360] This invention is a system that efficiently acquires audio information from meetings, transcribes it into text, and analyzes and records emotional information based on that text, thereby automatically generating and managing follow-up tasks.

[0361] The user activates the system at the start of the meeting. The hardware used is a terminal equipped with an audio acquisition device. The terminal acquires meeting audio in real time and converts it into text data using speech recognition technology. Software such as the Google Speech-to-Text API can be used for this speech recognition.

[0362] Next, the server uses emotion analysis technology to analyze the acquired audio data and determine the emotional state at the time of speaking. In this process, emotion analysis tools such as IBM Watson Tone Analyzer are used to evaluate elements such as intonation and speed of speech and identify emotions.

[0363] The generated text data and emotional information are unified by the server and automatically compiled into meeting minutes. These minutes include detailed descriptions of what was said, along with the emotional state at the time, allowing for a clearer understanding of the participants' attitudes and reactions.

[0364] Furthermore, this sentiment information is also used to generate and prioritize follow-up tasks. Based on meeting minutes and sentiment states, the server evaluates the urgency and importance of tasks. This allows the task management system to assign tasks to the appropriate personnel, manage progress, and support an efficient post-meeting process.

[0365] For example, if a new service is discussed in a meeting and participants show high interest, the server can analyze their sentiment, prioritize related tasks, and quickly notify the appropriate person. This system allows companies to improve meeting productivity and prevent delays or inadequate follow-up.

[0366] An example of a prompt would be, "Please provide an overview of the follow-up tasks generated as a result of converting the meeting audio data to text and performing sentiment analysis."

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The user activates the system at the start of the meeting. Once activated, the system prepares to begin acquiring meeting audio. The input here is an acoustic acquisition device that receives the audio signal. The output is the real-time collection of meeting audio.

[0370] Step 2:

[0371] The terminal uses an acoustic acquisition device to capture conference audio in real time. In this step, the conference audio is converted into a digital signal for use in subsequent analysis steps. The input is continuous audio data from the acoustic acquisition device. The output is in the form of a digital audio signal, which is passed on to the next step.

[0372] Step 3:

[0373] The device uses speech recognition technology to convert acquired speech into text data. Specifically, it analyzes the speech signal using APIs such as the Google Speech-to-Text API and generates the corresponding text. The input is a digital speech signal, and the output is the spoken content as text data.

[0374] Step 4:

[0375] The server utilizes emotion analysis technology to analyze the speaker's emotional state from audio data. For example, it evaluates the intonation, speed, and volume of the speech to identify emotions. The input is a digital audio signal and corresponding text data, and the output is numerical or categorical information indicating the speaker's emotional state.

[0376] Step 5:

[0377] The server combines text data and sentiment information to automatically generate meeting minutes that reflect the participants' statements and emotional states. In this step, the meeting record is comprehensively documented. The input is text data and sentiment information, and the output is a documented meeting record.

[0378] Step 6:

[0379] The server automatically generates follow-up tasks and sets priorities based on the generated meeting minutes and sentiment states. Here, the urgency and importance of the tasks are re-evaluated, and preparations are made for managing their progress in conjunction with the task management system. The input is the meeting record document, and the output is a prioritized list of follow-up tasks.

[0380] Step 7:

[0381] The server uses a task management system to assign follow-up tasks to appropriate personnel and monitors and manages their progress. Specifically, it notifies personnel of task details through a notification system and collects progress data. The input is a list of follow-up tasks, and the output is management information related to the progress of the tasks.

[0382] (Application Example 2)

[0383] 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."

[0384] In modern workplaces and homes, information sharing through meetings and conversations is highly valued, but the quality of communication can decline if appropriate follow-up is not conducted with an understanding of participants' emotions. In this situation, there is a need to improve the efficiency and quality of communication by understanding emotional states and automating and managing follow-up tasks.

[0385] 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.

[0386] In this invention, the server includes means for acquiring acoustic information of a meeting in real time using an acoustic information acquisition unit, means for converting the acquired acoustic information into document data using acoustic recognition technology, and emotion analysis means for analyzing the emotional state of participants from the acoustic data. This enables the automated management of conversation recordings and prioritized follow-up tasks based on emotional states.

[0387] An "acoustic information acquisition unit" is a device or group of devices for acquiring acoustic information in real time.

[0388] "Acoustic recognition technology" is a technology for converting acquired acoustic information into document data.

[0389] "Natural language processing technology" is a technique used to extract important information from document data.

[0390] "Emotional analysis means" refers to a technology or device for analyzing the emotional state of participants from their acoustic data.

[0391] "Meeting minutes" are documents that record the content of meetings and gatherings, and include important information and emotional states.

[0392] "Follow-up tasks" refer to a series of tasks performed to implement and manage the decisions made at meetings and gatherings.

[0393] A "task management tool" is software or a system used to track and manage the progress of follow-up tasks.

[0394] To implement this invention, a consumer robot is first equipped with an acoustic information acquisition unit. This allows the robot to acquire ambient sounds and conversations in real time when a meeting begins in a user's home or office. Software implementing acoustic recognition technology runs within the terminal and converts the real-time acquired acoustic information into document data. Acoustic recognition technologies such as the Google Cloud Speech-to-Text API are used in this process.

[0395] The server receives the converted document data and extracts important information using natural language processing techniques. The accuracy of the extraction can be improved by utilizing libraries such as the Natural Language Toolkit (NLTK) and TensorFlow.

[0396] Furthermore, as a means of emotion analysis, a system that analyzes participants' emotional states from acoustic data is operated on a server. This system analyzes the intonation and speed of the sounds to determine the emotional state. The generated emotional information is integrated with document data and reflected in the meeting minutes.

[0397] As a concrete example, during a family meeting at home, the robot can record each member's opinions and emotional state, and prioritize follow-up tasks for topics that show particularly high interest. Such a system facilitates smoother communication within the family and promotes decision-making.

[0398] Example of a prompt:

[0399] "Let's begin the meeting about our next family trip. Please have the robot record what we discussed today and pay particular attention to its emotional responses."

[0400] Thus, a specific embodiment of this invention is that consumer robots function as an important tool for improving the quality of communication.

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The terminal uses an acoustic information acquisition unit to record acoustic information of the meeting in real time. The input is ambient sound and conversation sounds, and the output is digital acoustic data. This acoustic data is sent to a server for further processing.

[0404] Step 2:

[0405] The server converts received acoustic data into document data using acoustic recognition technology. The input is digital acoustic data, and the output is document data in text format. It uses the Google Cloud Speech-to-Text API to analyze the acoustic waveform and convert it into word by word.

[0406] Step 3:

[0407] The server analyzes the generated document data using natural language processing techniques and extracts important information. The input is document data generated by speech recognition, and the output is important information such as key feedback and issues. Natural Language Toolkit (NLTK) is used for part-of-speech tagging and semantic analysis.

[0408] Step 4:

[0409] The server analyzes the emotional state of participants using sentiment analysis techniques based on the input acoustic data. The input is acoustic data, and the output is data indicating the emotional state for each statement. This uses machine learning models to evaluate changes in the speaker's tone and pace.

[0410] Step 5:

[0411] The server integrates the generated key information and emotional states to create meeting minutes. The input is key information and emotional states, and the output is a detailed meeting minute containing both. This meeting minute is then visualized for users and relevant parties.

[0412] Step 6:

[0413] Users review follow-up tasks based on meeting minutes and sentiment information, and prioritize tasks as needed. Input is meeting minutes, and output is task lists and priority settings. Notifications and task adjustments are handled through the user interface.

[0414] Step 7:

[0415] The server works in conjunction with the task management tool to monitor the progress of follow-up tasks and sends notifications of delays or incomplete tasks to relevant parties as needed. Inputs are progress status and completion data, while outputs are tracked task status and action instruction notifications. This is implemented using API integration with the task management platform.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] This invention is an embodiment of an integrated system that acquires meeting audio in real time, converts that audio into text data, and automatically extracts and manages important information. Specifically, it operates as follows:

[0433] First, the user activates the system at the start of the meeting. The activated terminal captures audio during the meeting using its built-in voice acquisition function or an external microphone device. The captured audio is then converted into text data by the terminal using speech recognition technology. The speech recognition technology is designed to handle a wide variety of audio data, enabling accurate text conversion.

[0434] Next, the server receives the text data and applies natural language processing technology. This extracts the important agenda items and decisions made during the meeting, and automatically generates meeting minutes based on this information. These minutes are clearly organized and easy to understand, helping to quickly grasp the overall picture of the meeting. Furthermore, they include action items and next steps that were pointed out during the meeting.

[0435] Next, the generated meeting minutes are analyzed by the server, and follow-up tasks are automatically created. These tasks are assigned to designated personnel. Task assignment is carried out in conjunction with task management tools used within the organization, and is smoothly reflected through APIs such as those of project management systems.

[0436] The server has the functionality to track these tasks and constantly monitor their progress. Progress information is notified to the person in charge via the task management tool platform, allowing them to immediately check the completion status of tasks and the percentage of incomplete tasks. In this way, information leaks and overlooked tasks are prevented, contributing to improved work efficiency.

[0437] As a concrete example, if the implementation schedule for a new feature changes during a product development meeting, users are immediately listed as a critical issue. This information is then reflected in subsequent follow-up tasks and assigned to the relevant development team members, resulting in transparent and efficient project management.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The user activates the AI ​​agent at the start of the meeting. The terminal that receives the activation command prepares to activate its audio acquisition unit in order to acquire meeting audio.

[0441] Step 2:

[0442] The terminal records audio data collected during the meeting via an audio acquisition unit. The recorded audio data is prepared in real time for speech recognition technology and processed quickly.

[0443] Step 3:

[0444] The device inputs recorded audio data into speech recognition technology and converts it into text data. The speech recognition results are optimized for high accuracy, and the converted text data is saved locally.

[0445] Step 4:

[0446] The server receives text data and analyzes it using natural language processing technology. Through this analysis, important meeting topics, speaker information, action items, and other relevant details are automatically extracted.

[0447] Step 5:

[0448] The server automatically generates meeting minutes based on the analysis results. The generated minutes are presented in a well-organized format, clearly indicating the key points and decisions of the meeting, and are prepared for easy sharing with relevant parties.

[0449] Step 6:

[0450] The server generates follow-up tasks from the meeting minutes. These tasks include action items decided at the meeting and incorporate necessary assignee information. This clearly identifies which tasks should be assigned to which individuals.

[0451] Step 7:

[0452] The server integrates task information into the task management tool. Tasks are registered via the management tool's API, and a system is in place to monitor progress in real time. In case of failure or delay, the system is configured to quickly notify relevant parties.

[0453] Step 8:

[0454] Users can check task progress through task management tools and take corrective actions as needed. This monitoring function is used to maximize work efficiency and productivity.

[0455] (Example 1)

[0456] 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."

[0457] Efficient management of audio information during meetings is essential to prevent overlooking important information and delaying tasks. In particular, the failure to accurately record important content after meetings and the resulting inadequate management of follow-up tasks can hinder project progress.

[0458] 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.

[0459] In this invention, the server includes means for acquiring meeting audio in real time using a receiving device, means for converting the acquired audio into text information using a speech recognition method, and means for extracting important information from the text information using natural language processing technology. This makes it possible to accurately record the key points of a meeting and to automatically generate and manage follow-up tasks.

[0460] A "receiving device" is a hardware or software system for acquiring audio during a meeting in real time.

[0461] A "speech recognition method" is a technical technique that analyzes acquired speech data and converts it into text information.

[0462] "Natural language processing technology" is a field of computer science that extracts and analyzes important information from text.

[0463] "Text information" refers to character information converted from audio data using speech recognition methods.

[0464] "Important information" refers to the topics and action items necessary for decision-making and follow-up during a meeting.

[0465] A "record document" is a document that is automatically generated based on extracted key information and summarizes the main points of a meeting.

[0466] A "tracking task" is an action item derived from the generated record document that is necessary for the progress of the work.

[0467] "Progress management techniques" are techniques for monitoring and appropriately managing the completion status and progress of tasks.

[0468] A "related party" is any person or entity that is directly responsible for or may be affected by the progress of the generated tracking task.

[0469] This invention is an integrated system for the efficient acquisition, conversion, analysis, and management of conference audio. Its embodiments are described in detail below.

[0470] The user activates the system when starting a meeting. This allows the terminal to capture audio in real time during the meeting using its built-in microphone or an external microphone device. While a standard audio capture device is used for audio acquisition, a high-sensitivity microphone with noise-canceling capabilities can reduce ambient noise and capture clear audio.

[0471] The acquired audio data is processed on the device and converted into text information using speech recognition software such as the Google Speech-to-Text API or Amazon Transcribe. This speech recognition process analyzes the audio information and outputs it as text, thereby achieving text conversion.

[0472] The generated text information is then sent to a server, where important information is extracted using natural language processing techniques. For example, by utilizing SpaCy, a Python library, contextual analysis can be performed to extract agenda items and important decisions.

[0473] Based on the extracted key information, the server automatically generates a record document. This document clarifies the key points of the meeting and serves as an important resource for scheduling appointments and reviewing decisions made later.

[0474] Furthermore, the server creates tracking tasks from the generated record documents, which are then properly managed by a progress management system that integrates with progress tracking technology. By utilizing APIs such as Asana and Trello, the generated tasks are smoothly reflected in these progress management tools and assigned to the responsible parties.

[0475] In this way, the server can constantly monitor progress and notify relevant parties if there are delays or incomplete tasks.

[0476] As a concrete example, the prompt "Extract important decisions from the following meeting minutes and create action items" is entered into the AI. This automatically extracts the critical information and suggests the next steps. This makes it easier to manage meeting content and allows subsequent actions to proceed efficiently.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The user activates the system at the start of the meeting. This action puts the terminal into a state where it can acquire audio during the meeting. The input is the audio signal acquired through the microphone device, and this signal is converted into digital audio data by the audio capture system inside the terminal. The output is audio data in digital format.

[0480] Step 2:

[0481] The device passes the acquired digital audio data to speech recognition software. This software analyzes the audio data using APIs such as the Google Speech-to-Text API and outputs it as text. The input is digital audio data, and the output is converted text information. Specifically, the process involves analyzing the pattern of the sound wave signal and converting it into a language structure.

[0482] Step 3:

[0483] The server receives text information sent from the terminal and extracts important information using natural language processing techniques. The input is text data related to a meeting, and the output is important information including agenda items and decisions. Specifically, the process involves identifying nouns and verbs within the text and analyzing the context of the sentences related to them.

[0484] Step 4:

[0485] The server automatically generates record documents based on the extracted key information. The input is the key information obtained in step 3, and the output is a well-organized meeting minutes-style document. In this process, the information is logically structured and output in a format that is easy to use for project progress and decision-making.

[0486] Step 5:

[0487] The server automatically generates tracking tasks from the generated record documents. The input is the action items contained in the meeting minutes, and the output is a list of tracking tasks. Specifically, it is a procedure to document tasks based on the necessary actions and instructions, and register them in the management system.

[0488] Step 6:

[0489] The server integrates with progress management technology to reflect generated tasks in related systems. The input is a list of tracked tasks, and the output is the status of their implementation in task management tools. This operation includes sending information via API and assigning tasks to assigned personnel.

[0490] Step 7:

[0491] The server monitors task progress in real time and notifies relevant parties as needed. Input is task progress data, and output is notifications to relevant parties. This process includes the ability to measure the degree of task completion and immediately notify if non-completion is suspected.

[0492] (Application Example 1)

[0493] 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."

[0494] In modern times, the development of autonomous driving technology has created a demand for driver assistance in vehicles. Efficiently acquiring instructions and safety-related information within autonomous vehicles and processing it in real time is crucial for safe driving and operational optimization. This invention aims to acquire such instruction information as voice, rapidly analyze it, and reflect it in the system.

[0495] 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.

[0496] In this invention, the server includes means for acquiring audio signals in real time using an audio acquisition unit, means for converting the acquired audio signals into text data using speech recognition technology, and means for analyzing instruction information in the driving environment in real time and reflecting it in the automatic control system. This enables efficient analysis of instruction information within an autonomous vehicle, allowing for safe and rapid driving control.

[0497] A "voice acquisition unit" is a device or system for acquiring voice signals in real time.

[0498] "Speech recognition technology" is a technology that converts acquired speech signals into text data.

[0499] "Natural language processing technology" is a technique for extracting and analyzing important information from text data.

[0500] "Information records" refer to documents or data that are automatically generated based on extracted important information.

[0501] A "follow-up task" is a subsequent task or instruction that is automatically generated from the generated information record.

[0502] A "task management system" is a system for monitoring and managing the progress of follow-up tasks.

[0503] "Driving environment" is a concept that refers to the surrounding conditions and circumstances while an autonomous vehicle is in motion.

[0504] "Instructional information" refers to commands and requests given verbally by drivers, passengers, etc.

[0505] An "automatic control system" is a system that automatically adjusts the vehicle's operation based on instruction information.

[0506] This system aims to effectively acquire and analyze instruction information within autonomous vehicles. The server uses a voice acquisition unit to acquire in-vehicle audio signals in real time. These acquired audio signals are then converted into text data using speech recognition technology.

[0507] The server applies natural language processing techniques to the converted text data to analyze important driving instructions. The instructions extracted through this analysis are then reflected in the automated control system in real time, ensuring proper vehicle control.

[0508] Users can instruct the system to change destinations or update driving information through simple voice commands. This improves driving efficiency and safety. For example, if a passenger instructs the system to change destinations by voice, the instruction is analyzed as text data, and the navigation system is quickly updated.

[0509] An example of a prompt message for a generated AI model might be: "Design a system that analyzes voice commands while driving and immediately reflects changes in the destination." This prompt message specifically describes the system's function and serves as a guide for realizing the necessary information processing while driving.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The terminal uses an audio acquisition unit to acquire audio signals from passengers and drivers in real time. The input is an audio signal, and the output is raw audio data. This audio data is acquired at a constant sampling rate and converted to a digital format for subsequent processing.

[0513] Step 2:

[0514] The server converts the acquired audio data into text data using speech recognition technology. The input is the audio data from step 1, and the output is parseable text data. This process uses a generative AI model in the speech recognition system to process the data to handle diverse pronunciations and noise.

[0515] Step 3:

[0516] The server analyzes the obtained text data using natural language processing technology and extracts the instruction information necessary for driving. The input is the text data from step 2, and the output is the instruction information. At this stage, keywords and context are analyzed from the text, and a generative AI model is used to evaluate the urgency and priority of the instructions.

[0517] Step 4:

[0518] The server reflects the extracted instruction information into the automatic control system and adjusts the vehicle's driving control. The input is the instruction information from step 3, and the output is the control command. In this process, the output is generated in a format compatible with the control system and immediately applied to the vehicle's operation.

[0519] Step 5:

[0520] The user can review system feedback as needed and provide additional instructions via voice. The input is the new voice instruction from the user, and the output is the voice data looped back to step 1 for reprocessing. This feedback loop allows for continuous optimization of the operating conditions.

[0521] 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.

[0522] This invention is a system that not only acquires meeting audio in real time and converts it into text data to extract important information, but also reads emotions from participants' voices and applies this information to the meeting recording and follow-up process. In this embodiment, the system operates as follows.

[0523] The user activates the system at the start of the meeting, and the terminal acquires the meeting audio in real time using the audio acquisition unit. The acquired audio data is converted into text data using speech recognition technology. This allows the content of the meeting to be quickly saved as text.

[0524] In addition, the server uses an emotion engine to analyze the user's emotions from the audio data. The emotion engine determines the participant's emotional state by analyzing the intonation, speed, and other parameters of the voice. The emotional information obtained here is incorporated into text data extracted using natural language processing techniques and reflected in the meeting minutes.

[0525] The server automatically generates meeting minutes with emotional information. In addition to the text data of what was said, these minutes record the emotional state at the time of the statement, which helps to understand the atmosphere of the meeting and the reactions of the participants.

[0526] Next, emotional information is also used to generate and prioritize follow-up tasks. Specifically, the server uses the user's emotional information to re-evaluate the urgency and importance of tasks and determine the need for follow-up. This automatically determines who should prioritize which tasks and assigns them to the appropriate personnel.

[0527] For example, if there is significant interest in feedback on a new product during a meeting, the server will use sentiment engine analysis of the participants to identify the high level of user interest in that product. As a result, it will prioritize tasks related to the new product, promptly notify those responsible, and support efficient project progress.

[0528] In this way, the system combines speech recognition and sentiment analysis to enhance meeting recording and subsequent business processes, enabling a dramatic improvement in corporate operational efficiency.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] The user activates the system at the start of the meeting. This initiates the operation of the terminal, including the audio acquisition unit, and prepares it to acquire meeting audio in real time.

[0532] Step 2:

[0533] The terminal uses speech recognition technology to convert the audio collected from the meeting into text data. The audio data is then transcribed with high accuracy by the platform and immediately sent to the server.

[0534] Step 3:

[0535] The server applies natural language processing techniques to the received text data to extract the meeting summary and key points. During this process, the information is organized and prepared as the source data for the meeting record.

[0536] Step 4:

[0537] Simultaneously, the device uses an emotion engine to analyze the tone and pitch of the user's voice from the audio data and performs emotion queries. This identifies the emotional state behind each statement.

[0538] Step 5:

[0539] The server integrates the sentiment analysis results into the meeting minutes data. Sentimental information associated with each statement is added, making the reactions of each participant during the meeting clearer.

[0540] Step 6:

[0541] The server generates follow-up tasks using meeting minutes with sentiment information. Sentiment information influences the determination of task importance and priority, highlighting issues that require immediate attention from the user.

[0542] Step 7:

[0543] The server uses a task management tool to assign follow-up tasks to the appropriate personnel, and is configured to make tasks immediately visible. The system automatically optimizes the allocation based on each person's workload and interests.

[0544] Step 8:

[0545] After a meeting, users track the progress of their tasks through a task management tool. The system can evaluate their focus on priority tasks based on sentiment analysis, and revise countermeasures as needed.

[0546] (Example 2)

[0547] 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."

[0548] Modern business meetings involve the frequent exchange of large amounts of information, necessitating rapid and accurate recording of meeting content and follow-up based on participants' emotional states. However, traditional methods often involve manual transcription of speech and emotional analysis, which is time-consuming and labor-intensive, and results in inconsistent recording accuracy and follow-up quality. Therefore, it is crucial to achieve efficient meeting management and follow-up through automated speech conversion and the utilization of emotional information.

[0549] 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.

[0550] In this invention, the server includes means for acquiring meeting audio in real time using an acoustic acquisition device, means for converting the acquired audio into text data using speech recognition technology, and means for analyzing the emotional state of speakers from the audio data using emotion analysis technology. This makes it possible to automatically transcribe meeting audio information into text and quickly analyze the emotional state of participants. Furthermore, this information can be used to extract important information and automatically generate meeting minutes, and to automatically generate and prioritize follow-up tasks that reflect the emotional information. This leads to improved efficiency and quality of work.

[0551] An "acoustic acquisition device" is a device used to acquire sound as a digital signal in settings such as meetings.

[0552] "Voice recognition technology" is a technology that analyzes acquired voice data and automatically converts it into corresponding text data.

[0553] "Text data" refers to text information converted from speech, specifically a written record of the presentations given at a meeting.

[0554] "Emotional analysis technology" is a technology that analyzes voice data to determine the emotional state of the speaker.

[0555] "Meeting minutes" are documents that record the content of conversations during a meeting, including the emotional state of the participants at the time.

[0556] "Follow-up tasks" are the work or tasks that need to be done after a meeting, and are generated based on the meeting minutes.

[0557] A "business management device" is a device used to manage the progress and priorities of follow-up tasks and to inform relevant parties of the results.

[0558] This invention is a system that efficiently acquires audio information from meetings, transcribes it into text, and analyzes and records emotional information based on that text, thereby automatically generating and managing follow-up tasks.

[0559] The user activates the system at the start of the meeting. The hardware used is a terminal equipped with an audio acquisition device. The terminal acquires meeting audio in real time and converts it into text data using speech recognition technology. Software such as the Google Speech-to-Text API can be used for this speech recognition.

[0560] Next, the server uses emotion analysis technology to analyze the acquired audio data and determine the emotional state at the time of speaking. In this process, emotion analysis tools such as IBM Watson Tone Analyzer are used to evaluate elements such as intonation and speed of speech and identify emotions.

[0561] The generated text data and emotional information are unified by the server and automatically compiled into meeting minutes. These minutes include detailed descriptions of what was said, along with the emotional state at the time, allowing for a clearer understanding of the participants' attitudes and reactions.

[0562] Furthermore, this sentiment information is also used to generate and prioritize follow-up tasks. Based on meeting minutes and sentiment states, the server evaluates the urgency and importance of tasks. This allows the task management system to assign tasks to the appropriate personnel, manage progress, and support an efficient post-meeting process.

[0563] For example, if a new service is discussed in a meeting and participants show high interest, the server can analyze their sentiment, prioritize related tasks, and quickly notify the appropriate person. This system allows companies to improve meeting productivity and prevent delays or inadequate follow-up.

[0564] An example of a prompt would be, "Please provide an overview of the follow-up tasks generated as a result of converting the meeting audio data to text and performing sentiment analysis."

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] The user activates the system at the start of the meeting. Once activated, the system prepares to begin acquiring meeting audio. The input here is an acoustic acquisition device that receives the audio signal. The output is the real-time collection of meeting audio.

[0568] Step 2:

[0569] The terminal uses an acoustic acquisition device to capture conference audio in real time. In this step, the conference audio is converted into a digital signal for use in subsequent analysis steps. The input is continuous audio data from the acoustic acquisition device. The output is in the form of a digital audio signal, which is passed on to the next step.

[0570] Step 3:

[0571] The device uses speech recognition technology to convert acquired speech into text data. Specifically, it analyzes the speech signal using APIs such as the Google Speech-to-Text API and generates the corresponding text. The input is a digital speech signal, and the output is the spoken content as text data.

[0572] Step 4:

[0573] The server utilizes emotion analysis technology to analyze the speaker's emotional state from audio data. For example, it evaluates the intonation, speed, and volume of the speech to identify emotions. The input is a digital audio signal and corresponding text data, and the output is numerical or categorical information indicating the speaker's emotional state.

[0574] Step 5:

[0575] The server combines text data and sentiment information to automatically generate meeting minutes that reflect the participants' statements and emotional states. In this step, the meeting record is comprehensively documented. The input is text data and sentiment information, and the output is a documented meeting record.

[0576] Step 6:

[0577] The server automatically generates follow-up tasks and sets priorities based on the generated meeting minutes and sentiment states. Here, the urgency and importance of the tasks are re-evaluated, and preparations are made for managing their progress in conjunction with the task management system. The input is the meeting record document, and the output is a prioritized list of follow-up tasks.

[0578] Step 7:

[0579] The server uses a task management system to assign follow-up tasks to appropriate personnel and monitors and manages their progress. Specifically, it notifies personnel of task details through a notification system and collects progress data. The input is a list of follow-up tasks, and the output is management information related to the progress of the tasks.

[0580] (Application Example 2)

[0581] 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."

[0582] In modern workplaces and homes, information sharing through meetings and conversations is highly valued, but the quality of communication can decline if appropriate follow-up is not conducted with an understanding of participants' emotions. In this situation, there is a need to improve the efficiency and quality of communication by understanding emotional states and automating and managing follow-up tasks.

[0583] 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.

[0584] In this invention, the server includes means for acquiring acoustic information of a meeting in real time using an acoustic information acquisition unit, means for converting the acquired acoustic information into document data using acoustic recognition technology, and emotion analysis means for analyzing the emotional state of participants from the acoustic data. This enables the automated management of conversation recordings and prioritized follow-up tasks based on emotional states.

[0585] An "acoustic information acquisition unit" is a device or group of devices for acquiring acoustic information in real time.

[0586] "Acoustic recognition technology" is a technology for converting acquired acoustic information into document data.

[0587] "Natural language processing technology" is a technique used to extract important information from document data.

[0588] "Emotional analysis means" refers to a technology or device for analyzing the emotional state of participants from their acoustic data.

[0589] "Meeting minutes" are documents that record the content of meetings and gatherings, and include important information and emotional states.

[0590] "Follow-up tasks" refer to a series of tasks performed to implement and manage the decisions made at meetings and gatherings.

[0591] A "task management tool" is software or a system used to track and manage the progress of follow-up tasks.

[0592] To implement this invention, a consumer robot is first equipped with an acoustic information acquisition unit. This allows the robot to acquire ambient sounds and conversations in real time when a meeting begins in a user's home or office. Software implementing acoustic recognition technology runs within the terminal and converts the real-time acquired acoustic information into document data. Acoustic recognition technologies such as the Google Cloud Speech-to-Text API are used in this process.

[0593] The server receives the converted document data and extracts important information using natural language processing techniques. The accuracy of the extraction can be improved by utilizing libraries such as the Natural Language Toolkit (NLTK) and TensorFlow.

[0594] Furthermore, as a means of emotion analysis, a system that analyzes participants' emotional states from acoustic data is operated on a server. This system analyzes the intonation and speed of the sounds to determine the emotional state. The generated emotional information is integrated with document data and reflected in the meeting minutes.

[0595] As a concrete example, during a family meeting at home, the robot can record each member's opinions and emotional state, and prioritize follow-up tasks for topics that show particularly high interest. Such a system facilitates smoother communication within the family and promotes decision-making.

[0596] Example of a prompt:

[0597] "Let's begin the meeting about our next family trip. Please have the robot record what we discussed today and pay particular attention to its emotional responses."

[0598] Thus, a specific embodiment of this invention is that consumer robots function as an important tool for improving the quality of communication.

[0599] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0600] Step 1:

[0601] The terminal uses an acoustic information acquisition unit to record acoustic information of the meeting in real time. The input is ambient sound and conversation sounds, and the output is digital acoustic data. This acoustic data is sent to a server for further processing.

[0602] Step 2:

[0603] The server converts received acoustic data into document data using acoustic recognition technology. The input is digital acoustic data, and the output is document data in text format. It uses the Google Cloud Speech-to-Text API to analyze the acoustic waveform and convert it into word by word.

[0604] Step 3:

[0605] The server analyzes the generated document data using natural language processing techniques and extracts important information. The input is document data generated by speech recognition, and the output is important information such as key feedback and issues. Natural Language Toolkit (NLTK) is used for part-of-speech tagging and semantic analysis.

[0606] Step 4:

[0607] The server analyzes the emotional state of participants using sentiment analysis techniques based on the input acoustic data. The input is acoustic data, and the output is data indicating the emotional state for each statement. This uses machine learning models to evaluate changes in the speaker's tone and pace.

[0608] Step 5:

[0609] The server integrates the generated key information and emotional states to create meeting minutes. The input is key information and emotional states, and the output is a detailed meeting minute containing both. This meeting minute is then visualized for users and relevant parties.

[0610] Step 6:

[0611] Users review follow-up tasks based on meeting minutes and sentiment information, and prioritize tasks as needed. Input is meeting minutes, and output is task lists and priority settings. Notifications and task adjustments are handled through the user interface.

[0612] Step 7:

[0613] The server works in conjunction with the task management tool to monitor the progress of follow-up tasks and sends notifications of delays or incomplete tasks to relevant parties as needed. Inputs are progress status and completion data, while outputs are tracked task status and action instruction notifications. This is implemented using API integration with the task management platform.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] This invention is an embodiment of an integrated system that acquires meeting audio in real time, converts that audio into text data, and automatically extracts and manages important information. Specifically, it operates as follows:

[0632] First, the user activates the system at the start of the meeting. The activated terminal captures audio during the meeting using its built-in voice acquisition function or an external microphone device. The captured audio is then converted into text data by the terminal using speech recognition technology. The speech recognition technology is designed to handle a wide variety of audio data, enabling accurate text conversion.

[0633] Next, the server receives the text data and applies natural language processing technology. This extracts the important agenda items and decisions made during the meeting, and automatically generates meeting minutes based on this information. These minutes are clearly organized and easy to understand, helping to quickly grasp the overall picture of the meeting. Furthermore, they include action items and next steps that were pointed out during the meeting.

[0634] Next, the generated meeting minutes are analyzed by the server, and follow-up tasks are automatically created. These tasks are assigned to designated personnel. Task assignment is carried out in conjunction with task management tools used within the organization, and is smoothly reflected through APIs such as those of project management systems.

[0635] The server has the functionality to track these tasks and constantly monitor their progress. Progress information is notified to the person in charge via the task management tool platform, allowing them to immediately check the completion status of tasks and the percentage of incomplete tasks. In this way, information leaks and overlooked tasks are prevented, contributing to improved work efficiency.

[0636] As a concrete example, if the implementation schedule for a new feature changes during a product development meeting, users are immediately listed as a critical issue. This information is then reflected in subsequent follow-up tasks and assigned to the relevant development team members, resulting in transparent and efficient project management.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The user activates the AI ​​agent at the start of the meeting. The terminal that receives the activation command prepares to activate its audio acquisition unit in order to acquire meeting audio.

[0640] Step 2:

[0641] The terminal records audio data collected during the meeting via an audio acquisition unit. The recorded audio data is prepared in real time for speech recognition technology and processed quickly.

[0642] Step 3:

[0643] The device inputs recorded audio data into speech recognition technology and converts it into text data. The speech recognition results are optimized for high accuracy, and the converted text data is saved locally.

[0644] Step 4:

[0645] The server receives text data and analyzes it using natural language processing technology. Through this analysis, important meeting topics, speaker information, action items, and other relevant details are automatically extracted.

[0646] Step 5:

[0647] The server automatically generates meeting minutes based on the analysis results. The generated minutes are presented in a well-organized format, clearly indicating the key points and decisions of the meeting, and are prepared for easy sharing with relevant parties.

[0648] Step 6:

[0649] The server generates follow-up tasks from the meeting minutes. These tasks include action items decided at the meeting and incorporate necessary assignee information. This clearly identifies which tasks should be assigned to which individuals.

[0650] Step 7:

[0651] The server integrates task information into the task management tool. Tasks are registered via the management tool's API, and a system is in place to monitor progress in real time. In case of failure or delay, the system is configured to quickly notify relevant parties.

[0652] Step 8:

[0653] Users can check task progress through task management tools and take corrective actions as needed. This monitoring function is used to maximize work efficiency and productivity.

[0654] (Example 1)

[0655] 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".

[0656] Efficient management of audio information during meetings is essential to prevent overlooking important information and delaying tasks. In particular, the failure to accurately record important content after meetings and the resulting inadequate management of follow-up tasks can hinder project progress.

[0657] 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.

[0658] In this invention, the server includes means for acquiring meeting audio in real time using a receiving device, means for converting the acquired audio into text information using a speech recognition method, and means for extracting important information from the text information using natural language processing technology. This makes it possible to accurately record the key points of a meeting and to automatically generate and manage follow-up tasks.

[0659] A "receiving device" is a hardware or software system for acquiring audio during a meeting in real time.

[0660] A "speech recognition method" is a technical technique that analyzes acquired speech data and converts it into text information.

[0661] "Natural language processing technology" is a field of computer science that extracts and analyzes important information from text.

[0662] "Text information" refers to character information converted from audio data using speech recognition methods.

[0663] "Important information" refers to the topics and action items necessary for decision-making and follow-up during a meeting.

[0664] A "record document" is a document that is automatically generated based on extracted key information and summarizes the main points of a meeting.

[0665] A "tracking task" is an action item derived from the generated record document that is necessary for the progress of the work.

[0666] "Progress management techniques" are techniques for monitoring and appropriately managing the completion status and progress of tasks.

[0667] A "related party" is any person or entity that is directly responsible for or may be affected by the progress of the generated tracking task.

[0668] This invention is an integrated system for the efficient acquisition, conversion, analysis, and management of conference audio. Its embodiments are described in detail below.

[0669] The user activates the system when starting a meeting. This allows the terminal to capture audio in real time during the meeting using its built-in microphone or an external microphone device. While a standard audio capture device is used for audio acquisition, a high-sensitivity microphone with noise-canceling capabilities can reduce ambient noise and capture clear audio.

[0670] The acquired audio data is processed on the device and converted into text information using speech recognition software such as the Google Speech-to-Text API or Amazon Transcribe. This speech recognition process analyzes the audio information and outputs it as text, thereby achieving text conversion.

[0671] The generated text information is then sent to a server, where important information is extracted using natural language processing techniques. For example, by utilizing SpaCy, a Python library, contextual analysis can be performed to extract agenda items and important decisions.

[0672] Based on the extracted key information, the server automatically generates a record document. This document clarifies the key points of the meeting and serves as an important resource for scheduling appointments and reviewing decisions made later.

[0673] Furthermore, the server creates tracking tasks from the generated record documents, which are then properly managed by a progress management system that integrates with progress tracking technology. By utilizing APIs such as Asana and Trello, the generated tasks are smoothly reflected in these progress management tools and assigned to the responsible parties.

[0674] In this way, the server can constantly monitor progress and notify relevant parties if there are delays or incomplete tasks.

[0675] As a concrete example, the prompt "Extract important decisions from the following meeting minutes and create action items" is entered into the AI. This automatically extracts the critical information and suggests the next steps. This makes it easier to manage meeting content and allows subsequent actions to proceed efficiently.

[0676] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0677] Step 1:

[0678] The user activates the system at the start of the meeting. This action puts the terminal into a state where it can acquire audio during the meeting. The input is the audio signal acquired through the microphone device, and this signal is converted into digital audio data by the audio capture system inside the terminal. The output is audio data in digital format.

[0679] Step 2:

[0680] The device passes the acquired digital audio data to speech recognition software. This software analyzes the audio data using APIs such as the Google Speech-to-Text API and outputs it as text. The input is digital audio data, and the output is converted text information. Specifically, the process involves analyzing the pattern of the sound wave signal and converting it into a language structure.

[0681] Step 3:

[0682] The server receives text information sent from the terminal and extracts important information using natural language processing techniques. The input is text data related to a meeting, and the output is important information including agenda items and decisions. Specifically, the process involves identifying nouns and verbs within the text and analyzing the context of the sentences related to them.

[0683] Step 4:

[0684] The server automatically generates record documents based on the extracted key information. The input is the key information obtained in step 3, and the output is a well-organized meeting minutes-style document. In this process, the information is logically structured and output in a format that is easy to use for project progress and decision-making.

[0685] Step 5:

[0686] The server automatically generates tracking tasks from the generated record documents. The input is the action items contained in the meeting minutes, and the output is a list of tracking tasks. Specifically, it is a procedure to document tasks based on the necessary actions and instructions, and register them in the management system.

[0687] Step 6:

[0688] The server integrates with progress management technology to reflect generated tasks in related systems. The input is a list of tracked tasks, and the output is the status of their implementation in task management tools. This operation includes sending information via API and assigning tasks to assigned personnel.

[0689] Step 7:

[0690] The server monitors task progress in real time and notifies relevant parties as needed. Input is task progress data, and output is notifications to relevant parties. This process includes the ability to measure the degree of task completion and immediately notify if non-completion is suspected.

[0691] (Application Example 1)

[0692] 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".

[0693] In modern times, the development of autonomous driving technology has created a demand for driver assistance in vehicles. Efficiently acquiring instructions and safety-related information within autonomous vehicles and processing it in real time is crucial for safe driving and operational optimization. This invention aims to acquire such instruction information as voice, rapidly analyze it, and reflect it in the system.

[0694] 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.

[0695] In this invention, the server includes means for acquiring audio signals in real time using an audio acquisition unit, means for converting the acquired audio signals into text data using speech recognition technology, and means for analyzing instruction information in the driving environment in real time and reflecting it in the automatic control system. This enables efficient analysis of instruction information within an autonomous vehicle, allowing for safe and rapid driving control.

[0696] A "voice acquisition unit" is a device or system for acquiring voice signals in real time.

[0697] "Speech recognition technology" is a technology that converts acquired speech signals into text data.

[0698] "Natural language processing technology" is a technique for extracting and analyzing important information from text data.

[0699] "Information records" refer to documents or data that are automatically generated based on extracted important information.

[0700] A "follow-up task" is a subsequent task or instruction that is automatically generated from the generated information record.

[0701] A "task management system" is a system for monitoring and managing the progress of follow-up tasks.

[0702] "Driving environment" is a concept that refers to the surrounding conditions and circumstances while an autonomous vehicle is in motion.

[0703] "Instructional information" refers to commands and requests given verbally by drivers, passengers, etc.

[0704] An "automatic control system" is a system that automatically adjusts the vehicle's operation based on instruction information.

[0705] This system aims to effectively acquire and analyze instruction information within autonomous vehicles. The server uses a voice acquisition unit to acquire in-vehicle audio signals in real time. These acquired audio signals are then converted into text data using speech recognition technology.

[0706] The server applies natural language processing techniques to the converted text data to analyze important driving instructions. The instructions extracted through this analysis are then reflected in the automated control system in real time, ensuring proper vehicle control.

[0707] Users can instruct the system to change destinations or update driving information through simple voice commands. This improves driving efficiency and safety. For example, if a passenger instructs the system to change destinations by voice, the instruction is analyzed as text data, and the navigation system is quickly updated.

[0708] An example of a prompt message for a generated AI model might be: "Design a system that analyzes voice commands while driving and immediately reflects changes in the destination." This prompt message specifically describes the system's function and serves as a guide for realizing the necessary information processing while driving.

[0709] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0710] Step 1:

[0711] The terminal uses an audio acquisition unit to acquire audio signals from passengers and drivers in real time. The input is an audio signal, and the output is raw audio data. This audio data is acquired at a constant sampling rate and converted to a digital format for subsequent processing.

[0712] Step 2:

[0713] The server converts the acquired audio data into text data using speech recognition technology. The input is the audio data from step 1, and the output is parseable text data. This process uses a generative AI model in the speech recognition system to process the data to handle diverse pronunciations and noise.

[0714] Step 3:

[0715] The server analyzes the obtained text data using natural language processing technology and extracts the instruction information necessary for driving. The input is the text data from step 2, and the output is the instruction information. At this stage, keywords and context are analyzed from the text, and a generative AI model is used to evaluate the urgency and priority of the instructions.

[0716] Step 4:

[0717] The server reflects the extracted instruction information into the automatic control system and adjusts the vehicle's driving control. The input is the instruction information from step 3, and the output is the control command. In this process, the output is generated in a format compatible with the control system and immediately applied to the vehicle's operation.

[0718] Step 5:

[0719] The user can review system feedback as needed and provide additional instructions via voice. The input is the new voice instruction from the user, and the output is the voice data looped back to step 1 for reprocessing. This feedback loop allows for continuous optimization of the operating conditions.

[0720] 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.

[0721] This invention is a system that not only acquires meeting audio in real time and converts it into text data to extract important information, but also reads emotions from participants' voices and applies this information to the meeting recording and follow-up process. In this embodiment, the system operates as follows.

[0722] The user activates the system at the start of the meeting, and the terminal acquires the meeting audio in real time using the audio acquisition unit. The acquired audio data is converted into text data using speech recognition technology. This allows the content of the meeting to be quickly saved as text.

[0723] In addition, the server uses an emotion engine to analyze the user's emotions from the audio data. The emotion engine determines the participant's emotional state by analyzing the intonation, speed, and other parameters of the voice. The emotional information obtained here is incorporated into text data extracted using natural language processing techniques and reflected in the meeting minutes.

[0724] The server automatically generates meeting minutes with emotional information. In addition to the text data of what was said, these minutes record the emotional state at the time of the statement, which helps to understand the atmosphere of the meeting and the reactions of the participants.

[0725] Next, emotional information is also used to generate and prioritize follow-up tasks. Specifically, the server uses the user's emotional information to re-evaluate the urgency and importance of tasks and determine the need for follow-up. This automatically determines who should prioritize which tasks and assigns them to the appropriate personnel.

[0726] For example, if there is significant interest in feedback on a new product during a meeting, the server will use sentiment engine analysis of the participants to identify the high level of user interest in that product. As a result, it will prioritize tasks related to the new product, promptly notify those responsible, and support efficient project progress.

[0727] In this way, the system combines speech recognition and sentiment analysis to enhance meeting recording and subsequent business processes, enabling a dramatic improvement in corporate operational efficiency.

[0728] The following describes the processing flow.

[0729] Step 1:

[0730] The user activates the system at the start of the meeting. This initiates the operation of the terminal, including the audio acquisition unit, and prepares it to acquire meeting audio in real time.

[0731] Step 2:

[0732] The terminal uses speech recognition technology to convert the audio collected from the meeting into text data. The audio data is then transcribed with high accuracy by the platform and immediately sent to the server.

[0733] Step 3:

[0734] The server applies natural language processing techniques to the received text data to extract the meeting summary and key points. During this process, the information is organized and prepared as the source data for the meeting record.

[0735] Step 4:

[0736] Simultaneously, the device uses an emotion engine to analyze the tone and pitch of the user's voice from the audio data and performs emotion queries. This identifies the emotional state behind each statement.

[0737] Step 5:

[0738] The server integrates the sentiment analysis results into the meeting minutes data. Sentimental information associated with each statement is added, making the reactions of each participant during the meeting clearer.

[0739] Step 6:

[0740] The server generates follow-up tasks using meeting minutes with sentiment information. Sentiment information influences the determination of task importance and priority, highlighting issues that require immediate attention from the user.

[0741] Step 7:

[0742] The server uses a task management tool to assign follow-up tasks to the appropriate personnel, and is configured to make tasks immediately visible. The system automatically optimizes the allocation based on each person's workload and interests.

[0743] Step 8:

[0744] After a meeting, users track the progress of their tasks through a task management tool. The system can evaluate their focus on priority tasks based on sentiment analysis, and revise countermeasures as needed.

[0745] (Example 2)

[0746] 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".

[0747] Modern business meetings involve the frequent exchange of large amounts of information, necessitating rapid and accurate recording of meeting content and follow-up based on participants' emotional states. However, traditional methods often involve manual transcription of speech and emotional analysis, which is time-consuming and labor-intensive, and results in inconsistent recording accuracy and follow-up quality. Therefore, it is crucial to achieve efficient meeting management and follow-up through automated speech conversion and the utilization of emotional information.

[0748] 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.

[0749] In this invention, the server includes means for acquiring meeting audio in real time using an acoustic acquisition device, means for converting the acquired audio into text data using speech recognition technology, and means for analyzing the emotional state of speakers from the audio data using emotion analysis technology. This makes it possible to automatically transcribe meeting audio information into text and quickly analyze the emotional state of participants. Furthermore, this information can be used to extract important information and automatically generate meeting minutes, and to automatically generate and prioritize follow-up tasks that reflect the emotional information. This leads to improved efficiency and quality of work.

[0750] An "acoustic acquisition device" is a device used to acquire sound as a digital signal in settings such as meetings.

[0751] "Voice recognition technology" is a technology that analyzes acquired voice data and automatically converts it into corresponding text data.

[0752] "Text data" refers to text information converted from speech, specifically a written record of the presentations given at a meeting.

[0753] "Emotional analysis technology" is a technology that analyzes voice data to determine the emotional state of the speaker.

[0754] "Meeting minutes" are documents that record the content of conversations during a meeting, including the emotional state of the participants at the time.

[0755] "Follow-up tasks" are the work or tasks that need to be done after a meeting, and are generated based on the meeting minutes.

[0756] A "business management device" is a device used to manage the progress and priorities of follow-up tasks and to inform relevant parties of the results.

[0757] This invention is a system that efficiently acquires audio information from meetings, transcribes it into text, and analyzes and records emotional information based on that text, thereby automatically generating and managing follow-up tasks.

[0758] The user activates the system at the start of the meeting. The hardware used is a terminal equipped with an audio acquisition device. The terminal acquires meeting audio in real time and converts it into text data using speech recognition technology. Software such as the Google Speech-to-Text API can be used for this speech recognition.

[0759] Next, the server uses emotion analysis technology to analyze the acquired audio data and determine the emotional state at the time of speaking. In this process, emotion analysis tools such as IBM Watson Tone Analyzer are used to evaluate elements such as intonation and speed of speech and identify emotions.

[0760] The generated text data and emotional information are unified by the server and automatically compiled into meeting minutes. These minutes include detailed descriptions of what was said, along with the emotional state at the time, allowing for a clearer understanding of the participants' attitudes and reactions.

[0761] Furthermore, this sentiment information is also used to generate and prioritize follow-up tasks. Based on meeting minutes and sentiment states, the server evaluates the urgency and importance of tasks. This allows the task management system to assign tasks to the appropriate personnel, manage progress, and support an efficient post-meeting process.

[0762] For example, if a new service is discussed in a meeting and participants show high interest, the server can analyze their sentiment, prioritize related tasks, and quickly notify the appropriate person. This system allows companies to improve meeting productivity and prevent delays or inadequate follow-up.

[0763] An example of a prompt would be, "Please provide an overview of the follow-up tasks generated as a result of converting the meeting audio data to text and performing sentiment analysis."

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] The user activates the system at the start of the meeting. Once activated, the system prepares to begin acquiring meeting audio. The input here is an acoustic acquisition device that receives the audio signal. The output is the real-time collection of meeting audio.

[0767] Step 2:

[0768] The terminal uses an acoustic acquisition device to capture conference audio in real time. In this step, the conference audio is converted into a digital signal for use in subsequent analysis steps. The input is continuous audio data from the acoustic acquisition device. The output is in the form of a digital audio signal, which is passed on to the next step.

[0769] Step 3:

[0770] The device uses speech recognition technology to convert acquired speech into text data. Specifically, it analyzes the speech signal using APIs such as the Google Speech-to-Text API and generates the corresponding text. The input is a digital speech signal, and the output is the spoken content as text data.

[0771] Step 4:

[0772] The server utilizes emotion analysis technology to analyze the speaker's emotional state from audio data. For example, it evaluates the intonation, speed, and volume of the speech to identify emotions. The input is a digital audio signal and corresponding text data, and the output is numerical or categorical information indicating the speaker's emotional state.

[0773] Step 5:

[0774] The server combines text data and sentiment information to automatically generate meeting minutes that reflect the participants' statements and emotional states. In this step, the meeting record is comprehensively documented. The input is text data and sentiment information, and the output is a documented meeting record.

[0775] Step 6:

[0776] The server automatically generates follow-up tasks and sets priorities based on the generated meeting minutes and sentiment states. Here, the urgency and importance of the tasks are re-evaluated, and preparations are made for managing their progress in conjunction with the task management system. The input is the meeting record document, and the output is a prioritized list of follow-up tasks.

[0777] Step 7:

[0778] The server uses a task management system to assign follow-up tasks to appropriate personnel and monitors and manages their progress. Specifically, it notifies personnel of task details through a notification system and collects progress data. The input is a list of follow-up tasks, and the output is management information related to the progress of the tasks.

[0779] (Application Example 2)

[0780] 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".

[0781] In modern workplaces and homes, information sharing through meetings and conversations is highly valued, but the quality of communication can decline if appropriate follow-up is not conducted with an understanding of participants' emotions. In this situation, there is a need to improve the efficiency and quality of communication by understanding emotional states and automating and managing follow-up tasks.

[0782] 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.

[0783] In this invention, the server includes means for acquiring acoustic information of a meeting in real time using an acoustic information acquisition unit, means for converting the acquired acoustic information into document data using acoustic recognition technology, and emotion analysis means for analyzing the emotional state of participants from the acoustic data. This enables the automated management of conversation recordings and prioritized follow-up tasks based on emotional states.

[0784] An "acoustic information acquisition unit" is a device or group of devices for acquiring acoustic information in real time.

[0785] "Acoustic recognition technology" is a technology for converting acquired acoustic information into document data.

[0786] "Natural language processing technology" is a technique used to extract important information from document data.

[0787] "Emotional analysis means" refers to a technology or device for analyzing the emotional state of participants from their acoustic data.

[0788] "Meeting minutes" are documents that record the content of meetings and gatherings, and include important information and emotional states.

[0789] "Follow-up tasks" refer to a series of tasks performed to implement and manage the decisions made at meetings and gatherings.

[0790] A "task management tool" is software or a system used to track and manage the progress of follow-up tasks.

[0791] To implement this invention, a consumer robot is first equipped with an acoustic information acquisition unit. This allows the robot to acquire ambient sounds and conversations in real time when a meeting begins in a user's home or office. Software implementing acoustic recognition technology runs within the terminal and converts the real-time acquired acoustic information into document data. Acoustic recognition technologies such as the Google Cloud Speech-to-Text API are used in this process.

[0792] The server receives the converted document data and extracts important information using natural language processing techniques. The accuracy of the extraction can be improved by utilizing libraries such as the Natural Language Toolkit (NLTK) and TensorFlow.

[0793] Furthermore, as a means of emotion analysis, a system that analyzes participants' emotional states from acoustic data is operated on a server. This system analyzes the intonation and speed of the sounds to determine the emotional state. The generated emotional information is integrated with document data and reflected in the meeting minutes.

[0794] As a concrete example, during a family meeting at home, the robot can record each member's opinions and emotional state, and prioritize follow-up tasks for topics that show particularly high interest. Such a system facilitates smoother communication within the family and promotes decision-making.

[0795] Example of a prompt:

[0796] "Let's begin the meeting about our next family trip. Please have the robot record what we discussed today and pay particular attention to its emotional responses."

[0797] Thus, a specific embodiment of this invention is that consumer robots function as an important tool for improving the quality of communication.

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] The terminal uses an acoustic information acquisition unit to record acoustic information of the meeting in real time. The input is ambient sound and conversation sounds, and the output is digital acoustic data. This acoustic data is sent to a server for further processing.

[0801] Step 2:

[0802] The server converts received acoustic data into document data using acoustic recognition technology. The input is digital acoustic data, and the output is document data in text format. It uses the Google Cloud Speech-to-Text API to analyze the acoustic waveform and convert it into word by word.

[0803] Step 3:

[0804] The server analyzes the generated document data using natural language processing techniques and extracts important information. The input is document data generated by speech recognition, and the output is important information such as key feedback and issues. Natural Language Toolkit (NLTK) is used for part-of-speech tagging and semantic analysis.

[0805] Step 4:

[0806] The server analyzes the emotional state of participants using sentiment analysis techniques based on the input acoustic data. The input is acoustic data, and the output is data indicating the emotional state for each statement. This uses machine learning models to evaluate changes in the speaker's tone and pace.

[0807] Step 5:

[0808] The server integrates the generated key information and emotional states to create meeting minutes. The input is key information and emotional states, and the output is a detailed meeting minute containing both. This meeting minute is then visualized for users and relevant parties.

[0809] Step 6:

[0810] Users review follow-up tasks based on meeting minutes and sentiment information, and prioritize tasks as needed. Input is meeting minutes, and output is task lists and priority settings. Notifications and task adjustments are handled through the user interface.

[0811] Step 7:

[0812] The server works in conjunction with the task management tool to monitor the progress of follow-up tasks and sends notifications of delays or incomplete tasks to relevant parties as needed. Inputs are progress status and completion data, while outputs are tracked task status and action instruction notifications. This is implemented using API integration with the task management platform.

[0813] 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.

[0814] 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.

[0815] 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 robot 414.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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."

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] A means of acquiring meeting audio in real time using an audio acquisition unit,

[0837] A means of converting speech acquired using speech recognition technology into text data,

[0838] A method for extracting important information from text data using natural language processing technology,

[0839] A means of automatically generating meeting minutes based on extracted important information,

[0840] A method for automatically generating follow-up tasks from the generated meeting minutes,

[0841] A means of managing the progress of follow-up tasks by integrating with a task management tool,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, comprising means for automatically assigning follow-up tasks to responsible persons based on extracted important information.

[0845] (Claim 3)

[0846] The system according to claim 1, which includes means for identifying delays or incomplete tasks based on progress management information and notifying relevant parties.

[0847] "Example 1"

[0848] (Claim 1)

[0849] A means of acquiring conference audio in real time using a receiving device,

[0850] A means of converting speech acquired using a speech recognition method into text information,

[0851] A method for extracting important information from text information using natural language processing technology,

[0852] A means for automatically generating record documents based on extracted important information,

[0853] A means for automatically generating tracking tasks from generated record documents,

[0854] A means of managing the progress of tracking tasks in conjunction with progress management technology,

[0855] A means of updating task completion information based on progress and notifying relevant parties,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising means for automatically assigning tracking tasks to responsible persons based on extracted important information.

[0859] (Claim 3)

[0860] The system according to claim 1, which includes means for identifying delays or incomplete tasks based on progress management information and notifying relevant parties.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] A means for acquiring audio signals in real time using an audio acquisition unit,

[0864] A means of converting an audio signal acquired using speech recognition technology into text data,

[0865] A method for extracting important information from text data using natural language processing technology,

[0866] A means for automatically generating information records based on extracted important information,

[0867] A means for automatically generating follow-up tasks from the generated information records,

[0868] A means of managing the progress of follow-up tasks in conjunction with a task management system,

[0869] A means of analyzing instruction information in the driving environment in real time and reflecting it in the automatic control system,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, which automatically assigns follow-up tasks to a designated person based on extracted important information.

[0873] (Claim 3)

[0874] The system according to claim 1, which identifies delays or incomplete tasks based on progress management information and notifies the relevant persons.

[0875] "Example 2 of combining an emotion engine"

[0876] (Claim 1)

[0877] A means of acquiring meeting audio in real time using an acoustic acquisition device,

[0878] A means of converting speech acquired using speech recognition technology into text data,

[0879] A method for extracting important information from text data using natural language processing technology,

[0880] A method for analyzing the emotional state of an utterance from audio data using emotion analysis technology,

[0881] A means for automatically generating meeting minutes based on extracted important information and emotional states,

[0882] A means of automatically generating and prioritizing follow-up tasks based on the generated meeting minutes and emotional state,

[0883] A means of managing the progress of follow-up tasks in conjunction with a business management system,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, comprising means for automatically assigning follow-up tasks to the person in charge.

[0887] (Claim 3)

[0888] The system according to claim 1, which includes means for identifying delays or incompleteness in work based on progress management information and notifying relevant parties.

[0889] "Application example 2 when combining with an emotional engine"

[0890] (Claim 1)

[0891] A means of acquiring acoustic information of a meeting in real time using an acoustic information acquisition unit,

[0892] A means of converting acoustic information acquired using acoustic recognition technology into document data,

[0893] A method for extracting important information from document data using natural language processing technology,

[0894] A method for analyzing emotional states from participants' acoustic data,

[0895] A means for automatically generating meeting minutes based on extracted key information and analyzed emotional states,

[0896] A means of automatically setting the priority of follow-up tasks based on emotional state,

[0897] A means of managing the progress of follow-up tasks in conjunction with a business management tool,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, comprising means for automatically assigning follow-up tasks to personnel based on extracted important information and emotional states.

[0901] (Claim 3)

[0902] The system according to claim 1, which includes means for identifying delays or incompleteness in work based on progress management information and notifying relevant parties. [Explanation of Symbols]

[0903] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring audio signals in real time using an audio acquisition unit, A means of converting an audio signal acquired using speech recognition technology into text data, A method for extracting important information from text data using natural language processing technology, A means for automatically generating information records based on extracted important information, A means for automatically generating follow-up tasks from the generated information records, A means of managing the progress of follow-up tasks in conjunction with a task management system, A means of analyzing instruction information in the driving environment in real time and reflecting it in the automatic control system, A system that includes this.

2. The system according to claim 1, which automatically assigns follow-up tasks to a designated person based on extracted important information.

3. The system according to claim 1, which identifies delays or incomplete tasks based on progress management information and notifies the relevant persons.

Images