System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to input a research theme and purpose; means for a server to collect relevant AI from information sources using a generative data model; means for the server to analyze the information and extract information relevant to the user's research theme; means for the server to generate reports and presentation materials based on the extracted information; and means for the server to deliver the generated materials to the user and provide necessary feedback and corrections.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] In cancer research, education, and awareness activities, collecting and analyzing vast amounts of information requires a great deal of time and effort. Furthermore, obtaining reliable information efficiently requires a high level of specialized knowledge, which places a significant burden on the average user. Furthermore, creating easy-to-understand reports and presentation materials based on the collected information requires information organization and editing skills. The present invention aims to solve these problems and provide a system that efficiently provides reliable information while reducing the burden on users. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems using the following means. The system includes a means for a user to input a research topic and purpose, a means for a server to collect relevant data from information sources using a generative AI model, a means for the server to analyze the information and extract data related to the user's research topic, a means for the server to generate reports and presentation materials based on the extracted data, and a means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. Furthermore, the system includes a means for the server to set up online consultations with expert researchers and writers, allowing the user to request additional information or explanations, thereby improving the accuracy and reliability of information collection. The system also includes a means for the server to use a generative AI model to filter information collection, prioritizing analysis of highly reliable information, thereby ensuring the reliability of the information provided to the user.

[0006] A "research topic" is a specific topic or subject that a user wishes to research.

[0007] "Purpose" refers to the results or uses that the user wants to achieve based on the research theme, such as creating a report or generating presentation materials.

[0008] A "generative AI model" is a computer program that uses artificial intelligence technology to generate and analyze data and extract useful information.

[0009] A "server" is a computer system that receives requests from users and uses generative AI models to collect, analyze, and generate information.

[0010] "Sources" are trusted sources, such as databases or websites, that a generative AI model can access to gather data.

[0011] "Relevant data" refers to data collected from sources related to the research topic and are the data points that are the subject of analysis.

[0012] "Extraction" is the process of selecting important items from the collected data.

[0013] A "report" is a document created based on extracted data that summarizes the research results.

[0014] "Presentation materials" are materials that visually express extracted data in an easy-to-understand manner and are used for presentations and explanations.

[0015] "Delivery" refers to the act of providing a completed report or presentation materials to a user.

[0016] "Feedback" refers to the exchange of opinions and corrections regarding materials provided by users.

[0017] "Revising" is the act of improving the content of a document based on user feedback.

[0018] A "specialist researcher" is a researcher or analyst who is knowledgeable in a particular field.

[0019] A "writer" is someone who specializes in writing and whose role is to express specialized content in an easy-to-understand manner. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention provides an online research service system in which users input their research topic and purpose, collect and analyze information using a generative AI model, and finally generate and deliver materials. A specific embodiment of this system is shown below.

[0042] System Overview

[0043] Accepting user requests

[0044] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. At this time, detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. The input information is sent to the server.

[0045] Information gathering

[0046] The server analyzes the request and triggers a generative AI model to gather relevant information from trusted sources (e.g., medical paper databases, news sites, official cancer research sites, etc.). The generative AI model then generates a specialized search query and accesses the source to crawl the data.

[0047] Examples:

[0048] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[0049] Data analysis and extraction

[0050] The server stores the collected information in a database and analyzes it using a generative AI model, which filters out noise and removes duplicate data to extract the necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.).

[0051] Examples:

[0052] The abstracts of each paper are analyzed using natural language processing technology to extract descriptions of the effectiveness of the treatment.

[0053] Generate materials

[0054] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the extracted data, and generates charts and graphs to present the data in a visually understandable manner.

[0055] Examples:

[0056] Create graphs comparing the effectiveness of each treatment and generate explanatory reports.

[0057] Delivery and feedback

[0058] The server delivers the generated materials to the user's device. If the user checks the materials and requests any necessary corrections or additional information, they send feedback to the server again. The server then corrects and updates the materials based on the user's feedback.

[0059] Consultation support with experts

[0060] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[0061] Examples:

[0062] A user requests more detailed information about immunotherapy, and researchers gather the additional information and incorporate it into the report.

[0063] Implementation method

[0064] The implementation of this system requires the following major components:

[0065] 1. A user terminal equipped with a web form for accepting requests

[0066] 2. Server responsible for collecting and analyzing information

[0067] 3. Generative AI Models

[0068] 4. Access to reliable sources of information

[0069] 5. Data filtering and analysis algorithms

[0070] 6. Report and presentation generation tools

[0071] 7. Online consultation interface with experts

[0072] Example

[0073] For example, if a user requests research on the latest lung cancer treatments, they input their research topic and purpose using their device. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about treatment effectiveness. The server then generates graphs comparing treatment effects and creates and delivers a comprehensive report. The user can review the delivered materials and, if necessary, consult with experts via the server to incorporate additional information or corrections. This series of processes allows users to obtain efficient and reliable research results.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user enters the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via a terminal. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered in the request form. This input information is then sent to the server.

[0077] Step 2:

[0078] The server receives the user's request and activates the generative AI model, which generates a search query based on the request and prepares access to reliable sources of information (e.g., medical paper databases, news sites, official research institution websites, etc.).

[0079] Step 3:

[0080] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[0081] Examples:

[0082] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[0083] Step 4:

[0084] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[0085] Step 5:

[0086] The server uses the generative AI model to analyze the stored data, where data cleansing (removal of noise data, elimination of duplicate data) is performed and reliable information is filtered.

[0087] Step 6:

[0088] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[0089] Examples:

[0090] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[0091] Step 7:

[0092] The server generates reports and presentation materials based on the extracted data, including charts and graphs to visually represent the data.

[0093] Examples:

[0094] Graphs are created based on the extracted effectiveness data for each treatment, and a report including an explanation is generated.

[0095] Step 8:

[0096] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review and provide feedback.

[0097] Step 9:

[0098] The user reviews the materials, sends any necessary corrections or requests for additional information from the terminal to the server, and, if necessary, requests online consultation with expert researchers or writers.

[0099] Step 10:

[0100] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[0101] Step 11:

[0102] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[0103] Example 1

[0104] 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."

[0105] The present invention relates to an online research service that enables users to accurately and quickly achieve their research themes and goals. However, conventional research systems require a significant amount of time for information gathering and data analysis, making it difficult to create the high-quality reports and presentation materials users require. Furthermore, feedback and revisions are not provided efficiently, making it difficult to respond to user requests promptly. Furthermore, there is no way to obtain detailed information or explanations through consultation with experts, making it difficult to meet user needs.

[0106] 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.

[0107] In this invention, the server includes: a means for a user to input a research topic and purpose; a means for transmitting the user's input to the server; a means for the server to collect relevant data from information sources using a generative AI model; a means for the server to store and analyze the collected information in a database; a means for the server to analyze the information and extract data related to the user's research topic; a means for the server to generate reports and presentation materials based on the extracted data; and a means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This allows users to quickly and efficiently obtain high-quality research results and can also respond to requests for necessary corrections and additional information. Furthermore, a means for obtaining detailed information and explanations through online consultations with professional researchers and writers is provided, thereby meeting a variety of user needs.

[0108] A "research topic" specifies a specific issue or topic that a user wants to research.

[0109] "Objective" indicates the specific goal the user wants to achieve through the survey.

[0110] "User" refers to an individual or organization that uses this system to collect information on a research topic and use the analysis results.

[0111] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that allows users to input their research topic and purpose and connect to the system.

[0112] "Server" refers to a computer system that receives requests from users and uses generative AI models to collect information, analyze it, manage databases, generate materials, and respond to feedback.

[0113] "Generative AI model" refers to an artificial intelligence algorithm that automatically collects, analyzes, and generates research information.

[0114] "Sources" refer to databases, websites, official organizations, etc. that provide information related to the research topic.

[0115] "Database" refers to an information management system that stores and manages information collected by a server and extracts necessary data.

[0116] "Analysis" refers to the process of analyzing collected information, filtering out noisy data, removing redundant data, and extracting necessary information.

[0117] "Material" refers to a collection of information generated in a format specified by the user (report, presentation materials, etc.).

[0118] "Delivery" refers to the process by which the server transmits and provides the generated materials to the user.

[0119] "Feedback" refers to the process by which a User reviews delivered materials and requests any necessary corrections or additional information.

[0120] "Researcher" refers to an expert who has specialized knowledge on a specific research topic and provides users with detailed information and explanations.

[0121] A "writer" refers to a specialist who generates materials based on collected information and writes them to be provided to users.

[0122] "Online consultation" refers to a communication session over the Internet between a user and a researcher or writer, set up by a server.

[0123] "Filtering" refers to the process of sorting collected data in order to prioritize and analyze highly reliable information.

[0124] MODE FOR CARRYING OUT THE INVENTION

[0125] This invention provides an online research service in which users input their research topic and objectives, use generative AI models to collect and analyze information, and ultimately generate and deliver materials. To implement this invention, the following main components are required:

[0126] 1. A user terminal equipped with a web form for accepting requests

[0127] Users use a web form to input detailed information such as research topic and purpose, etc. The device used can be an electronic device such as a PC, tablet, or smartphone.

[0128] 2. Server responsible for collecting and analyzing information

[0129] The server receives the request sent by the user, uses the generative AI model to collect relevant information, and stores that information in a database. The server also analyzes the collected information and extracts specific data according to the user's request. This requires a server with ample computing power and storage capacity.

[0130] 3. Generative AI Models

[0131] A generative AI model is an artificial intelligence algorithm that automates a series of processes, such as information gathering, analysis, and document generation. In particular, it utilizes natural language processing (NLP) technology to summarize acquired data, extract important information, and automatically generate documents.

[0132] 4. Access to reliable sources of information

[0133] The server uses a generative AI model to collect data from trusted sources (e.g., academic paper databases, public information sites, etc.). For example, to obtain data on the latest medical research, it uses the PubMed API.

[0134] 5. Data filtering and analysis algorithms

[0135] The server uses algorithms to filter out noise data and remove duplicate data in the early stages of analysis, extracting only the necessary information.

[0136] 6. Report and presentation generation tools

[0137] It is equipped with tools to generate documents in formats that meet user requirements based on collected and analyzed data, including the automatic generation of charts and graphs.

[0138] 7. Online consultation interface with experts

[0139] The server provides an interface for online consultation between users and experts (researchers and writers), allowing users to obtain additional information and detailed explanations.

[0140] As a concrete example, let us consider the case where a user requests research on the latest lung cancer treatments. The user uses a terminal to input the research topic ("latest lung cancer treatments") and purpose ("creating presentation materials"), and then submits detailed information ("research subject: research over the past five years," scope, deadline, desired data format, etc.).

[0141] The server then uses the generative AI model to retrieve relevant paper metadata (title, author, abstract, publication date) from the PubMed API using a query such as "lung cancer AND treatment AND latest." The server stores the collected information in a database and analyzes it using natural language processing techniques to extract key points about the effectiveness of treatments.

[0142] The server then creates graphs comparing the effectiveness of each treatment and generates a comprehensive report. The resulting data is delivered to the user's device for review. If necessary, the user can submit feedback requests for additional information or corrections, and the server will respond.

[0143] Furthermore, if a user requests "I would like to consult with an expert," the server will use an online consultation tool to set up an online meeting between the user and an expert, allowing them to obtain detailed information and explanations.

[0144] Example prompt sentence:

[0145] "I would like to research the latest lung cancer treatments. My goal is to create presentation materials, and my research will focus mainly on the latest treatments, their effectiveness, and side effects. The deadline is one week."

[0146] The present invention allows users to obtain high-quality research results quickly and efficiently, and also allows for requests for necessary corrections and additional information. Furthermore, a system is provided that can meet the diverse needs of users through online consultations with experts.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1: Accepting a user request

[0149] A user accesses the system using a terminal and inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials). They can also input detailed information (research subject, scope, deadline, desired data format, etc.). The input information is sent from the terminal to the server as an HTTP request.

[0150] Input: Research topic, purpose, detailed information (research subject, scope, deadline, desired data format, etc.)

[0151] Output: Request data sent to the server

[0152] Specific action: A user enters a research topic and purpose into a web form and clicks the submit button.

[0153] Step 2: Gather information

[0154] The server analyzes the received request and activates a generative AI model. The generative AI model generates specialized search queries against reliable sources (e.g., medical paper databases, news sites, official websites, etc.) to crawl the information. The server uses the generative AI model to collect the information and stores it in a database.

[0155] Input: Request data

[0156] Output: Collected information data

[0157] Specific operation: The server generates the query "lung cancer AND treatment AND latest," and the generative AI model uses the PubMed API to collect related information.

[0158] Step 3: Data analysis and extraction

[0159] The server stores the collected information in a database and performs analysis. During the analysis process, noise data is filtered out and duplicate data is removed, and necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.) is extracted.

[0160] Input: Collected information data

[0161] Output: Parsed information data

[0162] Specific operation: The server analyzes the abstract of each paper using natural language processing technology and extracts information about the effectiveness of treatments.

[0163] Step 4: Generate materials

[0164] Based on the analyzed information, the server generates materials in the format desired by the user (reports, presentation materials, etc.) It also creates charts and graphs to present the data visually in an easy-to-understand manner.

[0165] Input: Parsed information data

[0166] Output: Generated materials (reports, presentation materials)

[0167] Specific operation: The server creates a graph comparing the effects of each treatment and automatically generates a document containing an explanation.

[0168] Step 5: Delivery and feedback

[0169] The server sends the completed document to the user's device. If the user checks the document and requests any necessary corrections or additional information, they send their feedback to the server. The server then corrects and updates the document based on the user's feedback.

[0170] Input: Finished materials, user feedback

[0171] Output: Corrected and updated materials

[0172] Specific operation: The server sends the generated data to the user's email address, and the user fills in the feedback form with comments such as "I would like more data" and "I would like to change the color of the graph."

[0173] Step 6: Expert consultation support

[0174] If a user wishes to consult with a professional researcher or writer, the server will use online consultation tools (e.g., Zoom, Teams) to set up a consultation session, through which the user can obtain additional information and detailed explanations.

[0175] Input: User's consultation request

[0176] Output: A configured online consultation session

[0177] Specific behavior: A user requests "I would like to consult with an expert," and the server uses the consultation tool to send a meeting link to the user.

[0178] (Application example 1)

[0179] 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."

[0180] In today's virtual stores, it is difficult for users to quickly and efficiently gather product information and easily create comparison materials based on that information. Furthermore, there are limited ways to flexibly obtain appropriate feedback and additional information. Under these circumstances, there is a need for advanced information research systems to support purchasing decisions.

[0181] 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.

[0182] In this invention, the server includes a means for a user to input a research topic and purpose in the virtual store, a means for collecting related data using a generative AI model, and a means for analyzing the collected information and extracting data related to the user's needs, thereby enabling users to quickly and accurately compare and consider product information in the virtual store and automatically generate materials for that purpose.

[0183] "Research Topic" refers to a particular issue or problem that a User specifies as the subject of research.

[0184] "Objective" refers to the goal or outcome that the user is trying to achieve through research.

[0185] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate and analyze information.

[0186] "Sources" refer to trusted websites, databases, etc. that you access to gather data.

[0187] "Data" refers to a collection of information or facts that are collected and analyzed.

[0188] "Analysis" refers to the process of examining and analyzing collected data to find meaning and patterns.

[0189] "Extraction" refers to selecting the necessary information from the analyzed data.

[0190] A "report" refers to a document summarizing the results of an investigation.

[0191] "Presentation materials" refers to slides and documents used to visually represent and explain research results.

[0192] "Delivery" refers to providing the generated materials to the user.

[0193] "Feedback" refers to opinions and requests for corrections regarding materials received from users.

[0194] "Web crawling" refers to the techniques and processes used to automatically collect information on the Internet.

[0195] "Smart Device" means a user device that is connected to the Internet and capable of collecting and displaying information.

[0196] "Expert researchers and authors" refer to experts who have knowledge and experience in a particular field and can provide additional information and explanations to users.

[0197] "Filtering" refers to the process of prioritizing highly reliable and relevant information.

[0198] The present invention provides a system that allows users to efficiently conduct product research in a virtual store. A specific embodiment of the system is described below.

[0199] System Overview and Configuration

[0200] The user inputs the research topic and purpose using a smart device. For example, the research topic can be "creating a review and comparison document on the latest vitamin C-containing skin care products." The information entered by the user is sent to the server.

[0201] Information gathering

[0202] The server invokes the generative AI model to gather relevant data from trusted sources, specifically using web crawling techniques to gather information such as product names, prices, and links, using the requests and BeautifulSoup libraries.

[0203] Data analysis and extraction

[0204] The server analyzes the collected information and extracts the necessary data. Generative AI models and natural language processing techniques are used for data analysis. Filtering functions are used to prioritize reliable information.

[0205] Generate materials

[0206] The server generates materials in the user's desired format (reports, presentation materials, etc.) based on the extracted data. At this time, an AI model is used to create review and comparison materials. OpenAI's API is used to generate materials using AI.

[0207] Delivery and feedback

[0208] The generated materials are delivered to the user's smart device. The user can review the materials and send any necessary feedback to the server, which then corrects the materials.

[0209] Consultation support with experts

[0210] If the user wishes, the server can set up an online consultation with a researcher or author in the field, who can provide additional information and detailed explanations.

[0211] Specific examples

[0212] For example, if a user requests research on "the latest skin care products with vitamin C," they can enter the following prompt:

[0213] Write a review and comparison of the latest Vitamin C skin care products.

[0214] product:

[0215] 1. ABC Vitamin C Serum - $29.99

[0216] 2. XYZ Vitamin C Cream - $35.99

[0217] 3. LMN Vitamin C Essence - $45.00

[0218] By feeding this prompt into a generative AI model, a detailed report is generated that includes reviews and comparisons of each product, allowing users to make more efficient product choices.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The user inputs the research topic and purpose.

[0222] Using a smart device, users input their research topic (e.g., the latest vitamin C-containing skin care products) and goal (e.g., to create a product review and comparison document), including information such as the target market and delivery date.

[0223] Step 2:

[0224] The server uses a generative AI model to collect relevant data from sources.

[0225] The server uses a generative AI model to collect relevant data from reliable sources based on the research topic entered by the user, and uses web crawling technology to generate search queries and collect product information (e.g., product names, prices, links) from websites that have corresponding data.

[0226] Step 3:

[0227] The server analyzes the collected information and extracts data related to the user's research topic.

[0228] The server applies natural language processing technology to analyze the collected information and extracts the necessary data, specifically, product names, prices, review content, etc., and filters the information to prioritize the most reliable information for analysis.

[0229] Step 4:

[0230] The server generates reports and presentation materials based on the extracted data.

[0231] The server generates materials in the format specified by the user (reports, presentation materials, etc.) based on the analyzed data. This process involves using a generative AI model to create reviews and comparison materials for each product. Specifically, it creates graphs and tables that visually summarize each product's features, price, review content, etc.

[0232] Step 5:

[0233] The server delivers the generated materials to the user, who provides feedback and corrections.

[0234] The generated materials are sent to the user's smart device. The user reviews the materials and sends any necessary feedback or correction requests to the server. The server then corrects and updates the materials based on the received feedback.

[0235] Step 6:

[0236] The server sets up online consultations with expert researchers and authors.

[0237] If the user needs additional information or detailed explanation, the server will set up an online consultation with expert researchers and authors, through which the user can get more detailed information or further explanation.

[0238] The specific operations and inputs / outputs at each step are shown below:

[0239] Step 1 Input: Research topic, objectives, additional information (e.g. target market, deadline)

[0240] Step 1 Output: User request data

[0241] Step 2 Input: User Request Data

[0242] Step 2 Output: Collected Product Data

[0243] Input for Step 3: Collected Product Data

[0244] Output of Step 3: Parsed product data

[0245] Input for Step 4: Parsed Product Data

[0246] Step 4 Output: Generated reports and presentations

[0247] Step 5 Input: Generated materials, user feedback

[0248] Step 5 Output: Corrected and updated documentation

[0249] Step 6: Requesting additional information or clarification from the user

[0250] Step 6 Output: Additional information and detailed commentary from experts

[0251] 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.

[0252] The present invention is a system that provides an online research service that combines an emotion engine that recognizes the user's emotions, collects and analyzes reliable information based on the research theme and purpose, and finally generates and delivers materials. A specific embodiment of this system is shown below.

[0253] System Overview

[0254] Accepting user requests

[0255] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. This input information is then sent to the server.

[0256] Information gathering

[0257] The server receives the user's request and activates a generative AI model to collect relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). The generative AI model generates specialized search queries and accesses the sources to crawl the data.

[0258] Examples:

[0259] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[0260] Data analysis and extraction

[0261] The server temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion engine that recognizes emotions from user input and applies information collection and analysis methods according to those emotions.

[0262] Examples:

[0263] If a user types "I'm in a hurry," the emotion engine recognizes the urgency and quickly collects, analyzes, and delivers information.

[0264] Prioritizing information based on emotions

[0265] The server uses the emotion engine to prioritize information based on the user's emotions, thereby efficiently providing the information that is of most interest to the user.

[0266] Examples:

[0267] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[0268] Generate materials

[0269] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the analyzed data. At this time, the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[0270] Examples:

[0271] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[0272] Delivery and feedback

[0273] The server delivers the generated materials to the user's terminal and receives feedback from the user. If the user checks the materials and requests any necessary corrections or additional information, the server responds accordingly.

[0274] Consultation support with experts

[0275] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[0276] Examples:

[0277] The user requests a more detailed explanation and obtains additional information through consultation with an expert.

[0278] Implementation method

[0279] To implement this system, the following major components are required:

[0280] 1. A user terminal equipped with a web form for accepting requests

[0281] 2. Server responsible for collecting and analyzing information

[0282] 3. Generative AI Models

[0283] 4. Access to reliable sources of information

[0284] 5. Data filtering and analysis algorithms

[0285] 6. Emotion Engine

[0286] 7. Report and presentation generation tools

[0287] 8. Online consultation interface with experts

[0288] Example

[0289] For example, if a user requests research on the latest lung cancer treatments and inputs feelings of anxiety, the emotion engine recognizes the anxiety. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about the treatment's effectiveness. The emotion engine then prioritizes information that provides reassurance and issues a visually reassuring report. The materials are delivered to the user and revised based on their feedback. If necessary, additional information and detailed explanations can be added through consultation with experts. This series of processes provides efficient and reliable research results that take the user's emotions into account.

[0290] The processing flow will be explained below.

[0291] Step 1:

[0292] The user inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via their terminal. The emotion engine then extracts emotions (e.g., anxiety, excitement, urgency, etc.) from the user's input and a simple questionnaire. This input and emotion information are then sent to the server.

[0293] Step 2:

[0294] The server receives the user's request and emotion information, and then activates the generative AI model. The server generates a search query based on the user's request and prepares to access reliable information sources (e.g., medical paper databases, news sites, official research institution websites, etc.).

[0295] Step 3:

[0296] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[0297] Examples:

[0298] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[0299] Step 4:

[0300] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[0301] Step 5:

[0302] The server uses a generative AI model to analyze the stored data, including an emotion engine that applies information gathering and analysis techniques based on the emotions derived from the user's input.

[0303] Examples:

[0304] If a user types "I'm in a hurry," the emotion engine will recognize the urgency and quickly collect, analyze, and deliver information.

[0305] Step 6:

[0306] The server uses the emotion engine to prioritize information based on the user's emotions, allowing the server to efficiently provide the information that the user is most interested in.

[0307] Examples:

[0308] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[0309] Step 7:

[0310] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[0311] Examples:

[0312] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[0313] Step 8:

[0314] The server generates reports and presentation materials based on the extracted data, and the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[0315] Examples:

[0316] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[0317] Step 9:

[0318] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review the materials and make any necessary corrections or request additional information.

[0319] Step 10:

[0320] Users can review the materials, send requests for necessary corrections or additional information to the server from their terminal, and, if necessary, request online consultation with professional researchers or writers.

[0321] Step 11:

[0322] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[0323] Step 12:

[0324] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[0325] Example 2

[0326] 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."

[0327] Conventional online research services have struggled to prioritize information based on user sentiment or generate the materials users desire related to their research topic. They also face challenges in efficiently collecting and analyzing reliable information. Furthermore, efficient consultation with expert researchers and writers is difficult, and feedback responses to enhance user satisfaction are insufficient.

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

[0329] In this invention, the server includes means for a user to input a research topic and purpose, means for the server to collect related information from information sources using a generative AI model, means for the server to analyze the collected data and extract information related to the user's research topic, means for the server to perform analysis using an emotion recognition engine, means for the server to generate visual materials based on the extracted information, and means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This enables the provision of information according to the user's emotions, efficient collection and analysis of reliable information, and effective consultation with experts and feedback response.

[0330] A "research topic" is a specific topic or area that a user sets as the subject of research.

[0331] "Objectives" are the specific goals or objectives that a user wants to achieve when conducting research.

[0332] A "generative AI model" is an algorithmic system that uses artificial intelligence to perform natural language processing and data analysis.

[0333] "Sources" refer to external databases and websites that provide data and information needed for research.

[0334] An "emotion recognition engine" is a system that analyzes emotions based on user input and selects an appropriate processing method.

[0335] "Visual materials" are documents that are displayed visually, such as reports or presentations generated based on analyzed information.

[0336] "Feedback" is the process by which users provide corrections and comments on received material.

[0337] "Expert researchers and writers" are experts with knowledge and experience in a particular topic or field.

[0338] To implement this invention, a user terminal, a server, a generative AI model, an emotion recognition engine, and a database are required. A specific embodiment of this system is shown below.

[0339] First, the user inputs the research topic and purpose. For example, the user inputs "latest lung cancer treatment methods" and "creating presentation materials" from the terminal. The input information is then sent from the terminal to the server.

[0340] The server receives the user's request and launches a generative AI model. This generative AI model is, for example, a GPT-based model for natural language processing. The server collects relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). Specifically, the generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of the relevant paper.

[0341] The server then temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion recognition engine that recognizes emotions from the user's input and applies information collection and analysis methods based on that emotion. For example, if the user inputs "I'm in a hurry," the emotion recognition engine will recognize the urgency and quickly collect, analyze, and deliver the information.

[0342] The server then uses an emotion recognition engine to prioritize information based on the user's emotions, allowing it to efficiently provide the information the user is most interested in. For example, if the user types "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[0343] The server then generates materials in the user's desired format (report, presentation, etc.) based on the analyzed data. The emotion recognition engine uses expressions that match the user's emotions, providing materials in a format that is more user-friendly. For example, if a user requests presentation materials, the emotion recognition engine can sense the user's excitement and generate visually appealing slides.

[0344] Finally, the server delivers the generated materials to the user's device and receives feedback from the user. If the user reviews the materials and requests any necessary corrections or additional information, the server responds accordingly. If the user wishes, the server can also set up an online consultation with a professional researcher or writer. Through this consultation, the user can request additional information or detailed explanations.

[0345] An example of a specific prompt is, "Please hurry and provide reliable information about the latest lung cancer treatments. I'm feeling anxious."

[0346] This makes it possible to provide high-quality materials that correspond to the user's emotions and research needs, thereby increasing user satisfaction.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] Accepting user requests

[0350] The user enters the research topic and purpose from the device. For example, the user enters "latest lung cancer treatments" and "creating presentation materials" into a web form on the device.

[0351] Input: User's research topic and purpose

[0352] Output: Send request containing the entered request data

[0353] Specific operation: The user fills in detailed information (such as research subject, deadline, and desired data format) in each field of the web form and clicks the "Submit" button, which causes the device to send the entered information to the server.

[0354] Step 2:

[0355] Information gathering

[0356] The server receives the user's request and launches a generative AI model, which then gathers relevant information from trusted sources. For example, the generative AI model creates a query for "latest lung cancer treatments" and accesses the PubMed API to retrieve metadata for related papers.

[0357] Input: User request data

[0358] Output: A dataset containing the relevant information collected

[0359] How it works: The server calls the generative AI model to generate a specialized search query, which the generative AI model executes to efficiently crawl data from sources and retrieve relevant information.

[0360] Step 3:

[0361] Data analysis and extraction

[0362] The server temporarily stores the collected data in a database and performs data analysis using a generative AI model. This analysis includes an emotion recognition engine. For example, the emotion recognition engine recognizes the user's emotions and applies an analysis method according to the emotion.

[0363] Input: Collected relevant information

[0364] Output: Parsed dataset

[0365] How it works: The server stores the collected data in a database, the generative AI model performs natural language processing to extract key points from the data, and the emotion recognition engine selects an analysis method based on the emotion entered by the user.

[0366] Step 4:

[0367] Prioritizing information based on emotions

[0368] The server uses an emotion recognition engine to prioritize information based on the user's emotions. For example, if the user inputs "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[0369] Input: Parsed dataset and user emotion information

[0370] Output: prioritized information

[0371] How it works: The server applies an emotion recognition engine and a prioritization algorithm based on the user's input emotion. Information is organized around the content that the user is most interested in.

[0372] Step 5:

[0373] Generate materials

[0374] The server generates materials in the format desired by the user (reports, presentation materials) based on the analyzed data. At this time, an emotion recognition engine uses expressions that match the user's emotions. For example, in the case of presentation materials, visually appealing slides are generated.

[0375] Input: prioritized information and user preferred format

[0376] Output: Generated materials (reports and slides)

[0377] Specific operation: The server uses a document generation tool to create visually appealing documents based on an emotion recognition engine. The document generation tool uses templates and design elements to create high-quality documents.

[0378] Step 6:

[0379] Delivery and feedback

[0380] The server delivers the generated materials to the user's terminal and receives feedback from the user. The user checks the materials and requests any necessary corrections or additional information.

[0381] Input: Generated material

[0382] Output: User feedback and correction requests

[0383] Specific operation: The server sends the generated document file to the user's device. The user reads the document and uses the feedback form or comment function to request corrections or add additional information.

[0384] Step 7:

[0385] Consultation support with experts

[0386] If the user wishes, the server will set up an online consultation with a professional researcher or writer.

[0387] Input: User's consultation request

[0388] Output: Responses to inquiries and supplementary information

[0389] Specific operation: The user fills out a request form stating, "I would like to consult with an expert." The server schedules a session with the expert using a video conferencing tool or similar. After the consultation is completed, the user is provided with supplementary information and detailed explanations.

[0390] (Application example 2)

[0391] 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."

[0392] Current challenges in logistics centers include a work environment that ignores the emotional state of workers and inefficient work instructions. Failure to consider appropriate breaks and work priorities increases fatigue and stress, leading to problems with reduced work efficiency and quality. Furthermore, research does not take into account the emotions of users when collecting and analyzing information, creating a need for reliable results that are delivered quickly and efficiently.

[0393] 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.

[0394] In this invention, the server includes: [means for a user to input a research topic and purpose;] [means for the server to collect relevant data from information sources using a generated AI model; and] [means for recognizing the facial expressions and tone of voice of workers in real time and analyzing their emotional state.] This allows the emotional state of workers to be grasped in real time and optimal work instructions to be generated, thereby improving work efficiency and the work environment at logistics centers. Furthermore, reliable information collection and analysis based on user requests can be realized, allowing for fast and efficient provision of materials.

[0395] "Means for users to input research topic and purpose" refers to an interface that allows users to electronically input their research purpose and detailed research topic.

[0396] "Means for a server to collect relevant data from information sources using a generated AI model" refers to means for automatically collecting relevant data from reliable information sources using an artificial intelligence model generated by a server.

[0397] "Means for the server to analyze information and extract data related to the user's research topic" refers to the means for the server to analyze the information collected and select data that matches the research topic desired by the user.

[0398] "Means for generating reports and presentation materials based on data extracted by the server" refers to means for using data analyzed and extracted by the server to create reports and presentation materials tailored to the user's needs.

[0399] "Means for the server to deliver generated materials to the user and provide necessary feedback and corrections" refers to means for the server to provide generated reports and materials to the user and make corrections based on feedback from the user.

[0400] "Means for recognizing workers' facial expressions and tone of voice in real time and analyzing their emotional state" refers to means for monitoring workers' facial expressions and tone of voice in real time and evaluating their emotional state using emotion recognition technology.

[0401] The "means for analyzing emotion data and generating instructions for optimizing work efficiency" refers to a means for analyzing collected emotion data and generating optimal instructions for improving work efficiency.

[0402] This invention is a system that improves work efficiency in logistics centers and provides optimal work instructions based on the emotions of workers. This system incorporates a worker emotion recognition function as part of the collection and analysis of reliable information based on the user's research theme and purpose, and the creation of necessary materials.

[0403] System configuration

[0404] Hardware and software used

[0405] Hardware: Smartphones (Android and iOS), Head-Mounted Displays (HMDs: for example, Microsoft HoloLens)

[0406] Software: Emotion recognition engine (e.g., Affectiva SDK), generative AI model (e.g., OpenAI GPT-4), cloud server (e.g., AWS EC2 instance)

[0407] Program processing

[0408] overview

[0409] 1. Emotion Recognition: A worker wears a smartphone or HMD and launches the application. The camera captures the worker's facial expressions and tone of voice, and the emotion recognition engine (Affectiva SDK) analyzes their emotional state in real time. This data is sent to a cloud server.

[0410] 2. Data transmission and analysis: The cloud server (AWS EC2 instance) analyzes the received emotion data using a generative AI model (GPT-4) to evaluate the level of stress, fatigue, and anxiety. Based on this evaluation, work priorities and break instructions are optimized.

[0411] 3. Generating and providing work instructions: The generative AI model combines the analysis results with operational data to generate optimal work instructions. For example, it can recommend a break for a tired worker and assign urgent tasks to other workers. This information is fed back to the smartphone or HMD in real time.

[0412] Specific examples

[0413] Usage Scenarios

[0414] A worker at a logistics center starts his morning shift. He launches an emotion recognition app on his smartphone, which begins facial recognition and voice tone analysis. After 45 minutes, the emotion engine detects "fatigue," and a notification appears on A's smartphone saying, "Your fatigue level is increasing. We recommend you take a 10-minute break." After the break, the most important tasks are listed, allowing A to resume work efficiently.

[0415] Prompt Sentence Examples

[0416] An example prompt for a generative AI model is:

[0417] markdown

[0418] "Worker A's emotional data indicates that he is becoming increasingly fatigued for tasks with an urgency of C. Generate a message to encourage him to take a break, followed by suggestions to optimize the prioritization of his work."

[0419] This will enable optimal work instructions to be provided in real time based on the analysis results of the emotion recognition and generative AI model, enabling the realization of an efficient and healthy working environment in logistics centers. Furthermore, since it is possible to simultaneously collect reliable information based on research themes and quickly generate materials, a powerful system will be built that can meet the diverse needs of users.

[0420] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0421] Step 1:

[0422] The user puts on a smartphone or head-mounted display and launches the application. This causes the device's camera to begin capturing the worker's facial expressions and tone of voice in real time. The input is real-time facial expression data and tone of voice data from the camera, and the output is raw data sent to the emotion recognition engine.

[0423] Step 2:

[0424] An emotion recognition engine (e.g., Affectiva SDK) analyzes real-time facial expression data and tone of voice data. The input data includes multiple facial expressions and tone of voice data, and the output is an analysis result of the emotional state (e.g., fatigue, anxiety, stress, etc.) extracted from the data.

[0425] Step 3:

[0426] The server receives the emotion analysis results sent from the emotion recognition engine and stores the analyzed data on a cloud server (AWS EC2 instance). The input is the emotion analysis results, and processing is performed to store the emotional state in a database.

[0427] Step 4:

[0428] Based on the emotional state data received by the cloud server, a generative AI model (e.g., GPT-4) is launched and analyzed. The input is the emotional state data, and the output is the intermediate result for generating instruction prompts based on that data to improve work efficiency.

[0429] Step 5:

[0430] Based on the generated prompt sentence, the generative AI model generates optimal work instructions for improving work efficiency. For example, based on the input prompt sentence, it generates a message recommending that a fatigued worker take a break, or an instruction to assign a highly urgent task to another worker. The output is a specific work instruction message.

[0431] Step 6:

[0432] The cloud server then sends the generated work instruction messages to a smartphone or head-mounted display, providing real-time feedback to the worker. The input is the work instruction message output by the generative AI model, and the output is specific instructions displayed on the worker's device.

[0433] Step 7:

[0434] The worker actually performs the work based on the work instruction message received. For example, he / she takes a break or engages in other urgent work. The input is the feedback work instruction, and the output is the worker's action (performing the work, taking a break, etc.).

[0435] This series of processes enables real-time monitoring of workers' emotional states and the use of generative AI models to generate and provide optimal work instructions, thereby improving work efficiency and the working environment at logistics centers.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] [Second embodiment]

[0440] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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."

[0452] The present invention provides an online research service system in which users input their research topic and purpose, collect and analyze information using a generative AI model, and finally generate and deliver materials. A specific embodiment of this system is shown below.

[0453] System Overview

[0454] Accepting user requests

[0455] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. At this time, detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. The input information is sent to the server.

[0456] Information gathering

[0457] The server analyzes the request and triggers a generative AI model to gather relevant information from trusted sources (e.g., medical paper databases, news sites, official cancer research sites, etc.). The generative AI model then generates a specialized search query and accesses the source to crawl the data.

[0458] Examples:

[0459] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[0460] Data analysis and extraction

[0461] The server stores the collected information in a database and analyzes it using a generative AI model, which filters out noise and removes duplicate data to extract the necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.).

[0462] Examples:

[0463] The abstracts of each paper are analyzed using natural language processing technology to extract descriptions of the effectiveness of the treatment.

[0464] Generate materials

[0465] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the extracted data, and generates charts and graphs to present the data in a visually understandable manner.

[0466] Examples:

[0467] Create graphs comparing the effectiveness of each treatment and generate explanatory reports.

[0468] Delivery and feedback

[0469] The server delivers the generated materials to the user's device. If the user checks the materials and requests any necessary corrections or additional information, they send feedback to the server again. The server then corrects and updates the materials based on the user's feedback.

[0470] Consultation support with experts

[0471] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[0472] Examples:

[0473] A user requests more detailed information about immunotherapy, and researchers gather the additional information and incorporate it into the report.

[0474] Implementation method

[0475] The implementation of this system requires the following major components:

[0476] 1. A user terminal equipped with a web form for accepting requests

[0477] 2. Server responsible for collecting and analyzing information

[0478] 3. Generative AI Models

[0479] 4. Access to reliable sources of information

[0480] 5. Data filtering and analysis algorithms

[0481] 6. Report and presentation generation tools

[0482] 7. Interface for online consultation with experts

[0483] Example

[0484] For example, if a user requests research on the latest lung cancer treatments, they input their research topic and purpose using their device. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about treatment effectiveness. The server then generates graphs comparing treatment effects and creates and delivers a comprehensive report. The user can review the delivered materials and, if necessary, consult with experts via the server to incorporate additional information or corrections. This series of processes allows users to obtain efficient and reliable research results.

[0485] The processing flow will be explained below.

[0486] Step 1:

[0487] The user enters the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via a terminal. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered in the request form. This input information is then sent to the server.

[0488] Step 2:

[0489] The server receives the user's request and activates the generative AI model, which generates a search query based on the request and prepares access to reliable sources of information (e.g., medical paper databases, news sites, official research institution websites, etc.).

[0490] Step 3:

[0491] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[0492] Examples:

[0493] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[0494] Step 4:

[0495] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[0496] Step 5:

[0497] The server uses the generative AI model to analyze the stored data, where data cleansing (removal of noise data, elimination of duplicate data) is performed and reliable information is filtered.

[0498] Step 6:

[0499] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[0500] Examples:

[0501] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[0502] Step 7:

[0503] The server generates reports and presentation materials based on the extracted data, including charts and graphs to visually represent the data.

[0504] Examples:

[0505] Graphs are created based on the extracted effectiveness data for each treatment, and a report including an explanation is generated.

[0506] Step 8:

[0507] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review and provide feedback.

[0508] Step 9:

[0509] The user reviews the materials, sends any necessary corrections or requests for additional information from the terminal to the server, and, if necessary, requests online consultation with expert researchers or writers.

[0510] Step 10:

[0511] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[0512] Step 11:

[0513] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[0514] Example 1

[0515] 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."

[0516] The present invention relates to an online research service that enables users to accurately and quickly achieve their research themes and goals. However, conventional research systems require a significant amount of time for information gathering and data analysis, making it difficult to create the high-quality reports and presentation materials users require. Furthermore, feedback and revisions are not provided efficiently, making it difficult to respond to user requests promptly. Furthermore, there is no way to obtain detailed information or explanations through consultation with experts, making it difficult to meet user needs.

[0517] 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.

[0518] In this invention, the server includes: a means for a user to input a research topic and purpose; a means for transmitting the user's input to the server; a means for the server to collect relevant data from information sources using a generative AI model; a means for the server to store and analyze the collected information in a database; a means for the server to analyze the information and extract data related to the user's research topic; a means for the server to generate reports and presentation materials based on the extracted data; and a means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This allows users to quickly and efficiently obtain high-quality research results and can also respond to requests for necessary corrections and additional information. Furthermore, a means for obtaining detailed information and explanations through online consultations with professional researchers and writers is provided, thereby meeting a variety of user needs.

[0519] A "research topic" specifies a specific issue or topic that a user wants to research.

[0520] "Objective" indicates the specific goal the user wants to achieve through the survey.

[0521] "User" refers to an individual or organization that uses this system to collect information on a research topic and use the analysis results.

[0522] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that allows users to input their research topic and purpose and connect to the system.

[0523] "Server" refers to a computer system that receives requests from users and uses generative AI models to collect information, analyze it, manage databases, generate materials, and respond to feedback.

[0524] "Generative AI model" refers to an artificial intelligence algorithm that automatically collects, analyzes, and generates research information.

[0525] "Sources" refer to databases, websites, official organizations, etc. that provide information related to the research topic.

[0526] "Database" refers to an information management system that stores and manages information collected by a server and extracts necessary data.

[0527] "Analysis" refers to the process of analyzing collected information, filtering out noisy data, removing redundant data, and extracting necessary information.

[0528] "Material" refers to a collection of information generated in a format specified by the user (report, presentation materials, etc.).

[0529] "Delivery" refers to the process by which the server transmits and provides the generated materials to the user.

[0530] "Feedback" refers to the process by which a User reviews delivered materials and requests any necessary corrections or additional information.

[0531] "Researcher" refers to an expert who has specialized knowledge on a specific research topic and provides users with detailed information and explanations.

[0532] A "writer" refers to a specialist who generates materials based on collected information and writes them to be provided to users.

[0533] "Online consultation" refers to a communication session over the Internet between a user and a researcher or writer, set up by a server.

[0534] "Filtering" refers to the process of sorting collected data in order to prioritize and analyze highly reliable information.

[0535] MODE FOR CARRYING OUT THE INVENTION

[0536] This invention provides an online research service in which users input their research topic and objectives, use generative AI models to collect and analyze information, and ultimately generate and deliver materials. To implement this invention, the following main components are required:

[0537] 1. A user terminal equipped with a web form for accepting requests

[0538] Users use a web form to input detailed information such as research topic and purpose, etc. The device used can be an electronic device such as a PC, tablet, or smartphone.

[0539] 2. Server responsible for collecting and analyzing information

[0540] The server receives the request sent by the user, uses the generative AI model to collect relevant information, and stores that information in a database. The server also analyzes the collected information and extracts specific data according to the user's request. This requires a server with ample computing power and storage capacity.

[0541] 3. Generative AI Models

[0542] A generative AI model is an artificial intelligence algorithm that automates a series of processes, such as information gathering, analysis, and document generation. In particular, it utilizes natural language processing (NLP) technology to summarize acquired data, extract important information, and automatically generate documents.

[0543] 4. Access to reliable sources of information

[0544] The server uses a generative AI model to collect data from trusted sources (e.g., academic paper databases, public information sites, etc.). For example, to obtain data on the latest medical research, it uses the PubMed API.

[0545] 5. Data filtering and analysis algorithms

[0546] The server uses algorithms to filter out noise data and remove duplicate data in the early stages of analysis, extracting only the necessary information.

[0547] 6. Report and presentation generation tools

[0548] It is equipped with tools to generate documents in formats that meet user requirements based on collected and analyzed data, including the automatic generation of charts and graphs.

[0549] 7. Online consultation interface with experts

[0550] The server provides an interface for online consultation between users and experts (researchers and writers), allowing users to obtain additional information and detailed explanations.

[0551] As a concrete example, let us consider the case where a user requests research on the latest lung cancer treatments. The user uses a terminal to input the research topic ("latest lung cancer treatments") and purpose ("creating presentation materials"), and then submits detailed information ("research subject: research over the past five years," scope, deadline, desired data format, etc.).

[0552] The server then uses the generative AI model to retrieve relevant paper metadata (title, author, abstract, publication date) from the PubMed API using a query such as "lung cancer AND treatment AND latest." The server stores the collected information in a database and analyzes it using natural language processing techniques to extract key points about the effectiveness of treatments.

[0553] The server then creates graphs comparing the effectiveness of each treatment and generates a comprehensive report. The resulting data is delivered to the user's device for review. If necessary, the user can submit feedback requests for additional information or corrections, and the server will respond.

[0554] Furthermore, if a user requests "I would like to consult with an expert," the server will use an online consultation tool to set up an online meeting between the user and an expert, allowing them to obtain detailed information and explanations.

[0555] Example prompt sentence:

[0556] "I would like to research the latest lung cancer treatments. My goal is to create presentation materials, and my research will focus mainly on the latest treatments, their effectiveness, and side effects. The deadline is one week."

[0557] The present invention allows users to obtain high-quality research results quickly and efficiently, and also allows for requests for necessary corrections and additional information. Furthermore, a system is provided that can meet the diverse needs of users through online consultations with experts.

[0558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0559] Step 1: Accepting a user request

[0560] A user accesses the system using a terminal and inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials). They can also input detailed information (research subject, scope, deadline, desired data format, etc.). The input information is sent from the terminal to the server as an HTTP request.

[0561] Input: Research topic, purpose, detailed information (research subject, scope, deadline, desired data format, etc.)

[0562] Output: Request data sent to the server

[0563] Specific action: A user enters a research topic and purpose into a web form and clicks the submit button.

[0564] Step 2: Gather information

[0565] The server analyzes the received request and activates a generative AI model. The generative AI model generates specialized search queries against reliable sources (e.g., medical paper databases, news sites, official websites, etc.) to crawl the information. The server uses the generative AI model to collect the information and stores it in a database.

[0566] Input: Request data

[0567] Output: Collected information data

[0568] Specific operation: The server generates the query "lung cancer AND treatment AND latest," and the generative AI model uses the PubMed API to collect related information.

[0569] Step 3: Data analysis and extraction

[0570] The server stores the collected information in a database and performs analysis. During the analysis process, noise data is filtered out and duplicate data is removed, and necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.) is extracted.

[0571] Input: Collected information data

[0572] Output: Parsed information data

[0573] Specific operation: The server analyzes the abstract of each paper using natural language processing technology and extracts information about the effectiveness of treatments.

[0574] Step 4: Generate materials

[0575] Based on the analyzed information, the server generates materials in the format desired by the user (reports, presentation materials, etc.) It also creates charts and graphs to present the data visually in an easy-to-understand manner.

[0576] Input: Parsed information data

[0577] Output: Generated materials (reports, presentation materials)

[0578] Specific operation: The server creates a graph comparing the effects of each treatment and automatically generates a document containing an explanation.

[0579] Step 5: Delivery and feedback

[0580] The server sends the completed document to the user's device. If the user checks the document and requests any necessary corrections or additional information, they send their feedback to the server. The server then corrects and updates the document based on the user's feedback.

[0581] Input: Finished materials, user feedback

[0582] Output: Corrected and updated materials

[0583] Specific operation: The server sends the generated data to the user's email address, and the user fills in the feedback form with comments such as "I would like more data" and "I would like to change the color of the graph."

[0584] Step 6: Expert consultation support

[0585] If a user wishes to consult with a professional researcher or writer, the server will use online consultation tools (e.g., Zoom, Teams) to set up a consultation session, through which the user can obtain additional information and detailed explanations.

[0586] Input: User's consultation request

[0587] Output: A configured online consultation session

[0588] Specific behavior: A user requests "I would like to consult with an expert," and the server uses the consultation tool to send a meeting link to the user.

[0589] (Application example 1)

[0590] 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."

[0591] In today's virtual stores, it is difficult for users to quickly and efficiently gather product information and easily create comparison materials based on that information. Furthermore, there are limited ways to flexibly obtain appropriate feedback and additional information. Under these circumstances, there is a need for advanced information research systems to support purchasing decisions.

[0592] 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.

[0593] In this invention, the server includes a means for a user to input a research topic and purpose in the virtual store, a means for collecting related data using a generative AI model, and a means for analyzing the collected information and extracting data related to the user's needs, thereby enabling users to quickly and accurately compare and consider product information in the virtual store and automatically generate materials for that purpose.

[0594] "Research Topic" refers to a particular issue or problem that a User specifies as the subject of research.

[0595] "Objective" refers to the goal or outcome that the user is trying to achieve through research.

[0596] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate and analyze information.

[0597] "Sources" refer to trusted websites, databases, etc. that you access to gather data.

[0598] "Data" refers to a collection of information or facts that are collected and analyzed.

[0599] "Analysis" refers to the process of examining and analyzing collected data to find meaning and patterns.

[0600] "Extraction" refers to selecting the necessary information from the analyzed data.

[0601] A "report" refers to a document summarizing the results of an investigation.

[0602] "Presentation materials" refers to slides and documents used to visually represent and explain research results.

[0603] "Delivery" refers to providing the generated materials to the user.

[0604] "Feedback" refers to opinions and requests for corrections regarding materials received from users.

[0605] "Web crawling" refers to the techniques and processes used to automatically collect information on the Internet.

[0606] "Smart Device" means a user device that is connected to the Internet and capable of collecting and displaying information.

[0607] "Expert researchers and authors" refer to experts who have knowledge and experience in a particular field and can provide additional information and explanations to users.

[0608] "Filtering" refers to the process of prioritizing highly reliable and relevant information.

[0609] The present invention provides a system that allows users to efficiently conduct product research in a virtual store. A specific embodiment of the system is described below.

[0610] System Overview and Configuration

[0611] The user inputs the research topic and purpose using a smart device. For example, the research topic can be "creating a review and comparison document on the latest vitamin C-containing skin care products." The information entered by the user is sent to the server.

[0612] Information gathering

[0613] The server invokes the generative AI model to gather relevant data from trusted sources, specifically using web crawling techniques to gather information such as product names, prices, and links, using the requests and BeautifulSoup libraries.

[0614] Data analysis and extraction

[0615] The server analyzes the collected information and extracts the necessary data. Generative AI models and natural language processing techniques are used for data analysis. Filtering functions are used to prioritize reliable information.

[0616] Generate materials

[0617] The server generates materials in the user's desired format (reports, presentation materials, etc.) based on the extracted data. At this time, an AI model is used to create review and comparison materials. OpenAI's API is used to generate materials using AI.

[0618] Delivery and feedback

[0619] The generated materials are delivered to the user's smart device. The user can review the materials and send any necessary feedback to the server, which then corrects the materials.

[0620] Consultation support with experts

[0621] If the user wishes, the server can set up an online consultation with a researcher or author in the field, who can provide additional information and detailed explanations.

[0622] Specific examples

[0623] For example, if a user requests research on "the latest skin care products with vitamin C," they can enter the following prompt:

[0624] Write a review and comparison of the latest Vitamin C skin care products.

[0625] product:

[0626] 1. ABC Vitamin C Serum - $29.99

[0627] 2. XYZ Vitamin C Cream - $35.99

[0628] 3. LMN Vitamin C Essence - $45.00

[0629] By feeding this prompt into a generative AI model, a detailed report is generated that includes reviews and comparisons of each product, allowing users to make more efficient product choices.

[0630] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0631] Step 1:

[0632] The user inputs the research topic and purpose.

[0633] Using a smart device, users input their research topic (e.g., the latest vitamin C-containing skin care products) and goal (e.g., to create a product review and comparison document), including information such as the target market and delivery date.

[0634] Step 2:

[0635] The server uses a generative AI model to collect relevant data from sources.

[0636] The server uses a generative AI model to collect relevant data from reliable sources based on the research topic entered by the user, and uses web crawling technology to generate search queries and collect product information (e.g., product names, prices, links) from websites that have corresponding data.

[0637] Step 3:

[0638] The server analyzes the collected information and extracts data related to the user's research topic.

[0639] The server applies natural language processing technology to analyze the collected information and extracts the necessary data, specifically, product names, prices, review content, etc., and filters the information to prioritize the most reliable information for analysis.

[0640] Step 4:

[0641] The server generates reports and presentation materials based on the extracted data.

[0642] The server generates materials in the format specified by the user (reports, presentation materials, etc.) based on the analyzed data. This process involves using a generative AI model to create reviews and comparison materials for each product. Specifically, it creates graphs and tables that visually summarize each product's features, price, review content, etc.

[0643] Step 5:

[0644] The server delivers the generated materials to the user, who provides feedback and corrections.

[0645] The generated materials are sent to the user's smart device. The user reviews the materials and sends any necessary feedback or correction requests to the server. The server then corrects and updates the materials based on the received feedback.

[0646] Step 6:

[0647] The server sets up online consultations with expert researchers and authors.

[0648] If the user needs additional information or detailed explanation, the server will set up an online consultation with expert researchers and authors, through which the user can get more detailed information or further explanation.

[0649] The specific operations and inputs / outputs at each step are shown below:

[0650] Step 1 Input: Research topic, objectives, additional information (e.g. target market, deadline)

[0651] Step 1 Output: User request data

[0652] Step 2 Input: User Request Data

[0653] Step 2 Output: Collected Product Data

[0654] Input for Step 3: Collected Product Data

[0655] Output of Step 3: Parsed product data

[0656] Input for Step 4: Parsed Product Data

[0657] Step 4 Output: Generated reports and presentations

[0658] Step 5 Input: Generated materials, user feedback

[0659] Step 5 Output: Corrected and updated documentation

[0660] Step 6: Requesting additional information or clarification from the user

[0661] Step 6 Output: Additional information and detailed commentary from experts

[0662] 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.

[0663] The present invention is a system that provides an online research service that combines an emotion engine that recognizes the user's emotions, collects and analyzes reliable information based on the research theme and purpose, and finally generates and delivers materials. A specific embodiment of this system is shown below.

[0664] System Overview

[0665] Accepting user requests

[0666] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. This input information is then sent to the server.

[0667] Information gathering

[0668] The server receives the user's request and activates a generative AI model to collect relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). The generative AI model generates specialized search queries and accesses the sources to crawl the data.

[0669] Examples:

[0670] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[0671] Data analysis and extraction

[0672] The server temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion engine that recognizes emotions from user input and applies information collection and analysis methods according to those emotions.

[0673] Examples:

[0674] If a user types "I'm in a hurry," the emotion engine recognizes the urgency and quickly collects, analyzes, and delivers information.

[0675] Prioritizing information based on emotions

[0676] The server uses the emotion engine to prioritize information based on the user's emotions, thereby efficiently providing the information that is of most interest to the user.

[0677] Examples:

[0678] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[0679] Generate materials

[0680] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the analyzed data. At this time, the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[0681] Examples:

[0682] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[0683] Delivery and feedback

[0684] The server delivers the generated materials to the user's terminal and receives feedback from the user. If the user checks the materials and requests any necessary corrections or additional information, the server responds accordingly.

[0685] Consultation support with experts

[0686] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[0687] Examples:

[0688] The user requests a more detailed explanation and obtains additional information through consultation with an expert.

[0689] Implementation method

[0690] To implement this system, the following major components are required:

[0691] 1. A user terminal equipped with a web form for accepting requests

[0692] 2. Server responsible for collecting and analyzing information

[0693] 3. Generative AI Models

[0694] 4. Access to reliable sources of information

[0695] 5. Data filtering and analysis algorithms

[0696] 6. Emotion Engine

[0697] 7. Report and presentation generation tools

[0698] 8. Online consultation interface with experts

[0699] Example

[0700] For example, if a user requests research on the latest lung cancer treatments and inputs feelings of anxiety, the emotion engine recognizes the anxiety. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about the treatment's effectiveness. The emotion engine then prioritizes information that provides reassurance and issues a visually reassuring report. The materials are delivered to the user and revised based on their feedback. If necessary, additional information and detailed explanations can be added through consultation with experts. This series of processes provides efficient and reliable research results that take the user's emotions into account.

[0701] The processing flow will be explained below.

[0702] Step 1:

[0703] The user inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via their terminal. The emotion engine then extracts emotions (e.g., anxiety, excitement, urgency, etc.) from the user's input and a simple questionnaire. This input and emotion information are then sent to the server.

[0704] Step 2:

[0705] The server receives the user's request and emotion information, and then activates the generative AI model. The server generates a search query based on the user's request and prepares to access reliable information sources (e.g., medical paper databases, news sites, official research institution websites, etc.).

[0706] Step 3:

[0707] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[0708] Examples:

[0709] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[0710] Step 4:

[0711] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[0712] Step 5:

[0713] The server uses a generative AI model to analyze the stored data, including an emotion engine that applies information gathering and analysis techniques based on the emotions derived from the user's input.

[0714] Examples:

[0715] If a user types "I'm in a hurry," the emotion engine will recognize the urgency and quickly collect, analyze, and deliver information.

[0716] Step 6:

[0717] The server uses the emotion engine to prioritize information based on the user's emotions, allowing the server to efficiently provide the information that the user is most interested in.

[0718] Examples:

[0719] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[0720] Step 7:

[0721] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[0722] Examples:

[0723] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[0724] Step 8:

[0725] The server generates reports and presentation materials based on the extracted data, and the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[0726] Examples:

[0727] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[0728] Step 9:

[0729] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review the materials and make any necessary corrections or request additional information.

[0730] Step 10:

[0731] Users can review the materials, send requests for necessary corrections or additional information to the server from their terminal, and, if necessary, request online consultation with professional researchers or writers.

[0732] Step 11:

[0733] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[0734] Step 12:

[0735] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[0736] Example 2

[0737] 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."

[0738] Conventional online research services have struggled to prioritize information based on user sentiment or generate the materials users desire related to their research topic. They also face challenges in efficiently collecting and analyzing reliable information. Furthermore, efficient consultation with expert researchers and writers is difficult, and feedback responses to enhance user satisfaction are insufficient.

[0739] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0740] In this invention, the server includes means for a user to input a research topic and purpose, means for the server to collect related information from information sources using a generative AI model, means for the server to analyze the collected data and extract information related to the user's research topic, means for the server to perform analysis using an emotion recognition engine, means for the server to generate visual materials based on the extracted information, and means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This enables the provision of information according to the user's emotions, efficient collection and analysis of reliable information, and effective consultation with experts and feedback response.

[0741] A "research topic" is a specific topic or area that a user sets as the subject of research.

[0742] "Objectives" are the specific goals or objectives that a user wants to achieve when conducting research.

[0743] A "generative AI model" is an algorithmic system that uses artificial intelligence to perform natural language processing and data analysis.

[0744] "Sources" refer to external databases and websites that provide data and information needed for research.

[0745] An "emotion recognition engine" is a system that analyzes emotions based on user input and selects an appropriate processing method.

[0746] "Visual materials" are documents that are displayed visually, such as reports or presentations generated based on analyzed information.

[0747] "Feedback" is the process by which users provide corrections and comments on received material.

[0748] "Expert researchers and writers" are experts with knowledge and experience in a particular topic or field.

[0749] To implement this invention, a user terminal, a server, a generative AI model, an emotion recognition engine, and a database are required. A specific embodiment of this system is shown below.

[0750] First, the user inputs the research topic and purpose. For example, the user inputs "latest lung cancer treatment methods" and "creating presentation materials" from the terminal. The input information is then sent from the terminal to the server.

[0751] The server receives the user's request and launches a generative AI model. This generative AI model is, for example, a GPT-based model for natural language processing. The server collects relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). Specifically, the generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of the relevant paper.

[0752] The server then temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion recognition engine that recognizes emotions from the user's input and applies information collection and analysis methods based on that emotion. For example, if the user inputs "I'm in a hurry," the emotion recognition engine will recognize the urgency and quickly collect, analyze, and deliver the information.

[0753] The server then uses an emotion recognition engine to prioritize information based on the user's emotions, allowing it to efficiently provide the information the user is most interested in. For example, if the user types "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[0754] The server then generates materials in the user's desired format (report, presentation, etc.) based on the analyzed data. The emotion recognition engine uses expressions that match the user's emotions, providing materials in a format that is more user-friendly. For example, if a user requests presentation materials, the emotion recognition engine can sense the user's excitement and generate visually appealing slides.

[0755] Finally, the server delivers the generated materials to the user's device and receives feedback from the user. If the user reviews the materials and requests any necessary corrections or additional information, the server responds accordingly. If the user wishes, the server can also set up an online consultation with a professional researcher or writer. Through this consultation, the user can request additional information or detailed explanations.

[0756] An example of a specific prompt is, "Please hurry and provide reliable information about the latest lung cancer treatments. I'm feeling anxious."

[0757] This makes it possible to provide high-quality materials that correspond to the user's emotions and research needs, thereby increasing user satisfaction.

[0758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0759] Step 1:

[0760] Accepting user requests

[0761] The user enters the research topic and purpose from the device. For example, the user enters "latest lung cancer treatments" and "creating presentation materials" into a web form on the device.

[0762] Input: User's research topic and purpose

[0763] Output: Send request containing the entered request data

[0764] Specific operation: The user fills in detailed information (such as research subject, deadline, and desired data format) in each field of the web form and clicks the "Submit" button, which causes the device to send the entered information to the server.

[0765] Step 2:

[0766] Information gathering

[0767] The server receives the user's request and launches a generative AI model, which then gathers relevant information from trusted sources. For example, the generative AI model creates a query for "latest lung cancer treatments" and accesses the PubMed API to retrieve metadata for related papers.

[0768] Input: User request data

[0769] Output: A dataset containing the relevant information collected

[0770] How it works: The server calls the generative AI model to generate a specialized search query, which the generative AI model executes to efficiently crawl data from sources and retrieve relevant information.

[0771] Step 3:

[0772] Data analysis and extraction

[0773] The server temporarily stores the collected data in a database and performs data analysis using a generative AI model. This analysis includes an emotion recognition engine. For example, the emotion recognition engine recognizes the user's emotions and applies an analysis method according to the emotion.

[0774] Input: Collected relevant information

[0775] Output: Parsed dataset

[0776] How it works: The server stores the collected data in a database, the generative AI model performs natural language processing to extract key points from the data, and the emotion recognition engine selects an analysis method based on the emotion entered by the user.

[0777] Step 4:

[0778] Prioritizing information based on emotions

[0779] The server uses an emotion recognition engine to prioritize information based on the user's emotions. For example, if the user inputs "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[0780] Input: Parsed dataset and user emotion information

[0781] Output: prioritized information

[0782] How it works: The server applies an emotion recognition engine and a prioritization algorithm based on the user's input emotion. Information is organized around the content that the user is most interested in.

[0783] Step 5:

[0784] Generate materials

[0785] The server generates materials in the format desired by the user (reports, presentation materials) based on the analyzed data. At this time, an emotion recognition engine uses expressions that match the user's emotions. For example, in the case of presentation materials, visually appealing slides are generated.

[0786] Input: prioritized information and user preferred format

[0787] Output: Generated materials (reports and slides)

[0788] Specific operation: The server uses a document generation tool to create visually appealing documents based on an emotion recognition engine. The document generation tool uses templates and design elements to create high-quality documents.

[0789] Step 6:

[0790] Delivery and feedback

[0791] The server delivers the generated materials to the user's terminal and receives feedback from the user. The user checks the materials and requests any necessary corrections or additional information.

[0792] Input: Generated material

[0793] Output: User feedback and correction requests

[0794] Specific operation: The server sends the generated document file to the user's device. The user reads the document and uses the feedback form or comment function to request corrections or add additional information.

[0795] Step 7:

[0796] Consultation support with experts

[0797] If the user wishes, the server will set up an online consultation with a professional researcher or writer.

[0798] Input: User's consultation request

[0799] Output: Responses to inquiries and supplementary information

[0800] Specific operation: The user fills out a request form stating, "I would like to consult with an expert." The server schedules a session with the expert using a video conferencing tool or similar. After the consultation is completed, the user is provided with supplementary information and detailed explanations.

[0801] (Application example 2)

[0802] 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."

[0803] Current challenges in logistics centers include a work environment that ignores the emotional state of workers and inefficient work instructions. Failure to consider appropriate breaks and work priorities increases fatigue and stress, leading to problems with reduced work efficiency and quality. Furthermore, research does not take into account the emotions of users when collecting and analyzing information, creating a need for reliable results that are delivered quickly and efficiently.

[0804] 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.

[0805] In this invention, the server includes: [means for a user to input a research topic and purpose;] [means for the server to collect relevant data from information sources using a generated AI model; and] [means for recognizing the facial expressions and tone of voice of workers in real time and analyzing their emotional state.] This allows the emotional state of workers to be grasped in real time and optimal work instructions to be generated, thereby improving work efficiency and the work environment at logistics centers. Furthermore, reliable information collection and analysis based on user requests can be realized, allowing for fast and efficient provision of materials.

[0806] "Means for users to input research topic and purpose" refers to an interface that allows users to electronically input their research purpose and detailed research topic.

[0807] "Means for a server to collect relevant data from information sources using a generated AI model" refers to means for automatically collecting relevant data from reliable information sources using an artificial intelligence model generated by a server.

[0808] "Means for the server to analyze information and extract data related to the user's research topic" refers to the means for the server to analyze the information collected and select data that matches the research topic desired by the user.

[0809] "Means for generating reports and presentation materials based on data extracted by the server" refers to means for using data analyzed and extracted by the server to create reports and presentation materials tailored to the user's needs.

[0810] "Means for the server to deliver generated materials to the user and provide necessary feedback and corrections" refers to means for the server to provide generated reports and materials to the user and make corrections based on feedback from the user.

[0811] "Means for recognizing workers' facial expressions and tone of voice in real time and analyzing their emotional state" refers to means for monitoring workers' facial expressions and tone of voice in real time and evaluating their emotional state using emotion recognition technology.

[0812] The "means for analyzing emotion data and generating instructions for optimizing work efficiency" refers to a means for analyzing collected emotion data and generating optimal instructions for improving work efficiency.

[0813] This invention is a system that improves work efficiency in logistics centers and provides optimal work instructions based on the emotions of workers. This system incorporates a worker emotion recognition function as part of the collection and analysis of reliable information based on the user's research theme and purpose, and the creation of necessary materials.

[0814] System configuration

[0815] Hardware and software used

[0816] Hardware: Smartphones (Android and iOS), Head-Mounted Displays (HMDs: for example, Microsoft HoloLens)

[0817] Software: Emotion recognition engine (e.g., Affectiva SDK), generative AI model (e.g., OpenAI GPT-4), cloud server (e.g., AWS EC2 instance)

[0818] Program processing

[0819] overview

[0820] 1. Emotion Recognition: A worker wears a smartphone or HMD and launches the application. The camera captures the worker's facial expressions and tone of voice, and the emotion recognition engine (Affectiva SDK) analyzes their emotional state in real time. This data is sent to a cloud server.

[0821] 2. Data transmission and analysis: The cloud server (AWS EC2 instance) analyzes the received emotion data using a generative AI model (GPT-4) to evaluate the level of stress, fatigue, and anxiety. Based on this evaluation, work priorities and break instructions are optimized.

[0822] 3. Generating and providing work instructions: The generative AI model combines the analysis results with operational data to generate optimal work instructions. For example, it can recommend a break for a tired worker and assign urgent tasks to other workers. This information is fed back to the smartphone or HMD in real time.

[0823] Specific examples

[0824] Usage Scenarios

[0825] A worker at a logistics center starts his morning shift. He launches an emotion recognition app on his smartphone, which begins facial recognition and voice tone analysis. After 45 minutes, the emotion engine detects "fatigue," and a notification appears on A's smartphone saying, "Your fatigue level is increasing. We recommend you take a 10-minute break." After the break, the most important tasks are listed, allowing A to resume work efficiently.

[0826] Prompt Sentence Examples

[0827] An example prompt for a generative AI model is:

[0828] markdown

[0829] "Worker A's emotional data indicates that he is becoming increasingly fatigued for tasks with an urgency of C. Generate a message to encourage him to take a break, followed by suggestions to optimize the prioritization of his work."

[0830] This will enable optimal work instructions to be provided in real time based on the analysis results of the emotion recognition and generative AI model, enabling the realization of an efficient and healthy working environment in logistics centers. Furthermore, since it is possible to simultaneously collect reliable information based on research themes and quickly generate materials, a powerful system will be built that can meet the diverse needs of users.

[0831] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0832] Step 1:

[0833] The user puts on a smartphone or head-mounted display and launches the application. This causes the device's camera to begin capturing the worker's facial expressions and tone of voice in real time. The input is real-time facial expression data and tone of voice data from the camera, and the output is raw data sent to the emotion recognition engine.

[0834] Step 2:

[0835] An emotion recognition engine (e.g., Affectiva SDK) analyzes real-time facial expression data and tone of voice data. The input data includes multiple facial expressions and tone of voice data, and the output is an analysis result of the emotional state (e.g., fatigue, anxiety, stress, etc.) extracted from the data.

[0836] Step 3:

[0837] The server receives the emotion analysis results sent from the emotion recognition engine and stores the analyzed data on a cloud server (AWS EC2 instance). The input is the emotion analysis results, and processing is performed to store the emotional state in a database.

[0838] Step 4:

[0839] Based on the emotional state data received by the cloud server, a generative AI model (e.g., GPT-4) is launched and analyzed. The input is the emotional state data, and the output is the intermediate result for generating instruction prompts based on that data to improve work efficiency.

[0840] Step 5:

[0841] Based on the generated prompt sentence, the generative AI model generates optimal work instructions for improving work efficiency. For example, based on the input prompt sentence, it generates a message recommending that a fatigued worker take a break, or an instruction to assign a highly urgent task to another worker. The output is a specific work instruction message.

[0842] Step 6:

[0843] The cloud server then sends the generated work instruction messages to a smartphone or head-mounted display, providing real-time feedback to the worker. The input is the work instruction message output by the generative AI model, and the output is specific instructions displayed on the worker's device.

[0844] Step 7:

[0845] The worker actually performs the work based on the work instruction message received. For example, he / she takes a break or engages in other urgent work. The input is the feedback work instruction, and the output is the worker's action (performing the work, taking a break, etc.).

[0846] This series of processes enables real-time monitoring of workers' emotional states and the use of generative AI models to generate and provide optimal work instructions, thereby improving work efficiency and the working environment at logistics centers.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] [Third embodiment]

[0851] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0852] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0853] 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).

[0854] 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.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] The present invention provides an online research service system in which users input their research topic and purpose, collect and analyze information using a generative AI model, and finally generate and deliver materials. A specific embodiment of this system is shown below.

[0864] System Overview

[0865] Accepting user requests

[0866] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. At this time, detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. The input information is sent to the server.

[0867] Information gathering

[0868] The server analyzes the request and triggers a generative AI model to gather relevant information from trusted sources (e.g., medical paper databases, news sites, official cancer research sites, etc.). The generative AI model then generates a specialized search query and accesses the source to crawl the data.

[0869] Examples:

[0870] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[0871] Data analysis and extraction

[0872] The server stores the collected information in a database and analyzes it using a generative AI model, which filters out noise and removes duplicate data to extract the necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.).

[0873] Examples:

[0874] The abstracts of each paper are analyzed using natural language processing technology to extract descriptions of the effectiveness of the treatment.

[0875] Generate materials

[0876] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the extracted data, and generates charts and graphs to present the data in a visually understandable manner.

[0877] Examples:

[0878] Create graphs comparing the effectiveness of each treatment and generate explanatory reports.

[0879] Delivery and feedback

[0880] The server delivers the generated materials to the user's device. If the user checks the materials and requests any necessary corrections or additional information, they send feedback to the server again. The server then corrects and updates the materials based on the user's feedback.

[0881] Consultation support with experts

[0882] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[0883] Examples:

[0884] A user requests more detailed information about immunotherapy, and researchers gather the additional information and incorporate it into the report.

[0885] Implementation method

[0886] The implementation of this system requires the following major components:

[0887] 1. A user terminal equipped with a web form for accepting requests

[0888] 2. Server responsible for collecting and analyzing information

[0889] 3. Generative AI Models

[0890] 4. Access to reliable sources of information

[0891] 5. Data filtering and analysis algorithms

[0892] 6. Report and presentation generation tools

[0893] 7. Interface for online consultation with experts

[0894] Example

[0895] For example, if a user requests research on the latest lung cancer treatments, they input their research topic and purpose using their device. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about treatment effectiveness. The server then generates graphs comparing treatment effects and creates and delivers a comprehensive report. The user can review the delivered materials and, if necessary, consult with experts via the server to incorporate additional information or corrections. This series of processes allows users to obtain efficient and reliable research results.

[0896] The processing flow will be explained below.

[0897] Step 1:

[0898] The user enters the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via a terminal. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered in the request form. This input information is then sent to the server.

[0899] Step 2:

[0900] The server receives the user's request and activates the generative AI model, which generates a search query based on the request and prepares access to reliable sources of information (e.g., medical paper databases, news sites, official research institution websites, etc.).

[0901] Step 3:

[0902] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[0903] Examples:

[0904] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[0905] Step 4:

[0906] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[0907] Step 5:

[0908] The server uses the generative AI model to analyze the stored data, where data cleansing (removal of noise data, elimination of duplicate data) is performed and reliable information is filtered.

[0909] Step 6:

[0910] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[0911] Examples:

[0912] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[0913] Step 7:

[0914] The server generates reports and presentation materials based on the extracted data, including charts and graphs to visually represent the data.

[0915] Examples:

[0916] Graphs are created based on the extracted effectiveness data for each treatment, and a report including an explanation is generated.

[0917] Step 8:

[0918] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review and provide feedback.

[0919] Step 9:

[0920] The user reviews the materials, sends any necessary corrections or requests for additional information from the terminal to the server, and, if necessary, requests online consultation with expert researchers or writers.

[0921] Step 10:

[0922] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[0923] Step 11:

[0924] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[0925] Example 1

[0926] 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."

[0927] The present invention relates to an online research service that enables users to accurately and quickly achieve their research themes and goals. However, conventional research systems require a significant amount of time for information gathering and data analysis, making it difficult to create the high-quality reports and presentation materials users require. Furthermore, feedback and revisions are not provided efficiently, making it difficult to respond to user requests promptly. Furthermore, there is no way to obtain detailed information or explanations through consultation with experts, making it difficult to meet user needs.

[0928] 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.

[0929] In this invention, the server includes: a means for a user to input a research topic and purpose; a means for transmitting the user's input to the server; a means for the server to collect relevant data from information sources using a generative AI model; a means for the server to store and analyze the collected information in a database; a means for the server to analyze the information and extract data related to the user's research topic; a means for the server to generate reports and presentation materials based on the extracted data; and a means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This allows users to quickly and efficiently obtain high-quality research results and can also respond to requests for necessary corrections and additional information. Furthermore, a means for obtaining detailed information and explanations through online consultations with professional researchers and writers is provided, thereby meeting a variety of user needs.

[0930] A "research topic" specifies a specific issue or topic that a user wants to research.

[0931] "Objective" indicates the specific goal the user wants to achieve through the survey.

[0932] "User" refers to an individual or organization that uses this system to collect information on a research topic and use the analysis results.

[0933] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that allows users to input their research topic and purpose and connect to the system.

[0934] "Server" refers to a computer system that receives requests from users and uses a generative AI model to collect information, analyze it, manage a database, generate materials, and respond to feedback.

[0935] "Generative AI model" refers to an artificial intelligence algorithm that automatically collects, analyzes, and generates research information.

[0936] "Sources" refer to databases, websites, official organizations, etc. that provide information related to the research topic.

[0937] "Database" refers to an information management system that stores and manages information collected by a server and extracts necessary data.

[0938] "Analysis" refers to the process of analyzing collected information, filtering out noisy data, removing redundant data, and extracting necessary information.

[0939] "Material" refers to a collection of information generated in a format specified by the user (report, presentation materials, etc.).

[0940] "Delivery" refers to the process by which the server transmits and provides the generated materials to the user.

[0941] "Feedback" refers to the process by which a User reviews delivered materials and requests any necessary corrections or additional information.

[0942] "Researcher" refers to an expert who has specialized knowledge on a specific research topic and provides users with detailed information and explanations.

[0943] A "writer" refers to a specialist who generates materials based on collected information and writes them to be provided to users.

[0944] "Online consultation" refers to a communication session over the Internet between a user and a researcher or writer, set up by a server.

[0945] "Filtering" refers to the process of sorting collected data in order to prioritize and analyze highly reliable information.

[0946] MODE FOR CARRYING OUT THE INVENTION

[0947] This invention provides an online research service in which users input their research topic and objectives, use generative AI models to collect and analyze information, and ultimately generate and deliver materials. To implement this invention, the following main components are required:

[0948] 1. A user terminal equipped with a web form for accepting requests

[0949] Users use a web form to input detailed information such as research topic and purpose, etc. The device used can be an electronic device such as a PC, tablet, or smartphone.

[0950] 2. Server responsible for collecting and analyzing information

[0951] The server receives the request sent by the user, uses the generative AI model to collect relevant information, and stores that information in a database. The server also analyzes the collected information and extracts specific data according to the user's request. This requires a server with ample computing power and storage capacity.

[0952] 3. Generative AI Models

[0953] A generative AI model is an artificial intelligence algorithm that automates a series of processes, such as information gathering, analysis, and document generation. In particular, it utilizes natural language processing (NLP) technology to summarize acquired data, extract important information, and automatically generate documents.

[0954] 4. Access to reliable sources of information

[0955] The server uses a generative AI model to collect data from trusted sources (e.g., academic paper databases, public information sites, etc.). For example, to obtain data on the latest medical research, it uses the PubMed API.

[0956] 5. Data filtering and analysis algorithms

[0957] The server uses algorithms to filter out noise data and remove duplicate data in the early stages of analysis, extracting only the necessary information.

[0958] 6. Report and presentation generation tools

[0959] It is equipped with tools to generate documents in formats that meet user requirements based on collected and analyzed data, including the automatic generation of charts and graphs.

[0960] 7. Interface for online consultation with experts

[0961] The server provides an interface for online consultation between users and experts (researchers and writers), allowing users to obtain additional information and detailed explanations.

[0962] As a concrete example, let us consider the case where a user requests research on the latest lung cancer treatments. The user uses a terminal to input the research topic ("latest lung cancer treatments") and purpose ("creating presentation materials"), and then submits detailed information ("research subject: research over the past five years," scope, deadline, desired data format, etc.).

[0963] The server then uses the generative AI model to retrieve relevant paper metadata (title, author, abstract, publication date) from the PubMed API using a query such as "lung cancer AND treatment AND latest." The server stores the collected information in a database and analyzes it using natural language processing techniques to extract key points about the effectiveness of treatments.

[0964] The server then creates graphs comparing the effectiveness of each treatment and generates a comprehensive report. The resulting data is delivered to the user's device for review. If necessary, the user can submit feedback requests for additional information or corrections, and the server will respond.

[0965] Furthermore, if a user requests "I would like to consult with an expert," the server will use an online consultation tool to set up an online meeting between the user and an expert, allowing them to obtain detailed information and explanations.

[0966] Example prompt sentence:

[0967] "I would like to research the latest lung cancer treatments. My goal is to create presentation materials, and my research will focus mainly on the latest treatments, their effectiveness, and side effects. The deadline is one week."

[0968] The present invention allows users to obtain high-quality research results quickly and efficiently, and also allows for requests for necessary corrections and additional information. Furthermore, a system is provided that can meet the diverse needs of users through online consultations with experts.

[0969] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0970] Step 1: Accepting a user request

[0971] A user accesses the system using a terminal and inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials). They can also input detailed information (research subject, scope, deadline, desired data format, etc.). The input information is sent from the terminal to the server as an HTTP request.

[0972] Input: Research topic, purpose, detailed information (research subject, scope, deadline, desired data format, etc.)

[0973] Output: Request data sent to the server

[0974] Specific action: A user enters a research topic and purpose into a web form and clicks the submit button.

[0975] Step 2: Gather information

[0976] The server analyzes the received request and activates a generative AI model. The generative AI model generates specialized search queries against reliable sources (e.g., medical paper databases, news sites, official websites, etc.) to crawl the information. The server uses the generative AI model to collect the information and stores it in a database.

[0977] Input: Request data

[0978] Output: Collected information data

[0979] Specific operation: The server generates the query "lung cancer AND treatment AND latest," and the generative AI model uses the PubMed API to collect related information.

[0980] Step 3: Data analysis and extraction

[0981] The server stores the collected information in a database and performs analysis. During the analysis process, noise data is filtered out and duplicate data is removed, and necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.) is extracted.

[0982] Input: Collected information data

[0983] Output: Parsed information data

[0984] Specific operation: The server analyzes the abstract of each paper using natural language processing technology and extracts information about the effectiveness of treatments.

[0985] Step 4: Generate materials

[0986] Based on the analyzed information, the server generates materials in the format desired by the user (reports, presentation materials, etc.) It also creates charts and graphs to present the data visually in an easy-to-understand manner.

[0987] Input: Parsed information data

[0988] Output: Generated materials (reports, presentation materials)

[0989] Specific operation: The server creates a graph comparing the effects of each treatment and automatically generates a document containing an explanation.

[0990] Step 5: Delivery and feedback

[0991] The server sends the completed document to the user's device. If the user checks the document and requests any necessary corrections or additional information, they send their feedback to the server. The server then corrects and updates the document based on the user's feedback.

[0992] Input: Finished materials, user feedback

[0993] Output: Corrected and updated materials

[0994] Specific operation: The server sends the generated data to the user's email address, and the user fills in the feedback form with comments such as "I would like more data" and "I would like to change the color of the graph."

[0995] Step 6: Expert consultation support

[0996] If a user wishes to consult with a professional researcher or writer, the server will use online consultation tools (e.g., Zoom, Teams) to set up a consultation session, through which the user can obtain additional information and detailed explanations.

[0997] Input: User's consultation request

[0998] Output: A configured online consultation session

[0999] Specific behavior: A user requests "I would like to consult with an expert," and the server uses the consultation tool to send a meeting link to the user.

[1000] (Application example 1)

[1001] 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."

[1002] In today's virtual stores, it is difficult for users to quickly and efficiently gather product information and easily create comparison materials based on that information. Furthermore, there are limited ways to flexibly obtain appropriate feedback and additional information. Under these circumstances, there is a need for advanced information research systems to support purchasing decisions.

[1003] 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.

[1004] In this invention, the server includes a means for a user to input a research topic and purpose in the virtual store, a means for collecting related data using a generative AI model, and a means for analyzing the collected information and extracting data related to the user's needs, thereby enabling users to quickly and accurately compare and consider product information in the virtual store and automatically generate materials for that purpose.

[1005] "Research Topic" refers to a particular issue or problem that a User specifies as the subject of research.

[1006] "Objective" refers to the goal or outcome that the user is trying to achieve through research.

[1007] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate and analyze information.

[1008] "Sources" refer to trusted websites, databases, etc. that you access to gather data.

[1009] "Data" refers to a collection of information or facts that are collected and analyzed.

[1010] "Analysis" refers to the process of examining and analyzing collected data to find meaning and patterns.

[1011] "Extraction" refers to selecting the necessary information from the analyzed data.

[1012] A "report" refers to a document summarizing the results of an investigation.

[1013] "Presentation materials" refers to slides and documents used to visually represent and explain research results.

[1014] "Delivery" refers to providing the generated materials to the user.

[1015] "Feedback" refers to opinions and requests for corrections regarding materials received from users.

[1016] "Web crawling" refers to the techniques and processes used to automatically collect information on the Internet.

[1017] "Smart Device" means a user device that is connected to the Internet and capable of collecting and displaying information.

[1018] "Expert researchers and authors" refer to experts who have knowledge and experience in a particular field and can provide additional information and explanations to users.

[1019] "Filtering" refers to the process of prioritizing highly reliable and relevant information.

[1020] The present invention provides a system that allows users to efficiently conduct product research in a virtual store. A specific embodiment of the system is described below.

[1021] System Overview and Configuration

[1022] The user inputs the research topic and purpose using a smart device. For example, the research topic can be "creating a review and comparison document on the latest vitamin C-containing skin care products." The information entered by the user is sent to the server.

[1023] Information gathering

[1024] The server invokes the generative AI model to gather relevant data from trusted sources, specifically using web crawling techniques to gather information such as product names, prices, and links, using the requests and BeautifulSoup libraries.

[1025] Data analysis and extraction

[1026] The server analyzes the collected information and extracts the necessary data. Generative AI models and natural language processing techniques are used for data analysis. Filtering functions are used to prioritize reliable information.

[1027] Generate materials

[1028] The server generates materials in the user's desired format (reports, presentation materials, etc.) based on the extracted data. At this time, an AI model is used to create review and comparison materials. OpenAI's API is used to generate materials using AI.

[1029] Delivery and feedback

[1030] The generated materials are delivered to the user's smart device. The user can review the materials and send any necessary feedback to the server, which then corrects the materials.

[1031] Consultation support with experts

[1032] If the user wishes, the server can set up an online consultation with a researcher or author in the field, who can provide additional information and detailed explanations.

[1033] Specific examples

[1034] For example, if a user requests research on "the latest skin care products with vitamin C," they can enter the following prompt:

[1035] Write a review and comparison of the latest Vitamin C skin care products.

[1036] product:

[1037] 1. ABC Vitamin C Serum - $29.99

[1038] 2. XYZ Vitamin C Cream - $35.99

[1039] 3. LMN Vitamin C Essence - $45.00

[1040] By feeding this prompt into a generative AI model, a detailed report is generated that includes reviews and comparisons of each product, allowing users to make more efficient product choices.

[1041] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1042] Step 1:

[1043] The user inputs the research topic and purpose.

[1044] Using a smart device, users input their research topic (e.g., the latest vitamin C-containing skin care products) and goal (e.g., to create a product review and comparison document), including information such as the target market and delivery date.

[1045] Step 2:

[1046] The server uses a generative AI model to collect relevant data from sources.

[1047] Based on the research topic entered by the user, the server uses a generative AI model to collect relevant data from reliable sources, using web crawling technology to generate search queries and collect product information (e.g., product names, prices, links) from websites that have corresponding data.

[1048] Step 3:

[1049] The server analyzes the collected information and extracts data related to the user's research topic.

[1050] The server applies natural language processing technology to analyze the collected information and extracts the necessary data, specifically, product names, prices, review content, etc., and filters the information to prioritize the most reliable information for analysis.

[1051] Step 4:

[1052] The server generates reports and presentation materials based on the extracted data.

[1053] The server generates materials in the format specified by the user (reports, presentation materials, etc.) based on the analyzed data. This process involves using a generative AI model to create reviews and comparison materials for each product. Specifically, it creates graphs and tables that visually summarize each product's features, price, review content, etc.

[1054] Step 5:

[1055] The server delivers the generated materials to the user, who provides feedback and corrections.

[1056] The generated materials are sent to the user's smart device. The user reviews the materials and sends any necessary feedback or correction requests to the server. The server then corrects and updates the materials based on the received feedback.

[1057] Step 6:

[1058] The server sets up online consultations with expert researchers and authors.

[1059] If the user needs additional information or detailed explanation, the server will set up an online consultation with expert researchers and authors, through which the user can get more detailed information or further explanation.

[1060] The specific operations and inputs / outputs at each step are shown below:

[1061] Step 1 Input: Research topic, objectives, additional information (e.g. target market, deadline)

[1062] Step 1 Output: User request data

[1063] Step 2 Input: User Request Data

[1064] Step 2 Output: Collected Product Data

[1065] Input for Step 3: Collected Product Data

[1066] Output of Step 3: Parsed product data

[1067] Input for Step 4: Parsed Product Data

[1068] Step 4 Output: Generated reports and presentations

[1069] Step 5 Input: Generated materials, user feedback

[1070] Step 5 Output: Corrected and updated documentation

[1071] Step 6: Requesting additional information or clarification from the user

[1072] Step 6 Output: Additional information and detailed commentary from experts

[1073] 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.

[1074] The present invention is a system that provides an online research service that combines an emotion engine that recognizes the user's emotions, collects and analyzes reliable information based on the research theme and purpose, and finally generates and delivers materials. A specific embodiment of this system is shown below.

[1075] System Overview

[1076] Accepting user requests

[1077] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. This input information is sent to the server.

[1078] Information gathering

[1079] The server receives the user's request and activates a generative AI model to collect relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). The generative AI model generates specialized search queries and accesses the sources to crawl the data.

[1080] Examples:

[1081] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[1082] Data analysis and extraction

[1083] The server temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion engine that recognizes emotions from user input and applies information collection and analysis methods according to those emotions.

[1084] Examples:

[1085] If a user types "I'm in a hurry," the emotion engine recognizes the urgency and quickly collects, analyzes, and delivers information.

[1086] Prioritizing information based on emotions

[1087] The server uses the emotion engine to prioritize information based on the user's emotions, thereby efficiently providing the information that is of most interest to the user.

[1088] Examples:

[1089] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[1090] Generate materials

[1091] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the analyzed data. At this time, the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[1092] Examples:

[1093] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[1094] Delivery and feedback

[1095] The server delivers the generated materials to the user's terminal and receives feedback from the user. If the user checks the materials and requests any necessary corrections or additional information, the server responds accordingly.

[1096] Consultation support with experts

[1097] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[1098] Examples:

[1099] The user requests a more detailed explanation and obtains additional information through consultation with an expert.

[1100] Implementation method

[1101] To implement this system, the following major components are required:

[1102] 1. A user terminal equipped with a web form for accepting requests

[1103] 2. Server responsible for collecting and analyzing information

[1104] 3. Generative AI Models

[1105] 4. Access to reliable sources of information

[1106] 5. Data filtering and analysis algorithms

[1107] 6. Emotion Engine

[1108] 7. Report and presentation generation tools

[1109] 8. Online consultation interface with experts

[1110] Example

[1111] For example, if a user requests research on the latest lung cancer treatments and inputs feelings of anxiety, the emotion engine recognizes the anxiety. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about the treatment's effectiveness. The emotion engine then prioritizes information that provides reassurance and issues a visually reassuring report. The materials are delivered to the user and revised based on their feedback. If necessary, additional information and detailed explanations can be added through consultation with experts. This series of processes provides efficient and reliable research results that take the user's emotions into account.

[1112] The processing flow will be explained below.

[1113] Step 1:

[1114] The user inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via their terminal. The emotion engine then extracts emotions (e.g., anxiety, excitement, urgency, etc.) from the user's input and a simple questionnaire. This input and emotion information are then sent to the server.

[1115] Step 2:

[1116] The server receives the user's request and emotion information, and then activates the generative AI model. The server generates a search query based on the user's request and prepares to access reliable information sources (e.g., medical paper databases, news sites, official research institution websites, etc.).

[1117] Step 3:

[1118] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[1119] Examples:

[1120] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[1121] Step 4:

[1122] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[1123] Step 5:

[1124] The server uses a generative AI model to analyze the stored data, including an emotion engine that applies information gathering and analysis techniques based on the emotions derived from the user's input.

[1125] Examples:

[1126] If a user types "I'm in a hurry," the emotion engine will recognize the urgency and quickly collect, analyze, and deliver information.

[1127] Step 6:

[1128] The server uses the emotion engine to prioritize information based on the user's emotions, allowing the server to efficiently provide the information that the user is most interested in.

[1129] Examples:

[1130] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[1131] Step 7:

[1132] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[1133] Examples:

[1134] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[1135] Step 8:

[1136] The server generates reports and presentation materials based on the extracted data, and the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[1137] Examples:

[1138] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[1139] Step 9:

[1140] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review the materials and make any necessary corrections or request additional information.

[1141] Step 10:

[1142] Users can review the materials, send requests for necessary corrections or additional information to the server from their terminal, and, if necessary, request online consultation with professional researchers or writers.

[1143] Step 11:

[1144] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[1145] Step 12:

[1146] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[1147] Example 2

[1148] 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."

[1149] Conventional online research services have struggled to prioritize information based on user sentiment or generate the materials users desire related to their research topic. They also face challenges in efficiently collecting and analyzing reliable information. Furthermore, efficient consultation with expert researchers and writers is difficult, and feedback responses to enhance user satisfaction are insufficient.

[1150] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1151] In this invention, the server includes means for a user to input a research topic and purpose, means for the server to collect related information from information sources using a generative AI model, means for the server to analyze the collected data and extract information related to the user's research topic, means for the server to perform analysis using an emotion recognition engine, means for the server to generate visual materials based on the extracted information, and means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This enables the provision of information according to the user's emotions, efficient collection and analysis of reliable information, and effective consultation with experts and feedback response.

[1152] A "research topic" is a specific topic or area that a user sets as the subject of research.

[1153] "Objectives" are the specific goals or objectives that a user wants to achieve when conducting research.

[1154] A "generative AI model" is an algorithmic system that uses artificial intelligence to perform natural language processing and data analysis.

[1155] "Sources" refer to external databases and websites that provide data and information needed for research.

[1156] An "emotion recognition engine" is a system that analyzes emotions based on user input and selects an appropriate processing method.

[1157] "Visual materials" are documents that are visually displayed, such as reports or presentations generated based on analyzed information.

[1158] "Feedback" is the process by which users provide corrections and comments on received material.

[1159] "Expert researchers and writers" are experts with knowledge and experience in a particular topic or field.

[1160] To implement this invention, a user terminal, a server, a generative AI model, an emotion recognition engine, and a database are required. A specific embodiment of this system is shown below.

[1161] First, the user inputs the research topic and purpose. For example, the user inputs "latest lung cancer treatment methods" and "creating presentation materials" from the terminal. The input information is then sent from the terminal to the server.

[1162] The server receives the user's request and launches a generative AI model. This generative AI model is, for example, a GPT-based model for natural language processing. The server collects relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). Specifically, the generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of the relevant paper.

[1163] The server then temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion recognition engine that recognizes emotions from the user's input and applies information collection and analysis methods based on that emotion. For example, if the user inputs "I'm in a hurry," the emotion recognition engine will recognize the urgency and quickly collect, analyze, and deliver the information.

[1164] The server then uses an emotion recognition engine to prioritize information based on the user's emotions, allowing it to efficiently provide the information the user is most interested in. For example, if the user types "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[1165] The server then generates materials in the user's desired format (report, presentation, etc.) based on the analyzed data. The emotion recognition engine uses expressions that match the user's emotions, providing materials in a format that is more user-friendly. For example, if a user requests presentation materials, the emotion recognition engine can sense the user's excitement and generate visually appealing slides.

[1166] Finally, the server delivers the generated materials to the user's device and receives feedback from the user. If the user reviews the materials and requests any necessary corrections or additional information, the server responds accordingly. If the user wishes, the server can also set up an online consultation with a professional researcher or writer. Through this consultation, the user can request additional information or detailed explanations.

[1167] An example of a specific prompt is, "Please hurry and provide reliable information about the latest lung cancer treatments. I'm feeling anxious."

[1168] This makes it possible to provide high-quality materials that correspond to the user's emotions and research needs, thereby increasing user satisfaction.

[1169] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1170] Step 1:

[1171] Accepting user requests

[1172] The user enters the research topic and purpose from the device. For example, the user enters "latest lung cancer treatments" and "creating presentation materials" into a web form on the device.

[1173] Input: User's research topic and purpose

[1174] Output: Send request containing the entered request data

[1175] Specific operation: The user fills in detailed information (such as research subject, deadline, and desired data format) in each field of the web form and clicks the "Submit" button, which causes the device to send the entered information to the server.

[1176] Step 2:

[1177] Information gathering

[1178] The server receives the user's request and launches a generative AI model, which then gathers relevant information from trusted sources. For example, the generative AI model creates a query for "latest lung cancer treatments" and accesses the PubMed API to retrieve metadata for related papers.

[1179] Input: User request data

[1180] Output: A dataset containing the relevant information collected

[1181] How it works: The server calls the generative AI model to generate a specialized search query, which the generative AI model executes to efficiently crawl data from sources and retrieve relevant information.

[1182] Step 3:

[1183] Data analysis and extraction

[1184] The server temporarily stores the collected data in a database and performs data analysis using a generative AI model. This analysis includes an emotion recognition engine. For example, the emotion recognition engine recognizes the user's emotions and applies an analysis method according to the emotion.

[1185] Input: Collected relevant information

[1186] Output: Parsed dataset

[1187] How it works: The server stores the collected data in a database, the generative AI model performs natural language processing to extract key points from the data, and the emotion recognition engine selects an analysis method based on the emotion entered by the user.

[1188] Step 4:

[1189] Prioritizing information based on emotions

[1190] The server uses an emotion recognition engine to prioritize information based on the user's emotions. For example, if the user inputs "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[1191] Input: Parsed dataset and user emotion information

[1192] Output: prioritized information

[1193] How it works: The server applies an emotion recognition engine and a prioritization algorithm based on the user's input emotion. Information is organized around the content that the user is most interested in.

[1194] Step 5:

[1195] Generate materials

[1196] The server generates materials in the format desired by the user (reports, presentation materials) based on the analyzed data. At this time, an emotion recognition engine uses expressions that match the user's emotions. For example, in the case of presentation materials, visually appealing slides are generated.

[1197] Input: prioritized information and user preferred format

[1198] Output: Generated materials (reports and slides)

[1199] Specific operation: The server uses a document generation tool to create visually appealing documents based on an emotion recognition engine. The document generation tool uses templates and design elements to create high-quality documents.

[1200] Step 6:

[1201] Delivery and feedback

[1202] The server delivers the generated materials to the user's terminal and receives feedback from the user. The user checks the materials and requests any necessary corrections or additional information.

[1203] Input: Generated material

[1204] Output: User feedback and correction requests

[1205] Specific operation: The server sends the generated document file to the user's device. The user reads the document and uses the feedback form or comment function to request corrections or add additional information.

[1206] Step 7:

[1207] Consultation support with experts

[1208] If the user wishes, the server will set up an online consultation with a professional researcher or writer.

[1209] Input: User consultation request

[1210] Output: Responses to inquiries and supplementary information

[1211] Specific operation: The user fills out a request form stating, "I would like to consult with an expert." The server schedules a session with the expert using a video conferencing tool or similar. After the consultation is completed, the user is provided with supplementary information and detailed explanations.

[1212] (Application example 2)

[1213] 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."

[1214] Current challenges in logistics centers include a work environment that ignores the emotional state of workers and inefficient work instructions. Failure to consider appropriate breaks and work priorities increases fatigue and stress, leading to problems with reduced work efficiency and quality. Furthermore, research does not take into account the emotions of users when collecting and analyzing information, creating a need for reliable results that are delivered quickly and efficiently.

[1215] 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.

[1216] In this invention, the server includes: [means for a user to input a research topic and purpose;] [means for the server to collect relevant data from information sources using a generated AI model; and] [means for recognizing the facial expressions and tone of voice of workers in real time and analyzing their emotional state.] This allows the emotional state of workers to be grasped in real time and optimal work instructions to be generated, thereby improving work efficiency and the work environment at logistics centers. Furthermore, reliable information collection and analysis based on user requests can be realized, allowing for fast and efficient provision of materials.

[1217] "Means for users to input research topic and purpose" refers to an interface that allows users to electronically input their research purpose and detailed research topic.

[1218] "Means for a server to collect relevant data from information sources using a generated AI model" refers to means for automatically collecting relevant data from reliable information sources using an artificial intelligence model generated by a server.

[1219] "Means for the server to analyze information and extract data related to the user's research topic" refers to the means for the server to analyze the information collected and select data that matches the research topic desired by the user.

[1220] "Means for generating reports and presentation materials based on data extracted by the server" refers to means for using data analyzed and extracted by the server to create reports and presentation materials tailored to the user's needs.

[1221] "Means for the server to deliver generated materials to the user and provide necessary feedback and corrections" refers to means for the server to provide generated reports and materials to the user and make corrections based on feedback from the user.

[1222] "Means for recognizing a worker's facial expression and tone of voice in real time and analyzing their emotional state" refers to means for monitoring a worker's facial expression and tone of voice in real time and evaluating their emotional state using emotion recognition technology.

[1223] The "means for analyzing emotion data and generating instructions for optimizing work efficiency" refers to a means for analyzing collected emotion data and generating optimal instructions for improving work efficiency.

[1224] This invention is a system that improves work efficiency in logistics centers and provides optimal work instructions based on the emotions of workers. This system incorporates a worker emotion recognition function as part of the collection and analysis of reliable information based on the user's research theme and purpose, and the creation of necessary materials.

[1225] System configuration

[1226] Hardware and software used

[1227] Hardware: Smartphones (Android and iOS), Head-Mounted Displays (HMDs: for example, Microsoft HoloLens)

[1228] Software: Emotion recognition engine (e.g., Affectiva SDK), generative AI model (e.g., OpenAI GPT-4), cloud server (e.g., AWS EC2 instance)

[1229] Program processing

[1230] overview

[1231] 1. Emotion Recognition: A worker wears a smartphone or HMD and launches the application. The camera captures the worker's facial expressions and tone of voice, and the emotion recognition engine (Affectiva SDK) analyzes their emotional state in real time. This data is sent to a cloud server.

[1232] 2. Data transmission and analysis: The cloud server (AWS EC2 instance) analyzes the received emotion data using a generative AI model (GPT-4) to evaluate the level of stress, fatigue, and anxiety. Based on this evaluation, work priorities and break instructions are optimized.

[1233] 3. Generating and providing work instructions: The generative AI model combines the analysis results with operational data to generate optimal work instructions. For example, it can recommend a break for a tired worker and assign urgent tasks to other workers. This information is fed back to the smartphone or HMD in real time.

[1234] Specific examples

[1235] Usage Scenarios

[1236] A worker at a logistics center starts his morning shift. He launches an emotion recognition app on his smartphone, which begins facial recognition and voice tone analysis. After 45 minutes, the emotion engine detects "fatigue," and a notification appears on A's smartphone saying, "Your fatigue level is increasing. We recommend you take a 10-minute break." After the break, the most important tasks are listed, allowing A to resume work efficiently.

[1237] Prompt Sentence Examples

[1238] An example prompt for a generative AI model is:

[1239] markdown

[1240] "Worker A's emotional data indicates that he is becoming increasingly fatigued for tasks with an urgency of C. Generate a message to encourage him to take a break, followed by suggestions to optimize the prioritization of his work."

[1241] This will enable optimal work instructions to be provided in real time based on the analysis results of the emotion recognition and generative AI model, enabling the realization of an efficient and healthy working environment in logistics centers. Furthermore, since it is possible to simultaneously collect reliable information based on research themes and quickly generate materials, a powerful system will be built that can meet the diverse needs of users.

[1242] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1243] Step 1:

[1244] The user puts on a smartphone or head-mounted display and launches the application. This causes the device's camera to begin capturing the worker's facial expressions and tone of voice in real time. The input is real-time facial expression data and tone of voice data from the camera, and the output is raw data sent to the emotion recognition engine.

[1245] Step 2:

[1246] An emotion recognition engine (e.g., Affectiva SDK) analyzes real-time facial expression data and tone of voice data. The input data includes multiple facial expressions and tone of voice data, and the output is an analysis result of the emotional state (e.g., fatigue, anxiety, stress, etc.) extracted from the data.

[1247] Step 3:

[1248] The server receives the emotion analysis results sent from the emotion recognition engine and stores the analyzed data on a cloud server (AWS EC2 instance). The input is the emotion analysis results, and processing is performed to store the emotional state in a database.

[1249] Step 4:

[1250] Based on the emotional state data received by the cloud server, a generative AI model (e.g., GPT-4) is launched and analyzed. The input is the emotional state data, and the output is the intermediate result for generating instruction prompts based on that data to improve work efficiency.

[1251] Step 5:

[1252] Based on the generated prompt sentence, the generative AI model generates optimal work instructions for improving work efficiency. For example, based on the input prompt sentence, it generates a message recommending that a fatigued worker take a break, or an instruction to assign a highly urgent task to another worker. The output is a specific work instruction message.

[1253] Step 6:

[1254] The cloud server then sends the generated work instruction messages to a smartphone or head-mounted display, providing real-time feedback to the worker. The input is the work instruction message output by the generative AI model, and the output is specific instructions displayed on the worker's device.

[1255] Step 7:

[1256] The worker actually performs the work based on the work instruction message received. For example, he / she takes a break or engages in other urgent work. The input is the feedback work instruction, and the output is the worker's action (performing the work, taking a break, etc.).

[1257] This series of processes enables real-time monitoring of workers' emotional states and the use of generative AI models to generate and provide optimal work instructions, thereby improving work efficiency and the working environment at logistics centers.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] [Fourth embodiment]

[1262] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1263] 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.

[1264] 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).

[1265] 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.

[1266] 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.

[1267] 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).

[1268] 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.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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."

[1275] The present invention provides an online research service system in which users input their research topic and purpose, collect and analyze information using a generative AI model, and finally generate and deliver materials. A specific embodiment of this system is shown below.

[1276] System Overview

[1277] Accepting user requests

[1278] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. At this time, detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. The input information is sent to the server.

[1279] Information gathering

[1280] The server analyzes the request and triggers a generative AI model to gather relevant information from trusted sources (e.g., medical paper databases, news sites, official cancer research sites, etc.). The generative AI model then generates a specialized search query and accesses the source to crawl the data.

[1281] Examples:

[1282] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[1283] Data analysis and extraction

[1284] The server stores the collected information in a database and analyzes it using a generative AI model, which filters out noise and removes duplicate data to extract the necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.).

[1285] Examples:

[1286] The abstracts of each paper are analyzed using natural language processing technology to extract descriptions of the effectiveness of the treatment.

[1287] Generate materials

[1288] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the extracted data, and generates charts and graphs to present the data in a visually understandable manner.

[1289] Examples:

[1290] Create graphs comparing the effectiveness of each treatment and generate explanatory reports.

[1291] Delivery and feedback

[1292] The server delivers the generated materials to the user's device. If the user checks the materials and requests any necessary corrections or additional information, they send feedback to the server again. The server then corrects and updates the materials based on the user's feedback.

[1293] Consultation support with experts

[1294] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[1295] Examples:

[1296] A user requests more detailed information about immunotherapy, and researchers gather the additional information and incorporate it into the report.

[1297] Implementation method

[1298] The implementation of this system requires the following major components:

[1299] 1. A user terminal equipped with a web form for accepting requests

[1300] 2. Server responsible for collecting and analyzing information

[1301] 3. Generative AI Models

[1302] 4. Access to reliable sources of information

[1303] 5. Data filtering and analysis algorithms

[1304] 6. Report and presentation generation tools

[1305] 7. Interface for online consultation with experts

[1306] Example

[1307] For example, if a user requests research on the latest lung cancer treatments, they input their research topic and purpose using their device. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about treatment effectiveness. The server then generates graphs comparing treatment effects and creates and delivers a comprehensive report. The user can review the delivered materials and, if necessary, consult with experts via the server to incorporate additional information or corrections. This series of processes allows users to obtain efficient and reliable research results.

[1308] The processing flow will be explained below.

[1309] Step 1:

[1310] The user enters the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via a terminal. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered in the request form. This input information is then sent to the server.

[1311] Step 2:

[1312] The server receives the user's request and activates the generative AI model, which generates a search query based on the request and prepares access to reliable sources of information (e.g., medical paper databases, news sites, official research institution websites, etc.).

[1313] Step 3:

[1314] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[1315] Examples:

[1316] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[1317] Step 4:

[1318] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[1319] Step 5:

[1320] The server uses the generative AI model to analyze the stored data, where data cleansing (removal of noise data, elimination of duplicate data) is performed and reliable information is filtered.

[1321] Step 6:

[1322] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[1323] Examples:

[1324] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[1325] Step 7:

[1326] The server generates reports and presentation materials based on the extracted data, including charts and graphs to visually represent the data.

[1327] Examples:

[1328] Graphs are created based on the extracted effectiveness data for each treatment, and a report including an explanation is generated.

[1329] Step 8:

[1330] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review and provide feedback.

[1331] Step 9:

[1332] The user reviews the materials, sends any necessary corrections or requests for additional information from the terminal to the server, and, if necessary, requests online consultation with expert researchers or writers.

[1333] Step 10:

[1334] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[1335] Step 11:

[1336] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[1337] Example 1

[1338] 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."

[1339] The present invention relates to an online research service that enables users to accurately and quickly achieve their research themes and goals. However, conventional research systems require a significant amount of time for information gathering and data analysis, making it difficult to create the high-quality reports and presentation materials users require. Furthermore, feedback and revisions are not provided efficiently, making it difficult to respond to user requests promptly. Furthermore, there is no way to obtain detailed information or explanations through consultation with experts, making it difficult to meet user needs.

[1340] 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.

[1341] In this invention, the server includes: a means for a user to input a research topic and purpose; a means for transmitting the user's input to the server; a means for the server to collect relevant data from information sources using a generative AI model; a means for the server to store and analyze the collected information in a database; a means for the server to analyze the information and extract data related to the user's research topic; a means for the server to generate reports and presentation materials based on the extracted data; and a means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This allows users to quickly and efficiently obtain high-quality research results and can also respond to requests for necessary corrections and additional information. Furthermore, a means for obtaining detailed information and explanations through online consultations with professional researchers and writers is provided, thereby meeting a variety of user needs.

[1342] A "research topic" specifies a specific issue or topic that a user wants to research.

[1343] "Objective" indicates the specific goal the user wants to achieve through the survey.

[1344] "User" refers to an individual or organization that uses this system to collect information on a research topic and use the analysis results.

[1345] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that allows users to input their research topic and purpose and connect to the system.

[1346] "Server" refers to a computer system that receives requests from users and uses a generative AI model to collect information, analyze it, manage a database, generate materials, and respond to feedback.

[1347] "Generative AI model" refers to an artificial intelligence algorithm that automatically collects, analyzes, and generates research information.

[1348] "Sources" refer to databases, websites, official organizations, etc. that provide information related to the research topic.

[1349] "Database" refers to an information management system that stores and manages information collected by a server and extracts necessary data.

[1350] "Analysis" refers to the process of analyzing collected information, filtering out noisy data, removing redundant data, and extracting necessary information.

[1351] "Material" refers to a collection of information generated in a format specified by the user (report, presentation materials, etc.).

[1352] "Delivery" refers to the process by which the server transmits and provides the generated materials to the user.

[1353] "Feedback" refers to the process by which a User reviews delivered materials and requests any necessary corrections or additional information.

[1354] "Researcher" refers to an expert who has specialized knowledge on a specific research topic and provides users with detailed information and explanations.

[1355] A "writer" refers to a specialist who generates materials based on collected information and writes them to be provided to users.

[1356] "Online consultation" refers to a communication session over the Internet between a user and a researcher or writer, set up by a server.

[1357] "Filtering" refers to the process of sorting collected data in order to prioritize and analyze highly reliable information.

[1358] MODE FOR CARRYING OUT THE INVENTION

[1359] This invention provides an online research service in which users input their research topic and objectives, use generative AI models to collect and analyze information, and ultimately generate and deliver materials. To implement this invention, the following main components are required:

[1360] 1. A user terminal equipped with a web form for accepting requests

[1361] Users use a web form to input detailed information such as research topic and purpose, etc. The device used can be an electronic device such as a PC, tablet, or smartphone.

[1362] 2. Server responsible for collecting and analyzing information

[1363] The server receives the request sent by the user, uses the generative AI model to collect relevant information, and stores that information in a database. The server also analyzes the collected information and extracts specific data according to the user's request. This requires a server with ample computing power and storage capacity.

[1364] 3. Generative AI Models

[1365] A generative AI model is an artificial intelligence algorithm that automates a series of processes, such as information gathering, analysis, and document generation. In particular, it utilizes natural language processing (NLP) technology to summarize acquired data, extract important information, and automatically generate documents.

[1366] 4. Access to reliable sources of information

[1367] The server uses a generative AI model to collect data from trusted sources (e.g., academic paper databases, public information sites, etc.). For example, to obtain data on the latest medical research, it uses the PubMed API.

[1368] 5. Data filtering and analysis algorithms

[1369] The server uses algorithms to filter out noise data and remove duplicate data in the early stages of analysis, extracting only the necessary information.

[1370] 6. Report and presentation generation tools

[1371] It is equipped with tools to generate documents in formats that meet user requirements based on collected and analyzed data, including the automatic generation of charts and graphs.

[1372] 7. Interface for online consultation with experts

[1373] The server provides an interface for online consultation between users and experts (researchers and writers), allowing users to obtain additional information and detailed explanations.

[1374] As a concrete example, let us consider the case where a user requests research on the latest lung cancer treatments. The user uses a terminal to input the research topic ("latest lung cancer treatments") and purpose ("creating presentation materials"), and then submits detailed information ("research subject: research over the past five years," scope, deadline, desired data format, etc.).

[1375] The server then uses the generative AI model to retrieve relevant paper metadata (title, author, abstract, publication date) from the PubMed API using a query such as "lung cancer AND treatment AND latest." The server stores the collected information in a database and analyzes it using natural language processing techniques to extract key points about the effectiveness of treatments.

[1376] The server then creates graphs comparing the effectiveness of each treatment and generates a comprehensive report. The resulting data is delivered to the user's device for review. If necessary, the user can submit feedback requests for additional information or corrections, and the server will respond.

[1377] Furthermore, if a user requests "I would like to consult with an expert," the server will use an online consultation tool to set up an online meeting between the user and an expert, allowing them to obtain detailed information and explanations.

[1378] Example prompt sentence:

[1379] "I would like to research the latest lung cancer treatments. My goal is to create presentation materials, and my research will focus mainly on the latest treatments, their effectiveness, and side effects. The deadline is one week."

[1380] The present invention allows users to obtain high-quality research results quickly and efficiently, and also allows for requests for necessary corrections and additional information. Furthermore, a system is provided that can meet the diverse needs of users through online consultations with experts.

[1381] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1382] Step 1: Accepting a user request

[1383] A user accesses the system using a terminal and inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials). They can also input detailed information (research subject, scope, deadline, desired data format, etc.). The input information is sent from the terminal to the server as an HTTP request.

[1384] Input: Research topic, purpose, detailed information (research subject, scope, deadline, desired data format, etc.)

[1385] Output: Request data sent to the server

[1386] Specific action: A user enters a research topic and purpose into a web form and clicks the submit button.

[1387] Step 2: Gather information

[1388] The server analyzes the received request and activates a generative AI model. The generative AI model generates specialized search queries against reliable sources (e.g., medical paper databases, news sites, official websites, etc.) to crawl the information. The server uses the generative AI model to collect the information and stores it in a database.

[1389] Input: Request data

[1390] Output: Collected information data

[1391] Specific operation: The server generates the query "lung cancer AND treatment AND latest," and the generative AI model uses the PubMed API to collect related information.

[1392] Step 3: Data analysis and extraction

[1393] The server stores the collected information in a database and performs analysis. During the analysis process, noise data is filtered out and duplicate data is removed, and necessary information (e.g., the effectiveness of treatments, side effects, new technologies, etc.) is extracted.

[1394] Input: Collected information data

[1395] Output: Parsed information data

[1396] Specific operation: The server analyzes the abstract of each paper using natural language processing technology and extracts information about the effectiveness of treatments.

[1397] Step 4: Generate materials

[1398] Based on the analyzed information, the server generates materials in the format desired by the user (reports, presentation materials, etc.) It also creates charts and graphs to present the data visually in an easy-to-understand manner.

[1399] Input: Parsed information data

[1400] Output: Generated materials (reports, presentation materials)

[1401] Specific operation: The server creates a graph comparing the effects of each treatment and automatically generates a document containing an explanation.

[1402] Step 5: Delivery and feedback

[1403] The server sends the completed document to the user's device. If the user checks the document and requests any necessary corrections or additional information, they send their feedback to the server. The server then corrects and updates the document based on the user's feedback.

[1404] Input: Finished materials, user feedback

[1405] Output: Corrected and updated materials

[1406] Specific operation: The server sends the generated data to the user's email address, and the user fills in the feedback form with comments such as "I would like more data" and "I would like to change the color of the graph."

[1407] Step 6: Expert consultation support

[1408] If a user wishes to consult with a professional researcher or writer, the server will use online consultation tools (e.g., Zoom, Teams) to set up a consultation session, through which the user can obtain additional information and detailed explanations.

[1409] Input: User's consultation request

[1410] Output: A configured online consultation session

[1411] Specific behavior: A user requests "I would like to consult with an expert," and the server uses the consultation tool to send a meeting link to the user.

[1412] (Application example 1)

[1413] 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."

[1414] In today's virtual stores, it is difficult for users to quickly and efficiently gather product information and easily create comparison materials based on that information. Furthermore, there are limited ways to flexibly obtain appropriate feedback and additional information. Under these circumstances, there is a need for advanced information research systems to support purchasing decisions.

[1415] 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.

[1416] In this invention, the server includes a means for a user to input a research topic and purpose in the virtual store, a means for collecting related data using a generative AI model, and a means for analyzing the collected information and extracting data related to the user's needs, thereby enabling users to quickly and accurately compare and consider product information in the virtual store and automatically generate materials for that purpose.

[1417] "Research Topic" refers to a particular issue or problem that a User specifies as the subject of research.

[1418] "Objective" refers to the goal or outcome that the user is trying to achieve through research.

[1419] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to generate and analyze information.

[1420] "Sources" refer to trusted websites, databases, etc. that you access to gather data.

[1421] "Data" refers to a collection of information or facts that are collected and analyzed.

[1422] "Analysis" refers to the process of examining and analyzing collected data to find meaning and patterns.

[1423] "Extraction" refers to selecting the necessary information from the analyzed data.

[1424] A "report" refers to a document summarizing the results of an investigation.

[1425] "Presentation materials" refers to slides and documents used to visually represent and explain research results.

[1426] "Delivery" refers to providing the generated materials to the user.

[1427] "Feedback" refers to opinions and requests for corrections regarding materials received from users.

[1428] "Web crawling" refers to the techniques and processes used to automatically collect information on the Internet.

[1429] "Smart Device" means a user device that is connected to the Internet and capable of collecting and displaying information.

[1430] "Expert researchers and authors" refer to experts who have knowledge and experience in a particular field and can provide additional information and explanations to users.

[1431] "Filtering" refers to the process of prioritizing highly reliable and relevant information.

[1432] The present invention provides a system that allows users to efficiently conduct product research in a virtual store. A specific embodiment of the system is described below.

[1433] System Overview and Configuration

[1434] The user inputs the research topic and purpose using a smart device. For example, the research topic can be "creating a review and comparison document on the latest vitamin C-containing skin care products." The information entered by the user is sent to the server.

[1435] Information gathering

[1436] The server invokes the generative AI model to gather relevant data from trusted sources, specifically using web crawling techniques to gather information such as product names, prices, and links, using the requests and BeautifulSoup libraries.

[1437] Data analysis and extraction

[1438] The server analyzes the collected information and extracts the necessary data. Generative AI models and natural language processing techniques are used for data analysis. Filtering functions are used to prioritize reliable information.

[1439] Generate materials

[1440] The server generates materials in the user's desired format (reports, presentation materials, etc.) based on the extracted data. At this time, an AI model is used to create review and comparison materials. OpenAI's API is used to generate materials using AI.

[1441] Delivery and feedback

[1442] The generated materials are delivered to the user's smart device. The user can review the materials and send any necessary feedback to the server, which then corrects the materials.

[1443] Consultation support with experts

[1444] If the user wishes, the server can set up an online consultation with a researcher or author in the field, who can provide additional information and detailed explanations.

[1445] Specific examples

[1446] For example, if a user requests research on "the latest skin care products with vitamin C," they can enter the following prompt:

[1447] Write a review and comparison of the latest Vitamin C skin care products.

[1448] product:

[1449] 1. ABC Vitamin C Serum - $29.99

[1450] 2. XYZ Vitamin C Cream - $35.99

[1451] 3. LMN Vitamin C Essence - $45.00

[1452] By feeding this prompt into a generative AI model, a detailed report is generated that includes reviews and comparisons of each product, allowing users to make more efficient product choices.

[1453] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1454] Step 1:

[1455] The user inputs the research topic and purpose.

[1456] Using a smart device, users input their research topic (e.g., the latest vitamin C-containing skin care products) and goal (e.g., to create a product review and comparison document), including information such as the target market and delivery date.

[1457] Step 2:

[1458] The server uses a generative AI model to collect relevant data from sources.

[1459] Based on the research topic entered by the user, the server uses a generative AI model to collect relevant data from reliable sources, using web crawling technology to generate search queries and collect product information (e.g., product names, prices, links) from websites that have corresponding data.

[1460] Step 3:

[1461] The server analyzes the collected information and extracts data related to the user's research topic.

[1462] The server applies natural language processing technology to analyze the collected information and extracts the necessary data, specifically, product names, prices, review content, etc., and filters the information to prioritize the most reliable information for analysis.

[1463] Step 4:

[1464] The server generates reports and presentation materials based on the extracted data.

[1465] The server generates materials in the format specified by the user (reports, presentation materials, etc.) based on the analyzed data. This process involves using a generative AI model to create reviews and comparison materials for each product. Specifically, it creates graphs and tables that visually summarize each product's features, price, review content, etc.

[1466] Step 5:

[1467] The server delivers the generated materials to the user, who provides feedback and corrections.

[1468] The generated materials are sent to the user's smart device. The user reviews the materials and sends any necessary feedback or correction requests to the server. The server then corrects and updates the materials based on the received feedback.

[1469] Step 6:

[1470] The server sets up online consultations with expert researchers and authors.

[1471] If the user needs additional information or detailed explanation, the server will set up an online consultation with expert researchers and authors, through which the user can get more detailed information or further explanation.

[1472] The specific operations and inputs / outputs at each step are shown below:

[1473] Step 1 Input: Research topic, objectives, additional information (e.g. target market, deadline)

[1474] Step 1 Output: User request data

[1475] Step 2 Input: User Request Data

[1476] Step 2 Output: Collected Product Data

[1477] Input for Step 3: Collected Product Data

[1478] Output of Step 3: Parsed product data

[1479] Input for Step 4: Parsed Product Data

[1480] Step 4 Output: Generated reports and presentations

[1481] Step 5 Input: Generated materials, user feedback

[1482] Step 5 Output: Corrected and updated documentation

[1483] Step 6: Requesting additional information or clarification from the user

[1484] Step 6 Output: Additional information and detailed commentary from experts

[1485] 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.

[1486] The present invention is a system that provides an online research service that combines an emotion engine that recognizes the user's emotions, collects and analyzes reliable information based on the research theme and purpose, and finally generates and delivers materials. A specific embodiment of this system is shown below.

[1487] System Overview

[1488] Accepting user requests

[1489] The user uses a terminal to input the research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system. Detailed information (research subject, scope, deadline, desired data format, etc.) can be entered into the request form. This input information is sent to the server.

[1490] Information gathering

[1491] The server receives the user's request and activates a generative AI model to collect relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). The generative AI model generates specialized search queries and accesses the sources to crawl the data.

[1492] Examples:

[1493] The generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of relevant papers.

[1494] Data analysis and extraction

[1495] The server temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion engine that recognizes emotions from user input and applies information collection and analysis methods according to those emotions.

[1496] Examples:

[1497] If a user types "I'm in a hurry," the emotion engine recognizes the urgency and quickly collects, analyzes, and delivers information.

[1498] Prioritizing information based on emotions

[1499] The server uses the emotion engine to prioritize information based on the user's emotions, thereby efficiently providing the information that is of most interest to the user.

[1500] Examples:

[1501] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[1502] Generate materials

[1503] The server generates materials in the format desired by the user (reports, presentation materials, etc.) based on the analyzed data. At this time, the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[1504] Examples:

[1505] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[1506] Delivery and feedback

[1507] The server delivers the generated materials to the user's terminal and receives feedback from the user. If the user checks the materials and requests any necessary corrections or additional information, the server responds accordingly.

[1508] Consultation support with experts

[1509] If the user so desires, the server will set up an online consultation with a professional researcher or writer, through which the user can request additional information or detailed explanation.

[1510] Examples:

[1511] The user requests a more detailed explanation and obtains additional information through consultation with an expert.

[1512] Implementation method

[1513] To implement this system, the following major components are required:

[1514] 1. A user terminal equipped with a web form for accepting requests

[1515] 2. Server responsible for collecting and analyzing information

[1516] 3. Generative AI Models

[1517] 4. Access to reliable sources of information

[1518] 5. Data filtering and analysis algorithms

[1519] 6. Emotion Engine

[1520] 7. Report and presentation generation tools

[1521] 8. Online consultation interface with experts

[1522] Example

[1523] For example, if a user requests research on the latest lung cancer treatments and inputs feelings of anxiety, the emotion engine recognizes the anxiety. The server uses a generative AI model to collect relevant paper data from PubMed and uses natural language processing to extract key points about the treatment's effectiveness. The emotion engine then prioritizes information that provides reassurance and issues a visually reassuring report. The materials are delivered to the user and revised based on their feedback. If necessary, additional information and detailed explanations can be added through consultation with experts. This series of processes provides efficient and reliable research results that take the user's emotions into account.

[1524] The processing flow will be explained below.

[1525] Step 1:

[1526] The user inputs their research topic (e.g., "latest lung cancer treatment methods") and purpose (e.g., creating presentation materials) into the system via their terminal. The emotion engine then extracts emotions (e.g., anxiety, excitement, urgency, etc.) from the user's input and a simple questionnaire. This input and emotion information are then sent to the server.

[1527] Step 2:

[1528] The server receives the user's request and emotion information, and then activates the generative AI model. The server generates a search query based on the user's request and prepares to access reliable information sources (e.g., medical paper databases, news sites, official research institution websites, etc.).

[1529] Step 3:

[1530] The server uses a generative AI model to collect relevant data from target sources. The generative AI model accesses sources using queries and crawls relevant data (e.g., paper metadata, news articles).

[1531] Examples:

[1532] The generative AI model uses the PubMed API to search for the query "lung cancer AND treatment AND latest" and retrieves the metadata of relevant papers.

[1533] Step 4:

[1534] The server temporarily stores the collected data in a database. At this stage, the collected data is in raw format and has not yet been analyzed.

[1535] Step 5:

[1536] The server uses a generative AI model to analyze the stored data, including an emotion engine that applies information gathering and analysis techniques based on the emotions derived from the user's input.

[1537] Examples:

[1538] If a user types "I'm in a hurry," the emotion engine will recognize the urgency and quickly collect, analyze, and deliver information.

[1539] Step 6:

[1540] The server uses the emotion engine to prioritize information based on the user's emotions, allowing the server to efficiently provide the information that the user is most interested in.

[1541] Examples:

[1542] When a user inputs an emotion indicating anxiety, the emotion engine prioritizes the user's sense of security and provides information that is highly reliable and gives a sense of security.

[1543] Step 7:

[1544] The server extracts important information related to the user's research topic (e.g., effectiveness of treatments, side effects, new technologies) from the analyzed data. At this stage, natural language processing technology is used to capture abstract key points.

[1545] Examples:

[1546] The abstract of each paper is analyzed and descriptions of the effectiveness of the treatment are extracted.

[1547] Step 8:

[1548] The server generates reports and presentation materials based on the extracted data, and the emotion engine uses expressions that match the user's emotions, providing materials in a format that is more easily accepted by the user.

[1549] Examples:

[1550] When a user requests a presentation, the emotion engine senses the user's excitement and generates visually appealing slides.

[1551] Step 9:

[1552] The server sends the generated prototype report and presentation materials to the user's terminal, where the user can review the materials and make any necessary corrections or request additional information.

[1553] Step 10:

[1554] Users can review the materials, send requests for necessary corrections or additional information to the server from their terminal, and, if necessary, request online consultation with professional researchers or writers.

[1555] Step 11:

[1556] Based on user feedback, the server uses generative AI models and expert knowledge to revise and update the materials, and then performs a final check before delivering them to the user.

[1557] Step 12:

[1558] The server delivers the completed report or presentation materials to the user's device, and provides support for a certain period of time after delivery to respond to any additional questions or correction requests from the user.

[1559] Example 2

[1560] 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."

[1561] Conventional online research services have struggled to prioritize information based on user sentiment or generate the materials users desire related to their research topic. They also face challenges in efficiently collecting and analyzing reliable information. Furthermore, efficient consultation with expert researchers and writers is difficult, and feedback responses to enhance user satisfaction are insufficient.

[1562] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1563] In this invention, the server includes means for a user to input a research topic and purpose, means for the server to collect related information from information sources using a generative AI model, means for the server to analyze the collected data and extract information related to the user's research topic, means for the server to perform analysis using an emotion recognition engine, means for the server to generate visual materials based on the extracted information, and means for the server to deliver the generated materials to the user and provide necessary feedback and corrections. This enables the provision of information according to the user's emotions, efficient collection and analysis of reliable information, and effective consultation with experts and feedback response.

[1564] A "research topic" is a specific topic or area that a user sets as the subject of research.

[1565] "Objectives" are the specific goals or objectives that a user wants to achieve when conducting research.

[1566] A "generative AI model" is an algorithmic system that uses artificial intelligence to perform natural language processing and data analysis.

[1567] "Sources" refer to external databases and websites that provide data and information needed for research.

[1568] An "emotion recognition engine" is a system that analyzes emotions based on user input and selects an appropriate processing method.

[1569] "Visual materials" are documents that are visually displayed, such as reports or presentations generated based on analyzed information.

[1570] "Feedback" is the process by which users provide corrections and comments on received material.

[1571] "Expert researchers and writers" are experts with knowledge and experience in a particular topic or field.

[1572] To implement this invention, a user terminal, a server, a generative AI model, an emotion recognition engine, and a database are required. A specific embodiment of this system is shown below.

[1573] First, the user inputs the research topic and purpose. For example, the user inputs "latest lung cancer treatment methods" and "creating presentation materials" from the terminal. The input information is then sent from the terminal to the server.

[1574] The server receives the user's request and launches a generative AI model. This generative AI model is, for example, a GPT-based model for natural language processing. The server collects relevant information from reliable sources (e.g., medical paper databases, news sites, official research institution websites, etc.). Specifically, the generative AI model accesses the PubMed API using the query "lung cancer AND treatment AND latest" to retrieve the metadata of the relevant paper.

[1575] The server then temporarily stores the collected data in a database and analyzes it using a generative AI model. This analysis includes an emotion recognition engine that recognizes emotions from the user's input and applies information collection and analysis methods based on that emotion. For example, if the user inputs "I'm in a hurry," the emotion recognition engine will recognize the urgency and quickly collect, analyze, and deliver the information.

[1576] The server then uses an emotion recognition engine to prioritize information based on the user's emotions, allowing it to efficiently provide the information the user is most interested in. For example, if the user types "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[1577] The server then generates materials in the user's desired format (report, presentation, etc.) based on the analyzed data. The emotion recognition engine uses expressions that match the user's emotions, providing materials in a format that is more user-friendly. For example, if a user requests presentation materials, the emotion recognition engine can sense the user's excitement and generate visually appealing slides.

[1578] Finally, the server delivers the generated materials to the user's device and receives feedback from the user. If the user reviews the materials and requests any necessary corrections or additional information, the server responds accordingly. If the user wishes, the server can also set up an online consultation with a professional researcher or writer. Through this consultation, the user can request additional information or detailed explanations.

[1579] An example of a specific prompt is, "Please hurry and provide reliable information about the latest lung cancer treatments. I'm feeling anxious."

[1580] This makes it possible to provide high-quality materials that correspond to the user's emotions and research needs, thereby increasing user satisfaction.

[1581] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1582] Step 1:

[1583] Accepting user requests

[1584] The user enters the research topic and purpose from the device. For example, the user enters "latest lung cancer treatments" and "creating presentation materials" into a web form on the device.

[1585] Input: User's research topic and purpose

[1586] Output: Send request containing the entered request data

[1587] Specific operation: The user fills in detailed information (such as research subject, deadline, and desired data format) in each field of the web form and clicks the "Submit" button, which causes the device to send the entered information to the server.

[1588] Step 2:

[1589] Information gathering

[1590] The server receives the user's request and launches a generative AI model, which then gathers relevant information from trusted sources. For example, the generative AI model creates a query for "latest lung cancer treatments" and accesses the PubMed API to retrieve metadata for related papers.

[1591] Input: User request data

[1592] Output: A dataset containing the relevant information collected

[1593] How it works: The server calls the generative AI model to generate a specialized search query, which the generative AI model executes to efficiently crawl data from sources and retrieve relevant information.

[1594] Step 3:

[1595] Data analysis and extraction

[1596] The server temporarily stores the collected data in a database and performs data analysis using a generative AI model. This analysis includes an emotion recognition engine. For example, the emotion recognition engine recognizes the user's emotions and applies an analysis method according to the emotion.

[1597] Input: Collected relevant information

[1598] Output: Parsed dataset

[1599] How it works: The server stores the collected data in a database, the generative AI model performs natural language processing to extract key points from the data, and the emotion recognition engine selects an analysis method based on the emotion entered by the user.

[1600] Step 4:

[1601] Prioritizing information based on emotions

[1602] The server uses an emotion recognition engine to prioritize information based on the user's emotions. For example, if the user inputs "anxiety," the emotion recognition engine will prioritize information that gives a sense of security.

[1603] Input: Parsed dataset and user emotion information

[1604] Output: prioritized information

[1605] How it works: The server applies an emotion recognition engine and a prioritization algorithm based on the user's input emotion. Information is organized around the content that the user is most interested in.

[1606] Step 5:

[1607] Generate materials

[1608] The server generates materials in the format desired by the user (reports, presentation materials) based on the analyzed data. At this time, an emotion recognition engine uses expressions that match the user's emotions. For example, in the case of presentation materials, visually appealing slides are generated.

[1609] Input: prioritized information and user preferred format

[1610] Output: Generated materials (reports and slides)

[1611] Specific operation: The server uses a document generation tool to create visually appealing documents based on an emotion recognition engine. The document generation tool uses templates and design elements to create high-quality documents.

[1612] Step 6:

[1613] Delivery and feedback

[1614] The server delivers the generated materials to the user's terminal and receives feedback from the user. The user checks the materials and requests any necessary corrections or additional information.

[1615] Input: Generated material

[1616] Output: User feedback and correction requests

[1617] Specific operation: The server sends the generated document file to the user's device. The user reads the document and uses the feedback form or comment function to request corrections or add additional information.

[1618] Step 7:

[1619] Consultation support with experts

[1620] If the user wishes, the server will set up an online consultation with a professional researcher or writer.

[1621] Input: User consultation request

[1622] Output: Responses to inquiries and supplementary information

[1623] Specific operation: The user fills out a request form stating, "I would like to consult with an expert." The server schedules a session with the expert using a video conferencing tool or similar. After the consultation is completed, the user is provided with supplementary information and detailed explanations.

[1624] (Application example 2)

[1625] 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."

[1626] Current challenges in logistics centers include a work environment that ignores the emotional state of workers and inefficient work instructions. Failure to consider appropriate breaks and work priorities increases fatigue and stress, leading to problems with reduced work efficiency and quality. Furthermore, research does not take into account the emotions of users when collecting and analyzing information, creating a need for reliable results that are delivered quickly and efficiently.

[1627] 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.

[1628] In this invention, the server includes: [means for a user to input a research topic and purpose;] [means for the server to collect relevant data from information sources using a generated AI model; and] [means for recognizing the facial expressions and tone of voice of workers in real time and analyzing their emotional state.] This allows the emotional state of workers to be grasped in real time and optimal work instructions to be generated, thereby improving work efficiency and the work environment at logistics centers. Furthermore, reliable information collection and analysis based on user requests can be realized, allowing for fast and efficient provision of materials.

[1629] "Means for users to input research topic and purpose" refers to an interface that allows users to electronically input their research purpose and detailed research topic.

[1630] "Means for a server to collect relevant data from information sources using a generated AI model" refers to means for automatically collecting relevant data from reliable information sources using an artificial intelligence model generated by a server.

[1631] "Means for the server to analyze information and extract data related to the user's research topic" refers to the means for the server to analyze the information collected and select data that matches the research topic desired by the user.

[1632] "Means for generating reports and presentation materials based on data extracted by the server" refers to means for using data analyzed and extracted by the server to create reports and presentation materials tailored to the user's needs.

[1633] "Means for the server to deliver generated materials to the user and provide necessary feedback and corrections" refers to means for the server to provide generated reports and materials to the user and make corrections based on feedback from the user.

[1634] "Means for recognizing a worker's facial expression and tone of voice in real time and analyzing their emotional state" refers to means for monitoring a worker's facial expression and tone of voice in real time and evaluating their emotional state using emotion recognition technology.

[1635] The "means for analyzing emotion data and generating instructions for optimizing work efficiency" refers to a means for analyzing collected emotion data and generating optimal instructions for improving work efficiency.

[1636] This invention is a system that improves work efficiency in logistics centers and provides optimal work instructions based on the emotions of workers. This system incorporates a worker emotion recognition function as part of the collection and analysis of reliable information based on the user's research theme and purpose, and the creation of necessary materials.

[1637] System configuration

[1638] Hardware and software used

[1639] Hardware: Smartphones (Android and iOS), Head-Mounted Displays (HMDs: for example, Microsoft HoloLens)

[1640] Software: Emotion recognition engine (e.g., Affectiva SDK), generative AI model (e.g., OpenAI GPT-4), cloud server (e.g., AWS EC2 instance)

[1641] Program processing

[1642] overview

[1643] 1. Emotion Recognition: A worker wears a smartphone or HMD and launches the application. The camera captures the worker's facial expressions and tone of voice, and the emotion recognition engine (Affectiva SDK) analyzes their emotional state in real time. This data is sent to a cloud server.

[1644] 2. Data transmission and analysis: The cloud server (AWS EC2 instance) analyzes the received emotion data using a generative AI model (GPT-4) to evaluate the level of stress, fatigue, and anxiety. Based on this evaluation, work priorities and break instructions are optimized.

[1645] 3. Generating and providing work instructions: The generative AI model combines the analysis results with operational data to generate optimal work instructions. For example, it can recommend a break for a tired worker and assign urgent tasks to other workers. This information is fed back to the smartphone or HMD in real time.

[1646] Specific examples

[1647] Usage Scenarios

[1648] A worker at a logistics center starts his morning shift. He launches an emotion recognition app on his smartphone, which begins facial recognition and voice tone analysis. After 45 minutes, the emotion engine detects "fatigue," and a notification appears on A's smartphone saying, "Your fatigue level is increasing. We recommend you take a 10-minute break." After the break, the most important tasks are listed, allowing A to resume work efficiently.

[1649] Prompt Sentence Examples

[1650] An example prompt for a generative AI model is:

[1651] markdown

[1652] "Worker A's emotional data indicates that he is becoming increasingly fatigued for tasks with an urgency of C. Generate a message to encourage him to take a break, followed by suggestions to optimize the prioritization of his work."

[1653] This will enable optimal work instructions to be provided in real time based on the analysis results of the emotion recognition and generative AI model, enabling the realization of an efficient and healthy working environment in logistics centers. Furthermore, since it is possible to simultaneously collect reliable information based on research themes and quickly generate materials, a powerful system will be built that can meet the diverse needs of users.

[1654] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1655] Step 1:

[1656] The user puts on a smartphone or head-mounted display and launches the application. This causes the device's camera to begin capturing the worker's facial expressions and tone of voice in real time. The input is real-time facial expression data and tone of voice data from the camera, and the output is raw data sent to the emotion recognition engine.

[1657] Step 2:

[1658] An emotion recognition engine (e.g., Affectiva SDK) analyzes real-time facial expression data and tone of voice data. The input data includes multiple facial expressions and tone of voice data, and the output is an analysis result of the emotional state (e.g., fatigue, anxiety, stress, etc.) extracted from the data.

[1659] Step 3:

[1660] The server receives the emotion analysis results sent from the emotion recognition engine and stores the analyzed data on a cloud server (AWS EC2 instance). The input is the emotion analysis results, and processing is performed to store the emotional state in a database.

[1661] Step 4:

[1662] Based on the emotional state data received by the cloud server, a generative AI model (e.g., GPT-4) is launched and analyzed. The input is the emotional state data, and the output is the intermediate result for generating instruction prompts based on that data to improve work efficiency.

[1663] Step 5:

[1664] Based on the generated prompt sentence, the generative AI model generates optimal work instructions for improving work efficiency. For example, based on the input prompt sentence, it generates a message recommending that a fatigued worker take a break, or an instruction to assign a highly urgent task to another worker. The output is a specific work instruction message.

[1665] Step 6:

[1666] The cloud server then sends the generated work instruction messages to a smartphone or head-mounted display, providing real-time feedback to the worker. The input is the work instruction message output by the generative AI model, and the output is specific instructions displayed on the worker's device.

[1667] Step 7:

[1668] The worker actually performs the work based on the work instruction message received. For example, he / she takes a break or engages in other urgent work. The input is the feedback work instruction, and the output is the worker's action (performing the work, taking a break, etc.).

[1669] This series of processes enables real-time monitoring of workers' emotional states and the use of generative AI models to generate and provide optimal work instructions, thereby improving work efficiency and the working environment at logistics centers.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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).

[1677] 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.

[1678] 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."

[1679] 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.

[1680] 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).

[1681] 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.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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.

[1689] 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.

[1690] 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.

[1691] The following is further disclosed regarding the above embodiment.

[1692] (Claim 1)

[1693] [Means for users to input research topics and objectives;

[1694] [Means by which the server uses the generative AI model to collect relevant data from sources; and

[1695] [Means for the server to analyze the information and extract data relevant to the user's research topic; and

[1696] [Means for generating reports and presentation materials based on the data extracted by the server;

[1697] [Means for the server to deliver the generated materials to the user and provide necessary feedback and corrections;

[1698] A system including:

[1699] (Claim 2)

[1700] The system of claim 1, further comprising means by which the server can set up online consultations with expert researchers and writers to allow the user to request additional information or commentary.

[1701] (Claim 3)

[1702] The system of claim 1, further comprising means for the server to use the generative AI model to perform filtering to prioritize and analyze highly reliable information when collecting information.

[1703] "Example 1"

[1704] (Claim 1)

[1705] [Means for users to input research topics and objectives;

[1706] [Means for transmitting user input to a server;

[1707] [Means by which the server uses the generative AI model to collect relevant data from sources; and

[1708] [Means for storing and analyzing the information collected by the server in a database;

[1709] [Means for the server to analyze the information and extract data relevant to the user's research topic; and

[1710] [Means for generating reports and presentation materials based on the data extracted by the server;

[1711] [Means for the server to deliver the generated materials to the user and provide necessary feedback and corrections;

[1712] A system including:

[1713] (Claim 2)

[1714] The system of claim 1, further comprising means by which the server can set up online consultations with expert researchers and writers to allow the user to request additional information or commentary.

[1715] (Claim 3)

[1716] The system of claim 1, further comprising means for the server to use the generative AI model to perform filtering to prioritize and analyze highly reliable information when collecting information.

[1717] "Application Example 1"

[1718] (Claim 1)

[1719] [Means for users to input research topics and objectives;

[1720] [Means by which the server uses the generative AI model to collect relevant data from sources; and

[1721] [Means for the server to analyze the information and extract data relevant to the user's research topic; and

[1722] [Means for generating reports and presentation materials based on the data extracted by the server;

[1723] [Means for the server to deliver generated materials to users and provide feedback and corrections;

[1724] [Means for improving the efficiency of information gathering by using web crawling when gathering information;

[1725] [A means for users to check and compare the generated data via smart devices,

[1726] A system including:

[1727] (Claim 2)

[1728] The system of claim 1, further comprising means for the server to set up online consultations with expert researchers and authors to allow the user to request additional information or commentary.

[1729] (Claim 3)

[1730] The system of claim 1, further comprising means for the server to use the generative AI model to perform filtering to prioritize and analyze highly reliable information when collecting information.

[1731] "Example 2: Combining Emotion Engines"

[1732] (Claim 1)

[1733] [Means for users to input research topics and objectives;

[1734] [Means for the server to collect relevant information from sources using the generative AI model; and

[1735] [Means for analyzing the data collected by the server and extracting information related to the user's research topic;

[1736] [Means for the server to perform analysis using an emotion recognition engine;

[1737] [Means for generating visual materials based on the extracted information by the server;

[1738] [Means for the server to deliver the generated materials to the user and provide necessary feedback and corrections;

[1739] A system including:

[1740] (Claim 2)

[1741] The system of claim 1, further comprising means for the server to prioritize information based on emotions and provide information according to the user's emotions.

[1742] (Claim 3)

[1743] [The system of claim 1, wherein the server sets up online consultations with expert researchers and writers to allow users to request additional information or clarification.]

[1744] "Application example 2 when combining emotion engines"

[1745] (Claim 1)

[1746] [Means for users to input research topics and objectives;

[1747] [Means by which the server uses the generative AI model to collect relevant data from sources; and

[1748] [Means for the server to analyze the information and extract data relevant to the user's research topic; and

[1749] [Means for generating reports and presentation materials based on the data extracted by the server;

[1750] [Means for the server to deliver the generated materials to the user and provide necessary feedback and corrections;

[1751] [Means of recognizing workers' facial expressions and tone of voice in real time and analyzing their emotional state;

[1752] [Means for analyzing emotion data and generating instructions for optimizing work efficiency;

[1753] A system including:

[1754] (Claim 2)

[1755] The system of claim 1, further comprising means by which the server can set up online consultations with expert researchers and writers to allow the user to request additional information or commentary.

[1756] (Claim 3)

[1757] The system of claim 1, further comprising means for the server to use the generative AI model to perform filtering to prioritize and analyze highly reliable information when collecting information. [Explanation of symbols]

[1758] 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 for a user to input a research topic and objectives; a means by which the server uses the generative AI model to collect relevant data from sources; a means for the server to analyze the information and extract data relevant to the user's research topic; A means for generating reports and presentation materials based on the data extracted by the server; A means for the server to deliver the generated materials to the user and provide necessary feedback and corrections; A system including:

2. 10. The system of claim 1, further comprising means by which the server can set up online consultations with expert researchers and writers to allow users to request additional information or clarification.

3. The system according to claim 1, further comprising means for filtering information collected by the server using the generative AI model to prioritize and analyze highly reliable information.

Images