System

Abstract

A system is provided.SOLUTION: This system is provided with a means for collecting the data of famous persons, a means for classifying the collected data for each specialized field, a means for retrieving an optimal expert according to a theme based on the classified data, a means for inviting the expert selected based on the retrieved result to an online conference, and a means for feeding back the opinion of the expert in real time during the conference.SELECTED DRAWING: Figure 1

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] Previously, there was a lack of efficient ways to collect and classify the knowledge and experience of experts and specialists, and quickly search for and assign the most suitable experts to meetings when needed. As a result, it took a long time to find an expert suited to the topic of a meeting, and it was difficult to obtain appropriate feedback in real time. Furthermore, the management and classification of collected data was largely manual and inefficient. This created problems that hindered fast and accurate decision-making. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. A system is configured including means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for a particular topic based on the classified data, means for inviting the expert selected based on the search results to an online conference, and means for providing real-time feedback on the expert's opinion during the conference. This system makes it possible to quickly search for the most suitable expert when needed, invite them to an online conference, and also receive real-time feedback during the conference. This allows for faster and more efficient decision-making.

[0006] A "master" is someone who has expertise and extensive experience in a particular field and is widely recognized in that field.

[0007] "Data collection methods" refers to the technologies and processes used to automatically obtain the required data from the internet and other sources and store it in a database.

[0008] "Discipline classification means" refers to the techniques and processes that use specific algorithms and methods to organize and classify collected data by discipline.

[0009] "Means for searching for the most suitable expert based on the topic" refers to the technology or process for identifying the most suitable expert from the aforementioned classification data based on the input topic or keywords.

[0010] "Means of inviting participants to online meetings" refers to the technology and process of sending meeting invitations to selected experts using Zoom or other online meeting platforms.

[0011] "Means of real-time feedback" refers to technologies and processes that record what participants say during a meeting in real time and provide feedback to other participants as needed. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

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

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

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

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0027] 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.

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

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] The present invention provides a system that collects and classifies expert data, invites experts to online conferences, and provides real-time feedback. This system is realized by a server, a terminal, and a user who play specific roles.

[0034] System program processing

[0035] Master data collection

[0036] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to collect their biographies, papers, books, interviews, and other information, and stores it in a database.

[0037] Data classification

[0038] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[0039] Enter a topic and search for experts

[0040] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[0041] Selection and invitation of experts

[0042] The user selects the most suitable expert from the list of experts displayed on the device. For example, the user clicks on a person selected as an expert related to "new materials." The server then sends an invitation to the selected expert using an online conference platform such as Zoom.

[0043] Real-time feedback

[0044] During meetings, the device uses voice recognition technology to convert experts' comments into text in real time and provide feedback to other participants, such as specific suggestions for the manufacturing process of new materials.

[0045] Specific examples

[0046] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0047] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0048] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0049] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0050] 4. The server sends a Zoom meeting invitation to the selected scientists.

[0051] 5. During the meeting, the device uses voice recognition technology to convert the scientist's speech into text and provide real-time feedback to other participants.

[0052] This system makes it possible to efficiently select the most suitable experts, hold meetings quickly, and obtain useful information in real time, which will enable efficient discussion and improvement of manufacturing methods for industrial products that make the most of the properties of new materials.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The server runs a web scraping program to collect data on the masters, specifically, to retrieve data such as their careers, papers, books, and interview articles from a set URL.

[0056] Step 2:

[0057] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes the information for each expert.

[0058] Step 3:

[0059] The server runs natural language processing (NLP) algorithms to categorize the stored data by subject matter, using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[0060] Step 4:

[0061] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[0062] Step 5:

[0063] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[0064] Step 6:

[0065] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[0066] Step 7:

[0067] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[0068] Step 8:

[0069] The server sends a Zoom meeting invitation to the selected expert. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected expert.

[0070] Step 9:

[0071] After the meeting begins, the device records the expert's remarks in real time and provides feedback, converting them into text using voice recognition technology and displaying it to other participants.

[0072] Each of these processing steps allows for efficient collection and classification of expert data, inviting the most appropriate experts to the meeting, and providing real-time feedback.

[0073] Example 1

[0074] 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."

[0075] The problem that this invention aims to solve is to build a system that efficiently collects information on experts with specialized knowledge and appropriately classifies that data, allowing users to quickly search for the most suitable experts based on a specific topic, invite them to an online conference, and provide them with real-time expert feedback during the conference.

[0076] 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.

[0077] In this invention, the server includes means for acquiring information on experts, means for classifying the acquired information by area of ​​expertise, means for searching for the most suitable expert for the topic based on the classified information, means for inviting the expert selected based on the search results to an online conference, and means for providing feedback of the expert's comments during the conference in real time. This makes it possible to quickly and efficiently search for and invite experts and provide useful information in real time during the conference.

[0078] A "master" is an individual who has advanced expertise and skills and is highly regarded in their field.

[0079] "Information" refers to data related to the masters' expertise and achievements, such as their biographies, papers, books, and interviews.

[0080] "Acquisition" refers to the act of collecting information about celebrities through web scraping or other means.

[0081] "Classification" refers to the use of natural language processing algorithms to organize and separate collected information into specialized fields.

[0082] A "theme" refers to a specific topic or issue that a user sets when communicating or discussing.

[0083] An "expert" is an individual who has in-depth knowledge and skills related to a particular topic and has a proven track record in that field.

[0084] "Search" refers to the act of locating appropriate expert information from a database based on a topic.

[0085] An "online meeting" refers to a meeting that uses audio and video over the Internet, including video conferencing systems.

[0086] "Remarks" refers to comments and opinions provided by experts during the meeting.

[0087] The present invention is a system that collects and classifies expert information, invites experts to online conferences, and provides real-time feedback. Specifically, it is realized by specific roles of a server, a terminal, and a user.

[0088] Obtaining information about masters

[0089] The server runs a program to obtain information about the masters. This uses web scraping technology. Specifically, it uses the Python libraries BeautifulSoup and Scrapy to collect information such as the masters' biographies, papers, books, and interviews. The collected information is converted into JSON format and stored in a database (for example, PostgreSQL or MongoDB).

[0090] Information classification

[0091] The server uses natural language processing (NLP) algorithms to categorize the information it retrieves by area of ​​expertise. Specifically, it uses the natural language processing library SpaCy to analyze text and categorize the information based on the expert's area of ​​expertise. This allows the server to organize the information in the database into categories such as business, technology, medicine, and energy.

[0092] Enter a topic and search for experts

[0093] The user inputs the topic of the meeting into a dedicated device (e.g., a laptop or tablet). For example, the topic may be "improving the manufacturing process for new materials." The server analyzes the topic entered by the user and searches for relevant experts in the database. This search uses a full-text search engine (e.g., Elasticsearch).

[0094] Selection and invitation of experts

[0095] The user selects the most suitable expert from the list of experts displayed on the device. For example, they click on a prominent scientist related to "new materials." The server then sends an invitation to the selected expert using an online conferencing platform such as Zoom. Specifically, a Python library (e.g., zoomus) is used to call the Zoom API and automatically generate and send a meeting invitation. The invitation includes the meeting title, date and time, and a Zoom link.

[0096] Real-time feedback

[0097] The device uses speech recognition technology to convert speech into text during meetings in real time. Specifically, it uses APIs such as Google Speech-to-Text and IBM Watson Speech to Text to convert speech into text. The converted speech is then shared with other participants in real time.

[0098] Specific examples

[0099] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0100] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0101] 2. The server uses Elasticsearch to search the database for relevant experts (e.g., a particular scientist or engineer).

[0102] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0103] 4. The server sends a Zoom meeting invitation to the selected scientists using the zoomus library.

[0104] 5. During the meeting, the device uses the Google Speech-to-Text API to transcribe the scientists' speech in real time and provide real-time feedback to other participants.

[0105] Prompt Sentence Examples

[0106] Below are some example prompts to input to the generative AI model:

[0107] "Please explain the process for gathering information on who is a leading figure in the business technology field and finding relevant experts."

[0108] "How can I invite an expert on improving the manufacturing process of new materials to an online meeting?"

[0109] "Please explain how the system works, which converts experts' comments in online meetings into text in real time and provides feedback."

[0110] The above is an embodiment of the invention.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] The server runs a web scraping program to collect information about the experts. Specifically, it uses the Python libraries BeautifulSoup and Scrapy. It uses source URLs for the experts' biographies, papers, books, interviews, etc. on the internet as input, and converts the collected information into JSON format and stores it in a database as output. Specifically, the server sets up a daily batch job to automatically perform web scraping at 2:00 AM. If an error occurs, it records an error log and notifies the operations staff.

[0114] Step 2:

[0115] The server uses a natural language processing (NLP) algorithm to classify the collected information into specialized fields. Specifically, it uses the natural language processing library SpaCy. It uses JSON-formatted information stored in a database as input and generates data classified by specialized field (business, technology, medicine, energy, etc.) as output. Specifically, the server uses a GPU to run the SpaCy model and quickly process large amounts of data.

[0116] Step 3:

[0117] The user inputs a theme into a dedicated terminal. For example, the theme is "improving the manufacturing process for new materials." The user inputs the theme into the terminal as input, and the theme is sent to the server as output. Specifically, the user inputs the theme into the input form and clicks the send button, causing the terminal to send the theme data to the server.

[0118] Step 4:

[0119] The server analyzes the topic entered by the user and searches the database for the most suitable experts. Specifically, it performs a full-text search using Elasticsearch. It uses the topic submitted by the user and the classified data stored in the database as input, and generates a list of relevant experts as output. Specifically, the server generates an Elasticsearch query and returns the search results for experts related to the "new material" in the database.

[0120] Step 5:

[0121] The user selects the most suitable expert from the list of experts displayed on the terminal. For example, by clicking "famous scientists related to new materials." The information of the expert selected from the expert list is used as input, and the selected expert is notified to the server as output. Specifically, when the user selects the most suitable expert from the list and clicks the selection button, the terminal sends the selection information to the server.

[0122] Step 6:

[0123] The server sends invitations to the selected experts using an online conferencing platform such as Zoom. Specifically, it calls the Zoom API using the Python library zoomus. The information of the expert selected by the user and the details of the meeting are used as input, and an invitation is generated as output and sent to the expert. Specifically, the server connects to the Zoom API and automatically generates and sends a meeting invitation for the specified date and time.

[0124] Step 7:

[0125] The device converts the expert's speech during the meeting into text in real time using speech recognition technology. Specifically, it uses the Google Speech-to-Text and IBM Watson Speech to Text APIs. It uses the audio data from the meeting as input and generates the text of the speech as output. Specifically, the device establishes a connection to the speech recognition API and sends the audio data via streaming. The recognized text is displayed in real time on the front end using WebSocket.

[0126] The above are the specific processing steps of the program of this system.

[0127] (Application example 1)

[0128] 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."

[0129] In today's cybersecurity environment, it is extremely important for companies to take prompt and appropriate security measures. However, there are limited ways to utilize the knowledge and experience of security experts in real time, making it difficult to respond quickly to specific threats. There is also a lack of ways to quickly share expert opinions during meetings in a way that all participants can understand immediately. This can lead to delays in decision-making and discrepancies in information.

[0130] 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.

[0131] In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the topic based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion in real time during the conference, means for classifying the collected data into categories such as firewall, encryption technology, and endpoint protection, means for converting the expert's remarks during the conference into text using voice recognition technology, and means for sharing the converted text with other participants in real time, thereby enabling prompt and appropriate security measures.

[0132] "Master data" is information about people who have high levels of expertise and experience in their respective fields.

[0133] "Collection methods" are the mechanisms by which the necessary data is obtained and stored from the internet and other sources.

[0134] A "classification method" is an algorithm or method that separates collected data into categories based on specific criteria.

[0135] A "specialized field" is an academic or industrial field that requires specific knowledge or skills.

[0136] Searching is the process of finding information that matches specific criteria from a database or other source.

[0137] "Means for inviting participants to an online meeting" refers to communication methods or software that allow specific participants to join a meeting via the Internet.

[0138] "Feedback means" refers to a system or method for conveying expert opinions and comments to other participants in real time.

[0139] A "firewall" is a defensive system or software that ensures network security.

[0140] "Encryption technology" is a technology that converts information into an obfuscated form in order to protect the information.

[0141] "Endpoint protection" refers to software and hardware technologies that protect devices on a network from security threats.

[0142] "Speech recognition technology" is a technology for converting speech into text.

[0143] "Means for converting to text" refers to a method for converting voice data into text information and storing or displaying it.

[0144] A "sharing method" is the process of providing specific data or information to other users or systems.

[0145] The system configuration for implementing the present invention is realized by servers, terminals, and users taking on specific roles.

[0146] 1. Master data collection:

[0147] The server uses web scraping technology to collect data such as the biographies, papers, books, and interviews of celebrities from the Internet and stores it in a database using software such as Beautiful Soup and Scrapy.

[0148] 2. Data Classification:

[0149] The server uses natural language processing (NLP) techniques to classify the collected data into categories such as firewalls, encryption technologies, and endpoint protection, using NLP libraries such as Spacy and NLTK.

[0150] 3. Enter your topic and search for experts:

[0151] Users input a topic into a dedicated terminal, for example, "responding to ransomware attacks." Based on this input, the server searches the database for relevant experts. Matching based on the search query is also performed using NLP.

[0152] 4. Expert selection and invitation:

[0153] The user selects the most suitable expert from a list of experts displayed on the device. For example, they can select an expert in ransomware countermeasures. After selection, the server sends an invitation to the selected expert via Zoom or a dedicated security conference platform.

[0154] 5. Real-time feedback:

[0155] During the meeting, the server uses speech recognition technology to convert the expert's speech into text in real time and share it with other participants. This process uses speech recognition technologies such as Google Cloud Speech-to-Text and IBM Watson. The converted speech is immediately fed back to other participants in real time.

[0156] Examples:

[0157] A user inputs a topic such as, "A specific company has been attacked by ransomware and its files have been encrypted. Recovery and countermeasures are urgently needed. We need expert opinions on whether we should comply with the attacker's demands and how to recover the data." Based on this input, the server searches for relevant experts and suggests well-known experts who are experts in ransomware countermeasures. A meeting is then held, and the experts' comments are converted into text in real time using voice recognition technology and instantly shared with other participants.

[0158] Example prompt sentence:

[0159] “Please provide a list of security experts for the following incident.

[0160] Incident details: Ransomware attack

[0161] Details: A company has been hit by a ransomware attack and their files have been encrypted. Recovery and countermeasures are urgently needed. We need expert advice on whether to comply with the attacker's demands and how to recover the data.

[0162] Run the program that generates a list of suitable experts from the system's database.

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Step 1:

[0165] The server collects data on the masters. It uses web scraping technologies such as Beautiful Soup and Scrapy to retrieve the masters' biographies, papers, books, interviews, etc. from the Internet. It uses a list of URLs from multiple websites as input, and stores the masters' information as structured data in a database as output.

[0166] Step 2:

[0167] The server categorizes the collected data by area of ​​expertise. The server uses natural language processing (NLP) techniques such as Spacy or NLTK to categorize the collected data into categories such as firewalls, encryption technologies, and endpoint protection. It uses the collected data as input and obtains data organized by category as output.

[0168] Step 3:

[0169] The user inputs a theme into a dedicated terminal. The user inputs a specific theme using the terminal's input interface. For example, the user might input "responding to ransomware attacks." The theme keyword is used as input, and the keyword is sent to the server as output.

[0170] Step 4:

[0171] The server searches for relevant experts based on a topic. The server uses NLP techniques to search for experts related to a topic from a database. It uses the topic entered by the user as input and generates a list of relevant experts as output.

[0172] Step 5:

[0173] The user selects the most suitable expert from the list of experts displayed on the terminal. The user checks the list and presses the select button to select. The list of experts is used as input, and the information of the selected expert is sent to the server as output.

[0174] Step 6:

[0175] The server sends an online meeting invitation to the selected expert. The server sends the invitation using Zoom or a dedicated secure conferencing platform. The server uses the contact information of the selected expert as input and confirms that the invitation has been sent as output.

[0176] Step 7:

[0177] During the meeting, the server uses speech recognition technology to convert the experts' speech into text. The server uses speech recognition services such as Google Cloud Speech-to-Text and IBM Watson. The server uses the speech data from the meeting as input and obtains the text of the speech as output.

[0178] Step 8:

[0179] The server shares the textual utterances with other participants in real time. The server displays the textual utterances on the other participants' devices in real time. The server uses the textual utterance data as input and provides feedback to the participants' devices as output.

[0180] 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.

[0181] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[0182] System program processing

[0183] Master data collection

[0184] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to obtain data such as their career histories, papers, books, and interview articles, and stores it in a database.

[0185] Data classification

[0186] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[0187] Enter a topic and search for experts

[0188] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[0189] Selection and invitation of experts

[0190] The user selects the most suitable expert from the list of experts displayed on the device, for example by clicking on "famous scientists in new materials." The server then sends an invitation to the selected expert via an online conference platform such as Zoom.

[0191] Real-time feedback and sentiment analysis

[0192] The device converts the expert's speech into text using speech recognition technology in real time during the meeting and provides feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in real time during the meeting and sends the results to the server.

[0193] Specific examples

[0194] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0195] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0196] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0197] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0198] 4. The server sends a Zoom meeting invitation to the selected scientists.

[0199] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0200] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0201] This system can efficiently collect and classify expert data, invite the most suitable experts to the meeting, and analyze and provide feedback on the user's emotional state in real time, which will help meetings proceed smoothly and enable more effective decision-making.

[0202] The processing flow will be explained below.

[0203] Step 1:

[0204] The server runs a web scraping program to collect data on the masters. Specifically, it automatically retrieves data about the masters, such as their biographies, papers, books, and interview articles, from specific URLs and stores them in a structured format in a database.

[0205] Step 2:

[0206] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes and stores it by expert.

[0207] Step 3:

[0208] The server uses natural language processing (NLP) algorithms to categorize the stored data by subject area, specifically by using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[0209] Step 4:

[0210] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[0211] Step 5:

[0212] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[0213] Step 6:

[0214] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[0215] Step 7:

[0216] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[0217] Step 8:

[0218] The server sends a Zoom meeting invitation to the selected expert. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected expert.

[0219] Step 9:

[0220] Once the meeting has started, the device will convert the speech of the expert into text in real time using speech recognition technology and provide feedback to other participants. Specifically, the device converts the speech data into text and automatically highlights and displays important points.

[0221] Step 10:

[0222] The emotion engine analyzes users' emotions in real time during meetings, using facial recognition technology and voice analysis to extract emotional data from users' facial expressions, tone of voice, and choice of words.

[0223] Step 11:

[0224] The server receives the emotion data from the emotion engine and provides feedback according to the user's emotional state. For example, if the user is feeling stressed, the server sends a notification to the terminal to adjust the progress of the meeting.

[0225] Step 12:

[0226] The terminal receives notifications from the server and adjusts the progress of the meeting. Specifically, it displays a summary of questions to the expert and provides support to help the user understand the content.

[0227] Example 2

[0228] 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."

[0229] Conventional online conference systems make it difficult to efficiently search for and invite experts with specialized knowledge and provide real-time feedback during the meeting. Furthermore, there are no systems that recognize participants' emotional states during the meeting and optimize the progress of the meeting. As a result, the meeting may not proceed smoothly and decision-making may be delayed.

[0230] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the theme based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion during the conference in real time, and means for analyzing the emotional state of participants during the conference in real time and optimizing the progress of the conference based on the results. This makes it possible to efficiently search for and invite experts and optimize the progress based on feedback and emotions during the conference.

[0231] "Master data" refers to all information about individuals with specialized knowledge and experience, including their career history, papers, books, interviews, etc.

[0232] "Collection methods" refers to the methods used to obtain data from the internet or other sources and store it in a database.

[0233] "Means of classification by field of expertise" refers to a method of dividing collected data into specific fields of expertise or categories using natural language processing algorithms, etc.

[0234] "Means for searching for the most suitable expert for a topic" refers to a method for extracting relevant experts from a database based on an input topic.

[0235] "Means for inviting selected experts to an online conference" refers to a method of sending an invitation to an online conference to selected experts and requesting their participation.

[0236] "Means of providing real-time feedback of expert opinions during a meeting" refers to a method in which what an expert says during a meeting is converted into text using voice recognition technology and provided as feedback to other participants.

[0237] "Means for analyzing participants' emotional states in real time during a meeting" refers to a method using technology, such as an emotion recognition algorithm, to analyze participants' facial expressions and voices during a meeting and determine their emotional states.

[0238] "Means for optimizing meeting progress" refers to methods for adjusting the schedule and content of meetings based on the results of sentiment analysis to help participants understand the content.

[0239] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[0240] First, the server collects data about the masters from the Internet. Specifically, it uses web scraping technology. For example, it uses Python's BeautifulSoup or Scrapy to collect data such as the master's biography, papers, books, and interview articles, and temporarily stores that data in a cache such as Redis. This collected data is finally stored in a MySQL database.

[0241] The server then categorizes the collected data using natural language processing (NLP) algorithms, using services such as Google Cloud Natural Language API to organize the data into specialties such as business, technology, medicine, and energy. This results in the database containing data already categorized by speciality.

[0242] The user inputs a topic using a dedicated terminal. For example, they input the topic "improving the manufacturing process for new materials." Based on this input, the server searches the Elasticsearch database for relevant experts. As a result of the search, a list of relevant experts is displayed on the user's terminal.

[0243] The user selects the most suitable expert from the list. For example, they can select "famous scientists in new materials." Once the selection is complete, the server will invite the expert to an online meeting using the Zoom API or Google Calendar API. This will send a meeting invitation to the selected expert.

[0244] During the meeting, the device converts the expert's speech into text in real time using speech recognition technology (e.g., Google Speech-to-Text API) and provides it as feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in the meeting in real time. This emotion analysis is performed using the Microsoft Azure Emotion API. The analysis results are sent to the server, which then sends notifications to adjust the progress of the meeting based on the emotion data.

[0245] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0246] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0247] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0248] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0249] 4. The server sends an invitation to the selected scientists to attend the online meeting.

[0250] 5. Once the meeting begins, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0251] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0252] Examples of prompt sentences include:

[0253] "Find experts on manufacturing process improvements for new materials."

[0254] "Use the real-time feedback feature to analyze what experts say during meetings and provide feedback to users."

[0255] In this way, the system can efficiently collect and classify expert data, identify and invite the most suitable experts, and optimize the progress based on feedback and emotions during the meeting.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1: Collecting data on experts

[0258] The server runs a program that collects data on masters from the Internet. The input here is a list of URLs for the websites to be collected. Specifically, the server performs web scraping using BeautifulSoup and Scrapy to obtain information such as the master's career history, papers, books, and interview articles. The obtained data is temporarily stored in a Redis cache and then stored in a MySQL database.

[0259] Input: List of website URLs

[0260] Output: Data such as the master's biography, papers, books, interviews, etc.

[0261] Specific behavior:

[0262] The server performs web scraping based on the specified URL list.

[0263] The retrieved data is temporarily stored in the Redis cache.

[0264] Migrate the stored data to a MySQL database.

[0265] Step 2: Classify the data

[0266] The server classifies the collected data using a natural language processing (NLP) algorithm. The input here is expert data stored in a MySQL database. Specifically, the server analyzes the data using the Google Cloud Natural Language API and classifies the data into specialized fields such as business, technology, medicine, and energy based on the analysis results. The classified data is then stored back in the database.

[0267] Input: Master data stored in a MySQL database

[0268] Output: Classified virtuoso data

[0269] Specific behavior:

[0270] The server analyzes the data using NLP algorithms.

[0271] Categorize data by discipline.

[0272] Update the classified data into a MySQL database.

[0273] Step 3: Enter the theme

[0274] The user inputs a topic using a dedicated terminal. The input here is the topic the user wants to discuss. In concrete terms, the user inputs the topic into the input field of the terminal, and it is sent to the server. For example, the topic "improving the manufacturing process for new materials" is input.

[0275] Input: The theme entered by the user

[0276] Output: The theme sent to the server

[0277] Specific behavior:

[0278] The user enters a theme into an input field on the device.

[0279] The entered theme is sent to the server.

[0280] Step 4: Find an expert

[0281] The server searches for relevant experts from the Elasticsearch database based on the received topic. The input here is the topic sent by the user. Specifically, the server generates an Elasticsearch query and searches the database. As a search result, it generates a list of relevant experts and displays it on the user's device.

[0282] Input: User-submitted theme

[0283] Output: A list of relevant experts

[0284] Specific behavior:

[0285] The server generates an Elasticsearch query.

[0286] Search databases and identify relevant experts.

[0287] A list of experts is displayed on the user's terminal.

[0288] Step 5: Selecting an expert

[0289] The user selects the most suitable expert from the list of experts displayed on the terminal. The input here is the displayed list of experts. In concrete terms, the user clicks on the desired expert from the list. Information on the selected expert is sent to the server.

[0290] Input: List of displayed experts

[0291] Output: Information about selected experts

[0292] Specific behavior:

[0293] The user clicks on the desired expert from the list.

[0294] The information of the selected expert is sent to the server.

[0295] Step 6: Send invitations

[0296] The server sends an online meeting invitation to the selected expert. The input here is the information of the selected expert. Specifically, the server generates a meeting invitation using the Zoom API or Google Calendar API and sends it to the expert's email address.

[0297] Input: Selected expert information

[0298] Output: Online meeting invitation

[0299] Specific behavior:

[0300] The server generates a meeting invitation using the Zoom API or Google Calendar API.

[0301] Send the invitation to the expert's email.

[0302] Step 7: Real-time feedback

[0303] The device converts the expert's speech into text in real time during the meeting and provides feedback to other participants. The input here is the expert's real-time speech. Specifically, it converts the speech into text using the Google Speech-to-Text API and displays the text to participants.

[0304] Input: Real-time expert comments

[0305] Output: Translated utterances

[0306] Specific behavior:

[0307] The expert's speech is captured as audio data.

[0308] Converts speech to text using the Google Speech-to-Text API.

[0309] Display the transcribed text to the participants.

[0310] Step 8: Sentiment analysis

[0311] The emotion engine analyzes the emotional state of each user during a meeting in real time. The input here is video and audio data from the meeting. Specifically, it analyzes the data using the Microsoft Azure Emotion API and sends the analysis results of the emotional state to the server.

[0312] Input: Video and audio data during the meeting

[0313] Output: Emotional state analysis result

[0314] Specific behavior:

[0315] Capture video and audio data.

[0316] Analyze the data using the Microsoft Azure Emotion API.

[0317] The analysis results are sent to the server.

[0318] Step 9: Coordinate the meeting

[0319] Based on information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. The input here is the analysis result of the emotional state. Specifically, the server analyzes the analysis result and takes action to adjust the progress of the meeting as necessary (e.g., summarizing comments or suggesting a break).

[0320] Input: Emotional state analysis result

[0321] Output: Notification of meeting progress adjustment

[0322] Specific behavior:

[0323] Receive and analyze the results of the emotional state analysis.

[0324] Take action to coordinate meeting progress and send notifications.

[0325] (Application example 2)

[0326] 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."

[0327] The current problem with factory production lines is the lack of means to incorporate expert knowledge in real time and monitor and optimize the emotional state of workers and operators. In particular, when improving processing methods for new materials and production processes, real-time feedback from experts and management of workers' emotional states are required.

[0328] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0329] In this invention, the server includes a means for collecting data on experts, a means for classifying the collected data by field of expertise, and a means for searching for the most suitable expert for the theme based on the classified data. This makes it possible to utilize the knowledge of experts on factory production lines and provide optimal feedback and process adjustments while monitoring the emotional states of workers and operators in real time.

[0330] "Masterpiece data" refers to information such as the careers, achievements, writings, and interview articles of experts with outstanding knowledge and experience in a particular field.

[0331] "Classification" refers to the process of organizing and structuring collected data according to specific disciplines or categories.

[0332] A "topic" refers to the topic or topic that a user wants to cover in a particular meeting or consultation.

[0333] An "expert" is an individual who has advanced knowledge or skills in a particular area of ​​expertise.

[0334] An "online meeting" refers to a virtual meeting space where multiple participants can interact in real time via the Internet.

[0335] "Feedback" refers to the process of communicating information such as advice, opinions, and evaluations provided by experts to participants in real time.

[0336] An "artificial intelligence engine" refers to a software or hardware system for performing advanced computational tasks such as data analysis, emotion recognition, and natural language processing.

[0337] "Sentiment analysis" refers to the process of determining and analyzing the emotional state of meeting participants based on their facial expressions, tone of voice, and choice of words.

[0338] "Optimization" refers to the adjustment or improvement of a system or process to maximize its performance for specific purposes or conditions.

[0339] MODE FOR CARRYING OUT THE INVENTION

[0340] This invention relates to a system for real-time production supervision on factory production lines. The system incorporates expert knowledge, monitors the emotional states of workers and robot operators, and performs a series of processes including expert data collection, classification, expert search, online conferencing, and emotion analysis to provide optimal feedback and process adjustments.

[0341] Server Roles

[0342] The server collects data on the experts from the internet. Specifically, it uses web scraping technology to retrieve information such as their careers, achievements, papers, and interviews, and stores it in a database. This data is then categorized by field of expertise using natural language processing (NLP) algorithms. For example, it can be categorized into categories such as "business," "technology," "medical care," and "energy."

[0343] Next, based on the topic entered by the user into the dedicated terminal (e.g., "processing methods for new materials"), the server searches the database for relevant experts. Once the most suitable expert is selected, the server sends the selected expert an invitation to an online meeting. This is done using the Zoom API or Microsoft Teams API.

[0344] Device Role

[0345] The device receives the topic input by the user and sends it to the server. Once the conference begins, the device converts the expert's remarks into text in real time using speech recognition technology and provides feedback to other participants.

[0346] The terminal is also equipped with an emotion analysis engine that monitors the emotional state of workers and operators in real time. This emotion engine uses, for example, the DeepFace library to recognize facial expressions. It is also capable of voice analysis, determining the emotional state of participants from their speaking style and tone of voice. The collected emotion data is sent to a server and used to optimize the progress of the meeting.

[0347] User Roles

[0348] The user inputs the topic of the meeting into a dedicated terminal. For example, by entering a topic such as "processing methods for new materials," the process of searching for the most suitable expert related to that topic begins. The user then selects the most suitable expert from a list of experts displayed on the terminal. During the meeting, the user receives feedback provided in real time and adjusts the progress based on the results of sentiment analysis.

[0349] Examples of concrete examples and prompts

[0350] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0351] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0352] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0353] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on a new material.

[0354] 4. The server sends a Zoom meeting invitation to the selected expert.

[0355] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0356] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0357] An example of a prompt is as follows:

[0358] "Collect and store expert data. Use web scraping technology to retrieve expert profiles, careers, papers, and interviews, and store them in a database."

[0359] This system makes it possible to efficiently collect and classify expert data, invite the most suitable experts to meetings, and analyze and provide feedback on the user's emotional state in real time, resulting in smoother meetings and more effective decision-making.

[0360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0361] Step 1:

[0362] The server collects data on the masters. Based on the list of website URLs specified as input, it uses web scraping technology to obtain information such as the masters' careers, achievements, papers, and interview articles. The obtained data is stored in a database.

[0363] Step 2:

[0364] The server categorizes the collected data using natural language processing (NLP) algorithms. It takes as input the unclassified data in the database and categorizes each data into a specialized field, such as business, technology, medicine, or energy. The output is a classified dataset.

[0365] Step 3:

[0366] The user inputs the topic of the meeting into a dedicated terminal. The input is text information (e.g., "Processing method for new materials") that the user types into the terminal. The terminal then sends this input to the server.

[0367] Step 4:

[0368] The server searches the database for relevant experts based on the input topic. The input is the topic text submitted by the user, and the output is a list of relevant experts. The server searches the classification data in the database and selects the most suitable expert.

[0369] Step 5:

[0370] The user selects the most suitable expert from the list of experts displayed on the terminal. The input is the list of experts, and the expert information selected by the user is output. The selected expert is sent to the server.

[0371] Step 6:

[0372] The server sends online meeting invitations to the selected experts. The input is the experts' contact information and meeting details, and the output is the sent invitation. This uses the Zoom API or Microsoft Teams API.

[0373] Step 7:

[0374] After the conference begins, the device uses speech recognition technology to convert the expert's speech into text in real time. The input is the expert's speech data during the conference, and the output is the converted speech data. This data is immediately fed back to the other participants.

[0375] Step 8:

[0376] The device's sentiment analysis engine monitors the emotional state of participants in real time during a meeting. The input is the participants' video feeds and audio data, and the output is data representing their emotional state. This sentiment analysis is performed using libraries such as DeepFace.

[0377] Step 9:

[0378] The server optimizes the progress of the meeting based on the results of the sentiment analysis. The input is emotional state data, and the output is progress adjustments or notifications. For example, it may summarize and display the expert's comments or take actions to adjust the pace of the meeting. As a result, users can efficiently manage the progress of the meeting.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] [Second embodiment]

[0383] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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."

[0395] The present invention provides a system that collects and classifies expert data, invites experts to online conferences, and provides real-time feedback. This system is realized by a server, a terminal, and a user who play specific roles.

[0396] System program processing

[0397] Master data collection

[0398] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to collect their biographies, papers, books, interviews, and other information, and stores it in a database.

[0399] Data classification

[0400] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[0401] Enter a topic and search for experts

[0402] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[0403] Selection and invitation of experts

[0404] The user selects the most suitable expert from the list of experts displayed on the device. For example, the user clicks on a person selected as an expert related to "new materials." The server then sends an invitation to the selected expert using an online conference platform such as Zoom.

[0405] Real-time feedback

[0406] During meetings, the device uses voice recognition technology to convert experts' comments into text in real time and provide feedback to other participants, such as specific suggestions for the manufacturing process of new materials.

[0407] Specific examples

[0408] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0409] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0410] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0411] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0412] 4. The server sends a Zoom meeting invitation to the selected scientists.

[0413] 5. During the meeting, the device uses voice recognition technology to convert the scientist's speech into text and provide real-time feedback to other participants.

[0414] This system makes it possible to efficiently select the most suitable experts, hold meetings quickly, and obtain useful information in real time, which will enable efficient discussion and improvement of manufacturing methods for industrial products that make the most of the properties of new materials.

[0415] The processing flow will be explained below.

[0416] Step 1:

[0417] The server runs a web scraping program to collect data on the masters, specifically, to retrieve data such as their careers, papers, books, and interview articles from a set URL.

[0418] Step 2:

[0419] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes the information for each expert.

[0420] Step 3:

[0421] The server runs natural language processing (NLP) algorithms to categorize the stored data by subject matter, using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[0422] Step 4:

[0423] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[0424] Step 5:

[0425] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[0426] Step 6:

[0427] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[0428] Step 7:

[0429] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[0430] Step 8:

[0431] The server sends a Zoom meeting invitation to the selected expert. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected expert.

[0432] Step 9:

[0433] After the meeting begins, the device records the expert's remarks in real time and provides feedback, converting them into text using voice recognition technology and displaying it to other participants.

[0434] Each of these processing steps allows for efficient collection and classification of expert data, inviting the most appropriate experts to the meeting, and providing real-time feedback.

[0435] Example 1

[0436] 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."

[0437] The problem that this invention aims to solve is to build a system that efficiently collects information on experts with specialized knowledge and appropriately classifies that data, allowing users to quickly search for the most suitable experts based on a specific topic, invite them to an online conference, and provide them with real-time expert feedback during the conference.

[0438] 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.

[0439] In this invention, the server includes means for acquiring information on experts, means for classifying the acquired information by area of ​​expertise, means for searching for the most suitable expert for the topic based on the classified information, means for inviting the expert selected based on the search results to an online conference, and means for providing feedback of the expert's comments during the conference in real time. This makes it possible to quickly and efficiently search for and invite experts and provide useful information in real time during the conference.

[0440] A "master" is an individual who has advanced expertise and skills and is highly regarded in their field.

[0441] "Information" refers to data related to the masters' expertise and achievements, such as their biographies, papers, books, and interviews.

[0442] "Acquisition" refers to the act of collecting information about celebrities through web scraping or other means.

[0443] "Classification" refers to the use of natural language processing algorithms to organize and separate collected information into specialized fields.

[0444] A "theme" refers to a specific topic or issue that a user sets when communicating or discussing.

[0445] An "expert" is an individual who has in-depth knowledge and skills related to a particular topic and has a proven track record in that field.

[0446] "Search" refers to the act of locating appropriate expert information from a database based on a topic.

[0447] An "online meeting" refers to a meeting that uses audio and video over the Internet, including video conferencing systems.

[0448] "Remarks" refers to comments and opinions provided by experts during the meeting.

[0449] The present invention is a system that collects and classifies expert information, invites experts to online conferences, and provides real-time feedback. Specifically, it is realized by specific roles of a server, a terminal, and a user.

[0450] Obtaining information about masters

[0451] The server runs a program to obtain information about the masters. This uses web scraping technology. Specifically, it uses the Python libraries BeautifulSoup and Scrapy to collect information such as the masters' biographies, papers, books, and interviews. The collected information is converted into JSON format and stored in a database (for example, PostgreSQL or MongoDB).

[0452] Information classification

[0453] The server uses natural language processing (NLP) algorithms to categorize the information it retrieves by area of ​​expertise. Specifically, it uses the natural language processing library SpaCy to analyze text and categorize the information based on the expert's area of ​​expertise. This allows the server to organize the information in the database into categories such as business, technology, medicine, and energy.

[0454] Enter a topic and search for experts

[0455] The user inputs the topic of the meeting into a dedicated device (e.g., a laptop or tablet). For example, the topic may be "improving the manufacturing process for new materials." The server analyzes the topic entered by the user and searches for relevant experts in the database. This search uses a full-text search engine (e.g., Elasticsearch).

[0456] Selection and invitation of experts

[0457] The user selects the most suitable expert from the list of experts displayed on the device. For example, they click on a prominent scientist related to "new materials." The server then sends an invitation to the selected expert using an online conferencing platform such as Zoom. Specifically, a Python library (e.g., zoomus) is used to call the Zoom API and automatically generate and send a meeting invitation. The invitation includes the meeting title, date and time, and a Zoom link.

[0458] Real-time feedback

[0459] The device uses speech recognition technology to convert speech into text during meetings in real time. Specifically, it uses APIs such as Google Speech-to-Text and IBM Watson Speech to Text to convert speech into text. The converted speech is then shared with other participants in real time.

[0460] Specific examples

[0461] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0462] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0463] 2. The server uses Elasticsearch to search the database for relevant experts (e.g., a particular scientist or engineer).

[0464] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0465] 4. The server sends a Zoom meeting invitation to the selected scientists using the zoomus library.

[0466] 5. During the meeting, the device uses the Google Speech-to-Text API to transcribe the scientists' speech in real time and provide real-time feedback to other participants.

[0467] Prompt Sentence Examples

[0468] Below are some example prompts to input to the generative AI model:

[0469] "Please explain the process for gathering information on who is a leading figure in the business technology field and finding relevant experts."

[0470] "How can I invite an expert on improving the manufacturing process of new materials to an online meeting?"

[0471] "Please explain how the system works, which converts experts' comments in online meetings into text in real time and provides feedback."

[0472] The above is an embodiment of the invention.

[0473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0474] Step 1:

[0475] The server runs a web scraping program to collect information about the experts. Specifically, it uses the Python libraries BeautifulSoup and Scrapy. It uses source URLs for the experts' biographies, papers, books, interviews, etc. on the internet as input, and converts the collected information into JSON format and stores it in a database as output. Specifically, the server sets up a daily batch job to automatically perform web scraping at 2:00 AM. If an error occurs, it records an error log and notifies the operations staff.

[0476] Step 2:

[0477] The server uses a natural language processing (NLP) algorithm to classify the collected information into specialized fields. Specifically, it uses the natural language processing library SpaCy. It uses JSON-formatted information stored in a database as input and generates data classified by specialized field (business, technology, medicine, energy, etc.) as output. Specifically, the server uses a GPU to run the SpaCy model and quickly process large amounts of data.

[0478] Step 3:

[0479] The user inputs a theme into a dedicated terminal. For example, the theme is "improving the manufacturing process for new materials." The user inputs the theme into the terminal as input, and the theme is sent to the server as output. Specifically, the user inputs the theme into the input form and clicks the send button, causing the terminal to send the theme data to the server.

[0480] Step 4:

[0481] The server analyzes the topic entered by the user and searches the database for the most suitable experts. Specifically, it performs a full-text search using Elasticsearch. It uses the topic submitted by the user and the classified data stored in the database as input, and generates a list of relevant experts as output. Specifically, the server generates an Elasticsearch query and returns the search results for experts related to the "new material" in the database.

[0482] Step 5:

[0483] The user selects the most suitable expert from the list of experts displayed on the terminal. For example, by clicking "famous scientists related to new materials." The information of the expert selected from the expert list is used as input, and the selected expert is notified to the server as output. Specifically, when the user selects the most suitable expert from the list and clicks the selection button, the terminal sends the selection information to the server.

[0484] Step 6:

[0485] The server sends invitations to the selected experts using an online conferencing platform such as Zoom. Specifically, it calls the Zoom API using the Python library zoomus. The information of the expert selected by the user and the details of the meeting are used as input, and an invitation is generated as output and sent to the expert. Specifically, the server connects to the Zoom API and automatically generates and sends a meeting invitation for the specified date and time.

[0486] Step 7:

[0487] The device converts the expert's speech during the meeting into text in real time using speech recognition technology. Specifically, it uses the Google Speech-to-Text and IBM Watson Speech to Text APIs. It uses the audio data from the meeting as input and generates the text of the speech as output. Specifically, the device establishes a connection to the speech recognition API and sends the audio data via streaming. The recognized text is displayed in real time on the front end using WebSocket.

[0488] The above are the specific processing steps of the program of this system.

[0489] (Application example 1)

[0490] 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."

[0491] In today's cybersecurity environment, it is extremely important for companies to take prompt and appropriate security measures. However, there are limited ways to utilize the knowledge and experience of security experts in real time, making it difficult to respond quickly to specific threats. There is also a lack of ways to quickly share expert opinions during meetings in a way that all participants can understand immediately. This can lead to delays in decision-making and discrepancies in information.

[0492] 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.

[0493] In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the topic based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion in real time during the conference, means for classifying the collected data into categories such as firewall, encryption technology, and endpoint protection, means for converting the expert's remarks during the conference into text using voice recognition technology, and means for sharing the converted text with other participants in real time, thereby enabling prompt and appropriate security measures.

[0494] "Master data" is information about people who have high levels of expertise and experience in their respective fields.

[0495] "Collection methods" are the mechanisms by which the necessary data is obtained and stored from the internet and other sources.

[0496] A "classification method" is an algorithm or method that separates collected data into categories based on specific criteria.

[0497] A "specialized field" is an academic or industrial field that requires specific knowledge or skills.

[0498] Searching is the process of finding information that matches specific criteria from a database or other source.

[0499] "Means for inviting participants to an online meeting" refers to communication methods or software that allow specific participants to join a meeting via the Internet.

[0500] "Feedback means" refers to a system or method for conveying expert opinions and comments to other participants in real time.

[0501] A "firewall" is a defensive system or software that ensures network security.

[0502] "Encryption technology" is a technology that converts information into an obfuscated form in order to protect the information.

[0503] "Endpoint protection" refers to software and hardware technologies that protect devices on a network from security threats.

[0504] "Speech recognition technology" is a technology for converting speech into text.

[0505] "Means for converting to text" refers to a method for converting voice data into text information and storing or displaying it.

[0506] A "sharing method" is the process of providing specific data or information to other users or systems.

[0507] The system configuration for implementing the present invention is realized by servers, terminals, and users taking on specific roles.

[0508] 1. Master data collection:

[0509] The server uses web scraping technology to collect data such as the biographies, papers, books, and interviews of celebrities from the Internet and stores it in a database using software such as Beautiful Soup and Scrapy.

[0510] 2. Data Classification:

[0511] The server uses natural language processing (NLP) techniques to classify the collected data into categories such as firewalls, encryption technologies, and endpoint protection, using NLP libraries such as Spacy and NLTK.

[0512] 3. Enter your topic and search for experts:

[0513] Users input a topic into a dedicated terminal, for example, "responding to ransomware attacks." Based on this input, the server searches the database for relevant experts. Matching based on the search query is also performed using NLP.

[0514] 4. Expert selection and invitation:

[0515] The user selects the most suitable expert from a list of experts displayed on the device. For example, they can select an expert in ransomware countermeasures. After selection, the server sends an invitation to the selected expert via Zoom or a dedicated security conference platform.

[0516] 5. Real-time feedback:

[0517] During the meeting, the server uses speech recognition technology to convert the expert's speech into text in real time and share it with other participants. This process uses speech recognition technologies such as Google Cloud Speech-to-Text and IBM Watson. The converted speech is immediately fed back to other participants in real time.

[0518] Examples:

[0519] A user inputs a topic such as, "A specific company has been attacked by ransomware and its files have been encrypted. Recovery and countermeasures are urgently needed. We need expert opinions on whether we should comply with the attacker's demands and how to recover the data." Based on this input, the server searches for relevant experts and suggests well-known experts who are experts in ransomware countermeasures. A meeting is then held, and the experts' comments are converted into text in real time using voice recognition technology and instantly shared with other participants.

[0520] Example prompt sentence:

[0521] “Please provide a list of security experts for the following incident.

[0522] Incident details: Ransomware attack

[0523] Details: A company has been hit by a ransomware attack and their files have been encrypted. Recovery and countermeasures are urgently needed. We need expert advice on whether to comply with the attacker's demands and how to recover the data.

[0524] Run the program that generates a list of suitable experts from the system's database.

[0525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0526] Step 1:

[0527] The server collects data on the masters. It uses web scraping technologies such as Beautiful Soup and Scrapy to retrieve the masters' biographies, papers, books, interviews, etc. from the Internet. It uses a list of URLs from multiple websites as input, and stores the masters' information as structured data in a database as output.

[0528] Step 2:

[0529] The server categorizes the collected data by area of ​​expertise. The server uses natural language processing (NLP) techniques such as Spacy or NLTK to categorize the collected data into categories such as firewalls, encryption technologies, and endpoint protection. It uses the collected data as input and obtains data organized by category as output.

[0530] Step 3:

[0531] The user inputs a theme into a dedicated terminal. The user inputs a specific theme using the terminal's input interface. For example, the user might input "responding to ransomware attacks." The theme keyword is used as input, and the keyword is sent to the server as output.

[0532] Step 4:

[0533] The server searches for relevant experts based on a topic. The server uses NLP techniques to search for experts related to a topic from a database. It uses the topic entered by the user as input and generates a list of relevant experts as output.

[0534] Step 5:

[0535] The user selects the most suitable expert from the list of experts displayed on the terminal. The user checks the list and presses the select button to select. The list of experts is used as input, and the information of the selected expert is sent to the server as output.

[0536] Step 6:

[0537] The server sends an online meeting invitation to the selected expert. The server sends the invitation using Zoom or a dedicated secure conferencing platform. The server uses the contact information of the selected expert as input and confirms that the invitation has been sent as output.

[0538] Step 7:

[0539] During the meeting, the server uses speech recognition technology to convert the experts' speech into text. The server uses speech recognition services such as Google Cloud Speech-to-Text and IBM Watson. The server uses the speech data from the meeting as input and obtains the text of the speech as output.

[0540] Step 8:

[0541] The server shares the textual utterances with other participants in real time. The server displays the textual utterances on the other participants' devices in real time. The server uses the textual utterance data as input and provides feedback to the participants' devices as output.

[0542] 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.

[0543] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[0544] System program processing

[0545] Master data collection

[0546] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to obtain data such as their career histories, papers, books, and interview articles, and stores it in a database.

[0547] Data classification

[0548] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[0549] Enter a topic and search for experts

[0550] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[0551] Selection and invitation of experts

[0552] The user selects the most suitable expert from the list of experts displayed on the device, for example by clicking on "famous scientists in new materials." The server then sends an invitation to the selected expert via an online conference platform such as Zoom.

[0553] Real-time feedback and sentiment analysis

[0554] The device converts the expert's speech into text using speech recognition technology in real time during the meeting and provides feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in real time during the meeting and sends the results to the server.

[0555] Specific examples

[0556] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0557] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0558] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0559] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0560] 4. The server sends a Zoom meeting invitation to the selected scientists.

[0561] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0562] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0563] This system can efficiently collect and classify expert data, invite the most suitable experts to the meeting, and analyze and provide feedback on the user's emotional state in real time, which will help meetings proceed smoothly and enable more effective decision-making.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] The server runs a web scraping program to collect data on the masters. Specifically, it automatically retrieves data about the masters, such as their biographies, papers, books, and interview articles, from specific URLs and stores them in a structured format in a database.

[0567] Step 2:

[0568] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes and stores it by expert.

[0569] Step 3:

[0570] The server uses natural language processing (NLP) algorithms to categorize the stored data by subject area, specifically by using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[0571] Step 4:

[0572] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[0573] Step 5:

[0574] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[0575] Step 6:

[0576] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[0577] Step 7:

[0578] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[0579] Step 8:

[0580] The server sends a Zoom meeting invitation to the selected expert. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected expert.

[0581] Step 9:

[0582] Once the meeting has started, the device will convert the speech of the expert into text in real time using speech recognition technology and provide feedback to other participants. Specifically, the device converts the speech data into text and automatically highlights and displays important points.

[0583] Step 10:

[0584] The emotion engine analyzes users' emotions in real time during meetings, using facial recognition technology and voice analysis to extract emotional data from users' facial expressions, tone of voice, and choice of words.

[0585] Step 11:

[0586] The server receives the emotion data from the emotion engine and provides feedback according to the user's emotional state. For example, if the user is feeling stressed, the server sends a notification to the terminal to adjust the progress of the meeting.

[0587] Step 12:

[0588] The terminal receives notifications from the server and adjusts the progress of the meeting. Specifically, it displays a summary of questions to the expert and provides support to help the user understand the content.

[0589] Example 2

[0590] 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."

[0591] Conventional online conference systems make it difficult to efficiently search for and invite experts with specialized knowledge and provide real-time feedback during the meeting. Furthermore, there are no systems that recognize participants' emotional states during the meeting and optimize the progress of the meeting. As a result, the meeting may not proceed smoothly and decision-making may be delayed.

[0592] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the theme based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion during the conference in real time, and means for analyzing the emotional state of participants during the conference in real time and optimizing the progress of the conference based on the results. This makes it possible to efficiently search for and invite experts and optimize the progress based on feedback and emotions during the conference.

[0593] "Master data" refers to all information about individuals with specialized knowledge and experience, including their career history, papers, books, interviews, etc.

[0594] "Collection methods" refers to the methods used to obtain data from the internet or other sources and store it in a database.

[0595] "Means of classification by field of expertise" refers to a method of dividing collected data into specific fields of expertise or categories using natural language processing algorithms, etc.

[0596] "Means for searching for the most suitable expert for a topic" refers to a method for extracting relevant experts from a database based on an input topic.

[0597] "Means for inviting selected experts to an online conference" refers to a method of sending an invitation to an online conference to selected experts and requesting their participation.

[0598] "Means of providing real-time feedback of expert opinions during a meeting" refers to a method in which what an expert says during a meeting is converted into text using voice recognition technology and provided as feedback to other participants.

[0599] "Means for analyzing participants' emotional states in real time during a meeting" refers to a method using technology, such as an emotion recognition algorithm, to analyze participants' facial expressions and voices during a meeting and determine their emotional states.

[0600] "Means for optimizing meeting progress" refers to methods for adjusting the schedule and content of meetings based on the results of sentiment analysis to help participants understand the content.

[0601] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[0602] First, the server collects data about the masters from the Internet. Specifically, it uses web scraping technology. For example, it uses Python's BeautifulSoup or Scrapy to collect data such as the master's biography, papers, books, and interview articles, and temporarily stores that data in a cache such as Redis. This collected data is finally stored in a MySQL database.

[0603] The server then categorizes the collected data using natural language processing (NLP) algorithms, using services such as Google Cloud Natural Language API to organize the data into specialties such as business, technology, medicine, and energy. This results in the database containing data already categorized by speciality.

[0604] The user inputs a topic using a dedicated terminal. For example, they input the topic "improving the manufacturing process for new materials." Based on this input, the server searches the Elasticsearch database for relevant experts. As a result of the search, a list of relevant experts is displayed on the user's terminal.

[0605] The user selects the most suitable expert from the list. For example, they can select "famous scientists in new materials." Once the selection is complete, the server will invite the expert to an online meeting using the Zoom API or Google Calendar API. This will send a meeting invitation to the selected expert.

[0606] During the meeting, the device converts the expert's speech into text in real time using speech recognition technology (e.g., Google Speech-to-Text API) and provides it as feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in the meeting in real time. This emotion analysis is performed using the Microsoft Azure Emotion API. The analysis results are sent to the server, which then sends notifications to adjust the progress of the meeting based on the emotion data.

[0607] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0608] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0609] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0610] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0611] 4. The server sends an invitation to the selected scientists to attend the online meeting.

[0612] 5. Once the meeting begins, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0613] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0614] Examples of prompt sentences include:

[0615] "Find experts on manufacturing process improvements for new materials."

[0616] "Use the real-time feedback feature to analyze what experts say during meetings and provide feedback to users."

[0617] In this way, the system can efficiently collect and classify expert data, identify and invite the most suitable experts, and optimize the progress based on feedback and emotions during the meeting.

[0618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0619] Step 1: Collecting data on experts

[0620] The server runs a program that collects data on masters from the Internet. The input here is a list of URLs for the websites to be collected. Specifically, the server performs web scraping using BeautifulSoup and Scrapy to obtain information such as the master's career history, papers, books, and interview articles. The obtained data is temporarily stored in a Redis cache and then stored in a MySQL database.

[0621] Input: List of website URLs

[0622] Output: Data such as the master's biography, papers, books, interviews, etc.

[0623] Specific behavior:

[0624] The server performs web scraping based on the specified URL list.

[0625] The retrieved data is temporarily stored in the Redis cache.

[0626] Migrate the stored data to a MySQL database.

[0627] Step 2: Classify the data

[0628] The server classifies the collected data using a natural language processing (NLP) algorithm. The input here is expert data stored in a MySQL database. Specifically, the server analyzes the data using the Google Cloud Natural Language API and classifies the data into specialized fields such as business, technology, medicine, and energy based on the analysis results. The classified data is then stored back in the database.

[0629] Input: Master data stored in a MySQL database

[0630] Output: Classified virtuoso data

[0631] Specific behavior:

[0632] The server analyzes the data using NLP algorithms.

[0633] Categorize data by discipline.

[0634] Update the classified data into a MySQL database.

[0635] Step 3: Enter the theme

[0636] The user inputs a topic using a dedicated terminal. The input here is the topic the user wants to discuss. In concrete terms, the user inputs the topic into the input field of the terminal, and it is sent to the server. For example, the topic "improving the manufacturing process for new materials" is input.

[0637] Input: The theme entered by the user

[0638] Output: The theme sent to the server

[0639] Specific behavior:

[0640] The user enters a theme into an input field on the device.

[0641] The entered theme is sent to the server.

[0642] Step 4: Find an expert

[0643] The server searches for relevant experts from the Elasticsearch database based on the received topic. The input here is the topic sent by the user. Specifically, the server generates an Elasticsearch query and searches the database. As a search result, it generates a list of relevant experts and displays it on the user's device.

[0644] Input: User-submitted theme

[0645] Output: A list of relevant experts

[0646] Specific behavior:

[0647] The server generates an Elasticsearch query.

[0648] Search databases and identify relevant experts.

[0649] A list of experts is displayed on the user's terminal.

[0650] Step 5: Selecting an expert

[0651] The user selects the most suitable expert from the list of experts displayed on the terminal. The input here is the displayed list of experts. In concrete terms, the user clicks on the desired expert from the list. Information on the selected expert is sent to the server.

[0652] Input: List of displayed experts

[0653] Output: Information about selected experts

[0654] Specific behavior:

[0655] The user clicks on the desired expert from the list.

[0656] The information of the selected expert is sent to the server.

[0657] Step 6: Send invitations

[0658] The server sends an online meeting invitation to the selected expert. The input here is the information of the selected expert. Specifically, the server generates a meeting invitation using the Zoom API or Google Calendar API and sends it to the expert's email address.

[0659] Input: Selected expert information

[0660] Output: Online meeting invitation

[0661] Specific behavior:

[0662] The server generates a meeting invitation using the Zoom API or Google Calendar API.

[0663] Send the invitation to the expert's email.

[0664] Step 7: Real-time feedback

[0665] The device converts the expert's speech into text in real time during the meeting and provides feedback to other participants. The input here is the expert's real-time speech. Specifically, it converts the speech into text using the Google Speech-to-Text API and displays the text to participants.

[0666] Input: Real-time expert comments

[0667] Output: Translated utterances

[0668] Specific behavior:

[0669] The expert's speech is captured as audio data.

[0670] Converts speech to text using the Google Speech-to-Text API.

[0671] Display the transcribed text to the participants.

[0672] Step 8: Sentiment analysis

[0673] The emotion engine analyzes the emotional state of each user during a meeting in real time. The input here is video and audio data from the meeting. Specifically, it analyzes the data using the Microsoft Azure Emotion API and sends the analysis results of the emotional state to the server.

[0674] Input: Video and audio data during the meeting

[0675] Output: Emotional state analysis result

[0676] Specific behavior:

[0677] Capture video and audio data.

[0678] Analyze the data using the Microsoft Azure Emotion API.

[0679] The analysis results are sent to the server.

[0680] Step 9: Coordinate the meeting

[0681] Based on information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. The input here is the analysis result of the emotional state. Specifically, the server analyzes the analysis result and takes action to adjust the progress of the meeting as necessary (e.g., summarizing comments or suggesting a break).

[0682] Input: Emotional state analysis result

[0683] Output: Notification of meeting progress adjustment

[0684] Specific behavior:

[0685] Receive and analyze the results of the emotional state analysis.

[0686] Take action to coordinate meeting progress and send notifications.

[0687] (Application example 2)

[0688] 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."

[0689] The current problem with factory production lines is the lack of means to incorporate expert knowledge in real time and monitor and optimize the emotional state of workers and operators. In particular, when improving processing methods for new materials and production processes, real-time feedback from experts and management of workers' emotional states are required.

[0690] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0691] In this invention, the server includes a means for collecting data on experts, a means for classifying the collected data by field of expertise, and a means for searching for the most suitable expert for the theme based on the classified data. This makes it possible to utilize the knowledge of experts on factory production lines and provide optimal feedback and process adjustments while monitoring the emotional states of workers and operators in real time.

[0692] "Masterpiece data" refers to information such as the careers, achievements, writings, and interview articles of experts with outstanding knowledge and experience in a particular field.

[0693] "Classification" refers to the process of organizing and structuring collected data according to specific disciplines or categories.

[0694] A "topic" refers to the topic or topic that a user wants to cover in a particular meeting or consultation.

[0695] An "expert" is an individual who has advanced knowledge or skills in a particular area of ​​expertise.

[0696] An "online meeting" refers to a virtual meeting space where multiple participants can interact in real time via the Internet.

[0697] "Feedback" refers to the process of communicating information such as advice, opinions, and evaluations provided by experts to participants in real time.

[0698] An "artificial intelligence engine" refers to a software or hardware system for performing advanced computational tasks such as data analysis, emotion recognition, and natural language processing.

[0699] "Sentiment analysis" refers to the process of determining and analyzing the emotional state of meeting participants based on their facial expressions, tone of voice, and choice of words.

[0700] "Optimization" refers to the adjustment or improvement of a system or process to maximize its performance for specific purposes or conditions.

[0701] MODE FOR CARRYING OUT THE INVENTION

[0702] This invention relates to a system for real-time production supervision on factory production lines. The system incorporates expert knowledge, monitors the emotional states of workers and robot operators, and performs a series of processes including expert data collection, classification, expert search, online conferencing, and emotion analysis to provide optimal feedback and process adjustments.

[0703] Server Roles

[0704] The server collects data on the experts from the internet. Specifically, it uses web scraping technology to retrieve information such as their careers, achievements, papers, and interviews, and stores it in a database. This data is then categorized by field of expertise using natural language processing (NLP) algorithms. For example, it can be categorized into categories such as "business," "technology," "medical care," and "energy."

[0705] Next, based on the topic entered by the user into the dedicated terminal (e.g., "processing methods for new materials"), the server searches the database for relevant experts. Once the most suitable expert is selected, the server sends the selected expert an invitation to an online meeting. This is done using the Zoom API or Microsoft Teams API.

[0706] Device Role

[0707] The device receives the topic input by the user and sends it to the server. Once the conference begins, the device converts the expert's remarks into text in real time using speech recognition technology and provides feedback to other participants.

[0708] The terminal is also equipped with an emotion analysis engine that monitors the emotional state of workers and operators in real time. This emotion engine uses, for example, the DeepFace library to recognize facial expressions. It is also capable of voice analysis, determining the emotional state of participants from their speaking style and tone of voice. The collected emotion data is sent to a server and used to optimize the progress of the meeting.

[0709] User Roles

[0710] The user inputs the topic of the meeting into a dedicated terminal. For example, by entering a topic such as "processing methods for new materials," the process of searching for the most suitable expert related to that topic begins. The user then selects the most suitable expert from a list of experts displayed on the terminal. During the meeting, the user receives feedback provided in real time and adjusts the progress based on the results of sentiment analysis.

[0711] Examples of concrete examples and prompts

[0712] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0713] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0714] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0715] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on a new material.

[0716] 4. The server sends a Zoom meeting invitation to the selected expert.

[0717] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0718] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0719] An example of a prompt is as follows:

[0720] "Collect and store expert data. Use web scraping technology to retrieve expert profiles, careers, papers, and interviews, and store them in a database."

[0721] This system makes it possible to efficiently collect and classify expert data, invite the most suitable experts to meetings, and analyze and provide feedback on the user's emotional state in real time, resulting in smoother meetings and more effective decision-making.

[0722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0723] Step 1:

[0724] The server collects data on the masters. Based on the list of website URLs specified as input, it uses web scraping technology to obtain information such as the masters' careers, achievements, papers, and interview articles. The obtained data is stored in a database.

[0725] Step 2:

[0726] The server categorizes the collected data using natural language processing (NLP) algorithms. It takes as input the unclassified data in the database and categorizes each data into a specialized field, such as business, technology, medicine, or energy. The output is a classified dataset.

[0727] Step 3:

[0728] The user inputs the topic of the meeting into a dedicated terminal. The input is text information (e.g., "Processing method for new materials") that the user types into the terminal. The terminal then sends this input to the server.

[0729] Step 4:

[0730] The server searches the database for relevant experts based on the input topic. The input is the topic text submitted by the user, and the output is a list of relevant experts. The server searches the classification data in the database and selects the most suitable expert.

[0731] Step 5:

[0732] The user selects the most suitable expert from the list of experts displayed on the terminal. The input is the list of experts, and the expert information selected by the user is output. The selected expert is sent to the server.

[0733] Step 6:

[0734] The server sends online meeting invitations to the selected experts. The input is the experts' contact information and meeting details, and the output is the sent invitation. This uses the Zoom API or Microsoft Teams API.

[0735] Step 7:

[0736] After the conference begins, the device uses speech recognition technology to convert the expert's speech into text in real time. The input is the expert's speech data during the conference, and the output is the converted speech data. This data is immediately fed back to the other participants.

[0737] Step 8:

[0738] The device's sentiment analysis engine monitors the emotional state of participants in real time during a meeting. The input is the participants' video feeds and audio data, and the output is data representing their emotional state. This sentiment analysis is performed using libraries such as DeepFace.

[0739] Step 9:

[0740] The server optimizes the progress of the meeting based on the results of the sentiment analysis. The input is emotional state data, and the output is progress adjustments or notifications. For example, it may summarize and display the expert's comments or take actions to adjust the pace of the meeting. As a result, users can efficiently manage the progress of the meeting.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] [Third embodiment]

[0745] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0746] 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.

[0747] 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).

[0748] 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.

[0749] 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.

[0750] 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).

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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."

[0757] The present invention provides a system that collects and classifies expert data, invites experts to online conferences, and provides real-time feedback. This system is realized by a server, a terminal, and a user who play specific roles.

[0758] System program processing

[0759] Master data collection

[0760] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to collect their biographies, papers, books, interviews, and other information, and stores it in a database.

[0761] Data classification

[0762] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[0763] Enter a topic and search for experts

[0764] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[0765] Selection and invitation of experts

[0766] The user selects the most suitable expert from the list of experts displayed on the device. For example, the user clicks on a person selected as an expert related to "new materials." The server then sends an invitation to the selected expert using an online conference platform such as Zoom.

[0767] Real-time feedback

[0768] The device uses voice recognition technology to convert experts' comments into text in real time during the meeting and provide feedback to other participants, such as specific suggestions for the manufacturing process of a new material.

[0769] Specific examples

[0770] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0771] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0772] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0773] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0774] 4. The server sends a Zoom meeting invitation to the selected scientists.

[0775] 5. During the meeting, the device uses voice recognition technology to convert the scientist's speech into text and provide real-time feedback to other participants.

[0776] This system makes it possible to efficiently select the most suitable experts, hold meetings quickly, and obtain useful information in real time, which will enable efficient discussion and improvement of manufacturing methods for industrial products that make the most of the properties of new materials.

[0777] The processing flow will be explained below.

[0778] Step 1:

[0779] The server runs a web scraping program to collect data on the masters, specifically, to retrieve data such as their careers, papers, books, and interview articles from the configured URLs.

[0780] Step 2:

[0781] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes the information for each expert.

[0782] Step 3:

[0783] The server runs natural language processing (NLP) algorithms to categorize the stored data by subject matter, using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[0784] Step 4:

[0785] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[0786] Step 5:

[0787] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[0788] Step 6:

[0789] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[0790] Step 7:

[0791] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[0792] Step 8:

[0793] The server sends a Zoom meeting invitation to the selected experts. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected experts.

[0794] Step 9:

[0795] After the meeting begins, the device records the expert's remarks in real time and provides feedback, converting them into text using voice recognition technology and displaying it to other participants.

[0796] Each of these processing steps allows for efficient collection and classification of expert data, inviting the most appropriate experts to the meeting, and providing real-time feedback.

[0797] Example 1

[0798] 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."

[0799] The problem that this invention aims to solve is to build a system that efficiently collects information on experts with specialized knowledge and appropriately classifies that data, allowing users to quickly search for the most suitable experts based on a specific topic, invite them to an online conference, and provide them with real-time expert feedback during the conference.

[0800] 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.

[0801] In this invention, the server includes means for acquiring information on experts, means for classifying the acquired information by area of ​​expertise, means for searching for the most suitable expert for the topic based on the classified information, means for inviting the expert selected based on the search results to an online conference, and means for providing feedback of the expert's comments during the conference in real time. This makes it possible to quickly and efficiently search for and invite experts and provide useful information in real time during the conference.

[0802] A "master" is an individual who has advanced expertise and skills and is highly regarded in their field.

[0803] "Information" refers to data related to the masters' expertise and achievements, such as their biographies, papers, books, and interviews.

[0804] "Acquisition" refers to the act of collecting information about celebrities through web scraping or other means.

[0805] "Classification" refers to the use of natural language processing algorithms to organize and separate collected information into specialized fields.

[0806] A "theme" refers to a specific topic or issue that a user sets when communicating or discussing.

[0807] An "expert" is an individual who has in-depth knowledge and skills related to a particular topic and has a proven track record in that field.

[0808] "Search" refers to the act of locating appropriate expert information from a database based on a topic.

[0809] An "online meeting" refers to a meeting that uses audio and video over the Internet, including video conferencing systems.

[0810] "Remarks" refers to comments and opinions provided by experts during the meeting.

[0811] The present invention is a system that collects and classifies expert information, invites experts to online conferences, and provides real-time feedback. Specifically, it is realized by specific roles of a server, a terminal, and a user.

[0812] Obtaining information about masters

[0813] The server runs a program to obtain information about the masters. This uses web scraping technology. Specifically, it uses the Python libraries BeautifulSoup and Scrapy to collect information such as the masters' biographies, papers, books, and interviews. The collected information is converted into JSON format and stored in a database (for example, PostgreSQL or MongoDB).

[0814] Information classification

[0815] The server uses natural language processing (NLP) algorithms to categorize the information it retrieves by area of ​​expertise. Specifically, it uses the natural language processing library SpaCy to analyze text and categorize the information based on the expert's area of ​​expertise. This allows the server to organize the information in the database into categories such as business, technology, medicine, and energy.

[0816] Enter a topic and search for experts

[0817] The user inputs the topic of the meeting into a dedicated device (e.g., a laptop or tablet). For example, the topic may be "improving the manufacturing process for new materials." The server analyzes the topic entered by the user and searches for relevant experts in the database. This search uses a full-text search engine (e.g., Elasticsearch).

[0818] Selection and invitation of experts

[0819] The user selects the most suitable expert from the list of experts displayed on the device. For example, they click on a prominent scientist related to "new materials." The server then sends an invitation to the selected expert using an online conferencing platform such as Zoom. Specifically, a Python library (e.g., zoomus) is used to call the Zoom API and automatically generate and send a meeting invitation. The invitation includes the meeting title, date and time, and a Zoom link.

[0820] Real-time feedback

[0821] The device uses speech recognition technology to convert experts' speech into text in real time during the meeting. Specifically, it uses APIs such as Google Speech-to-Text and IBM Watson Speech to Text to convert speech into text. The converted speech is then shared with other participants in real time.

[0822] Specific examples

[0823] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0824] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0825] 2. The server uses Elasticsearch to search the database for relevant experts (e.g., a particular scientist or engineer).

[0826] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0827] 4. The server sends a Zoom meeting invitation to the selected scientists using the zoomus library.

[0828] 5. During the meeting, the device uses the Google Speech-to-Text API to transcribe the scientists' speech in real time and provide real-time feedback to other participants.

[0829] Prompt Sentence Examples

[0830] Below are some example prompts to input to the generative AI model:

[0831] "Please explain the process for gathering information on who is a leading figure in the business technology field and finding relevant experts."

[0832] "How can I invite an expert on improving the manufacturing process of new materials to an online meeting?"

[0833] "Please explain how the system works, which converts experts' comments in online meetings into text in real time and provides feedback."

[0834] The above is an embodiment of the invention.

[0835] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0836] Step 1:

[0837] The server runs a web scraping program to collect information about the experts. Specifically, it uses the Python libraries BeautifulSoup and Scrapy. It uses source URLs for the experts' biographies, papers, books, interviews, etc. on the internet as input, and converts the collected information into JSON format and stores it in a database as output. Specifically, the server sets up a daily batch job to automatically perform web scraping at 2:00 AM. If an error occurs, it records an error log and notifies the operations staff.

[0838] Step 2:

[0839] The server uses a natural language processing (NLP) algorithm to classify the collected information into specialized fields. Specifically, it uses the natural language processing library SpaCy. It uses JSON-formatted information stored in a database as input and generates data classified by specialized field (business, technology, medicine, energy, etc.) as output. Specifically, the server uses a GPU to run the SpaCy model and quickly process large amounts of data.

[0840] Step 3:

[0841] The user inputs a theme into a dedicated terminal. For example, the theme is "improving the manufacturing process for new materials." The user inputs the theme into the terminal as input, and the theme is sent to the server as output. Specifically, the user inputs the theme into the input form and clicks the send button, causing the terminal to send the theme data to the server.

[0842] Step 4:

[0843] The server analyzes the topic entered by the user and searches the database for the most suitable experts. Specifically, it performs a full-text search using Elasticsearch. It uses the topic submitted by the user and the classified data stored in the database as input, and generates a list of relevant experts as output. Specifically, the server generates an Elasticsearch query and returns the search results for experts related to the "new material" in the database.

[0844] Step 5:

[0845] The user selects the most suitable expert from the list of experts displayed on the terminal. For example, by clicking "famous scientists related to new materials." The information of the expert selected from the expert list is used as input, and the selected expert is notified to the server as output. Specifically, when the user selects the most suitable expert from the list and clicks the selection button, the terminal sends the selection information to the server.

[0846] Step 6:

[0847] The server sends invitations to the selected experts using an online conferencing platform such as Zoom. Specifically, it calls the Zoom API using the Python library zoomus. The information of the expert selected by the user and the details of the meeting are used as input, and an invitation is generated as output and sent to the expert. Specifically, the server connects to the Zoom API and automatically generates and sends a meeting invitation for the specified date and time.

[0848] Step 7:

[0849] The device converts the expert's speech during the meeting into text in real time using speech recognition technology. Specifically, it uses the Google Speech-to-Text and IBM Watson Speech to Text APIs. It uses the audio data from the meeting as input and generates the text of the speech as output. Specifically, the device establishes a connection to the speech recognition API and sends the audio data via streaming. The recognized text is displayed in real time on the front end using WebSocket.

[0850] The above are the specific processing steps of the program of this system.

[0851] (Application example 1)

[0852] 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."

[0853] In today's cybersecurity environment, it is extremely important for companies to take prompt and appropriate security measures. However, there are limited ways to utilize the knowledge and experience of security experts in real time, making it difficult to respond quickly to specific threats. There is also a lack of ways to quickly share expert opinions during meetings in a way that all participants can understand immediately. This can lead to delays in decision-making and discrepancies in information.

[0854] 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.

[0855] In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the topic based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion in real time during the conference, means for classifying the collected data into categories such as firewall, encryption technology, and endpoint protection, means for converting the expert's remarks during the conference into text using voice recognition technology, and means for sharing the converted text with other participants in real time, thereby enabling prompt and appropriate security measures.

[0856] "Master data" is information about people who have high levels of expertise and experience in their respective fields.

[0857] "Collection methods" are the mechanisms by which the necessary data is obtained and stored from the internet and other sources.

[0858] A "classification method" is an algorithm or method that separates collected data into categories based on specific criteria.

[0859] A "specialized field" is an academic or industrial field that requires specific knowledge or skills.

[0860] Searching is the process of finding information that matches specific criteria from a database or other source.

[0861] "Means for inviting participants to an online meeting" refers to communication methods or software that allow specific participants to join a meeting via the Internet.

[0862] "Feedback means" refers to a system or method for conveying expert opinions and comments to other participants in real time.

[0863] A "firewall" is a defensive system or software that ensures network security.

[0864] "Encryption technology" is a technology that converts information into an obfuscated form in order to protect the information.

[0865] "Endpoint protection" refers to software and hardware technologies that protect devices on a network from security threats.

[0866] "Speech recognition technology" is a technology for converting speech into text.

[0867] "Means for converting to text" refers to a method for converting voice data into text information and storing or displaying it.

[0868] A "sharing method" is the process of providing specific data or information to other users or systems.

[0869] The system configuration for implementing the present invention is realized by servers, terminals, and users taking on specific roles.

[0870] 1. Master data collection:

[0871] The server uses web scraping technology to collect data such as the biographies, papers, books, and interviews of celebrities from the Internet and stores it in a database using software such as Beautiful Soup and Scrapy.

[0872] 2. Data Classification:

[0873] The server uses natural language processing (NLP) techniques to categorize the collected data into categories such as firewalls, encryption technologies, and endpoint protection, using NLP libraries such as Spacy and NLTK.

[0874] 3. Enter your topic and search for experts:

[0875] Users input a topic into a dedicated terminal, for example, "responding to ransomware attacks." Based on this input, the server searches the database for relevant experts. Matching based on the search query is also performed using NLP.

[0876] 4. Expert selection and invitation:

[0877] The user selects the most suitable expert from a list of experts displayed on the device. For example, they can select an expert in ransomware countermeasures. After selection, the server sends an invitation to the selected expert via Zoom or a dedicated security conference platform.

[0878] 5. Real-time feedback:

[0879] During the meeting, the server uses speech recognition technology to convert the expert's speech into text in real time and share it with other participants. This process uses speech recognition technologies such as Google Cloud Speech-to-Text and IBM Watson. The converted speech is immediately fed back to other participants in real time.

[0880] Examples:

[0881] A user inputs a topic such as, "A specific company has been attacked by ransomware and its files have been encrypted. Recovery and countermeasures are urgently needed. We need expert opinions on whether we should comply with the attacker's demands and how to recover the data." Based on this input, the server searches for relevant experts and suggests well-known experts who are experts in ransomware countermeasures. A meeting is then held, and the experts' comments are converted into text in real time using voice recognition technology and instantly shared with other participants.

[0882] Example prompt sentence:

[0883] “Please provide a list of security experts for the following incident.

[0884] Incident details: Ransomware attack

[0885] Details: A company has been hit by a ransomware attack and their files have been encrypted. Recovery and countermeasures are urgently needed. We need expert advice on whether to comply with the attacker's demands and how to recover the data.

[0886] Run the program that generates a list of suitable experts from the system's database.

[0887] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0888] Step 1:

[0889] The server collects data on the masters. It uses web scraping technologies such as Beautiful Soup and Scrapy to retrieve the masters' biographies, papers, books, interviews, etc. from the Internet. It uses a list of URLs from multiple websites as input, and stores the masters' information as structured data in a database as output.

[0890] Step 2:

[0891] The server categorizes the collected data by area of ​​expertise. The server uses natural language processing (NLP) techniques such as Spacy or NLTK to categorize the collected data into categories such as firewalls, encryption technologies, and endpoint protection. It uses the collected data as input and obtains data organized by category as output.

[0892] Step 3:

[0893] The user inputs a theme into a dedicated terminal. The user inputs a specific theme using the terminal's input interface. For example, the user might input "responding to ransomware attacks." The theme keyword is used as input, and the keyword is sent to the server as output.

[0894] Step 4:

[0895] The server searches for relevant experts based on a topic. The server uses NLP techniques to search for experts related to a topic from a database. It uses the topic entered by the user as input and generates a list of relevant experts as output.

[0896] Step 5:

[0897] The user selects the most suitable expert from the list of experts displayed on the terminal. The user checks the list and presses the select button to select. The list of experts is used as input, and the information of the selected expert is sent to the server as output.

[0898] Step 6:

[0899] The server sends an online meeting invitation to the selected expert. The server sends the invitation using Zoom or a dedicated secure conferencing platform. The server uses the selected expert's contact information as input and confirms that the invitation has been sent as output.

[0900] Step 7:

[0901] During the meeting, the server uses speech recognition technology to convert the experts' speech into text. The server uses speech recognition services such as Google Cloud Speech-to-Text and IBM Watson. The server uses the speech data from the meeting as input and obtains the text of the speech as output.

[0902] Step 8:

[0903] The server shares the textual utterances with other participants in real time. The server displays the textual utterances on the other participants' devices in real time. The server uses the textual utterance data as input and provides feedback to the participants' devices as output.

[0904] 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.

[0905] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[0906] System program processing

[0907] Master data collection

[0908] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to obtain data such as their career histories, papers, books, and interview articles, and stores it in a database.

[0909] Data classification

[0910] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[0911] Enter a topic and search for experts

[0912] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[0913] Selection and invitation of experts

[0914] The user selects the most suitable expert from the list of experts displayed on the device. For example, by clicking on "famous scientists in new materials," the server then sends an invitation to the selected expert via an online conference platform such as Zoom.

[0915] Real-time feedback and sentiment analysis

[0916] The device uses speech recognition technology to convert experts' comments into text in real time during the meeting and provide feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in real time during the meeting and sends the results to the server.

[0917] Specific examples

[0918] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0919] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0920] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0921] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0922] 4. The server sends a Zoom meeting invitation to the selected scientists.

[0923] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and send that information to the server.

[0924] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0925] This system can efficiently collect and classify expert data, invite the most suitable experts to the meeting, and analyze and provide feedback on the user's emotional state in real time, which will help meetings proceed more smoothly and enable more effective decision-making.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The server runs a web scraping program to collect data on the masters. Specifically, it automatically retrieves data about the masters, such as their biographies, papers, books, and interview articles, from specific URLs and stores them in a structured format in a database.

[0929] Step 2:

[0930] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes and stores it by expert.

[0931] Step 3:

[0932] The server uses natural language processing (NLP) algorithms to categorize the stored data by subject area, specifically by using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[0933] Step 4:

[0934] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[0935] Step 5:

[0936] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[0937] Step 6:

[0938] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[0939] Step 7:

[0940] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[0941] Step 8:

[0942] The server sends a Zoom meeting invitation to the selected experts. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected experts.

[0943] Step 9:

[0944] Once the meeting has started, the device will convert the speech of the expert into text in real time using speech recognition technology and provide feedback to other participants. Specifically, the device converts the speech data into text and automatically highlights and displays important points.

[0945] Step 10:

[0946] The emotion engine analyzes users' emotions in real time during meetings, using facial recognition technology and voice analysis to extract emotional data from users' facial expressions, tone of voice, and choice of words.

[0947] Step 11:

[0948] The server receives the emotion data from the emotion engine and provides feedback according to the user's emotional state. For example, if the user is feeling stressed, the server sends a notification to the terminal to adjust the progress of the meeting.

[0949] Step 12:

[0950] The terminal receives notifications from the server and adjusts the progress of the meeting. Specifically, it displays a summary of questions to the expert and provides support to help the user understand the content.

[0951] Example 2

[0952] 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."

[0953] Conventional online conference systems make it difficult to efficiently search for and invite experts with specialized knowledge and provide real-time feedback during the meeting. Furthermore, there are no systems that recognize participants' emotional states during the meeting and optimize the progress of the meeting. As a result, the meeting may not proceed smoothly and decision-making may be delayed.

[0954] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the theme based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion during the conference in real time, and means for analyzing the emotional state of participants during the conference in real time and optimizing the progress of the conference based on the results. This makes it possible to efficiently search for and invite experts and optimize the progress based on feedback and emotions during the conference.

[0955] "Master data" refers to all information about individuals with specialized knowledge and experience, including their career history, papers, books, interviews, etc.

[0956] "Collection methods" refers to the methods used to obtain data from the internet or other sources and store it in a database.

[0957] "Means of classification by field of expertise" refers to a method of dividing collected data into specific fields of expertise or categories using natural language processing algorithms, etc.

[0958] "Means for searching for the most suitable expert for a topic" refers to a method for extracting relevant experts from a database based on an input topic.

[0959] "Means of inviting selected experts to an online conference" refers to a method of sending an invitation to an online conference to selected experts and requesting their participation.

[0960] "Means of providing real-time feedback of expert opinions during a meeting" refers to a method in which what an expert says during a meeting is converted into text using voice recognition technology and provided as feedback to other participants.

[0961] "Means for analyzing participants' emotional states in real time during a meeting" refers to a method using technology, such as an emotion recognition algorithm, to analyze participants' facial expressions and voices during a meeting and determine their emotional states.

[0962] "Means for optimizing meeting progress" refers to methods for adjusting the schedule and content of meetings based on the results of sentiment analysis to help participants understand the content.

[0963] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[0964] First, the server collects data about the masters from the Internet. Specifically, it uses web scraping technology. For example, it uses Python's BeautifulSoup or Scrapy to collect data such as the master's biography, papers, books, and interview articles, and temporarily stores that data in a cache such as Redis. This collected data is finally stored in a MySQL database.

[0965] The server then categorizes the collected data using natural language processing (NLP) algorithms, using services such as Google Cloud Natural Language API to organize the data into specialties such as business, technology, medicine, and energy. This results in the database containing data already categorized by speciality.

[0966] The user inputs a topic using a dedicated terminal. For example, they input the topic "improving the manufacturing process for new materials." Based on this input, the server searches the Elasticsearch database for relevant experts. As a result of the search, a list of relevant experts is displayed on the user's terminal.

[0967] The user selects the most suitable expert from the list. For example, they can select "famous scientists in new materials." Once the selection is complete, the server invites the expert to an online meeting using the Zoom API or Google Calendar API. This sends a meeting invitation to the selected expert.

[0968] During the meeting, the device converts the expert's speech into text in real time using speech recognition technology (e.g., Google Speech-to-Text API) and provides it as feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in the meeting in real time. This emotion analysis is performed using the Microsoft Azure Emotion API. The analysis results are sent to the server, which then sends notifications to adjust the progress of the meeting based on the emotion data.

[0969] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[0970] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[0971] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[0972] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[0973] 4. The server sends an invitation to the selected scientists to attend the online meeting.

[0974] 5. Once the meeting begins, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[0975] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[0976] Examples of prompt sentences include:

[0977] "Find experts on manufacturing process improvements for new materials."

[0978] "Use the real-time feedback feature to analyze what experts say during meetings and provide feedback to users."

[0979] In this way, the system can efficiently collect and classify expert data, identify and invite the most suitable experts, and optimize the progress based on feedback and emotions during the meeting.

[0980] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0981] Step 1: Collecting data on experts

[0982] The server runs a program that collects data on masters from the Internet. The input here is a list of URLs for the websites to be collected. Specifically, the server performs web scraping using BeautifulSoup and Scrapy to obtain information such as the master's career history, papers, books, and interview articles. The obtained data is temporarily stored in a Redis cache and then stored in a MySQL database.

[0983] Input: List of website URLs

[0984] Output: Data such as the master's biography, papers, books, interviews, etc.

[0985] Specific behavior:

[0986] The server performs web scraping based on the specified URL list.

[0987] The retrieved data is temporarily stored in the Redis cache.

[0988] Migrate the stored data to a MySQL database.

[0989] Step 2: Classify the data

[0990] The server classifies the collected data using a natural language processing (NLP) algorithm. The input here is expert data stored in a MySQL database. Specifically, the server analyzes the data using the Google Cloud Natural Language API and classifies the data into specialized fields such as business, technology, medicine, and energy based on the analysis results. The classified data is then stored back in the database.

[0991] Input: Master data stored in a MySQL database

[0992] Output: Classified virtuoso data

[0993] Specific behavior:

[0994] The server analyzes the data using NLP algorithms.

[0995] Categorize data by discipline.

[0996] Update the classified data into a MySQL database.

[0997] Step 3: Enter the theme

[0998] The user inputs a topic using a dedicated terminal. The input here is the topic the user wants to discuss. In concrete terms, the user inputs the topic into the input field of the terminal, and it is sent to the server. For example, the topic "improving the manufacturing process for new materials" is input.

[0999] Input: The theme entered by the user

[1000] Output: The theme sent to the server

[1001] Specific behavior:

[1002] The user enters a theme into an input field on the device.

[1003] The entered theme is sent to the server.

[1004] Step 4: Find an expert

[1005] The server searches for relevant experts from the Elasticsearch database based on the received topic. The input here is the topic submitted by the user. Specifically, the server generates an Elasticsearch query and searches the database. As a search result, it generates a list of relevant experts and displays it on the user's device.

[1006] Input: User-submitted theme

[1007] Output: A list of relevant experts

[1008] Specific behavior:

[1009] The server generates an Elasticsearch query.

[1010] Search databases and identify relevant experts.

[1011] A list of experts is displayed on the user's terminal.

[1012] Step 5: Selecting an expert

[1013] The user selects the most suitable expert from the list of experts displayed on the terminal. The input here is the displayed list of experts. In concrete terms, the user clicks on the desired expert from the list. Information on the selected expert is sent to the server.

[1014] Input: List of displayed experts

[1015] Output: Information about selected experts

[1016] Specific behavior:

[1017] The user clicks on the desired expert from the list.

[1018] The information of the selected expert is sent to the server.

[1019] Step 6: Send invitations

[1020] The server sends an online meeting invitation to the selected expert. The input here is the information of the selected expert. Specifically, the server generates a meeting invitation using the Zoom API or Google Calendar API and sends it to the expert's email address.

[1021] Input: Selected expert information

[1022] Output: Online meeting invitation

[1023] Specific behavior:

[1024] The server generates a meeting invitation using the Zoom API or Google Calendar API.

[1025] Send the invitation to the expert's email.

[1026] Step 7: Real-time feedback

[1027] The device converts the expert's speech into text in real time during the meeting and provides feedback to other participants. The input here is the expert's real-time speech. Specifically, it converts the speech into text using the Google Speech-to-Text API and displays the text to participants.

[1028] Input: Real-time expert comments

[1029] Output: Translated utterances

[1030] Specific behavior:

[1031] The expert's speech is captured as audio data.

[1032] Converts speech to text using the Google Speech-to-Text API.

[1033] Display the transcribed text to the participants.

[1034] Step 8: Sentiment analysis

[1035] The emotion engine analyzes the emotional state of each user during a meeting in real time. The input here is video and audio data from the meeting. Specifically, it analyzes the data using the Microsoft Azure Emotion API and sends the analysis results of the emotional state to the server.

[1036] Input: Video and audio data during the meeting

[1037] Output: Emotional state analysis result

[1038] Specific behavior:

[1039] Capture video and audio data.

[1040] Analyze the data using the Microsoft Azure Emotion API.

[1041] The analysis results are sent to the server.

[1042] Step 9: Coordinate the meeting

[1043] Based on information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. The input here is the analysis result of the emotional state. Specifically, the server analyzes the analysis result and takes action to adjust the progress of the meeting as necessary (e.g., summarizing comments or suggesting a break).

[1044] Input: Emotional state analysis result

[1045] Output: Notification of meeting progress adjustment

[1046] Specific behavior:

[1047] Receive and analyze the results of the emotional state analysis.

[1048] Take action to coordinate meeting progress and send notifications.

[1049] (Application example 2)

[1050] 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."

[1051] The current problem with factory production lines is the lack of means to incorporate expert knowledge in real time and monitor and optimize the emotional state of workers and operators. In particular, when improving processing methods for new materials and production processes, real-time feedback from experts and management of workers' emotional states are required.

[1052] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1053] In this invention, the server includes a means for collecting data on experts, a means for classifying the collected data by field of expertise, and a means for searching for the most suitable expert for the theme based on the classified data. This makes it possible to utilize the knowledge of experts on factory production lines and provide optimal feedback and process adjustments while monitoring the emotional states of workers and operators in real time.

[1054] "Masterpiece data" refers to information such as the careers, achievements, writings, and interview articles of experts with outstanding knowledge and experience in a particular field.

[1055] "Classification" refers to the process of organizing and structuring collected data according to specific disciplines or categories.

[1056] A "topic" refers to the topic or topic that a user wants to cover in a particular meeting or consultation.

[1057] An "expert" is an individual who has advanced knowledge or skills in a particular area of ​​expertise.

[1058] An "online meeting" refers to a virtual meeting space where multiple participants can interact in real time via the Internet.

[1059] "Feedback" refers to the process of communicating information such as advice, opinions, and evaluations provided by experts to participants in real time.

[1060] An "artificial intelligence engine" refers to a software or hardware system for performing advanced computational tasks such as data analysis, emotion recognition, and natural language processing.

[1061] "Sentiment analysis" refers to the process of determining and analyzing the emotional state of meeting participants based on their facial expressions, tone of voice, and choice of words.

[1062] "Optimization" refers to the adjustment or improvement of a system or process to maximize its performance for specific purposes or conditions.

[1063] MODE FOR CARRYING OUT THE INVENTION

[1064] This invention relates to a system for real-time production supervision on factory production lines. The system incorporates expert knowledge, monitors the emotional states of workers and robot operators, and performs a series of processes including expert data collection, classification, expert search, online conferencing, and emotion analysis to provide optimal feedback and process adjustments.

[1065] Server Roles

[1066] The server collects data on the experts from the internet. Specifically, it uses web scraping technology to retrieve information such as their careers, achievements, papers, and interviews, and stores it in a database. This data is then categorized by field of expertise using natural language processing (NLP) algorithms. For example, it can be categorized into categories such as "business," "technology," "medical care," and "energy."

[1067] Next, based on the topic entered by the user into the dedicated terminal (e.g., "processing methods for new materials"), the server searches the database for relevant experts. Once the most suitable expert is selected, the server sends the selected expert an invitation to an online meeting. This is done using the Zoom API or Microsoft Teams API.

[1068] Device Role

[1069] The device receives the topic input by the user and sends it to the server. Once the conference begins, the device converts the expert's remarks into text in real time using speech recognition technology and provides feedback to other participants.

[1070] The terminal is also equipped with an emotion analysis engine that monitors the emotional state of workers and operators in real time. This emotion engine uses, for example, the DeepFace library to recognize facial expressions. It is also capable of voice analysis, determining the emotional state of participants from their speaking style and tone of voice. The collected emotion data is sent to a server and used to optimize the progress of the meeting.

[1071] User Roles

[1072] The user inputs the topic of the meeting into a dedicated terminal. For example, by entering a topic such as "processing methods for new materials," the process of searching for the most suitable expert related to that topic begins. The user then selects the most suitable expert from a list of experts displayed on the terminal. During the meeting, the user receives feedback provided in real time and adjusts the progress based on the results of sentiment analysis.

[1073] Examples of concrete examples and prompts

[1074] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[1075] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[1076] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[1077] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on a new material.

[1078] 4. The server sends a Zoom meeting invitation to the selected expert.

[1079] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[1080] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[1081] An example of a prompt is as follows:

[1082] "Collect and store expert data. Use web scraping technology to retrieve expert profiles, careers, papers, and interviews, and store them in a database."

[1083] This system makes it possible to efficiently collect and classify expert data, invite the most suitable experts to meetings, and analyze and provide feedback on the user's emotional state in real time, resulting in smoother meetings and more effective decision-making.

[1084] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1085] Step 1:

[1086] The server collects data on the masters. Based on the list of website URLs specified as input, it uses web scraping technology to obtain information such as the masters' careers, achievements, papers, and interview articles. The obtained data is stored in a database.

[1087] Step 2:

[1088] The server categorizes the collected data using natural language processing (NLP) algorithms. It takes as input the unclassified data in the database and categorizes each data into a specialized field, such as business, technology, medicine, or energy. The output is a classified dataset.

[1089] Step 3:

[1090] The user inputs the topic of the meeting into a dedicated terminal. The input is text information (e.g., "Processing method for new materials") that the user types into the terminal. The terminal then sends this input to the server.

[1091] Step 4:

[1092] The server searches the database for relevant experts based on the input topic. The input is the topic text submitted by the user, and the output is a list of relevant experts. The server searches the classification data in the database and selects the most suitable expert.

[1093] Step 5:

[1094] The user selects the most suitable expert from the list of experts displayed on the terminal. The input is the list of experts, and the expert information selected by the user is output. The selected expert is sent to the server.

[1095] Step 6:

[1096] The server sends online meeting invitations to the selected experts. The input is the experts' contact information and meeting details, and the output is the sent invitation. This uses the Zoom API or Microsoft Teams API.

[1097] Step 7:

[1098] After the conference begins, the device uses speech recognition technology to convert the expert's speech into text in real time. The input is the expert's speech data during the conference, and the output is the converted speech data. This data is immediately fed back to the other participants.

[1099] Step 8:

[1100] The device's sentiment analysis engine monitors the emotional state of participants in real time during a meeting. The input is the participants' video feeds and audio data, and the output is data representing their emotional state. This sentiment analysis is performed using libraries such as DeepFace.

[1101] Step 9:

[1102] The server optimizes the progress of the meeting based on the results of the sentiment analysis. The input is emotional state data, and the output is progress adjustments or notifications. For example, it may summarize and display the expert's comments or take actions to adjust the pace of the meeting. As a result, users can efficiently manage the progress of the meeting.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] [Fourth embodiment]

[1107] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1108] 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.

[1109] 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).

[1110] 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.

[1111] 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.

[1112] 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).

[1113] 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.

[1114] 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.

[1115] 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.

[1116] 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.

[1117] 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.

[1118] 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.

[1119] 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."

[1120] The present invention provides a system that collects and classifies expert data, invites experts to online conferences, and provides real-time feedback. This system is realized by a server, a terminal, and a user who play specific roles.

[1121] System program processing

[1122] Master data collection

[1123] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to collect their biographies, papers, books, interviews, and other information, and stores it in a database.

[1124] Data classification

[1125] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[1126] Enter a topic and search for experts

[1127] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[1128] Selection and invitation of experts

[1129] The user selects the most suitable expert from the list of experts displayed on the device. For example, the user clicks on a person selected as an expert related to "new materials." The server then sends an invitation to the selected expert using an online conference platform such as Zoom.

[1130] Real-time feedback

[1131] The device uses voice recognition technology to convert experts' comments into text in real time during the meeting and provide feedback to other participants, such as specific suggestions for the manufacturing process of a new material.

[1132] Specific examples

[1133] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[1134] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[1135] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[1136] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[1137] 4. The server sends a Zoom meeting invitation to the selected scientists.

[1138] 5. During the meeting, the device uses voice recognition technology to convert the scientist's speech into text and provide real-time feedback to other participants.

[1139] This system makes it possible to efficiently select the most suitable experts, hold meetings quickly, and obtain useful information in real time, which will enable efficient discussion and improvement of manufacturing methods for industrial products that make the most of the properties of new materials.

[1140] The processing flow will be explained below.

[1141] Step 1:

[1142] The server runs a web scraping program to collect data on the masters, specifically, to retrieve data such as their careers, papers, books, and interview articles from the configured URLs.

[1143] Step 2:

[1144] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes the information for each expert.

[1145] Step 3:

[1146] The server runs natural language processing (NLP) algorithms to categorize the stored data by subject matter, using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[1147] Step 4:

[1148] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[1149] Step 5:

[1150] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[1151] Step 6:

[1152] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[1153] Step 7:

[1154] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[1155] Step 8:

[1156] The server sends a Zoom meeting invitation to the selected experts. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected experts.

[1157] Step 9:

[1158] After the meeting begins, the device records the expert's remarks in real time and provides feedback, converting them into text using voice recognition technology and displaying it to other participants.

[1159] Each of these processing steps allows for efficient collection and classification of expert data, inviting the most appropriate experts to the meeting, and providing real-time feedback.

[1160] Example 1

[1161] 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."

[1162] The problem that this invention aims to solve is to build a system that efficiently collects information on experts with specialized knowledge and appropriately classifies that data, allowing users to quickly search for the most suitable experts based on a specific topic, invite them to an online conference, and provide them with real-time expert feedback during the conference.

[1163] 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.

[1164] In this invention, the server includes means for acquiring information on experts, means for classifying the acquired information by area of ​​expertise, means for searching for the most suitable expert for the topic based on the classified information, means for inviting the expert selected based on the search results to an online conference, and means for providing feedback of the expert's comments during the conference in real time. This makes it possible to quickly and efficiently search for and invite experts and provide useful information in real time during the conference.

[1165] A "master" is an individual who has advanced expertise and skills and is highly regarded in their field.

[1166] "Information" refers to data related to the masters' expertise and achievements, such as their biographies, papers, books, and interviews.

[1167] "Acquisition" refers to the act of collecting information about celebrities through web scraping or other means.

[1168] "Classification" refers to the use of natural language processing algorithms to organize and separate collected information into specialized fields.

[1169] A "theme" refers to a specific topic or issue that a user sets when communicating or discussing.

[1170] An "expert" is an individual who has in-depth knowledge and skills related to a particular topic and has a proven track record in that field.

[1171] "Search" refers to the act of locating appropriate expert information from a database based on a topic.

[1172] An "online meeting" refers to a meeting that uses audio and video over the Internet, including video conferencing systems.

[1173] "Remarks" refers to comments and opinions provided by experts during the meeting.

[1174] The present invention is a system that collects and classifies expert information, invites experts to online conferences, and provides real-time feedback. Specifically, it is realized by specific roles of a server, a terminal, and a user.

[1175] Obtaining information about masters

[1176] The server runs a program to obtain information about the masters. This uses web scraping technology. Specifically, it uses the Python libraries BeautifulSoup and Scrapy to collect information such as the masters' biographies, papers, books, and interviews. The collected information is converted into JSON format and stored in a database (for example, PostgreSQL or MongoDB).

[1177] Information classification

[1178] The server uses natural language processing (NLP) algorithms to categorize the information it retrieves by area of ​​expertise. Specifically, it uses the natural language processing library SpaCy to analyze text and categorize the information based on the expert's area of ​​expertise. This allows the server to organize the information in the database into categories such as business, technology, medicine, and energy.

[1179] Enter a topic and search for experts

[1180] The user inputs the topic of the meeting into a dedicated device (e.g., a laptop or tablet). For example, the topic may be "improving the manufacturing process for new materials." The server analyzes the topic entered by the user and searches for relevant experts in the database. This search uses a full-text search engine (e.g., Elasticsearch).

[1181] Selection and invitation of experts

[1182] The user selects the most suitable expert from the list of experts displayed on the device. For example, they click on a prominent scientist related to "new materials." The server then sends an invitation to the selected expert using an online conferencing platform such as Zoom. Specifically, a Python library (e.g., zoomus) is used to call the Zoom API and automatically generate and send a meeting invitation. The invitation includes the meeting title, date and time, and a Zoom link.

[1183] Real-time feedback

[1184] The device uses speech recognition technology to convert experts' speech into text in real time during the meeting. Specifically, it uses APIs such as Google Speech-to-Text and IBM Watson Speech to Text to convert speech into text. The converted speech is then shared with other participants in real time.

[1185] Specific examples

[1186] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[1187] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[1188] 2. The server uses Elasticsearch to search the database for relevant experts (e.g., a particular scientist or engineer).

[1189] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[1190] 4. The server sends a Zoom meeting invitation to the selected scientists using the zoomus library.

[1191] 5. During the meeting, the device uses the Google Speech-to-Text API to transcribe the scientists' speech in real time and provide real-time feedback to other participants.

[1192] Prompt Sentence Examples

[1193] Below are some example prompts to input to the generative AI model:

[1194] "Please explain the process for gathering information on who is a leading figure in the business technology field and finding relevant experts."

[1195] "How can I invite an expert on improving the manufacturing process of new materials to an online meeting?"

[1196] "Please explain how the system works, which converts experts' comments in online meetings into text in real time and provides feedback."

[1197] The above is an embodiment of the invention.

[1198] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1199] Step 1:

[1200] The server runs a web scraping program to collect information about the experts. Specifically, it uses the Python libraries BeautifulSoup and Scrapy. It uses source URLs for the experts' biographies, papers, books, interviews, etc. on the internet as input, and converts the collected information into JSON format and stores it in a database as output. Specifically, the server sets up a daily batch job to automatically perform web scraping at 2:00 AM. If an error occurs, it records an error log and notifies the operations staff.

[1201] Step 2:

[1202] The server uses a natural language processing (NLP) algorithm to classify the collected information into specialized fields. Specifically, it uses the natural language processing library SpaCy. It uses JSON-formatted information stored in a database as input and generates data classified by specialized field (business, technology, medicine, energy, etc.) as output. Specifically, the server uses a GPU to run the SpaCy model and quickly process large amounts of data.

[1203] Step 3:

[1204] The user inputs a theme into a dedicated terminal. For example, the theme is "improving the manufacturing process for new materials." The user inputs the theme into the terminal as input, and the theme is sent to the server as output. Specifically, the user inputs the theme into the input form and clicks the send button, causing the terminal to send the theme data to the server.

[1205] Step 4:

[1206] The server analyzes the topic entered by the user and searches the database for the most suitable experts. Specifically, it performs a full-text search using Elasticsearch. It uses the topic submitted by the user and the classified data stored in the database as input, and generates a list of relevant experts as output. Specifically, the server generates an Elasticsearch query and returns the search results for experts related to the "new material" in the database.

[1207] Step 5:

[1208] The user selects the most suitable expert from the list of experts displayed on the terminal. For example, by clicking "famous scientists related to new materials." The information of the expert selected from the expert list is used as input, and the selected expert is notified to the server as output. Specifically, when the user selects the most suitable expert from the list and clicks the selection button, the terminal sends the selection information to the server.

[1209] Step 6:

[1210] The server sends invitations to the selected experts using an online conferencing platform such as Zoom. Specifically, it calls the Zoom API using the Python library zoomus. The information of the expert selected by the user and the details of the meeting are used as input, and an invitation is generated as output and sent to the expert. Specifically, the server connects to the Zoom API and automatically generates and sends a meeting invitation for the specified date and time.

[1211] Step 7:

[1212] The device converts the expert's speech during the meeting into text in real time using speech recognition technology. Specifically, it uses the Google Speech-to-Text and IBM Watson Speech to Text APIs. It uses the audio data from the meeting as input and generates the text of the speech as output. Specifically, the device establishes a connection to the speech recognition API and sends the audio data via streaming. The recognized text is displayed in real time on the front end using WebSocket.

[1213] The above are the specific processing steps of the program of this system.

[1214] (Application example 1)

[1215] 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."

[1216] In today's cybersecurity environment, it is extremely important for companies to take prompt and appropriate security measures. However, there are limited ways to utilize the knowledge and experience of security experts in real time, making it difficult to respond quickly to specific threats. There is also a lack of ways to quickly share expert opinions during meetings in a way that all participants can understand immediately. This can lead to delays in decision-making and discrepancies in information.

[1217] 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.

[1218] In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the topic based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion in real time during the conference, means for classifying the collected data into categories such as firewall, encryption technology, and endpoint protection, means for converting the expert's remarks during the conference into text using voice recognition technology, and means for sharing the converted text with other participants in real time, thereby enabling prompt and appropriate security measures.

[1219] "Master data" is information about people who have high levels of expertise and experience in their respective fields.

[1220] "Collection methods" are the mechanisms by which the necessary data is obtained and stored from the internet and other sources.

[1221] A "classification method" is an algorithm or method that separates collected data into categories based on specific criteria.

[1222] A "specialized field" is an academic or industrial field that requires specific knowledge or skills.

[1223] Searching is the process of finding information that matches specific criteria from a database or other source.

[1224] "Means for inviting participants to an online meeting" refers to communication methods or software that allow specific participants to join a meeting via the Internet.

[1225] "Feedback means" refers to a system or method for conveying expert opinions and comments to other participants in real time.

[1226] A "firewall" is a defensive system or software that ensures network security.

[1227] "Encryption technology" is a technology that converts information into an obfuscated form in order to protect the information.

[1228] "Endpoint protection" refers to software and hardware technologies that protect devices on a network from security threats.

[1229] "Speech recognition technology" is a technology for converting speech into text.

[1230] "Means for converting to text" refers to a method for converting voice data into text information and storing or displaying it.

[1231] A "sharing method" is the process of providing specific data or information to other users or systems.

[1232] The system configuration for implementing the present invention is realized by servers, terminals, and users taking on specific roles.

[1233] 1. Master data collection:

[1234] The server uses web scraping technology to collect data such as the biographies, papers, books, and interviews of celebrities from the Internet and stores it in a database using software such as Beautiful Soup and Scrapy.

[1235] 2. Data Classification:

[1236] The server uses natural language processing (NLP) techniques to categorize the collected data into categories such as firewalls, encryption technologies, and endpoint protection, using NLP libraries such as Spacy and NLTK.

[1237] 3. Enter your topic and search for experts:

[1238] Users input a topic into a dedicated terminal, for example, "responding to ransomware attacks." Based on this input, the server searches the database for relevant experts. Matching based on the search query is also performed using NLP.

[1239] 4. Expert selection and invitation:

[1240] The user selects the most suitable expert from a list of experts displayed on the device. For example, they can select an expert in ransomware countermeasures. After selection, the server sends an invitation to the selected expert via Zoom or a dedicated security conference platform.

[1241] 5. Real-time feedback:

[1242] During the meeting, the server uses speech recognition technology to convert the expert's speech into text in real time and share it with other participants. This process uses speech recognition technologies such as Google Cloud Speech-to-Text and IBM Watson. The converted speech is immediately fed back to other participants in real time.

[1243] Examples:

[1244] A user inputs a topic such as, "A specific company has been attacked by ransomware and its files have been encrypted. Recovery and countermeasures are urgently needed. We need expert opinions on whether we should comply with the attacker's demands and how to recover the data." Based on this input, the server searches for relevant experts and suggests well-known experts who are experts in ransomware countermeasures. A meeting is then held, and the experts' comments are converted into text in real time using voice recognition technology and instantly shared with other participants.

[1245] Example prompt sentence:

[1246] “Please provide a list of security experts for the following incident.

[1247] Incident details: Ransomware attack

[1248] Details: A company has been hit by a ransomware attack and their files have been encrypted. Recovery and countermeasures are urgently needed. We need expert advice on whether to comply with the attacker's demands and how to recover the data.

[1249] Run the program that generates a list of suitable experts from the system's database.

[1250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1251] Step 1:

[1252] The server collects data on the masters. It uses web scraping technologies such as Beautiful Soup and Scrapy to retrieve the masters' biographies, papers, books, interviews, etc. from the Internet. It uses a list of URLs from multiple websites as input, and stores the masters' information as structured data in a database as output.

[1253] Step 2:

[1254] The server categorizes the collected data by area of ​​expertise. The server uses natural language processing (NLP) techniques such as Spacy or NLTK to categorize the collected data into categories such as firewalls, encryption technologies, and endpoint protection. It uses the collected data as input and obtains data organized by category as output.

[1255] Step 3:

[1256] The user inputs a theme into a dedicated terminal. The user inputs a specific theme using the terminal's input interface. For example, the user might input "responding to ransomware attacks." The theme keyword is used as input, and the keyword is sent to the server as output.

[1257] Step 4:

[1258] The server searches for relevant experts based on a topic. The server uses NLP techniques to search for experts related to a topic from a database. It uses the topic entered by the user as input and generates a list of relevant experts as output.

[1259] Step 5:

[1260] The user selects the most suitable expert from the list of experts displayed on the terminal. The user checks the list and presses the select button to select. The list of experts is used as input, and the information of the selected expert is sent to the server as output.

[1261] Step 6:

[1262] The server sends an online meeting invitation to the selected expert. The server sends the invitation using Zoom or a dedicated secure conferencing platform. The server uses the selected expert's contact information as input and confirms that the invitation has been sent as output.

[1263] Step 7:

[1264] During the meeting, the server uses speech recognition technology to convert the experts' speech into text. The server uses speech recognition services such as Google Cloud Speech-to-Text and IBM Watson. The server uses the speech data from the meeting as input and obtains the text of the speech as output.

[1265] Step 8:

[1266] The server shares the textual utterances with other participants in real time. The server displays the textual utterances on the other participants' devices in real time. The server uses the textual utterance data as input and provides feedback to the participants' devices as output.

[1267] 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.

[1268] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[1269] System program processing

[1270] Master data collection

[1271] The server runs a program that collects data on the masters from the Internet, specifically using web scraping technology to obtain data such as their career histories, papers, books, and interview articles, and stores it in a database.

[1272] Data classification

[1273] The server uses natural language processing (NLP) algorithms to categorize the collected data by subject area, such as business, technology, medicine, energy, and other categories.

[1274] Enter a topic and search for experts

[1275] The user inputs a topic into a dedicated terminal. For example, the topic is "improving the manufacturing process of new materials." Based on this input, the server searches the database for relevant experts.

[1276] Selection and invitation of experts

[1277] The user selects the most suitable expert from the list of experts displayed on the device. For example, by clicking on "famous scientists in new materials," the server then sends an invitation to the selected expert via an online conference platform such as Zoom.

[1278] Real-time feedback and sentiment analysis

[1279] The device uses speech recognition technology to convert experts' comments into text in real time during the meeting and provide feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in real time during the meeting and sends the results to the server.

[1280] Specific examples

[1281] For example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[1282] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[1283] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[1284] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[1285] 4. The server sends a Zoom meeting invitation to the selected scientists.

[1286] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and send that information to the server.

[1287] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[1288] This system can efficiently collect and classify expert data, invite the most suitable experts to the meeting, and analyze and provide feedback on the user's emotional state in real time, which will help meetings proceed more smoothly and enable more effective decision-making.

[1289] The processing flow will be explained below.

[1290] Step 1:

[1291] The server runs a web scraping program to collect data on the masters. Specifically, it automatically retrieves data about the masters, such as their biographies, papers, books, and interview articles, from specific URLs and stores them in a structured format in a database.

[1292] Step 2:

[1293] The server stores the collected data in a database. Specifically, it inserts the acquired text data into the database using SQL queries and organizes and stores it by expert.

[1294] Step 3:

[1295] The server uses natural language processing (NLP) algorithms to categorize the stored data by subject area, specifically by using topic modeling and clustering techniques to categorize the data into categories such as business, technology, medicine, and energy.

[1296] Step 4:

[1297] The user inputs the topic of the meeting through the interface of the dedicated terminal, for example, "improving the manufacturing process of new materials," and clicks the search button.

[1298] Step 5:

[1299] The server searches the database based on the topic entered by the user and lists relevant experts. Specifically, it queries the database with keywords related to the topic and extracts relevant experts.

[1300] Step 6:

[1301] The server sends a list of experts found in the search to the device, and specifically makes a call to display the names and areas of expertise of the listed experts on the user's device via the API.

[1302] Step 7:

[1303] The user selects the most appropriate expert from the displayed list of experts, for example, by clicking on "famous scientists on new materials."

[1304] Step 8:

[1305] The server sends a Zoom meeting invitation to the selected experts. Specifically, it uses Zoom's API to send an invitation email containing the date and time of the meeting and a link to the selected experts.

[1306] Step 9:

[1307] Once the meeting has started, the device will convert the speech of the expert into text in real time using speech recognition technology and provide feedback to other participants. Specifically, the device converts the speech data into text and automatically highlights and displays important points.

[1308] Step 10:

[1309] The emotion engine analyzes users' emotions in real time during meetings, using facial recognition technology and voice analysis to extract emotional data from users' facial expressions, tone of voice, and choice of words.

[1310] Step 11:

[1311] The server receives the emotion data from the emotion engine and provides feedback according to the user's emotional state. For example, if the user is feeling stressed, the server sends a notification to the terminal to adjust the progress of the meeting.

[1312] Step 12:

[1313] The terminal receives notifications from the server and adjusts the progress of the meeting. Specifically, it displays a summary of questions to the expert and provides support to help the user understand the content.

[1314] Example 2

[1315] 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."

[1316] Conventional online conference systems make it difficult to efficiently search for and invite experts with specialized knowledge and provide real-time feedback during the meeting. Furthermore, there are no systems that recognize participants' emotional states during the meeting and optimize the progress of the meeting. As a result, the meeting may not proceed smoothly and decision-making may be delayed.

[1317] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting expert data, means for classifying the collected data by field of expertise, means for searching for the most suitable expert for the theme based on the classified data, means for inviting the expert selected based on the search results to an online conference, means for providing feedback of the expert's opinion during the conference in real time, and means for analyzing the emotional state of participants during the conference in real time and optimizing the progress of the conference based on the results. This makes it possible to efficiently search for and invite experts and optimize the progress based on feedback and emotions during the conference.

[1318] "Master data" refers to all information about individuals with specialized knowledge and experience, including their career history, papers, books, interviews, etc.

[1319] "Collection methods" refers to the methods used to obtain data from the internet or other sources and store it in a database.

[1320] "Means of classification by field of expertise" refers to a method of dividing collected data into specific fields of expertise or categories using natural language processing algorithms, etc.

[1321] "Means for searching for the most suitable expert for a topic" refers to a method for extracting relevant experts from a database based on an input topic.

[1322] "Means of inviting selected experts to an online conference" refers to a method of sending an invitation to an online conference to selected experts and requesting their participation.

[1323] "Means of providing real-time feedback of expert opinions during a meeting" refers to a method in which what an expert says during a meeting is converted into text using voice recognition technology and provided as feedback to other participants.

[1324] "Means for analyzing participants' emotional states in real time during a meeting" refers to a method using technology, such as an emotion recognition algorithm, to analyze participants' facial expressions and voices during a meeting and determine their emotional states.

[1325] "Means for optimizing meeting progress" refers to methods for adjusting the schedule and content of meetings based on the results of sentiment analysis to help participants understand the content.

[1326] This invention provides a system that recognizes the user's emotions and optimizes the progress of a meeting based on them by combining an emotion engine with a system that collects and classifies expert data, invites experts to online meetings, and provides real-time feedback. This system is realized by the server, terminals, users, and the emotion engine each playing a specific role.

[1327] First, the server collects data about the masters from the Internet. Specifically, it uses web scraping technology. For example, it uses Python's BeautifulSoup or Scrapy to collect data such as the master's biography, papers, books, and interview articles, and temporarily stores that data in a cache such as Redis. This collected data is finally stored in a MySQL database.

[1328] The server then categorizes the collected data using natural language processing (NLP) algorithms, using services such as Google Cloud Natural Language API to organize the data into specialties such as business, technology, medicine, and energy. This results in the database containing data already categorized by speciality.

[1329] The user inputs a topic using a dedicated terminal. For example, they input the topic "improving the manufacturing process for new materials." Based on this input, the server searches the Elasticsearch database for relevant experts. As a result of the search, a list of relevant experts is displayed on the user's terminal.

[1330] The user selects the most suitable expert from the list. For example, they can select "famous scientists in new materials." Once the selection is complete, the server invites the expert to an online meeting using the Zoom API or Google Calendar API. This sends a meeting invitation to the selected expert.

[1331] During the meeting, the device converts the expert's speech into text in real time using speech recognition technology (e.g., Google Speech-to-Text API) and provides it as feedback to other participants. In addition, the emotion engine analyzes the emotional state of each user in the meeting in real time. This emotion analysis is performed using the Microsoft Azure Emotion API. The analysis results are sent to the server, which then sends notifications to adjust the progress of the meeting based on the emotion data.

[1332] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[1333] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[1334] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[1335] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on new materials.

[1336] 4. The server sends an invitation to the selected scientists to attend the online meeting.

[1337] 5. Once the meeting begins, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[1338] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[1339] Examples of prompt sentences include:

[1340] "Find experts on manufacturing process improvements for new materials."

[1341] "Use the real-time feedback feature to analyze what experts say during meetings and provide feedback to users."

[1342] In this way, the system can efficiently collect and classify expert data, identify and invite the most suitable experts, and optimize the progress based on feedback and emotions during the meeting.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1: Collecting data on experts

[1345] The server runs a program that collects data on masters from the Internet. The input here is a list of URLs for the websites to be collected. Specifically, the server performs web scraping using BeautifulSoup and Scrapy to obtain information such as the master's career history, papers, books, and interview articles. The obtained data is temporarily stored in a Redis cache and then stored in a MySQL database.

[1346] Input: List of website URLs

[1347] Output: Data such as the master's biography, papers, books, interviews, etc.

[1348] Specific behavior:

[1349] The server performs web scraping based on the specified URL list.

[1350] The retrieved data is temporarily stored in the Redis cache.

[1351] Migrate the stored data to a MySQL database.

[1352] Step 2: Classify the data

[1353] The server classifies the collected data using a natural language processing (NLP) algorithm. The input here is expert data stored in a MySQL database. Specifically, the server analyzes the data using the Google Cloud Natural Language API and classifies the data into specialized fields such as business, technology, medicine, and energy based on the analysis results. The classified data is then stored back in the database.

[1354] Input: Master data stored in a MySQL database

[1355] Output: Classified virtuoso data

[1356] Specific behavior:

[1357] The server analyzes the data using NLP algorithms.

[1358] Categorize data by discipline.

[1359] Update the classified data into a MySQL database.

[1360] Step 3: Enter the theme

[1361] The user inputs a topic using a dedicated terminal. The input here is the topic the user wants to discuss. In concrete terms, the user inputs the topic into the input field of the terminal, and it is sent to the server. For example, the topic "improving the manufacturing process for new materials" is input.

[1362] Input: The theme entered by the user

[1363] Output: The theme sent to the server

[1364] Specific behavior:

[1365] The user enters a theme into an input field on the device.

[1366] The entered theme is sent to the server.

[1367] Step 4: Find an expert

[1368] The server searches for relevant experts from the Elasticsearch database based on the received topic. The input here is the topic submitted by the user. Specifically, the server generates an Elasticsearch query and searches the database. As a search result, it generates a list of relevant experts and displays it on the user's device.

[1369] Input: User-submitted theme

[1370] Output: A list of relevant experts

[1371] Specific behavior:

[1372] The server generates an Elasticsearch query.

[1373] Search databases and identify relevant experts.

[1374] A list of experts is displayed on the user's terminal.

[1375] Step 5: Selecting an expert

[1376] The user selects the most suitable expert from the list of experts displayed on the terminal. The input here is the displayed list of experts. In concrete terms, the user clicks on the desired expert from the list. Information on the selected expert is sent to the server.

[1377] Input: List of displayed experts

[1378] Output: Information about selected experts

[1379] Specific behavior:

[1380] The user clicks on the desired expert from the list.

[1381] The information of the selected expert is sent to the server.

[1382] Step 6: Send invitations

[1383] The server sends an online meeting invitation to the selected expert. The input here is the information of the selected expert. Specifically, the server generates a meeting invitation using the Zoom API or Google Calendar API and sends it to the expert's email address.

[1384] Input: Selected expert information

[1385] Output: Online meeting invitation

[1386] Specific behavior:

[1387] The server generates a meeting invitation using the Zoom API or Google Calendar API.

[1388] Send the invitation to the expert's email.

[1389] Step 7: Real-time feedback

[1390] The device converts the expert's speech into text in real time during the meeting and provides feedback to other participants. The input here is the expert's real-time speech. Specifically, it converts the speech into text using the Google Speech-to-Text API and displays the text to participants.

[1391] Input: Real-time expert comments

[1392] Output: Translated utterances

[1393] Specific behavior:

[1394] The expert's speech is captured as audio data.

[1395] Converts speech to text using the Google Speech-to-Text API.

[1396] Display the transcribed text to the participants.

[1397] Step 8: Sentiment analysis

[1398] The emotion engine analyzes the emotional state of each user during a meeting in real time. The input here is video and audio data from the meeting. Specifically, it analyzes the data using the Microsoft Azure Emotion API and sends the analysis results of the emotional state to the server.

[1399] Input: Video and audio data during the meeting

[1400] Output: Emotional state analysis result

[1401] Specific behavior:

[1402] Capture video and audio data.

[1403] Analyze the data using the Microsoft Azure Emotion API.

[1404] The analysis results are sent to the server.

[1405] Step 9: Coordinate the meeting

[1406] Based on information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. The input here is the analysis result of the emotional state. Specifically, the server analyzes the analysis result and takes action to adjust the progress of the meeting as necessary (e.g., summarizing comments or suggesting a break).

[1407] Input: Emotional state analysis result

[1408] Output: Notification of meeting progress adjustment

[1409] Specific behavior:

[1410] Receive and analyze the results of the emotional state analysis.

[1411] Take action to coordinate meeting progress and send notifications.

[1412] (Application example 2)

[1413] 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."

[1414] The current problem with factory production lines is the lack of means to incorporate expert knowledge in real time and monitor and optimize the emotional state of workers and operators. In particular, when improving processing methods for new materials and production processes, real-time feedback from experts and management of workers' emotional states are required.

[1415] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1416] In this invention, the server includes a means for collecting data on experts, a means for classifying the collected data by field of expertise, and a means for searching for the most suitable expert for the theme based on the classified data. This makes it possible to utilize the knowledge of experts on factory production lines and provide optimal feedback and process adjustments while monitoring the emotional states of workers and operators in real time.

[1417] "Masterpiece data" refers to information such as the careers, achievements, writings, and interview articles of experts with outstanding knowledge and experience in a particular field.

[1418] "Classification" refers to the process of organizing and structuring collected data according to specific disciplines or categories.

[1419] A "topic" refers to the topic or topic that a user wants to cover in a particular meeting or consultation.

[1420] An "expert" is an individual who has advanced knowledge or skills in a particular area of ​​expertise.

[1421] An "online meeting" refers to a virtual meeting space where multiple participants can interact in real time via the Internet.

[1422] "Feedback" refers to the process of communicating information such as advice, opinions, and evaluations provided by experts to participants in real time.

[1423] An "artificial intelligence engine" refers to a software or hardware system for performing advanced computational tasks such as data analysis, emotion recognition, and natural language processing.

[1424] "Sentiment analysis" refers to the process of determining and analyzing the emotional state of meeting participants based on their facial expressions, tone of voice, and choice of words.

[1425] "Optimization" refers to the adjustment or improvement of a system or process to maximize its performance for specific purposes or conditions.

[1426] MODE FOR CARRYING OUT THE INVENTION

[1427] This invention relates to a system for real-time production supervision on factory production lines. The system incorporates expert knowledge, monitors the emotional states of workers and robot operators, and performs a series of processes including expert data collection, classification, expert search, online conferencing, and emotion analysis to provide optimal feedback and process adjustments.

[1428] Server Roles

[1429] The server collects data on the experts from the internet. Specifically, it uses web scraping technology to retrieve information such as their careers, achievements, papers, and interviews, and stores it in a database. This data is then categorized by field of expertise using natural language processing (NLP) algorithms. For example, it can be categorized into categories such as "business," "technology," "medical care," and "energy."

[1430] Next, based on the topic entered by the user into the dedicated terminal (e.g., "processing methods for new materials"), the server searches the database for relevant experts. Once the most suitable expert is selected, the server sends the selected expert an invitation to an online meeting. This is done using the Zoom API or Microsoft Teams API.

[1431] Device Role

[1432] The device receives the topic input by the user and sends it to the server. Once the conference begins, the device converts the expert's remarks into text in real time using speech recognition technology and provides feedback to other participants.

[1433] The terminal is also equipped with an emotion analysis engine that monitors the emotional state of workers and operators in real time. This emotion engine uses, for example, the DeepFace library to recognize facial expressions. It is also capable of voice analysis, determining the emotional state of participants from their speaking style and tone of voice. The collected emotion data is sent to a server and used to optimize the progress of the meeting.

[1434] User Roles

[1435] The user inputs the topic of the meeting into a dedicated terminal. For example, by entering a topic such as "processing methods for new materials," the process of searching for the most suitable expert related to that topic begins. The user then selects the most suitable expert from a list of experts displayed on the terminal. During the meeting, the user receives feedback provided in real time and adjusts the progress based on the results of sentiment analysis.

[1436] Examples of specific examples and prompts

[1437] As a concrete example, when planning a meeting to improve manufacturing methods for industrial products by making the most of the properties of new materials, the following steps are taken:

[1438] 1. The user types "improvement of manufacturing process for new material" into the terminal.

[1439] 2. The server searches the database for relevant experts, for example, a particular scientist or engineer.

[1440] 3. The user selects and selects the most suitable expert from the list, for example, a renowned scientist on a new material.

[1441] 4. The server sends a Zoom meeting invitation to the selected expert.

[1442] 5. After the meeting starts, the device records the expert's remarks in real time and provides feedback. In addition, the emotion engine uses facial recognition technology and voice analysis to recognize the user's emotional state and sends that information to the server.

[1443] 6. Based on the information from the emotion engine, the server sends a notification to adjust the progress of the meeting if the user's emotional stress is increasing. For example, it displays a summary of the expert's remarks and takes actions to help the user understand.

[1444] An example of a prompt is as follows:

[1445] "Collect and store expert data. Use web scraping technology to retrieve expert profiles, careers, papers, and interviews, and store them in a database."

[1446] This system makes it possible to efficiently collect and classify expert data, invite the most suitable experts to meetings, and analyze and provide feedback on the user's emotional state in real time, resulting in smoother meetings and more effective decision-making.

[1447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1448] Step 1:

[1449] The server collects data on the masters. Based on the website URL list specified as input, it uses web scraping technology to obtain information such as the masters' careers, achievements, papers, and interview articles. The obtained data is stored in a database.

[1450] Step 2:

[1451] The server categorizes the collected data using natural language processing (NLP) algorithms. It takes as input the unclassified data in the database and categorizes each data into a specialized field, such as business, technology, medicine, or energy. The output is a classified dataset.

[1452] Step 3:

[1453] The user inputs the topic of the meeting into a dedicated terminal. The input is text information (e.g., "Processing method for new materials") that the user types into the terminal. The terminal then sends this input to the server.

[1454] Step 4:

[1455] The server searches the database for relevant experts based on the input topic. The input is the topic text submitted by the user, and the output is a list of relevant experts. The server searches the classification data in the database and selects the most suitable expert.

[1456] Step 5:

[1457] The user selects the most suitable expert from the list of experts displayed on the terminal. The input is the list of experts, and the expert information selected by the user is output. The selected expert is sent to the server.

[1458] Step 6:

[1459] The server sends online meeting invitations to the selected experts. The input is the experts' contact information and meeting details, and the output is the sent invitation. This uses the Zoom API or Microsoft Teams API.

[1460] Step 7:

[1461] After the conference begins, the device uses speech recognition technology to convert the expert's speech into text in real time. The input is the expert's speech data during the conference, and the output is the converted speech data. This data is immediately fed back to the other participants.

[1462] Step 8:

[1463] The device's sentiment analysis engine monitors the emotional state of participants in real time during a meeting. The input is the participants' video feeds and audio data, and the output is data representing their emotional state. This sentiment analysis is performed using libraries such as DeepFace.

[1464] Step 9:

[1465] The server optimizes the progress of the meeting based on the results of the sentiment analysis. The input is emotional state data, and the output is progress adjustments or notifications. For example, it may summarize and display the expert's comments or take actions to adjust the pace of the meeting. As a result, users can efficiently manage the progress of the meeting.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] FIG. 9 is a diagram illustrating 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 actions 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.

[1471] 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.

[1472] 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).

[1473] 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.

[1474] 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."

[1475] 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.

[1476] 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).

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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 example of a 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] The following is further disclosed regarding the above embodiment.

[1488] (Claim 1)

[1489] A means of collecting data on masters;

[1490] A means of categorizing the collected data by discipline;

[1491] A way to search for the best experts for a particular topic based on classified data, and

[1492] A means for inviting experts selected based on the search results to an online conference;

[1493] A means of providing real-time feedback of expert opinions during meetings;

[1494] A system including:

[1495] (Claim 2)

[1496] 2. The system of claim 1, wherein the data of the masters is stored in a database.

[1497] (Claim 3)

[1498] 10. The system of claim 1, wherein the system uses a natural language processing algorithm to categorize the data by subject area.

[1499] "Example 1"

[1500] (Claim 1)

[1501] A means for obtaining information about the master;

[1502] A means of classifying the acquired information by area of ​​expertise;

[1503] A way to search for the best experts for a particular topic based on classified information, and

[1504] A means for inviting experts selected based on the search results to an online conference;

[1505] A means of providing real-time feedback on what experts say during meetings, and

[1506] A system including:

[1507] (Claim 2)

[1508] 2. The system of claim 1, wherein the information of the masters is stored in a database.

[1509] (Claim 3)

[1510] 10. The system of claim 1, wherein the system uses natural language processing algorithms to categorize information by subject area.

[1511] "Application Example 1"

[1512] (Claim 1)

[1513] A means of collecting data on masters;

[1514] A means of categorizing the collected data by discipline;

[1515] A way to search for the best experts for a particular topic based on classified data, and

[1516] A means for inviting experts selected based on the search results to an online conference;

[1517] A means of providing real-time feedback of expert opinions during meetings;

[1518] A means of categorizing the collected data into categories such as firewalls, encryption technologies, and endpoint protection;

[1519] A means for converting the speech of experts during a meeting into text using speech recognition technology;

[1520] A way to share textual comments with other participants in real time,

[1521] A system including:

[1522] (Claim 2)

[1523] 2. The system of claim 1, wherein the data of the masters is stored in a database.

[1524] (Claim 3)

[1525] 10. The system of claim 1, wherein the system uses a natural language processing algorithm to categorize the data by subject area.

[1526] "Example 2: Combining Emotion Engines"

[1527] (Claim 1)

[1528] A means of collecting data on masters;

[1529] A means of categorizing the collected data by discipline;

[1530] A way to search for the best experts for a particular topic based on classified data, and

[1531] A means for inviting experts selected based on the search results to an online conference;

[1532] A means of providing real-time feedback of expert opinions during meetings;

[1533] A method for analyzing the emotional state of participants in real time during a meeting and optimizing the progress of the meeting based on the results.

[1534] A system including:

[1535] (Claim 2)

[1536] 2. The system of claim 1, wherein the data of the masters is stored in a database.

[1537] (Claim 3)

[1538] 10. The system of claim 1, wherein the system uses a natural language processing algorithm to categorize the data by subject area.

[1539] "Application example 2 when combining emotion engines"

[1540] (Claim 1)

[1541] A means of collecting data on masters;

[1542] A means of categorizing the collected data by discipline;

[1543] A way to search for the best experts for a particular topic based on classified data, and

[1544] A means for inviting experts selected based on the search results to an online conference;

[1545] A means of providing real-time feedback of expert opinions during meetings;

[1546] A means for analyzing the emotions of participants during a meeting using an artificial intelligence engine;

[1547] A means for optimizing the progress of a meeting based on the results of sentiment analysis;

[1548] A system including:

[1549] (Claim 2)

[1550] 2. The system of claim 1, wherein the data of the masters is stored in a database.

[1551] (Claim 3)

[1552] 10. The system of claim 1, wherein the system uses a natural language processing algorithm to categorize the data by subject area. [Explanation of symbols]

[1553] 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. A means of collecting data on masters; A means of categorizing the collected data by discipline; A way to search for the best experts for a particular topic based on classified data, and A means for inviting experts selected based on the search results to an online conference; A means of providing real-time feedback of expert opinions during meetings; A system including:

2. 2. The system of claim 1, wherein the data of the masters is stored in a database.

3. The system of claim 1 , wherein the system uses a natural language processing algorithm to categorize the data by subject area.

Images