System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data from a reliable information source; means for evaluating reliability of the collected data; means for analyzing the collected data using a natural language processing algorithm; means for generating a discussion based on an analysis result; means for transmitting the generated discussion to a terminal of a user; and means for displaying the generated discussion on the terminal of the user.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 today's information environment, fake news and misleading / exaggerated information are rampant, and the influence of filter bubbles on social media is increasingly marginalizing diverse perspectives and differing opinions. As a result, users often receive biased information, making it difficult to access fair and reliable information. Furthermore, many users lack the means to quickly obtain reliable information and gain a deeper understanding. Therefore, there is a need for a system that provides multifaceted and fair discussions based on reliable information sources. [Means for solving the problem]

[0005] The present invention provides a system that includes means for collecting data from reliable sources and evaluating its reliability, means for analyzing the collected data using a natural language processing algorithm, and means for generating multifaceted discussions based on the analysis results. The system transmits the generated discussions to a user's device, allowing the user to view them through an interface. Specifically, the system collects data from reliable sources, evaluates its reliability through cross-referencing, analyzes the data using natural language processing, and generates discussions by integrating opinions and views from different perspectives based on the analysis results. This allows users to obtain multifaceted and fair information, contributing to improving information literacy throughout society.

[0006] A "reliable source" is a source that provides information that is recognized as reliable, such as a public agency, academic institution, certified expert, or official document.

[0007] "Means of collecting data" refers to the mechanisms by which information is obtained from the internet or databases, such as through API requests, web scraping, or other methods.

[0008] "Means for assessing reliability" refers to a system for cross-referencing the source and content of collected data and assessing the reliability and accuracy of the information.

[0009] "Natural language processing algorithms" is a general term for statistical and machine learning techniques used to analyze text data and understand its structure and meaning.

[0010] "Means for analyzing data" refers to a system that uses natural language processing algorithms to analyze collected text data and extract important information.

[0011] "Means for generating discussions" refers to a mechanism that integrates opinions and views from different perspectives based on the analysis results and creates information in the form of discussions to be provided to users.

[0012] "Means for transmitting to the user's terminal" refers to the mechanism for encoding the generated discussion and transmitting it to the user's electronic device (e.g., smartphone, computer) via a network.

[0013] "Means for displaying on the user's terminal" refers to an interface for visually presenting the discussion received on the terminal to the user.

[0014] "Cross-referencing" is a method of cross-referencing different sources of information to check for agreements or contradictions in the information.

[0015] "Different perspectives" refers to the diverse viewpoints and opinions on a particular issue or topic, and the multiple perspectives necessary to deepen overall understanding. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[0038] Program processing

[0039] 1. Data Collection:

[0040] The server collects data from reliable sources (e.g., announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[0041] 2. Reliability assessment:

[0042] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[0043] 3. Natural Language Processing Analysis:

[0044] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[0045] 4. Discussion Generation:

[0046] The server generates a multifaceted discussion based on the analysis results, a process that balances and integrates different viewpoints and opinions, and compiles them into a discussion-style information format that contains fair and multifaceted views.

[0047] 5. Send to user device:

[0048] The server encodes the generated discussion and sends it to the user's device using a RESTful API, with the data sent in JSON format.

[0049] 6. Display and Feedback:

[0050] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The user can check the content of the discussion through this interface and provide feedback as needed. The feedback is sent to the server and used to improve the system.

[0051] Specific examples

[0052] Example 1: COVID-19 discussion

[0053] 1. Data Collection:

[0054] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[0055] 2. Reliability assessment:

[0056] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[0057] 3. Natural Language Processing Analysis:

[0058] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0059] 4. Discussion Generation:

[0060] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0061] 5. Send to user device:

[0062] The server sends the generated discussion in JSON format to the user's device.

[0063] 6. Display and Feedback:

[0064] The user's terminal visually displays the received discussion data, which the user can view in detail. Through the feedback function, the user can contribute to improving the system.

[0065] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and corporate press releases and articles from major news sites using web scraping technology.

[0069] Step 2:

[0070] The server evaluates the reliability of the collected data. First, it cross-references the source of the data and calculates a reliability score. Information with a low reliability score is rejected at this point.

[0071] Step 3:

[0072] The server analyzes the collected data using natural language processing (NLP) algorithms: topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract key terms, and sentiment analysis (e.g., VADER) to assess emotional tone.

[0073] Step 4:

[0074] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[0075] Step 5:

[0076] The server sends the generated discussion to the user's device. The server encodes the generated discussion information in JSON format and sends it to the user's device using a RESTful API.

[0077] Step 6:

[0078] The user's device analyzes the received discussion data and visually displays it, allowing the user to check the details of the discussion through the interface.

[0079] Step 7:

[0080] Users provide feedback through their devices, which is sent to the server and used to improve the system and its accuracy.

[0081] Through this series of steps, we are able to collect data from reliable sources and provide users with a multifaceted and fair discussion.

[0082] Example 1

[0083] 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."

[0084] In today's information environment, problems such as filter bubbles and fake news are becoming more serious, making it difficult for users to obtain reliable information. It is also difficult to integrate different perspectives from the vast amount of information and generate fair and multifaceted discussions. To solve this problem, a system is needed that can collect reliable data, analyze that data, and generate multifaceted discussions.

[0085] 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.

[0086] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data by cross-referencing, means for analyzing the collected data using a natural language processing algorithm, means for generating a discussion by integrating opinions and views from different perspectives based on the analysis results, means for constructing a multifaceted discussion in natural sentences using a generative AI model, means for transmitting the generated discussion to a user's terminal, and means for displaying the received discussion on the user's terminal and collecting feedback from the user. This makes it possible to provide reliable, multifaceted information and enable users to access fair, multifaceted discussions.

[0087] A "reliable source" is a source that provides accurate and trustworthy data, such as announcements from public institutions, academic papers, and official corporate statements.

[0088] "Means of collecting data" refers to methods of obtaining the necessary information using API requests or web scraping technology.

[0089] "Cross-reference reliability assessment method" is a method for verifying the reliability of collected data by cross-referencing it from multiple sources and calculating a reliability score.

[0090] A "natural language processing algorithm" is a technology that analyzes collected text data, specifically performing topic modeling, keyword extraction, sentiment analysis, etc.

[0091] "Means for generating discussion by integrating opinions and views from different perspectives" refers to a method for generating discussion that incorporates a variety of perspectives and opinions in a balanced manner based on the results of analysis.

[0092] A "generative AI model" is an artificial intelligence technology that generates natural-looking sentences based on given data.

[0093] "Means for sending to the user's device" refers to a method for encoding the generated discussion and sending the data to the user's device via the Internet using a RESTful API.

[0094] "Means for displaying discussions received on the user's terminal and collecting feedback from the user" is a function that displays received discussion data on an interface and allows the user to provide feedback.

[0095] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[0096] System configuration

[0097] The system includes the following main components:

[0098] 1. Server: Responsible for data collection, credibility assessment, natural language processing, argument generation, and data transmission.

[0099] 2. User's terminal: Responsible for displaying generated discussions and collecting user feedback.

[0100] 3. Communication interface: Used to send and receive data between the server and the user's terminal.

[0101] Hardware and software used

[0102] server:

[0103] Hardware: A server machine with a powerful processor and plenty of memory.

[0104] Software: Python for data collection and libraries for performing API requests and web scraping (e.g., BeautifulSoup). NLTK and spaCy for natural language processing. Generative AI models such as GPT-3 are used.

[0105] On the user's device:

[0106] Hardware: PCs, tablets, smartphones, etc.

[0107] Software: Web browser and JavaScript interface.

[0108] Operation details

[0109] Data collection

[0110] The server retrieves data by sending API requests from reliable sources. For example, it retrieves the latest statistical data on COVID-19 from government health agency APIs. It also uses web scraping techniques to gather relevant articles from major news sites. This data collection process is performed periodically to ensure the information is always up to date.

[0111] Reliability evaluation

[0112] The server cross-references the reliability of the collected data, comparing data from multiple reliable sources and assigning a high reliability score to matching information. This evaluation process filters out information with low reliability.

[0113] Natural Language Processing

[0114] The server uses natural language processing algorithms on the collected data, including tokenizing the text using the NLTK library, modeling topics using LDA (Latent Dirichlet Allocation), extracting keywords using TF-IDF (Term Frequency-Inverse Document Frequency), and performing sentiment analysis using VADER (Valence Aware Dictionary for Sentiment Reasoning).

[0115] discussion generation

[0116] The server generates multifaceted discussions based on the analysis results. For example, it uses a generative AI model to construct natural-sounding sentences that combine multiple perspectives, such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[0117] Data transmission and display

[0118] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API. The user's device analyzes the received discussion data and displays it visually on the interface. The user can view the displayed discussions and provide feedback. The feedback is sent to the server and used to improve the system.

[0119] Specific examples

[0120] COVID-19 debate

[0121] 1. Data Collection:

[0122] The server collects official announcements from government health agencies, related academic papers, and press conference reports from major news sites.

[0123] 2. Reliability assessment:

[0124] The server cross-references the reliability of the collected data and selects only the most reliable information.

[0125] 3. Natural Language Processing:

[0126] The server performs sentiment analysis, topic modeling and keyword extraction.

[0127] 4. Discussion generation:

[0128] The server generates multifaceted discussions, including "medical opinions on the effectiveness of vaccines," "opinions on the government's lockdown policy," and "impact on the economy."

[0129] 5. Data transmission and display:

[0130] The server sends the generated discussion in JSON format to the user's device, where the user can view it in an interface.

[0131] Prompt Sentence Examples

[0132] Please generate a well-rounded and fair discussion on the following points regarding COVID-19:

[0133] 1. Medical opinion on vaccine effectiveness

[0134] 2. Opinions on the government's lockdown policy

[0135] 3. Economic impact

[0136] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: Collect data

[0139] The server collects data from reliable sources. It uses URLs and API endpoint information, such as public announcements, academic papers, and official corporate statements, as input. Specifically, the server generates an API request, calling, for example, "https: / / api.example.gov / covid19 / latest." It also uses a Python library for web scraping (e.g., BeautifulSoup) to parse articles from news sites. The output is the collected text data or JSON-formatted data.

[0140] Step 2: Assess reliability

[0141] The server evaluates the reliability of the collected data through cross-referencing. It uses the data collected in step 1 as input. The server compares the URLs and publication dates of the collected data sources and calculates a reliability score. Specifically, the server verifies the origin of each data point and assigns a high score to matching information. The output is a dataset with a reliability assessment and an attached score.

[0142] Step 3: Natural Language Processing Analysis

[0143] The server analyzes the data whose trustworthiness has been evaluated using a natural language processing algorithm. The data whose trustworthiness has been evaluated in step 2 is used as input. The server tokenizes the text using the NLTK library and models topics using LDA (Latent Dirichlet Allocation). Keywords are extracted using TF-IDF (Term Frequency-Inverse Document Frequency), and sentiment analysis is performed using VADER (Valence Aware Dictionary for Sentiment Reasoning). The output is a topic model, important keywords, and sentiment scores as the analysis results.

[0144] Step 4: Generate discussion

[0145] The server generates a multifaceted discussion based on the analysis results. The topic model, keywords, and sentiment scores obtained in step 3 are used as input. The server uses a generative AI model to integrate opinions and views from different perspectives and construct a fair, multifaceted discussion in natural-sounding sentences. Specifically, based on the given prompt, it generates a multifaceted discussion, such as "medical opinion on the effectiveness of vaccines," "opinions on government lockdown policies," and "impact on the economy." The output is text data of the generated discussion.

[0146] Step 5: Send to user device

[0147] The server encodes the generated discussion and sends it to the user's device via a RESTful API. The text data of the discussion generated in step 4 is used as input. The server implements the RESTful API using Python's Flask or similar and sends JSON-formatted data to the endpoint " / sendDiscussion" via a POST request. The output is the discussion data sent to the user's device.

[0148] Step 6: Display and feedback

[0149] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The discussion data sent in step 5 is used as input. The user's device parses the JSON data using JavaScript and displays it visually on a web page. Specifically, a section is created for each discussion point on the interface and text is displayed. The user can view this in detail and enter their opinion through a feedback form. The feedback is sent to the server and used to improve the system. The output is the feedback data from the user.

[0150] (Application example 1)

[0151] 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."

[0152] In today's information environment, unreliable information and fake news are rampant, making it difficult for users to obtain accurate and fair information. This problem increases the risk of making incorrect decisions based on false information. It also makes it difficult to integrate opinions and views from different perspectives in a balanced manner. Furthermore, there is a lack of means to effectively utilize user feedback and improve the accuracy of the system.

[0153] 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.

[0154] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to users' terminals, means for displaying the generated discussions on the users' terminals and receiving feedback, and means for analyzing user feedback and using it to improve the system. This allows for the provision of multifaceted and fair discussions based on reliable information, enabling users to make decisions based on accurate and balanced information. Furthermore, by effectively utilizing user feedback, the accuracy of the system can be continuously improved.

[0155] A "reliable source" is a source whose accuracy and reliability are guaranteed, such as announcements from public institutions, academic papers, and official corporate opinions.

[0156] "Methods for assessing data reliability" refers to the process of cross-referencing the origins of collected data and calculating a reliability score.

[0157] "Means of analyzing data" refers to techniques that use natural language processing algorithms to analyze the structure and meaning of text and extract key information.

[0158] "Means of generating discussion" refers to the process of integrating different perspectives and opinions in a balanced manner based on the results of analysis, and compiling information in a discussion format that includes fair and multifaceted views.

[0159] "Means for sending to the user's device" refers to the process of encoding the generated discussion and sending the data to the user's device using a RESTful API.

[0160] "Means for displaying discussions generated on the user's terminal" refers to a mechanism for analyzing received discussion data and displaying it on an interface that can be viewed by the user.

[0161] "Means for receiving feedback" refers to the process of collecting opinions and suggestions for improvement provided by users and using them to improve the system.

[0162] "Means for analyzing user feedback and using it to improve the system" refers to a method for analyzing collected feedback and improving the functionality and accuracy of the system.

[0163] The system for implementing this invention collects data from reliable information sources and uses that data to generate multifaceted and fair discussions. This system operates in cooperation with three parties: a server, terminals, and users.

[0164] System configuration

[0165] Hardware:

[0166] Server: Responsible for data collection, reliability assessment, natural language processing, and discussion generation.

[0167] User's device: A smartphone or other device that displays the generated discussion and receives feedback.

[0168] software:

[0169] Requests: Communication with external APIs for data collection.

[0170] scikit-learn: Analysis of text data (TF-IDF, topic modeling).

[0171] Flask: A web server that sends and receives data via a RESTful API.

[0172] Data collection and reliability assessment

[0173] The server collects data from reliable sources (e.g., government agencies, public institution announcements, academic papers, etc.) through APIs. This collected data is then cross-referenced to evaluate the reliability of each piece of information. Unreliable data is then eliminated.

[0174] Natural Language Processing

[0175] The server performs TF-IDF vectorization and topic modeling (such as LDA) on the collected text data to extract important information and major topics, allowing users to accurately obtain the information they need from a vast amount of data.

[0176] Generating discussions

[0177] Based on the analysis results, multifaceted discussions are generated that integrate different perspectives and opinions. The generated discussions are intended to include fair and multifaceted views. For example, a "discussion on COVID-19" could include a wide range of topics, such as opinions on the effectiveness of vaccines, views on government countermeasures, and the impact on the economy.

[0178] Sending to user terminal and displaying

[0179] The discussions generated by the server are sent to the user's device in JSON format using a RESTful API, which receives them and presents them to the user in a visual interface.

[0180] Collecting and analyzing feedback

[0181] Users provide feedback on the displayed discussions, which is then sent back to the server. The server analyzes the collected feedback and uses it to improve the system. This cycle allows the system to continuously evolve and become more accurate.

[0182] Examples and prompts

[0183] For example, when generating arguments against climate change, the following prompts might be used:

[0184] plaintext

[0185] Generate a multifaceted and fair discussion of climate change based on official government statements on climate change, recent academic papers, and news articles. Take into account different perspectives, such as the need for renewable energy, ways to reduce greenhouse gas emissions, and the economic impact.

[0186] In this way, the system of the present invention can provide users with multifaceted and fair discussions based on reliable information, thereby solving the problems of filter bubbles and fake news in the modern information environment.

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] Data collection

[0190] The server collects data from reliable sources, such as government APIs, public website data, and academic paper databases. The inputs are API endpoints and website URLs, and the output is the raw data stored in JSON format. This allows the server to secure the original data.

[0191] Step 2:

[0192] Reliability assessment

[0193] The server evaluates the reliability of the collected data, which includes cross-reference checks, specifically verifying the origin of the data and calculating a reliability score. The input is the raw data obtained, and the output is a selection of only reliable data. Data with low reliability is rejected at this stage.

[0194] Step 3:

[0195] Data analysis using natural language processing

[0196] The server applies natural language processing (NLP) algorithms to the highly reliable data. Specifically, it performs keyword extraction using TF-IDF vectorization and topic modeling using LDA. The input is selected, highly reliable data, and the output is the extraction of important keywords and topics. The structure and meaning of the text data are analyzed.

[0197] Step 4:

[0198] Generating discussions

[0199] The server generates multifaceted discussions based on the analysis results. Specifically, it integrates opinions from different perspectives based on the extracted keywords and topics. The input is keywords and topics extracted by the NLP algorithm, and the output is information in the form of a fair and multifaceted discussion. This allows for discussions that take multiple perspectives into account.

[0200] Step 5:

[0201] Send to user terminal

[0202] The server sends the generated discussion to the user's device using a RESTful API. Specifically, the data is encoded in JSON format and sent to the user's device. The input is the generated discussion data, and the output is received by the user's device. The data is encoded and sent.

[0203] Step 6:

[0204] View and receive feedback

[0205] The terminal visually displays the received discussion data, and the user views it. Specifically, the discussion is displayed on the interface, and the user checks its content. At the same time, a feedback function is provided, allowing the user to input their opinions and suggestions for improvement regarding the discussion. Inputs include the discussion data received from the server and user feedback, and outputs include display on the user's interface and transmission of feedback to the server.

[0206] Step 7:

[0207] Analyzing feedback and improving the system

[0208] The server analyzes the feedback received from users to improve the accuracy and functionality of the system. Specifically, it analyzes the content of the feedback using a natural language processing algorithm and extracts areas for improvement in the system. The input is the feedback data received from users, and the output is a system improvement plan. This allows the system to continuously evolve and increase user satisfaction.

[0209] 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.

[0210] The system of the present invention collects data from highly reliable information sources and generates multifaceted and fair discussions based on that data. This system incorporates an emotion engine that recognizes the user's emotions, making it possible to provide appropriate information and feedback processing according to the user's emotions. The system operates in cooperation with three parties: a server, a terminal, and a user.

[0211] Program processing

[0212] 1. Data Collection:

[0213] The server collects data from reliable sources (e.g., official announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[0214] 2. Reliability assessment:

[0215] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[0216] 3. Natural Language Processing Analysis:

[0217] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[0218] 4. Discussion Generation:

[0219] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[0220] 5. User Emotion Recognition:

[0221] The terminal has an emotion engine for recognizing the user's emotions, which analyzes the user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[0222] 6. Submitting and Viewing Discussions:

[0223] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. The device analyzes the received discussion data and displays it in a format that corresponds to the user's emotional state. For example, if the user is under stress, the information is presented in a calmer tone.

[0224] 7. Feedback and optimization:

[0225] Users provide feedback through their devices. The feedback is sent to the server, which records the user's emotional state through an emotion engine. The server uses this feedback information to improve the system and optimize it to provide more appropriate information.

[0226] Specific examples

[0227] Example 1: COVID-19 discussion

[0228] 1. Data Collection:

[0229] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[0230] 2. Reliability assessment:

[0231] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[0232] 3. Natural Language Processing Analysis:

[0233] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0234] 4. Discussion Generation:

[0235] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0236] 5. User Emotion Recognition:

[0237] The device analyzes the user's facial expressions and voice to identify their current emotional state. For example, if the user is feeling anxious, the emotion engine will recognize that emotional state.

[0238] 6. Submitting and Viewing Discussions:

[0239] The server sends the generated discussion in JSON format to the user's device, which visually displays the information according to the user's emotional state and presents it in a steady tone to reduce anxiety.

[0240] 7. Feedback and optimization:

[0241] Users provide feedback after viewing a discussion, and their emotional state is recorded. This information is sent to the server to continuously improve the system.

[0242] The present invention, which combines an emotion engine, allows users to obtain not only multifaceted and highly reliable information, but also information that is adapted to their own emotional state, thereby improving information literacy and reducing stress.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and web scraping technology to collect corporate press releases and articles from major news sites, allowing information to be gathered from multiple sources.

[0246] Step 2:

[0247] The server evaluates the reliability of the collected data by cross-referencing the data's origins and calculating a reliability score. By checking for matches from multiple sources, it eliminates data that may be erroneous and leaves only reliable information.

[0248] Step 3:

[0249] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract important terms, and sentiment analysis (e.g., VADER) to evaluate the emotional tone of the text, resulting in a detailed analysis of the text's content.

[0250] Step 4:

[0251] The server generates multifaceted discussions based on the analysis results. Specifically, it extracts important viewpoints and opinions from the analyzed data in a balanced manner, creating information in the form of a multifaceted discussion with a fair perspective. In doing so, it appropriately integrates positive, negative, and neutral views.

[0252] Step 5:

[0253] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. This allows the user to quickly access the information they need.

[0254] Step 6:

[0255] The device recognizes the user's emotions. It uses an emotion engine to analyze the user's facial expressions, voice, input data, etc. to identify the user's current emotional state. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice to estimate the user's emotional state.

[0256] Step 7:

[0257] The device analyzes the received discussion data and displays it in a way that reflects the user's emotional state. For example, if the user is under stress, the device will adjust the tone of the information provided to them to be calmer. The visual interface is also designed with the user's emotional state in mind.

[0258] Step 8:

[0259] Users can check the discussion content through the terminal and provide feedback as needed. The feedback includes a field where users can input their impressions of the discussion content, and the terminal collects this information.

[0260] Step 9:

[0261] The device analyzes the user's feedback through an emotion engine and sends it to the server, which then optimizes the system based on the feedback information and the user's emotional state, improving the discussion generation algorithm and data collection process.

[0262] Specific examples

[0263] COVID-19 debate

[0264] Step 1:

[0265] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites through API requests and web scraping.

[0266] Step 2:

[0267] The server evaluates the reliability of the collected data through cross-referencing and selects the most reliable data.

[0268] Step 3:

[0269] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0270] Step 4:

[0271] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0272] Step 5:

[0273] The server sends the generated discussion in JSON format to the user's device.

[0274] Step 6:

[0275] The device uses a camera and microphone to analyze the user's facial expressions and voice and recognize the user's emotional state.

[0276] Step 7:

[0277] The device adjusts the content of the discussion displayed in the user interface depending on the user's emotional state, for example, presenting information in a more reassuring tone if the user is feeling anxious.

[0278] Step 8:

[0279] Users can check the content of the discussion through the terminal and input their feedback, including their feelings.

[0280] Step 9:

[0281] The device analyzes the collected feedback using an emotion engine and sends it to a server, which uses this information to improve its data collection process and discussion generation algorithms.

[0282] This process allows users to obtain multifaceted and reliable information, and provides information that is adapted to each individual's emotional state.

[0283] Example 2

[0284] 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."

[0285] In modern society, it is extremely important to efficiently and fairly collect reliable information and generate multifaceted discussions. However, the mixing of unreliable information and the lack of information provision that is tailored to user sentiment make it difficult to form accurate and balanced discussions. Furthermore, there is a lack of means to effectively incorporate user feedback and continuously optimize the system. As a result, issues arise such as a decline in the reliability of information and user satisfaction.

[0286] 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.

[0287] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to the user's terminal, means for recognizing the user's emotions, means for displaying information in a form corresponding to the user's emotional state, and means for collecting user feedback and optimizing the system, thereby enabling reliable information collection, fair and multifaceted discussion generation, information provision adapted to the user's emotions, and continuous system optimization.

[0288] A "reliable source" refers to an information provider that is highly objective and accurate, and whose data credibility is guaranteed, such as official announcements from public institutions, academic papers, and official corporate opinions.

[0289] "Means for assessing reliability" refers to methods for analyzing the origins and meta-information of collected data and determining the reliability of the data through cross-referencing and reliability scoring.

[0290] "Natural language processing algorithms" are computational algorithms used to analyze collected text data, and include techniques such as topic modeling, keyword extraction, and sentiment analysis.

[0291] "Means for generating discussion" refers to methods for extracting important perspectives and opinions from the analyzed data and integrating them to create information in the form of a fair and multifaceted discussion.

[0292] "Means for recognizing user emotions" refers to technology that analyzes the user's facial expressions, voice, and input data to determine the user's current emotional state.

[0293] "Means for displaying information" refers to technology for displaying generated discussion information on a user's terminal, and includes techniques that incorporate display methods that correspond to the user's emotional state.

[0294] "Means for collecting feedback and optimizing the system" refers to methods for collecting feedback and emotional state data provided by users and using that data to improve the performance of the system and the quality of information provided.

[0295] "Generative AI models" refer to advanced artificial intelligence algorithms used to perform tasks such as natural language generation and argument generation.

[0296] A "prompt" is text data input into a generative AI model, and refers to instructions that allow the AI ​​to generate an appropriate response according to a specific format and content.

[0297] The system of the present invention operates in cooperation with three parties: the user, the terminal, and the server. The system's main function is to collect data from reliable sources and generate multifaceted and fair discussions based on that data. Furthermore, it is capable of recognizing the user's emotions and providing appropriate information and feedback.

[0298] Hardware and software used

[0299] 1. Server:

[0300] Hardware: A server machine with a high-performance CPU and sufficient memory

[0301] Software: Python programs and libraries (Beautiful Soup, Scrapy, Gensim, NLTK, VADER, etc.), RESTful API servers (e.g., Flask and Django), reliability assessment algorithms, generative AI models

[0302] 2. Terminal:

[0303] Hardware: The PC or smartphone used by the user

[0304] Software: Emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API), JavaScript program running in the browser, screen display using HTML and CSS

[0305] 3. User:

[0306] Interface: User feedback form, camera, microphone

[0307] Specific explanation of data processing and data calculation

[0308] Server Action:

[0309] The server first collects data from reliable sources. For example, it uses official APIs from public institutions to obtain the latest statistical information. It also uses web scraping tools to extract academic papers and news articles, and uses RSS feeds to obtain updates from major news sites. It then evaluates the reliability of the collected data, cross-referencing and scoring it.

[0310] Next, the data is analyzed using natural language processing algorithms. Specifically, the Gensim library is used for topic modeling, and NLTK is used for keyword extraction. For sentiment analysis, VADER is used to evaluate the emotional tone of the text. Based on these analysis results, a generative AI model is used to generate fair and multifaceted discussions. For example, it combines positive opinions such as "Infections are likely to decrease as vaccinations progress" with neutral opinions such as "Fair distribution is necessary for countries with low vaccination rates."

[0311] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API.

[0312] Terminal handling:

[0313] The device uses JavaScript to parse the received JSON-formatted discussion data and displays it visually using HTML and CSS. The device also uses an emotion engine to recognize the user's emotions. It captures the user's facial expressions using a camera and performs facial emotion analysis using OpenCV. For example, if the user frowns, it recognizes the user as anxious. It also collects audio data through the microphone and analyzes it with the Google Cloud Speech-to-Text API to evaluate the tone and tempo of the voice. Based on this information, it changes the display method depending on the user's emotional state. For example, if the user is stressed, it presents information using a blue background and soft font.

[0314] User role:

[0315] Users can view the displayed discussions and provide feedback, which is then sent back to the server, where the emotion engine records the user's emotional state. The server uses this feedback data to improve the system's performance and the quality of information provided.

[0316] Specific examples

[0317] Example 1: COVID-19 discussion:

[0318] The server collects official announcements from public institutions, related academic papers, and press conference articles from major news sites. It cross-references the reliability of the collected data and selects only the most up-to-date and reliable information. The server uses natural language processing algorithms to perform topic modeling, keyword extraction, and sentiment analysis to generate multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[0319] The server sends the generated discussion in JSON format to the user's device, which then visually displays the information according to the user's emotional state and presents it in a calm tone to reduce anxiety. For example, if the user is stressed, a blue background and soft font are used.

[0320] Example prompt sentence:

[0321] "Collect the latest, reliable information on COVID-19 and generate multifaceted discussions. If users are feeling anxious, focus on providing information in a calm tone."

[0322] This system allows users to improve their information literacy by viewing reliable and multifaceted discussions, and also reduces stress by providing information adapted to their emotional state.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1:

[0325] The server collects data from reliable sources.

[0326] Input: Official APIs from public institutions, databases of academic papers, RSS feeds from major news sites

[0327] Data processing: Send API requests and extract the required information using a web scraping tool (such as Beautiful Soup or Scrapy).

[0328] Output: Raw collected data (e.g., latest case counts, text of academic papers, news articles)

[0329] Step 2:

[0330] The server evaluates the reliability of the collected data.

[0331] Input: Raw data collected

[0332] Data calculation: Perform cross-referencing and analyze meta-information such as data source, author, publication date, etc. Calculate reliability scores and filter out data with low scores.

[0333] Output: Highly reliable data (data with a reliability score of 50 or higher)

[0334] Step 3:

[0335] The server analyzes the data with high reliability using natural language processing algorithms.

[0336] Input: Reliable data

[0337] Data Computation: We use the Gensim library for topic modeling to extract major themes, NLTK for keyword extraction, and VADER for sentiment analysis to assess the emotional tone of the text.

[0338] Output: Analysis information (extracted topics, keywords, emotional tone)

[0339] Step 4:

[0340] The server generates a discussion based on the analysis results.

[0341] Input: Analysis information

[0342] Data Computation: Using generative AI models (e.g., GPT-3), we generate fair and multifaceted arguments from the analysis results, generating text that integrates positive, negative, and neutral views.

[0343] Output: Generated discussion (text data in sentence format)

[0344] Step 5:

[0345] The server transmits the generated discussion to the user's terminal.

[0346] Input: Generated arguments

[0347] Data processing: The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API.

[0348] Output: JSON formatted discussion data

[0349] Step 6:

[0350] The terminal visually displays the received discussion data.

[0351] Input: JSON format discussion data

[0352] Data Calculation: Parse the data using JavaScript and display it visually using HTML and CSS, adjusting font size, color, and layout depending on the user's emotional state.

[0353] Output: A visual representation of the argument (information presented to the user)

[0354] Step 7:

[0355] The terminal uses an emotion engine to recognize the user's emotions.

[0356] Input: User's facial expression (via camera), voice data (via microphone)

[0357] Data calculation: Analyze facial expressions with OpenCV and voice with Google Cloud Speech-to-Text API to determine the user's emotional state.

[0358] Output: User's emotional state (e.g., anxiety, stress)

[0359] Step 8:

[0360] The user provides feedback through the terminal.

[0361] Input: User feedback (text input)

[0362] Data processing: Collected feedback and emotional states are stored and sent to the server.

[0363] Output: Stored feedback data

[0364] Step 9:

[0365] The server optimizes the system based on the feedback information.

[0366] Input: User feedback data

[0367] Data computation: Using machine learning algorithms to analyze feedback and identify areas for system improvement.

[0368] Output: Improved system parameters (improving the quality of information provided next time)

[0369] (Application example 2)

[0370] 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."

[0371] While conventional systems can provide information from reliable sources, they do not take into account the provision of information or feedback according to the user's emotional state. As a result, users do not receive the information they need appropriately, making it difficult to increase satisfaction. In particular, inappropriate information may be provided to users who are feeling stressed or anxious, so there is a need to improve the user experience. To address this issue, it is necessary not only to provide reliable information, but also to adjust the content of the information according to the user's emotional state.

[0372] 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.

[0373] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to a user's terminal, means for displaying the generated discussions on the user's terminal, means for recognizing the user's emotions, means for recommending products and services based on the user's emotional state, and means for adjusting display information according to the emotional state. This not only allows the user to obtain reliable information, but also enables the provision of information adapted to the user's emotional state, thereby improving the user experience.

[0374] A "reliable source" generally refers to a place that provides accurate and trustworthy information, such as official announcements from public institutions, academic papers, and official corporate positions.

[0375] "Data collection methods" refers to technologies for obtaining information from online databases through API requests, or for collecting necessary information from the Internet using web scraping, etc.

[0376] "Reliability assessment method" refers to a technology that cross-references the source of collected data and calculates its reliability score to eliminate unreliable data.

[0377] "Natural language processing algorithm" refers to a technology that uses techniques such as topic modeling, keyword extraction, and sentiment analysis to analyze the structure and meaning of text data and extract important information.

[0378] "Discussion generation means" refers to technology that extracts a balanced mix of positive, negative, and neutral views from data analyzed using natural language processing, creating multifaceted discussions from a fair perspective.

[0379] "Transmission means" refers to the technology that encodes the generated discussion information in JSON format and transmits the data to the user's device using a RESTful API.

[0380] "Display means" refers to technology that analyzes the discussion data received by the user's terminal and visually presents the information in a format that is easy for the user to understand.

[0381] "Emotion recognition means" refers to technology that analyzes a user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[0382] "Recommendation means" refers to technology that selects appropriate products and services based on the user's emotional state and suggests them to the user.

[0383] "Information adjustment means" refers to technology that adjusts the tone and content of information according to the user's emotional state, providing information to the user in a more appropriate form.

[0384] System Overview

[0385] The system for implementing this invention collects data from reliable information sources, analyzes that data, and generates multifaceted discussions. It can also recognize the user's emotions and provide information and recommend products according to their emotional state. This system is primarily composed of three elements: a server, a terminal, and a user.

[0386] Hardware and software used

[0387] Hardware:

[0388] Camera: Used to recognize the user's facial expressions

[0389] High-performance PC: Used for image analysis and data analysis

[0390] Smartphone or tablet: Used to display information to the user

[0391] software:

[0392] facial_recognition: A library for analyzing customer facial expressions

[0393] sentiment_analysis: A library for analyzing the emotional tone of collected data

[0394] requests: A library for sending HTTP requests to retrieve data from an API.

[0395] Natural language processing algorithms: used to analyze collected data and extract key information (e.g., topic modeling, keyword extraction, sentiment analysis)

[0396] Detailed explanation of the process

[0397] 1. Data Collection:

[0398] The server collects data from reliable sources, such as official announcements from public institutions, academic papers, and official company statements, using API requests and web scraping techniques.

[0399] 2. Reliability assessment:

[0400] The server evaluates the reliability of the collected data through cross-referencing and calculates a reliability score, at which point unreliable data is eliminated.

[0401] 3. Natural Language Processing Analysis:

[0402] The server analyzes the data using natural language processing algorithms to extract key information through topic modeling, keyword extraction, and sentiment analysis.

[0403] 4. Discussion Generation:

[0404] The server generates multifaceted discussions based on the analysis results, providing fair information by integrating positive, negative, and neutral viewpoints in a balanced manner.

[0405] 5. Submitting and Viewing Discussions:

[0406] The server sends the generated discussion to the user's device, which analyzes the received discussion and visually displays it. The display content is adjusted according to the user's emotional state.

[0407] 6. Emotion recognition:

[0408] The device recognizes emotions by analyzing the user's facial expressions, voice, and input data, thereby identifying the user's current emotional state.

[0409] 7. Recommendations based on emotional state:

[0410] The device will recommend appropriate products and services based on the user's emotional state, for example, if the user is under stress, it will suggest products that have a relaxing effect.

[0411] Specific example explanation

[0412] For example, if a customer enters a store and the emotion recognition engine detects that the customer looks a little tired, the emotion score will be found to be 0.2 or less, and based on that result, the following prompt sentence can be input into the generative AI model:

[0413] Example prompt sentence:

[0414] Please provide a list of relaxation products. I would like to suggest products that will help my customers if they are tired.

[0415] This system not only provides users with multifaceted discussions based on reliable data, but also allows them to receive information and product recommendations that are suited to their emotional state, thereby improving the user experience.

[0416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0417] Step 1:

[0418] The server collects data from reliable sources. Specifically, the server sends API requests or uses web scraping technology to obtain the necessary information from official announcements from public institutions, academic papers, official corporate statements, etc. This allows reliable data to be input into the server.

[0419] Step 2:

[0420] The server evaluates the reliability of the collected data. Specifically, it cross-references the origin of the collected data and calculates a reliability score to eliminate data with low reliability. This process outputs data that is evaluated as highly reliable.

[0421] Step 3:

[0422] The server applies natural language processing (NLP) algorithms to the data that has been evaluated as highly reliable. Specifically, it performs topic modeling, keyword extraction, and sentiment analysis to extract important information from the text data. This generates analyzed data that is output to the server.

[0423] Step 4:

[0424] The server generates a multifaceted discussion based on the analysis results. Specifically, it extracts a balanced mix of positive, negative, and neutral views, creating a multifaceted discussion from a fair perspective. The generated discussion is then output from the server.

[0425] Step 5:

[0426] The server sends the generated discussion to the user's device. Specifically, it encodes the generated discussion information in JSON format and sends the data to the user's device using a RESTful API. This transfers the discussion data from the server to the device.

[0427] Step 6:

[0428] The terminal analyzes the received discussion data and displays it to the user. Specifically, the analyzed discussion data is visually displayed and presented in a format that is easy for the user to understand, allowing the user to access the discussion information.

[0429] Step 7:

[0430] The device recognizes the user's emotions. Specifically, it analyzes the user's facial expressions, voice, and input data to identify the user's current emotional state. This information is then output to the device.

[0431] Step 8:

[0432] The device recommends products and services based on the user's emotional state. Specifically, it selects appropriate products and services according to the user's emotional state and proposes them to the user. This provides the user with optimal recommendation information.

[0433] Step 9:

[0434] The device adjusts the displayed information according to the user's emotional state, for example, presenting information in a calmer tone to a user who is under stress, thereby improving the user experience.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Second embodiment]

[0439] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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."

[0451] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[0452] Program processing

[0453] 1. Data Collection:

[0454] The server collects data from reliable sources (e.g., announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[0455] 2. Reliability assessment:

[0456] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[0457] 3. Natural Language Processing Analysis:

[0458] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[0459] 4. Discussion Generation:

[0460] The server generates a multifaceted discussion based on the analysis results, a process that balances and integrates different viewpoints and opinions, and compiles them into a discussion-style information format that contains fair and multifaceted views.

[0461] 5. Send to user device:

[0462] The server encodes the generated discussion and sends it to the user's device using a RESTful API, with the data sent in JSON format.

[0463] 6. Display and Feedback:

[0464] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The user can check the content of the discussion through this interface and provide feedback as needed. The feedback is sent to the server and used to improve the system.

[0465] Specific examples

[0466] Example 1: COVID-19 discussion

[0467] 1. Data Collection:

[0468] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[0469] 2. Reliability assessment:

[0470] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[0471] 3. Natural Language Processing Analysis:

[0472] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0473] 4. Discussion Generation:

[0474] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0475] 5. Send to user device:

[0476] The server sends the generated discussion in JSON format to the user's device.

[0477] 6. Display and Feedback:

[0478] The user's terminal visually displays the received discussion data, which the user can view in detail. Through the feedback function, the user can contribute to improving the system.

[0479] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[0480] The processing flow will be explained below.

[0481] Step 1:

[0482] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and corporate press releases and articles from major news sites using web scraping technology.

[0483] Step 2:

[0484] The server evaluates the reliability of the collected data. First, it cross-references the source of the data and calculates a reliability score. Information with a low reliability score is rejected at this point.

[0485] Step 3:

[0486] The server analyzes the collected data using natural language processing (NLP) algorithms: topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract key terms, and sentiment analysis (e.g., VADER) to assess emotional tone.

[0487] Step 4:

[0488] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[0489] Step 5:

[0490] The server sends the generated discussion to the user's device. The server encodes the generated discussion information in JSON format and sends it to the user's device using a RESTful API.

[0491] Step 6:

[0492] The user's device analyzes the received discussion data and visually displays it, allowing the user to check the details of the discussion through the interface.

[0493] Step 7:

[0494] Users provide feedback through their devices, which is sent to the server and used to improve the system and its accuracy.

[0495] Through this series of steps, we are able to collect data from reliable sources and provide users with a multifaceted and fair discussion.

[0496] Example 1

[0497] 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."

[0498] In today's information environment, problems such as filter bubbles and fake news are becoming more serious, making it difficult for users to obtain reliable information. It is also difficult to integrate different perspectives from the vast amount of information and generate fair and multifaceted discussions. To solve this problem, a system is needed that can collect reliable data, analyze that data, and generate multifaceted discussions.

[0499] 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.

[0500] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data by cross-referencing, means for analyzing the collected data using a natural language processing algorithm, means for generating a discussion by integrating opinions and views from different perspectives based on the analysis results, means for constructing a multifaceted discussion in natural sentences using a generative AI model, means for transmitting the generated discussion to a user's terminal, and means for displaying the received discussion on the user's terminal and collecting feedback from the user. This makes it possible to provide reliable, multifaceted information and enable users to access fair, multifaceted discussions.

[0501] A "reliable source" is a source that provides accurate and trustworthy data, such as announcements from public institutions, academic papers, and official corporate statements.

[0502] "Means of collecting data" refers to methods of obtaining the necessary information using API requests or web scraping technology.

[0503] "Cross-reference reliability assessment method" is a method for verifying the reliability of collected data by cross-referencing it from multiple sources and calculating a reliability score.

[0504] A "natural language processing algorithm" is a technology that analyzes collected text data, specifically performing topic modeling, keyword extraction, sentiment analysis, etc.

[0505] "Means for generating discussion by integrating opinions and views from different perspectives" refers to a method for generating discussion that incorporates a variety of perspectives and opinions in a balanced manner based on the results of analysis.

[0506] A "generative AI model" is an artificial intelligence technology that generates natural-looking sentences based on given data.

[0507] "Means for sending to the user's device" refers to a method for encoding the generated discussion and sending the data to the user's device via the Internet using a RESTful API.

[0508] "Means for displaying discussions received on the user's terminal and collecting feedback from the user" is a function that displays received discussion data on an interface and allows the user to provide feedback.

[0509] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[0510] System configuration

[0511] The system includes the following main components:

[0512] 1. Server: Responsible for data collection, credibility assessment, natural language processing, argument generation, and data transmission.

[0513] 2. User's terminal: Responsible for displaying generated discussions and collecting user feedback.

[0514] 3. Communication interface: Used to send and receive data between the server and the user's terminal.

[0515] Hardware and software used

[0516] server:

[0517] Hardware: A server machine with a powerful processor and plenty of memory.

[0518] Software: Python for data collection and libraries for performing API requests and web scraping (e.g., BeautifulSoup). NLTK and spaCy for natural language processing. Generative AI models such as GPT-3 are used.

[0519] On the user's device:

[0520] Hardware: PCs, tablets, smartphones, etc.

[0521] Software: Web browser and JavaScript interface.

[0522] Operation details

[0523] Data collection

[0524] The server retrieves data by sending API requests from reliable sources. For example, it retrieves the latest statistical data on COVID-19 from government health agency APIs. It also uses web scraping techniques to gather relevant articles from major news sites. This data collection process is performed periodically to ensure the information is always up to date.

[0525] Reliability evaluation

[0526] The server cross-references the reliability of the collected data, comparing data from multiple reliable sources and assigning a high reliability score to matching information. This evaluation process filters out information with low reliability.

[0527] Natural Language Processing

[0528] The server uses natural language processing algorithms on the collected data, including tokenizing the text using the NLTK library, modeling topics using LDA (Latent Dirichlet Allocation), extracting keywords using TF-IDF (Term Frequency-Inverse Document Frequency), and performing sentiment analysis using VADER (Valence Aware Dictionary for Sentiment Reasoning).

[0529] discussion generation

[0530] The server generates multifaceted discussions based on the analysis results. For example, it uses a generative AI model to construct natural-sounding sentences that combine multiple perspectives, such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[0531] Data transmission and display

[0532] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API. The user's device analyzes the received discussion data and displays it visually on the interface. The user can view the displayed discussions and provide feedback. The feedback is sent to the server and used to improve the system.

[0533] Specific examples

[0534] COVID-19 debate

[0535] 1. Data Collection:

[0536] The server collects official announcements from government health agencies, related academic papers, and press conference reports from major news sites.

[0537] 2. Reliability assessment:

[0538] The server cross-references the reliability of the collected data and selects only the most reliable information.

[0539] 3. Natural Language Processing:

[0540] The server performs sentiment analysis, topic modeling and keyword extraction.

[0541] 4. Discussion generation:

[0542] The server generates multifaceted discussions, including "medical opinions on the effectiveness of vaccines," "opinions on the government's lockdown policy," and "impact on the economy."

[0543] 5. Data transmission and display:

[0544] The server sends the generated discussion in JSON format to the user's device, where the user can view it in an interface.

[0545] Prompt Sentence Examples

[0546] Please generate a well-rounded and fair discussion on the following points regarding COVID-19:

[0547] 1. Medical opinion on vaccine effectiveness

[0548] 2. Opinions on the government's lockdown policy

[0549] 3. Economic impact

[0550] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[0551] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0552] Step 1: Collect data

[0553] The server collects data from reliable sources. It uses URLs and API endpoint information, such as public announcements, academic papers, and official corporate statements, as input. Specifically, the server generates an API request, calling, for example, "https: / / api.example.gov / covid19 / latest." It also uses a Python library for web scraping (e.g., BeautifulSoup) to parse articles from news sites. The output is the collected text data or JSON-formatted data.

[0554] Step 2: Assess reliability

[0555] The server evaluates the reliability of the collected data through cross-referencing. It uses the data collected in step 1 as input. The server compares the URLs and publication dates of the collected data sources and calculates a reliability score. Specifically, the server verifies the origin of each data point and assigns a high score to matching information. The output is a dataset with a reliability assessment and an attached score.

[0556] Step 3: Natural Language Processing Analysis

[0557] The server analyzes the data whose trustworthiness has been evaluated using a natural language processing algorithm. The data whose trustworthiness has been evaluated in step 2 is used as input. The server tokenizes the text using the NLTK library and models topics using LDA (Latent Dirichlet Allocation). Keywords are extracted using TF-IDF (Term Frequency-Inverse Document Frequency), and sentiment analysis is performed using VADER (Valence Aware Dictionary for Sentiment Reasoning). The output is a topic model, important keywords, and sentiment scores as the analysis results.

[0558] Step 4: Generate discussion

[0559] The server generates a multifaceted discussion based on the analysis results. The topic model, keywords, and sentiment scores obtained in step 3 are used as input. The server uses a generative AI model to integrate opinions and views from different perspectives and construct a fair, multifaceted discussion in natural-sounding sentences. Specifically, based on the given prompt, it generates a multifaceted discussion, such as "medical opinion on the effectiveness of vaccines," "opinions on government lockdown policies," and "impact on the economy." The output is text data of the generated discussion.

[0560] Step 5: Send to user device

[0561] The server encodes the generated discussion and sends it to the user's device via a RESTful API. The text data of the discussion generated in step 4 is used as input. The server implements the RESTful API using Python's Flask or similar and sends JSON-formatted data to the endpoint " / sendDiscussion" via a POST request. The output is the discussion data sent to the user's device.

[0562] Step 6: Display and feedback

[0563] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The discussion data sent in step 5 is used as input. The user's device parses the JSON data using JavaScript and displays it visually on a web page. Specifically, a section is created for each discussion point on the interface and text is displayed. The user can view this in detail and enter their opinion through a feedback form. The feedback is sent to the server and used to improve the system. The output is the feedback data from the user.

[0564] (Application example 1)

[0565] 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."

[0566] In today's information environment, unreliable information and fake news are rampant, making it difficult for users to obtain accurate and fair information. This problem increases the risk of making incorrect decisions based on false information. It also makes it difficult to integrate opinions and views from different perspectives in a balanced manner. Furthermore, there is a lack of means to effectively utilize user feedback and improve the accuracy of the system.

[0567] 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.

[0568] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to users' terminals, means for displaying the generated discussions on the users' terminals and receiving feedback, and means for analyzing user feedback and using it to improve the system. This allows for the provision of multifaceted and fair discussions based on reliable information, enabling users to make decisions based on accurate and balanced information. Furthermore, by effectively utilizing user feedback, the accuracy of the system can be continuously improved.

[0569] A "reliable source" is a source whose accuracy and reliability are guaranteed, such as announcements from public institutions, academic papers, and official corporate opinions.

[0570] "Methods for assessing data reliability" refers to the process of cross-referencing the origins of collected data and calculating a reliability score.

[0571] "Means of analyzing data" refers to techniques that use natural language processing algorithms to analyze the structure and meaning of text and extract key information.

[0572] "Means of generating discussion" refers to the process of integrating different perspectives and opinions in a balanced manner based on the results of analysis, and compiling information in a discussion format that includes fair and multifaceted views.

[0573] "Means for sending to the user's device" refers to the process of encoding the generated discussion and sending the data to the user's device using a RESTful API.

[0574] "Means for displaying discussions generated on the user's terminal" refers to a mechanism for analyzing received discussion data and displaying it on an interface that can be viewed by the user.

[0575] "Means for receiving feedback" refers to the process of collecting opinions and suggestions for improvement provided by users and using them to improve the system.

[0576] "Means for analyzing user feedback and using it to improve the system" refers to a method for analyzing collected feedback and improving the functionality and accuracy of the system.

[0577] The system for implementing this invention collects data from reliable information sources and uses that data to generate multifaceted and fair discussions. This system operates in cooperation with three parties: a server, terminals, and users.

[0578] System configuration

[0579] Hardware:

[0580] Server: Responsible for data collection, reliability assessment, natural language processing, and discussion generation.

[0581] User's device: A smartphone or other device that displays the generated discussion and receives feedback.

[0582] software:

[0583] Requests: Communication with external APIs for data collection.

[0584] scikit-learn: Analysis of text data (TF-IDF, topic modeling).

[0585] Flask: A web server that sends and receives data via a RESTful API.

[0586] Data collection and reliability assessment

[0587] The server collects data from reliable sources (e.g., government agencies, public institution announcements, academic papers, etc.) through APIs. This collected data is then cross-referenced to evaluate the reliability of each piece of information. Unreliable data is then eliminated.

[0588] Natural Language Processing

[0589] The server performs TF-IDF vectorization and topic modeling (such as LDA) on the collected text data to extract important information and major topics, allowing users to accurately obtain the information they need from a vast amount of data.

[0590] Generating discussions

[0591] Based on the analysis results, multifaceted discussions are generated that integrate different perspectives and opinions. The generated discussions are intended to include fair and multifaceted views. For example, a "discussion on COVID-19" could include a wide range of topics, such as opinions on the effectiveness of vaccines, views on government countermeasures, and the impact on the economy.

[0592] Sending to user terminal and displaying

[0593] The discussions generated by the server are sent to the user's device in JSON format using a RESTful API, which receives them and presents them to the user in a visual interface.

[0594] Collecting and analyzing feedback

[0595] Users provide feedback on the displayed discussions, which is then sent back to the server. The server analyzes the collected feedback and uses it to improve the system. This cycle allows the system to continuously evolve and become more accurate.

[0596] Examples and prompts

[0597] For example, when generating arguments against climate change, the following prompts might be used:

[0598] plaintext

[0599] Generate a multifaceted and fair discussion of climate change based on official government statements on climate change, recent academic papers, and news articles. Take into account different perspectives, such as the need for renewable energy, ways to reduce greenhouse gas emissions, and the economic impact.

[0600] In this way, the system of the present invention can provide users with multifaceted and fair discussions based on reliable information, thereby solving the problems of filter bubbles and fake news in the modern information environment.

[0601] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0602] Step 1:

[0603] Data collection

[0604] The server collects data from reliable sources, such as government APIs, public website data, and academic paper databases. The inputs are API endpoints and website URLs, and the output is the raw data stored in JSON format. This allows the server to secure the original data.

[0605] Step 2:

[0606] Reliability assessment

[0607] The server evaluates the reliability of the collected data, which includes cross-reference checks, specifically verifying the origin of the data and calculating a reliability score. The input is the raw data obtained, and the output is a selection of only reliable data. Data with low reliability is rejected at this stage.

[0608] Step 3:

[0609] Data analysis using natural language processing

[0610] The server applies natural language processing (NLP) algorithms to the highly reliable data. Specifically, it performs keyword extraction using TF-IDF vectorization and topic modeling using LDA. The input is selected, highly reliable data, and the output is the extraction of important keywords and topics. The structure and meaning of the text data are analyzed.

[0611] Step 4:

[0612] Generating discussions

[0613] The server generates multifaceted discussions based on the analysis results. Specifically, it integrates opinions from different perspectives based on the extracted keywords and topics. The input is keywords and topics extracted by the NLP algorithm, and the output is information in the form of a fair and multifaceted discussion. This allows for discussions that take multiple perspectives into account.

[0614] Step 5:

[0615] Send to user terminal

[0616] The server sends the generated discussion to the user's device using a RESTful API. Specifically, the data is encoded in JSON format and sent to the user's device. The input is the generated discussion data, and the output is received by the user's device. The data is encoded and sent.

[0617] Step 6:

[0618] View and receive feedback

[0619] The terminal visually displays the received discussion data, and the user views it. Specifically, the discussion is displayed on the interface, and the user checks its content. At the same time, a feedback function is provided, allowing the user to input their opinions and suggestions for improvement regarding the discussion. Inputs include the discussion data received from the server and user feedback, and outputs include display on the user's interface and transmission of feedback to the server.

[0620] Step 7:

[0621] Analyzing feedback and improving the system

[0622] The server analyzes the feedback received from users to improve the accuracy and functionality of the system. Specifically, it analyzes the content of the feedback using a natural language processing algorithm and extracts areas for improvement in the system. The input is the feedback data received from users, and the output is a system improvement plan. This allows the system to continuously evolve and increase user satisfaction.

[0623] 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.

[0624] The system of the present invention collects data from highly reliable information sources and generates multifaceted and fair discussions based on that data. This system incorporates an emotion engine that recognizes the user's emotions, making it possible to provide appropriate information and feedback processing according to the user's emotions. The system operates in cooperation with three parties: a server, a terminal, and a user.

[0625] Program processing

[0626] 1. Data Collection:

[0627] The server collects data from reliable sources (e.g., official announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[0628] 2. Reliability assessment:

[0629] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[0630] 3. Natural Language Processing Analysis:

[0631] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[0632] 4. Discussion Generation:

[0633] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[0634] 5. User Emotion Recognition:

[0635] The terminal has an emotion engine for recognizing the user's emotions, which analyzes the user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[0636] 6. Submitting and Viewing Discussions:

[0637] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. The device analyzes the received discussion data and displays it in a format that corresponds to the user's emotional state. For example, if the user is under stress, the information is presented in a calmer tone.

[0638] 7. Feedback and optimization:

[0639] Users provide feedback through their devices. The feedback is sent to the server, which records the user's emotional state through an emotion engine. The server uses this feedback information to improve the system and optimize it to provide more appropriate information.

[0640] Specific examples

[0641] Example 1: COVID-19 discussion

[0642] 1. Data Collection:

[0643] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[0644] 2. Reliability assessment:

[0645] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[0646] 3. Natural Language Processing Analysis:

[0647] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0648] 4. Discussion Generation:

[0649] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0650] 5. User Emotion Recognition:

[0651] The device analyzes the user's facial expressions and voice to identify their current emotional state. For example, if the user is feeling anxious, the emotion engine will recognize that emotional state.

[0652] 6. Submitting and Viewing Discussions:

[0653] The server sends the generated discussion in JSON format to the user's device, which visually displays the information according to the user's emotional state and presents it in a steady tone to reduce anxiety.

[0654] 7. Feedback and optimization:

[0655] Users provide feedback after viewing a discussion, and their emotional state is recorded. This information is sent to the server to continuously improve the system.

[0656] The present invention, which combines an emotion engine, allows users to obtain not only multifaceted and highly reliable information, but also information that is adapted to their own emotional state, thereby improving information literacy and reducing stress.

[0657] The processing flow will be explained below.

[0658] Step 1:

[0659] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and web scraping technology to collect corporate press releases and articles from major news sites, allowing information to be gathered from multiple sources.

[0660] Step 2:

[0661] The server evaluates the reliability of the collected data by cross-referencing the data's origins and calculating a reliability score. By checking for matches from multiple sources, it eliminates data that may be erroneous and leaves only reliable information.

[0662] Step 3:

[0663] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract important terms, and sentiment analysis (e.g., VADER) to evaluate the emotional tone of the text, resulting in a detailed analysis of the text's content.

[0664] Step 4:

[0665] The server generates multifaceted discussions based on the analysis results. Specifically, it extracts important viewpoints and opinions from the analyzed data in a balanced manner, creating information in the form of a multifaceted discussion with a fair perspective. In doing so, it appropriately integrates positive, negative, and neutral views.

[0666] Step 5:

[0667] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. This allows the user to quickly access the information they need.

[0668] Step 6:

[0669] The device recognizes the user's emotions. It uses an emotion engine to analyze the user's facial expressions, voice, input data, etc. to identify the user's current emotional state. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice to estimate the user's emotional state.

[0670] Step 7:

[0671] The device analyzes the received discussion data and displays it in a way that reflects the user's emotional state. For example, if the user is under stress, the device will adjust the tone of the information provided to them to be calmer. The visual interface is also designed with the user's emotional state in mind.

[0672] Step 8:

[0673] Users can check the discussion content through the terminal and provide feedback as needed. The feedback includes a field where users can input their impressions of the discussion content, and the terminal collects this information.

[0674] Step 9:

[0675] The device analyzes the user's feedback through an emotion engine and sends it to the server, which then optimizes the system based on the feedback information and the user's emotional state, improving the discussion generation algorithm and data collection process.

[0676] Specific examples

[0677] COVID-19 debate

[0678] Step 1:

[0679] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites through API requests and web scraping.

[0680] Step 2:

[0681] The server evaluates the reliability of the collected data through cross-referencing and selects the most reliable data.

[0682] Step 3:

[0683] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0684] Step 4:

[0685] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0686] Step 5:

[0687] The server sends the generated discussion in JSON format to the user's device.

[0688] Step 6:

[0689] The device uses a camera and microphone to analyze the user's facial expressions and voice and recognize the user's emotional state.

[0690] Step 7:

[0691] The device adjusts the content of the discussion displayed in the user interface depending on the user's emotional state, for example, presenting information in a more reassuring tone if the user is feeling anxious.

[0692] Step 8:

[0693] Users can check the content of the discussion through the terminal and input their feedback, including their feelings.

[0694] Step 9:

[0695] The device analyzes the collected feedback using an emotion engine and sends it to a server, which uses this information to improve its data collection process and discussion generation algorithms.

[0696] This process allows users to obtain multifaceted and reliable information, and provides information that is adapted to each individual's emotional state.

[0697] Example 2

[0698] 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."

[0699] In modern society, it is extremely important to efficiently and fairly collect reliable information and generate multifaceted discussions. However, the mixing of unreliable information and the lack of information provision that is tailored to user sentiment make it difficult to form accurate and balanced discussions. Furthermore, there is a lack of means to effectively incorporate user feedback and continuously optimize the system. As a result, issues arise such as a decline in the reliability of information and user satisfaction.

[0700] 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.

[0701] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to the user's terminal, means for recognizing the user's emotions, means for displaying information in a form corresponding to the user's emotional state, and means for collecting user feedback and optimizing the system, thereby enabling reliable information collection, fair and multifaceted discussion generation, information provision adapted to the user's emotions, and continuous system optimization.

[0702] A "reliable source" refers to an information provider that is highly objective and accurate, and whose data credibility is guaranteed, such as official announcements from public institutions, academic papers, and official corporate opinions.

[0703] "Means for assessing reliability" refers to methods for analyzing the origins and meta-information of collected data and determining the reliability of the data through cross-referencing and reliability scoring.

[0704] "Natural language processing algorithms" are computational algorithms used to analyze collected text data, and include techniques such as topic modeling, keyword extraction, and sentiment analysis.

[0705] "Means for generating discussion" refers to methods for extracting important perspectives and opinions from the analyzed data and integrating them to create information in the form of a fair and multifaceted discussion.

[0706] "Means for recognizing user emotions" refers to technology that analyzes the user's facial expressions, voice, and input data to determine the user's current emotional state.

[0707] "Means for displaying information" refers to technology for displaying generated discussion information on a user's terminal, and includes techniques that incorporate display methods that correspond to the user's emotional state.

[0708] "Means for collecting feedback and optimizing the system" refers to methods for collecting feedback and emotional state data provided by users and using that data to improve the performance of the system and the quality of information provided.

[0709] "Generative AI models" refer to advanced artificial intelligence algorithms used to perform tasks such as natural language generation and argument generation.

[0710] A "prompt" is text data input into a generative AI model, and refers to instructions that allow the AI ​​to generate an appropriate response according to a specific format and content.

[0711] The system of the present invention operates in cooperation with three parties: the user, the terminal, and the server. The system's main function is to collect data from reliable sources and generate multifaceted and fair discussions based on that data. Furthermore, it is capable of recognizing the user's emotions and providing appropriate information and feedback.

[0712] Hardware and software used

[0713] 1. Server:

[0714] Hardware: A server machine with a high-performance CPU and sufficient memory

[0715] Software: Python programs and libraries (Beautiful Soup, Scrapy, Gensim, NLTK, VADER, etc.), RESTful API servers (e.g., Flask and Django), reliability assessment algorithms, generative AI models

[0716] 2. Terminal:

[0717] Hardware: The PC or smartphone used by the user

[0718] Software: Emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API), JavaScript program running in the browser, screen display using HTML and CSS

[0719] 3. User:

[0720] Interface: User feedback form, camera, microphone

[0721] Specific explanation of data processing and data calculation

[0722] Server Action:

[0723] The server first collects data from reliable sources. For example, it uses official APIs from public institutions to obtain the latest statistical information. It also uses web scraping tools to extract academic papers and news articles, and uses RSS feeds to obtain updates from major news sites. It then evaluates the reliability of the collected data, cross-referencing and scoring it.

[0724] Next, the data is analyzed using natural language processing algorithms. Specifically, the Gensim library is used for topic modeling, and NLTK is used for keyword extraction. For sentiment analysis, VADER is used to evaluate the emotional tone of the text. Based on these analysis results, a generative AI model is used to generate fair and multifaceted discussions. For example, it combines positive opinions such as "Infections are likely to decrease as vaccinations progress" with neutral opinions such as "Fair distribution is necessary for countries with low vaccination rates."

[0725] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API.

[0726] Terminal handling:

[0727] The device uses JavaScript to parse the received JSON-formatted discussion data and displays it visually using HTML and CSS. The device also uses an emotion engine to recognize the user's emotions. It captures the user's facial expressions using a camera and performs facial emotion analysis using OpenCV. For example, if the user frowns, it recognizes the user as anxious. It also collects audio data through the microphone and analyzes it with the Google Cloud Speech-to-Text API to evaluate the tone and tempo of the voice. Based on this information, it changes the display method depending on the user's emotional state. For example, if the user is stressed, it presents information using a blue background and soft font.

[0728] User role:

[0729] Users can view the displayed discussions and provide feedback, which is then sent back to the server, where the emotion engine records the user's emotional state. The server uses this feedback data to improve the system's performance and the quality of information provided.

[0730] Specific examples

[0731] Example 1: COVID-19 discussion:

[0732] The server collects official announcements from public institutions, related academic papers, and press conference articles from major news sites. It cross-references the reliability of the collected data and selects only the most up-to-date and reliable information. The server uses natural language processing algorithms to perform topic modeling, keyword extraction, and sentiment analysis to generate multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[0733] The server sends the generated discussion in JSON format to the user's device, which then visually displays the information according to the user's emotional state and presents it in a calm tone to reduce anxiety. For example, if the user is stressed, a blue background and soft font are used.

[0734] Example prompt sentence:

[0735] "Collect the latest, reliable information on COVID-19 and generate multifaceted discussions. If users are feeling anxious, focus on providing information in a calm tone."

[0736] This system allows users to improve their information literacy by viewing reliable and multifaceted discussions, and also reduces stress by providing information adapted to their emotional state.

[0737] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0738] Step 1:

[0739] The server collects data from reliable sources.

[0740] Input: Official APIs from public institutions, databases of academic papers, RSS feeds from major news sites

[0741] Data processing: Send API requests and extract the required information using a web scraping tool (such as Beautiful Soup or Scrapy).

[0742] Output: Raw collected data (e.g., latest case counts, text of academic papers, news articles)

[0743] Step 2:

[0744] The server evaluates the reliability of the collected data.

[0745] Input: Raw data collected

[0746] Data calculation: Perform cross-referencing and analyze meta-information such as data source, author, publication date, etc. Calculate reliability scores and filter out data with low scores.

[0747] Output: Highly reliable data (data with a reliability score of 50 or higher)

[0748] Step 3:

[0749] The server analyzes the data with high reliability using natural language processing algorithms.

[0750] Input: Reliable data

[0751] Data Computation: We use the Gensim library for topic modeling to extract major themes, NLTK for keyword extraction, and VADER for sentiment analysis to assess the emotional tone of the text.

[0752] Output: Analysis information (extracted topics, keywords, emotional tone)

[0753] Step 4:

[0754] The server generates a discussion based on the analysis results.

[0755] Input: Analysis information

[0756] Data Computation: Using generative AI models (e.g., GPT-3), we generate fair and multifaceted arguments from the analysis results, generating text that integrates positive, negative, and neutral views.

[0757] Output: Generated discussion (text data in sentence format)

[0758] Step 5:

[0759] The server transmits the generated discussion to the user's terminal.

[0760] Input: Generated arguments

[0761] Data processing: The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API.

[0762] Output: JSON formatted discussion data

[0763] Step 6:

[0764] The terminal visually displays the received discussion data.

[0765] Input: JSON format discussion data

[0766] Data Calculation: Parse the data using JavaScript and display it visually using HTML and CSS, adjusting font size, color, and layout depending on the user's emotional state.

[0767] Output: A visual representation of the argument (information presented to the user)

[0768] Step 7:

[0769] The terminal uses an emotion engine to recognize the user's emotions.

[0770] Input: User's facial expression (via camera), voice data (via microphone)

[0771] Data calculation: Analyze facial expressions with OpenCV and voice with Google Cloud Speech-to-Text API to determine the user's emotional state.

[0772] Output: User's emotional state (e.g., anxiety, stress)

[0773] Step 8:

[0774] The user provides feedback through the terminal.

[0775] Input: User feedback (text input)

[0776] Data processing: Collected feedback and emotional states are stored and sent to the server.

[0777] Output: Stored feedback data

[0778] Step 9:

[0779] The server optimizes the system based on the feedback information.

[0780] Input: User feedback data

[0781] Data computation: Using machine learning algorithms to analyze feedback and identify areas for system improvement.

[0782] Output: Improved system parameters (improving the quality of information provided next time)

[0783] (Application example 2)

[0784] 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."

[0785] While conventional systems can provide information from reliable sources, they do not take into account the provision of information or feedback according to the user's emotional state. As a result, users do not receive the information they need appropriately, making it difficult to increase satisfaction. In particular, inappropriate information may be provided to users who are feeling stressed or anxious, so there is a need to improve the user experience. To address this issue, it is necessary not only to provide reliable information, but also to adjust the content of the information according to the user's emotional state.

[0786] 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.

[0787] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to a user's terminal, means for displaying the generated discussions on the user's terminal, means for recognizing the user's emotions, means for recommending products and services based on the user's emotional state, and means for adjusting display information according to the emotional state. This not only allows the user to obtain reliable information, but also enables the provision of information adapted to the user's emotional state, thereby improving the user experience.

[0788] A "reliable source" generally refers to a place that provides accurate and trustworthy information, such as official announcements from public institutions, academic papers, and official corporate positions.

[0789] "Data collection methods" refers to technologies for obtaining information from online databases through API requests, or for collecting necessary information from the Internet using web scraping, etc.

[0790] "Reliability assessment method" refers to a technology that cross-references the source of collected data and calculates its reliability score to eliminate unreliable data.

[0791] "Natural language processing algorithm" refers to a technology that uses techniques such as topic modeling, keyword extraction, and sentiment analysis to analyze the structure and meaning of text data and extract important information.

[0792] "Discussion generation means" refers to technology that extracts a balanced mix of positive, negative, and neutral views from data analyzed using natural language processing, creating multifaceted discussions from a fair perspective.

[0793] "Transmission means" refers to the technology that encodes the generated discussion information in JSON format and transmits the data to the user's device using a RESTful API.

[0794] "Display means" refers to technology that analyzes the discussion data received by the user's terminal and visually presents the information in a format that is easy for the user to understand.

[0795] "Emotion recognition means" refers to technology that analyzes a user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[0796] "Recommendation means" refers to technology that selects appropriate products and services based on the user's emotional state and suggests them to the user.

[0797] "Information adjustment means" refers to technology that adjusts the tone and content of information according to the user's emotional state, providing information to the user in a more appropriate form.

[0798] System Overview

[0799] The system for implementing this invention collects data from reliable information sources, analyzes that data, and generates multifaceted discussions. It can also recognize the user's emotions and provide information and recommend products according to their emotional state. This system is primarily composed of three elements: a server, a terminal, and a user.

[0800] Hardware and software used

[0801] Hardware:

[0802] Camera: Used to recognize the user's facial expressions

[0803] High-performance PC: Used for image analysis and data analysis

[0804] Smartphone or tablet: Used to display information to the user

[0805] software:

[0806] facial_recognition: A library for analyzing customer facial expressions

[0807] sentiment_analysis: A library for analyzing the emotional tone of collected data

[0808] requests: A library for sending HTTP requests to retrieve data from an API.

[0809] Natural language processing algorithms: used to analyze collected data and extract key information (e.g., topic modeling, keyword extraction, sentiment analysis)

[0810] Detailed explanation of the process

[0811] 1. Data Collection:

[0812] The server collects data from reliable sources, such as official announcements from public institutions, academic papers, and official company statements, using API requests and web scraping techniques.

[0813] 2. Reliability assessment:

[0814] The server evaluates the reliability of the collected data through cross-referencing and calculates a reliability score, at which point unreliable data is eliminated.

[0815] 3. Natural Language Processing Analysis:

[0816] The server analyzes the data using natural language processing algorithms to extract key information through topic modeling, keyword extraction, and sentiment analysis.

[0817] 4. Discussion Generation:

[0818] The server generates multifaceted discussions based on the analysis results, providing fair information by integrating positive, negative, and neutral viewpoints in a balanced manner.

[0819] 5. Submitting and Viewing Discussions:

[0820] The server sends the generated discussion to the user's device, which analyzes the received discussion and visually displays it. The display content is adjusted according to the user's emotional state.

[0821] 6. Emotion recognition:

[0822] The device recognizes emotions by analyzing the user's facial expressions, voice, and input data, thereby identifying the user's current emotional state.

[0823] 7. Recommendations based on emotional state:

[0824] The device will recommend appropriate products and services based on the user's emotional state, for example, if the user is under stress, it will suggest products that have a relaxing effect.

[0825] Specific example explanation

[0826] For example, if a customer enters a store and the emotion recognition engine detects that the customer looks a little tired, the emotion score will be found to be 0.2 or less, and based on that result, the following prompt sentence can be input into the generative AI model:

[0827] Example prompt sentence:

[0828] Please provide a list of relaxation products. I would like to suggest products that will help my customers if they are tired.

[0829] This system not only provides users with multifaceted discussions based on reliable data, but also allows them to receive information and product recommendations that are suited to their emotional state, thereby improving the user experience.

[0830] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0831] Step 1:

[0832] The server collects data from reliable sources. Specifically, the server sends API requests or uses web scraping technology to obtain the necessary information from official announcements from public institutions, academic papers, official corporate statements, etc. This allows reliable data to be input into the server.

[0833] Step 2:

[0834] The server evaluates the reliability of the collected data. Specifically, it cross-references the origin of the collected data and calculates a reliability score to eliminate data with low reliability. This process outputs data that is evaluated as highly reliable.

[0835] Step 3:

[0836] The server applies natural language processing (NLP) algorithms to the data that has been evaluated as highly reliable. Specifically, it performs topic modeling, keyword extraction, and sentiment analysis to extract important information from the text data. This generates analyzed data that is output to the server.

[0837] Step 4:

[0838] The server generates a multifaceted discussion based on the analysis results. Specifically, it extracts a balanced mix of positive, negative, and neutral views, creating a multifaceted discussion from a fair perspective. The generated discussion is then output from the server.

[0839] Step 5:

[0840] The server sends the generated discussion to the user's device. Specifically, it encodes the generated discussion information in JSON format and sends the data to the user's device using a RESTful API. This transfers the discussion data from the server to the device.

[0841] Step 6:

[0842] The terminal analyzes the received discussion data and displays it to the user. Specifically, the analyzed discussion data is visually displayed and presented in a format that is easy for the user to understand, allowing the user to access the discussion information.

[0843] Step 7:

[0844] The device recognizes the user's emotions. Specifically, it analyzes the user's facial expressions, voice, and input data to identify the user's current emotional state. This information is then output to the device.

[0845] Step 8:

[0846] The device recommends products and services based on the user's emotional state. Specifically, it selects appropriate products and services according to the user's emotional state and proposes them to the user. This provides the user with optimal recommendation information.

[0847] Step 9:

[0848] The device adjusts the displayed information according to the user's emotional state, for example, presenting information in a calmer tone to a user who is under stress, thereby improving the user experience.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] [Third embodiment]

[0853] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0854] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0855] 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).

[0856] 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.

[0857] 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.

[0858] 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).

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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."

[0865] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[0866] Program processing

[0867] 1. Data Collection:

[0868] The server collects data from reliable sources (e.g., announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[0869] 2. Reliability assessment:

[0870] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[0871] 3. Natural Language Processing Analysis:

[0872] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[0873] 4. Discussion Generation:

[0874] The server generates a multifaceted discussion based on the analysis results, a process that balances and integrates different viewpoints and opinions, and compiles them into a discussion-style information format that contains fair and multifaceted views.

[0875] 5. Send to user device:

[0876] The server encodes the generated discussion and sends it to the user's device using a RESTful API, with the data sent in JSON format.

[0877] 6. Display and Feedback:

[0878] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The user can check the content of the discussion through this interface and provide feedback as needed. The feedback is sent to the server and used to improve the system.

[0879] Specific examples

[0880] Example 1: COVID-19 discussion

[0881] 1. Data Collection:

[0882] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[0883] 2. Reliability assessment:

[0884] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[0885] 3. Natural Language Processing Analysis:

[0886] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[0887] 4. Discussion Generation:

[0888] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[0889] 5. Send to user device:

[0890] The server sends the generated discussion in JSON format to the user's device.

[0891] 6. Display and Feedback:

[0892] The user's terminal visually displays the received discussion data, which the user can view in detail. Through the feedback function, the user can contribute to improving the system.

[0893] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[0894] The processing flow will be explained below.

[0895] Step 1:

[0896] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and corporate press releases and articles from major news sites using web scraping technology.

[0897] Step 2:

[0898] The server evaluates the reliability of the collected data. First, it cross-references the source of the data and calculates a reliability score. Information with a low reliability score is rejected at this point.

[0899] Step 3:

[0900] The server analyzes the collected data using natural language processing (NLP) algorithms: topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract key terms, and sentiment analysis (e.g., VADER) to assess emotional tone.

[0901] Step 4:

[0902] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[0903] Step 5:

[0904] The server sends the generated discussion to the user's device. The server encodes the generated discussion information in JSON format and sends it to the user's device using a RESTful API.

[0905] Step 6:

[0906] The user's device analyzes the received discussion data and visually displays it, allowing the user to check the details of the discussion through the interface.

[0907] Step 7:

[0908] Users provide feedback through their devices, which is sent to the server and used to improve the system and its accuracy.

[0909] Through this series of steps, we are able to collect data from reliable sources and provide users with a multifaceted and fair discussion.

[0910] Example 1

[0911] 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."

[0912] In today's information environment, problems such as filter bubbles and fake news are becoming more serious, making it difficult for users to obtain reliable information. It is also difficult to integrate different perspectives from the vast amount of information and generate fair and multifaceted discussions. To solve this problem, a system is needed that can collect reliable data, analyze that data, and generate multifaceted discussions.

[0913] 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.

[0914] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data by cross-referencing, means for analyzing the collected data using a natural language processing algorithm, means for generating a discussion by integrating opinions and views from different perspectives based on the analysis results, means for constructing a multifaceted discussion in natural sentences using a generative AI model, means for transmitting the generated discussion to a user's terminal, and means for displaying the received discussion on the user's terminal and collecting feedback from the user. This makes it possible to provide reliable, multifaceted information and enable users to access fair, multifaceted discussions.

[0915] A "reliable source" is a source that provides accurate and trustworthy data, such as announcements from public institutions, academic papers, and official corporate statements.

[0916] "Means of collecting data" refers to methods of obtaining the necessary information using API requests or web scraping technology.

[0917] "Cross-reference reliability assessment method" is a method for verifying the reliability of collected data by cross-referencing it from multiple sources and calculating a reliability score.

[0918] A "natural language processing algorithm" is a technology that analyzes collected text data, specifically performing topic modeling, keyword extraction, sentiment analysis, etc.

[0919] "Means for generating discussion by integrating opinions and views from different perspectives" refers to a method for generating discussion that incorporates a variety of perspectives and opinions in a balanced manner based on the results of analysis.

[0920] A "generative AI model" is an artificial intelligence technology that generates natural-looking sentences based on given data.

[0921] "Means for sending to the user's device" refers to a method for encoding the generated discussion and sending the data to the user's device via the Internet using a RESTful API.

[0922] "Means for displaying discussions received on the user's terminal and collecting feedback from the user" is a function that displays received discussion data on an interface and allows the user to provide feedback.

[0923] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[0924] System configuration

[0925] The system includes the following main components:

[0926] 1. Server: Responsible for data collection, credibility assessment, natural language processing, argument generation, and data transmission.

[0927] 2. User's terminal: Responsible for displaying generated discussions and collecting user feedback.

[0928] 3. Communication interface: Used to send and receive data between the server and the user's terminal.

[0929] Hardware and software used

[0930] server:

[0931] Hardware: A server machine with a powerful processor and plenty of memory.

[0932] Software: Python for data collection and libraries for performing API requests and web scraping (e.g., BeautifulSoup). NLTK and spaCy for natural language processing. Generative AI models such as GPT-3 are used.

[0933] On the user's device:

[0934] Hardware: PCs, tablets, smartphones, etc.

[0935] Software: Web browser and JavaScript interface.

[0936] Operation details

[0937] Data collection

[0938] The server retrieves data by sending API requests from reliable sources. For example, it retrieves the latest statistical data on COVID-19 from government health agency APIs. It also uses web scraping techniques to gather relevant articles from major news sites. This data collection process is performed periodically to ensure the information is always up to date.

[0939] Reliability evaluation

[0940] The server cross-references the reliability of the collected data, comparing data from multiple reliable sources and assigning a high reliability score to matching information. This evaluation process filters out information with low reliability.

[0941] Natural Language Processing

[0942] The server uses natural language processing algorithms on the collected data, including tokenizing the text using the NLTK library, modeling topics using LDA (Latent Dirichlet Allocation), extracting keywords using TF-IDF (Term Frequency-Inverse Document Frequency), and performing sentiment analysis using VADER (Valence Aware Dictionary for Sentiment Reasoning).

[0943] discussion generation

[0944] The server generates multifaceted discussions based on the analysis results. For example, it uses a generative AI model to construct natural-sounding sentences that combine multiple perspectives, such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[0945] Data transmission and display

[0946] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API. The user's device analyzes the received discussion data and displays it visually on the interface. The user can view the displayed discussions and provide feedback. The feedback is sent to the server and used to improve the system.

[0947] Specific examples

[0948] COVID-19 debate

[0949] 1. Data Collection:

[0950] The server collects official announcements from government health agencies, related academic papers, and press conference reports from major news sites.

[0951] 2. Reliability assessment:

[0952] The server cross-references the reliability of the collected data and selects only the most reliable information.

[0953] 3. Natural Language Processing:

[0954] The server performs sentiment analysis, topic modeling and keyword extraction.

[0955] 4. Discussion generation:

[0956] The server generates multifaceted discussions, including "medical opinions on the effectiveness of vaccines," "opinions on the government's lockdown policy," and "impact on the economy."

[0957] 5. Data transmission and display:

[0958] The server sends the generated discussion in JSON format to the user's device, where the user can view it in an interface.

[0959] Prompt Sentence Examples

[0960] Please generate a well-rounded and fair discussion on the following points regarding COVID-19:

[0961] 1. Medical opinion on vaccine effectiveness

[0962] 2. Opinions on the government's lockdown policy

[0963] 3. Economic impact

[0964] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[0965] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0966] Step 1: Collect data

[0967] The server collects data from reliable sources. It uses URLs and API endpoint information, such as public announcements, academic papers, and official corporate statements, as input. Specifically, the server generates an API request, calling, for example, "https: / / api.example.gov / covid19 / latest." It also uses a Python library for web scraping (e.g., BeautifulSoup) to parse articles from news sites. The output is the collected text data or JSON-formatted data.

[0968] Step 2: Assess reliability

[0969] The server evaluates the reliability of the collected data through cross-referencing. It uses the data collected in step 1 as input. The server compares the URLs and publication dates of the collected data sources and calculates a reliability score. Specifically, the server verifies the origin of each data point and assigns a high score to matching information. The output is a dataset with a reliability assessment and an attached score.

[0970] Step 3: Natural Language Processing Analysis

[0971] The server analyzes the data whose trustworthiness has been evaluated using a natural language processing algorithm. The data whose trustworthiness has been evaluated in step 2 is used as input. The server tokenizes the text using the NLTK library and models topics using LDA (Latent Dirichlet Allocation). Keywords are extracted using TF-IDF (Term Frequency-Inverse Document Frequency), and sentiment analysis is performed using VADER (Valence Aware Dictionary for Sentiment Reasoning). The output is a topic model, important keywords, and sentiment scores as the analysis results.

[0972] Step 4: Generate discussion

[0973] The server generates a multifaceted discussion based on the analysis results. The topic model, keywords, and sentiment scores obtained in step 3 are used as input. The server uses a generative AI model to integrate opinions and views from different perspectives and construct a fair, multifaceted discussion in natural-sounding sentences. Specifically, based on the given prompt, it generates a multifaceted discussion, such as "medical opinion on the effectiveness of vaccines," "opinions on government lockdown policies," and "impact on the economy." The output is text data of the generated discussion.

[0974] Step 5: Send to user device

[0975] The server encodes the generated discussion and sends it to the user's device via a RESTful API. The text data of the discussion generated in step 4 is used as input. The server implements the RESTful API using Python's Flask or similar and sends JSON-formatted data to the endpoint " / sendDiscussion" via a POST request. The output is the discussion data sent to the user's device.

[0976] Step 6: Display and feedback

[0977] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The discussion data sent in step 5 is used as input. The user's device parses the JSON data using JavaScript and displays it visually on a web page. Specifically, a section is created for each discussion point on the interface and text is displayed. The user can view this in detail and enter their opinion through a feedback form. The feedback is sent to the server and used to improve the system. The output is the feedback data from the user.

[0978] (Application example 1)

[0979] 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."

[0980] In today's information environment, unreliable information and fake news are rampant, making it difficult for users to obtain accurate and fair information. This problem increases the risk of making incorrect decisions based on false information. It also makes it difficult to integrate opinions and views from different perspectives in a balanced manner. Furthermore, there is a lack of means to effectively utilize user feedback and improve the accuracy of the system.

[0981] 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.

[0982] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to users' terminals, means for displaying the generated discussions on the users' terminals and receiving feedback, and means for analyzing user feedback and using it to improve the system. This allows for the provision of multifaceted and fair discussions based on reliable information, enabling users to make decisions based on accurate and balanced information. Furthermore, by effectively utilizing user feedback, the accuracy of the system can be continuously improved.

[0983] A "reliable source" is a source whose accuracy and reliability are guaranteed, such as announcements from public institutions, academic papers, and official corporate opinions.

[0984] "Methods for assessing data reliability" refers to the process of cross-referencing the origins of collected data and calculating a reliability score.

[0985] "Means of analyzing data" refers to techniques that use natural language processing algorithms to analyze the structure and meaning of text and extract key information.

[0986] "Means of generating discussion" refers to the process of integrating different perspectives and opinions in a balanced manner based on the results of analysis, and compiling information in a discussion format that includes fair and multifaceted views.

[0987] "Means for sending to the user's device" refers to the process of encoding the generated discussion and sending the data to the user's device using a RESTful API.

[0988] "Means for displaying discussions generated on the user's terminal" refers to a mechanism for analyzing received discussion data and displaying it on an interface that can be viewed by the user.

[0989] "Means for receiving feedback" refers to the process of collecting opinions and suggestions for improvement provided by users and using them to improve the system.

[0990] "Means for analyzing user feedback and using it to improve the system" refers to a method for analyzing collected feedback and improving the functionality and accuracy of the system.

[0991] The system for implementing this invention collects data from reliable information sources and uses that data to generate multifaceted and fair discussions. This system operates in cooperation with three parties: a server, terminals, and users.

[0992] System configuration

[0993] Hardware:

[0994] Server: Responsible for data collection, reliability assessment, natural language processing, and discussion generation.

[0995] User's device: A smartphone or other device that displays the generated discussion and receives feedback.

[0996] software:

[0997] Requests: Communication with external APIs for data collection.

[0998] scikit-learn: Analysis of text data (TF-IDF, topic modeling).

[0999] Flask: A web server that sends and receives data via a RESTful API.

[1000] Data collection and reliability assessment

[1001] The server collects data from reliable sources (e.g., government agencies, public institution announcements, academic papers, etc.) through APIs. This collected data is then cross-referenced to evaluate the reliability of each piece of information. Unreliable data is then eliminated.

[1002] Natural Language Processing

[1003] The server performs TF-IDF vectorization and topic modeling (such as LDA) on the collected text data to extract important information and major topics, allowing users to accurately obtain the information they need from a vast amount of data.

[1004] Generating discussions

[1005] Based on the analysis results, multifaceted discussions are generated that integrate different perspectives and opinions. The generated discussions are intended to include fair and multifaceted views. For example, a "discussion on COVID-19" could include a wide range of topics, such as opinions on the effectiveness of vaccines, views on government countermeasures, and the impact on the economy.

[1006] Sending to user terminal and displaying

[1007] The discussions generated by the server are sent to the user's device in JSON format using a RESTful API, which receives them and presents them to the user in a visual interface.

[1008] Collecting and analyzing feedback

[1009] Users provide feedback on the displayed discussions, which is then sent back to the server. The server analyzes the collected feedback and uses it to improve the system. This cycle allows the system to continuously evolve and become more accurate.

[1010] Examples and prompts

[1011] For example, when generating arguments against climate change, the following prompts might be used:

[1012] plaintext

[1013] Generate a multifaceted and fair discussion of climate change based on official government statements on climate change, recent academic papers, and news articles. Take into account different perspectives, such as the need for renewable energy, ways to reduce greenhouse gas emissions, and the economic impact.

[1014] In this way, the system of the present invention can provide users with multifaceted and fair discussions based on reliable information, thereby solving the problems of filter bubbles and fake news in the modern information environment.

[1015] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1016] Step 1:

[1017] Data collection

[1018] The server collects data from reliable sources, such as government APIs, public website data, and academic paper databases. The inputs are API endpoints and website URLs, and the output is the raw data stored in JSON format. This allows the server to secure the original data.

[1019] Step 2:

[1020] Reliability assessment

[1021] The server evaluates the reliability of the collected data, which includes cross-reference checks, specifically verifying the origin of the data and calculating a reliability score. The input is the raw data obtained, and the output is a selection of only reliable data. Data with low reliability is rejected at this stage.

[1022] Step 3:

[1023] Data analysis using natural language processing

[1024] The server applies natural language processing (NLP) algorithms to the highly reliable data. Specifically, it performs keyword extraction using TF-IDF vectorization and topic modeling using LDA. The input is selected, highly reliable data, and the output is the extraction of important keywords and topics. The structure and meaning of the text data are analyzed.

[1025] Step 4:

[1026] Generating discussions

[1027] The server generates multifaceted discussions based on the analysis results. Specifically, it integrates opinions from different perspectives based on the extracted keywords and topics. The input is keywords and topics extracted by the NLP algorithm, and the output is information in the form of a fair and multifaceted discussion. This allows for discussions that take multiple perspectives into account.

[1028] Step 5:

[1029] Send to user terminal

[1030] The server sends the generated discussion to the user's device using a RESTful API. Specifically, the data is encoded in JSON format and sent to the user's device. The input is the generated discussion data, and the output is received by the user's device. The data is encoded and sent.

[1031] Step 6:

[1032] View and receive feedback

[1033] The terminal visually displays the received discussion data, and the user views it. Specifically, the discussion is displayed on the interface, and the user checks its content. At the same time, a feedback function is provided, allowing the user to input their opinions and suggestions for improvement regarding the discussion. Inputs include the discussion data received from the server and user feedback, and outputs include display on the user's interface and transmission of feedback to the server.

[1034] Step 7:

[1035] Analyzing feedback and improving the system

[1036] The server analyzes the feedback received from users to improve the accuracy and functionality of the system. Specifically, it analyzes the content of the feedback using a natural language processing algorithm and extracts areas for improvement in the system. The input is the feedback data received from users, and the output is a system improvement plan. This allows the system to continuously evolve and increase user satisfaction.

[1037] 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.

[1038] The system of the present invention collects data from highly reliable information sources and generates multifaceted and fair discussions based on that data. This system incorporates an emotion engine that recognizes the user's emotions, making it possible to provide appropriate information and feedback processing according to the user's emotions. The system operates in cooperation with three parties: a server, a terminal, and a user.

[1039] Program processing

[1040] 1. Data Collection:

[1041] The server collects data from reliable sources (e.g., official announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[1042] 2. Reliability assessment:

[1043] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[1044] 3. Natural Language Processing Analysis:

[1045] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[1046] 4. Discussion Generation:

[1047] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[1048] 5. User Emotion Recognition:

[1049] The terminal has an emotion engine for recognizing the user's emotions, which analyzes the user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[1050] 6. Submitting and Viewing Discussions:

[1051] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. The device analyzes the received discussion data and displays it in a format that corresponds to the user's emotional state. For example, if the user is under stress, the information is presented in a calmer tone.

[1052] 7. Feedback and optimization:

[1053] Users provide feedback through their devices. The feedback is sent to the server, which records the user's emotional state through an emotion engine. The server uses this feedback information to improve the system and optimize it to provide more appropriate information.

[1054] Specific examples

[1055] Example 1: COVID-19 discussion

[1056] 1. Data Collection:

[1057] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[1058] 2. Reliability assessment:

[1059] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[1060] 3. Natural Language Processing Analysis:

[1061] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[1062] 4. Discussion Generation:

[1063] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[1064] 5. User Emotion Recognition:

[1065] The device analyzes the user's facial expressions and voice to identify their current emotional state. For example, if the user is feeling anxious, the emotion engine will recognize that emotional state.

[1066] 6. Submitting and Viewing Discussions:

[1067] The server sends the generated discussion in JSON format to the user's device, which visually displays the information according to the user's emotional state and presents it in a steady tone to reduce anxiety.

[1068] 7. Feedback and optimization:

[1069] Users provide feedback after viewing a discussion, and their emotional state is recorded. This information is sent to the server to continuously improve the system.

[1070] The present invention, which combines an emotion engine, allows users to obtain not only multifaceted and highly reliable information, but also information that is adapted to their own emotional state, thereby improving information literacy and reducing stress.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and web scraping technology to collect corporate press releases and articles from major news sites, allowing information to be gathered from multiple sources.

[1074] Step 2:

[1075] The server evaluates the reliability of the collected data by cross-referencing the data's origins and calculating a reliability score. By checking for matches from multiple sources, it eliminates data that may be erroneous and leaves only reliable information.

[1076] Step 3:

[1077] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract important terms, and sentiment analysis (e.g., VADER) to evaluate the emotional tone of the text, resulting in a detailed analysis of the text's content.

[1078] Step 4:

[1079] The server generates multifaceted discussions based on the analysis results. Specifically, it extracts important viewpoints and opinions from the analyzed data in a balanced manner, creating information in the form of a multifaceted discussion with a fair perspective. In doing so, it appropriately integrates positive, negative, and neutral views.

[1080] Step 5:

[1081] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. This allows the user to quickly access the information they need.

[1082] Step 6:

[1083] The device recognizes the user's emotions. It uses an emotion engine to analyze the user's facial expressions, voice, input data, etc. to identify the user's current emotional state. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice to estimate the user's emotional state.

[1084] Step 7:

[1085] The device analyzes the received discussion data and displays it in a way that reflects the user's emotional state. For example, if the user is under stress, the device will adjust the tone of the information provided to them to be calmer. The visual interface is also designed with the user's emotional state in mind.

[1086] Step 8:

[1087] Users can check the discussion content through the terminal and provide feedback as needed. The feedback includes a field where users can input their impressions of the discussion content, and the terminal collects this information.

[1088] Step 9:

[1089] The device analyzes the user's feedback through an emotion engine and sends it to the server, which then optimizes the system based on the feedback information and the user's emotional state, improving the discussion generation algorithm and data collection process.

[1090] Specific examples

[1091] COVID-19 debate

[1092] Step 1:

[1093] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites through API requests and web scraping.

[1094] Step 2:

[1095] The server evaluates the reliability of the collected data through cross-referencing and selects the most reliable data.

[1096] Step 3:

[1097] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[1098] Step 4:

[1099] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[1100] Step 5:

[1101] The server sends the generated discussion in JSON format to the user's device.

[1102] Step 6:

[1103] The device uses a camera and microphone to analyze the user's facial expressions and voice and recognize the user's emotional state.

[1104] Step 7:

[1105] The device adjusts the content of the discussion displayed in the user interface depending on the user's emotional state, for example, presenting information in a more reassuring tone if the user is feeling anxious.

[1106] Step 8:

[1107] Users can check the content of the discussion through the terminal and input their feedback, including their feelings.

[1108] Step 9:

[1109] The device analyzes the collected feedback using an emotion engine and sends it to a server, which uses this information to improve its data collection process and discussion generation algorithms.

[1110] This process allows users to obtain multifaceted and reliable information, and provides information that is adapted to each individual's emotional state.

[1111] Example 2

[1112] 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."

[1113] In modern society, it is extremely important to efficiently and fairly collect reliable information and generate multifaceted discussions. However, the mixing of unreliable information and the lack of information provision that is tailored to user sentiment make it difficult to form accurate and balanced discussions. Furthermore, there is a lack of means to effectively incorporate user feedback and continuously optimize the system. As a result, issues arise such as a decline in the reliability of information and user satisfaction.

[1114] 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.

[1115] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to the user's terminal, means for recognizing the user's emotions, means for displaying information in a form corresponding to the user's emotional state, and means for collecting user feedback and optimizing the system, thereby enabling reliable information collection, fair and multifaceted discussion generation, information provision adapted to the user's emotions, and continuous system optimization.

[1116] A "reliable source" refers to an information provider that is highly objective and accurate, and whose data credibility is guaranteed, such as official announcements from public institutions, academic papers, and official corporate opinions.

[1117] "Means for assessing reliability" refers to methods for analyzing the origins and meta-information of collected data and determining the reliability of the data through cross-referencing and reliability scoring.

[1118] "Natural language processing algorithms" are computational algorithms used to analyze collected text data, and include techniques such as topic modeling, keyword extraction, and sentiment analysis.

[1119] "Means for generating discussion" refers to methods for extracting important perspectives and opinions from the analyzed data and integrating them to create information in the form of a fair and multifaceted discussion.

[1120] "Means for recognizing user emotions" refers to technology that analyzes the user's facial expressions, voice, and input data to determine the user's current emotional state.

[1121] "Means for displaying information" refers to technology for displaying generated discussion information on a user's terminal, and includes techniques that incorporate display methods that correspond to the user's emotional state.

[1122] "Means for collecting feedback and optimizing the system" refers to methods for collecting feedback and emotional state data provided by users and using that data to improve the performance of the system and the quality of information provided.

[1123] "Generative AI models" refer to advanced artificial intelligence algorithms used to perform tasks such as natural language generation and argument generation.

[1124] A "prompt" is text data input into a generative AI model, and refers to instructions that allow the AI ​​to generate an appropriate response according to a specific format and content.

[1125] The system of the present invention operates in cooperation with three parties: the user, the terminal, and the server. The system's main function is to collect data from reliable sources and generate multifaceted and fair discussions based on that data. Furthermore, it is capable of recognizing the user's emotions and providing appropriate information and feedback.

[1126] Hardware and software used

[1127] 1. Server:

[1128] Hardware: A server machine with a high-performance CPU and sufficient memory

[1129] Software: Python programs and libraries (Beautiful Soup, Scrapy, Gensim, NLTK, VADER, etc.), RESTful API servers (e.g., Flask and Django), reliability assessment algorithms, generative AI models

[1130] 2. Terminal:

[1131] Hardware: The PC or smartphone used by the user

[1132] Software: Emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API), JavaScript program running in the browser, screen display using HTML and CSS

[1133] 3. User:

[1134] Interface: User feedback form, camera, microphone

[1135] Specific explanation of data processing and data calculation

[1136] Server Action:

[1137] The server first collects data from reliable sources. For example, it uses official APIs from public institutions to obtain the latest statistical information. It also uses web scraping tools to extract academic papers and news articles, and uses RSS feeds to obtain updates from major news sites. It then evaluates the reliability of the collected data, cross-referencing and scoring it.

[1138] Next, the data is analyzed using natural language processing algorithms. Specifically, the Gensim library is used for topic modeling, and NLTK is used for keyword extraction. For sentiment analysis, VADER is used to evaluate the emotional tone of the text. Based on these analysis results, a generative AI model is used to generate fair and multifaceted discussions. For example, it combines positive opinions such as "Infections are likely to decrease as vaccinations progress" with neutral opinions such as "Fair distribution is necessary for countries with low vaccination rates."

[1139] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API.

[1140] Terminal handling:

[1141] The device uses JavaScript to parse the received JSON-formatted discussion data and displays it visually using HTML and CSS. The device also uses an emotion engine to recognize the user's emotions. It captures the user's facial expressions using a camera and performs facial emotion analysis using OpenCV. For example, if the user frowns, it recognizes the user as anxious. It also collects audio data through the microphone and analyzes it with the Google Cloud Speech-to-Text API to evaluate the tone and tempo of the voice. Based on this information, it changes the display method depending on the user's emotional state. For example, if the user is stressed, it presents information using a blue background and soft font.

[1142] User role:

[1143] Users can view the displayed discussions and provide feedback, which is then sent back to the server, where the emotion engine records the user's emotional state. The server uses this feedback data to improve the system's performance and the quality of information provided.

[1144] Specific examples

[1145] Example 1: COVID-19 discussion:

[1146] The server collects official announcements from public institutions, related academic papers, and press conference articles from major news sites. It cross-references the reliability of the collected data and selects only the most up-to-date and reliable information. The server uses natural language processing algorithms to perform topic modeling, keyword extraction, and sentiment analysis to generate multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[1147] The server sends the generated discussion in JSON format to the user's device, which then visually displays the information according to the user's emotional state and presents it in a calm tone to reduce anxiety. For example, if the user is stressed, a blue background and soft font are used.

[1148] Example prompt sentence:

[1149] "Collect the latest, reliable information on COVID-19 and generate multifaceted discussions. If users are feeling anxious, focus on providing information in a calm tone."

[1150] This system allows users to improve their information literacy by viewing reliable and multifaceted discussions, and also reduces stress by providing information adapted to their emotional state.

[1151] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1152] Step 1:

[1153] The server collects data from reliable sources.

[1154] Input: Official APIs from public institutions, databases of academic papers, RSS feeds from major news sites

[1155] Data processing: Send API requests and extract the required information using a web scraping tool (such as Beautiful Soup or Scrapy).

[1156] Output: Raw collected data (e.g., latest case counts, text of academic papers, news articles)

[1157] Step 2:

[1158] The server evaluates the reliability of the collected data.

[1159] Input: Raw data collected

[1160] Data calculation: Perform cross-referencing and analyze meta-information such as data source, author, publication date, etc. Calculate reliability scores and filter out data with low scores.

[1161] Output: Highly reliable data (data with a reliability score of 50 or higher)

[1162] Step 3:

[1163] The server analyzes the data with high reliability using natural language processing algorithms.

[1164] Input: Reliable data

[1165] Data Computation: We use the Gensim library for topic modeling to extract major themes, NLTK for keyword extraction, and VADER for sentiment analysis to assess the emotional tone of the text.

[1166] Output: Analysis information (extracted topics, keywords, emotional tone)

[1167] Step 4:

[1168] The server generates a discussion based on the analysis results.

[1169] Input: Analysis information

[1170] Data Computation: Using generative AI models (e.g., GPT-3), we generate fair and multifaceted arguments from the analysis results, generating text that integrates positive, negative, and neutral views.

[1171] Output: Generated discussion (text data in sentence format)

[1172] Step 5:

[1173] The server transmits the generated discussion to the user's terminal.

[1174] Input: Generated arguments

[1175] Data processing: The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API.

[1176] Output: JSON formatted discussion data

[1177] Step 6:

[1178] The terminal visually displays the received discussion data.

[1179] Input: JSON format discussion data

[1180] Data Calculation: Parse the data using JavaScript and display it visually using HTML and CSS, adjusting font size, color, and layout depending on the user's emotional state.

[1181] Output: A visual representation of the argument (information presented to the user)

[1182] Step 7:

[1183] The terminal uses an emotion engine to recognize the user's emotions.

[1184] Input: User's facial expression (via camera), voice data (via microphone)

[1185] Data calculation: Analyze facial expressions with OpenCV and voice with Google Cloud Speech-to-Text API to determine the user's emotional state.

[1186] Output: User's emotional state (e.g., anxiety, stress)

[1187] Step 8:

[1188] The user provides feedback through the terminal.

[1189] Input: User feedback (text input)

[1190] Data processing: Collected feedback and emotional states are stored and sent to the server.

[1191] Output: Stored feedback data

[1192] Step 9:

[1193] The server optimizes the system based on the feedback information.

[1194] Input: User feedback data

[1195] Data computation: Using machine learning algorithms to analyze feedback and identify areas for system improvement.

[1196] Output: Improved system parameters (improving the quality of information provided next time)

[1197] (Application example 2)

[1198] 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."

[1199] While conventional systems can provide information from reliable sources, they do not take into account the provision of information or feedback according to the user's emotional state. As a result, users do not receive the information they need appropriately, making it difficult to increase satisfaction. In particular, inappropriate information may be provided to users who are feeling stressed or anxious, so there is a need to improve the user experience. To address this issue, it is necessary not only to provide reliable information, but also to adjust the content of the information according to the user's emotional state.

[1200] 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.

[1201] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to a user's terminal, means for displaying the generated discussions on the user's terminal, means for recognizing the user's emotions, means for recommending products and services based on the user's emotional state, and means for adjusting display information according to the emotional state. This not only allows the user to obtain reliable information, but also enables the provision of information adapted to the user's emotional state, thereby improving the user experience.

[1202] A "reliable source" generally refers to a place that provides accurate and trustworthy information, such as official announcements from public institutions, academic papers, and official corporate positions.

[1203] "Data collection methods" refers to technologies for obtaining information from online databases through API requests, or for collecting necessary information from the Internet using web scraping, etc.

[1204] "Reliability assessment method" refers to a technology that cross-references the source of collected data and calculates its reliability score to eliminate unreliable data.

[1205] "Natural language processing algorithm" refers to a technology that uses techniques such as topic modeling, keyword extraction, and sentiment analysis to analyze the structure and meaning of text data and extract important information.

[1206] "Discussion generation means" refers to technology that extracts a balanced mix of positive, negative, and neutral views from data analyzed using natural language processing, creating multifaceted discussions from a fair perspective.

[1207] "Transmission means" refers to the technology that encodes the generated discussion information in JSON format and transmits the data to the user's device using a RESTful API.

[1208] "Display means" refers to technology that analyzes the discussion data received by the user's terminal and visually presents the information in a format that is easy for the user to understand.

[1209] "Emotion recognition means" refers to technology that analyzes a user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[1210] "Recommendation means" refers to technology that selects appropriate products and services based on the user's emotional state and suggests them to the user.

[1211] "Information adjustment means" refers to technology that adjusts the tone and content of information according to the user's emotional state, providing information to the user in a more appropriate form.

[1212] System Overview

[1213] The system for implementing this invention collects data from reliable information sources, analyzes that data, and generates multifaceted discussions. It can also recognize the user's emotions and provide information and recommend products according to their emotional state. This system is primarily composed of three elements: a server, a terminal, and a user.

[1214] Hardware and software used

[1215] Hardware:

[1216] Camera: Used to recognize the user's facial expressions

[1217] High-performance PC: Used for image analysis and data analysis

[1218] Smartphone or tablet: Used to display information to the user

[1219] software:

[1220] facial_recognition: A library for analyzing customer facial expressions

[1221] sentiment_analysis: A library for analyzing the emotional tone of collected data

[1222] requests: A library for sending HTTP requests to retrieve data from an API.

[1223] Natural language processing algorithms: used to analyze collected data and extract key information (e.g., topic modeling, keyword extraction, sentiment analysis)

[1224] Detailed explanation of the process

[1225] 1. Data Collection:

[1226] The server collects data from reliable sources, such as official announcements from public institutions, academic papers, and official company statements, using API requests and web scraping techniques.

[1227] 2. Reliability assessment:

[1228] The server evaluates the reliability of the collected data through cross-referencing and calculates a reliability score, at which point unreliable data is eliminated.

[1229] 3. Natural Language Processing Analysis:

[1230] The server analyzes the data using natural language processing algorithms to extract key information through topic modeling, keyword extraction, and sentiment analysis.

[1231] 4. Discussion Generation:

[1232] The server generates multifaceted discussions based on the analysis results, providing fair information by integrating positive, negative, and neutral viewpoints in a balanced manner.

[1233] 5. Submitting and Viewing Discussions:

[1234] The server sends the generated discussion to the user's device, which analyzes the received discussion and visually displays it. The display content is adjusted according to the user's emotional state.

[1235] 6. Emotion recognition:

[1236] The device recognizes emotions by analyzing the user's facial expressions, voice, and input data, thereby identifying the user's current emotional state.

[1237] 7. Recommendations based on emotional state:

[1238] The device will recommend appropriate products and services based on the user's emotional state, for example, if the user is under stress, it will suggest products that have a relaxing effect.

[1239] Specific example explanation

[1240] For example, if a customer enters a store and the emotion recognition engine detects that the customer looks a little tired, the emotion score will be found to be 0.2 or less, and based on that result, the following prompt sentence can be input into the generative AI model:

[1241] Example prompt sentence:

[1242] Please provide a list of relaxation products. I would like to suggest products that will help my customers if they are tired.

[1243] This system not only provides users with multifaceted discussions based on reliable data, but also allows them to receive information and product recommendations that are suited to their emotional state, thereby improving the user experience.

[1244] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1245] Step 1:

[1246] The server collects data from reliable sources. Specifically, the server sends API requests or uses web scraping technology to obtain the necessary information from official announcements from public institutions, academic papers, official corporate statements, etc. This allows reliable data to be input into the server.

[1247] Step 2:

[1248] The server evaluates the reliability of the collected data. Specifically, it cross-references the origin of the collected data and calculates a reliability score to eliminate data with low reliability. This process outputs data that is evaluated as highly reliable.

[1249] Step 3:

[1250] The server applies natural language processing (NLP) algorithms to the data that has been evaluated as highly reliable. Specifically, it performs topic modeling, keyword extraction, and sentiment analysis to extract important information from the text data. This generates analyzed data that is output to the server.

[1251] Step 4:

[1252] The server generates a multifaceted discussion based on the analysis results. Specifically, it extracts a balanced mix of positive, negative, and neutral views, creating a multifaceted discussion from a fair perspective. The generated discussion is then output from the server.

[1253] Step 5:

[1254] The server sends the generated discussion to the user's device. Specifically, it encodes the generated discussion information in JSON format and sends the data to the user's device using a RESTful API. This transfers the discussion data from the server to the device.

[1255] Step 6:

[1256] The terminal analyzes the received discussion data and displays it to the user. Specifically, the analyzed discussion data is visually displayed and presented in a format that is easy for the user to understand, allowing the user to access the discussion information.

[1257] Step 7:

[1258] The device recognizes the user's emotions. Specifically, it analyzes the user's facial expressions, voice, and input data to identify the user's current emotional state. This information is then output to the device.

[1259] Step 8:

[1260] The device recommends products and services based on the user's emotional state. Specifically, it selects appropriate products and services according to the user's emotional state and proposes them to the user. This provides the user with optimal recommendation information.

[1261] Step 9:

[1262] The device adjusts the displayed information according to the user's emotional state, for example, presenting information in a calmer tone to a user who is under stress, thereby improving the user experience.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] [Fourth embodiment]

[1267] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1268] 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.

[1269] 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).

[1270] 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.

[1271] 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.

[1272] 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).

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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."

[1280] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[1281] Program processing

[1282] 1. Data Collection:

[1283] The server collects data from reliable sources (e.g., announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[1284] 2. Reliability assessment:

[1285] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[1286] 3. Natural Language Processing Analysis:

[1287] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[1288] 4. Discussion Generation:

[1289] The server generates a multifaceted discussion based on the analysis results, a process that balances and integrates different viewpoints and opinions, and compiles them into a discussion-style information format that contains fair and multifaceted views.

[1290] 5. Send to user device:

[1291] The server encodes the generated discussion and sends it to the user's device using a RESTful API, with the data sent in JSON format.

[1292] 6. Display and Feedback:

[1293] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The user can check the content of the discussion through this interface and provide feedback as needed. The feedback is sent to the server and used to improve the system.

[1294] Specific examples

[1295] Example 1: COVID-19 discussion

[1296] 1. Data Collection:

[1297] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[1298] 2. Reliability assessment:

[1299] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[1300] 3. Natural Language Processing Analysis:

[1301] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[1302] 4. Discussion Generation:

[1303] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[1304] 5. Send to user device:

[1305] The server sends the generated discussion in JSON format to the user's device.

[1306] 6. Display and Feedback:

[1307] The user's terminal visually displays the received discussion data, which the user can view in detail. Through the feedback function, the user can contribute to improving the system.

[1308] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[1309] The processing flow will be explained below.

[1310] Step 1:

[1311] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and corporate press releases and articles from major news sites using web scraping technology.

[1312] Step 2:

[1313] The server evaluates the reliability of the collected data. First, it cross-references the source of the data and calculates a reliability score. Information with a low reliability score is rejected at this point.

[1314] Step 3:

[1315] The server analyzes the collected data using natural language processing (NLP) algorithms: topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract key terms, and sentiment analysis (e.g., VADER) to assess emotional tone.

[1316] Step 4:

[1317] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[1318] Step 5:

[1319] The server sends the generated discussion to the user's device. The server encodes the generated discussion information in JSON format and sends it to the user's device using a RESTful API.

[1320] Step 6:

[1321] The user's device analyzes the received discussion data and visually displays it, allowing the user to check the details of the discussion through the interface.

[1322] Step 7:

[1323] Users provide feedback through their devices, which is sent to the server and used to improve the system and its accuracy.

[1324] Through this series of steps, we are able to collect data from reliable sources and provide users with a multifaceted and fair discussion.

[1325] Example 1

[1326] 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."

[1327] In today's information environment, problems such as filter bubbles and fake news are becoming more serious, making it difficult for users to obtain reliable information. It is also difficult to integrate different perspectives from the vast amount of information and generate fair and multifaceted discussions. To solve this problem, a system is needed that can collect reliable data, analyze that data, and generate multifaceted discussions.

[1328] 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.

[1329] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data by cross-referencing, means for analyzing the collected data using a natural language processing algorithm, means for generating a discussion by integrating opinions and views from different perspectives based on the analysis results, means for constructing a multifaceted discussion in natural sentences using a generative AI model, means for transmitting the generated discussion to a user's terminal, and means for displaying the received discussion on the user's terminal and collecting feedback from the user. This makes it possible to provide reliable, multifaceted information and enable users to access fair, multifaceted discussions.

[1330] A "reliable source" is a source that provides accurate and trustworthy data, such as announcements from public institutions, academic papers, and official corporate statements.

[1331] "Means of collecting data" refers to methods of obtaining the necessary information using API requests or web scraping technology.

[1332] "Cross-reference reliability assessment method" is a method for verifying the reliability of collected data by cross-referencing it from multiple sources and calculating a reliability score.

[1333] A "natural language processing algorithm" is a technology that analyzes collected text data, specifically performing topic modeling, keyword extraction, sentiment analysis, etc.

[1334] "Means for generating discussion by integrating opinions and views from different perspectives" refers to a method for generating discussion that incorporates a variety of perspectives and opinions in a balanced manner based on the results of analysis.

[1335] A "generative AI model" is an artificial intelligence technology that generates natural-looking sentences based on given data.

[1336] "Means for sending to the user's device" refers to a method for encoding the generated discussion and sending the data to the user's device via the Internet using a RESTful API.

[1337] "Means for displaying discussions received on the user's terminal and collecting feedback from the user" is a function that displays received discussion data on an interface and allows the user to provide feedback.

[1338] The system of the present invention collects data from reliable sources and generates multifaceted and fair discussions based on that data. This system operates in cooperation with three parties: a server, terminals, and users.

[1339] System configuration

[1340] The system includes the following main components:

[1341] 1. Server: Responsible for data collection, credibility assessment, natural language processing, argument generation, and data transmission.

[1342] 2. User's terminal: Responsible for displaying generated discussions and collecting user feedback.

[1343] 3. Communication interface: Used to send and receive data between the server and the user's terminal.

[1344] Hardware and software used

[1345] server:

[1346] Hardware: A server machine with a powerful processor and plenty of memory.

[1347] Software: Python for data collection and libraries for performing API requests and web scraping (e.g., BeautifulSoup). NLTK and spaCy for natural language processing. Generative AI models such as GPT-3 are used.

[1348] On the user's device:

[1349] Hardware: PCs, tablets, smartphones, etc.

[1350] Software: Web browser and JavaScript interface.

[1351] Operation details

[1352] Data collection

[1353] The server retrieves data by sending API requests from reliable sources. For example, it retrieves the latest statistical data on COVID-19 from government health agency APIs. It also uses web scraping techniques to gather relevant articles from major news sites. This data collection process is performed periodically to ensure the information is always up to date.

[1354] Reliability evaluation

[1355] The server cross-references the reliability of the collected data, comparing data from multiple reliable sources and assigning a high reliability score to matching information. This evaluation process filters out information with low reliability.

[1356] Natural Language Processing

[1357] The server uses natural language processing algorithms on the collected data, including tokenizing the text using the NLTK library, modeling topics using LDA (Latent Dirichlet Allocation), extracting keywords using TF-IDF (Term Frequency-Inverse Document Frequency), and performing sentiment analysis using VADER (Valence Aware Dictionary for Sentiment Reasoning).

[1358] discussion generation

[1359] The server generates multifaceted discussions based on the analysis results. For example, it uses a generative AI model to construct natural-sounding sentences that combine multiple perspectives, such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[1360] Data transmission and display

[1361] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API. The user's device analyzes the received discussion data and displays it visually on the interface. The user can view the displayed discussions and provide feedback. The feedback is sent to the server and used to improve the system.

[1362] Specific examples

[1363] COVID-19 debate

[1364] 1. Data Collection:

[1365] The server collects official announcements from government health agencies, related academic papers, and press conference reports from major news sites.

[1366] 2. Reliability assessment:

[1367] The server cross-references the reliability of the collected data and selects only the most reliable information.

[1368] 3. Natural Language Processing:

[1369] The server performs sentiment analysis, topic modeling and keyword extraction.

[1370] 4. Discussion generation:

[1371] The server generates multifaceted discussions, including "medical opinions on the effectiveness of vaccines," "opinions on the government's lockdown policy," and "impact on the economy."

[1372] 5. Data transmission and display:

[1373] The server sends the generated discussion in JSON format to the user's device, where the user can view it in an interface.

[1374] Prompt Sentence Examples

[1375] Please generate a well-rounded and fair discussion on the following points regarding COVID-19:

[1376] 1. Medical opinion on vaccine effectiveness

[1377] 2. Opinions on the government's lockdown policy

[1378] 3. Economic impact

[1379] In this way, the system of the present invention can provide users with multifaceted and reliable information, solving the problems of filter bubbles and fake news in the modern information environment.

[1380] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1381] Step 1: Collect data

[1382] The server collects data from reliable sources. It uses URLs and API endpoint information, such as public announcements, academic papers, and official corporate statements, as input. Specifically, the server generates an API request, calling, for example, "https: / / api.example.gov / covid19 / latest." It also uses a Python library for web scraping (e.g., BeautifulSoup) to parse articles from news sites. The output is the collected text data or JSON-formatted data.

[1383] Step 2: Assess reliability

[1384] The server evaluates the reliability of the collected data through cross-referencing. It uses the data collected in step 1 as input. The server compares the URLs and publication dates of the collected data sources and calculates a reliability score. Specifically, the server verifies the origin of each data point and assigns a high score to matching information. The output is a dataset with a reliability assessment and an attached score.

[1385] Step 3: Natural Language Processing Analysis

[1386] The server analyzes the data whose trustworthiness has been evaluated using a natural language processing algorithm. The data whose trustworthiness has been evaluated in step 2 is used as input. The server tokenizes the text using the NLTK library and models topics using LDA (Latent Dirichlet Allocation). Keywords are extracted using TF-IDF (Term Frequency-Inverse Document Frequency), and sentiment analysis is performed using VADER (Valence Aware Dictionary for Sentiment Reasoning). The output is a topic model, important keywords, and sentiment scores as the analysis results.

[1387] Step 4: Generate discussion

[1388] The server generates a multifaceted discussion based on the analysis results. The topic model, keywords, and sentiment scores obtained in step 3 are used as input. The server uses a generative AI model to integrate opinions and views from different perspectives and construct a fair, multifaceted discussion in natural-sounding sentences. Specifically, based on the given prompt, it generates a multifaceted discussion, such as "medical opinion on the effectiveness of vaccines," "opinions on government lockdown policies," and "impact on the economy." The output is text data of the generated discussion.

[1389] Step 5: Send to user device

[1390] The server encodes the generated discussion and sends it to the user's device via a RESTful API. The text data of the discussion generated in step 4 is used as input. The server implements the RESTful API using Python's Flask or similar and sends JSON-formatted data to the endpoint " / sendDiscussion" via a POST request. The output is the discussion data sent to the user's device.

[1391] Step 6: Display and feedback

[1392] The user's device analyzes the received discussion data and displays it in an interface that the user can view. The discussion data sent in step 5 is used as input. The user's device parses the JSON data using JavaScript and displays it visually on a web page. Specifically, a section is created for each discussion point on the interface and text is displayed. The user can view this in detail and enter their opinion through a feedback form. The feedback is sent to the server and used to improve the system. The output is the feedback data from the user.

[1393] (Application example 1)

[1394] 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."

[1395] In today's information environment, unreliable information and fake news are rampant, making it difficult for users to obtain accurate and fair information. This problem increases the risk of making incorrect decisions based on false information. It also makes it difficult to integrate opinions and views from different perspectives in a balanced manner. Furthermore, there is a lack of means to effectively utilize user feedback and improve the accuracy of the system.

[1396] 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.

[1397] In this invention, the server includes means for collecting data from reliable sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to users' terminals, means for displaying the generated discussions on the users' terminals and receiving feedback, and means for analyzing user feedback and using it to improve the system. This allows for the provision of multifaceted and fair discussions based on reliable information, enabling users to make decisions based on accurate and balanced information. Furthermore, by effectively utilizing user feedback, the accuracy of the system can be continuously improved.

[1398] A "reliable source" is a source whose accuracy and reliability are guaranteed, such as announcements from public institutions, academic papers, and official corporate opinions.

[1399] "Methods for assessing data reliability" refers to the process of cross-referencing the origins of collected data and calculating a reliability score.

[1400] "Means of analyzing data" refers to techniques that use natural language processing algorithms to analyze the structure and meaning of text and extract key information.

[1401] "Means of generating discussion" refers to the process of integrating different perspectives and opinions in a balanced manner based on the results of analysis, and compiling information in a discussion format that includes fair and multifaceted views.

[1402] "Means for sending to the user's device" refers to the process of encoding the generated discussion and sending the data to the user's device using a RESTful API.

[1403] "Means for displaying discussions generated on the user's terminal" refers to a mechanism for analyzing received discussion data and displaying it on an interface that can be viewed by the user.

[1404] "Means for receiving feedback" refers to the process of collecting opinions and suggestions for improvement provided by users and using them to improve the system.

[1405] "Means for analyzing user feedback and using it to improve the system" refers to a method for analyzing collected feedback and improving the functionality and accuracy of the system.

[1406] The system for implementing this invention collects data from reliable information sources and uses that data to generate multifaceted and fair discussions. This system operates in cooperation with three parties: a server, terminals, and users.

[1407] System configuration

[1408] Hardware:

[1409] Server: Responsible for data collection, reliability assessment, natural language processing, and discussion generation.

[1410] User's device: A smartphone or other device that displays the generated discussion and receives feedback.

[1411] software:

[1412] Requests: Communication with external APIs for data collection.

[1413] scikit-learn: Analysis of text data (TF-IDF, topic modeling).

[1414] Flask: A web server that sends and receives data via a RESTful API.

[1415] Data collection and reliability assessment

[1416] The server collects data from reliable sources (e.g., government agencies, public institution announcements, academic papers, etc.) through APIs. This collected data is then cross-referenced to evaluate the reliability of each piece of information. Unreliable data is then eliminated.

[1417] Natural Language Processing

[1418] The server performs TF-IDF vectorization and topic modeling (such as LDA) on the collected text data to extract important information and major topics, allowing users to accurately obtain the information they need from a vast amount of data.

[1419] Generating discussions

[1420] Based on the analysis results, multifaceted discussions are generated that integrate different perspectives and opinions. The generated discussions are intended to include fair and multifaceted views. For example, a "discussion on COVID-19" could include a wide range of topics, such as opinions on the effectiveness of vaccines, views on government countermeasures, and the impact on the economy.

[1421] Sending to user terminal and displaying

[1422] The discussions generated by the server are sent to the user's device in JSON format using a RESTful API, which receives them and presents them to the user in a visual interface.

[1423] Collecting and analyzing feedback

[1424] Users provide feedback on the displayed discussions, which is then sent back to the server. The server analyzes the collected feedback and uses it to improve the system. This cycle allows the system to continuously evolve and become more accurate.

[1425] Examples and prompts

[1426] For example, when generating arguments against climate change, the following prompts might be used:

[1427] plaintext

[1428] Generate a multifaceted and fair discussion of climate change based on official government statements on climate change, recent academic papers, and news articles. Take into account different perspectives, such as the need for renewable energy, ways to reduce greenhouse gas emissions, and the economic impact.

[1429] In this way, the system of the present invention can provide users with multifaceted and fair discussions based on reliable information, thereby solving the problems of filter bubbles and fake news in the modern information environment.

[1430] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1431] Step 1:

[1432] Data collection

[1433] The server collects data from reliable sources, such as government APIs, public website data, and academic paper databases. The inputs are API endpoints and website URLs, and the output is the raw data stored in JSON format. This allows the server to secure the original data.

[1434] Step 2:

[1435] Reliability assessment

[1436] The server evaluates the reliability of the collected data, which includes cross-reference checks, specifically verifying the origin of the data and calculating a reliability score. The input is the raw data obtained, and the output is a selection of only reliable data. Data with low reliability is rejected at this stage.

[1437] Step 3:

[1438] Data analysis using natural language processing

[1439] The server applies natural language processing (NLP) algorithms to the highly reliable data. Specifically, it performs keyword extraction using TF-IDF vectorization and topic modeling using LDA. The input is selected, highly reliable data, and the output is the extraction of important keywords and topics. The structure and meaning of the text data are analyzed.

[1440] Step 4:

[1441] Generating discussions

[1442] The server generates multifaceted discussions based on the analysis results. Specifically, it integrates opinions from different perspectives based on the extracted keywords and topics. The input is keywords and topics extracted by the NLP algorithm, and the output is information in the form of a fair and multifaceted discussion. This allows for discussions that take multiple perspectives into account.

[1443] Step 5:

[1444] Send to user terminal

[1445] The server sends the generated discussion to the user's device using a RESTful API. Specifically, the data is encoded in JSON format and sent to the user's device. The input is the generated discussion data, and the output is received by the user's device. The data is encoded and sent.

[1446] Step 6:

[1447] View and receive feedback

[1448] The terminal visually displays the received discussion data, and the user views it. Specifically, the discussion is displayed on the interface, and the user checks its content. At the same time, a feedback function is provided, allowing the user to input their opinions and suggestions for improvement regarding the discussion. Inputs include the discussion data received from the server and user feedback, and outputs include display on the user's interface and transmission of feedback to the server.

[1449] Step 7:

[1450] Analyzing feedback and improving the system

[1451] The server analyzes the feedback received from users to improve the accuracy and functionality of the system. Specifically, it analyzes the content of the feedback using a natural language processing algorithm and extracts areas for improvement in the system. The input is the feedback data received from users, and the output is a system improvement plan. This allows the system to continuously evolve and increase user satisfaction.

[1452] 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.

[1453] The system of the present invention collects data from highly reliable information sources and generates multifaceted and fair discussions based on that data. This system incorporates an emotion engine that recognizes the user's emotions, making it possible to provide appropriate information and feedback processing according to the user's emotions. The system operates in cooperation with three parties: a server, a terminal, and a user.

[1454] Program processing

[1455] 1. Data Collection:

[1456] The server collects data from reliable sources (e.g., official announcements from public institutions, academic papers, official company statements, etc.) Specifically, it obtains the required information from various databases by sending API requests or using web scraping technology.

[1457] 2. Reliability assessment:

[1458] The server evaluates the reliability of the collected data by cross-referencing the data's origin and calculating a reliability score. Unreliable data is then rejected.

[1459] 3. Natural Language Processing Analysis:

[1460] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA), keyword extraction (e.g., TF-IDF), and sentiment analysis (e.g., VADER), to analyze the structure and meaning of the text and extract key information.

[1461] 4. Discussion Generation:

[1462] The server generates multifaceted discussions based on the analysis results, extracting important viewpoints and opinions in a balanced manner from the analyzed data and creating information in the form of a multifaceted discussion with fair perspectives, integrating positive, negative, and neutral views.

[1463] 5. User Emotion Recognition:

[1464] The terminal has an emotion engine for recognizing the user's emotions, which analyzes the user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[1465] 6. Submitting and Viewing Discussions:

[1466] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. The device analyzes the received discussion data and displays it in a format that corresponds to the user's emotional state. For example, if the user is under stress, the information is presented in a calmer tone.

[1467] 7. Feedback and optimization:

[1468] Users provide feedback through their devices. The feedback is sent to the server, which records the user's emotional state through an emotion engine. The server uses this feedback information to improve the system and optimize it to provide more appropriate information.

[1469] Specific examples

[1470] Example 1: COVID-19 discussion

[1471] 1. Data Collection:

[1472] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites.

[1473] 2. Reliability assessment:

[1474] The server cross-references the reliability of the collected data and selects only the most up-to-date and reliable information.

[1475] 3. Natural Language Processing Analysis:

[1476] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[1477] 4. Discussion Generation:

[1478] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[1479] 5. User Emotion Recognition:

[1480] The device analyzes the user's facial expressions and voice to identify their current emotional state. For example, if the user is feeling anxious, the emotion engine will recognize that emotional state.

[1481] 6. Submitting and Viewing Discussions:

[1482] The server sends the generated discussion in JSON format to the user's device, which visually displays the information according to the user's emotional state and presents it in a steady tone to reduce anxiety.

[1483] 7. Feedback and optimization:

[1484] Users provide feedback after viewing a discussion, and their emotional state is recorded. This information is sent to the server to continuously improve the system.

[1485] The present invention, which combines an emotion engine, allows users to obtain not only multifaceted and highly reliable information, but also information that is adapted to their own emotional state, thereby improving information literacy and reducing stress.

[1486] The processing flow will be explained below.

[1487] Step 1:

[1488] The server collects data from reliable sources, such as official announcements from public institutions and academic papers using API requests, and web scraping technology to collect corporate press releases and articles from major news sites, allowing information to be gathered from multiple sources.

[1489] Step 2:

[1490] The server evaluates the reliability of the collected data by cross-referencing the data's origins and calculating a reliability score. By checking for matches from multiple sources, it eliminates data that may be erroneous and leaves only reliable information.

[1491] Step 3:

[1492] The server analyzes the collected data using natural language processing (NLP) algorithms, such as topic modeling (e.g., LDA) to identify themes, keyword extraction (e.g., TF-IDF) to extract important terms, and sentiment analysis (e.g., VADER) to evaluate the emotional tone of the text, resulting in a detailed analysis of the text's content.

[1493] Step 4:

[1494] The server generates multifaceted discussions based on the analysis results. Specifically, it extracts important viewpoints and opinions from the analyzed data in a balanced manner, creating information in the form of a multifaceted discussion with a fair perspective. In doing so, it appropriately integrates positive, negative, and neutral views.

[1495] Step 5:

[1496] The server sends the generated discussion to the user's device. The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API. This allows the user to quickly access the information they need.

[1497] Step 6:

[1498] The device recognizes the user's emotions. It uses an emotion engine to analyze the user's facial expressions, voice, input data, etc. to identify the user's current emotional state. For example, it uses a camera and microphone to analyze the user's facial expressions and tone of voice to estimate the user's emotional state.

[1499] Step 7:

[1500] The device analyzes the received discussion data and displays it in a way that reflects the user's emotional state. For example, if the user is under stress, the device will adjust the tone of the information provided to them to be calmer. The visual interface is also designed with the user's emotional state in mind.

[1501] Step 8:

[1502] Users can check the discussion content through the terminal and provide feedback as needed. The feedback includes a field where users can input their impressions of the discussion content, and the terminal collects this information.

[1503] Step 9:

[1504] The device analyzes the user's feedback through an emotion engine and sends it to the server, which then optimizes the system based on the feedback information and the user's emotional state, improving the discussion generation algorithm and data collection process.

[1505] Specific examples

[1506] COVID-19 debate

[1507] Step 1:

[1508] The server collects official announcements from government health agencies, relevant academic papers, and press conference reports from major news sites through API requests and web scraping.

[1509] Step 2:

[1510] The server evaluates the reliability of the collected data through cross-referencing and selects the most reliable data.

[1511] Step 3:

[1512] The server performs sentiment analysis to analyze the emotional tone of the text, and topic modeling and keyword extraction to extract major topics.

[1513] Step 4:

[1514] The server generates multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impact."

[1515] Step 5:

[1516] The server sends the generated discussion in JSON format to the user's device.

[1517] Step 6:

[1518] The device uses a camera and microphone to analyze the user's facial expressions and voice and recognize the user's emotional state.

[1519] Step 7:

[1520] The device adjusts the content of the discussion displayed in the user interface depending on the user's emotional state, for example, presenting information in a more reassuring tone if the user is feeling anxious.

[1521] Step 8:

[1522] Users can check the content of the discussion through the terminal and input their feedback, including their feelings.

[1523] Step 9:

[1524] The device analyzes the collected feedback using an emotion engine and sends it to a server, which uses this information to improve its data collection process and discussion generation algorithms.

[1525] This process allows users to obtain multifaceted and reliable information, and provides information that is adapted to each individual's emotional state.

[1526] Example 2

[1527] 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."

[1528] In modern society, it is extremely important to efficiently and fairly collect reliable information and generate multifaceted discussions. However, the mixing of unreliable information and the lack of information provision that is tailored to user sentiment make it difficult to form accurate and balanced discussions. Furthermore, there is a lack of means to effectively incorporate user feedback and continuously optimize the system. As a result, issues arise such as a decline in the reliability of information and user satisfaction.

[1529] 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.

[1530] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to the user's terminal, means for recognizing the user's emotions, means for displaying information in a form corresponding to the user's emotional state, and means for collecting user feedback and optimizing the system, thereby enabling reliable information collection, fair and multifaceted discussion generation, information provision adapted to the user's emotions, and continuous system optimization.

[1531] A "reliable source" refers to an information provider that is highly objective and accurate, and whose data credibility is guaranteed, such as official announcements from public institutions, academic papers, and official corporate opinions.

[1532] "Means for assessing reliability" refers to methods for analyzing the origins and meta-information of collected data and determining the reliability of the data through cross-referencing and reliability scoring.

[1533] "Natural language processing algorithms" are computational algorithms used to analyze collected text data, and include techniques such as topic modeling, keyword extraction, and sentiment analysis.

[1534] "Means for generating discussion" refers to methods for extracting important perspectives and opinions from the analyzed data and integrating them to create information in the form of a fair and multifaceted discussion.

[1535] "Means for recognizing user emotions" refers to technology that analyzes the user's facial expressions, voice, and input data to determine the user's current emotional state.

[1536] "Means for displaying information" refers to technology for displaying generated discussion information on a user's terminal, and includes techniques that incorporate display methods that correspond to the user's emotional state.

[1537] "Means for collecting feedback and optimizing the system" refers to methods for collecting feedback and emotional state data provided by users and using that data to improve the performance of the system and the quality of information provided.

[1538] "Generative AI models" refer to advanced artificial intelligence algorithms used to perform tasks such as natural language generation and argument generation.

[1539] A "prompt" is text data input into a generative AI model, and refers to instructions that allow the AI ​​to generate an appropriate response according to a specific format and content.

[1540] The system of the present invention operates in cooperation with three parties: the user, the terminal, and the server. The system's main function is to collect data from reliable sources and generate multifaceted and fair discussions based on that data. Furthermore, it is capable of recognizing the user's emotions and providing appropriate information and feedback.

[1541] Hardware and software used

[1542] 1. Server:

[1543] Hardware: A server machine with a high-performance CPU and sufficient memory

[1544] Software: Python programs and libraries (Beautiful Soup, Scrapy, Gensim, NLTK, VADER, etc.), RESTful API servers (e.g., Flask and Django), reliability assessment algorithms, generative AI models

[1545] 2. Terminal:

[1546] Hardware: The PC or smartphone used by the user

[1547] Software: Emotion engine (e.g., OpenCV, Google Cloud Speech-to-Text API), JavaScript program running in the browser, screen display using HTML and CSS

[1548] 3. User:

[1549] Interface: User feedback form, camera, microphone

[1550] Specific explanation of data processing and data calculation

[1551] Server Action:

[1552] The server first collects data from reliable sources. For example, it uses official APIs from public institutions to obtain the latest statistical information. It also uses web scraping tools to extract academic papers and news articles, and uses RSS feeds to obtain updates from major news sites. It then evaluates the reliability of the collected data, cross-referencing and scoring it.

[1553] Next, the data is analyzed using natural language processing algorithms. Specifically, the Gensim library is used for topic modeling, and NLTK is used for keyword extraction. For sentiment analysis, VADER is used to evaluate the emotional tone of the text. Based on these analysis results, a generative AI model is used to generate fair and multifaceted discussions. For example, it combines positive opinions such as "Infections are likely to decrease as vaccinations progress" with neutral opinions such as "Fair distribution is necessary for countries with low vaccination rates."

[1554] The generated discussions are encoded in JSON format and sent to the user's device using a RESTful API.

[1555] Terminal handling:

[1556] The device uses JavaScript to parse the received JSON-formatted discussion data and displays it visually using HTML and CSS. The device also uses an emotion engine to recognize the user's emotions. It captures the user's facial expressions using a camera and performs facial emotion analysis using OpenCV. For example, if the user frowns, it recognizes the user as anxious. It also collects audio data through the microphone and analyzes it with the Google Cloud Speech-to-Text API to evaluate the tone and tempo of the voice. Based on this information, it changes the display method depending on the user's emotional state. For example, if the user is stressed, it presents information using a blue background and soft font.

[1557] User role:

[1558] Users can view the displayed discussions and provide feedback, which is then sent back to the server, where the emotion engine records the user's emotional state. The server uses this feedback data to improve the system's performance and the quality of information provided.

[1559] Specific examples

[1560] Example 1: COVID-19 discussion:

[1561] The server collects official announcements from public institutions, related academic papers, and press conference articles from major news sites. It cross-references the reliability of the collected data and selects only the most up-to-date and reliable information. The server uses natural language processing algorithms to perform topic modeling, keyword extraction, and sentiment analysis to generate multifaceted discussions such as "medical opinions on the effectiveness of vaccines," "opinions on government lockdown policies," and "economic impacts."

[1562] The server sends the generated discussion in JSON format to the user's device, which then visually displays the information according to the user's emotional state and presents it in a calm tone to reduce anxiety. For example, if the user is stressed, a blue background and soft font are used.

[1563] Example prompt sentence:

[1564] "Collect the latest, reliable information on COVID-19 and generate multifaceted discussions. If users are feeling anxious, focus on providing information in a calm tone."

[1565] This system allows users to improve their information literacy by viewing reliable and multifaceted discussions, and also reduces stress by providing information adapted to their emotional state.

[1566] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1567] Step 1:

[1568] The server collects data from reliable sources.

[1569] Input: Official APIs from public institutions, databases of academic papers, RSS feeds from major news sites

[1570] Data processing: Send API requests and extract the required information using a web scraping tool (such as Beautiful Soup or Scrapy).

[1571] Output: Raw collected data (e.g., latest case counts, text of academic papers, news articles)

[1572] Step 2:

[1573] The server evaluates the reliability of the collected data.

[1574] Input: Raw data collected

[1575] Data calculation: Perform cross-referencing and analyze meta-information such as data source, author, publication date, etc. Calculate reliability scores and filter out data with low scores.

[1576] Output: Highly reliable data (data with a reliability score of 50 or higher)

[1577] Step 3:

[1578] The server analyzes the data with high reliability using natural language processing algorithms.

[1579] Input: Reliable data

[1580] Data Computation: We use the Gensim library for topic modeling to extract major themes, NLTK for keyword extraction, and VADER for sentiment analysis to assess the emotional tone of the text.

[1581] Output: Analysis information (extracted topics, keywords, emotional tone)

[1582] Step 4:

[1583] The server generates a discussion based on the analysis results.

[1584] Input: Analysis information

[1585] Data Computation: Using generative AI models (e.g., GPT-3), we generate fair and multifaceted arguments from the analysis results, generating text that integrates positive, negative, and neutral views.

[1586] Output: Generated discussion (text data in sentence format)

[1587] Step 5:

[1588] The server transmits the generated discussion to the user's terminal.

[1589] Input: Generated arguments

[1590] Data processing: The generated discussion information is encoded in JSON format and sent to the user's device using a RESTful API.

[1591] Output: JSON formatted discussion data

[1592] Step 6:

[1593] The terminal visually displays the received discussion data.

[1594] Input: JSON format discussion data

[1595] Data Calculation: Parse the data using JavaScript and display it visually using HTML and CSS, adjusting font size, color, and layout depending on the user's emotional state.

[1596] Output: A visual representation of the argument (information presented to the user)

[1597] Step 7:

[1598] The terminal uses an emotion engine to recognize the user's emotions.

[1599] Input: User's facial expression (via camera), voice data (via microphone)

[1600] Data calculation: Analyze facial expressions with OpenCV and voice with Google Cloud Speech-to-Text API to determine the user's emotional state.

[1601] Output: User's emotional state (e.g., anxiety, stress)

[1602] Step 8:

[1603] The user provides feedback through the terminal.

[1604] Input: User feedback (text input)

[1605] Data processing: Collected feedback and emotional states are stored and sent to the server.

[1606] Output: Stored feedback data

[1607] Step 9:

[1608] The server optimizes the system based on the feedback information.

[1609] Input: User feedback data

[1610] Data computation: Using machine learning algorithms to analyze feedback and identify areas for system improvement.

[1611] Output: Improved system parameters (improving the quality of information provided next time)

[1612] (Application example 2)

[1613] 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."

[1614] While conventional systems can provide information from reliable sources, they do not take into account the provision of information or feedback according to the user's emotional state. As a result, users do not receive the information they need appropriately, making it difficult to increase satisfaction. In particular, inappropriate information may be provided to users who are feeling stressed or anxious, so there is a need to improve the user experience. To address this issue, it is necessary not only to provide reliable information, but also to adjust the content of the information according to the user's emotional state.

[1615] 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.

[1616] In this invention, the server includes means for collecting data from reliable information sources, means for evaluating the reliability of the collected data, means for analyzing the collected data using a natural language processing algorithm, means for generating discussions based on the analysis results, means for transmitting the generated discussions to a user's terminal, means for displaying the generated discussions on the user's terminal, means for recognizing the user's emotions, means for recommending products and services based on the user's emotional state, and means for adjusting display information according to the emotional state. This not only allows the user to obtain reliable information, but also enables the provision of information adapted to the user's emotional state, thereby improving the user experience.

[1617] A "reliable source" generally refers to a place that provides accurate and trustworthy information, such as official announcements from public institutions, academic papers, and official corporate positions.

[1618] "Data collection methods" refers to technologies for obtaining information from online databases through API requests, or for collecting necessary information from the Internet using web scraping, etc.

[1619] "Reliability assessment method" refers to a technology that cross-references the source of collected data and calculates its reliability score to eliminate unreliable data.

[1620] "Natural language processing algorithm" refers to a technology that uses techniques such as topic modeling, keyword extraction, and sentiment analysis to analyze the structure and meaning of text data and extract important information.

[1621] "Discussion generation means" refers to technology that extracts a balanced mix of positive, negative, and neutral views from data analyzed using natural language processing, creating multifaceted discussions from a fair perspective.

[1622] "Transmission means" refers to the technology that encodes the generated discussion information in JSON format and transmits the data to the user's device using a RESTful API.

[1623] "Display means" refers to technology that analyzes the discussion data received by the user's terminal and visually presents the information in a format that is easy for the user to understand.

[1624] "Emotion recognition means" refers to technology that analyzes a user's facial expressions, voice, input data, etc. to identify the user's current emotional state.

[1625] "Recommendation means" refers to technology that selects appropriate products and services based on the user's emotional state and suggests them to the user.

[1626] "Information adjustment means" refers to technology that adjusts the tone and content of information according to the user's emotional state, providing information to the user in a more appropriate form.

[1627] System Overview

[1628] The system for implementing this invention collects data from reliable information sources, analyzes that data, and generates multifaceted discussions. It can also recognize the user's emotions and provide information and recommend products according to their emotional state. This system is primarily composed of three elements: a server, a terminal, and a user.

[1629] Hardware and software used

[1630] Hardware:

[1631] Camera: Used to recognize the user's facial expressions

[1632] High-performance PC: Used for image analysis and data analysis

[1633] Smartphone or tablet: Used to display information to the user

[1634] software:

[1635] facial_recognition: A library for analyzing customer facial expressions

[1636] sentiment_analysis: A library for analyzing the emotional tone of collected data

[1637] requests: A library for sending HTTP requests to retrieve data from an API.

[1638] Natural language processing algorithms: used to analyze collected data and extract key information (e.g., topic modeling, keyword extraction, sentiment analysis)

[1639] Detailed explanation of the process

[1640] 1. Data Collection:

[1641] The server collects data from reliable sources, such as official announcements from public institutions, academic papers, and official company statements, using API requests and web scraping techniques.

[1642] 2. Reliability assessment:

[1643] The server evaluates the reliability of the collected data through cross-referencing and calculates a reliability score, at which point unreliable data is eliminated.

[1644] 3. Natural Language Processing Analysis:

[1645] The server analyzes the data using natural language processing algorithms to extract key information through topic modeling, keyword extraction, and sentiment analysis.

[1646] 4. Discussion Generation:

[1647] The server generates multifaceted discussions based on the analysis results, providing fair information by integrating positive, negative, and neutral viewpoints in a balanced manner.

[1648] 5. Submitting and Viewing Discussions:

[1649] The server sends the generated discussion to the user's device, which analyzes the received discussion and visually displays it. The display content is adjusted according to the user's emotional state.

[1650] 6. Emotion recognition:

[1651] The device recognizes emotions by analyzing the user's facial expressions, voice, and input data, thereby identifying the user's current emotional state.

[1652] 7. Recommendations based on emotional state:

[1653] The device will recommend appropriate products and services based on the user's emotional state, for example, if the user is under stress, it will suggest products that have a relaxing effect.

[1654] Specific example explanation

[1655] For example, if a customer enters a store and the emotion recognition engine detects that the customer looks a little tired, the emotion score will be found to be 0.2 or less, and based on that result, the following prompt sentence can be input into the generative AI model:

[1656] Example prompt sentence:

[1657] Please provide a list of relaxation products. I would like to suggest products that will help my customers if they are tired.

[1658] This system not only provides users with multifaceted discussions based on reliable data, but also allows them to receive information and product recommendations that are suited to their emotional state, thereby improving the user experience.

[1659] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1660] Step 1:

[1661] The server collects data from reliable sources. Specifically, the server sends API requests or uses web scraping technology to obtain the necessary information from official announcements from public institutions, academic papers, official corporate statements, etc. This allows reliable data to be input into the server.

[1662] Step 2:

[1663] The server evaluates the reliability of the collected data. Specifically, it cross-references the origin of the collected data and calculates a reliability score to eliminate data with low reliability. This process outputs data that is evaluated as highly reliable.

[1664] Step 3:

[1665] The server applies natural language processing (NLP) algorithms to the data that has been evaluated as highly reliable. Specifically, it performs topic modeling, keyword extraction, and sentiment analysis to extract important information from the text data. This generates analyzed data that is output to the server.

[1666] Step 4:

[1667] The server generates a multifaceted discussion based on the analysis results. Specifically, it extracts a balanced mix of positive, negative, and neutral views, creating a multifaceted discussion from a fair perspective. The generated discussion is then output from the server.

[1668] Step 5:

[1669] The server sends the generated discussion to the user's device. Specifically, it encodes the generated discussion information in JSON format and sends the data to the user's device using a RESTful API. This transfers the discussion data from the server to the device.

[1670] Step 6:

[1671] The terminal analyzes the received discussion data and displays it to the user. Specifically, the analyzed discussion data is visually displayed and presented in a format that is easy for the user to understand, allowing the user to access the discussion information.

[1672] Step 7:

[1673] The device recognizes the user's emotions. Specifically, it analyzes the user's facial expressions, voice, and input data to identify the user's current emotional state. This information is then output to the device.

[1674] Step 8:

[1675] The device recommends products and services based on the user's emotional state. Specifically, it selects appropriate products and services according to the user's emotional state and proposes them to the user. This provides the user with optimal recommendation information.

[1676] Step 9:

[1677] The device adjusts the displayed information according to the user's emotional state, for example, presenting information in a calmer tone to a user who is under stress, thereby improving the user experience.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1683] 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.

[1684] 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).

[1685] 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.

[1686] 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."

[1687] 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.

[1688] 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).

[1689] 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.

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] The following is further disclosed regarding the above embodiment.

[1700] (Claim 1)

[1701] A means of collecting data from reliable sources;

[1702] a means of assessing the reliability of the collected data;

[1703] means for analyzing the collected data using natural language processing algorithms;

[1704] a means for generating arguments based on the analysis results;

[1705] A means for transmitting the generated discussion to a user's terminal;

[1706] A means to display discussions generated on the user's device

[1707] A system including:

[1708] (Claim 2)

[1709] The system of claim 1, wherein the reliability of the collected data is evaluated by cross-referencing.

[1710] (Claim 3)

[1711] The system according to claim 1, wherein the system generates a discussion by integrating opinions and views from different perspectives based on the analysis results.

[1712] "Example 1"

[1713] (Claim 1)

[1714] A means of collecting data from reliable sources;

[1715] a means of cross-referencing and assessing the reliability of the collected data;

[1716] means for analyzing the collected data using natural language processing algorithms;

[1717] A means of generating discussion by integrating opinions and views from different perspectives based on the analysis results;

[1718] A means to construct multifaceted discussions in natural sentences using generative AI models,

[1719] A means for transmitting the generated discussion to a user's terminal;

[1720] A means to display received discussions on the user's device and collect feedback from the user

[1721] A system including:

[1722] (Claim 2)

[1723] The system of claim 1, wherein the reliability of the collected data is evaluated by cross-referencing.

[1724] (Claim 3)

[1725] The system of claim 1 generates a discussion by integrating opinions and views from different perspectives based on the analysis results, and constructs the discussion in natural-sounding sentences using a generative AI model.

[1726] "Application Example 1"

[1727] (Claim 1)

[1728] A means of collecting data from reliable sources;

[1729] a means of assessing the reliability of the collected data;

[1730] means for analyzing the collected data using natural language processing algorithms;

[1731] a means for generating arguments based on the analysis results;

[1732] A means for transmitting the generated discussion to a user's terminal;

[1733] a means for displaying the generated discussion on a user's device and receiving feedback;

[1734] A means of analyzing user feedback and using it to improve the system;

[1735] A system including:

[1736] (Claim 2)

[1737] The system of claim 1, wherein the reliability of the collected data is evaluated by cross-referencing.

[1738] (Claim 3)

[1739] The system according to claim 1, wherein the system generates a discussion by integrating opinions and views from different perspectives based on the analysis results.

[1740] "Example 2: Combining Emotion Engines"

[1741] (Claim 1)

[1742] A means of collecting data from reliable sources;

[1743] a means of assessing the reliability of the collected data;

[1744] means for analyzing the collected data using natural language processing algorithms;

[1745] a means for generating arguments based on the analysis results;

[1746] A means for transmitting the generated discussion to a user's terminal;

[1747] means for displaying the discussion generated on the user's terminal;

[1748] means for recognizing a user's emotion;

[1749] means for displaying information in a manner that corresponds to the emotional state of the user;

[1750] A means of gathering user feedback and optimizing the system

[1751] A system including:

[1752] (Claim 2)

[1753] 10. The system of claim 1, further comprising means for cross-referencing and evaluating the reliability of the collected data to calculate a reliability score.

[1754] (Claim 3)

[1755] The system of claim 1 further includes a means for generating a multifaceted discussion by integrating opinions and views from different perspectives based on the analysis results, and providing information with an unbiased perspective using a generative AI model.

[1756] "Application example 2 when combining emotion engines"

[1757] (Claim 1)

[1758] A means of collecting data from reliable sources;

[1759] a means of assessing the reliability of the collected data;

[1760] means for analyzing the collected data using natural language processing algorithms;

[1761] a means for generating arguments based on the analysis results;

[1762] A means for transmitting the generated discussion to a user's terminal;

[1763] means for displaying the discussion generated on the user's terminal;

[1764] means for recognizing a user's emotion;

[1765] a means for recommending products and services based on the emotional state of a user;

[1766] A means of adjusting displayed information according to emotional state

[1767] A system including:

[1768] (Claim 2)

[1769] The system of claim 1, wherein the reliability of the collected data is evaluated by cross-referencing.

[1770] (Claim 3)

[1771] The system according to claim 1, wherein the system generates a discussion by integrating opinions and views from different perspectives based on the analysis results. [Explanation of symbols]

[1772] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data from reliable sources; a means of assessing the reliability of the collected data; means for analyzing the collected data using natural language processing algorithms; a means for generating arguments based on the analysis results; A means for transmitting the generated discussion to a user's terminal; A means to display discussions generated on the user's device A system including:

2. The system of claim 1, wherein the reliability of the collected data is evaluated by cross-referencing.

3. The system according to claim 1, wherein the system generates a discussion by integrating opinions and views from different perspectives based on the analysis results.

Images