system

Abstract

Provide a system. The present invention includes: a means for collecting information entered by a user on a whiteboard during a meeting in real time; a terminal means for transmitting the collected information to a server; A means for converting the information received by the server into text; A means of gathering relevant information from internal databases and external sources based on the textual information; means for analyzing and visually displaying the collected relevant information; A system including:

Description

[Technical Field]

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

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

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

[0004] Meetings are an important means of communication for companies and organizations, but creating meeting minutes and collecting related information often requires time and effort, resulting in reduced efficiency. In particular, the difficulty of obtaining necessary relevant information in real time during a meeting often slows down the progress of the meeting. Furthermore, manually compiling minutes after a meeting is inefficient and prone to errors and information omissions. To address these issues, a system is needed that can generate meeting minutes in real time during a meeting and automatically add relevant information. [Means for solving the problem]

[0005] This invention provides a terminal means for collecting information entered by users on a whiteboard during a meeting in real time and transmitting it to a server. The terminal means uses a camera and microphone to capture the contents of the meeting and transmits the captured information to the server. The server converts the received information into text using voice recognition technology or optical character recognition technology, and automatically collects related information from an internal database or external information sources based on the converted text. The collected related information is analyzed by the server and visually displayed. This system allows users to obtain necessary information in real time during a meeting and automatically generates meeting minutes, significantly improving the efficiency of the meeting.

[0006] "User" refers to the individual or group who operates the system and enters information on the whiteboard during a meeting.

[0007] A "whiteboard" is a board on which a user can write information by hand, and refers to a device used to visualize the contents of a meeting.

[0008] "Real-time" refers to processing and data exchange occurring immediately, without delay.

[0009] "Means of collection" refers to a device or system that captures audio and video generated during a meeting using a camera, microphone, etc., and stores it as digital data.

[0010] "Terminal means" refers to a device or apparatus for collecting data and transmitting it to a server.

[0011] "Server" refers to a computer system for processing and analyzing received data.

[0012] "Voice recognition technology" refers to technology that converts voice data into text data.

[0013] "Optical character recognition technology (OCR)" refers to the technology that converts handwritten or printed characters into digital text.

[0014] "Texting" refers to the process of converting speech or optically recognized characters into digital text data.

[0015] "Relevant information" refers to supplementary or background information related to the agenda of the meeting, including data obtained from internal company databases or external sources.

[0016] "Analysis" refers to the process of classifying collected data and organizing it into an appropriate format.

[0017] "Visual display means" refers to technology or devices that display analyzed information on a whiteboard or screen in a format that is easy for users to understand, such as graphs or charts.

[0018] "System" refers to a collection of devices, technologies, and software in which the above elements work together to achieve a specific function. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that generates minutes in real time during a meeting and automatically adds related information. This system is realized by collecting information entered by users on the terminal, and processing and analyzing it on the server.

[0041] System configuration

[0042] The system consists of the following main components:

[0043] User: An individual or group who enters information on the whiteboard during a meeting.

[0044] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[0045] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user.

[0046] Program processing

[0047] 1. User Actions

[0048] A user starts a meeting and handwrites "New Product Release Date" on the whiteboard.

[0049] 2. Data Collection

[0050] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[0051] The captured data is sent to a server in real time.

[0052] 3. Data Processing

[0053] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0054] At the same time, the voice data is converted into text data using voice recognition technology.

[0055] Text data of the "new product release date" is generated.

[0056] 4. Collection of relevant information

[0057] Based on the text data, the server automatically collects past project data related to the "new product release date," documents from internal databases, external market trend reports, and so on.

[0058] 5. Data Analysis and Presentation

[0059] The server analyzes the collected information and compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[0060] The compiled information is displayed on a whiteboard in real time for the user to review.

[0061] Specific examples

[0062] Example 1: Starting a meeting and generating minutes

[0063] A user writes on a whiteboard, "Decide the budget for the next project."

[0064] The device captures handwritten text with its camera and records audio with its microphone.

[0065] The server uses OCR technology to convert handwritten characters into text data, and at the same time uses voice recognition technology to convert voice data into text.

[0066] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database.

[0067] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[0068] Example 2: Dynamic information addition during a meeting

[0069] A user says in a statement, "I want to find out about market trends this year."

[0070] The device captures the audio and sends it to the server.

[0071] The server recognizes the voice and converts it into text, then automatically searches for market trend reports based on that text.

[0072] Market trend graphs and report summaries are displayed on the whiteboard, allowing users to review them as they conduct the meeting.

[0073] This system automatically collects and analyzes necessary information during meetings, allowing users to efficiently conduct meetings and obtain relevant information in real time, greatly simplifying the creation of minutes and improving the quality of meetings.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[0077] Step 2:

[0078] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[0079] Step 3:

[0080] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[0081] Step 4:

[0082] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[0083] Step 5:

[0084] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[0085] Step 6:

[0086] The server analyzes the transcripts of the meeting minutes and automatically collects relevant information from internal databases and external sources. In this case, it retrieves past release data and market trend reports related to the "new product release date."

[0087] Step 7:

[0088] The server analyzes the collected related information and organizes the necessary information into an appropriate format, for example, generating graphs of past release schedules or market trends.

[0089] Step 8:

[0090] The server sends the organized information to the device in real time, where it is displayed visually on the whiteboard.

[0091] Step 9:

[0092] Users can check the supplementary information displayed on the whiteboard and proceed with the meeting, adding new topics or expressing opinions as necessary.

[0093] Step 10:

[0094] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the agenda, what was said, and any related information collected during the meeting.

[0095] Step 11:

[0096] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] In modern meetings, a large amount of information is exchanged in real time, making it difficult to create minutes and search for information during the meeting. Furthermore, there is a lack of systems that can efficiently manage various information formats, including handwritten and audio recordings, and support the progress of meetings. This leads to issues such as reduced meeting productivity and a loss of accuracy in meeting minutes.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for collecting information input by users to a display device during a meeting in real time, terminal means for transmitting the collected information to a computer, means for converting the information received by the computer into text, means for collecting related information from an internal database or external information source based on the converted text, and means for analyzing and visually displaying the collected related information. This makes it possible to instantly obtain related information during a meeting and reflect it in the minutes, significantly improving the productivity of the meeting and the accuracy of the minutes.

[0102] A "user" is an individual or group that enters information during a conference.

[0103] A "display device" is a device that allows a user to input information, and includes, for example, a whiteboard or digital screen.

[0104] "Means for collecting information in real time" refers to technologies and devices that instantly acquire information entered during a meeting and use it for subsequent processing.

[0105] "Terminal means for transmitting to a computer" refers to a device or network infrastructure for transmitting collected information to a server.

[0106] A "computer" is an electronic device that processes received information and performs various data conversions and analyses.

[0107] "Means of converting text" refers to technologies that convert handwritten or voice data into character data, including optical character recognition (OCR) and voice recognition.

[0108] An "internal database" is a database that stores various data within a company.

[0109] "External sources" are sources of information provided on the Internet or by external organizations.

[0110] "Means of collecting relevant information" refers to the techniques and processes used to obtain the necessary data from internal databases and external sources based on the textual information.

[0111] "Visual display means" refers to techniques and devices that present the collected and analyzed information to the user in the form of charts, graphs, text, etc.

[0112] This system collects and analyzes information input to a display device during a meeting in real time, and automatically acquires and displays related information. The system is mainly composed of three elements: users, terminals, and a server.

[0113] User

[0114] During a meeting, users input information into the display device, for example, by writing documents by hand on a whiteboard or digital screen, or by making speeches.

[0115] Terminal

[0116] The terminal is a device for collecting information entered by the user, and includes a camera and a microphone. For example, handwritten information entered on a whiteboard is captured by the camera, and audio of conversations is recorded by the microphone. Specific devices used include Logitech webcams and Shure conference microphones. The collected data is sent from the terminal to a server in real time.

[0117] server

[0118] The server receives the data sent from the device and performs the following operations:

[0119] 1. Convert data to text

[0120] The server converts the received data into character data. At this time, handwritten data is converted into text data using optical character recognition (OCR) technology. The specific software used is Google® Cloud Vision API. At the same time, voice data is converted into text data using voice recognition technology. Google Cloud Speech-to-Text is used for this process.

[0121] 2. Collection of relevant information

[0122] Based on the textual information, the server automatically collects related information, such as from past project data, an internal database (Microsoft® SharePoint), or external market trend reports (Gartner). This allows users to quickly gather the information they need.

[0123] 3. Data Analysis and Presentation

[0124] The server analyzes the collected information and compiles it into an appropriate format (for example, using Excel or Tableau). The compiled information is then displayed in real time on a display device so that the user can view it.

[0125] Specific examples

[0126] Example 1: Starting a meeting and generating minutes

[0127] A user writes on a whiteboard, "Decide the budget for the next project."

[0128] The device captures the handwriting with its camera and records the audio with its microphone.

[0129] The server uses OCR technology (Google Cloud Vision API) to convert handwritten characters into text data, and converts the audio data into text using speech recognition technology (Google Cloud Speech-to-Text).

[0130] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database (Microsoft SharePoint).

[0131] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[0132] Example 2: Dynamic information addition during a meeting

[0133] A user says in a statement, "I want to find out about market trends this year."

[0134] The device captures the audio and sends it to the server.

[0135] The server recognizes the speech and converts it into text, then automatically searches for market trend reports (Gartner reports) based on that text.

[0136] Market trend graphs and report summaries are displayed on the whiteboard, and users can review them as they conduct the meeting.

[0137] Prompt Sentence Examples

[0138] "Please explain in detail the processing procedures of a system that captures written content and audio in real time during a meeting and automatically collects and displays information related to that content. Also, please name the specific hardware and software, and describe the data processing and calculation methods."

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] The user inputs information into the display device.

[0142] Input: A user handwrites "New product release date" on the display device.

[0143] Output: Written and spoken text is recorded on the display device.

[0144] Specific operation: The user writes characters by hand on the whiteboard and speaks at the same time.

[0145] Step 2:

[0146] The device captures your handwriting and voice.

[0147] Input: Written text on the display and spoken words by the user.

[0148] Output: Captured image and audio data.

[0149] What it does: The camera captures what you write, and the microphone records what you say.

[0150] Step 3:

[0151] The device sends the captured data to the server.

[0152] Input: Image and audio data.

[0153] Output: Image and audio data sent to the server.

[0154] Specific operation: The terminal's communication module sends the collected data to a server via the Internet.

[0155] Step 4:

[0156] The server converts the image data and audio data into text data.

[0157] Input: Image and audio data sent to the server.

[0158] Output: The converted text data.

[0159] Specific operation: The server's OCR engine extracts characters from image data, and the speech recognition engine generates text from speech.

[0160] Step 5:

[0161] The server collects related information based on the text data.

[0162] Input: The converted text data.

[0163] Output: Relevant information collected (historical project data, external reports, etc.).

[0164] What happens: The server queries internal databases and external sources to retrieve the required data.

[0165] Step 6:

[0166] The server analyzes the collected information and displays it visually.

[0167] Input: The relevant information you have collected.

[0168] Output: A visual format (text, graphs, charts, etc.) containing the results of the analysis.

[0169] Specific operation: The server analyzes the data, visually summarizes the information using Excel or Tableau, and sends it to the display device.

[0170] Step 7:

[0171] The user proceeds with the conference while checking the presented information.

[0172] Input: Visual information displayed on a display device.

[0173] Output: Review meeting progress and minutes.

[0174] Specific operation: The user refers to the information displayed on the display device and decides on the next agenda item or action item.

[0175] (Application example 1)

[0176] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0177] Conventional conference systems and factory robots lacked systems that could collect information in real time and automatically present relevant information. This made it difficult to quickly and effectively obtain necessary information during meetings or factory work, leading to calls for improvements in work efficiency and quality. Furthermore, there was a lack of technology that could convert handwritten text and voice into text in real time and automatically collect and analyze relevant information based on that information, making it difficult for users to use information efficiently. This created the risk of delays in meeting and work progress and decisions being made based on incorrect information.

[0178] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0179] In this invention, the server includes a means for collecting information entered by users during meetings or work in real time, a terminal means for transmitting the collected information to the server, and a means for converting the information received by the server into text. This makes it possible to collect related information from databases and external information sources based on the converted text, analyze the collected related information, and visually display it, and to present the related information in real time to devices used in the factory. This allows factory work and meetings to proceed quickly and effectively, improving work efficiency and quality.

[0180] "User" refers to an individual or group that uses the system to hold meetings or carry out factory work.

[0181] "Real-time" refers to information being processed and displayed almost in sync with the moment it is generated.

[0182] "Terminal means" refers to a device, such as a camera, microphone, smart glasses, or head-mounted display, that collects information entered by a user and transmits it to a server.

[0183] "Server" refers to a computing system for processing received data, performing necessary analysis, and providing relevant information.

[0184] "Text conversion" refers to the conversion of non-text information, such as handwritten characters or audio data, into machine-readable text data.

[0185] "Database" refers to an information system that stores related information in a structured manner so that it can be efficiently searched and accessed at a later time.

[0186] "External sources" refers to information sources other than internal databases, such as external databases, network resources, and online reports.

[0187] "Analysis" refers to the act of processing collected data using statistical and logical methods to extract meaningful information and insights.

[0188] "Visually" refers to presenting information in the form of text, graphs, charts, images, etc., so that it can be easily understood by the user.

[0189] "Devices used within the factory" refers to devices used by factory workers to receive and display information, such as smart glasses, tablets, and head-mounted displays.

[0190] "Related information" refers to additional data or materials related to the information or statements entered by the user that are useful for work or decision-making.

[0191] This invention is a system that presents relevant information in real time to devices primarily used in factories, and is composed of the following components:

[0192] System configuration

[0193] 1. User:

[0194] Factory workers use devices such as smart glasses and tablet computers to perform their work.

[0195] 2. Terminal means:

[0196] These include smart glasses, tablet devices, head-mounted displays, etc., which capture information such as voice and handwritten characters and send it to a server.

[0197] 3. Server:

[0198] Its main functions are:

[0199] The received voice data is converted into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0200] Optical character recognition technology (e.g., OCR) is used to convert handwritten characters into text.

[0201] Based on the textual data, relevant information is collected from databases and external sources.

[0202] The collected information is analyzed and displayed on the device in real time.

[0203] Operation flow

[0204] Data collection:

[0205] Take the example of a user saying, "Please display the work instructions for the next process." The microphone in the smart glasses captures the voice and sends it to the server.

[0206] Data Processing:

[0207] The server converts the voice data into text data using the Google Speech-to-Text API, and then collects and analyzes information related to work instructions for the next process from an internal database.

[0208] Information presentation:

[0209] Relevant information collected from databases and external information sources is displayed in real time on the display of smart glasses or tablet devices, allowing users to work while checking the displayed information.

[0210] Specific examples

[0211] Consider a factory worker saying, "Tell me how to assemble this part." The smart glasses capture the voice and the server converts it into text data. The server then retrieves the relevant assembly procedure data from the database and visually displays it on the smart glasses' display. In this way, users can obtain the information they need in real time while working, allowing them to perform their tasks efficiently and accurately.

[0212] Prompt Sentence Examples

[0213] Factory worker: "Show me the work instructions for the next process."

[0214] Server (prompt for input to generative AI model): "Search for the next process step. Display relevant information from the factory database."

[0215] It is expected that such a system will improve the efficiency of work within the factory and the quality of work.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] The user speaks into the smart glasses, saying, "Show me the work instructions for the next step." The input is voice data, which is captured by the smart glasses' microphone. The output is the captured voice data.

[0219] Step 2:

[0220] The smart glasses of the terminal means transmit the captured voice data to the server. The input is the captured voice data, and the output is the data transmission to the server.

[0221] Step 3:

[0222] The voice data received by the server is converted into text data using the Google Speech-to-Text API. The input is the voice data received by the server, and the output is text data. Specifically, the server sends the voice data to the API and receives text data as the conversion result.

[0223] Step 4:

[0224] The server searches an internal database for information related to the work instructions for the next process based on the text data. The input is the converted text data ("Show me the work instructions for the next process"), and the output is the related work instruction data. Specifically, the server generates a query and searches the database.

[0225] Step 5:

[0226] The server analyzes the work instruction data retrieved from the database and converts it into a format for visual display. The input is raw data retrieved from the database, and the output is formatted data that can be displayed visually (e.g., text, graphs, charts). Specifically, the server performs formatting processing on the data and converts it into a format that is easy for users to understand.

[0227] Step 6:

[0228] The server transmits formatted work instruction data to the smart glasses as the terminal means. The input is the formatted data formatted by the server, and the output is the data displayed on the smart glasses.

[0229] Step 7:

[0230] The smart glasses display the received work instruction data in the user's field of view. The input is formatted data received from the server, and the output is visual information displayed on the smart glasses' display. Specifically, the smart glasses render the received data on their display.

[0231] Through these processing steps, users can obtain the information they need in real time while working, allowing them to work efficiently and accurately.

[0232] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0233] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision according to the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by the server.

[0234] System configuration

[0235] The system consists of the following main components:

[0236] User: An individual or group who enters information on the whiteboard during a meeting.

[0237] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[0238] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user. It also uses an emotion engine to recognize and analyze the user's emotions.

[0239] Emotion engine: Recognizes the user's emotions from audio and video data, and changes the priority of information and feedback based on those emotions.

[0240] Program processing

[0241] 1. User Actions

[0242] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[0243] 2. Data Collection

[0244] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[0245] The captured data is sent to a server in real time.

[0246] 3. Data Processing

[0247] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0248] At the same time, the voice data is converted into text data using voice recognition technology.

[0249] Text data of the "new product release date" is generated.

[0250] 4. Emotion recognition

[0251] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[0252] The emotion engine generates emotion data indicating whether the user is excited, calm, anxious, etc.

[0253] 5. Collection of relevant information

[0254] The server automatically collects past project data, documents from internal databases, external market trend reports, etc. related to the "new product release date" based on text data and sentiment data.

[0255] 6. Data Analysis and Presentation

[0256] The server analyzes and prioritizes the collected information based on emotional data, and then compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[0257] If the user is feeling anxious, more detailed information and supplementary materials will be displayed preferentially.

[0258] 7. Real-time feedback

[0259] The compiled information is displayed on a whiteboard in real time, allowing users to check information that corresponds to their emotions.

[0260] Specific examples

[0261] Example 1: User excitement

[0262] "This is a very important release," an excited user said.

[0263] The device captures the audio and sends it to the server.

[0264] The server uses voice recognition and an emotion engine to recognize the user's state of excitement.

[0265] The server collects and displays a list of planned release dates and competitive information.

[0266] Example 2: User Concerns

[0267] The user stated in an anxious tone that he was "unsure of the release date."

[0268] The device captures the audio and sends it to the server.

[0269] The server uses voice recognition and an emotion engine to recognize the user's anxiety state.

[0270] The server prioritizes the collection and display of supplementary information such as "past success stories" and "risk management plans."

[0271] This system not only automatically collects and analyzes necessary information during meetings, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[0272] The processing flow will be explained below.

[0273] Step 1:

[0274] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[0275] Step 2:

[0276] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[0277] Step 3:

[0278] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[0279] Step 4:

[0280] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[0281] Step 5:

[0282] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[0283] Step 6:

[0284] The server's emotion engine analyzes audio and video data to recognize the user's emotions and generates emotion data such as "excited," "anxious," or "calm."

[0285] Step 7:

[0286] The server analyzes the textual minutes and sentiment data, and automatically collects relevant information from internal databases and external sources, such as past project data and market trend reports related to "new product release dates."

[0287] Step 8:

[0288] The server analyzes the collected relevant information and prioritizes it based on emotional data: for example, if the user is excited, it will promptly present a release candidate date, but if the user is anxious, it will prioritize detailed risk management information.

[0289] Step 9:

[0290] The server sends the organized information to the terminal in real time and displays it visually on the whiteboard. Users can proceed with the meeting while checking the displayed supplementary information.

[0291] Step 10:

[0292] If a user adds a new comment or topic during the meeting, the device will again capture voice and handwritten data and send it to the server, which will then analyze the data again and collect and display the relevant information.

[0293] Step 11:

[0294] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the meeting topics, comments, emotional data, and other relevant information collected during the meeting.

[0295] Step 12:

[0296] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[0297] Example 2

[0298] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0299] Creating effective minutes during meetings is an important challenge for many companies and organizations. However, traditional methods for creating minutes have made it difficult to collect information in real time and provide relevant information promptly. It has also been difficult to accurately grasp users' emotions during the meeting and provide information appropriate to those emotions. As a result, the efficiency and effectiveness of meetings are often compromised.

[0300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0301] In this invention, the server includes means for recognizing user emotions from audio data and video data, means for changing information priority and feedback based on the emotion data, and means for analyzing and visually displaying collected related information, thereby enabling the creation of minutes and provision of related information in real time during a meeting according to the user's emotions.

[0302] A "user" is an individual or group who enters information onto the whiteboard during a meeting.

[0303] "Terminal means" refers to devices that collect information entered by users and transmit it to a server, including cameras, microphones, smart whiteboards, etc.

[0304] "Server" refers to the central processing unit that processes and analyzes collected information and collects and displays related information.

[0305] "Means for converting to text" refers to technology for converting received handwritten data or voice data into text data.

[0306] "Database" refers to a source of information for storing and managing related information, including internal project data and documents.

[0307] "External information sources" refers to information providers or information systems that include external market trend reports, competitive information, etc.

[0308] "Emotion engine" refers to technology for recognizing and analyzing user emotions from audio and video data.

[0309] "Emotion data" refers to data relating to a user's emotions generated by the emotion engine.

[0310] "Means for changing priorities and feedback" refers to a technique or method for setting the importance of information based on emotional data and adjusting the order and content of information provided to the user.

[0311] "Visual display means" refers to techniques and methods for presenting analyzed information to users in the form of graphs, charts, text, etc.

[0312] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision based on the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by a server. The hardware used includes a camera, microphone, and smart whiteboard, while the software includes optical character recognition (OCR) technology, voice recognition technology, and an emotion engine. Specifically, the system operates as follows:

[0313] First, a user starts a meeting and writes something on a whiteboard, such as "the release date of a new product." The device captures what is handwritten on the whiteboard with a camera and captures the audio of the conversation with a microphone. This captured data is sent to a server in real time. The server converts the received handwritten data into text data using optical character recognition (OCR) technology, and converts the audio data into text data using speech recognition technology. For example, Google Cloud Vision API or Google Cloud Speech-to-Text may be used.

[0314] Next, the server's emotion engine analyzes the audio and video data to recognize the user's emotions. The emotion engine uses, for example, the Microsoft Azure® Emotion API. As a result of the analysis, emotional data is generated, indicating whether the user is excited, calm, anxious, or other such emotions. The server then collects and analyzes related information based on this emotional data and text data. Specifically, the server collects past project data, documents, external market trend reports, and other information from internal databases and external sources. This allows the server to prioritize information and change feedback based on the user's emotions.

[0315] For example, if a user is feeling anxious, the server will prioritize displaying supplementary information such as "past success stories" and "risk management plans." The collected information is analyzed and compiled in the form of text, graphs, charts, and other information, and displayed on the whiteboard in real time. This allows users to instantly check the information they need even during a meeting, making it possible to conduct the meeting efficiently and effectively.

[0316] Specific examples

[0317] Example 1: User excitement

[0318] A user excitedly says, "This release is super important!"

[0319] The device captures this speech with a microphone and sends it to the server.

[0320] The server recognizes the user's excitement state using voice recognition and an emotion engine.

[0321] The server automatically collects a list of planned release dates and competitive information and displays them on a whiteboard.

[0322] Example 2: User Concerns

[0323] The user expresses concern by saying, "I'm not sure about the release date."

[0324] The device captures this speech with a microphone and sends it to the server.

[0325] The server uses voice recognition and an emotion engine to recognize the anxiety state of the user.

[0326] The server prioritizes collecting supplementary information such as "past success stories" and "risk management plans" and displays it on the whiteboard.

[0327] Prompt Sentence Examples

[0328] Here is an example prompt:

[0329] If a user is excitedly talking in a release meeting:

[0330] "During a meeting, a user excitedly says, 'This release is so important.' Record the conversation and explain how the system will recognize the user's emotion and display relevant release dates and competitive information."

[0331] This not only automatically collects and analyzes necessary information during a meeting, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[0332] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0333] Step 1:

[0334] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[0335] Input: The user enters information by hand on the whiteboard.

[0336] Specific behavior: A user uses a smart whiteboard and writes "New product release date" with a pen.

[0337] Step 2:

[0338] The device uses a camera to capture what is handwritten on the whiteboard.

[0339] Input: Handwritten text on a whiteboard.

[0340] Specific operation: The device's camera captures the handwriting on the whiteboard as an image.

[0341] Step 3:

[0342] The device captures the audio of the conversation using a microphone.

[0343] Input: What people say during the meeting.

[0344] What it does: The microphone captures the audio of the conversation as audio data.

[0345] Step 4:

[0346] The terminal transmits the captured image data and audio data to the server.

[0347] Input: Captured image and audio data.

[0348] Output: Image and audio data sent to the server.

[0349] Specific operation: The terminal sends image data and audio data to the server via the network.

[0350] Step 5:

[0351] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0352] Input: Handwritten data (image data) on a whiteboard.

[0353] Output: Text data converted by optical character recognition (OCR).

[0354] Specific operation: The server's OCR software analyzes the handwritten data and converts it into text data called "New product release date."

[0355] Step 6:

[0356] The server converts the voice data into text data using voice recognition technology.

[0357] Input: Audio data.

[0358] Output: Text data converted by speech recognition.

[0359] Specific operation: The server's voice recognition software analyzes the voice data and converts what the user says into text data.

[0360] Step 7:

[0361] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[0362] Input: Audio and video data.

[0363] Output: User emotion data.

[0364] Specific operation: The emotion engine analyzes voice tone and facial expressions and generates data representing the user's emotional state (excitement, anxiety, etc.).

[0365] Step 8:

[0366] The server collects relevant information from databases and external information sources based on the text data and emotion data.

[0367] Input: Text data and emotion data.

[0368] Output: Relevant information (historical project data, external market trend reports, etc.).

[0369] Specific operation: The server searches and collects relevant information using internal databases and external APIs.

[0370] Step 9:

[0371] The server analyzes the collected information and prioritizes it based on emotional data.

[0372] Input: Collected relevant information and sentiment data.

[0373] Output: Prioritized information.

[0374] Specific operation: The server takes into account the emotional data and, for example, prioritizes detailed risk management plans when the user is in an anxious state.

[0375] Step 10:

[0376] The server uses a means for visually displaying the analyzed information to display it on a whiteboard.

[0377] Input: Prioritized information.

[0378] Output: Visually displayed information (text, graphs, charts, etc.).

[0379] Specific operation: The server organizes the information and displays it on the whiteboard in real time, so that the user can check it.

[0380] (Application example 2)

[0381] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0382] Conventional automatic meeting memo generation systems lack the ability to generate minutes in real time, as well as the ability to provide flexible information based on the user's emotions. Furthermore, when robot operators hold work instructions or troubleshooting meetings in factories, it is difficult to immediately obtain relevant information based on the meeting content, and information appropriate to the user's emotions is not provided. This hinders rapid problem-solving and efficient meeting management.

[0383] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion from audio data and video data and adjusting the priority of information and feedback based on the emotion, means for analyzing and visually displaying the collected information, and means for collecting related information from an internal database and external information sources. This makes it possible to not only generate minutes of a meeting but also provide appropriate information according to the user's emotion.

[0384] A "user" is an individual or group who uses the system to provide information during a meeting via a whiteboard or voice input.

[0385] "Means for collecting information in real time" refers to technology and devices that instantly detect information or statements entered by users on the whiteboard and collect them as data.

[0386] "Terminal means" refers to devices or equipment that have the function of transmitting collected information to a server. Specifically, it includes cameras, microphones, network communication modules, etc.

[0387] "Server" means a computer system that processes and analyzes the information it receives and provides relevant information to the user.

[0388] "Means of converting to text" refers to the technology of converting voice data or handwritten data into character data using OCR and voice recognition technology.

[0389] "Means for collecting related information" refers to technology that searches for and acquires related data from internal databases and external information sources based on the textual content of meetings.

[0390] "Means for visually displaying" refers to a display device or interface for visually presenting the analysis results and related information to a user.

[0391] "Means for recognizing a user's emotions from audio and video data" refers to technology that determines a user's emotional state through voice tone and facial expression analysis.

[0392] "Means for adjusting information priority and feedback" refers to technology that dynamically changes the order and content of information provided depending on the recognized emotional state of the user.

[0393] System configuration

[0394] This invention is a system that collects and analyzes information in real time, provided by users during a meeting via a whiteboard or voice input. The main components of the system include:

[0395] 1. Terminal: Consists of devices such as a camera, microphone, and smart glasses, which collects information entered by the user in real time and sends it to the server.

[0396] 2. Server: Processes and analyzes the collected information, collects relevant information, and provides it to the user. It also recognizes the user's emotions from audio and video data, and adjusts the priority of information and feedback based on those emotions.

[0397] 3. Emotion engine: Analyzes voice tone and facial expressions to recognize the user's emotions.

[0398] 4. Visual display devices: Using display devices such as smart glasses, collected and analyzed information is presented to users in real time.

[0399] Program processing

[0400] Hardware and software used

[0401] Smart glasses: worn by the user and act as a display and audio interface.

[0402] Camera and microphone: Built into the smart glasses to capture audio and video.

[0403] Server: A computer system that processes data and performs sentiment analysis.

[0404] OCR technology: Optical character recognition technology is used to convert handwritten characters on a whiteboard into text data (a specific example is the Google Cloud Vision API).

[0405] Speech recognition engine: Technology that converts voice data into text data (a specific example is the Google Cloud Speech-to-Text API).

[0406] Emotion engine: Technology that recognizes emotions by analyzing voice tone and facial expressions (a specific example is the Microsoft Azure Emotion API).

[0407] Processing Details

[0408] 1. Data Collection:

[0409] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time.

[0410] The collected data is immediately sent to the server.

[0411] 2. Data Processing:

[0412] The server converts the received voice data into text using a voice recognition engine.

[0413] The received video data is converted into text data using OCR technology, with handwritten characters converted into text data.

[0414] Based on the converted text data, relevant information is collected from internal databases and external sources.

[0415] 3. Emotion recognition:

[0416] The server's emotion engine analyzes voice tone and facial expressions to recognize the user's emotions.

[0417] Adjust the priority and content of the information displayed based on the perceived emotion.

[0418] 4. Information provision:

[0419] -The analyzed information and related information are displayed in real time on a visual display device (smart glasses).

[0420] -Users can access the information they need hands-free.

[0421] Specific examples

[0422] Example 1: Operator excitement

[0423] If an operator excitedly says, "This machine's new function is revolutionary!", the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's excitement, and depending on the operator's excitement, collects and displays related information such as "detailed information on the new function" and "implementation procedures."

[0424] Example 2: Operator anxiety

[0425] If an operator says in an anxious tone, "I don't know how to solve this problem," the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's state of anxiety, and prioritizes the collection and display of "past troubleshooting cases" and "expert advice."

[0426] Example prompts for generative AI models

[0427] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[0428] Generate content: Generate text taking into account the following:

[0429] New feature details

[0430] Step-by-step implementation guide

[0431] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0432] Step 1: The device collects audio and video data in real time.

[0433] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time. The input is audio and video data, which are used directly in the next processing step, so no data processing is performed. The output is the captured raw audio and video data.

[0434] Step 2: The device sends the collected data to the server

[0435] The audio and video data captured by the device is sent to the server via the network. The input is the raw audio and video data, and the data is sent. The output is the audio and video data that has arrived at the server.

[0436] Step 3: The server converts the audio data into text data

[0437] The server converts the received voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text API). The input is voice data, and the data is processed using voice recognition technology to output text data.

[0438] Step 4: The server extracts handwritten characters from the video data and converts them into text data.

[0439] The server extracts handwritten characters from the video data received by the server using OCR technology (for example, Google Cloud Vision API) and converts them into text data. The input is video data, and the output is text data after processing using OCR technology.

[0440] Step 5: The server collects relevant information based on the text data.

[0441] The server searches and collects related information from internal databases and external information sources based on the generated text data. The input is text data, and the collected related information is output by processing the data through database searches and API requests.

[0442] Step 6: The server analyzes voice tone and facial expressions to recognize emotions

[0443] The server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the audio and video data and recognize the user's emotions. The input is audio and video data, and emotion analysis technology processes the data to obtain emotional data as output.

[0444] Step 7: The server adjusts the priority of information based on the emotion data.

[0445] The server adjusts the priority and display content of collected related information based on the recognized emotion data. The input is emotion data and related information, and by processing and filtering the data, it obtains output information appropriate to the emotion.

[0446] Step 8: The server sends the information in real time to a visual display device

[0447] The server transmits the adjusted information to the visual display device (smart glasses) in real time. The input is the adjusted information, and by transmitting the data, the display information that the user can visually confirm is obtained as the output.

[0448] Example prompts for generative AI models

[0449] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[0450] Generate content: Generate text taking into account the following:

[0451] New feature details

[0452] Step-by-step implementation guide

[0453] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0454] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0455] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0456] [Second embodiment]

[0457] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0458] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0459] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0460] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0461] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0462] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0463] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0464] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0465] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0466] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0467] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0468] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0469] This invention is a system that generates minutes in real time during a meeting and automatically adds related information. This system is realized by collecting information entered by users on the terminal, and processing and analyzing it on the server.

[0470] System configuration

[0471] The system consists of the following main components:

[0472] User: An individual or group who enters information on the whiteboard during a meeting.

[0473] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[0474] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user.

[0475] Program processing

[0476] 1. User Actions

[0477] A user starts a meeting and handwrites "New Product Release Date" on the whiteboard.

[0478] 2. Data Collection

[0479] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[0480] The captured data is sent to a server in real time.

[0481] 3. Data Processing

[0482] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0483] At the same time, the voice data is converted into text data using voice recognition technology.

[0484] Text data of the "new product release date" is generated.

[0485] 4. Collection of relevant information

[0486] Based on the text data, the server automatically collects past project data related to the "new product release date," documents from internal databases, external market trend reports, and so on.

[0487] 5. Data Analysis and Presentation

[0488] The server analyzes the collected information and compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[0489] The compiled information is displayed on a whiteboard in real time for the user to review.

[0490] Specific examples

[0491] Example 1: Starting a meeting and generating minutes

[0492] A user writes on a whiteboard, "Decide the budget for the next project."

[0493] The device captures handwritten text with its camera and records audio with its microphone.

[0494] The server uses OCR technology to convert handwritten characters into text data, and at the same time uses voice recognition technology to convert voice data into text.

[0495] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database.

[0496] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[0497] Example 2: Dynamic information addition during a meeting

[0498] A user says in a statement, "I want to find out about market trends this year."

[0499] The device captures the audio and sends it to the server.

[0500] The server recognizes the voice and converts it into text, then automatically searches for market trend reports based on that text.

[0501] Market trend graphs and report summaries are displayed on the whiteboard, allowing users to review them as they conduct the meeting.

[0502] This system automatically collects and analyzes necessary information during meetings, allowing users to efficiently conduct meetings and obtain relevant information in real time, greatly simplifying the creation of minutes and improving the quality of meetings.

[0503] The processing flow will be explained below.

[0504] Step 1:

[0505] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[0506] Step 2:

[0507] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[0508] Step 3:

[0509] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[0510] Step 4:

[0511] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[0512] Step 5:

[0513] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[0514] Step 6:

[0515] The server analyzes the transcripts of the meeting minutes and automatically collects relevant information from internal databases and external sources. In this case, it retrieves past release data and market trend reports related to the "new product release date."

[0516] Step 7:

[0517] The server analyzes the collected related information and organizes the necessary information into an appropriate format, for example, generating graphs of past release schedules or market trends.

[0518] Step 8:

[0519] The server sends the organized information to the device in real time, where it is displayed visually on the whiteboard.

[0520] Step 9:

[0521] Users can check the supplementary information displayed on the whiteboard and proceed with the meeting, adding new topics or expressing opinions as necessary.

[0522] Step 10:

[0523] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the agenda, what was said, and any related information collected during the meeting.

[0524] Step 11:

[0525] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[0526] Example 1

[0527] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] In modern meetings, a large amount of information is exchanged in real time, making it difficult to create minutes and search for information during the meeting. Furthermore, there is a lack of systems that can efficiently manage various information formats, including handwritten and audio recordings, and support the progress of meetings. This leads to issues such as reduced meeting productivity and a loss of accuracy in meeting minutes.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0530] In this invention, the server includes means for collecting information input by users to a display device during a meeting in real time, terminal means for transmitting the collected information to a computer, means for converting the information received by the computer into text, means for collecting related information from an internal database or external information source based on the converted text, and means for analyzing and visually displaying the collected related information. This makes it possible to instantly obtain related information during a meeting and reflect it in the minutes, significantly improving the productivity of the meeting and the accuracy of the minutes.

[0531] A "user" is an individual or group that enters information during a conference.

[0532] A "display device" is a device that allows a user to input information, and includes, for example, a whiteboard or digital screen.

[0533] "Means for collecting information in real time" refers to technologies and devices that instantly acquire information entered during a meeting and use it for subsequent processing.

[0534] "Terminal means for transmitting to a computer" refers to a device or network infrastructure for transmitting collected information to a server.

[0535] A "computer" is an electronic device that processes received information and performs various data conversions and analyses.

[0536] "Means of converting text" refers to technologies that convert handwritten or voice data into character data, including optical character recognition (OCR) and voice recognition.

[0537] An "internal database" is a database that stores various data within a company.

[0538] "External sources" are sources of information provided on the Internet or by external organizations.

[0539] "Means of collecting relevant information" refers to the techniques and processes used to obtain the necessary data from internal databases and external sources based on the textual information.

[0540] "Visual display means" refers to techniques and devices that present the collected and analyzed information to the user in the form of charts, graphs, text, etc.

[0541] This system collects and analyzes information input to a display device during a meeting in real time, and automatically acquires and displays related information. The system is mainly composed of three elements: users, terminals, and a server.

[0542] User

[0543] During a meeting, users input information into the display device, for example, by writing documents by hand on a whiteboard or digital screen, or by making speeches.

[0544] Terminal

[0545] The terminal is a device for collecting information entered by the user, and includes a camera and a microphone. For example, handwritten information entered on a whiteboard is captured by the camera, and audio of conversations is recorded by the microphone. Specific devices used include Logitech webcams and Shure conference microphones. The collected data is sent from the terminal to a server in real time.

[0546] server

[0547] The server receives the data sent from the device and performs the following operations:

[0548] 1. Convert data to text

[0549] The server converts the received data into character data. At this time, handwritten data is converted into text data using optical character recognition (OCR) technology. The specific software used is Google Cloud Vision API. At the same time, audio data is converted into text data using voice recognition technology. Google Cloud Speech-to-Text is used for this process.

[0550] 2. Collection of relevant information

[0551] Based on the textual information, the server automatically collects related information, such as past project data, internal databases (Microsoft SharePoint), and external market trend reports (Gartner). This allows users to quickly gather the information they need.

[0552] 3. Data Analysis and Presentation

[0553] The server analyzes the collected information and compiles it into an appropriate format (for example, using Excel or Tableau). The compiled information is then displayed in real time on a display device so that the user can view it.

[0554] Specific examples

[0555] Example 1: Starting a meeting and generating minutes

[0556] A user writes on a whiteboard, "Decide the budget for the next project."

[0557] The device captures the handwriting with its camera and records the audio with its microphone.

[0558] The server uses OCR technology (Google Cloud Vision API) to convert handwritten characters into text data, and converts the audio data into text using speech recognition technology (Google Cloud Speech-to-Text).

[0559] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database (Microsoft SharePoint).

[0560] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[0561] Example 2: Dynamic information addition during a meeting

[0562] A user says in a statement, "I want to find out about market trends this year."

[0563] The device captures the audio and sends it to the server.

[0564] The server recognizes the speech and converts it into text, then automatically searches for market trend reports (Gartner reports) based on that text.

[0565] Market trend graphs and report summaries are displayed on the whiteboard, and users can review them as they conduct the meeting.

[0566] Prompt Sentence Examples

[0567] "Please explain in detail the processing procedures of a system that captures written content and audio in real time during a meeting and automatically collects and displays information related to that content. Also, please name the specific hardware and software, and describe the data processing and calculation methods."

[0568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0569] Step 1:

[0570] The user inputs information into the display device.

[0571] Input: A user handwrites "New product release date" on the display device.

[0572] Output: Written and spoken text is recorded on the display device.

[0573] Specific operation: The user writes characters by hand on the whiteboard and speaks at the same time.

[0574] Step 2:

[0575] The device captures your handwriting and voice.

[0576] Input: Written text on the display and spoken words by the user.

[0577] Output: Captured image and audio data.

[0578] What it does: The camera captures what you write, and the microphone records what you say.

[0579] Step 3:

[0580] The device sends the captured data to the server.

[0581] Input: Image and audio data.

[0582] Output: Image and audio data sent to the server.

[0583] Specific operation: The terminal's communication module sends the collected data to a server via the Internet.

[0584] Step 4:

[0585] The server converts the image data and audio data into text data.

[0586] Input: Image and audio data sent to the server.

[0587] Output: The converted text data.

[0588] Specific operation: The server's OCR engine extracts characters from image data, and the speech recognition engine generates text from speech.

[0589] Step 5:

[0590] The server collects related information based on the text data.

[0591] Input: The converted text data.

[0592] Output: Relevant information collected (historical project data, external reports, etc.).

[0593] What happens: The server queries internal databases and external sources to retrieve the required data.

[0594] Step 6:

[0595] The server analyzes the collected information and displays it visually.

[0596] Input: The relevant information you have collected.

[0597] Output: A visual format (text, graphs, charts, etc.) containing the results of the analysis.

[0598] Specific operation: The server analyzes the data, visually summarizes the information using Excel or Tableau, and sends it to the display device.

[0599] Step 7:

[0600] The user proceeds with the conference while checking the presented information.

[0601] Input: Visual information displayed on a display device.

[0602] Output: Review meeting progress and minutes.

[0603] Specific operation: The user refers to the information displayed on the display device and decides on the next agenda item or action item.

[0604] (Application example 1)

[0605] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0606] Conventional conference systems and factory robots lacked systems that could collect information in real time and automatically present relevant information. This made it difficult to quickly and effectively obtain necessary information during meetings or factory work, leading to calls for improvements in work efficiency and quality. Furthermore, there was a lack of technology that could convert handwritten text and voice into text in real time and automatically collect and analyze relevant information based on that information, making it difficult for users to use information efficiently. This created the risk of delays in meeting and work progress and decisions being made based on incorrect information.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0608] In this invention, the server includes a means for collecting information entered by users during meetings or work in real time, a terminal means for transmitting the collected information to the server, and a means for converting the information received by the server into text. This makes it possible to collect related information from databases and external information sources based on the converted text, analyze the collected related information, and visually display it, and to present the related information in real time to devices used in the factory. This allows factory work and meetings to proceed quickly and effectively, improving work efficiency and quality.

[0609] "User" refers to an individual or group that uses the system to hold meetings or carry out factory work.

[0610] "Real-time" refers to information being processed and displayed almost in sync with the moment it is generated.

[0611] "Terminal means" refers to a device, such as a camera, microphone, smart glasses, or head-mounted display, that collects information entered by a user and transmits it to a server.

[0612] "Server" refers to a computing system for processing received data, performing necessary analysis, and providing relevant information.

[0613] "Text conversion" refers to the conversion of non-text information, such as handwritten characters or audio data, into machine-readable text data.

[0614] "Database" refers to an information system that stores related information in a structured manner so that it can be efficiently searched and accessed at a later time.

[0615] "External sources" refers to information sources other than internal databases, such as external databases, network resources, and online reports.

[0616] "Analysis" refers to the act of processing collected data using statistical and logical methods to extract meaningful information and insights.

[0617] "Visually" refers to presenting information in the form of text, graphs, charts, images, etc., so that it can be easily understood by the user.

[0618] "Devices used within the factory" refers to devices used by factory workers to receive and display information, such as smart glasses, tablets, and head-mounted displays.

[0619] "Related information" refers to additional data or materials related to the information or statements entered by the user that are useful for work or decision-making.

[0620] This invention is a system that presents relevant information in real time to devices primarily used in factories, and is composed of the following components:

[0621] System configuration

[0622] 1. User:

[0623] Factory workers use devices such as smart glasses and tablet computers to perform their work.

[0624] 2. Terminal means:

[0625] These include smart glasses, tablet devices, head-mounted displays, etc., which capture information such as voice and handwritten characters and send it to a server.

[0626] 3. Server:

[0627] Its main functions are:

[0628] The received voice data is converted into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0629] Optical character recognition technology (e.g., OCR) is used to convert handwritten characters into text.

[0630] Based on the textual data, relevant information is collected from databases and external sources.

[0631] The collected information is analyzed and displayed on the device in real time.

[0632] Operation flow

[0633] Data collection:

[0634] Take the example of a user saying, "Please display the work instructions for the next process." The microphone in the smart glasses captures the voice and sends it to the server.

[0635] Data Processing:

[0636] The server converts the voice data into text data using the Google Speech-to-Text API, and then collects and analyzes information related to work instructions for the next process from an internal database.

[0637] Information presentation:

[0638] Relevant information collected from databases and external information sources is displayed in real time on the display of smart glasses or tablet devices, allowing users to work while checking the displayed information.

[0639] Specific examples

[0640] Consider a factory worker saying, "Tell me how to assemble this part." The smart glasses capture the voice and the server converts it into text data. The server then retrieves the relevant assembly procedure data from the database and visually displays it on the smart glasses' display. In this way, users can obtain the information they need in real time while working, allowing them to perform their tasks efficiently and accurately.

[0641] Prompt Sentence Examples

[0642] Factory worker: "Show me the work instructions for the next process."

[0643] Server (prompt for input to generative AI model): "Search for the next process step. Display relevant information from the factory database."

[0644] It is expected that such a system will improve the efficiency of work within the factory and the quality of work.

[0645] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0646] Step 1:

[0647] The user speaks into the smart glasses, saying, "Show me the work instructions for the next step." The input is voice data, which is captured by the smart glasses' microphone. The output is the captured voice data.

[0648] Step 2:

[0649] The smart glasses of the terminal means transmit the captured voice data to the server. The input is the captured voice data, and the output is the data transmission to the server.

[0650] Step 3:

[0651] The voice data received by the server is converted into text data using the Google Speech-to-Text API. The input is the voice data received by the server, and the output is text data. Specifically, the server sends the voice data to the API and receives text data as the conversion result.

[0652] Step 4:

[0653] The server searches an internal database for information related to the work instructions for the next process based on the text data. The input is the converted text data ("Show me the work instructions for the next process"), and the output is the related work instruction data. Specifically, the server generates a query and searches the database.

[0654] Step 5:

[0655] The server analyzes the work instruction data retrieved from the database and converts it into a format for visual display. The input is raw data retrieved from the database, and the output is formatted data that can be displayed visually (e.g., text, graphs, charts). Specifically, the server performs formatting processing on the data and converts it into a format that is easy for users to understand.

[0656] Step 6:

[0657] The server transmits formatted work instruction data to the smart glasses as the terminal means. The input is the formatted data formatted by the server, and the output is the data displayed on the smart glasses.

[0658] Step 7:

[0659] The smart glasses display the received work instruction data in the user's field of view. The input is formatted data received from the server, and the output is visual information displayed on the smart glasses' display. Specifically, the smart glasses render the received data on their display.

[0660] Through these processing steps, users can obtain the information they need in real time while working, allowing them to work efficiently and accurately.

[0661] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0662] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision according to the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by the server.

[0663] System configuration

[0664] The system consists of the following main components:

[0665] User: An individual or group who enters information on the whiteboard during a meeting.

[0666] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[0667] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user. It also uses an emotion engine to recognize and analyze the user's emotions.

[0668] Emotion engine: Recognizes the user's emotions from audio and video data, and changes the priority of information and feedback based on those emotions.

[0669] Program processing

[0670] 1. User Actions

[0671] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[0672] 2. Data Collection

[0673] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[0674] The captured data is sent to a server in real time.

[0675] 3. Data Processing

[0676] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0677] At the same time, the voice data is converted into text data using voice recognition technology.

[0678] Text data of the "new product release date" is generated.

[0679] 4. Emotion recognition

[0680] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[0681] The emotion engine generates emotion data indicating whether the user is excited, calm, anxious, etc.

[0682] 5. Collection of relevant information

[0683] The server automatically collects past project data, documents from internal databases, external market trend reports, etc. related to the "new product release date" based on text data and sentiment data.

[0684] 6. Data Analysis and Presentation

[0685] The server analyzes and prioritizes the collected information based on emotional data, and then compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[0686] If the user is feeling anxious, more detailed information and supplementary materials will be displayed preferentially.

[0687] 7. Real-time feedback

[0688] The compiled information is displayed on a whiteboard in real time, allowing users to check information that corresponds to their emotions.

[0689] Specific examples

[0690] Example 1: User excitement

[0691] "This is a very important release," an excited user said.

[0692] The device captures the audio and sends it to the server.

[0693] The server uses voice recognition and an emotion engine to recognize the user's state of excitement.

[0694] The server collects and displays a list of planned release dates and competitive information.

[0695] Example 2: User Concerns

[0696] The user stated in an anxious tone that he was "unsure of the release date."

[0697] The device captures the audio and sends it to the server.

[0698] The server uses voice recognition and an emotion engine to recognize the user's anxiety state.

[0699] The server prioritizes the collection and display of supplementary information such as "past success stories" and "risk management plans."

[0700] This system not only automatically collects and analyzes necessary information during meetings, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[0701] The processing flow will be explained below.

[0702] Step 1:

[0703] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[0704] Step 2:

[0705] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[0706] Step 3:

[0707] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[0708] Step 4:

[0709] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[0710] Step 5:

[0711] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[0712] Step 6:

[0713] The server's emotion engine analyzes audio and video data to recognize the user's emotions and generates emotion data such as "excited," "anxious," or "calm."

[0714] Step 7:

[0715] The server analyzes the textual minutes and sentiment data, and automatically collects relevant information from internal databases and external sources, such as past project data and market trend reports related to "new product release dates."

[0716] Step 8:

[0717] The server analyzes the collected relevant information and prioritizes it based on emotional data: for example, if the user is excited, it will promptly present a release candidate date, but if the user is anxious, it will prioritize detailed risk management information.

[0718] Step 9:

[0719] The server sends the organized information to the terminal in real time and displays it visually on the whiteboard. Users can proceed with the meeting while checking the displayed supplementary information.

[0720] Step 10:

[0721] If a user adds a new comment or topic during the meeting, the device will again capture voice and handwritten data and send it to the server, which will then analyze the data again and collect and display the relevant information.

[0722] Step 11:

[0723] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the meeting topics, comments, emotional data, and other relevant information collected during the meeting.

[0724] Step 12:

[0725] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[0726] Example 2

[0727] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0728] Creating effective minutes during meetings is an important challenge for many companies and organizations. However, traditional methods for creating minutes have made it difficult to collect information in real time and provide relevant information promptly. It has also been difficult to accurately grasp users' emotions during the meeting and provide information appropriate to those emotions. As a result, the efficiency and effectiveness of meetings are often compromised.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0730] In this invention, the server includes means for recognizing user emotions from audio data and video data, means for changing information priority and feedback based on the emotion data, and means for analyzing and visually displaying collected related information, thereby enabling the creation of minutes and provision of related information in real time during a meeting according to the user's emotions.

[0731] A "user" is an individual or group who enters information onto the whiteboard during a meeting.

[0732] "Terminal means" refers to devices that collect information entered by users and transmit it to a server, including cameras, microphones, smart whiteboards, etc.

[0733] "Server" refers to the central processing unit that processes and analyzes collected information and collects and displays related information.

[0734] "Means for converting to text" refers to technology for converting received handwritten data or voice data into text data.

[0735] "Database" refers to a source of information for storing and managing related information, including internal project data and documents.

[0736] "External information sources" refers to information providers or information systems that include external market trend reports, competitive information, etc.

[0737] "Emotion engine" refers to technology for recognizing and analyzing user emotions from audio and video data.

[0738] "Emotion data" refers to data relating to a user's emotions generated by the emotion engine.

[0739] "Means for changing priorities and feedback" refers to a technique or method for setting the importance of information based on emotional data and adjusting the order and content of information provided to the user.

[0740] "Visual display means" refers to techniques and methods for presenting analyzed information to users in the form of graphs, charts, text, etc.

[0741] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision based on the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by a server. The hardware used includes a camera, microphone, and smart whiteboard, while the software includes optical character recognition (OCR) technology, voice recognition technology, and an emotion engine. Specifically, the system operates as follows:

[0742] First, a user starts a meeting and writes something on a whiteboard, such as "the release date of a new product." The device captures what is handwritten on the whiteboard with a camera and captures the audio of the conversation with a microphone. This captured data is sent to a server in real time. The server converts the received handwritten data into text data using optical character recognition (OCR) technology, and converts the audio data into text data using speech recognition technology. For example, Google Cloud Vision API or Google Cloud Speech-to-Text may be used.

[0743] Next, the server's emotion engine analyzes the audio and video data to recognize the user's emotions. The emotion engine uses, for example, the Microsoft Azure Emotion API. As a result of the analysis, emotional data is generated, indicating whether the user is excited, calm, or anxious. The server then collects and analyzes related information based on this emotional data and text data. Specifically, the server collects past project data, documents, external market trend reports, and other information from internal databases and external sources. This allows the server to prioritize information and change feedback based on the user's emotions.

[0744] For example, if a user is feeling anxious, the server will prioritize displaying supplementary information such as "past success stories" and "risk management plans." The collected information is analyzed and compiled in the form of text, graphs, charts, and other information, and displayed on the whiteboard in real time. This allows users to instantly check the information they need even during a meeting, making it possible to conduct the meeting efficiently and effectively.

[0745] Specific examples

[0746] Example 1: User excitement

[0747] A user excitedly says, "This release is super important!"

[0748] The device captures this speech with a microphone and sends it to the server.

[0749] The server recognizes the user's excitement state using voice recognition and an emotion engine.

[0750] The server automatically collects a list of planned release dates and competitive information and displays them on a whiteboard.

[0751] Example 2: User Concerns

[0752] The user expresses concern by saying, "I'm not sure about the release date."

[0753] The device captures this speech with a microphone and sends it to the server.

[0754] The server uses voice recognition and an emotion engine to recognize the anxiety state of the user.

[0755] The server prioritizes collecting supplementary information such as "past success stories" and "risk management plans" and displays it on the whiteboard.

[0756] Prompt Sentence Examples

[0757] Here is an example prompt:

[0758] If a user is excitedly talking in a release meeting:

[0759] "During a meeting, a user excitedly says, 'This release is so important.' Record the conversation and explain how the system will recognize the user's emotion and display relevant release dates and competitive information."

[0760] This not only automatically collects and analyzes necessary information during a meeting, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[0761] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0762] Step 1:

[0763] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[0764] Input: The user enters information by hand on the whiteboard.

[0765] Specific behavior: A user uses a smart whiteboard and writes "New product release date" with a pen.

[0766] Step 2:

[0767] The device uses a camera to capture what is handwritten on the whiteboard.

[0768] Input: Handwritten text on a whiteboard.

[0769] Specific operation: The device's camera captures the handwriting on the whiteboard as an image.

[0770] Step 3:

[0771] The device captures the audio of the conversation using a microphone.

[0772] Input: What people say during the meeting.

[0773] What it does: The microphone captures the audio of the conversation as audio data.

[0774] Step 4:

[0775] The terminal transmits the captured image data and audio data to the server.

[0776] Input: Captured image and audio data.

[0777] Output: Image and audio data sent to the server.

[0778] Specific operation: The terminal sends image data and audio data to the server via the network.

[0779] Step 5:

[0780] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0781] Input: Handwritten data (image data) on a whiteboard.

[0782] Output: Text data converted by optical character recognition (OCR).

[0783] Specific operation: The server's OCR software analyzes the handwritten data and converts it into text data called "New product release date."

[0784] Step 6:

[0785] The server converts the voice data into text data using voice recognition technology.

[0786] Input: Audio data.

[0787] Output: Text data converted by speech recognition.

[0788] Specific operation: The server's voice recognition software analyzes the voice data and converts what the user says into text data.

[0789] Step 7:

[0790] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[0791] Input: Audio and video data.

[0792] Output: User emotion data.

[0793] Specific operation: The emotion engine analyzes voice tone and facial expressions and generates data representing the user's emotional state (excitement, anxiety, etc.).

[0794] Step 8:

[0795] The server collects relevant information from databases and external information sources based on the text data and emotion data.

[0796] Input: Text data and emotion data.

[0797] Output: Relevant information (historical project data, external market trend reports, etc.).

[0798] Specific operation: The server searches and collects relevant information using internal databases and external APIs.

[0799] Step 9:

[0800] The server analyzes the collected information and prioritizes it based on emotional data.

[0801] Input: Collected relevant information and sentiment data.

[0802] Output: Prioritized information.

[0803] Specific operation: The server takes into account the emotional data and, for example, prioritizes detailed risk management plans when the user is in an anxious state.

[0804] Step 10:

[0805] The server uses a means for visually displaying the analyzed information to display it on a whiteboard.

[0806] Input: Prioritized information.

[0807] Output: Visually displayed information (text, graphs, charts, etc.).

[0808] Specific operation: The server organizes the information and displays it on the whiteboard in real time, so that the user can check it.

[0809] (Application example 2)

[0810] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0811] Conventional automatic meeting memo generation systems lack the ability to generate minutes in real time, as well as the ability to provide flexible information based on the user's emotions. Furthermore, when robot operators hold work instructions or troubleshooting meetings in factories, it is difficult to immediately obtain relevant information based on the meeting content, and information appropriate to the user's emotions is not provided. This hinders rapid problem-solving and efficient meeting management.

[0812] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion from audio data and video data and adjusting the priority of information and feedback based on the emotion, means for analyzing and visually displaying the collected information, and means for collecting related information from an internal database and external information sources. This makes it possible to not only generate minutes of a meeting but also provide appropriate information according to the user's emotion.

[0813] A "user" is an individual or group who uses the system to provide information during a meeting via a whiteboard or voice input.

[0814] "Means for collecting information in real time" refers to technology and devices that instantly detect information or statements entered by users on the whiteboard and collect them as data.

[0815] "Terminal means" refers to devices or equipment that have the function of transmitting collected information to a server. Specifically, it includes cameras, microphones, network communication modules, etc.

[0816] "Server" means a computer system that processes and analyzes the information it receives and provides relevant information to the user.

[0817] "Means of converting to text" refers to the technology of converting voice data or handwritten data into character data using OCR and voice recognition technology.

[0818] "Means for collecting related information" refers to technology that searches for and acquires related data from internal databases and external information sources based on the textual content of meetings.

[0819] "Means for visually displaying" refers to a display device or interface for visually presenting the analysis results and related information to a user.

[0820] "Means for recognizing a user's emotions from audio and video data" refers to technology that determines a user's emotional state through voice tone and facial expression analysis.

[0821] "Means for adjusting information priority and feedback" refers to technology that dynamically changes the order and content of information provided depending on the recognized emotional state of the user.

[0822] System configuration

[0823] This invention is a system that collects and analyzes information in real time, provided by users during a meeting via a whiteboard or voice input. The main components of the system include:

[0824] 1. Terminal: Consists of devices such as a camera, microphone, and smart glasses, which collects information entered by the user in real time and sends it to the server.

[0825] 2. Server: Processes and analyzes the collected information, collects relevant information, and provides it to the user. It also recognizes the user's emotions from audio and video data, and adjusts the priority of information and feedback based on those emotions.

[0826] 3. Emotion engine: Analyzes voice tone and facial expressions to recognize the user's emotions.

[0827] 4. Visual display devices: Using display devices such as smart glasses, collected and analyzed information is presented to users in real time.

[0828] Program processing

[0829] Hardware and software used

[0830] Smart glasses: worn by the user and act as a display and audio interface.

[0831] Camera and microphone: Built into the smart glasses to capture audio and video.

[0832] Server: A computer system that processes data and performs sentiment analysis.

[0833] OCR technology: Optical character recognition technology is used to convert handwritten characters on a whiteboard into text data (a specific example is the Google Cloud Vision API).

[0834] Speech recognition engine: Technology that converts voice data into text data (a specific example is the Google Cloud Speech-to-Text API).

[0835] Emotion engine: Technology that recognizes emotions by analyzing voice tone and facial expressions (a specific example is the Microsoft Azure Emotion API).

[0836] Processing Details

[0837] 1. Data Collection:

[0838] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time.

[0839] The collected data is immediately sent to the server.

[0840] 2. Data Processing:

[0841] The server converts the received voice data into text using a voice recognition engine.

[0842] The received video data is converted into text data using OCR technology, with handwritten characters converted into text data.

[0843] Based on the converted text data, relevant information is collected from internal databases and external sources.

[0844] 3. Emotion recognition:

[0845] The server's emotion engine analyzes voice tone and facial expressions to recognize the user's emotions.

[0846] Adjust the priority and content of the information displayed based on the perceived emotion.

[0847] 4. Information provision:

[0848] -The analyzed information and related information are displayed in real time on a visual display device (smart glasses).

[0849] -Users can access the information they need hands-free.

[0850] Specific examples

[0851] Example 1: Operator excitement

[0852] If an operator excitedly says, "This machine's new function is revolutionary!", the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's excitement, and depending on the operator's excitement, collects and displays related information such as "detailed information on the new function" and "implementation procedures."

[0853] Example 2: Operator anxiety

[0854] If an operator says in an anxious tone, "I don't know how to solve this problem," the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's state of anxiety, and prioritizes the collection and display of "past troubleshooting cases" and "expert advice."

[0855] Example prompts for generative AI models

[0856] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[0857] Generate content: Generate text taking into account the following:

[0858] New feature details

[0859] Step-by-step implementation guide

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861] Step 1: The device collects audio and video data in real time.

[0862] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time. The input is audio and video data, which are used directly in the next processing step, so no data processing is performed. The output is the captured raw audio and video data.

[0863] Step 2: The device sends the collected data to the server

[0864] The audio and video data captured by the device is sent to the server via the network. The input is the raw audio and video data, and the data is sent. The output is the audio and video data that has arrived at the server.

[0865] Step 3: The server converts the audio data into text data

[0866] The server converts the received voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text API). The input is voice data, and the data is processed using voice recognition technology to output text data.

[0867] Step 4: The server extracts handwritten characters from the video data and converts them into text data.

[0868] The server extracts handwritten characters from the video data received by the server using OCR technology (for example, Google Cloud Vision API) and converts them into text data. The input is video data, and the output is text data after processing using OCR technology.

[0869] Step 5: The server collects relevant information based on the text data.

[0870] The server searches and collects related information from internal databases and external information sources based on the generated text data. The input is text data, and the collected related information is output by processing the data through database searches and API requests.

[0871] Step 6: The server analyzes voice tone and facial expressions to recognize emotions

[0872] The server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the audio and video data and recognize the user's emotions. The input is audio and video data, and emotion analysis technology processes the data to obtain emotional data as output.

[0873] Step 7: The server adjusts the priority of information based on the emotion data.

[0874] The server adjusts the priority and display content of collected related information based on the recognized emotion data. The input is emotion data and related information, and by processing and filtering the data, it obtains output information appropriate to the emotion.

[0875] Step 8: The server sends the information in real time to a visual display device

[0876] The server transmits the adjusted information to the visual display device (smart glasses) in real time. The input is the adjusted information, and by transmitting the data, the display information that the user can visually confirm is obtained as the output.

[0877] Example prompts for generative AI models

[0878] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[0879] Generate content: Generate text taking into account the following:

[0880] New feature details

[0881] Step-by-step implementation guide

[0882] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0883] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0884] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0885] [Third embodiment]

[0886] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0887] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0888] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0889] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0890] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0891] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0892] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0893] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0894] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0895] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0896] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0897] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0898] This invention is a system that generates minutes in real time during a meeting and automatically adds related information. This system is realized by collecting information entered by users on the terminal, and processing and analyzing it on the server.

[0899] System configuration

[0900] The system consists of the following main components:

[0901] User: An individual or group who enters information on the whiteboard during a meeting.

[0902] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[0903] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user.

[0904] Program processing

[0905] 1. User Actions

[0906] A user starts a meeting and handwrites "New Product Release Date" on the whiteboard.

[0907] 2. Data Collection

[0908] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[0909] The captured data is sent to a server in real time.

[0910] 3. Data Processing

[0911] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[0912] At the same time, the voice data is converted into text data using voice recognition technology.

[0913] Text data of the "new product release date" is generated.

[0914] 4. Collection of relevant information

[0915] Based on the text data, the server automatically collects past project data related to the "new product release date," documents from internal databases, external market trend reports, and so on.

[0916] 5. Data Analysis and Presentation

[0917] The server analyzes the collected information and compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[0918] The compiled information is displayed on a whiteboard in real time for the user to review.

[0919] Specific examples

[0920] Example 1: Starting a meeting and generating minutes

[0921] A user writes on a whiteboard, "Decide the budget for the next project."

[0922] The device captures handwritten text with its camera and records audio with its microphone.

[0923] The server uses OCR technology to convert handwritten characters into text data, and at the same time uses voice recognition technology to convert voice data into text.

[0924] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database.

[0925] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[0926] Example 2: Dynamic information addition during a meeting

[0927] A user says in a statement, "I want to find out about market trends this year."

[0928] The device captures the audio and sends it to the server.

[0929] The server recognizes the voice and converts it into text, then automatically searches for market trend reports based on that text.

[0930] Market trend graphs and report summaries are displayed on the whiteboard, allowing users to review them as they conduct the meeting.

[0931] This system automatically collects and analyzes necessary information during meetings, allowing users to efficiently conduct meetings and obtain relevant information in real time, greatly simplifying the creation of minutes and improving the quality of meetings.

[0932] The processing flow will be explained below.

[0933] Step 1:

[0934] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[0935] Step 2:

[0936] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[0937] Step 3:

[0938] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[0939] Step 4:

[0940] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[0941] Step 5:

[0942] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[0943] Step 6:

[0944] The server analyzes the transcripts of the meeting minutes and automatically collects relevant information from internal databases and external sources. In this case, it retrieves past release data and market trend reports related to the "new product release date."

[0945] Step 7:

[0946] The server analyzes the collected related information and organizes the necessary information into an appropriate format, for example, generating graphs of past release schedules or market trends.

[0947] Step 8:

[0948] The server sends the organized information to the device in real time, where it is displayed visually on the whiteboard.

[0949] Step 9:

[0950] Users can check the supplementary information displayed on the whiteboard and proceed with the meeting, adding new topics or expressing opinions as necessary.

[0951] Step 10:

[0952] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the agenda, what was said, and any related information collected during the meeting.

[0953] Step 11:

[0954] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[0955] Example 1

[0956] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0957] In modern meetings, a large amount of information is exchanged in real time, making it difficult to create minutes and search for information during the meeting. Furthermore, there is a lack of systems that can efficiently manage various information formats, including handwritten and audio recordings, and support the progress of meetings. This leads to issues such as reduced meeting productivity and a loss of accuracy in meeting minutes.

[0958] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0959] In this invention, the server includes means for collecting information input by users to a display device during a meeting in real time, terminal means for transmitting the collected information to a computer, means for converting the information received by the computer into text, means for collecting related information from an internal database or external information source based on the converted text, and means for analyzing and visually displaying the collected related information. This makes it possible to instantly obtain related information during a meeting and reflect it in the minutes, significantly improving the productivity of the meeting and the accuracy of the minutes.

[0960] A "user" is an individual or group that enters information during a conference.

[0961] A "display device" is a device that allows a user to input information, and includes, for example, a whiteboard or digital screen.

[0962] "Means for collecting information in real time" refers to technologies and devices that instantly acquire information entered during a meeting and use it for subsequent processing.

[0963] "Terminal means for transmitting to a computer" refers to a device or network infrastructure for transmitting collected information to a server.

[0964] A "computer" is an electronic device that processes received information and performs various data conversions and analyses.

[0965] "Means of converting text" refers to technologies that convert handwritten or voice data into character data, including optical character recognition (OCR) and voice recognition.

[0966] An "internal database" is a database that stores various data within a company.

[0967] "External sources" are sources of information provided on the Internet or by external organizations.

[0968] "Means of collecting relevant information" refers to the techniques and processes used to obtain the necessary data from internal databases and external sources based on the textual information.

[0969] "Visual display means" refers to techniques and devices that present the collected and analyzed information to the user in the form of charts, graphs, text, etc.

[0970] This system collects and analyzes information input to a display device during a meeting in real time, and automatically acquires and displays related information. The system is mainly composed of three elements: users, terminals, and a server.

[0971] User

[0972] During a meeting, users input information into the display device, for example, by writing documents by hand on a whiteboard or digital screen, or by making speeches.

[0973] Terminal

[0974] The terminal is a device for collecting information entered by the user, and includes a camera and a microphone. For example, handwritten information entered on a whiteboard is captured by the camera, and audio of conversations is recorded by the microphone. Specific devices used include Logitech webcams and Shure conference microphones. The collected data is sent from the terminal to a server in real time.

[0975] server

[0976] The server receives the data sent from the device and performs the following operations:

[0977] 1. Convert data to text

[0978] The server converts the received data into character data. At this time, handwritten data is converted into text data using optical character recognition (OCR) technology. The specific software used is Google Cloud Vision API. At the same time, audio data is converted into text data using voice recognition technology. Google Cloud Speech-to-Text is used for this process.

[0979] 2. Collection of relevant information

[0980] Based on the textual information, the server automatically collects related information, such as past project data, internal databases (Microsoft SharePoint), and external market trend reports (Gartner). This allows users to quickly gather the information they need.

[0981] 3. Data Analysis and Presentation

[0982] The server analyzes the collected information and compiles it into an appropriate format (for example, using Excel or Tableau). The compiled information is then displayed in real time on a display device so that the user can view it.

[0983] Specific examples

[0984] Example 1: Starting a meeting and generating minutes

[0985] A user writes on a whiteboard, "Decide the budget for the next project."

[0986] The device captures the handwriting with its camera and records the audio with its microphone.

[0987] The server uses OCR technology (Google Cloud Vision API) to convert handwritten characters into text data, and converts the audio data into text using speech recognition technology (Google Cloud Speech-to-Text).

[0988] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database (Microsoft SharePoint).

[0989] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[0990] Example 2: Dynamic information addition during a meeting

[0991] A user says in a statement, "I want to find out about market trends this year."

[0992] The device captures the audio and sends it to the server.

[0993] The server recognizes the speech and converts it into text, then automatically searches for market trend reports (Gartner reports) based on that text.

[0994] Market trend graphs and report summaries are displayed on the whiteboard, and users can review them as they conduct the meeting.

[0995] Prompt Sentence Examples

[0996] "Please explain in detail the processing procedures of a system that captures written content and audio in real time during a meeting and automatically collects and displays information related to that content. Also, please name the specific hardware and software, and describe the data processing and calculation methods."

[0997] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0998] Step 1:

[0999] The user inputs information into the display device.

[1000] Input: A user handwrites "New product release date" on the display device.

[1001] Output: Written and spoken text is recorded on the display device.

[1002] Specific operation: The user writes characters by hand on the whiteboard and speaks at the same time.

[1003] Step 2:

[1004] The device captures your handwriting and voice.

[1005] Input: Written text on the display and spoken words by the user.

[1006] Output: Captured image and audio data.

[1007] What it does: The camera captures what you write, and the microphone records what you say.

[1008] Step 3:

[1009] The device sends the captured data to the server.

[1010] Input: Image and audio data.

[1011] Output: Image and audio data sent to the server.

[1012] Specific operation: The terminal's communication module sends the collected data to a server via the Internet.

[1013] Step 4:

[1014] The server converts the image data and audio data into text data.

[1015] Input: Image and audio data sent to the server.

[1016] Output: The converted text data.

[1017] Specific operation: The server's OCR engine extracts characters from image data, and the speech recognition engine generates text from speech.

[1018] Step 5:

[1019] The server collects related information based on the text data.

[1020] Input: The converted text data.

[1021] Output: Relevant information collected (historical project data, external reports, etc.).

[1022] What happens: The server queries internal databases and external sources to retrieve the required data.

[1023] Step 6:

[1024] The server analyzes the collected information and displays it visually.

[1025] Input: The relevant information you have collected.

[1026] Output: A visual format (text, graphs, charts, etc.) containing the results of the analysis.

[1027] Specific operation: The server analyzes the data, visually summarizes the information using Excel or Tableau, and sends it to the display device.

[1028] Step 7:

[1029] The user proceeds with the conference while checking the presented information.

[1030] Input: Visual information displayed on a display device.

[1031] Output: Review meeting progress and minutes.

[1032] Specific operation: The user refers to the information displayed on the display device and decides on the next agenda item or action item.

[1033] (Application example 1)

[1034] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1035] Conventional conference systems and factory robots lacked systems that could collect information in real time and automatically present relevant information. This made it difficult to quickly and effectively obtain necessary information during meetings or factory work, leading to calls for improvements in work efficiency and quality. Furthermore, there was a lack of technology that could convert handwritten text and voice into text in real time and automatically collect and analyze relevant information based on that information, making it difficult for users to use information efficiently. This created the risk of delays in meeting and work progress and decisions being made based on incorrect information.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1037] In this invention, the server includes a means for collecting information entered by users during meetings or work in real time, a terminal means for transmitting the collected information to the server, and a means for converting the information received by the server into text. This makes it possible to collect related information from databases and external information sources based on the converted text, analyze the collected related information, and visually display it, and to present the related information in real time to devices used in the factory. This allows factory work and meetings to proceed quickly and effectively, improving work efficiency and quality.

[1038] "User" refers to an individual or group that uses the system to hold meetings or carry out factory work.

[1039] "Real-time" refers to information being processed and displayed almost in sync with the moment it is generated.

[1040] "Terminal means" refers to a device, such as a camera, microphone, smart glasses, or head-mounted display, that collects information entered by a user and transmits it to a server.

[1041] "Server" refers to a computing system for processing received data, performing necessary analysis, and providing relevant information.

[1042] "Text conversion" refers to the conversion of non-text information, such as handwritten characters or audio data, into machine-readable text data.

[1043] "Database" refers to an information system that stores related information in a structured manner so that it can be efficiently searched and accessed at a later time.

[1044] "External sources" refers to information sources other than internal databases, such as external databases, network resources, and online reports.

[1045] "Analysis" refers to the act of processing collected data using statistical and logical methods to extract meaningful information and insights.

[1046] "Visually" refers to presenting information in the form of text, graphs, charts, images, etc., so that it can be easily understood by the user.

[1047] "Devices used within the factory" refers to devices used by factory workers to receive and display information, such as smart glasses, tablets, and head-mounted displays.

[1048] "Related information" refers to additional data or materials related to the information or statements entered by the user that are useful for work or decision-making.

[1049] This invention is a system that presents relevant information in real time to devices primarily used in factories, and is composed of the following components:

[1050] System configuration

[1051] 1. User:

[1052] Factory workers use devices such as smart glasses and tablet computers to perform their work.

[1053] 2. Terminal means:

[1054] These include smart glasses, tablet devices, head-mounted displays, etc., which capture information such as voice and handwritten characters and send it to a server.

[1055] 3. Server:

[1056] Its main functions are:

[1057] The received voice data is converted into text data using voice recognition software (e.g., Google Speech-to-Text API).

[1058] Optical character recognition technology (e.g., OCR) is used to convert handwritten characters into text.

[1059] Based on the textual data, relevant information is collected from databases and external sources.

[1060] The collected information is analyzed and displayed on the device in real time.

[1061] Operation flow

[1062] Data collection:

[1063] Take the example of a user saying, "Please display the work instructions for the next process." The microphone in the smart glasses captures the voice and sends it to the server.

[1064] Data Processing:

[1065] The server converts the voice data into text data using the Google Speech-to-Text API, and then collects and analyzes information related to work instructions for the next process from an internal database.

[1066] Information presentation:

[1067] Relevant information collected from databases and external information sources is displayed in real time on the display of smart glasses or tablet devices, allowing users to work while checking the displayed information.

[1068] Specific examples

[1069] Consider a factory worker saying, "Tell me how to assemble this part." The smart glasses capture the voice and the server converts it into text data. The server then retrieves the relevant assembly procedure data from the database and visually displays it on the smart glasses' display. In this way, users can obtain the information they need in real time while working, allowing them to perform their tasks efficiently and accurately.

[1070] Prompt Sentence Examples

[1071] Factory worker: "Show me the work instructions for the next process."

[1072] Server (prompt for input to generative AI model): "Search for the next process step. Display relevant information from the factory database."

[1073] It is expected that such a system will improve the efficiency of work within the factory and the quality of work.

[1074] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1075] Step 1:

[1076] The user speaks into the smart glasses, saying, "Show me the work instructions for the next step." The input is voice data, which is captured by the smart glasses' microphone. The output is the captured voice data.

[1077] Step 2:

[1078] The smart glasses of the terminal means transmit the captured voice data to the server. The input is the captured voice data, and the output is the data transmission to the server.

[1079] Step 3:

[1080] The voice data received by the server is converted into text data using the Google Speech-to-Text API. The input is the voice data received by the server, and the output is text data. Specifically, the server sends the voice data to the API and receives text data as the conversion result.

[1081] Step 4:

[1082] The server searches an internal database for information related to the work instructions for the next process based on the text data. The input is the converted text data ("Show me the work instructions for the next process"), and the output is the related work instruction data. Specifically, the server generates a query and searches the database.

[1083] Step 5:

[1084] The server analyzes the work instruction data retrieved from the database and converts it into a format for visual display. The input is raw data retrieved from the database, and the output is formatted data that can be displayed visually (e.g., text, graphs, charts). Specifically, the server performs formatting processing on the data and converts it into a format that is easy for users to understand.

[1085] Step 6:

[1086] The server transmits formatted work instruction data to the smart glasses as the terminal means. The input is the formatted data formatted by the server, and the output is the data displayed on the smart glasses.

[1087] Step 7:

[1088] The smart glasses display the received work instruction data in the user's field of view. The input is formatted data received from the server, and the output is visual information displayed on the smart glasses' display. Specifically, the smart glasses render the received data on their display.

[1089] Through these processing steps, users can obtain the information they need in real time while working, allowing them to work efficiently and accurately.

[1090] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1091] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision according to the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by the server.

[1092] System configuration

[1093] The system consists of the following main components:

[1094] User: An individual or group who enters information on the whiteboard during a meeting.

[1095] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[1096] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user. It also uses an emotion engine to recognize and analyze the user's emotions.

[1097] Emotion engine: Recognizes the user's emotions from audio and video data, and changes the priority of information and feedback based on those emotions.

[1098] Program processing

[1099] 1. User Actions

[1100] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[1101] 2. Data Collection

[1102] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[1103] The captured data is sent to a server in real time.

[1104] 3. Data Processing

[1105] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[1106] At the same time, the voice data is converted into text data using voice recognition technology.

[1107] Text data of the "new product release date" is generated.

[1108] 4. Emotion recognition

[1109] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[1110] The emotion engine generates emotion data indicating whether the user is excited, calm, anxious, etc.

[1111] 5. Collection of relevant information

[1112] The server automatically collects past project data, documents from internal databases, external market trend reports, etc. related to the "new product release date" based on text data and sentiment data.

[1113] 6. Data Analysis and Presentation

[1114] The server analyzes and prioritizes the collected information based on emotional data, and then compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[1115] If the user is feeling anxious, more detailed information and supplementary materials will be displayed preferentially.

[1116] 7. Real-time feedback

[1117] The compiled information is displayed on a whiteboard in real time, allowing users to check information that corresponds to their emotions.

[1118] Specific examples

[1119] Example 1: User excitement

[1120] "This is a very important release," an excited user said.

[1121] The device captures the audio and sends it to the server.

[1122] The server uses voice recognition and an emotion engine to recognize the user's state of excitement.

[1123] The server collects and displays a list of planned release dates and competitive information.

[1124] Example 2: User Concerns

[1125] The user stated in an anxious tone that he was "unsure of the release date."

[1126] The device captures the audio and sends it to the server.

[1127] The server uses voice recognition and an emotion engine to recognize the user's anxiety state.

[1128] The server prioritizes the collection and display of supplementary information such as "past success stories" and "risk management plans."

[1129] This system not only automatically collects and analyzes necessary information during meetings, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[1130] The processing flow will be explained below.

[1131] Step 1:

[1132] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[1133] Step 2:

[1134] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[1135] Step 3:

[1136] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[1137] Step 4:

[1138] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[1139] Step 5:

[1140] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[1141] Step 6:

[1142] The server's emotion engine analyzes audio and video data to recognize the user's emotions and generates emotion data such as "excited," "anxious," or "calm."

[1143] Step 7:

[1144] The server analyzes the textual minutes and sentiment data, and automatically collects relevant information from internal databases and external sources, such as past project data and market trend reports related to "new product release dates."

[1145] Step 8:

[1146] The server analyzes the collected relevant information and prioritizes it based on emotional data: for example, if the user is excited, it will promptly present a release candidate date, but if the user is anxious, it will prioritize detailed risk management information.

[1147] Step 9:

[1148] The server sends the organized information to the terminal in real time and displays it visually on the whiteboard. Users can proceed with the meeting while checking the displayed supplementary information.

[1149] Step 10:

[1150] If a user adds a new comment or topic during the meeting, the device will again capture voice and handwritten data and send it to the server, which will then analyze the data again and collect and display the relevant information.

[1151] Step 11:

[1152] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the meeting topics, comments, emotional data, and other relevant information collected during the meeting.

[1153] Step 12:

[1154] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[1155] Example 2

[1156] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1157] Creating effective minutes during meetings is an important challenge for many companies and organizations. However, traditional methods for creating minutes have made it difficult to collect information in real time and provide relevant information promptly. It has also been difficult to accurately grasp users' emotions during the meeting and provide information appropriate to those emotions. As a result, the efficiency and effectiveness of meetings are often compromised.

[1158] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1159] In this invention, the server includes means for recognizing user emotions from audio data and video data, means for changing information priority and feedback based on the emotion data, and means for analyzing and visually displaying collected related information, thereby enabling the creation of minutes and provision of related information in real time during a meeting according to the user's emotions.

[1160] A "user" is an individual or group who enters information onto the whiteboard during a meeting.

[1161] "Terminal means" refers to devices that collect information entered by users and transmit it to a server, including cameras, microphones, smart whiteboards, etc.

[1162] "Server" refers to the central processing unit that processes and analyzes collected information and collects and displays related information.

[1163] "Means for converting to text" refers to technology for converting received handwritten data or voice data into text data.

[1164] "Database" refers to a source of information for storing and managing related information, including internal project data and documents.

[1165] "External information sources" refers to information providers or information systems that include external market trend reports, competitive information, etc.

[1166] "Emotion engine" refers to technology for recognizing and analyzing user emotions from audio and video data.

[1167] "Emotion data" refers to data relating to a user's emotions generated by the emotion engine.

[1168] "Means for changing priorities and feedback" refers to a technique or method for setting the importance of information based on emotional data and adjusting the order and content of information provided to the user.

[1169] "Visual display means" refers to techniques and methods for presenting analyzed information to users in the form of graphs, charts, text, etc.

[1170] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision based on the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by a server. The hardware used includes a camera, microphone, and smart whiteboard, while the software includes optical character recognition (OCR) technology, voice recognition technology, and an emotion engine. Specifically, the system operates as follows:

[1171] First, a user starts a meeting and writes something on a whiteboard, such as "the release date of a new product." The device captures what is handwritten on the whiteboard with a camera and captures the audio of the conversation with a microphone. This captured data is sent to a server in real time. The server converts the received handwritten data into text data using optical character recognition (OCR) technology, and converts the audio data into text data using speech recognition technology. For example, Google Cloud Vision API or Google Cloud Speech-to-Text may be used.

[1172] Next, the server's emotion engine analyzes the audio and video data to recognize the user's emotions. The emotion engine uses, for example, the Microsoft Azure Emotion API. As a result of the analysis, emotional data is generated, indicating whether the user is excited, calm, or anxious. The server then collects and analyzes related information based on this emotional data and text data. Specifically, the server collects past project data, documents, external market trend reports, and other information from internal databases and external sources. This allows the server to prioritize information and change feedback based on the user's emotions.

[1173] For example, if a user is feeling anxious, the server will prioritize displaying supplementary information such as "past success stories" and "risk management plans." The collected information is analyzed and compiled in the form of text, graphs, charts, and other information, and displayed on the whiteboard in real time. This allows users to instantly check the information they need even during a meeting, making it possible to conduct the meeting efficiently and effectively.

[1174] Specific examples

[1175] Example 1: User excitement

[1176] A user excitedly says, "This release is super important!"

[1177] The device captures this speech with a microphone and sends it to the server.

[1178] The server recognizes the user's excitement state using voice recognition and an emotion engine.

[1179] The server automatically collects a list of planned release dates and competitive information and displays them on a whiteboard.

[1180] Example 2: User Concerns

[1181] The user expresses concern by saying, "I'm not sure about the release date."

[1182] The device captures this speech with a microphone and sends it to the server.

[1183] The server uses voice recognition and an emotion engine to recognize the anxiety state of the user.

[1184] The server prioritizes collecting supplementary information such as "past success stories" and "risk management plans" and displays it on the whiteboard.

[1185] Prompt Sentence Examples

[1186] Here is an example prompt:

[1187] If a user is excitedly talking in a release meeting:

[1188] "During a meeting, a user excitedly says, 'This release is so important.' Record the conversation and explain how the system will recognize the user's emotion and display relevant release dates and competitive information."

[1189] This not only automatically collects and analyzes necessary information during a meeting, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[1190] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1191] Step 1:

[1192] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[1193] Input: The user enters information by hand on the whiteboard.

[1194] Specific behavior: A user uses a smart whiteboard and writes "New product release date" with a pen.

[1195] Step 2:

[1196] The device uses a camera to capture what is handwritten on the whiteboard.

[1197] Input: Handwritten text on a whiteboard.

[1198] Specific operation: The device's camera captures the handwriting on the whiteboard as an image.

[1199] Step 3:

[1200] The device captures the audio of the conversation using a microphone.

[1201] Input: What people say during the meeting.

[1202] What it does: The microphone captures the audio of the conversation as audio data.

[1203] Step 4:

[1204] The terminal transmits the captured image data and audio data to the server.

[1205] Input: Captured image and audio data.

[1206] Output: Image and audio data sent to the server.

[1207] Specific operation: The terminal sends image data and audio data to the server via the network.

[1208] Step 5:

[1209] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[1210] Input: Handwritten data (image data) on a whiteboard.

[1211] Output: Text data converted by optical character recognition (OCR).

[1212] Specific operation: The server's OCR software analyzes the handwritten data and converts it into text data called "New product release date."

[1213] Step 6:

[1214] The server converts the voice data into text data using voice recognition technology.

[1215] Input: Audio data.

[1216] Output: Text data converted by speech recognition.

[1217] Specific operation: The server's voice recognition software analyzes the voice data and converts what the user says into text data.

[1218] Step 7:

[1219] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[1220] Input: Audio and video data.

[1221] Output: User emotion data.

[1222] Specific operation: The emotion engine analyzes voice tone and facial expressions and generates data representing the user's emotional state (excitement, anxiety, etc.).

[1223] Step 8:

[1224] The server collects relevant information from databases and external information sources based on the text data and emotion data.

[1225] Input: Text data and emotion data.

[1226] Output: Relevant information (historical project data, external market trend reports, etc.).

[1227] Specific operation: The server searches and collects relevant information using internal databases and external APIs.

[1228] Step 9:

[1229] The server analyzes the collected information and prioritizes it based on emotional data.

[1230] Input: Collected relevant information and sentiment data.

[1231] Output: Prioritized information.

[1232] Specific operation: The server takes into account the emotional data and, for example, prioritizes detailed risk management plans when the user is in an anxious state.

[1233] Step 10:

[1234] The server uses a means for visually displaying the analyzed information to display it on a whiteboard.

[1235] Input: Prioritized information.

[1236] Output: Visually displayed information (text, graphs, charts, etc.).

[1237] Specific operation: The server organizes the information and displays it on the whiteboard in real time, so that the user can check it.

[1238] (Application example 2)

[1239] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1240] Conventional automatic meeting memo generation systems lack the ability to generate minutes in real time, as well as the ability to provide flexible information based on the user's emotions. Furthermore, when robot operators hold work instructions or troubleshooting meetings in factories, it is difficult to immediately obtain relevant information based on the meeting content, and information appropriate to the user's emotions is not provided. This hinders rapid problem-solving and efficient meeting management.

[1241] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion from audio data and video data and adjusting the priority of information and feedback based on the emotion, means for analyzing and visually displaying the collected information, and means for collecting related information from an internal database and external information sources. This makes it possible to not only generate minutes of a meeting but also provide appropriate information according to the user's emotion.

[1242] A "user" is an individual or group who uses the system to provide information during a meeting via a whiteboard or voice input.

[1243] "Means for collecting information in real time" refers to technology and devices that instantly detect information or statements entered by users on the whiteboard and collect them as data.

[1244] "Terminal means" refers to devices or equipment that have the function of transmitting collected information to a server. Specifically, it includes cameras, microphones, network communication modules, etc.

[1245] "Server" means a computer system that processes and analyzes the information it receives and provides relevant information to the user.

[1246] "Means of converting to text" refers to the technology of converting voice data or handwritten data into character data using OCR and voice recognition technology.

[1247] "Means for collecting related information" refers to technology that searches for and acquires related data from internal databases and external information sources based on the textual content of meetings.

[1248] "Means for visually displaying" refers to a display device or interface for visually presenting the analysis results and related information to a user.

[1249] "Means for recognizing a user's emotions from audio and video data" refers to technology that determines a user's emotional state through voice tone and facial expression analysis.

[1250] "Means for adjusting information priority and feedback" refers to technology that dynamically changes the order and content of information provided depending on the recognized emotional state of the user.

[1251] System configuration

[1252] This invention is a system that collects and analyzes information in real time, provided by users during a meeting via a whiteboard or voice input. The main components of the system include:

[1253] 1. Terminal: Consists of devices such as a camera, microphone, and smart glasses, which collects information entered by the user in real time and sends it to the server.

[1254] 2. Server: Processes and analyzes the collected information, collects relevant information, and provides it to the user. It also recognizes the user's emotions from audio and video data, and adjusts the priority of information and feedback based on those emotions.

[1255] 3. Emotion engine: Analyzes voice tone and facial expressions to recognize the user's emotions.

[1256] 4. Visual display devices: Using display devices such as smart glasses, collected and analyzed information is presented to users in real time.

[1257] Program processing

[1258] Hardware and software used

[1259] Smart glasses: worn by the user and act as a display and audio interface.

[1260] Camera and microphone: Built into the smart glasses to capture audio and video.

[1261] Server: A computer system that processes data and performs sentiment analysis.

[1262] OCR technology: Optical character recognition technology is used to convert handwritten characters on a whiteboard into text data (a specific example is the Google Cloud Vision API).

[1263] Speech recognition engine: Technology that converts voice data into text data (a specific example is the Google Cloud Speech-to-Text API).

[1264] Emotion engine: Technology that recognizes emotions by analyzing voice tone and facial expressions (a specific example is the Microsoft Azure Emotion API).

[1265] Processing Details

[1266] 1. Data Collection:

[1267] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time.

[1268] The collected data is immediately sent to the server.

[1269] 2. Data Processing:

[1270] The server converts the received voice data into text using a voice recognition engine.

[1271] The received video data is converted into text data using OCR technology, with handwritten characters converted into text data.

[1272] Based on the converted text data, relevant information is collected from internal databases and external sources.

[1273] 3. Emotion recognition:

[1274] The server's emotion engine analyzes voice tone and facial expressions to recognize the user's emotions.

[1275] Adjust the priority and content of the information displayed based on the perceived emotion.

[1276] 4. Information provision:

[1277] -The analyzed information and related information are displayed in real time on a visual display device (smart glasses).

[1278] -Users can access the information they need hands-free.

[1279] Specific examples

[1280] Example 1: Operator excitement

[1281] If an operator excitedly says, "This machine's new function is revolutionary!", the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's excitement, and depending on the operator's excitement, collects and displays related information such as "detailed information on the new function" and "implementation procedures."

[1282] Example 2: Operator anxiety

[1283] If an operator says in an anxious tone, "I don't know how to solve this problem," the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's state of anxiety, and prioritizes the collection and display of "past troubleshooting cases" and "expert advice."

[1284] Example prompts for generative AI models

[1285] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[1286] Generate content: Generate text taking into account the following:

[1287] New feature details

[1288] Step-by-step implementation guide

[1289] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1290] Step 1: The device collects audio and video data in real time.

[1291] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time. The input is audio and video data, which are used directly in the next processing step, so no data processing is performed. The output is the captured raw audio and video data.

[1292] Step 2: The device sends the collected data to the server

[1293] The audio and video data captured by the device is sent to the server via the network. The input is the raw audio and video data, and the data is sent. The output is the audio and video data that has arrived at the server.

[1294] Step 3: The server converts the audio data into text data

[1295] The server converts the received voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text API). The input is voice data, and the data is processed using voice recognition technology to output text data.

[1296] Step 4: The server extracts handwritten characters from the video data and converts them into text data.

[1297] The server extracts handwritten characters from the video data received by the server using OCR technology (for example, Google Cloud Vision API) and converts them into text data. The input is video data, and the output is text data after processing using OCR technology.

[1298] Step 5: The server collects relevant information based on the text data.

[1299] The server searches and collects related information from internal databases and external information sources based on the generated text data. The input is text data, and the collected related information is output by processing the data through database searches and API requests.

[1300] Step 6: The server analyzes voice tone and facial expressions to recognize emotions

[1301] The server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the audio and video data and recognize the user's emotions. The input is audio and video data, and emotion analysis technology processes the data to obtain emotional data as output.

[1302] Step 7: The server adjusts the priority of information based on the emotion data.

[1303] The server adjusts the priority and display content of collected related information based on the recognized emotion data. The input is emotion data and related information, and by processing and filtering the data, it obtains output information appropriate to the emotion.

[1304] Step 8: The server sends the information in real time to a visual display device

[1305] The server transmits the adjusted information to the visual display device (smart glasses) in real time. The input is the adjusted information, and by transmitting the data, the display information that the user can visually confirm is obtained as the output.

[1306] Example prompts for generative AI models

[1307] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[1308] Generate content: Generate text taking into account the following:

[1309] New feature details

[1310] Step-by-step implementation guide

[1311] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1312] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1313] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1314] [Fourth embodiment]

[1315] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1316] 7, a 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.

[1317] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1318] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1319] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1320] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1321] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1322] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1323] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1324] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1325] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1326] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1327] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1328] This invention is a system that generates minutes in real time during a meeting and automatically adds related information. This system is realized by collecting information entered by users on the terminal, and processing and analyzing it on the server.

[1329] System configuration

[1330] The system consists of the following main components:

[1331] User: An individual or group who enters information on the whiteboard during a meeting.

[1332] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[1333] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user.

[1334] Program processing

[1335] 1. User Actions

[1336] A user starts a meeting and handwrites "New Product Release Date" on the whiteboard.

[1337] 2. Data Collection

[1338] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[1339] The captured data is sent to a server in real time.

[1340] 3. Data Processing

[1341] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[1342] At the same time, the voice data is converted into text data using voice recognition technology.

[1343] Text data of the "new product release date" is generated.

[1344] 4. Collection of relevant information

[1345] Based on the text data, the server automatically collects past project data related to the "new product release date," documents from internal databases, external market trend reports, and so on.

[1346] 5. Data Analysis and Presentation

[1347] The server analyzes the collected information and compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[1348] The compiled information is displayed on a whiteboard in real time for the user to review.

[1349] Specific examples

[1350] Example 1: Starting a meeting and generating minutes

[1351] A user writes on a whiteboard, "Decide the budget for the next project."

[1352] The device captures handwritten text with its camera and records audio with its microphone.

[1353] The server uses OCR technology to convert handwritten characters into text data, and at the same time uses voice recognition technology to convert voice data into text.

[1354] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database.

[1355] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[1356] Example 2: Dynamic information addition during a meeting

[1357] A user says in a statement, "I want to find out about market trends this year."

[1358] The device captures the audio and sends it to the server.

[1359] The server recognizes the voice and converts it into text, then automatically searches for market trend reports based on that text.

[1360] Market trend graphs and report summaries are displayed on the whiteboard, allowing users to review them as they conduct the meeting.

[1361] This system automatically collects and analyzes necessary information during meetings, allowing users to efficiently conduct meetings and obtain relevant information in real time, greatly simplifying the creation of minutes and improving the quality of meetings.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[1365] Step 2:

[1366] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[1367] Step 3:

[1368] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[1369] Step 4:

[1370] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[1371] Step 5:

[1372] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[1373] Step 6:

[1374] The server analyzes the transcripts of the meeting minutes and automatically collects relevant information from internal databases and external sources. In this case, it retrieves past release data and market trend reports related to the "new product release date."

[1375] Step 7:

[1376] The server analyzes the collected related information and organizes the necessary information into an appropriate format, for example, generating graphs of past release schedules or market trends.

[1377] Step 8:

[1378] The server sends the organized information to the device in real time, where it is displayed visually on the whiteboard.

[1379] Step 9:

[1380] Users can check the supplementary information displayed on the whiteboard and proceed with the meeting, adding new topics or expressing opinions as necessary.

[1381] Step 10:

[1382] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the agenda, what was said, and any related information collected during the meeting.

[1383] Step 11:

[1384] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[1385] Example 1

[1386] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1387] In modern meetings, a large amount of information is exchanged in real time, making it difficult to create minutes and search for information during the meeting. Furthermore, there is a lack of systems that can efficiently manage various information formats, including handwritten and audio recordings, and support the progress of meetings. This leads to issues such as reduced meeting productivity and a loss of accuracy in meeting minutes.

[1388] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1389] In this invention, the server includes means for collecting information input by users to a display device during a meeting in real time, terminal means for transmitting the collected information to a computer, means for converting the information received by the computer into text, means for collecting related information from an internal database or external information source based on the converted text, and means for analyzing and visually displaying the collected related information. This makes it possible to instantly obtain related information during a meeting and reflect it in the minutes, significantly improving the productivity of the meeting and the accuracy of the minutes.

[1390] A "user" is an individual or group that enters information during a conference.

[1391] A "display device" is a device that allows a user to input information, and includes, for example, a whiteboard or digital screen.

[1392] "Means for collecting information in real time" refers to technologies and devices that instantly acquire information entered during a meeting and use it for subsequent processing.

[1393] "Terminal means for transmitting to a computer" refers to a device or network infrastructure for transmitting collected information to a server.

[1394] A "computer" is an electronic device that processes received information and performs various data conversions and analyses.

[1395] "Means of converting text" refers to technologies that convert handwritten or voice data into character data, including optical character recognition (OCR) and voice recognition.

[1396] An "internal database" is a database that stores various data within a company.

[1397] "External sources" are sources of information provided on the Internet or by external organizations.

[1398] "Means of collecting relevant information" refers to the techniques and processes used to obtain the necessary data from internal databases and external sources based on the textual information.

[1399] "Visual display means" refers to techniques and devices that present the collected and analyzed information to the user in the form of charts, graphs, text, etc.

[1400] This system collects and analyzes information input to a display device during a meeting in real time, and automatically acquires and displays related information. The system is mainly composed of three elements: users, terminals, and a server.

[1401] User

[1402] During a meeting, users input information into the display device, for example, by writing documents by hand on a whiteboard or digital screen, or by making speeches.

[1403] Terminal

[1404] The terminal is a device for collecting information entered by the user, and includes a camera and a microphone. For example, handwritten information entered on a whiteboard is captured by the camera, and audio of conversations is recorded by the microphone. Specific devices used include Logitech webcams and Shure conference microphones. The collected data is sent from the terminal to a server in real time.

[1405] server

[1406] The server receives the data sent from the device and performs the following operations:

[1407] 1. Convert data to text

[1408] The server converts the received data into character data. At this time, handwritten data is converted into text data using optical character recognition (OCR) technology. The specific software used is Google Cloud Vision API. At the same time, audio data is converted into text data using voice recognition technology. Google Cloud Speech-to-Text is used for this process.

[1409] 2. Collection of relevant information

[1410] Based on the textual information, the server automatically collects related information, such as past project data, internal databases (Microsoft SharePoint), and external market trend reports (Gartner). This allows users to quickly gather the information they need.

[1411] 3. Data Analysis and Presentation

[1412] The server analyzes the collected information and compiles it into an appropriate format (for example, using Excel or Tableau). The compiled information is then displayed in real time on a display device so that the user can view it.

[1413] Specific examples

[1414] Example 1: Starting a meeting and generating minutes

[1415] A user writes on a whiteboard, "Decide the budget for the next project."

[1416] The device captures the handwriting with its camera and records the audio with its microphone.

[1417] The server uses OCR technology (Google Cloud Vision API) to convert handwritten characters into text data, and converts the audio data into text using speech recognition technology (Google Cloud Speech-to-Text).

[1418] The server automatically collects past budget data and proposal materials related to the "budget for the next project" from the company's internal database (Microsoft SharePoint).

[1419] The whiteboard automatically collects relevant information and displays it for immediate review by the user.

[1420] Example 2: Dynamic information addition during a meeting

[1421] A user says in a statement, "I want to find out about market trends this year."

[1422] The device captures the audio and sends it to the server.

[1423] The server recognizes the speech and converts it into text, then automatically searches for market trend reports (Gartner reports) based on that text.

[1424] Market trend graphs and report summaries are displayed on the whiteboard, and users can review them as they conduct the meeting.

[1425] Prompt Sentence Examples

[1426] "Please explain in detail the processing procedures of a system that captures written content and audio in real time during a meeting and automatically collects and displays information related to that content. Also, please name the specific hardware and software, and describe the data processing and calculation methods."

[1427] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1428] Step 1:

[1429] The user inputs information into the display device.

[1430] Input: A user handwrites "New product release date" on the display device.

[1431] Output: Written and spoken text is recorded on the display device.

[1432] Specific operation: The user writes characters by hand on the whiteboard and speaks at the same time.

[1433] Step 2:

[1434] The device captures your handwriting and voice.

[1435] Input: Written text on the display and spoken words by the user.

[1436] Output: Captured image and audio data.

[1437] What it does: The camera captures what you write, and the microphone records what you say.

[1438] Step 3:

[1439] The device sends the captured data to the server.

[1440] Input: Image and audio data.

[1441] Output: Image and audio data sent to the server.

[1442] Specific operation: The terminal's communication module sends the collected data to a server via the Internet.

[1443] Step 4:

[1444] The server converts the image data and audio data into text data.

[1445] Input: Image and audio data sent to the server.

[1446] Output: The converted text data.

[1447] Specific operation: The server's OCR engine extracts characters from image data, and the speech recognition engine generates text from speech.

[1448] Step 5:

[1449] The server collects related information based on the text data.

[1450] Input: The converted text data.

[1451] Output: Relevant information collected (historical project data, external reports, etc.).

[1452] What happens: The server queries internal databases and external sources to retrieve the required data.

[1453] Step 6:

[1454] The server analyzes the collected information and displays it visually.

[1455] Input: The relevant information you have collected.

[1456] Output: A visual format (text, graphs, charts, etc.) containing the results of the analysis.

[1457] Specific operation: The server analyzes the data, visually summarizes the information using Excel or Tableau, and sends it to the display device.

[1458] Step 7:

[1459] The user proceeds with the conference while checking the presented information.

[1460] Input: Visual information displayed on a display device.

[1461] Output: Review meeting progress and minutes.

[1462] Specific operation: The user refers to the information displayed on the display device and decides on the next agenda item or action item.

[1463] (Application example 1)

[1464] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1465] Conventional conference systems and factory robots lacked systems that could collect information in real time and automatically present relevant information. This made it difficult to quickly and effectively obtain necessary information during meetings or factory work, leading to calls for improvements in work efficiency and quality. Furthermore, there was a lack of technology that could convert handwritten text and voice into text in real time and automatically collect and analyze relevant information based on that information, making it difficult for users to use information efficiently. This created the risk of delays in meeting and work progress and decisions being made based on incorrect information.

[1466] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1467] In this invention, the server includes a means for collecting information entered by users during meetings or work in real time, a terminal means for transmitting the collected information to the server, and a means for converting the information received by the server into text. This makes it possible to collect related information from databases and external information sources based on the converted text, analyze the collected related information, and visually display it, and to present the related information in real time to devices used in the factory. This allows factory work and meetings to proceed quickly and effectively, improving work efficiency and quality.

[1468] "User" refers to an individual or group that uses the system to hold meetings or carry out factory work.

[1469] "Real-time" refers to information being processed and displayed almost in sync with the moment it is generated.

[1470] "Terminal means" refers to a device, such as a camera, microphone, smart glasses, or head-mounted display, that collects information entered by a user and transmits it to a server.

[1471] "Server" refers to a computing system for processing received data, performing necessary analysis, and providing relevant information.

[1472] "Text conversion" refers to the conversion of non-text information, such as handwritten characters or audio data, into machine-readable text data.

[1473] "Database" refers to an information system that stores related information in a structured manner so that it can be efficiently searched and accessed at a later time.

[1474] "External sources" refers to information sources other than internal databases, such as external databases, network resources, and online reports.

[1475] "Analysis" refers to the act of processing collected data using statistical and logical methods to extract meaningful information and insights.

[1476] "Visually" refers to presenting information in the form of text, graphs, charts, images, etc., so that it can be easily understood by the user.

[1477] "Devices used within the factory" refers to devices used by factory workers to receive and display information, such as smart glasses, tablets, and head-mounted displays.

[1478] "Related information" refers to additional data or materials related to the information or statements entered by the user that are useful for work or decision-making.

[1479] This invention is a system that presents relevant information in real time to devices primarily used in factories, and is composed of the following components:

[1480] System configuration

[1481] 1. User:

[1482] Factory workers use devices such as smart glasses and tablet computers to perform their work.

[1483] 2. Terminal means:

[1484] These include smart glasses, tablet devices, head-mounted displays, etc., which capture information such as voice and handwritten characters and send it to a server.

[1485] 3. Server:

[1486] Its main functions are:

[1487] The received voice data is converted into text data using voice recognition software (e.g., Google Speech-to-Text API).

[1488] Optical character recognition technology (e.g., OCR) is used to convert handwritten characters into text.

[1489] Based on the textual data, relevant information is collected from databases and external sources.

[1490] The collected information is analyzed and displayed on the device in real time.

[1491] Operation flow

[1492] Data collection:

[1493] Take the example of a user saying, "Please display the work instructions for the next process." The microphone in the smart glasses captures the voice and sends it to the server.

[1494] Data Processing:

[1495] The server converts the voice data into text data using the Google Speech-to-Text API, and then collects and analyzes information related to work instructions for the next process from an internal database.

[1496] Information presentation:

[1497] Relevant information collected from databases and external information sources is displayed in real time on the display of smart glasses or tablet devices, allowing users to work while checking the displayed information.

[1498] Specific examples

[1499] Consider a factory worker saying, "Tell me how to assemble this part." The smart glasses capture the voice and the server converts it into text data. The server then retrieves the relevant assembly procedure data from the database and visually displays it on the smart glasses' display. In this way, users can obtain the information they need in real time while working, allowing them to perform their tasks efficiently and accurately.

[1500] Prompt Sentence Examples

[1501] Factory worker: "Show me the work instructions for the next process."

[1502] Server (prompt for input to generative AI model): "Search for the next process step. Display relevant information from the factory database."

[1503] It is expected that such a system will improve the efficiency of work within the factory and the quality of work.

[1504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1505] Step 1:

[1506] The user speaks into the smart glasses, saying, "Show me the work instructions for the next step." The input is voice data, which is captured by the smart glasses' microphone. The output is the captured voice data.

[1507] Step 2:

[1508] The smart glasses of the terminal means transmit the captured voice data to the server. The input is the captured voice data, and the output is the data transmission to the server.

[1509] Step 3:

[1510] The voice data received by the server is converted into text data using the Google Speech-to-Text API. The input is the voice data received by the server, and the output is text data. Specifically, the server sends the voice data to the API and receives text data as the conversion result.

[1511] Step 4:

[1512] The server searches an internal database for information related to the work instructions for the next process based on the text data. The input is the converted text data ("Show me the work instructions for the next process"), and the output is the related work instruction data. Specifically, the server generates a query and searches the database.

[1513] Step 5:

[1514] The server analyzes the work instruction data retrieved from the database and converts it into a format for visual display. The input is raw data retrieved from the database, and the output is formatted data that can be displayed visually (e.g., text, graphs, charts). Specifically, the server performs formatting processing on the data and converts it into a format that is easy for users to understand.

[1515] Step 6:

[1516] The server transmits formatted work instruction data to the smart glasses as the terminal means. The input is the formatted data formatted by the server, and the output is the data displayed on the smart glasses.

[1517] Step 7:

[1518] The smart glasses display the received work instruction data in the user's field of view. The input is formatted data received from the server, and the output is visual information displayed on the smart glasses' display. Specifically, the smart glasses render the received data on their display.

[1519] Through these processing steps, users can obtain the information they need in real time while working, allowing them to work efficiently and accurately.

[1520] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1521] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision according to the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by the server.

[1522] System configuration

[1523] The system consists of the following main components:

[1524] User: An individual or group who enters information on the whiteboard during a meeting.

[1525] Terminal: Consists of devices such as a camera, microphone, and smart whiteboard, which collects information entered by the user and sends it to the server.

[1526] Server: Processes and analyzes the received data, collects relevant information, and provides it to the user. It also uses an emotion engine to recognize and analyze the user's emotions.

[1527] Emotion engine: Recognizes the user's emotions from audio and video data, and changes the priority of information and feedback based on those emotions.

[1528] Program processing

[1529] 1. User Actions

[1530] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[1531] 2. Data Collection

[1532] The device captures what is written on the whiteboard and the audio of the conversation using a camera and microphone.

[1533] The captured data is sent to a server in real time.

[1534] 3. Data Processing

[1535] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[1536] At the same time, the voice data is converted into text data using voice recognition technology.

[1537] Text data of the "new product release date" is generated.

[1538] 4. Emotion recognition

[1539] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[1540] The emotion engine generates emotion data indicating whether the user is excited, calm, anxious, etc.

[1541] 5. Collection of relevant information

[1542] The server automatically collects past project data, documents from internal databases, external market trend reports, etc. related to the "new product release date" based on text data and sentiment data.

[1543] 6. Data Analysis and Presentation

[1544] The server analyzes and prioritizes the collected information based on emotional data, and then compiles it in the form of text, graphs, charts, and other information for use as reference during meetings.

[1545] If the user is feeling anxious, more detailed information and supplementary materials will be displayed preferentially.

[1546] 7. Real-time feedback

[1547] The compiled information is displayed on a whiteboard in real time, allowing users to check information that corresponds to their emotions.

[1548] Specific examples

[1549] Example 1: User excitement

[1550] "This is a very important release," an excited user said.

[1551] The device captures the audio and sends it to the server.

[1552] The server uses voice recognition and an emotion engine to recognize the user's state of excitement.

[1553] The server collects and displays a list of planned release dates and competitive information.

[1554] Example 2: User Concerns

[1555] The user stated in an anxious tone that he was "unsure of the release date."

[1556] The device captures the audio and sends it to the server.

[1557] The server uses voice recognition and an emotion engine to recognize the user's anxiety state.

[1558] The server prioritizes the collection and display of supplementary information such as "past success stories" and "risk management plans."

[1559] This system not only automatically collects and analyzes necessary information during meetings, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[1560] The processing flow will be explained below.

[1561] Step 1:

[1562] A user starts a meeting and writes an agenda on the whiteboard, for example, by handwriting "Determine the release date for a new product."

[1563] Step 2:

[1564] The device (camera and microphone) captures handwriting input on the whiteboard and audio during the meeting in real time, and this captured data is temporarily stored on the device.

[1565] Step 3:

[1566] The device transmits the captured data to the server in real time, including both handwritten image data and voice data.

[1567] Step 4:

[1568] The server converts the received handwritten image data into text data using optical character recognition (OCR) technology, which recognizes the handwritten phrase "Determine the release date of the new product" as text.

[1569] Step 5:

[1570] The server converts the received voice data into text data using speech recognition technology. For example, a statement such as "When should we release the new product?" is converted into the text "When should we release the new product?"

[1571] Step 6:

[1572] The server's emotion engine analyzes audio and video data to recognize the user's emotions and generates emotion data such as "excited," "anxious," or "calm."

[1573] Step 7:

[1574] The server analyzes the textual minutes and sentiment data, and automatically collects relevant information from internal databases and external sources, such as past project data and market trend reports related to "new product release dates."

[1575] Step 8:

[1576] The server analyzes the collected relevant information and prioritizes it based on emotional data: for example, if the user is excited, it will promptly present a release candidate date, but if the user is anxious, it will prioritize detailed risk management information.

[1577] Step 9:

[1578] The server sends the organized information to the terminal in real time and displays it visually on the whiteboard. Users can proceed with the meeting while checking the displayed supplementary information.

[1579] Step 10:

[1580] If a user adds a new comment or topic during the meeting, the device will again capture voice and handwritten data and send it to the server, which will then analyze the data again and collect and display the relevant information.

[1581] Step 11:

[1582] After the meeting, the server compiles all the data collected and analyzed during the meeting and automatically generates the final minutes, which include the meeting topics, comments, emotional data, and other relevant information collected during the meeting.

[1583] Step 12:

[1584] The server automatically distributes the generated final minutes to meeting participants, either by email or via internal systems, making them accessible to everyone.

[1585] Example 2

[1586] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1587] Creating effective minutes during meetings is an important challenge for many companies and organizations. However, traditional methods for creating minutes have made it difficult to collect information in real time and provide relevant information promptly. It has also been difficult to accurately grasp users' emotions during the meeting and provide information appropriate to those emotions. As a result, the efficiency and effectiveness of meetings are often compromised.

[1588] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1589] In this invention, the server includes means for recognizing user emotions from audio data and video data, means for changing information priority and feedback based on the emotion data, and means for analyzing and visually displaying collected related information, thereby enabling the creation of minutes and provision of related information in real time during a meeting according to the user's emotions.

[1590] A "user" is an individual or group who enters information onto the whiteboard during a meeting.

[1591] "Terminal means" refers to devices that collect information entered by users and transmit it to a server, including cameras, microphones, smart whiteboards, etc.

[1592] "Server" refers to the central processing unit that processes and analyzes collected information and collects and displays related information.

[1593] "Means for converting to text" refers to technology for converting received handwritten data or voice data into text data.

[1594] "Database" refers to a source of information for storing and managing related information, including internal project data and documents.

[1595] "External information sources" refers to information providers or information systems that include external market trend reports, competitive information, etc.

[1596] "Emotion engine" refers to technology for recognizing and analyzing user emotions from audio and video data.

[1597] "Emotion data" refers to data relating to a user's emotions generated by the emotion engine.

[1598] "Means for changing priorities and feedback" refers to a technique or method for setting the importance of information based on emotional data and adjusting the order and content of information provided to the user.

[1599] "Visual display means" refers to techniques and methods for presenting analyzed information to users in the form of graphs, charts, text, etc.

[1600] This invention combines an emotion engine with a system that generates meeting minutes in real time during a meeting and automatically adds related information, enabling flexible information provision based on the user's emotions. This system is realized by having the terminal collect information entered by the user, which is then processed and analyzed by a server. The hardware used includes a camera, microphone, and smart whiteboard, while the software includes optical character recognition (OCR) technology, voice recognition technology, and an emotion engine. Specifically, the system operates as follows:

[1601] First, a user starts a meeting and writes something on a whiteboard, such as "the release date of a new product." The device captures what is handwritten on the whiteboard with a camera and captures the audio of the conversation with a microphone. This captured data is sent to a server in real time. The server converts the received handwritten data into text data using optical character recognition (OCR) technology, and converts the audio data into text data using speech recognition technology. For example, Google Cloud Vision API or Google Cloud Speech-to-Text may be used.

[1602] Next, the server's emotion engine analyzes the audio and video data to recognize the user's emotions. The emotion engine uses, for example, the Microsoft Azure Emotion API. As a result of the analysis, emotional data is generated, indicating whether the user is excited, calm, or anxious. The server then collects and analyzes related information based on this emotional data and text data. Specifically, the server collects past project data, documents, external market trend reports, and other information from internal databases and external sources. This allows the server to prioritize information and change feedback based on the user's emotions.

[1603] For example, if a user is feeling anxious, the server will prioritize displaying supplementary information such as "past success stories" and "risk management plans." The collected information is analyzed and compiled in the form of text, graphs, charts, and other information, and displayed on the whiteboard in real time. This allows users to instantly check the information they need even during a meeting, making it possible to conduct the meeting efficiently and effectively.

[1604] Specific examples

[1605] Example 1: User excitement

[1606] A user excitedly says, "This release is super important!"

[1607] The device captures this speech with a microphone and sends it to the server.

[1608] The server recognizes the user's excitement state using voice recognition and an emotion engine.

[1609] The server automatically collects a list of planned release dates and competitive information and displays them on a whiteboard.

[1610] Example 2: User Concerns

[1611] The user expresses concern by saying, "I'm not sure about the release date."

[1612] The device captures this speech with a microphone and sends it to the server.

[1613] The server uses voice recognition and an emotion engine to recognize the anxiety state of the user.

[1614] The server prioritizes collecting supplementary information such as "past success stories" and "risk management plans" and displays it on the whiteboard.

[1615] Prompt Sentence Examples

[1616] Here is an example prompt:

[1617] If a user is excitedly talking in a release meeting:

[1618] "During a meeting, a user excitedly says, 'This release is so important.' Record the conversation and explain how the system will recognize the user's emotion and display relevant release dates and competitive information."

[1619] This not only automatically collects and analyzes necessary information during a meeting, but also flexibly adjusts according to the user's emotions, allowing users to conduct meetings efficiently and effectively, greatly simplifying the creation of meeting minutes and improving the quality of meetings.

[1620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1621] Step 1:

[1622] A user starts a meeting and writes "New Product Release Date" on the whiteboard.

[1623] Input: The user enters information by hand on the whiteboard.

[1624] Specific behavior: A user uses a smart whiteboard and writes "New product release date" with a pen.

[1625] Step 2:

[1626] The device uses a camera to capture what is handwritten on the whiteboard.

[1627] Input: Handwritten text on a whiteboard.

[1628] Specific operation: The device's camera captures the handwriting on the whiteboard as an image.

[1629] Step 3:

[1630] The device captures the audio of the conversation using a microphone.

[1631] Input: What people say during the meeting.

[1632] What it does: The microphone captures the audio of the conversation as audio data.

[1633] Step 4:

[1634] The terminal transmits the captured image data and audio data to the server.

[1635] Input: Captured image and audio data.

[1636] Output: Image and audio data sent to the server.

[1637] Specific operation: The terminal sends image data and audio data to the server via the network.

[1638] Step 5:

[1639] The server converts the received handwritten data into text data using optical character recognition (OCR) technology.

[1640] Input: Handwritten data (image data) on a whiteboard.

[1641] Output: Text data converted by optical character recognition (OCR).

[1642] Specific operation: The server's OCR software analyzes the handwritten data and converts it into text data called "New product release date."

[1643] Step 6:

[1644] The server converts the voice data into text data using voice recognition technology.

[1645] Input: Audio data.

[1646] Output: Text data converted by speech recognition.

[1647] Specific operation: The server's voice recognition software analyzes the voice data and converts what the user says into text data.

[1648] Step 7:

[1649] The server's emotion engine analyzes audio and video data to recognize the user's emotions.

[1650] Input: Audio and video data.

[1651] Output: User emotion data.

[1652] Specific operation: The emotion engine analyzes voice tone and facial expressions and generates data representing the user's emotional state (excitement, anxiety, etc.).

[1653] Step 8:

[1654] The server collects relevant information from databases and external information sources based on the text data and emotion data.

[1655] Input: Text data and emotion data.

[1656] Output: Relevant information (historical project data, external market trend reports, etc.).

[1657] Specific operation: The server searches and collects relevant information using internal databases and external APIs.

[1658] Step 9:

[1659] The server analyzes the collected information and prioritizes it based on emotional data.

[1660] Input: Collected relevant information and sentiment data.

[1661] Output: Prioritized information.

[1662] Specific operation: The server takes into account the emotional data and, for example, prioritizes detailed risk management plans when the user is in an anxious state.

[1663] Step 10:

[1664] The server uses a means for visually displaying the analyzed information to display it on a whiteboard.

[1665] Input: Prioritized information.

[1666] Output: Visually displayed information (text, graphs, charts, etc.).

[1667] Specific operation: The server organizes the information and displays it on the whiteboard in real time, so that the user can check it.

[1668] (Application example 2)

[1669] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1670] Conventional automatic meeting memo generation systems lack the ability to generate minutes in real time, as well as the ability to provide flexible information based on the user's emotions. Furthermore, when robot operators hold work instructions or troubleshooting meetings in factories, it is difficult to immediately obtain relevant information based on the meeting content, and information appropriate to the user's emotions is not provided. This hinders rapid problem-solving and efficient meeting management.

[1671] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recognizing a user's emotion from audio data and video data and adjusting the priority of information and feedback based on the emotion, means for analyzing and visually displaying the collected information, and means for collecting related information from an internal database and external information sources. This makes it possible to not only generate minutes of a meeting but also provide appropriate information according to the user's emotion.

[1672] A "user" is an individual or group who uses the system to provide information during a meeting via a whiteboard or voice input.

[1673] "Means for collecting information in real time" refers to technology and devices that instantly detect information or statements entered by users on the whiteboard and collect them as data.

[1674] "Terminal means" refers to devices or equipment that have the function of transmitting collected information to a server. Specifically, it includes cameras, microphones, network communication modules, etc.

[1675] "Server" means a computer system that processes and analyzes the information it receives and provides relevant information to the user.

[1676] "Means of converting to text" refers to the technology of converting voice data or handwritten data into character data using OCR and voice recognition technology.

[1677] "Means for collecting related information" refers to technology that searches for and acquires related data from internal databases and external information sources based on the textual content of meetings.

[1678] "Means for visually displaying" refers to a display device or interface for visually presenting the analysis results and related information to a user.

[1679] "Means for recognizing a user's emotions from audio and video data" refers to technology that determines a user's emotional state through voice tone and facial expression analysis.

[1680] "Means for adjusting information priority and feedback" refers to technology that dynamically changes the order and content of information provided depending on the recognized emotional state of the user.

[1681] System configuration

[1682] This invention is a system that collects and analyzes information in real time, provided by users during a meeting via a whiteboard or voice input. The main components of the system include:

[1683] 1. Terminal: Consists of devices such as a camera, microphone, and smart glasses, which collects information entered by the user in real time and sends it to the server.

[1684] 2. Server: Processes and analyzes the collected information, collects relevant information, and provides it to the user. It also recognizes the user's emotions from audio and video data, and adjusts the priority of information and feedback based on those emotions.

[1685] 3. Emotion engine: Analyzes voice tone and facial expressions to recognize the user's emotions.

[1686] 4. Visual display devices: Using display devices such as smart glasses, collected and analyzed information is presented to users in real time.

[1687] Program processing

[1688] Hardware and software used

[1689] Smart glasses: worn by the user and act as a display and audio interface.

[1690] Camera and microphone: Built into the smart glasses to capture audio and video.

[1691] Server: A computer system that processes data and performs sentiment analysis.

[1692] OCR technology: Optical character recognition technology is used to convert handwritten characters on a whiteboard into text data (a specific example is the Google Cloud Vision API).

[1693] Speech recognition engine: Technology that converts voice data into text data (a specific example is the Google Cloud Speech-to-Text API).

[1694] Emotion engine: Technology that recognizes emotions by analyzing voice tone and facial expressions (a specific example is the Microsoft Azure Emotion API).

[1695] Processing Details

[1696] 1. Data Collection:

[1697] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time.

[1698] The collected data is immediately sent to the server.

[1699] 2. Data Processing:

[1700] The server converts the received voice data into text using a voice recognition engine.

[1701] The received video data is converted into text data using OCR technology, with handwritten characters converted into text data.

[1702] Based on the converted text data, relevant information is collected from internal databases and external sources.

[1703] 3. Emotion recognition:

[1704] The server's emotion engine analyzes voice tone and facial expressions to recognize the user's emotions.

[1705] Adjust the priority and content of the information displayed based on the perceived emotion.

[1706] 4. Information provision:

[1707] -The analyzed information and related information are displayed in real time on a visual display device (smart glasses).

[1708] -Users can access the information they need hands-free.

[1709] Specific examples

[1710] Example 1: Operator excitement

[1711] If an operator excitedly says, "This machine's new function is revolutionary!", the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's excitement, and depending on the operator's excitement, collects and displays related information such as "detailed information on the new function" and "implementation procedures."

[1712] Example 2: Operator anxiety

[1713] If an operator says in an anxious tone, "I don't know how to solve this problem," the smart glasses capture the voice data and send it to the server. The server uses voice recognition and an emotion engine to recognize the operator's state of anxiety, and prioritizes the collection and display of "past troubleshooting cases" and "expert advice."

[1714] Example prompts for generative AI models

[1715] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[1716] Generate content: Generate text taking into account the following:

[1717] New feature details

[1718] Step-by-step implementation guide

[1719] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1720] Step 1: The device collects audio and video data in real time.

[1721] The device (a camera and microphone built into the smart glasses) captures audio and video data during the meeting in real time. The input is audio and video data, which are used directly in the next processing step, so no data processing is performed. The output is the captured raw audio and video data.

[1722] Step 2: The device sends the collected data to the server

[1723] The audio and video data captured by the device is sent to the server via the network. The input is the raw audio and video data, and the data is sent. The output is the audio and video data that has arrived at the server.

[1724] Step 3: The server converts the audio data into text data

[1725] The server converts the received voice data into text data using a voice recognition engine (for example, Google Cloud Speech-to-Text API). The input is voice data, and the data is processed using voice recognition technology to output text data.

[1726] Step 4: The server extracts handwritten characters from the video data and converts them into text data.

[1727] The server extracts handwritten characters from the video data received by the server using OCR technology (for example, Google Cloud Vision API) and converts them into text data. The input is video data, and the output is text data after processing using OCR technology.

[1728] Step 5: The server collects relevant information based on the text data.

[1729] The server searches and collects related information from internal databases and external information sources based on the generated text data. The input is text data, and the collected related information is output by processing the data through database searches and API requests.

[1730] Step 6: The server analyzes voice tone and facial expressions to recognize emotions

[1731] The server uses an emotion engine (for example, Microsoft Azure Emotion API) to analyze the audio and video data and recognize the user's emotions. The input is audio and video data, and emotion analysis technology processes the data to obtain emotional data as output.

[1732] Step 7: The server adjusts the priority of information based on the emotion data.

[1733] The server adjusts the priority and display content of collected related information based on the recognized emotion data. The input is emotion data and related information, and by processing and filtering the data, it obtains output information appropriate to the emotion.

[1734] Step 8: The server sends the information in real time to a visual display device

[1735] The server transmits the adjusted information to the visual display device (smart glasses) in real time. The input is the adjusted information, and by transmitting the data, the display information that the user can visually confirm is obtained as the output.

[1736] Example prompts for generative AI models

[1737] Prompt: The robot operator is testing a new feature and explaining the "test procedure for this feature." He seems excited.

[1738] Generate content: Generate text taking into account the following:

[1739] New feature details

[1740] Step-by-step implementation guide

[1741] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1742] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1743] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1744] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1745] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1746] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1747] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1748] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1749] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1750] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1751] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1752] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1753] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1754] 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.

[1755] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1756] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1757] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1758] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1759] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1760] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1761] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1762] The following is further disclosed regarding the above embodiment.

[1763] (Claim 1)

[1764] means for collecting information entered by users on a whiteboard during a meeting in real time;

[1765] a terminal means for transmitting the collected information to a server;

[1766] A means for converting the information received by the server into text;

[1767] A means of gathering relevant information from internal databases and external sources based on the textual information;

[1768] means for analyzing and visually displaying the collected relevant information;

[1769] A system including:

[1770] (Claim 2)

[1771] 2. The system of claim 1, wherein the system converts user utterances into text using voice recognition technology.

[1772] (Claim 3)

[1773] 10. The system of claim 1, wherein optical character recognition technology is utilized to convert handwritten characters on a whiteboard into text.

[1774] "Example 1"

[1775] (Claim 1)

[1776] means for collecting information entered by users into the display device in real time during the conference;

[1777] a terminal means for transmitting the collected information to a computer;

[1778] means for converting the received information into text by the computer;

[1779] A means for collecting relevant information from internal databases and external sources based on the textual information;

[1780] means for analyzing and visually displaying the collected relevant information;

[1781] A system including:

[1782] (Claim 2)

[1783] 2. The system of claim 1, wherein the system converts user utterances into text using voice recognition technology.

[1784] (Claim 3)

[1785] 10. The system of claim 1, wherein optical character recognition technology is utilized to convert handwritten characters on a display device into text.

[1786] "Application Example 1"

[1787] (Claim 1)

[1788] A means for collecting information input by a user in real time during a meeting or while working;

[1789] a terminal means for transmitting the collected information to a server;

[1790] A means for converting the information received by the server into text;

[1791] A means for collecting related information from databases and external sources based on the textual information;

[1792] means for analyzing and visually displaying the collected relevant information;

[1793] A means of presenting relevant information in real time to devices used within the factory;

[1794] A system including:

[1795] (Claim 2)

[1796] 2. The system of claim 1, wherein the system converts user utterances into text using voice recognition technology.

[1797] (Claim 3)

[1798] 10. The system of claim 1, wherein the system converts handwritten characters into text using optical character recognition technology.

[1799] "Example 2: Combining Emotion Engines"

[1800] (Claim 1)

[1801] means for collecting information entered by users on a whiteboard during a meeting in real time;

[1802] a terminal means for transmitting the collected information to a server;

[1803] A means for converting the information received by the server into text;

[1804] A means for collecting related information from databases and external sources based on the textual information;

[1805] means for analyzing and visually displaying the collected relevant information;

[1806] means for recognizing a user's emotion from audio data and video data;

[1807] A means of changing information priorities and feedback based on emotional data; and

[1808] A system including:

[1809] (Claim 2)

[1810] 2. The system of claim 1, wherein the system converts user utterances into text using voice recognition technology.

[1811] (Claim 3)

[1812] 10. The system of claim 1, wherein optical character recognition technology is utilized to convert handwritten characters on a whiteboard into text.

[1813] "Application example 2 when combining emotion engines"

[1814] (Claim 1)

[1815] means for collecting information entered by users on a whiteboard during a meeting in real time;

[1816] a terminal means for transmitting the collected information to a server;

[1817] A means for converting the information received by the server into text;

[1818] A means for collecting relevant information from internal databases and external sources based on the textual information;

[1819] means for analyzing and visually displaying the collected relevant information;

[1820] A means for recognizing a user's emotions from audio data and video data and adjusting information priority and feedback based on the emotions;

[1821] A system including:

[1822] (Claim 2)

[1823] 2. The system of claim 1, wherein the system converts user utterances into text using voice recognition technology.

[1824] (Claim 3)

[1825] 10. The system of claim 1, wherein optical character recognition technology is utilized to convert handwritten characters on a whiteboard into text. [Explanation of symbols]

[1826] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting information entered by users on a whiteboard during a meeting in real time; a terminal means for transmitting the collected information to a server; A means for converting the information received by the server into text; A means of gathering relevant information from internal databases and external sources based on the textual information; means for analyzing and visually displaying the collected relevant information; A system including:

2. 10. The system of claim 1, wherein the system converts user utterances into text using voice recognition technology.

3. The system of claim 1, wherein optical character recognition technology is utilized to convert handwritten characters on a whiteboard into text.

Images