system

Abstract

We provide the system. [Solution] Means for acquiring sound, A sound recognition means for receiving acoustic information transferred from the aforementioned means and converting it into symbolic information, A natural language processing means analyzes the aforementioned symbolic information, extracts important information and decision information, and performs a summary. A formatting means that applies the summary according to the format specified by the user and generates a report, A supply means for supplying the generated report to the user, A mobile device that displays the aforementioned report and important information in real time, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 conventional minutes creation work in a meeting, it hinders participants from concentrating on the conversation and there is a risk of important remarks and decisions being missed. Therefore, the productivity of the meeting decreases, which has been a problem affecting subsequent operations. Furthermore, it takes time to adjust the format of the minutes, which has been a factor hindering efficient meeting operation.

Means for Solving the Problems

[0005] This invention solves these problems by accurately converting meeting audio into text data using speech recognition means and summarizing key points using natural language processing means. The generated summary is formatted according to the user's requirements using formatting application means and provided as automatically generated meeting minutes. This system allows participants to remain focused on the meeting, record important points of the discussion without missing anything, and achieve efficient meeting minute creation.

[0006] A "terminal device" is a device used to input and record the audio of a meeting, and its role is to transmit the audio data to the server.

[0007] "Speech recognition means" refers to a technology or device that processes speech data received from a terminal means and converts it into text data.

[0008] "Natural language processing means" refers to a technology or device that analyzes text data, extracts important information and decisions, and summarizes them.

[0009] "Format application means" refers to a technology or device that formats summary results and generates organized meeting minutes based on a format specified by the user.

[0010] "Means of delivery" refers to the functions and methods for presenting the generated meeting minutes to users, thereby enabling user access. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention provides a technology for efficiently and accurately converting meeting audio into meeting minutes. The following describes a specific embodiment of the system and its operation.

[0033] First, when the meeting begins, the terminal starts recording via the microphone to collect audio data. The terminal converts the recorded audio into digital data in real time and transmits it to the server via wireless or wired communication. At this time, the audio data is preprocessed, including noise filtering, to ensure it is suitable for speech recognition.

[0034] Next, the server receives this audio data and uses a speech recognition engine to convert it from speech to text data. The speech recognition engine uses a highly accurate algorithm to reflect the diverse utterances in the text and adds metadata to identify each speaker in the audio.

[0035] The converted text data is analyzed by the server using natural language processing techniques. This process involves keyword extraction, summarization of key points, and classification. Particularly important statements and decisions are automatically highlighted, making them easily accessible to the user later.

[0036] The analysis results are formatted by the server according to the user's pre-specified format or template. Formatting options include organized formats by agenda item, timeline formats, and other formats tailored to the type and purpose of the meeting.

[0037] Finally, the generated meeting minutes are created in a file format specified by the server and placed on a portal or dashboard accessible to users. This allows users to easily download and share them.

[0038] For example, when a user conducts a project meeting, the device records the audio in the meeting room, and the audio data is sent to the server in real time. After the meeting ends or during the meeting, the server automatically generates detailed minutes corresponding to the progress of the meeting, making them immediately accessible to the user. In this way, participants can conduct the meeting efficiently without losing any details of the discussion.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The device detects the start of the meeting and begins recording audio via the microphone. The audio data is converted to a digital format in real time and filtered to reduce background noise.

[0042] Step 2:

[0043] The terminal divides the audio data into chunks of a certain length and transfers them sequentially to the server via a communication line (wired or wireless). The data is transmitted in an efficient stream format.

[0044] Step 3:

[0045] The server sequentially passes the received audio chunks through the speech recognition engine, converting them from audio to text data. The converted text data is then tagged with metadata to identify the speaker.

[0046] Step 4:

[0047] The server analyzes the generated text data and uses natural language processing techniques to extract key keywords, main points, and decisions. This summarizes the main content of the meeting.

[0048] Step 5:

[0049] The server formats the extracted information according to the user's specifications. The format can be tailored to the user's needs, such as organizing by agenda item or using a timeline format.

[0050] Step 6:

[0051] The server generates the final meeting minutes in the specified file format, including PDF and Word, allowing users to view and share them.

[0052] Step 7:

[0053] After a meeting, users can access a dedicated portal or dashboard to access and download the created meeting minutes in real time. A notification system can also be used to inform users when the minutes are ready.

[0054] (Example 1)

[0055] 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."

[0056] In meetings and discussions, it is crucial to quickly and accurately record audio information as a document. However, conventional technologies have limitations in terms of audio conversion accuracy and the efficiency of extracting key points. Therefore, there has been a need for a system that can efficiently identify speakers, extract key points from discussions, and output them in various formats.

[0057] 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.

[0058] In this invention, the server includes an input device for inputting speech, a speech conversion device for receiving speech information transmitted from the input device and converting it into text information, and a natural language processing device for analyzing the text information, extracting important information and decision-making information, and summarizing it. This makes it possible to efficiently and accurately generate speech information as a recorded document and provide it in an appropriate format according to the user's needs.

[0059] An "input device" is a device that collects audio and transmits it to a server in a format that can be processed.

[0060] A "voice conversion device" is a device that has the function of analyzing received voice information and converting it into text information.

[0061] A "natural language processing system" is a device that extracts important information and decision-making information from text information and performs summarization.

[0062] A "format application device" is a device that has the function of formatting summarized information into a record document according to the format specified by the user.

[0063] A "providing device" is a device that provides generated record documents to users and places them on an online portal as needed.

[0064] An "information extraction device" is a device that has the function of accurately extracting the key points from a discussion.

[0065] This invention is a system for efficiently collecting audio from meetings and discussions and saving it as a documentary recording. This system is primarily implemented using the following hardware and software.

[0066] The terminal functions as an input device for collecting audio. It uses a microphone to record audio and is equipped with software that converts the collected audio into a digital signal in real time. This digitized audio data is transmitted to a server via a wireless or wired network.

[0067] The server functions as a speech converter. It converts received speech data into text data using speech recognition software, particularly generative AI models. It also acts as a natural language analyzer, analyzing the text data, extracting and summarizing important information and decision-making relevant information. Keyword extraction algorithms are used for this extraction process.

[0068] The server then uses a formatting device to generate a formatted record document based on the output format specified by the user. The server then uses a distribution device to provide the generated document to the user on an online portal or dashboard accessible by the user. This allows the user to easily view, download, and share the document.

[0069] As a concrete example, when a user initiates a team meeting, the device records the audio from the entire meeting room and sends that data to the server in real time. At the end of the meeting, or even during the meeting, the server transcribes the audio into text in real time and automatically generates a detailed record document based on the agenda.

[0070] An example of a prompt used as input to the generation AI model is, "Extract the main topics and decisions from this audio data and create meeting minutes." This system helps to accurately and efficiently document meeting content, enabling users to quickly retrieve the information they need.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The terminal receives audio input. When a user begins speaking in a conference room, the terminal's microphone captures the sound. The input is an analog audio signal, and the terminal converts this signal into digital audio data. The converted data is then noise-filtered to produce clear audio data. This data is then ready to be sent to the server.

[0074] Step 2:

[0075] The terminal transmits digital audio data to the server. The terminal sends the collected audio data to the server in real time via wireless or wired communication. The input here is digital audio data, and the output is a data stream destined for the server. A communication protocol is applied to ensure data integrity during transmission.

[0076] Step 3:

[0077] The server receives audio data and converts it to text. The server analyzes the audio data sent from the terminal using speech recognition software. The input is digital audio data, and the output is corresponding text data. This process uses a generative AI model to accurately transcribe a wide variety of speech.

[0078] Step 4:

[0079] The server analyzes text data and extracts key points. The generated text data is then processed by natural language processing software to extract important information. The input is text data, and the output is a set of summarized information. Here, a keyword extraction algorithm is used to identify important statements on the agenda.

[0080] Step 5:

[0081] The server formats the extracted information into a user-specified format. Based on the analyzed data, it generates a record document according to the format pre-configured by the user. The input is a summarized text set, and the output is a formatted document. This allows for document output tailored to different meeting formats.

[0082] Step 6:

[0083] The server provides the generated record documents. Finally, the generated record documents are saved in a specified electronic file format and placed on an online portal accessible to users. The input is the final document, and the output is the link or placement in storage for user access. This allows users to easily download and share the record documents.

[0084] (Application Example 1)

[0085] 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."

[0086] In today's business environment, meetings involving multiple participants are crucial for important decision-making, but accurately and quickly recording their content and sharing necessary information with stakeholders is not easy. In particular, the inability to check key points in real time during a meeting makes it difficult to grasp important matters without losing track of the flow of the discussion.

[0087] 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.

[0088] In this invention, the server includes means for acquiring sound; acoustic recognition means for receiving acoustic information transmitted from the means and converting it into symbolic information; and natural language processing means for analyzing the symbolic information, extracting important information and decision information, and summarizing it. This makes it possible to analyze the acoustic information of a meeting in real time and display important information on a mobile terminal.

[0089] "Means for acquiring sound" refers to devices including microphones and recording equipment for voice input.

[0090] "Acoustic information" refers to data that represents surrounding sounds and conversations as digital data.

[0091] "Symbolic information" refers to text data obtained through speech recognition based on acoustic information.

[0092] "Acoustic recognition means" refers to a processor or software that has speech analysis technology for converting acoustic information into text format.

[0093] A "natural language processing tool" is a computer program that analyzes symbolic information and efficiently extracts important information and decision-making information.

[0094] "User" refers to the person who operates this system.

[0095] A "format application means" is software that has the function of systematically organizing and outputting text information based on a format specified by the user.

[0096] "Supply means" refers to the network and communication means used to provide generated information and content to users.

[0097] A "mobile device" is an information display device that a user can carry with them, including smartphones and smart glasses.

[0098] In this system, the server acquires sound through microphones and recording devices placed in the conference room and transmits this sound information as digital data to the terminal. The terminal first receives the sound information and converts it into symbolic information using an acoustic recognition means. This acoustic recognition means implements a generally available speech recognition engine (e.g., Google® Speech-to-Text API), and noise filtering is performed in real time.

[0099] The server then uses natural language processing tools to analyze the symbolic information and extract important and decision-making information. This process utilizes natural language processing libraries (e.g., spaCy and NLTK) to identify key keywords and meeting decisions, organizing them as summary data. Furthermore, this summary data is organized into a format specified by the user using a format application tool.

[0100] Users can view real-time analysis results provided by the server using mobile devices such as smartphones and smart glasses. The application implemented on the mobile device provides a user interface (UI) that allows for immediate review of the generated reports. This UI is designed to visually highlight important information, enabling users to instantly access the information they need during a meeting.

[0101] For example, when the sales department holds a strategy meeting for a new product, the server analyzes the meeting audio in real time and instantly displays the decisions on the smart glasses' display, allowing users to grasp the information without interrupting the flow of the discussion. An example of a prompt to the generative AI model to make the most of this system is as follows: "Convert the following meeting audio data to text and automatically generate meeting minutes highlighting the key points."

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The terminal uses high-performance microphones placed in the conference room to acquire acoustic information in real time. This information captures surrounding conversations and sounds as digital data.

[0105] Step 2:

[0106] The terminal transfers the acquired acoustic information to the server. During this process, the audio data is transmitted using wireless or wired communication methods, minimizing latency.

[0107] Step 3:

[0108] The server analyzes the received acoustic information using acoustic recognition means and converts it into symbolic information. Specifically, it uses a speech recognition engine to convert the data into text and simultaneously performs noise reduction. This process removes noise from the acoustic information, resulting in clear symbolic information.

[0109] Step 4:

[0110] The server performs further analysis of the symbolic information using natural language processing tools. Through the natural language processing libraries used here, it extracts key information, identifies key decisions, and generates summary data. At this stage, it utilizes generative AI model algorithms to organize the information compactly.

[0111] Step 5:

[0112] The server formats the generated summary data into the user's specified format using formatting means. The output report format can include features such as categorization by agenda item and timeline display, and is designed to be easily understood by the user.

[0113] Step 6:

[0114] Users receive analysis results in real time via their mobile devices. The application on the device is designed to highlight important information and decisions, allowing users to review them immediately. This makes it possible to stay on top of the discussion flow without missing important information during meetings.

[0115] 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.

[0116] This invention provides new functionality by combining an emotion engine with a conventional meeting minutes generation system. By analyzing the emotions of participants during a meeting and managing this information together with the meeting record, this invention enables the creation of richer meeting minutes.

[0117] During the meeting, the device continuously collects audio and transmits the data to the server in real time. The audio data is converted into text data by a speech recognition engine, with an emotion engine also working in conjunction. The emotion engine analyzes parameters such as tone, pitch, and speed of the voice to recognize the user's emotional state.

[0118] The server analyzes the continuously acquired sentiment data along with the textualized content of the statements. While natural language processing extracts and summarizes important points, the sentiment engine grasps and quantifies the emotional response to each statement. This makes it possible to understand the atmosphere of the discussion within the meeting and the changes in the participants' emotions.

[0119] The generated meeting minutes record the emotional state of participants along with the identified key points. This recorded emotional data can be used as an indicator of whether the meeting proceeded smoothly or whether there was tension regarding a particular topic. Furthermore, when the minutes are organized into a user-specified format using a formatting application method, the emotional information serves as visually represented supplementary information.

[0120] The server then creates the final generated meeting minutes and sentiment report together in the specified file format. These generated documents can then be viewed and downloaded in real time by users accessing a dedicated portal.

[0121] For example, during project progress meetings, users can utilize emotional data to later review members' reactions. This allows project managers to develop future strategies based not only on the meeting content but also on the team's atmosphere and reactions. By using this system, an emotional dimension is added to the content of discussions during meetings, providing more detailed insights.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The device detects the start of a meeting and collects audio using the microphone. The audio data is converted to a digital format in real time and filtered to minimize background noise.

[0125] Step 2:

[0126] The terminal divides the recorded audio data into chunks of regular time intervals and sends them sequentially to the server. This minimizes data delay and enables efficient communication.

[0127] Step 3:

[0128] The server uses a speech recognition engine to convert received speech chunks into text data. During this process, information about speech intonation and speed is preserved, thus retaining non-verbal data necessary for sentiment analysis.

[0129] Step 4:

[0130] The server runs an emotion engine in parallel, analyzing emotion parameters extracted from the audio data. It determines the user's emotions based on volume, tone, tempo, etc., and records this as metadata by tagging each utterance.

[0131] Step 5:

[0132] The server utilizes natural language processing technology to analyze text data and extract important points and resolutions. Based on the analysis results of the emotion engine, it associates the content of statements with the user's emotional state to create a meeting minutes summary.

[0133] Step 6:

[0134] The server organizes the obtained summaries and sentiment information according to a format specified by the user. This includes preparing to visualize the sentiment analysis results associated with each statement.

[0135] Step 7:

[0136] The server generates the final meeting minutes and sentiment report and saves them in the selected file format (e.g., PDF or Word). These are then placed in a dedicated portal for easy access by users.

[0137] Step 8:

[0138] Users can access the portal to view and download the generated meeting minutes. The server can also automatically notify users when the minutes are complete through a notification function.

[0139] (Example 2)

[0140] 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".

[0141] Conventional meeting minute generation systems summarize meeting content and extract key points, but they do not analyze or record participants' emotions. As a result, meeting minutes are not created that reflect the atmosphere of the meeting or the changes in participants' emotions, leading to a lack of insights necessary for decision-making.

[0142] 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.

[0143] In this invention, the server includes speech recognition means for receiving audio information and converting it into text information, natural language processing means for analyzing the text information and extracting and expressing important points and emotional states, and emotion analysis means for analyzing the tone, pitch, and speed of the voice and capturing the user's emotional state. This makes it possible to generate detailed and useful meeting minutes that take into account not only the content of the meeting but also the emotions of the participants.

[0144] "Audio information" refers to the digital representation of sounds and language used when recording or processing words spoken in meetings or conversations.

[0145] An "information processing device" is an electronic device capable of receiving voice information and transmitting it to a server.

[0146] "Speech recognition means" refers to a technology or system for converting speech information into text format.

[0147] "Textual information" refers to text data converted from speech information by speech recognition technology.

[0148] "Natural language processing means" refers to technologies or systems that analyze textual information to extract important information and emotional states.

[0149] "Emotional analysis means" refers to technology that analyzes elements such as tone, pitch, and speed of voice to capture the user's emotional state.

[0150] "Format application means" refers to technologies and systems for generating and organizing meeting minutes according to a format specified by the user.

[0151] "Delivery method" refers to the means of providing the generated meeting minutes and sentiment reports to users in an available format.

[0152] This invention is an information processing system for analyzing audio information in meetings and conversations and generating rich meeting minutes that include the emotions of the participants. Specific embodiments of the system are described below.

[0153] The terminal is an information processing device equipped with voice input capabilities, which collects the voices of participants during a meeting in real time. This voice information is then transmitted to the server in a digitized format. The terminal can use a high-sensitivity microphone or the microphone built into a laptop computer.

[0154] The server is equipped with various technical means for processing received audio information. First, it uses a publicly available general-purpose speech recognition engine (e.g., a large-scale cloud-based speech recognition service) as a speech recognition means to convert the audio information into text information. Next, it uses machine learning and generative AI models as natural language processing means to extract and analyze important items and emotional states from the text information. Furthermore, it uses analytical techniques for emotion analysis as an emotion analysis means to analyze the speech characteristics in detail.

[0155] Through these processes, a report is created in the format specified by the user. This report visually includes not only what was said during the meeting, but also the emotional reactions of the participants and the tone of the discussion, thereby improving the quality of decision-making.

[0156] Users can review and download generated meeting minutes and sentiment reports through a specially accessible online portal. For example, in a project progress meeting, it's possible to generate prompts such as, "In the Project A progress meeting, please propose the next steps based on the changes in members' opinions and sentiments," and then use a generative AI model to develop further strategies. In this way, meeting minutes with added sentiment dimension take not only the content of the meeting but also the insights gained from it to an entirely new level.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The terminal continuously collects the voices of meeting participants using a microphone. It collects raw voice information from meeting participants as input, digitizes it, and sends it to the server. Specifically, voice data is recorded from the microphone connected to the terminal and transmitted to the server in real time via the network.

[0160] Step 2:

[0161] The server analyzes the audio data received from the terminal and converts it into text data using speech recognition. The input is digitized audio data, and the output is text-based character data. In this process, the speech recognition software analyzes the audio waveform and automatically generates text in the corresponding language.

[0162] Step 3:

[0163] The server analyzes the emotional state of participants using emotion analysis tools that analyze the tone, pitch, and speed of their voices. The input is the text data processed in step 2 and the original audio data, and the output is metadata of the emotional state associated with the text data. Specifically, it identifies emotions such as anger, joy, and doubt by analyzing the parameters of the audio data.

[0164] Step 4:

[0165] The server analyzes the text data using natural language processing techniques to extract and summarize the key points of the meeting. The input is the text data and emotional state metadata obtained in steps 2 and 3, and the output is the text summarizing the key points and data including the emotions at that time. Specifically, the server extracts keywords from the spoken content and then summarizes them.

[0166] Step 5:

[0167] The server generates meeting minutes and sentiment reports in the user-specified format based on the formatting application mechanism. The input is the summarized data generated in step 4, and the output is the meeting minutes and sentiment report formatted in the final format. Specific operations include document formatting based on templates and graphical visualization of sentiment information.

[0168] Step 6:

[0169] Users access meeting minutes and sentiment reports generated by the server through a dedicated portal. Input is a formatted document obtained from the server, and output is available for viewing on the user's device. Specifically, users access the portal using a web browser and download the necessary documents.

[0170] (Application Example 2)

[0171] 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".

[0172] Traditional meeting minute systems have the drawback of failing to capture the emotional elements of meetings, making it difficult to analyze changes in participants' emotions and the overall atmosphere. Furthermore, there has been a lack of means to collect and utilize emotional information in real-time during real-world human interactions. This has limited opportunities for improving responses and enhancing services based on feedback.

[0173] 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.

[0174] In this invention, the server includes emotion analysis means for analyzing voice tone and speed to identify emotional states, speech recognition means for converting voice data into text data, and formatting means for generating reports according to a user-specified format. This allows for the addition of an emotional dimension to spoken content in meetings and service settings, enabling real-time, detailed insights and feedback.

[0175] "Speech recognition means" refers to technology for converting speech data into text data.

[0176] "Natural language processing methods" are technologies that analyze text data, extract important points and decisions, and summarize them.

[0177] "Emotional analysis techniques" are technologies that analyze the tone and speed of speech to identify the speaker's emotional state.

[0178] "Format application means" refers to technology for organizing data according to a user-specified configuration and generating reports and meeting minutes.

[0179] "Means of delivery" refers to the technology used to supply generated reports and meeting minutes to users.

[0180] "Device means" refers to a device or system for inputting audio.

[0181] A "report" is a document used to present analyzed information to the user.

[0182] The system implementing this invention handles everything from inputting voice data to generating reports that include emotional information. The main components of this system are a device, a server, and a user.

[0183] A device is hardware for inputting voice, such as a microphone or smart glasses. Its role is to collect voice data in real time during a conversation and send it to a server.

[0184] The server implements a speech recognition engine and an emotion analysis engine. The server uses the Python SpeechRecognition library to convert speech data into text data. This text data is then used to recognize the emotional state using emotion analysis tools such as IBM Watson® Tone Analyzer.

[0185] In addition, the server utilizes natural language processing technology to extract and summarize important information from text data. It then uses a formatting mechanism to format the data in a user-specified format, compiling the generated data into a report.

[0186] Finally, the server provides the generated report to the user via an interface accessible through the delivery system. The user can review this report and use it, for example, to review meetings or to implement measures for service improvement.

[0187] For example, when store staff interact with customers using smart glasses, voice is transmitted from the device, sentiment analysis is performed, and the results are then presented as visual feedback on the smart glasses. This allows staff to respond in a way that is in line with the customer's emotions, contributing to improved customer satisfaction.

[0188] Furthermore, the prompt "Please advise how to adjust customer service methods based on the customer's emotional state" can be used as input to the generative AI model.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The terminal uses a microphone to acquire audio data in real time. The acquired audio data is sent to the server in its original format. The input is audio data, which forms the basis for subsequent processing.

[0192] Step 2:

[0193] The server converts received audio data into text data using the Python SpeechRecognition library. This process adjusts the audio quality and removes noise to achieve high-precision text conversion. The input is audio data, and the output is the corresponding text data.

[0194] Step 3:

[0195] The server uses natural language processing to analyze text data and extract key information. In this process, the server identifies key phrases and decisions from the text and generates summary information. The input is text data, and the output is summarized key information.

[0196] Step 4:

[0197] The server utilizes IBM Watson Tone Analyzer to perform sentiment analysis on text data. This process identifies emotional states within the text and quantifies the results. The input is text data, and the output is data on the emotional states identified therein.

[0198] Step 5:

[0199] The server generates a report integrating extracted key information and emotional states based on the format specified by the user. The formatting means the report is visually organized. The input is key information and emotional state data, and the output is a formatted report.

[0200] Step 6:

[0201] The server uploads the generated report to the specified interface to provide it to the user. This process manages access rights to the report, allowing users to view and download it. The input is the report data, and the output is a document accessible to the user.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] This invention provides a technology for efficiently and accurately converting meeting audio into meeting minutes. The following describes a specific embodiment of the system and its operation.

[0219] First, when the meeting begins, the terminal starts recording via the microphone to collect audio data. The terminal converts the recorded audio into digital data in real time and transmits it to the server via wireless or wired communication. At this time, the audio data is preprocessed, including noise filtering, to ensure it is suitable for speech recognition.

[0220] Next, the server receives this audio data and uses a speech recognition engine to convert it from speech to text data. The speech recognition engine uses a highly accurate algorithm to reflect the diverse utterances in the text and adds metadata to identify each speaker in the audio.

[0221] The converted text data is analyzed by the server using natural language processing techniques. This process involves keyword extraction, summarization of key points, and classification. Particularly important statements and decisions are automatically highlighted, making them easily accessible to the user later.

[0222] The analysis results are formatted by the server according to the user's pre-specified format or template. Formatting options include organized formats by agenda item, timeline formats, and other formats tailored to the type and purpose of the meeting.

[0223] Finally, the generated meeting minutes are created in a file format specified by the server and placed on a portal or dashboard accessible to users. This allows users to easily download and share them.

[0224] For example, when a user conducts a project meeting, the device records the audio in the meeting room, and the audio data is sent to the server in real time. After the meeting ends or during the meeting, the server automatically generates detailed minutes corresponding to the progress of the meeting, making them immediately accessible to the user. In this way, participants can conduct the meeting efficiently without losing any details of the discussion.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The device detects the start of the meeting and begins recording audio via the microphone. The audio data is converted to a digital format in real time and filtered to reduce background noise.

[0228] Step 2:

[0229] The terminal divides the audio data into chunks of a certain length and transfers them sequentially to the server via a communication line (wired or wireless). The data is transmitted in an efficient stream format.

[0230] Step 3:

[0231] The server sequentially passes the received audio chunks through the speech recognition engine, converting them from audio to text data. The converted text data is then tagged with metadata to identify the speaker.

[0232] Step 4:

[0233] The server analyzes the generated text data and uses natural language processing techniques to extract key keywords, main points, and decisions. This summarizes the main content of the meeting.

[0234] Step 5:

[0235] The server formats the extracted information according to the user's specifications. The format can be tailored to the user's needs, such as organizing by agenda item or using a timeline format.

[0236] Step 6:

[0237] The server generates the final meeting minutes in the specified file format, including PDF and Word, allowing users to view and share them.

[0238] Step 7:

[0239] After a meeting, users can access a dedicated portal or dashboard to access and download the created meeting minutes in real time. A notification system can also be used to inform users when the minutes are ready.

[0240] (Example 1)

[0241] 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."

[0242] In meetings and discussions, it is crucial to quickly and accurately record audio information as a document. However, conventional technologies have limitations in terms of audio conversion accuracy and the efficiency of extracting key points. Therefore, there has been a need for a system that can efficiently identify speakers, extract key points from discussions, and output them in various formats.

[0243] 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.

[0244] In this invention, the server includes an input device for inputting speech, a speech conversion device for receiving speech information transmitted from the input device and converting it into text information, and a natural language processing device for analyzing the text information, extracting important information and decision-making information, and summarizing it. This makes it possible to efficiently and accurately generate speech information as a recorded document and provide it in an appropriate format according to the user's needs.

[0245] An "input device" is a device that collects audio and transmits it to a server in a format that can be processed.

[0246] A "voice conversion device" is a device that has the function of analyzing received voice information and converting it into text information.

[0247] A "natural language processing system" is a device that extracts important information and decision-making information from text information and performs summarization.

[0248] A "format application device" is a device that has the function of formatting summarized information into a record document according to the format specified by the user.

[0249] A "providing device" is a device that provides generated record documents to users and places them on an online portal as needed.

[0250] An "information extraction device" is a device that has the function of accurately extracting the key points from a discussion.

[0251] This invention is a system for efficiently collecting audio from meetings and discussions and saving it as a documentary recording. This system is primarily implemented using the following hardware and software.

[0252] The terminal functions as an input device for collecting audio. It uses a microphone to record audio and is equipped with software that converts the collected audio into a digital signal in real time. This digitized audio data is transmitted to a server via a wireless or wired network.

[0253] The server functions as a speech converter. It converts received speech data into text data using speech recognition software, particularly generative AI models. It also acts as a natural language analyzer, analyzing the text data, extracting and summarizing important information and decision-making relevant information. Keyword extraction algorithms are used for this extraction process.

[0254] The server then uses a formatting device to generate a formatted record document based on the output format specified by the user. The server then uses a distribution device to provide the generated document to the user on an online portal or dashboard accessible by the user. This allows the user to easily view, download, and share the document.

[0255] As a concrete example, when a user initiates a team meeting, the device records the audio from the entire meeting room and sends that data to the server in real time. At the end of the meeting, or even during the meeting, the server transcribes the audio into text in real time and automatically generates a detailed record document based on the agenda.

[0256] An example of a prompt used as input to the generation AI model is, "Extract the main topics and decisions from this audio data and create meeting minutes." This system helps to accurately and efficiently document meeting content, enabling users to quickly retrieve the information they need.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The terminal receives audio input. When a user begins speaking in a conference room, the terminal's microphone captures the sound. The input is an analog audio signal, and the terminal converts this signal into digital audio data. The converted data is then noise-filtered to produce clear audio data. This data is then ready to be sent to the server.

[0260] Step 2:

[0261] The terminal transmits digital audio data to the server. The terminal sends the collected audio data to the server in real time via wireless or wired communication. The input here is digital audio data, and the output is a data stream destined for the server. A communication protocol is applied to ensure data integrity during transmission.

[0262] Step 3:

[0263] The server receives audio data and converts it to text. The server analyzes the audio data sent from the terminal using speech recognition software. The input is digital audio data, and the output is corresponding text data. This process uses a generative AI model to accurately transcribe a wide variety of speech.

[0264] Step 4:

[0265] The server analyzes text data and extracts key points. The generated text data is then processed by natural language processing software to extract important information. The input is text data, and the output is a set of summarized information. Here, a keyword extraction algorithm is used to identify important statements on the agenda.

[0266] Step 5:

[0267] The server formats the extracted information into a user-specified format. Based on the analyzed data, it generates a record document according to the format pre-configured by the user. The input is a summarized text set, and the output is a formatted document. This allows for document output tailored to different meeting formats.

[0268] Step 6:

[0269] The server provides the generated record documents. Finally, the generated record documents are saved in a specified electronic file format and placed on an online portal accessible to users. The input is the final document, and the output is the link or placement in storage for user access. This allows users to easily download and share the record documents.

[0270] (Application Example 1)

[0271] 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."

[0272] In today's business environment, meetings involving multiple participants are crucial for important decision-making, but accurately and quickly recording their content and sharing necessary information with stakeholders is not easy. In particular, the inability to check key points in real time during a meeting makes it difficult to grasp important matters without losing track of the flow of the discussion.

[0273] 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.

[0274] In this invention, the server includes means for acquiring sound; acoustic recognition means for receiving acoustic information transmitted from the means and converting it into symbolic information; and natural language processing means for analyzing the symbolic information, extracting important information and decision information, and summarizing it. This makes it possible to analyze the acoustic information of a meeting in real time and display important information on a mobile terminal.

[0275] "Means for acquiring sound" refers to devices including microphones and recording equipment for voice input.

[0276] "Acoustic information" refers to data that represents surrounding sounds and conversations as digital data.

[0277] "Symbolic information" refers to text data obtained through speech recognition based on acoustic information.

[0278] "Acoustic recognition means" refers to a processor or software that has speech analysis technology for converting acoustic information into text format.

[0279] A "natural language processing tool" is a computer program that analyzes symbolic information and efficiently extracts important information and decision-making information.

[0280] "User" refers to the person who operates this system.

[0281] A "format application means" is software that has the function of systematically organizing and outputting text information based on a format specified by the user.

[0282] "Supply means" refers to the network and communication means used to provide generated information and content to users.

[0283] A "portable terminal" is an information display device that can be carried by a user, including smartphones and smart glasses.

[0284] In this system, the server acquires sound through a microphone or recording device placed in the meeting room and transmits the sound information to the terminal as digital data. At the terminal, first, the sound information is received and converted into symbol information using sound recognition means. This sound recognition means is implemented with a generally available speech recognition engine (e.g., Google Speech-to-Text API), and noise filtering is performed in real time.

[0285] Next, the server analyzes the symbol information using natural language processing means and extracts important information and decision information. In this process, a natural language processing library (e.g., spaCy or NLTK) is used to identify important keywords and decisions made in the meeting and organize them as summary data. Furthermore, this summary data is organized in the format specified by the user by means of format application means.

[0286] The user can use a portable terminal such as a smartphone or smart glasses to check the real-time analysis results provided by the server. The application installed on the portable terminal provides a UI so that the generated report can be immediately checked. This UI is designed so that the user can immediately access the information necessary during the meeting by visually emphasizing the important information.

[0287] For example, when the sales department holds a strategic meeting for a new product, the server analyzes the voice of the meeting in real time and immediately displays the decisions on the display of the smart glasses, so that the user can grasp the information without interrupting the flow of the discussion. An example of a prompt sentence for the generative AI model to make the most of this system is as follows: "Please convert the following meeting voice data into text and automatically generate minutes highlighting the important points."

[0288] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The terminal uses high-performance microphones placed in the conference room to acquire acoustic information in real time. This information captures surrounding conversations and sounds as digital data.

[0291] Step 2:

[0292] The terminal transfers the acquired acoustic information to the server. During this process, the audio data is transmitted using wireless or wired communication methods, minimizing latency.

[0293] Step 3:

[0294] The server analyzes the received acoustic information using acoustic recognition means and converts it into symbolic information. Specifically, it uses a speech recognition engine to convert the data into text and simultaneously performs noise reduction. This process removes noise from the acoustic information, resulting in clear symbolic information.

[0295] Step 4:

[0296] The server performs further analysis of the symbolic information using natural language processing tools. Through the natural language processing libraries used here, it extracts key information, identifies key decisions, and generates summary data. At this stage, it utilizes generative AI model algorithms to organize the information compactly.

[0297] Step 5:

[0298] The server formats the generated summary data into the user's specified format using formatting means. The output report format can include features such as categorization by agenda item and timeline display, and is designed to be easily understood by the user.

[0299] Step 6:

[0300] Users receive analysis results in real time via their mobile devices. The application on the device is designed to highlight important information and decisions, allowing users to review them immediately. This makes it possible to stay on top of the discussion flow without missing important information during meetings.

[0301] 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.

[0302] This invention provides new functionality by combining an emotion engine with a conventional meeting minutes generation system. By analyzing the emotions of participants during a meeting and managing this information together with the meeting record, this invention enables the creation of richer meeting minutes.

[0303] During the meeting, the device continuously collects audio and transmits the data to the server in real time. The audio data is converted into text data by a speech recognition engine, with an emotion engine also working in conjunction. The emotion engine analyzes parameters such as tone, pitch, and speed of the voice to recognize the user's emotional state.

[0304] The server analyzes the continuously acquired sentiment data along with the textualized content of the statements. While natural language processing extracts and summarizes important points, the sentiment engine grasps and quantifies the emotional response to each statement. This makes it possible to understand the atmosphere of the discussion within the meeting and the changes in the participants' emotions.

[0305] The generated meeting minutes record the emotional state of participants along with the identified key points. This recorded emotional data can be used as an indicator of whether the meeting proceeded smoothly or whether there was tension regarding a particular topic. Furthermore, when the minutes are organized into a user-specified format using a formatting application method, the emotional information serves as visually represented supplementary information.

[0306] The server creates the finally generated minutes and sentiment report together in the specified file format. The materials thus generated can be viewed and downloaded in real time by the user accessing the dedicated portal.

[0307] For example, in a project progress meeting, the user can utilize the sentiment data to review the reactions of the members later. This enables the project manager to formulate the next strategy not only based on the evaluation of the meeting content but also on the team atmosphere and reactions. By using this system, an emotional dimension is added to the speech content during the meeting, allowing for more detailed insights.

[0308] The following describes the processing flow.

[0309] Step 1:

[0310] The terminal detects the start of the meeting and collects audio using the microphone. The audio data is converted into a digital format in real time and undergoes filtering processing to minimize background noise.

[0311] Step 2:

[0312] The terminal divides the recorded audio data into chunks at regular intervals and sequentially transmits them to the server. This enables efficient communication with minimal data delay.

[0313] Step 3:

[0314] The server uses an audio recognition engine to convert the received audio chunks into text data. At this time, by preserving information such as the intonation and speed of the audio, non-verbal data necessary for sentiment analysis is also retained. <\\

[0315] Step 4:

[0316] The server runs an emotion engine in parallel, analyzing emotion parameters extracted from the audio data. It determines the user's emotions based on volume, tone, tempo, etc., and records this as metadata by tagging each utterance.

[0317] Step 5:

[0318] The server utilizes natural language processing technology to analyze text data and extract important points and resolutions. Based on the analysis results of the emotion engine, it associates the content of statements with the user's emotional state to create a meeting minutes summary.

[0319] Step 6:

[0320] The server organizes the obtained summaries and sentiment information according to a format specified by the user. This includes preparing to visualize the sentiment analysis results associated with each statement.

[0321] Step 7:

[0322] The server generates the final meeting minutes and sentiment report and saves them in the selected file format (e.g., PDF or Word). These are then placed in a dedicated portal for easy access by users.

[0323] Step 8:

[0324] Users can access the portal to view and download the generated meeting minutes. The server can also automatically notify users when the minutes are complete through a notification function.

[0325] (Example 2)

[0326] 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".

[0327] Conventional meeting minute generation systems summarize meeting content and extract key points, but they do not analyze or record participants' emotions. As a result, meeting minutes are not created that reflect the atmosphere of the meeting or the changes in participants' emotions, leading to a lack of insights necessary for decision-making.

[0328] 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.

[0329] In this invention, the server includes speech recognition means for receiving audio information and converting it into text information, natural language processing means for analyzing the text information and extracting and expressing important points and emotional states, and emotion analysis means for analyzing the tone, pitch, and speed of the voice and capturing the user's emotional state. This makes it possible to generate detailed and useful meeting minutes that take into account not only the content of the meeting but also the emotions of the participants.

[0330] "Audio information" refers to the digital representation of sounds and language used when recording or processing words spoken in meetings or conversations.

[0331] An "information processing device" is an electronic device capable of receiving voice information and transmitting it to a server.

[0332] "Speech recognition means" refers to a technology or system for converting speech information into text format.

[0333] "Textual information" refers to text data converted from speech information by speech recognition technology.

[0334] "Natural language processing means" refers to technologies or systems that analyze textual information to extract important information and emotional states.

[0335] "Emotional analysis means" refers to technology that analyzes elements such as tone, pitch, and speed of voice to capture the user's emotional state.

[0336] "Format application means" refers to technologies and systems for generating and organizing meeting minutes according to a format specified by the user.

[0337] "Delivery method" refers to the means of providing the generated meeting minutes and sentiment reports to users in an available format.

[0338] This invention is an information processing system for analyzing audio information in meetings and conversations and generating rich meeting minutes that include the emotions of the participants. Specific embodiments of the system are described below.

[0339] The terminal is an information processing device equipped with voice input capabilities, which collects the voices of participants during a meeting in real time. This voice information is then transmitted to the server in a digitized format. The terminal can use a high-sensitivity microphone or the microphone built into a laptop computer.

[0340] The server is equipped with various technical means for processing received audio information. First, it uses a publicly available general-purpose speech recognition engine (e.g., a large-scale cloud-based speech recognition service) as a speech recognition means to convert the audio information into text information. Next, it uses machine learning and generative AI models as natural language processing means to extract and analyze important items and emotional states from the text information. Furthermore, it uses analytical techniques for emotion analysis as an emotion analysis means to analyze the speech characteristics in detail.

[0341] Through these processes, a report is created in the format specified by the user. This report visually includes not only what was said during the meeting, but also the emotional reactions of the participants and the tone of the discussion, thereby improving the quality of decision-making.

[0342] Users can review and download generated meeting minutes and sentiment reports through a specially accessible online portal. For example, in a project progress meeting, it's possible to generate prompts such as, "In the Project A progress meeting, please propose the next steps based on the changes in members' opinions and sentiments," and then use a generative AI model to develop further strategies. In this way, meeting minutes with added sentiment dimension take not only the content of the meeting but also the insights gained from it to an entirely new level.

[0343] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0344] Step 1:

[0345] The terminal continuously collects the voices of meeting participants using a microphone. It collects raw voice information from meeting participants as input, digitizes it, and sends it to the server. Specifically, voice data is recorded from the microphone connected to the terminal and transmitted to the server in real time via the network.

[0346] Step 2:

[0347] The server analyzes the audio data received from the terminal and converts it into text data using speech recognition. The input is digitized audio data, and the output is text-based character data. In this process, the speech recognition software analyzes the audio waveform and automatically generates text in the corresponding language.

[0348] Step 3:

[0349] The server analyzes the emotional state of participants using emotion analysis tools that analyze the tone, pitch, and speed of their voices. The input is the text data processed in step 2 and the original audio data, and the output is metadata of the emotional state associated with the text data. Specifically, it identifies emotions such as anger, joy, and doubt by analyzing the parameters of the audio data.

[0350] Step 4:

[0351] The server analyzes the text data using natural language processing techniques to extract and summarize the key points of the meeting. The input is the text data and emotional state metadata obtained in steps 2 and 3, and the output is the text summarizing the key points and data including the emotions at that time. Specifically, the server extracts keywords from the spoken content and then summarizes them.

[0352] Step 5:

[0353] The server generates meeting minutes and sentiment reports in the user-specified format based on the formatting application mechanism. The input is the summarized data generated in step 4, and the output is the meeting minutes and sentiment report formatted in the final format. Specific operations include document formatting based on templates and graphical visualization of sentiment information.

[0354] Step 6:

[0355] Users access meeting minutes and sentiment reports generated by the server through a dedicated portal. Input is a formatted document obtained from the server, and output is available for viewing on the user's device. Specifically, users access the portal using a web browser and download the necessary documents.

[0356] (Application Example 2)

[0357] 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."

[0358] Traditional meeting minute systems have the drawback of failing to capture the emotional elements of meetings, making it difficult to analyze changes in participants' emotions and the overall atmosphere. Furthermore, there has been a lack of means to collect and utilize emotional information in real-time during real-world human interactions. This has limited opportunities for improving responses and enhancing services based on feedback.

[0359] 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.

[0360] In this invention, the server includes emotion analysis means for analyzing voice tone and speed to identify emotional states, speech recognition means for converting voice data into text data, and formatting means for generating reports according to a user-specified format. This allows for the addition of an emotional dimension to spoken content in meetings and service settings, enabling real-time, detailed insights and feedback.

[0361] "Speech recognition means" refers to technology for converting speech data into text data.

[0362] "Natural language processing methods" are technologies that analyze text data, extract important points and decisions, and summarize them.

[0363] "Emotional analysis techniques" are technologies that analyze the tone and speed of speech to identify the speaker's emotional state.

[0364] "Format application means" refers to technology for organizing data according to a user-specified configuration and generating reports and meeting minutes.

[0365] "Means of delivery" refers to the technology used to supply generated reports and meeting minutes to users.

[0366] "Device means" refers to a device or system for inputting audio.

[0367] A "report" is a document used to present analyzed information to the user.

[0368] The system implementing this invention handles everything from inputting voice data to generating reports that include emotional information. The main components of this system are a device, a server, and a user.

[0369] A device is hardware for inputting voice, such as a microphone or smart glasses. Its role is to collect voice data in real time during a conversation and send it to a server.

[0370] The server implements a speech recognition engine and an emotion analysis engine. The server uses the Python SpeechRecognition library to convert speech data into text data. This text data is then used to recognize the emotional state using emotion analysis tools such as IBM Watson Tone Analyzer.

[0371] In addition, the server utilizes natural language processing technology to extract and summarize important information from text data. It then uses a formatting mechanism to format the data in a user-specified format, compiling the generated data into a report.

[0372] Finally, the server provides the generated report to the user via an interface accessible through the delivery system. The user can review this report and use it, for example, to review meetings or to implement measures for service improvement.

[0373] For example, when store staff interact with customers using smart glasses, voice is transmitted from the device, sentiment analysis is performed, and the results are then presented as visual feedback on the smart glasses. This allows staff to respond in a way that is in line with the customer's emotions, contributing to improved customer satisfaction.

[0374] Furthermore, the prompt "Please advise how to adjust customer service methods based on the customer's emotional state" can be used as input to the generative AI model.

[0375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0376] Step 1:

[0377] The terminal uses a microphone to acquire audio data in real time. The acquired audio data is sent to the server in its original format. The input is audio data, which forms the basis for subsequent processing.

[0378] Step 2:

[0379] The server converts received audio data into text data using the Python SpeechRecognition library. This process adjusts the audio quality and removes noise to achieve high-precision text conversion. The input is audio data, and the output is the corresponding text data.

[0380] Step 3:

[0381] The server uses natural language processing to analyze text data and extract key information. In this process, the server identifies key phrases and decisions from the text and generates summary information. The input is text data, and the output is summarized key information.

[0382] Step 4:

[0383] The server utilizes IBM Watson Tone Analyzer to perform sentiment analysis on text data. This process identifies emotional states within the text and quantifies the results. The input is text data, and the output is data on the emotional states identified therein.

[0384] Step 5:

[0385] The server generates a report integrating extracted key information and emotional states based on the format specified by the user. The formatting means the report is visually organized. The input is key information and emotional state data, and the output is a formatted report.

[0386] Step 6:

[0387] The server uploads the generated report to the specified interface to provide it to the user. This process manages access rights to the report, allowing users to view and download it. The input is the report data, and the output is a document accessible to the user.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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".

[0404] This invention provides a technology for efficiently and accurately converting meeting audio into meeting minutes. The following describes a specific embodiment of the system and its operation.

[0405] First, when the meeting begins, the terminal starts recording via the microphone to collect audio data. The terminal converts the recorded audio into digital data in real time and transmits it to the server via wireless or wired communication. At this time, the audio data is preprocessed, including noise filtering, to ensure it is suitable for speech recognition.

[0406] Next, the server receives this audio data and uses a speech recognition engine to convert it from speech to text data. The speech recognition engine uses a highly accurate algorithm to reflect the diverse utterances in the text and adds metadata to identify each speaker in the audio.

[0407] The converted text data is analyzed by the server using natural language processing techniques. This process involves keyword extraction, summarization of key points, and classification. Particularly important statements and decisions are automatically highlighted, making them easily accessible to the user later.

[0408] The analysis results are formatted by the server according to the user's pre-specified format or template. Formatting options include organized formats by agenda item, timeline formats, and other formats tailored to the type and purpose of the meeting.

[0409] Finally, the generated meeting minutes are created in a file format specified by the server and placed on a portal or dashboard accessible to users. This allows users to easily download and share them.

[0410] For example, when a user conducts a project meeting, the device records the audio in the meeting room, and the audio data is sent to the server in real time. After the meeting ends or during the meeting, the server automatically generates detailed minutes corresponding to the progress of the meeting, making them immediately accessible to the user. In this way, participants can conduct the meeting efficiently without losing any details of the discussion.

[0411] The following describes the processing flow.

[0412] Step 1:

[0413] The device detects the start of the meeting and begins recording audio via the microphone. The audio data is converted to a digital format in real time and filtered to reduce background noise.

[0414] Step 2:

[0415] The terminal divides the audio data into chunks of a certain length and transfers them sequentially to the server via a communication line (wired or wireless). The data is transmitted in an efficient stream format.

[0416] Step 3:

[0417] The server sequentially passes the received audio chunks through the speech recognition engine, converting them from audio to text data. The converted text data is then tagged with metadata to identify the speaker.

[0418] Step 4:

[0419] The server analyzes the generated text data and uses natural language processing techniques to extract key keywords, main points, and decisions. This summarizes the main content of the meeting.

[0420] Step 5:

[0421] The server formats the extracted information according to the user's specifications. The format can be tailored to the user's needs, such as organizing by agenda item or using a timeline format.

[0422] Step 6:

[0423] The server generates the final meeting minutes in the specified file format, including PDF and Word, allowing users to view and share them.

[0424] Step 7:

[0425] After a meeting, users can access a dedicated portal or dashboard to access and download the created meeting minutes in real time. A notification system can also be used to inform users when the minutes are ready.

[0426] (Example 1)

[0427] 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."

[0428] In meetings and discussions, it is crucial to quickly and accurately record audio information as a document. However, conventional technologies have limitations in terms of audio conversion accuracy and the efficiency of extracting key points. Therefore, there has been a need for a system that can efficiently identify speakers, extract key points from discussions, and output them in various formats.

[0429] 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.

[0430] In this invention, the server includes an input device for inputting speech, a speech conversion device for receiving speech information transmitted from the input device and converting it into text information, and a natural language processing device for analyzing the text information, extracting important information and decision-making information, and summarizing it. This makes it possible to efficiently and accurately generate speech information as a recorded document and provide it in an appropriate format according to the user's needs.

[0431] An "input device" is a device that collects audio and transmits it to a server in a format that can be processed.

[0432] A "voice conversion device" is a device that has the function of analyzing received voice information and converting it into text information.

[0433] A "natural language processing system" is a device that extracts important information and decision-making information from text information and performs summarization.

[0434] A "format application device" is a device that has the function of formatting summarized information into a record document according to the format specified by the user.

[0435] A "providing device" is a device that provides generated record documents to users and places them on an online portal as needed.

[0436] An "information extraction device" is a device that has the function of accurately extracting the key points from a discussion.

[0437] This invention is a system for efficiently collecting audio from meetings and discussions and saving it as a documentary recording. This system is primarily implemented using the following hardware and software.

[0438] The terminal functions as an input device for collecting audio. It uses a microphone to record audio and is equipped with software that converts the collected audio into a digital signal in real time. This digitized audio data is transmitted to a server via a wireless or wired network.

[0439] The server functions as a speech converter. It converts received speech data into text data using speech recognition software, particularly generative AI models. It also acts as a natural language analyzer, analyzing the text data, extracting and summarizing important information and decision-making relevant information. Keyword extraction algorithms are used for this extraction process.

[0440] The server then uses a formatting device to generate a formatted record document based on the output format specified by the user. The server then uses a distribution device to provide the generated document to the user on an online portal or dashboard accessible by the user. This allows the user to easily view, download, and share the document.

[0441] As a concrete example, when a user initiates a team meeting, the device records the audio from the entire meeting room and sends that data to the server in real time. At the end of the meeting, or even during the meeting, the server transcribes the audio into text in real time and automatically generates a detailed record document based on the agenda.

[0442] An example of a prompt used as input to the generation AI model is, "Extract the main topics and decisions from this audio data and create meeting minutes." This system helps to accurately and efficiently document meeting content, enabling users to quickly retrieve the information they need.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1:

[0445] The terminal receives audio input. When a user begins speaking in a conference room, the terminal's microphone captures the sound. The input is an analog audio signal, and the terminal converts this signal into digital audio data. The converted data is then noise-filtered to produce clear audio data. This data is then ready to be sent to the server.

[0446] Step 2:

[0447] The terminal transmits digital audio data to the server. The terminal sends the collected audio data to the server in real time via wireless or wired communication. The input here is digital audio data, and the output is a data stream destined for the server. A communication protocol is applied to ensure data integrity during transmission.

[0448] Step 3:

[0449] The server receives audio data and converts it to text. The server analyzes the audio data sent from the terminal using speech recognition software. The input is digital audio data, and the output is corresponding text data. This process uses a generative AI model to accurately transcribe a wide variety of speech.

[0450] Step 4:

[0451] The server analyzes text data and extracts key points. The generated text data is then processed by natural language processing software to extract important information. The input is text data, and the output is a set of summarized information. Here, a keyword extraction algorithm is used to identify important statements on the agenda.

[0452] Step 5:

[0453] The server formats the extracted information into a user-specified format. Based on the analyzed data, it generates a record document according to the format pre-configured by the user. The input is a summarized text set, and the output is a formatted document. This allows for document output tailored to different meeting formats.

[0454] Step 6:

[0455] The server provides the generated record documents. Finally, the generated record documents are saved in a specified electronic file format and placed on an online portal accessible to users. The input is the final document, and the output is the link or placement in storage for user access. This allows users to easily download and share the record documents.

[0456] (Application Example 1)

[0457] 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."

[0458] In today's business environment, meetings involving multiple participants are crucial for important decision-making, but accurately and quickly recording their content and sharing necessary information with stakeholders is not easy. In particular, the inability to check key points in real time during a meeting makes it difficult to grasp important matters without losing track of the flow of the discussion.

[0459] 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.

[0460] In this invention, the server includes means for acquiring sound; acoustic recognition means for receiving acoustic information transmitted from the means and converting it into symbolic information; and natural language processing means for analyzing the symbolic information, extracting important information and decision information, and summarizing it. This makes it possible to analyze the acoustic information of a meeting in real time and display important information on a mobile terminal.

[0461] "Means for acquiring sound" refers to devices including microphones and recording equipment for voice input.

[0462] "Acoustic information" refers to data that represents surrounding sounds and conversations as digital data.

[0463] "Symbolic information" refers to text data obtained through speech recognition based on acoustic information.

[0464] "Acoustic recognition means" refers to a processor or software that has speech analysis technology for converting acoustic information into text format.

[0465] A "natural language processing tool" is a computer program that analyzes symbolic information and efficiently extracts important information and decision-making information.

[0466] "User" refers to the person who operates this system.

[0467] A "format application means" is software that has the function of systematically organizing and outputting text information based on a format specified by the user.

[0468] "Supply means" refers to the network and communication means used to provide generated information and content to users.

[0469] A "mobile device" is an information display device that a user can carry with them, including smartphones and smart glasses.

[0470] In this system, the server acquires sound through microphones and recording devices placed in the conference room and transmits this acoustic information as digital data to the terminal. The terminal first receives the acoustic information and converts it into symbolic information using an acoustic recognition means. This acoustic recognition means implements a generally available speech recognition engine (e.g., Google Speech-to-Text API), and noise filtering is performed in real time.

[0471] The server then uses natural language processing tools to analyze the symbolic information and extract important and decision-making information. This process utilizes natural language processing libraries (e.g., spaCy and NLTK) to identify key keywords and meeting decisions, organizing them as summary data. Furthermore, this summary data is organized into a format specified by the user using a format application tool.

[0472] Users can view real-time analysis results provided by the server using mobile devices such as smartphones and smart glasses. The application implemented on the mobile device provides a user interface (UI) that allows for immediate review of the generated reports. This UI is designed to visually highlight important information, enabling users to instantly access the information they need during a meeting.

[0473] For example, when the sales department holds a strategy meeting for a new product, the server analyzes the meeting audio in real time and instantly displays the decisions on the smart glasses' display, allowing users to grasp the information without interrupting the flow of the discussion. An example of a prompt to the generative AI model to make the most of this system is as follows: "Convert the following meeting audio data to text and automatically generate meeting minutes highlighting the key points."

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The terminal uses high-performance microphones placed in the conference room to acquire acoustic information in real time. This information captures surrounding conversations and sounds as digital data.

[0477] Step 2:

[0478] The terminal transfers the acquired acoustic information to the server. During this process, the audio data is transmitted using wireless or wired communication methods, minimizing latency.

[0479] Step 3:

[0480] The server analyzes the received acoustic information using acoustic recognition means and converts it into symbolic information. Specifically, it uses a speech recognition engine to convert the data into text and simultaneously performs noise reduction. This process removes noise from the acoustic information, resulting in clear symbolic information.

[0481] Step 4:

[0482] The server performs further analysis of the symbolic information using natural language processing tools. Through the natural language processing libraries used here, it extracts key information, identifies key decisions, and generates summary data. At this stage, it utilizes generative AI model algorithms to organize the information compactly.

[0483] Step 5:

[0484] The server formats the generated summary data into the user's specified format using formatting means. The output report format can include features such as categorization by agenda item and timeline display, and is designed to be easily understood by the user.

[0485] Step 6:

[0486] Users receive analysis results in real time via their mobile devices. The application on the device is designed to highlight important information and decisions, allowing users to review them immediately. This makes it possible to stay on top of the discussion flow without missing important information during meetings.

[0487] 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.

[0488] This invention provides new functionality by combining an emotion engine with a conventional meeting minutes generation system. By analyzing the emotions of participants during a meeting and managing this information together with the meeting record, this invention enables the creation of richer meeting minutes.

[0489] During the meeting, the device continuously collects audio and transmits the data to the server in real time. The audio data is converted into text data by a speech recognition engine, with an emotion engine also working in conjunction. The emotion engine analyzes parameters such as tone, pitch, and speed of the voice to recognize the user's emotional state.

[0490] The server analyzes the continuously acquired sentiment data along with the textualized content of the statements. While natural language processing extracts and summarizes important points, the sentiment engine grasps and quantifies the emotional response to each statement. This makes it possible to understand the atmosphere of the discussion within the meeting and the changes in the participants' emotions.

[0491] The generated meeting minutes record the emotional state of participants along with the identified key points. This recorded emotional data can be used as an indicator of whether the meeting proceeded smoothly or whether there was tension regarding a particular topic. Furthermore, when the minutes are organized into a user-specified format using a formatting application method, the emotional information serves as visually represented supplementary information.

[0492] The server then creates the final generated meeting minutes and sentiment report together in the specified file format. These generated documents can then be viewed and downloaded in real time by users accessing a dedicated portal.

[0493] For example, during project progress meetings, users can utilize emotional data to later review members' reactions. This allows project managers to develop future strategies based not only on the meeting content but also on the team's atmosphere and reactions. By using this system, an emotional dimension is added to the content of discussions during meetings, providing more detailed insights.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] The device detects the start of a meeting and collects audio using the microphone. The audio data is converted to a digital format in real time and filtered to minimize background noise.

[0497] Step 2:

[0498] The terminal divides the recorded audio data into chunks of regular time intervals and sends them sequentially to the server. This minimizes data delay and enables efficient communication.

[0499] Step 3:

[0500] The server uses a speech recognition engine to convert received speech chunks into text data. During this process, information about speech intonation and speed is preserved, thus retaining non-verbal data necessary for sentiment analysis.

[0501] Step 4:

[0502] The server runs an emotion engine in parallel, analyzing emotion parameters extracted from the audio data. It determines the user's emotions based on volume, tone, tempo, etc., and records this as metadata by tagging each utterance.

[0503] Step 5:

[0504] The server utilizes natural language processing technology to analyze text data and extract important points and resolutions. Based on the analysis results of the emotion engine, it associates the content of statements with the user's emotional state to create a meeting minutes summary.

[0505] Step 6:

[0506] The server organizes the obtained summaries and sentiment information according to a format specified by the user. This includes preparing to visualize the sentiment analysis results associated with each statement.

[0507] Step 7:

[0508] The server generates the final meeting minutes and sentiment report and saves them in the selected file format (e.g., PDF or Word). These are then placed in a dedicated portal for easy access by users.

[0509] Step 8:

[0510] Users can access the portal to view and download the generated meeting minutes. The server can also automatically notify users when the minutes are complete through a notification function.

[0511] (Example 2)

[0512] 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."

[0513] Conventional meeting minute generation systems summarize meeting content and extract key points, but they do not analyze or record participants' emotions. As a result, meeting minutes are not created that reflect the atmosphere of the meeting or the changes in participants' emotions, leading to a lack of insights necessary for decision-making.

[0514] 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.

[0515] In this invention, the server includes speech recognition means for receiving audio information and converting it into text information, natural language processing means for analyzing the text information and extracting and expressing important points and emotional states, and emotion analysis means for analyzing the tone, pitch, and speed of the voice and capturing the user's emotional state. This makes it possible to generate detailed and useful meeting minutes that take into account not only the content of the meeting but also the emotions of the participants.

[0516] "Audio information" refers to the digital representation of sounds and language used when recording or processing words spoken in meetings or conversations.

[0517] An "information processing device" is an electronic device capable of receiving voice information and transmitting it to a server.

[0518] "Speech recognition means" refers to a technology or system for converting speech information into text format.

[0519] "Textual information" refers to text data converted from speech information by speech recognition technology.

[0520] "Natural language processing means" refers to technologies or systems that analyze textual information to extract important information and emotional states.

[0521] "Emotional analysis means" refers to technology that analyzes elements such as tone, pitch, and speed of voice to capture the user's emotional state.

[0522] "Format application means" refers to technologies and systems for generating and organizing meeting minutes according to a format specified by the user.

[0523] "Delivery method" refers to the means of providing the generated meeting minutes and sentiment reports to users in an available format.

[0524] This invention is an information processing system for analyzing audio information in meetings and conversations and generating rich meeting minutes that include the emotions of the participants. Specific embodiments of the system are described below.

[0525] The terminal is an information processing device equipped with voice input capabilities, which collects the voices of participants during a meeting in real time. This voice information is then transmitted to the server in a digitized format. The terminal can use a high-sensitivity microphone or the microphone built into a laptop computer.

[0526] The server is equipped with various technical means for processing received audio information. First, it uses a publicly available general-purpose speech recognition engine (e.g., a large-scale cloud-based speech recognition service) as a speech recognition means to convert the audio information into text information. Next, it uses machine learning and generative AI models as natural language processing means to extract and analyze important items and emotional states from the text information. Furthermore, it uses analytical techniques for emotion analysis as an emotion analysis means to analyze the speech characteristics in detail.

[0527] Through these processes, a report is created in the format specified by the user. This report visually includes not only what was said during the meeting, but also the emotional reactions of the participants and the tone of the discussion, thereby improving the quality of decision-making.

[0528] Users can review and download generated meeting minutes and sentiment reports through a specially accessible online portal. For example, in a project progress meeting, it's possible to generate prompts such as, "In the Project A progress meeting, please propose the next steps based on the changes in members' opinions and sentiments," and then use a generative AI model to develop further strategies. In this way, meeting minutes with added sentiment dimension take not only the content of the meeting but also the insights gained from it to an entirely new level.

[0529] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0530] Step 1:

[0531] The terminal continuously collects the voices of meeting participants using a microphone. It collects raw voice information from meeting participants as input, digitizes it, and sends it to the server. Specifically, voice data is recorded from the microphone connected to the terminal and transmitted to the server in real time via the network.

[0532] Step 2:

[0533] The server analyzes the audio data received from the terminal and converts it into text data using speech recognition. The input is digitized audio data, and the output is text-based character data. In this process, the speech recognition software analyzes the audio waveform and automatically generates text in the corresponding language.

[0534] Step 3:

[0535] The server analyzes the emotional state of participants using emotion analysis tools that analyze the tone, pitch, and speed of their voices. The input is the text data processed in step 2 and the original audio data, and the output is metadata of the emotional state associated with the text data. Specifically, it identifies emotions such as anger, joy, and doubt by analyzing the parameters of the audio data.

[0536] Step 4:

[0537] The server analyzes the text data using natural language processing techniques to extract and summarize the key points of the meeting. The input is the text data and emotional state metadata obtained in steps 2 and 3, and the output is the text summarizing the key points and data including the emotions at that time. Specifically, the server extracts keywords from the spoken content and then summarizes them.

[0538] Step 5:

[0539] The server generates meeting minutes and sentiment reports in the user-specified format based on the formatting application mechanism. The input is the summarized data generated in step 4, and the output is the meeting minutes and sentiment report formatted in the final format. Specific operations include document formatting based on templates and graphical visualization of sentiment information.

[0540] Step 6:

[0541] Users access meeting minutes and sentiment reports generated by the server through a dedicated portal. Input is a formatted document obtained from the server, and output is available for viewing on the user's device. Specifically, users access the portal using a web browser and download the necessary documents.

[0542] (Application Example 2)

[0543] 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."

[0544] Traditional meeting minute systems have the drawback of failing to capture the emotional elements of meetings, making it difficult to analyze changes in participants' emotions and the overall atmosphere. Furthermore, there has been a lack of means to collect and utilize emotional information in real-time during real-world human interactions. This has limited opportunities for improving responses and enhancing services based on feedback.

[0545] 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.

[0546] In this invention, the server includes emotion analysis means for analyzing voice tone and speed to identify emotional states, speech recognition means for converting voice data into text data, and formatting means for generating reports according to a user-specified format. This allows for the addition of an emotional dimension to spoken content in meetings and service settings, enabling real-time, detailed insights and feedback.

[0547] "Speech recognition means" refers to technology for converting speech data into text data.

[0548] "Natural language processing methods" are technologies that analyze text data, extract important points and decisions, and summarize them.

[0549] "Emotional analysis techniques" are technologies that analyze the tone and speed of speech to identify the speaker's emotional state.

[0550] "Format application means" refers to technology for organizing data according to a user-specified configuration and generating reports and meeting minutes.

[0551] "Means of delivery" refers to the technology used to supply generated reports and meeting minutes to users.

[0552] "Device means" refers to a device or system for inputting audio.

[0553] A "report" is a document used to present analyzed information to the user.

[0554] The system implementing this invention handles everything from inputting voice data to generating reports that include emotional information. The main components of this system are a device, a server, and a user.

[0555] A device is hardware for inputting voice, such as a microphone or smart glasses. Its role is to collect voice data in real time during a conversation and send it to a server.

[0556] The server implements a speech recognition engine and an emotion analysis engine. The server uses the Python SpeechRecognition library to convert speech data into text data. This text data is then used to recognize the emotional state using emotion analysis tools such as IBM Watson Tone Analyzer.

[0557] In addition, the server utilizes natural language processing technology to extract and summarize important information from text data. It then uses a formatting mechanism to format the data in a user-specified format, compiling the generated data into a report.

[0558] Finally, the server provides the generated report to the user via an interface accessible through the delivery system. The user can review this report and use it, for example, to review meetings or to implement measures for service improvement.

[0559] For example, when store staff interact with customers using smart glasses, voice is transmitted from the device, sentiment analysis is performed, and the results are then presented as visual feedback on the smart glasses. This allows staff to respond in a way that is in line with the customer's emotions, contributing to improved customer satisfaction.

[0560] Furthermore, the prompt "Please advise how to adjust customer service methods based on the customer's emotional state" can be used as input to the generative AI model.

[0561] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0562] Step 1:

[0563] The terminal uses a microphone to acquire audio data in real time. The acquired audio data is sent to the server in its original format. The input is audio data, which forms the basis for subsequent processing.

[0564] Step 2:

[0565] The server converts received audio data into text data using the Python SpeechRecognition library. This process adjusts the audio quality and removes noise to achieve high-precision text conversion. The input is audio data, and the output is the corresponding text data.

[0566] Step 3:

[0567] The server uses natural language processing to analyze text data and extract key information. In this process, the server identifies key phrases and decisions from the text and generates summary information. The input is text data, and the output is summarized key information.

[0568] Step 4:

[0569] The server utilizes IBM Watson Tone Analyzer to perform sentiment analysis on text data. This process identifies emotional states within the text and quantifies the results. The input is text data, and the output is data on the emotional states identified therein.

[0570] Step 5:

[0571] The server generates a report integrating extracted key information and emotional states based on the format specified by the user. The formatting means the report is visually organized. The input is key information and emotional state data, and the output is a formatted report.

[0572] Step 6:

[0573] The server uploads the generated report to the specified interface to provide it to the user. This process manages access rights to the report, allowing users to view and download it. The input is the report data, and the output is a document accessible to the user.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] [Fourth Embodiment]

[0578] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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).

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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".

[0591] This invention provides a technology for efficiently and accurately converting meeting audio into meeting minutes. The following describes a specific embodiment of the system and its operation.

[0592] First, when the meeting begins, the terminal starts recording via the microphone to collect audio data. The terminal converts the recorded audio into digital data in real time and transmits it to the server via wireless or wired communication. At this time, the audio data is preprocessed, including noise filtering, to ensure it is suitable for speech recognition.

[0593] Next, the server receives this audio data and uses a speech recognition engine to convert it from speech to text data. The speech recognition engine uses a highly accurate algorithm to reflect the diverse utterances in the text and adds metadata to identify each speaker in the audio.

[0594] The converted text data is analyzed by the server using natural language processing techniques. This process involves keyword extraction, summarization of key points, and classification. Particularly important statements and decisions are automatically highlighted, making them easily accessible to the user later.

[0595] The analysis results are formatted by the server according to the user's pre-specified format or template. Formatting options include organized formats by agenda item, timeline formats, and other formats tailored to the type and purpose of the meeting.

[0596] Finally, the generated meeting minutes are created in a file format specified by the server and placed on a portal or dashboard accessible to users. This allows users to easily download and share them.

[0597] For example, when a user conducts a project meeting, the device records the audio in the meeting room, and the audio data is sent to the server in real time. After the meeting ends or during the meeting, the server automatically generates detailed minutes corresponding to the progress of the meeting, making them immediately accessible to the user. In this way, participants can conduct the meeting efficiently without losing any details of the discussion.

[0598] The following describes the processing flow.

[0599] Step 1:

[0600] The device detects the start of the meeting and begins recording audio via the microphone. The audio data is converted to a digital format in real time and filtered to reduce background noise.

[0601] Step 2:

[0602] The terminal divides the audio data into chunks of a certain length and transfers them sequentially to the server via a communication line (wired or wireless). The data is transmitted in an efficient stream format.

[0603] Step 3:

[0604] The server sequentially passes the received audio chunks through the speech recognition engine, converting them from audio to text data. The converted text data is then tagged with metadata to identify the speaker.

[0605] Step 4:

[0606] The server analyzes the generated text data and uses natural language processing techniques to extract key keywords, main points, and decisions. This summarizes the main content of the meeting.

[0607] Step 5:

[0608] The server formats the extracted information according to the user's specifications. The format can be tailored to the user's needs, such as organizing by agenda item or using a timeline format.

[0609] Step 6:

[0610] The server generates the final meeting minutes in the specified file format, including PDF and Word, allowing users to view and share them.

[0611] Step 7:

[0612] After a meeting, users can access a dedicated portal or dashboard to access and download the created meeting minutes in real time. A notification system can also be used to inform users when the minutes are ready.

[0613] (Example 1)

[0614] 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".

[0615] In meetings and discussions, it is crucial to quickly and accurately record audio information as a document. However, conventional technologies have limitations in terms of audio conversion accuracy and the efficiency of extracting key points. Therefore, there has been a need for a system that can efficiently identify speakers, extract key points from discussions, and output them in various formats.

[0616] 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.

[0617] In this invention, the server includes an input device for inputting speech, a speech conversion device for receiving speech information transmitted from the input device and converting it into text information, and a natural language processing device for analyzing the text information, extracting important information and decision-making information, and summarizing it. This makes it possible to efficiently and accurately generate speech information as a recorded document and provide it in an appropriate format according to the user's needs.

[0618] An "input device" is a device that collects audio and transmits it to a server in a format that can be processed.

[0619] A "voice conversion device" is a device that has the function of analyzing received voice information and converting it into text information.

[0620] A "natural language processing system" is a device that extracts important information and decision-making information from text information and performs summarization.

[0621] A "format application device" is a device that has the function of formatting summarized information into a record document according to the format specified by the user.

[0622] A "providing device" is a device that provides generated record documents to users and places them on an online portal as needed.

[0623] An "information extraction device" is a device that has the function of accurately extracting the key points from a discussion.

[0624] This invention is a system for efficiently collecting audio from meetings and discussions and saving it as a documentary recording. This system is primarily implemented using the following hardware and software.

[0625] The terminal functions as an input device for collecting audio. It uses a microphone to record audio and is equipped with software that converts the collected audio into a digital signal in real time. This digitized audio data is transmitted to a server via a wireless or wired network.

[0626] The server functions as a speech converter. It converts received speech data into text data using speech recognition software, particularly generative AI models. It also acts as a natural language analyzer, analyzing the text data, extracting and summarizing important information and decision-making relevant information. Keyword extraction algorithms are used for this extraction process.

[0627] The server then uses a formatting device to generate a formatted record document based on the output format specified by the user. The server then uses a distribution device to provide the generated document to the user on an online portal or dashboard accessible by the user. This allows the user to easily view, download, and share the document.

[0628] As a concrete example, when a user initiates a team meeting, the device records the audio from the entire meeting room and sends that data to the server in real time. At the end of the meeting, or even during the meeting, the server transcribes the audio into text in real time and automatically generates a detailed record document based on the agenda.

[0629] An example of a prompt used as input to the generation AI model is, "Extract the main topics and decisions from this audio data and create meeting minutes." This system helps to accurately and efficiently document meeting content, enabling users to quickly retrieve the information they need.

[0630] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0631] Step 1:

[0632] The terminal receives audio input. When a user begins speaking in a conference room, the terminal's microphone captures the sound. The input is an analog audio signal, and the terminal converts this signal into digital audio data. The converted data is then noise-filtered to produce clear audio data. This data is then ready to be sent to the server.

[0633] Step 2:

[0634] The terminal transmits digital audio data to the server. The terminal sends the collected audio data to the server in real time via wireless or wired communication. The input here is digital audio data, and the output is a data stream destined for the server. A communication protocol is applied to ensure data integrity during transmission.

[0635] Step 3:

[0636] The server receives audio data and converts it to text. The server analyzes the audio data sent from the terminal using speech recognition software. The input is digital audio data, and the output is corresponding text data. This process uses a generative AI model to accurately transcribe a wide variety of speech.

[0637] Step 4:

[0638] The server analyzes text data and extracts key points. The generated text data is then processed by natural language processing software to extract important information. The input is text data, and the output is a set of summarized information. Here, a keyword extraction algorithm is used to identify important statements on the agenda.

[0639] Step 5:

[0640] The server formats the extracted information into a user-specified format. Based on the analyzed data, it generates a record document according to the format pre-configured by the user. The input is a summarized text set, and the output is a formatted document. This allows for document output tailored to different meeting formats.

[0641] Step 6:

[0642] The server provides the generated record documents. Finally, the generated record documents are saved in a specified electronic file format and placed on an online portal accessible to users. The input is the final document, and the output is the link or placement in storage for user access. This allows users to easily download and share the record documents.

[0643] (Application Example 1)

[0644] 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".

[0645] In today's business environment, meetings involving multiple participants are crucial for important decision-making, but accurately and quickly recording their content and sharing necessary information with stakeholders is not easy. In particular, the inability to check key points in real time during a meeting makes it difficult to grasp important matters without losing track of the flow of the discussion.

[0646] 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.

[0647] In this invention, the server includes means for acquiring sound; acoustic recognition means for receiving acoustic information transmitted from the means and converting it into symbolic information; and natural language processing means for analyzing the symbolic information, extracting important information and decision information, and summarizing it. This makes it possible to analyze the acoustic information of a meeting in real time and display important information on a mobile terminal.

[0648] "Means for acquiring sound" refers to devices including microphones and recording equipment for voice input.

[0649] "Acoustic information" refers to data that represents surrounding sounds and conversations as digital data.

[0650] "Symbolic information" refers to text data obtained through speech recognition based on acoustic information.

[0651] "Acoustic recognition means" refers to a processor or software that has speech analysis technology for converting acoustic information into text format.

[0652] A "natural language processing tool" is a computer program that analyzes symbolic information and efficiently extracts important information and decision-making information.

[0653] "User" refers to the person who operates this system.

[0654] A "format application means" is software that has the function of systematically organizing and outputting text information based on a format specified by the user.

[0655] "Supply means" refers to the network and communication means used to provide generated information and content to users.

[0656] A "mobile device" is an information display device that a user can carry with them, including smartphones and smart glasses.

[0657] In this system, the server acquires sound through microphones and recording devices placed in the conference room and transmits this acoustic information as digital data to the terminal. The terminal first receives the acoustic information and converts it into symbolic information using an acoustic recognition means. This acoustic recognition means implements a generally available speech recognition engine (e.g., Google Speech-to-Text API), and noise filtering is performed in real time.

[0658] The server then uses natural language processing tools to analyze the symbolic information and extract important and decision-making information. This process utilizes natural language processing libraries (e.g., spaCy and NLTK) to identify key keywords and meeting decisions, organizing them as summary data. Furthermore, this summary data is organized into a format specified by the user using a format application tool.

[0659] Users can view real-time analysis results provided by the server using mobile devices such as smartphones and smart glasses. The application implemented on the mobile device provides a user interface (UI) that allows for immediate review of the generated reports. This UI is designed to visually highlight important information, enabling users to instantly access the information they need during a meeting.

[0660] For example, when the sales department holds a strategy meeting for a new product, the server analyzes the meeting audio in real time and instantly displays the decisions on the smart glasses' display, allowing users to grasp the information without interrupting the flow of the discussion. An example of a prompt to the generative AI model to make the most of this system is as follows: "Convert the following meeting audio data to text and automatically generate meeting minutes highlighting the key points."

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The terminal uses high-performance microphones placed in the conference room to acquire acoustic information in real time. This information captures surrounding conversations and sounds as digital data.

[0664] Step 2:

[0665] The terminal transfers the acquired acoustic information to the server. During this process, the audio data is transmitted using wireless or wired communication methods, minimizing latency.

[0666] Step 3:

[0667] The server analyzes the received acoustic information using acoustic recognition means and converts it into symbolic information. Specifically, it uses a speech recognition engine to convert the data into text and simultaneously performs noise reduction. This process removes noise from the acoustic information, resulting in clear symbolic information.

[0668] Step 4:

[0669] The server performs further analysis of the symbolic information using natural language processing tools. Through the natural language processing libraries used here, it extracts key information, identifies key decisions, and generates summary data. At this stage, it utilizes generative AI model algorithms to organize the information compactly.

[0670] Step 5:

[0671] The server formats the generated summary data into the user's specified format using formatting means. The output report format can include features such as categorization by agenda item and timeline display, and is designed to be easily understood by the user.

[0672] Step 6:

[0673] Users receive analysis results in real time via their mobile devices. The application on the device is designed to highlight important information and decisions, allowing users to review them immediately. This makes it possible to stay on top of the discussion flow without missing important information during meetings.

[0674] 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.

[0675] This invention provides new functionality by combining an emotion engine with a conventional meeting minutes generation system. By analyzing the emotions of participants during a meeting and managing this information together with the meeting record, this invention enables the creation of richer meeting minutes.

[0676] During the meeting, the device continuously collects audio and transmits the data to the server in real time. The audio data is converted into text data by a speech recognition engine, with an emotion engine also working in conjunction. The emotion engine analyzes parameters such as tone, pitch, and speed of the voice to recognize the user's emotional state.

[0677] The server analyzes the continuously acquired sentiment data along with the textualized content of the statements. While natural language processing extracts and summarizes important points, the sentiment engine grasps and quantifies the emotional response to each statement. This makes it possible to understand the atmosphere of the discussion within the meeting and the changes in the participants' emotions.

[0678] The generated meeting minutes record the emotional state of participants along with the identified key points. This recorded emotional data can be used as an indicator of whether the meeting proceeded smoothly or whether there was tension regarding a particular topic. Furthermore, when the minutes are organized into a user-specified format using a formatting application method, the emotional information serves as visually represented supplementary information.

[0679] The server then creates the final generated meeting minutes and sentiment report together in the specified file format. These generated documents can then be viewed and downloaded in real time by users accessing a dedicated portal.

[0680] For example, during project progress meetings, users can utilize emotional data to later review members' reactions. This allows project managers to develop future strategies based not only on the meeting content but also on the team's atmosphere and reactions. By using this system, an emotional dimension is added to the content of discussions during meetings, providing more detailed insights.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The device detects the start of a meeting and collects audio using the microphone. The audio data is converted to a digital format in real time and filtered to minimize background noise.

[0684] Step 2:

[0685] The terminal divides the recorded audio data into chunks of regular time intervals and sends them sequentially to the server. This minimizes data delay and enables efficient communication.

[0686] Step 3:

[0687] The server uses a speech recognition engine to convert received speech chunks into text data. During this process, information about speech intonation and speed is preserved, thus retaining non-verbal data necessary for sentiment analysis.

[0688] Step 4:

[0689] The server runs an emotion engine in parallel, analyzing emotion parameters extracted from the audio data. It determines the user's emotions based on volume, tone, tempo, etc., and records this as metadata by tagging each utterance.

[0690] Step 5:

[0691] The server utilizes natural language processing technology to analyze text data and extract important points and resolutions. Based on the analysis results of the emotion engine, it associates the content of statements with the user's emotional state to create a meeting minutes summary.

[0692] Step 6:

[0693] The server organizes the obtained summaries and sentiment information according to a format specified by the user. This includes preparing to visualize the sentiment analysis results associated with each statement.

[0694] Step 7:

[0695] The server generates the final meeting minutes and sentiment report and saves them in the selected file format (e.g., PDF or Word). These are then placed in a dedicated portal for easy access by users.

[0696] Step 8:

[0697] Users can access the portal to view and download the generated meeting minutes. The server can also automatically notify users when the minutes are complete through a notification function.

[0698] (Example 2)

[0699] 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".

[0700] Conventional meeting minute generation systems summarize meeting content and extract key points, but they do not analyze or record participants' emotions. As a result, meeting minutes are not created that reflect the atmosphere of the meeting or the changes in participants' emotions, leading to a lack of insights necessary for decision-making.

[0701] 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.

[0702] In this invention, the server includes speech recognition means for receiving audio information and converting it into text information, natural language processing means for analyzing the text information and extracting and expressing important points and emotional states, and emotion analysis means for analyzing the tone, pitch, and speed of the voice and capturing the user's emotional state. This makes it possible to generate detailed and useful meeting minutes that take into account not only the content of the meeting but also the emotions of the participants.

[0703] "Audio information" refers to the digital representation of sounds and language used when recording or processing words spoken in meetings or conversations.

[0704] An "information processing device" is an electronic device capable of receiving voice information and transmitting it to a server.

[0705] "Speech recognition means" refers to a technology or system for converting speech information into text format.

[0706] "Textual information" refers to text data converted from speech information by speech recognition technology.

[0707] "Natural language processing means" refers to technologies or systems that analyze textual information to extract important information and emotional states.

[0708] "Emotional analysis means" refers to technology that analyzes elements such as tone, pitch, and speed of voice to capture the user's emotional state.

[0709] "Format application means" refers to technologies and systems for generating and organizing meeting minutes according to a format specified by the user.

[0710] "Delivery method" refers to the means of providing the generated meeting minutes and sentiment reports to users in an available format.

[0711] This invention is an information processing system for analyzing audio information in meetings and conversations and generating rich meeting minutes that include the emotions of the participants. Specific embodiments of the system are described below.

[0712] The terminal is an information processing device equipped with voice input capabilities, which collects the voices of participants during a meeting in real time. This voice information is then transmitted to the server in a digitized format. The terminal can use a high-sensitivity microphone or the microphone built into a laptop computer.

[0713] The server is equipped with various technical means for processing received audio information. First, it uses a publicly available general-purpose speech recognition engine (e.g., a large-scale cloud-based speech recognition service) as a speech recognition means to convert the audio information into text information. Next, it uses machine learning and generative AI models as natural language processing means to extract and analyze important items and emotional states from the text information. Furthermore, it uses analytical techniques for emotion analysis as an emotion analysis means to analyze the speech characteristics in detail.

[0714] Through these processes, a report is created in the format specified by the user. This report visually includes not only what was said during the meeting, but also the emotional reactions of the participants and the tone of the discussion, thereby improving the quality of decision-making.

[0715] Users can review and download generated meeting minutes and sentiment reports through a specially accessible online portal. For example, in a project progress meeting, it's possible to generate prompts such as, "In the Project A progress meeting, please propose the next steps based on the changes in members' opinions and sentiments," and then use a generative AI model to develop further strategies. In this way, meeting minutes with added sentiment dimension take not only the content of the meeting but also the insights gained from it to an entirely new level.

[0716] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0717] Step 1:

[0718] The terminal continuously collects the voices of meeting participants using a microphone. It collects raw voice information from meeting participants as input, digitizes it, and sends it to the server. Specifically, voice data is recorded from the microphone connected to the terminal and transmitted to the server in real time via the network.

[0719] Step 2:

[0720] The server analyzes the audio data received from the terminal and converts it into text data using speech recognition. The input is digitized audio data, and the output is text-based character data. In this process, the speech recognition software analyzes the audio waveform and automatically generates text in the corresponding language.

[0721] Step 3:

[0722] The server analyzes the emotional state of participants using emotion analysis tools that analyze the tone, pitch, and speed of their voices. The input is the text data processed in step 2 and the original audio data, and the output is metadata of the emotional state associated with the text data. Specifically, it identifies emotions such as anger, joy, and doubt by analyzing the parameters of the audio data.

[0723] Step 4:

[0724] The server analyzes the text data using natural language processing techniques to extract and summarize the key points of the meeting. The input is the text data and emotional state metadata obtained in steps 2 and 3, and the output is the text summarizing the key points and data including the emotions at that time. Specifically, the server extracts keywords from the spoken content and then summarizes them.

[0725] Step 5:

[0726] The server generates meeting minutes and sentiment reports in the user-specified format based on the formatting application mechanism. The input is the summarized data generated in step 4, and the output is the meeting minutes and sentiment report formatted in the final format. Specific operations include document formatting based on templates and graphical visualization of sentiment information.

[0727] Step 6:

[0728] Users access meeting minutes and sentiment reports generated by the server through a dedicated portal. Input is a formatted document obtained from the server, and output is available for viewing on the user's device. Specifically, users access the portal using a web browser and download the necessary documents.

[0729] (Application Example 2)

[0730] 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".

[0731] Traditional meeting minute systems have the drawback of failing to capture the emotional elements of meetings, making it difficult to analyze changes in participants' emotions and the overall atmosphere. Furthermore, there has been a lack of means to collect and utilize emotional information in real-time during real-world human interactions. This has limited opportunities for improving responses and enhancing services based on feedback.

[0732] 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.

[0733] In this invention, the server includes emotion analysis means for analyzing voice tone and speed to identify emotional states, speech recognition means for converting voice data into text data, and formatting means for generating reports according to a user-specified format. This allows for the addition of an emotional dimension to spoken content in meetings and service settings, enabling real-time, detailed insights and feedback.

[0734] "Speech recognition means" refers to technology for converting speech data into text data.

[0735] "Natural language processing methods" are technologies that analyze text data, extract important points and decisions, and summarize them.

[0736] "Emotional analysis techniques" are technologies that analyze the tone and speed of speech to identify the speaker's emotional state.

[0737] "Format application means" refers to technology for organizing data according to a user-specified configuration and generating reports and meeting minutes.

[0738] "Means of delivery" refers to the technology used to supply generated reports and meeting minutes to users.

[0739] "Device means" refers to a device or system for inputting audio.

[0740] A "report" is a document used to present analyzed information to the user.

[0741] The system implementing this invention handles everything from inputting voice data to generating reports that include emotional information. The main components of this system are a device, a server, and a user.

[0742] A device is hardware for inputting voice, such as a microphone or smart glasses. Its role is to collect voice data in real time during a conversation and send it to a server.

[0743] The server implements a speech recognition engine and an emotion analysis engine. The server uses the Python SpeechRecognition library to convert speech data into text data. This text data is then used to recognize the emotional state using emotion analysis tools such as IBM Watson Tone Analyzer.

[0744] In addition, the server utilizes natural language processing technology to extract and summarize important information from text data. It then uses a formatting mechanism to format the data in a user-specified format, compiling the generated data into a report.

[0745] Finally, the server provides the generated report to the user via an interface accessible through the delivery system. The user can review this report and use it, for example, to review meetings or to implement measures for service improvement.

[0746] For example, when store staff interact with customers using smart glasses, voice is transmitted from the device, sentiment analysis is performed, and the results are then presented as visual feedback on the smart glasses. This allows staff to respond in a way that is in line with the customer's emotions, contributing to improved customer satisfaction.

[0747] Furthermore, the prompt "Please advise how to adjust customer service methods based on the customer's emotional state" can be used as input to the generative AI model.

[0748] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0749] Step 1:

[0750] The terminal uses a microphone to acquire audio data in real time. The acquired audio data is sent to the server in its original format. The input is audio data, which forms the basis for subsequent processing.

[0751] Step 2:

[0752] The server converts received audio data into text data using the Python SpeechRecognition library. This process adjusts the audio quality and removes noise to achieve high-precision text conversion. The input is audio data, and the output is the corresponding text data.

[0753] Step 3:

[0754] The server uses natural language processing to analyze text data and extract key information. In this process, the server identifies key phrases and decisions from the text and generates summary information. The input is text data, and the output is summarized key information.

[0755] Step 4:

[0756] The server utilizes IBM Watson Tone Analyzer to perform sentiment analysis on text data. This process identifies emotional states within the text and quantifies the results. The input is text data, and the output is data on the emotional states identified therein.

[0757] Step 5:

[0758] The server generates a report integrating extracted key information and emotional states based on the format specified by the user. The formatting means the report is visually organized. The input is key information and emotional state data, and the output is a formatted report.

[0759] Step 6:

[0760] The server uploads the generated report to the specified interface to provide it to the user. This process manages access rights to the report, allowing users to view and download it. The input is the report data, and the output is a document accessible to the user.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] The following is further disclosed regarding the embodiments described above.

[0783] (Claim 1)

[0784] A terminal device for inputting voice,

[0785] A speech recognition means for receiving audio data transmitted from the terminal means and converting it into text data,

[0786] A natural language processing means that analyzes the aforementioned text data, extracts important points and decisions, and performs a summary;

[0787] A formatting application means that applies the summary according to the format specified by the user and generates meeting minutes,

[0788] A means for providing the generated meeting minutes to the user,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, wherein the natural language processing means comprises keyword extraction means for extracting the main points of the discussion.

[0792] (Claim 3)

[0793] The system according to claim 1, wherein the providing means includes means for saving the generated meeting minutes in a specified file format and placing them on a portal accessible to users.

[0794] "Example 1"

[0795] (Claim 1)

[0796] An input device for inputting audio,

[0797] A speech conversion device for receiving speech information transmitted from the aforementioned input device and converting it into text information,

[0798] A natural language processing device that analyzes the aforementioned text information, extracts important information and decision-making information, and performs a summary thereof.

[0799] A formatting device that applies the summary according to the format specified by the user and generates a record document,

[0800] A providing device for providing the generated record document to the user,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the natural language processing device comprises an information extraction device for extracting the main points of a discussion.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the providing device includes a device that stores the generated record documents in a specified electronic format and places them on an online portal accessible to users.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] Means for acquiring sound,

[0809] A sound recognition means for receiving acoustic information transferred from the aforementioned means and converting it into symbolic information,

[0810] A natural language processing means analyzes the aforementioned symbolic information, extracts important information and decision information, and performs a summary.

[0811] A formatting means that applies the summary according to the format specified by the user and generates a report,

[0812] A supply means for supplying the generated report to the user,

[0813] A mobile device that displays the aforementioned report and important information in real time,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein the natural language processing means comprises information extraction means for extracting key points of a meeting.

[0817] (Claim 3)

[0818] The system according to claim 1, wherein the supply means includes means for recording the generated report in a specified information format and placing it on an online portal accessible to the user.

[0819] "Example 2 of combining an emotion engine"

[0820] (Claim 1)

[0821] Information processing means for inputting voice,

[0822] A speech recognition means for receiving speech information transmitted from the aforementioned information processing means and converting it into text information,

[0823] A natural language processing means that analyzes the aforementioned textual information, extracts important information and emotional states, and expresses them;

[0824] An emotion analysis method that analyzes the tone, pitch, and speed of voice to capture the user's emotional state,

[0825] A formatting means that applies the aforementioned expression according to the format specified by the user and generates meeting minutes,

[0826] A means for providing the generated meeting minutes and sentiment report to the user,

[0827] An information processing system that includes this.

[0828] (Claim 2)

[0829] The information processing system according to claim 1, wherein the natural language processing means comprises data extraction means for extracting the main points of a discussion and related emotional responses.

[0830] (Claim 3)

[0831] The information processing system according to claim 1, wherein the providing means includes means for saving the generated meeting minutes and sentiment reports in a specified electronic file format and placing them on an online portal accessible to users.

[0832] "Application example 2 when combining with an emotional engine"

[0833] (Claim 1)

[0834] A device for inputting voice,

[0835] A speech recognition means for receiving audio data transmitted from the aforementioned device means and converting it into text data,

[0836] A natural language processing means that analyzes the aforementioned text data, extracts important points and decisions, and performs a summary;

[0837] A means of emotional analysis for identifying emotional states by analyzing voice tone and speed,

[0838] A formatting application means that applies the summary and sentiment information according to a format specified by the user to generate a report,

[0839] A means for providing the generated report to the user,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, wherein the natural language processing means comprises a key word extraction means for extracting the main points of a discussion.

[0843] (Claim 3)

[0844] The system according to claim 1, wherein the providing means includes means for saving the generated report in a specified file format and placing it on an interface accessible to the user. [Explanation of Symbols]

[0845] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for acquiring sound, A sound recognition means for receiving acoustic information transferred from the aforementioned means and converting it into symbolic information, A natural language processing means analyzes the aforementioned symbolic information, extracts important information and decision information, and performs a summary. A formatting means that applies the summary according to the format specified by the user and generates a report, A supply means for supplying the generated report to the user, A mobile device that displays the aforementioned report and important information in real time, A system that includes this.

2. The system according to claim 1, wherein the natural language processing means comprises information extraction means for extracting key points of a meeting.

3. The system according to claim 1, wherein the supply means includes means for recording the generated report in a specified information format and placing it on an online portal accessible to the user.

Images