system

Abstract

We provide the system. [Solution] A means of automatically obtaining data from internet information sources, Means for preprocessing the acquired data and converting it into an analyzable format, A means of inputting preprocessed data into a generative model and analyzing its relationships, A means for generating visual data based on the results of the analysis, A means for outputting the visual data via a terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Cutting off the relationship with anti-social forces in a company is extremely important as compliance with laws and regulations and social responsibility. However, the current checking methods for this mainly rely on proper nouns, so there are problems of inaccuracy and requiring a great deal of labor. Especially for overseas transactions, language barriers and lack of information are obstacles, and improvements are required in both the accuracy and efficiency of the checks.

Means for Solving the Problems

[0005] This invention provides a means for automatically acquiring data from internet information sources, preprocessing it, and converting it into an analyzable format. It also inputs the preprocessed data into a generative model to automatically analyze its relevance to anti-social forces. Based on this analysis, it generates visual data and outputs it via a terminal. Furthermore, by providing means for evaluating and ranking the strength of the relevance obtained using the generative model, and means for collecting new data and re-analyzing it based on user feedback, the invention improves the accuracy and efficiency of severing ties with anti-social forces.

[0006] "Internet information sources" refer to resources that provide a variety of data accessible online, such as news articles, official company announcements, social media posts, and legal databases.

[0007] "Methods of automatic acquisition" refer to technologies that collect necessary data from the internet using programs without human intervention, and typically involve using web scraping or API access.

[0008] "Preprocessing" refers to the process of converting collected raw data into an analyzable format, and specifically includes data cleansing and formatting standardization.

[0009] "Analyzable format" refers to a state in which data has a specific structure or format necessary for analysis, and usually refers to data that has been formatted as text or numerical data.

[0010] A "generative model" is a computer model equipped with algorithms that generate relationships and patterns from given data, and it particularly utilizes natural language processing and machine learning techniques.

[0011] "Methods for analyzing relationships" refer to the process of calculating the relationships between individuals and organizations based on input data, and evaluating their strength and characteristics.

[0012] "Visual data" refers to information that visually represents the results of analysis using diagrams, graphs, etc., with the aim of enabling users to understand it intuitively.

[0013] "Means of outputting via a terminal" refers to technologies for displaying analyzed data on the display of a computer or device used by the user.

[0014] "Methods for evaluating and ranking the strength of relevance" refers to the process of quantifying the strength of connections between specific elements in data analyzed by a generative model, and then determining priorities based on that.

[0015] "User feedback" is part of a process that involves collecting user reactions and opinions on the system's output, which allows for further improvements and reanalysis. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to an automated checking system for severing ties with anti-social forces, and a detailed embodiment thereof is shown below.

[0038] This system automatically collects necessary data from internet sources via a server. The collected data includes news articles, official company announcements, social media posts, and legal databases. The server periodically retrieves this information, enabling analysis based on the latest information.

[0039] The acquired data is preprocessed by the server and converted into an analyzable format. Preprocessing includes data cleansing, noise reduction, and formatting standardization. This makes the data suitable for input into generative models, improving the accuracy of the analysis.

[0040] The server inputs pre-processed data into a generative model to analyze its connections to anti-social forces. The generative model utilizes a multi-layered neural network to automatically detect potential relationships within the data. This process reveals the extent to which companies and individuals are associated with anti-social forces.

[0041] The analysis results are generated as visual data by the server and sent to the user's terminal. This visual data includes a relevance network diagram, which allows the user to quickly grasp the risks. The network diagram represents the relationships between individuals and organizations using dots and lines, and is displayed with key relationships highlighted.

[0042] Furthermore, the server uses a generative model to quantify and rank the strength of relationships. This makes it easy for users to understand which relationships require particular attention.

[0043] Users can view information via their devices and provide feedback to the server. This feedback triggers system improvements and reanalysis, and the server keeps itself constantly up-to-date by collecting and analyzing new data.

[0044] As a concrete example, when a user checks the directors of a certain company, they enter the company name into the system, and the server collects and analyzes relevant information, displaying a network diagram on the terminal that shows potential connections with anti-social forces. This allows the user to quickly identify problematic relationships and take appropriate action.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server collects data from information sources on the internet. Here, the server uses web scraping and API access to automatically retrieve necessary data from news articles, official company announcements, social media posts, and legal databases.

[0048] Step 2:

[0049] The server preprocesses the collected data. Preprocessing involves data cleansing, noise removal, formatting standardization, and conversion into an analyzable format.

[0050] Step 3:

[0051] The server inputs pre-processed data into a generative model. The generative model uses a multi-layer neural network to automatically analyze potential relationships and connections within the data.

[0052] Step 4:

[0053] The server converts the analysis results into visual data. Specifically, it generates a relationship network diagram, visually representing the relationships between individuals and organizations using points and lines.

[0054] Step 5:

[0055] The server generates visual data and sends it to the user's terminal. The terminal receives this data and displays it on the user interface, allowing the user to intuitively understand the risks.

[0056] Step 6:

[0057] Users review the information displayed on their devices and provide feedback to the server as needed. This feedback is used to improve the system and trigger new data collection.

[0058] Step 7:

[0059] The server collects new data and re-analyzes it based on user feedback. This ensures the system always handles the latest information and can continuously check for risks related to anti-social forces quickly and accurately.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In modern society, it is extremely important to quickly identify and sever ties with anti-social forces, but manual verification is time-consuming and labor-intensive, making an efficient automated system necessary.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for automatically acquiring information from a network information collection using an information gathering device, means for organizing the acquired information and converting it into an analyzable format, and means for inputting the organized information into a generating AI model to analyze relationships. This makes it possible to automatically and efficiently detect relationships with anti-social forces and provide that information quickly.

[0065] An "information gathering device" is a mechanism for automatically acquiring necessary information from a network.

[0066] An "information collection" is a group of data consisting of various sources of information that exist on the internet, such as news articles, official announcements, social media posts, and legal databases.

[0067] "Organization" is the process of converting acquired information into an analyzable format by cleansing, removing noise, and standardizing the format.

[0068] A "generative AI model" is an analytical algorithm that uses a multi-layer neural network to detect latent relationships within data.

[0069] "Visual information" refers to information that visually represents analysis results and outputs them as graphs or network diagrams.

[0070] A "computer device" is a terminal device that allows users to visually confirm the analysis results.

[0071] This invention is an automated checking system for severing ties with anti-social forces. This system primarily consists of server, terminal, and user components.

[0072] The server automatically retrieves data from information collections on the internet using information gathering devices. The server efficiently collects target information from sources such as news articles, social media posts, and legal databases using tools like web crawlers. Specifically, the Python BeautifulSoup library is used for this purpose.

[0073] The acquired information is organized by the server and input into the generative AI model. The server cleanses the data using regular expressions and NLP tools to remove noise and standardize the format. This transforms the data into a format suitable for analysis. The generative AI model utilizes deep learning libraries such as TENSORFLOW® and PyTorch, and uses a multi-layer neural network to analyze latent relationships in the data.

[0074] The analysis results are generated as visual information by the server and sent to the user's terminal. This visual information is represented as a relationship network diagram using NetworkX or Matplotlib. Through this, users can quickly grasp the risks. In addition, the generating AI model quantifies the strength of relationships and provides ranked results. This allows users to understand relationships that require particular attention.

[0075] Users can view analysis results via their devices and send feedback to the system. This feedback is processed on the server and used to collect new information and perform further analysis, ensuring the system is always up-to-date.

[0076] As a concrete example, when checking a company's directors, the user might enter a prompt such as, "Please check the connections between the directors of Company XYZ and anti-social forces." In response to this request, the server collects and analyzes data and provides the user's terminal with a network diagram visually showing the relationships. This allows the user to identify problematic relationships and quickly decide on appropriate actions.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server automatically acquires data from information collections on the network using information gathering devices. Specifically, the server uses web crawlers to collect target information from news articles, social media posts, and legal databases. The input is unstructured data from the internet, and the output is raw data stored within the server.

[0080] Step 2:

[0081] The server organizes the acquired raw data. This process involves removing unnecessary text using regular expressions and tokenizing and structuring the data using NLP tools. The input is the raw data obtained in step 1, and the output is clean data that can be analyzed.

[0082] Step 3:

[0083] The server inputs clean data into a generating AI model to analyze relationships. Specifically, it uses a multi-layer neural network with TensorFlow to perform calculations that detect latent relationships in the data. The input is clean data, and the output is a relevance score and relationship determination as the analysis result.

[0084] Step 4:

[0085] The server generates visual information based on the analysis results. It visually displays the analysis results by drawing a relevance network diagram using NetworkX or Matplotlib. The input is the analysis results from step 3, and the output is the visualized relevance network diagram.

[0086] Step 5:

[0087] The server quantifies the strength of relevance to the generated visual information and ranks it. It evaluates the relationships using the score of the generating AI model and sorts them in order of importance. The input is the visual information from step 4, and the output is the ranked relationship information.

[0088] Step 6:

[0089] Users view visual information via their terminals and send feedback to the server. Based on network diagrams, users can evaluate relationships with antisocial forces and send suggestions for improvement and feedback to the system. Inputs are visual information and user feedback, while outputs are instructions for system updates or reanalysis that reflect the feedback.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] In modern society, the ability of companies and individuals to quickly assess the trustworthiness of their relationships with third parties is increasingly important from a risk management perspective. However, the sheer volume and fragmentation of information presents challenges, as manual checks require considerable effort and time. Furthermore, identifying potential connections with anti-social forces requires sophisticated analytical capabilities, but conventional methods often lack sufficient accuracy.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relationships, means for generating visual data and creating a visual relationship diagram based on the results of the analysis, means for outputting the visual data and visual relationship diagram via a communication device and providing a user interface that allows for the evaluation of relationships with third parties, means for evaluating the strength of the relationships analyzed by the generative model, ranking them, and identifying high-risk relationships, and means for receiving responses from users, collecting and re-analyzing new information, and updating based on the latest situation. This enables companies and individuals to efficiently evaluate their relationships with third parties, quickly grasp potential risks, and make reliable decisions.

[0095] "Internet information sources" refer to online platforms where diverse information is aggregated, such as websites, news feeds, and social media.

[0096] "Automatically acquiring data" refers to the process by which programs or systems collect information from the internet without human intervention.

[0097] "Preprocessing" refers to a series of processes performed to convert acquired data into a format that can be analyzed, and mainly includes data cleansing and formatting standardization.

[0098] A "generative model" is a pre-trained algorithm that uses a neural network to analyze data and reveal underlying patterns and relationships.

[0099] "Analyzing relationships" is the process of analyzing the relationships and correlations between elements using acquired and pre-processed data.

[0100] "Visual data" refers to information that visualizes analysis results so that users can intuitively understand them, and it mainly takes the form of graphs and charts.

[0101] A "visual relationship diagram" is a diagram that uses dots and lines to show the relationships between individual elements or subjects, and it focuses on displaying particularly important relationships.

[0102] A "communication device" is a device used for sending and receiving data, and primarily has the function of transmitting information via a network.

[0103] A "user interface" is an interface that provides screens and operational elements for a user to interact with a system, enabling the display and input of information.

[0104] "Evaluating the strength of relevance and ranking it" is the process of quantifying the importance and reliability of each relationship obtained through analysis and determining its priority.

[0105] "Receiving responses from users" means that the system accepts feedback and additional information input from users.

[0106] "Collecting and reanalyzing new information" refers to the process of gathering new data as needed based on feedback, and then processing and analyzing that information again.

[0107] The system for implementing this invention is particularly useful for enabling companies and individuals to efficiently evaluate their relationships with third parties. The server basically has the following main functions:

[0108] First, data is automatically retrieved. The server uses a Python program to collect data from multiple sources on the internet via an API. The retrieved information comes from a wide range of sources, including news sites, social media, and official announcements.

[0109] Next, preprocessing is performed. Data cleansing is carried out on the server using the Pandas library. This is a process that removes noise from the data and converts it into a standardized, analyzable format.

[0110] The pre-processed data is then input into a generative AI model. A model consisting of a multi-layered neural network using PyTorch is used to detect latent relationships in the data.

[0111] The analysis results are generated as visual data, and a visual relationship diagram is created. Using the D3.js library, it is visualized as an interactive network graph.

[0112] This visualized information is sent to the user's terminal via a communication device. The user can then review the information through a smartphone application with an intuitive user interface and evaluate their relationship with a third party.

[0113] For example, when a company evaluates the potential risks of a new business partner, the user enters the business partner's name into the system. The server collects relevant information, analyzes it using an AI model, and generates visual data. This allows the user to quickly grasp the risks of relationships with third parties and make reliable business decisions.

[0114] An example of a prompt to input into the generating AI model is, "Please check for any ties between our new business partner, XYZ Corporation, and anti-social forces."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server automatically retrieves data from internet sources. Specifically, it uses a Python program and APIs to collect information from news sites and social media. The input is the URL or API key of the data to be collected, and the output is raw text data.

[0118] Step 2:

[0119] The server preprocesses the acquired raw data. Using the Pandas library, it performs data cleansing, removing unwanted noise and standardizing the format. This process transforms the data into a parseable format. The input is raw text data, and the output is cleansed text data.

[0120] Step 3:

[0121] The server inputs pre-processed data into a generating AI model. A PyTorch-based multilayer neural network analyzes this data and detects potential associations with antisocial forces. The input is cleansed text data, and the output is the analyzed association score.

[0122] Step 4:

[0123] The server generates a visual relationship diagram based on the analysis results. It utilizes the D3.js library to visualize the relationships as a network graph connecting points and lines. The input is the analyzed relationship score, and the output is HTML and related scripts representing the visual relationship diagram.

[0124] Step 5:

[0125] The terminal receives visual data sent from the server and displays it on the user interface. Through the terminal, the user can evaluate relationships with third parties. The input is visual relationship diagram data from the server, and the output is a graph displayed on the terminal's interface.

[0126] Step 6:

[0127] Based on the displayed relationship diagram, the user provides feedback to the system to make trading decisions and evaluate relationship risks. The user enters additional views and comments in the input fields. The input is the user's feedback, and the output is the user response data sent to the server.

[0128] Step 7:

[0129] The server receives feedback from users and collects and re-analyzes new information. This ensures the system constantly updates and provides users with information based on the latest situation. Input is user feedback data, and output is updated analysis data and visual relationship diagrams.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention combines an automated checking system for severing ties with anti-social forces with an emotion engine that recognizes the user's emotions. A detailed embodiment is shown below.

[0132] This system automatically collects information from data sources on the internet. This information includes news articles, official company announcements, social media posts, and legal databases. The collected data is regularly updated to enable analysis based on the latest trends.

[0133] The acquired data is preprocessed by the server and converted into an analyzable format. The preprocessing process includes data cleansing, noise reduction, and formatting standardization. This optimizes the data for input to generative models.

[0134] Next, the server inputs the preprocessed data into a generative model, which analyzes the relationships within the data. The generative model uses a multi-layer neural network to process the data and automatically detect potential connections with antisocial forces.

[0135] The analysis results are generated as visual data by the server and sent to the user's terminal. The terminal receives this data and displays it on the user interface. The visual data includes a correlation network diagram, which allows the user to intuitively grasp the risks.

[0136] Furthermore, the system incorporates an emotion engine that analyzes user feedback to infer user emotions. Based on this emotion recognition, the way information is presented is modified. For example, if a user is highly anxious, the information presentation is adjusted to be more detailed and easier to understand. The emotion engine can also dynamically adjust the priority of presented content by evaluating the strength of relevance based on user reactions.

[0137] As a concrete example, when conducting an investigation of a company's board of directors, the user enters the company name into the system, and the server collects and analyzes relevant information. When the resulting network diagram is displayed on the user's terminal, the user's reactions are monitored, and if there are areas of particular interest, for example, the emotion engine highlights that information or presents additional information. In this way, the system is capable of flexibly presenting information while taking the user's emotions into consideration.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server automatically collects data from internet sources. Here, the server uses API access and web scraping to target news articles, company reports, and social media posts to obtain the necessary information.

[0141] Step 2:

[0142] The server preprocesses the collected data. Specifically, it performs tasks such as denoising text, standardizing formats, and translating languages, converting the data into a format that can be input into the analysis model.

[0143] Step 3:

[0144] The server inputs pre-processed data into a generative model and performs relevance analysis. The generative model uses proper nouns and contextual information within the data to detect relationship patterns and identify connections to antisocial forces.

[0145] Step 4:

[0146] The server generates a visual network diagram based on the analysis results. The network diagram visually displays the relationships between individuals and organizations, and elements of the diagram are highlighted according to the strength of their relationships.

[0147] Step 5:

[0148] The server generates a visual network diagram and sends it to the terminal. The terminal receives this and displays it in its user interface, allowing the user to intuitively understand the situation.

[0149] Step 6:

[0150] Users can review the network diagram displayed on their device and provide feedback to the server. They can also request additional information on specific points of interest.

[0151] Step 7:

[0152] The server evaluates user feedback and analyzes the user's emotional state using an emotion engine. The emotion engine feeds back the user's response as data and adjusts the output accordingly.

[0153] Step 8:

[0154] The server dynamically adjusts how information is presented based on the sentiment analysis results. For example, if user anxiety is detected, the server will present information in more detail and modify the output to provide a sense of reassurance.

[0155] Step 9:

[0156] By considering newly collected data and reanalysis results from the server, and updating information that focuses on specific relevances that users are concerned about, the system ensures that users always receive up-to-date and reliable information.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] Currently, there is a lack of efficient means to acquire information about organizations and individuals suspected of having ties to anti-social forces and to present it to users in a visually and emotionally appropriate manner. This results in the problem of cumbersome and non-intuitive risk assessment. Furthermore, there is the challenge of flexibly adjusting information presentation based on user reactions and feedback.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes means for automatically collecting data from information sources on an information storage device, means for preprocessing the collected data and converting it into an analyzable format, and means for dynamically adjusting the presented information through sentiment analysis. This makes it possible to present information regarding antisocial risks to the user in an effective and adaptive manner.

[0162] An "information storage device" is a device used to store and manage various types of data, and servers and cloud storage fall into this category.

[0163] "Means of collection" refers to a device or program for automatically retrieving data that matches a specific purpose from an information source on an information storage device.

[0164] "Preprocessing" is the process of removing unnecessary information and standardizing the format of collected data so that it is suitable for analysis.

[0165] A "model" is a mathematical or statistical method used to analyze the relationships and characteristics of data, and includes generative AI models, among others.

[0166] "Visual information" refers to data that is visually represented in the form of diagrams, graphs, etc., to make the analysis results easier to understand.

[0167] An "output device" is a hardware device such as a display or tablet used to present information transmitted from a server to the user.

[0168] "Emotion analysis" is a technology that infers a user's emotional state from their input and responses, and dynamically adjusts information based on the results.

[0169] "Means of dynamic adjustment" refers to a function that changes the way information is presented and the content of that information in real time, based on analysis results and user responses.

[0170] This invention comprises a system having a server, a terminal, and a user interface. This system automatically evaluates relationships with anti-social forces and provides intuitive and emotionally resonant information.

[0171] The server uses an internet-connected storage device to collect data. Specifically, it retrieves articles using news APIs and collects publicly available information using web crawlers. It also uses social media APIs to retrieve relevant posts, thereby improving the comprehensiveness of the information.

[0172] The collected data is preprocessed on the server. This processing includes database unification, cleansing of unnecessary information, and formatting standardization. The preprocessed data is then input into a generative AI model using a multi-layer neural network for correlation analysis.

[0173] The resulting visual information is constructed as network diagrams and graphs. The server transmits this visual information to an output device, which the terminal receives and presents to the user. The presented information is dynamically adjusted based on sentiment analysis to match the user's current emotional state.

[0174] Users can interactively manipulate information through their devices, and feedback from these interactions is sent back to the server. This feedback is analyzed by the system's emotion engine, and continuous adjustments are made to further refine the information presentation.

[0175] As a concrete example, if a user wants to perform a risk assessment of an organization, they would enter the organization's name into the system. A possible prompt might be, "I would like to obtain the latest information on the association of Organization X with anti-social forces." The server would then automatically collect relevant information and present the analysis results to the user. In this process, information would be highlighted or detailed information provided based on the user's responses, aiding in understanding the information.

[0176] This system allows users to quickly and accurately grasp risk information, which supports better decision-making.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The server collects data from publicly available information stored in an information storage device via an internet connection. The input is a prompt statement provided by the user, for example, "I would like to obtain the latest information on the association of Organization X with anti-social forces." Based on this, an automated crawler calls news APIs and social media APIs to retrieve relevant articles and posts. The output is a collection of the collected raw data.

[0180] Step 2:

[0181] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. At this stage, unnecessary information is cleansed and the data is converted into a unified format that can be parsed (such as JSON). Processing includes text normalization and deduplication. The output is a formatted, clean dataset.

[0182] Step 3:

[0183] The server inputs pre-processed data into a generating AI model and performs correlation analysis. The input is clean data that has undergone pre-processing. Using a multi-layer neural network, it analyzes the potential relationships and importance contained in the collected data and calculates correlation scores. The output is the analyzed correlation scores.

[0184] Step 4:

[0185] The server generates visual information based on the analysis results. The input is the relevance score obtained in step 3. Using a visualization library, it generates relevance network diagrams and graphs, and formats them into a user-friendly format. The output is visually formatted data.

[0186] Step 5:

[0187] The terminal displays visual information sent from the server on its user interface. The input is the visual data generated in step 4. The terminal uses the received data to display an interactive user interface, allowing the user to manipulate the network diagram. The output is the network diagram visually displayed on the screen.

[0188] Step 6:

[0189] The user reacts to information presented through the terminal and provides feedback. The input is the presented visual information. The user can select specific nodes or input responses in text. The terminal collects this feedback and sends it to the server. The output is the user's interaction data.

[0190] Step 7:

[0191] The server performs sentiment analysis based on user feedback and dynamically adjusts the information presentation. The input is the user interaction data obtained in step 6. Using the sentiment analysis engine, it infers the user's emotional state and decides whether to highlight information or provide additional information based on the results. The output is the adjusted information display settings.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] The challenge is to enable more effective and user-friendly security management by automatically detecting relationships with anti-social forces, allowing users to intuitively understand the risks, and dynamically adjusting information presentation based on user emotions.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relevance, and means for monitoring user responses and automatically adjusting settings for prioritizing the display of information. This enables users to more effectively recognize risks and select appropriate responses.

[0197] An "automatic data acquisition method" is a mechanism for collecting necessary data from various information sources on the internet without user intervention.

[0198] A "preprocessing means" is a mechanism that performs processing to cleanse the acquired data and convert it into a format suitable for analysis.

[0199] A "generative model" is an algorithm, based on multilayer neural networks and other methods, used to analyze the relationships between input data.

[0200] A "visual data generation means" is a mechanism for converting analyzed data into a visually easy-to-understand format and presenting it.

[0201] A "user emotion analysis tool" is a mechanism that monitors user reactions to infer their emotional state and appropriately adjust the way information is presented.

[0202] An "information priority display adjustment mechanism" is a system that analyzes user interests and attention and dynamically sets the display priority of information according to its importance.

[0203] In the system implementing this invention, the server first automatically retrieves data from internet information sources. During this process, it efficiently collects relevant information using news article APIs and social networking service APIs. The retrieved data is then preprocessed by the server. This preprocessing includes using Python to cleanse the data and convert it into a parseable format.

[0204] The transformed data is analyzed by a generative model built with TensorFlow. This generative model, which uses a multi-layer neural network, has the ability to automatically detect connections to antisocial forces. The analysis results are generated as visual data by the server and sent to the user via the terminal. The visual data is provided in the form of network diagrams and other diagrams that show the connections.

[0205] Furthermore, the device utilizes Microsoft's Azure Text Analytics API to analyze user reactions and adaptively adjust information presentation based on those emotions. If the user's anxiety level is high, important information will be displayed in more detail, and actions such as adding suggested solutions will be taken.

[0206] As a concrete example, a company's security officer could use this system to investigate relationships with new business partners. When the officer enters the business partner's name, the server analyzes the relevant information and presents comprehensive visual data outlining the risks. During this process, if the user shows strong interest in specific information, that information is prioritized and highlighted.

[0207] An example of a prompt for a generative AI model is: "Collect the latest news articles about this company and analyze any associations with anti-social forces. Also, analyze the user's concerns and tailor the information presentation accordingly."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server automatically retrieves data from internet sources. When a user enters the name of a company or subject, the server calls news article APIs and social media APIs to collect relevant information. Based on this input, the server retrieves raw data such as news articles and social media posts.

[0211] Step 2:

[0212] The server preprocesses the acquired data. Specifically, it uses Python to cleanse the data and remove noise. It also performs text normalization to unify data in different formats. This results in outputting data in a parseable format suitable for generative models.

[0213] Step 3:

[0214] The server inputs preprocessed data into a generative model for analysis. The TensorFlow-based generative model utilizes a multi-layer neural network to extract connections to antisocial forces from the data. It analyzes the input, standardized data, determines whether a connection exists, and outputs the result.

[0215] Step 4:

[0216] The server generates the analyzed results as visual data and sends it to the terminal. Based on the analysis results, it creates intuitively understandable visual data such as network diagrams. The generated visual data is sent to the user's terminal.

[0217] Step 5:

[0218] The device uses Microsoft's Azure Text Analytics API to analyze user emotions. When a user responds to visual data, it extracts emotional indicators from their facial expressions and text input to evaluate the user's emotions, such as anxiety or reassurance. Based on these analysis results, the information presentation method is dynamically adjusted.

[0219] Step 6:

[0220] Based on user sentiment analysis results, the information displayed is adaptively changed. The device highlights more detailed explanations and additional information for information that the user is highly anxious about or interested in. This action prioritizes information that is important to the user, enabling appropriate responses according to the risk.

[0221] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0227] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0228] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0229] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0230] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0231] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0232] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0233] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0234] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0235] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0236] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0237] This invention relates to an automated checking system for severing ties with anti-social forces, and a detailed embodiment thereof is shown below.

[0238] This system automatically collects necessary data from internet sources via a server. The collected data includes news articles, official company announcements, social media posts, and legal databases. The server periodically retrieves this information, enabling analysis based on the latest information.

[0239] The acquired data is preprocessed by the server and converted into an analyzable format. Preprocessing includes data cleansing, noise reduction, and formatting standardization. This makes the data suitable for input into generative models, improving the accuracy of the analysis.

[0240] The server inputs pre-processed data into a generative model to analyze its connections to anti-social forces. The generative model utilizes a multi-layered neural network to automatically detect potential relationships within the data. This process reveals the extent to which companies and individuals are associated with anti-social forces.

[0241] The analysis results are generated as visual data by the server and sent to the user's terminal. This visual data includes a relevance network diagram, which allows the user to quickly grasp the risks. The network diagram represents the relationships between individuals and organizations using dots and lines, and is displayed with key relationships highlighted.

[0242] Furthermore, the server uses a generative model to quantify and rank the strength of relationships. This makes it easy for users to understand which relationships require particular attention.

[0243] Users can view information via their devices and provide feedback to the server. This feedback triggers system improvements and reanalysis, and the server keeps itself constantly up-to-date by collecting and analyzing new data.

[0244] As a concrete example, when a user checks the directors of a certain company, they enter the company name into the system, and the server collects and analyzes relevant information, displaying a network diagram on the terminal that shows potential connections with anti-social forces. This allows the user to quickly identify problematic relationships and take appropriate action.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The server collects data from information sources on the internet. Here, the server uses web scraping and API access to automatically retrieve necessary data from news articles, official company announcements, social media posts, and legal databases.

[0248] Step 2:

[0249] The server preprocesses the collected data. Preprocessing involves data cleansing, noise removal, formatting standardization, and conversion into an analyzable format.

[0250] Step 3:

[0251] The server inputs pre-processed data into a generative model. The generative model uses a multi-layer neural network to automatically analyze potential relationships and connections within the data.

[0252] Step 4:

[0253] The server converts the analysis results into visual data. Specifically, it generates a relationship network diagram, visually representing the relationships between individuals and organizations using points and lines.

[0254] Step 5:

[0255] The server generates visual data and sends it to the user's terminal. The terminal receives this data and displays it on the user interface, allowing the user to intuitively understand the risks.

[0256] Step 6:

[0257] Users review the information displayed on their devices and provide feedback to the server as needed. This feedback is used to improve the system and trigger new data collection.

[0258] Step 7:

[0259] The server collects new data and re-analyzes it based on user feedback. This ensures the system always handles the latest information and can continuously check for risks related to anti-social forces quickly and accurately.

[0260] (Example 1)

[0261] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0262] In modern society, it is extremely important to quickly identify and sever ties with anti-social forces, but manual verification is time-consuming and labor-intensive, making an efficient automated system necessary.

[0263] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0264] In this invention, the server includes means for automatically acquiring information from a network information collection using an information gathering device, means for organizing the acquired information and converting it into an analyzable format, and means for inputting the organized information into a generating AI model to analyze relationships. This makes it possible to automatically and efficiently detect relationships with anti-social forces and provide that information quickly.

[0265] An "information gathering device" is a mechanism for automatically acquiring necessary information from a network.

[0266] An "information collection" is a group of data consisting of various sources of information that exist on the internet, such as news articles, official announcements, social media posts, and legal databases.

[0267] "Organization" is the process of converting acquired information into an analyzable format by cleansing, removing noise, and standardizing the format.

[0268] A "generative AI model" is an analytical algorithm that uses a multi-layer neural network to detect latent relationships within data.

[0269] "Visual information" refers to information that visually represents analysis results and outputs them as graphs or network diagrams.

[0270] A "computer device" is a terminal device that allows users to visually confirm the analysis results.

[0271] This invention is an automated checking system for severing ties with anti-social forces. This system primarily consists of server, terminal, and user components.

[0272] The server automatically retrieves data from information collections on the internet using information gathering devices. The server efficiently collects target information from sources such as news articles, social media posts, and legal databases using tools like web crawlers. Specifically, the Python BeautifulSoup library is used for this purpose.

[0273] The acquired information is organized by the server and input into the generative AI model. The server cleanses the data using regular expressions and NLP tools to remove noise and standardize the format. This transforms the data into a format suitable for analysis. The generative AI model utilizes deep learning libraries such as TensorFlow and PyTorch, and uses multi-layer neural networks to analyze latent relationships in the data.

[0274] The analysis results are generated as visual information by the server and sent to the user's terminal. This visual information is represented as a relationship network diagram using NetworkX or Matplotlib. Through this, users can quickly grasp the risks. In addition, the generating AI model quantifies the strength of relationships and provides ranked results. This allows users to understand relationships that require particular attention.

[0275] Users can view analysis results via their devices and send feedback to the system. This feedback is processed on the server and used to collect new information and perform further analysis, ensuring the system is always up-to-date.

[0276] As a concrete example, when checking a company's directors, the user might enter a prompt such as, "Please check the connections between the directors of Company XYZ and anti-social forces." In response to this request, the server collects and analyzes data and provides the user's terminal with a network diagram visually showing the relationships. This allows the user to identify problematic relationships and quickly decide on appropriate actions.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The server automatically acquires data from information collections on the network using information gathering devices. Specifically, the server uses web crawlers to collect target information from news articles, social media posts, and legal databases. The input is unstructured data from the internet, and the output is raw data stored within the server.

[0280] Step 2:

[0281] The server sorts out the acquired raw data. In this process, it removes unnecessary text using regular expressions and tokenizes and structures the data using NLP tools. The input is the raw data obtained in step 1, and the output is analyzable clean data.

[0282] Step 3:

[0283] The server inputs the clean data into the generative AI model to analyze the relationships. Specifically, it performs operations to detect potential relationships in the data using a multi-layer neural network with TensorFlow. The input is the clean data, and the output is the relevance score and relationship determination as the analysis result.

[0284] Step 4:

[0285] The server generates visual information based on the analysis result. By using NetworkX and Matplotlib to draw a relevance network diagram, the analysis result is visually displayed. The input is the analysis result of step 3, and the output is the visualized relevance network diagram.

[0286] Step 5:

[0287] The server quantifies the generated visual information and the strength of the relevance and ranks them. It evaluates the relationships using the scores of the generative AI model and sorts them in the order that requires attention. The input is the visual information of step 4, and the output is the ranked relationship information.

[0288] Step 6:

[0289] The user checks the visual information via the terminal and sends feedback to the server. The user can evaluate the relationship with anti-social forces based on the network diagram and send improvement points and opinions to the system. The input is the visual information and the user's feedback, and the output is an instruction for system update or re-analysis that reflects the feedback.

[0290] (Application Example 1)

[0291] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0292] In modern society, the ability of companies and individuals to quickly assess the trustworthiness of their relationships with third parties is increasingly important from a risk management perspective. However, the sheer volume and fragmentation of information presents challenges, as manual checks require considerable effort and time. Furthermore, identifying potential connections with anti-social forces requires sophisticated analytical capabilities, but conventional methods often lack sufficient accuracy.

[0293] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0294] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relationships, means for generating visual data and creating a visual relationship diagram based on the results of the analysis, means for outputting the visual data and visual relationship diagram via a communication device and providing a user interface that allows for the evaluation of relationships with third parties, means for evaluating the strength of the relationships analyzed by the generative model, ranking them, and identifying high-risk relationships, and means for receiving responses from users, collecting and re-analyzing new information, and updating based on the latest situation. This enables companies and individuals to efficiently evaluate their relationships with third parties, quickly grasp potential risks, and make reliable decisions.

[0295] "Internet information sources" refer to online platforms where diverse information is aggregated, such as websites, news feeds, and social media.

[0296] "Automatically acquiring data" refers to the process by which programs or systems collect information from the internet without human intervention.

[0297] "Preprocessing" refers to a series of processes performed to convert acquired data into a format that can be analyzed, and mainly includes data cleansing and formatting standardization.

[0298] A "generative model" is a pre-trained algorithm that uses a neural network to analyze data and reveal underlying patterns and relationships.

[0299] "Analyzing relationships" is the process of analyzing the relationships and correlations between elements using acquired and pre-processed data.

[0300] "Visual data" refers to information that visualizes analysis results so that users can intuitively understand them, and it mainly takes the form of graphs and charts.

[0301] A "visual relationship diagram" is a diagram that uses dots and lines to show the relationships between individual elements or subjects, and it focuses on displaying particularly important relationships.

[0302] A "communication device" is a device used for sending and receiving data, and primarily has the function of transmitting information via a network.

[0303] A "user interface" is an interface that provides screens and operational elements for a user to interact with a system, enabling the display and input of information.

[0304] "Evaluating the strength of relevance and ranking it" is the process of quantifying the importance and reliability of each relationship obtained through analysis and determining its priority.

[0305] "Receiving responses from users" means that the system accepts feedback and additional information input from users.

[0306] "Performing new information collection and re-analysis" refers to a process of collecting new data as needed and reprocessing and analyzing information based on feedback.

[0307] The system for implementing this invention enables enterprises and individuals, in particular, to efficiently evaluate their relationships with third parties. The server basically has the following main functions.

[0308] First, data is automatically acquired. The server uses a Python program to collect data from multiple information sources on the Internet through an API. The acquired information covers a wide range, such as news sites, social media, and official announcements.

[0309] Next, preprocessing is performed. The Pandas library is utilized on the server to conduct data cleaning. This is a process of removing data noise, unifying the format, and converting it into an analyzable form.

[0310] After that, the preprocessed data is input into a generative AI model. A model composed of a multi-layer neural network using PyTorch is used to detect potential relationships in the data.

[0311] The analysis results are generated as visual data to create a visual relationship diagram. The D3.js library is utilized to visualize it as an interactive network graph.

[0312] This visualized information is sent to the user's terminal via a communication device. The user can view the information through a smartphone application with an intuitive user interface and evaluate the relationship with a third party.

[0313] For example, when a company evaluates the potential risks of a new business partner, the user enters the business partner's name into the system. The server collects relevant information, analyzes it using an AI model, and generates visual data. This allows the user to quickly grasp the risks of relationships with third parties and make reliable business decisions.

[0314] An example of a prompt to input into the generating AI model is, "Please check for any ties between our new business partner, XYZ Corporation, and anti-social forces."

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The server automatically retrieves data from internet sources. Specifically, it uses a Python program and APIs to collect information from news sites and social media. The input is the URL or API key of the data to be collected, and the output is raw text data.

[0318] Step 2:

[0319] The server preprocesses the acquired raw data. Using the Pandas library, it performs data cleansing, removing unwanted noise and standardizing the format. This process transforms the data into a parseable format. The input is raw text data, and the output is cleansed text data.

[0320] Step 3:

[0321] The server inputs pre-processed data into a generating AI model. A PyTorch-based multilayer neural network analyzes this data and detects potential associations with antisocial forces. The input is cleansed text data, and the output is the analyzed association score.

[0322] Step 4:

[0323] The server generates a visual relationship diagram based on the analysis results. It utilizes the D3.js library to visualize the relationships as a network graph connecting points and lines. The input is the analyzed relationship score, and the output is HTML and related scripts representing the visual relationship diagram.

[0324] Step 5:

[0325] The terminal receives visual data sent from the server and displays it on the user interface. Through the terminal, the user can evaluate relationships with third parties. The input is visual relationship diagram data from the server, and the output is a graph displayed on the terminal's interface.

[0326] Step 6:

[0327] Based on the displayed relationship diagram, the user provides feedback to the system to make trading decisions and evaluate relationship risks. The user enters additional views and comments in the input fields. The input is the user's feedback, and the output is the user response data sent to the server.

[0328] Step 7:

[0329] The server receives feedback from users and collects and re-analyzes new information. This ensures the system constantly updates and provides users with information based on the latest situation. Input is user feedback data, and output is updated analysis data and visual relationship diagrams.

[0330] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0331] This invention combines an automated checking system for severing ties with anti-social forces with an emotion engine that recognizes the user's emotions. A detailed embodiment is shown below.

[0332] This system automatically collects information from data sources on the internet. This information includes news articles, official company announcements, social media posts, and legal databases. The collected data is regularly updated to enable analysis based on the latest trends.

[0333] The acquired data is preprocessed by the server and converted into an analyzable format. The preprocessing process includes data cleansing, noise reduction, and formatting standardization. This optimizes the data for input to generative models.

[0334] Next, the server inputs the preprocessed data into a generative model, which analyzes the relationships within the data. The generative model uses a multi-layer neural network to process the data and automatically detect potential connections with antisocial forces.

[0335] The analysis results are generated as visual data by the server and sent to the user's terminal. The terminal receives this data and displays it on the user interface. The visual data includes a correlation network diagram, which allows the user to intuitively grasp the risks.

[0336] Furthermore, the system incorporates an emotion engine that analyzes user feedback to infer user emotions. Based on this emotion recognition, the way information is presented is modified. For example, if a user is highly anxious, the information presentation is adjusted to be more detailed and easier to understand. The emotion engine can also dynamically adjust the priority of presented content by evaluating the strength of relevance based on user reactions.

[0337] As a concrete example, when conducting an investigation of a company's board of directors, the user enters the company name into the system, and the server collects and analyzes relevant information. When the resulting network diagram is displayed on the user's terminal, the user's reactions are monitored, and if there are areas of particular interest, for example, the emotion engine highlights that information or presents additional information. In this way, the system is capable of flexibly presenting information while taking the user's emotions into consideration.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The server automatically collects data from internet sources. Here, the server uses API access and web scraping to target news articles, company reports, and social media posts to obtain the necessary information.

[0341] Step 2:

[0342] The server preprocesses the collected data. Specifically, it performs tasks such as denoising text, standardizing formats, and translating languages, converting the data into a format that can be input into the analysis model.

[0343] Step 3:

[0344] The server inputs pre-processed data into a generative model and performs relevance analysis. The generative model uses proper nouns and contextual information within the data to detect relationship patterns and identify connections to antisocial forces.

[0345] Step 4:

[0346] The server generates a visual network diagram based on the analysis results. The network diagram visually displays the relationships between individuals and organizations, and elements of the diagram are highlighted according to the strength of their relationships.

[0347] Step 5:

[0348] The server generates a visual network diagram and sends it to the terminal. The terminal receives this and displays it in its user interface, allowing the user to intuitively understand the situation.

[0349] Step 6:

[0350] Users can review the network diagram displayed on their device and provide feedback to the server. They can also request additional information on specific points of interest.

[0351] Step 7:

[0352] The server evaluates user feedback and analyzes the user's emotional state using an emotion engine. The emotion engine feeds back the user's response as data and adjusts the output accordingly.

[0353] Step 8:

[0354] The server dynamically adjusts how information is presented based on the sentiment analysis results. For example, if user anxiety is detected, the server will present information in more detail and modify the output to provide a sense of reassurance.

[0355] Step 9:

[0356] By considering newly collected data and reanalysis results from the server, and updating information that focuses on specific relevances that users are concerned about, the system ensures that users always receive up-to-date and reliable information.

[0357] (Example 2)

[0358] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0359] Currently, there is a lack of efficient means to acquire information about organizations and individuals suspected of having ties to anti-social forces and to present it to users in a visually and emotionally appropriate manner. This results in the problem of cumbersome and non-intuitive risk assessment. Furthermore, there is the challenge of flexibly adjusting information presentation based on user reactions and feedback.

[0360] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0361] In this invention, the server includes means for automatically collecting data from information sources on an information storage device, means for preprocessing the collected data and converting it into an analyzable format, and means for dynamically adjusting the presented information through sentiment analysis. This makes it possible to present information regarding antisocial risks to the user in an effective and adaptive manner.

[0362] An "information storage device" is a device used to store and manage various types of data, and servers and cloud storage fall into this category.

[0363] "Means of collection" refers to a device or program for automatically retrieving data that matches a specific purpose from an information source on an information storage device.

[0364] "Preprocessing" is the process of removing unnecessary information and standardizing the format of collected data so that it is suitable for analysis.

[0365] A "model" is a mathematical or statistical method used to analyze the relationships and characteristics of data, and includes generative AI models, among others.

[0366] "Visual information" refers to data that is visually represented in the form of diagrams, graphs, etc., to make the analysis results easier to understand.

[0367] An "output device" is a hardware device such as a display or tablet used to present information transmitted from a server to the user.

[0368] "Emotion analysis" is a technology that infers a user's emotional state from their input and responses, and dynamically adjusts information based on the results.

[0369] "Means of dynamic adjustment" refers to a function that changes the way information is presented and the content of that information in real time, based on analysis results and user responses.

[0370] This invention comprises a system having a server, a terminal, and a user interface. This system automatically evaluates relationships with anti-social forces and provides intuitive and emotionally resonant information.

[0371] The server uses an internet-connected storage device to collect data. Specifically, it retrieves articles using news APIs and collects publicly available information using web crawlers. It also uses social media APIs to retrieve relevant posts, thereby improving the comprehensiveness of the information.

[0372] The collected data is preprocessed on the server. This processing includes database unification, cleansing of unnecessary information, and formatting standardization. The preprocessed data is then input into a generative AI model using a multi-layer neural network for correlation analysis.

[0373] The resulting visual information is constructed as network diagrams and graphs. The server transmits this visual information to an output device, which the terminal receives and presents to the user. The presented information is dynamically adjusted based on sentiment analysis to match the user's current emotional state.

[0374] Users can interactively manipulate information through their devices, and feedback from these interactions is sent back to the server. This feedback is analyzed by the system's emotion engine, and continuous adjustments are made to further refine the information presentation.

[0375] As a concrete example, if a user wants to perform a risk assessment of an organization, they would enter the organization's name into the system. A possible prompt might be, "I would like to obtain the latest information on the association of Organization X with anti-social forces." The server would then automatically collect relevant information and present the analysis results to the user. In this process, information would be highlighted or detailed information provided based on the user's responses, aiding in understanding the information.

[0376] This system allows users to quickly and accurately grasp risk information, which supports better decision-making.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The server collects data from publicly available information stored in an information storage device via an internet connection. The input is a prompt statement provided by the user, for example, "I would like to obtain the latest information on the association of Organization X with anti-social forces." Based on this, an automated crawler calls news APIs and social media APIs to retrieve relevant articles and posts. The output is a collection of the collected raw data.

[0380] Step 2:

[0381] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. At this stage, unnecessary information is cleansed and the data is converted into a unified format that can be parsed (such as JSON). Processing includes text normalization and deduplication. The output is a formatted, clean dataset.

[0382] Step 3:

[0383] The server inputs pre-processed data into a generating AI model and performs correlation analysis. The input is clean data that has undergone pre-processing. Using a multi-layer neural network, it analyzes the potential relationships and importance contained in the collected data and calculates correlation scores. The output is the analyzed correlation scores.

[0384] Step 4:

[0385] The server generates visual information based on the analysis results. The input is the relevance score obtained in step 3. Using a visualization library, it generates relevance network diagrams and graphs, and formats them into a user-friendly format. The output is visually formatted data.

[0386] Step 5:

[0387] The terminal displays visual information sent from the server on its user interface. The input is the visual data generated in step 4. The terminal uses the received data to display an interactive user interface, allowing the user to manipulate the network diagram. The output is the network diagram visually displayed on the screen.

[0388] Step 6:

[0389] The user reacts to information presented through the terminal and provides feedback. The input is the presented visual information. The user can select specific nodes or input responses in text. The terminal collects this feedback and sends it to the server. The output is the user's interaction data.

[0390] Step 7:

[0391] The server performs sentiment analysis based on user feedback and dynamically adjusts the information presentation. The input is the user interaction data obtained in step 6. Using the sentiment analysis engine, it infers the user's emotional state and decides whether to highlight information or provide additional information based on the results. The output is the adjusted information display settings.

[0392] (Application Example 2)

[0393] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0394] The challenge is to enable more effective and user-friendly security management by automatically detecting relationships with anti-social forces, allowing users to intuitively understand the risks, and dynamically adjusting information presentation based on user emotions.

[0395] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0396] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relevance, and means for monitoring user responses and automatically adjusting settings for prioritizing the display of information. This enables users to more effectively recognize risks and select appropriate responses.

[0397] An "automatic data acquisition method" is a mechanism for collecting necessary data from various information sources on the internet without user intervention.

[0398] A "preprocessing means" is a mechanism that performs processing to cleanse the acquired data and convert it into a format suitable for analysis.

[0399] A "generative model" is an algorithm, based on multilayer neural networks and other methods, used to analyze the relationships between input data.

[0400] A "visual data generation means" is a mechanism for converting analyzed data into a visually easy-to-understand format and presenting it.

[0401] A "user emotion analysis tool" is a mechanism that monitors user reactions to infer their emotional state and appropriately adjust the way information is presented.

[0402] An "information priority display adjustment mechanism" is a system that analyzes user interests and attention and dynamically sets the display priority of information according to its importance.

[0403] In the system implementing this invention, the server first automatically retrieves data from internet information sources. During this process, it efficiently collects relevant information using news article APIs and social networking service APIs. The retrieved data is then preprocessed by the server. This preprocessing includes using Python to cleanse the data and convert it into a parseable format.

[0404] The transformed data is analyzed by a generative model built with TensorFlow. This generative model, which uses a multi-layer neural network, has the ability to automatically detect connections to antisocial forces. The analysis results are generated as visual data by the server and sent to the user via the terminal. The visual data is provided in the form of network diagrams and other diagrams that show the connections.

[0405] Furthermore, the device utilizes Microsoft's Azure Text Analytics API to analyze user reactions and adaptively adjust information presentation based on those emotions. If the user's anxiety level is high, important information will be displayed in more detail, and actions such as adding suggested solutions will be taken.

[0406] As a concrete example, a company's security officer could use this system to investigate relationships with new business partners. When the officer enters the business partner's name, the server analyzes the relevant information and presents comprehensive visual data outlining the risks. During this process, if the user shows strong interest in specific information, that information is prioritized and highlighted.

[0407] An example of a prompt for a generative AI model is: "Collect the latest news articles about this company and analyze any associations with anti-social forces. Also, analyze the user's concerns and tailor the information presentation accordingly."

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The server automatically retrieves data from internet sources. When a user enters the name of a company or subject, the server calls news article APIs and social media APIs to collect relevant information. Based on this input, the server retrieves raw data such as news articles and social media posts.

[0411] Step 2:

[0412] The server preprocesses the acquired data. Specifically, it uses Python to cleanse the data and remove noise. It also performs text normalization to unify data in different formats. This results in outputting data in a parseable format suitable for generative models.

[0413] Step 3:

[0414] The server inputs preprocessed data into a generative model for analysis. The TensorFlow-based generative model utilizes a multi-layer neural network to extract connections to antisocial forces from the data. It analyzes the input, standardized data, determines whether a connection exists, and outputs the result.

[0415] Step 4:

[0416] The server generates the analyzed results as visual data and sends it to the terminal. Based on the analysis results, it creates intuitively understandable visual data such as network diagrams. The generated visual data is sent to the user's terminal.

[0417] Step 5:

[0418] The device uses Microsoft's Azure Text Analytics API to analyze user emotions. When a user responds to visual data, it extracts emotional indicators from their facial expressions and text input to evaluate the user's emotions, such as anxiety or reassurance. Based on these analysis results, the information presentation method is dynamically adjusted.

[0419] Step 6:

[0420] Based on user sentiment analysis results, the information displayed is adaptively changed. The device highlights more detailed explanations and additional information for information that the user is highly anxious about or interested in. This action prioritizes information that is important to the user, enabling appropriate responses according to the risk.

[0421] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0422] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0423] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0427] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0428] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0429] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0430] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0431] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0432] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0433] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0434] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0435] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0436] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0437] This invention relates to an automated checking system for severing ties with anti-social forces, and a detailed embodiment thereof is shown below.

[0438] This system automatically collects necessary data from internet sources via a server. The collected data includes news articles, official company announcements, social media posts, and legal databases. The server periodically retrieves this information, enabling analysis based on the latest information.

[0439] The acquired data is preprocessed by the server and converted into an analyzable format. Preprocessing includes data cleansing, noise reduction, and formatting standardization. This makes the data suitable for input into generative models, improving the accuracy of the analysis.

[0440] The server inputs pre-processed data into a generative model to analyze its connections to anti-social forces. The generative model utilizes a multi-layered neural network to automatically detect potential relationships within the data. This process reveals the extent to which companies and individuals are associated with anti-social forces.

[0441] The analysis results are generated as visual data by the server and sent to the user's terminal. This visual data includes a relevance network diagram, which allows the user to quickly grasp the risks. The network diagram represents the relationships between individuals and organizations using dots and lines, and is displayed with key relationships highlighted.

[0442] Furthermore, the server uses a generative model to quantify and rank the strength of relationships. This makes it easy for users to understand which relationships require particular attention.

[0443] Users can view information via their devices and provide feedback to the server. This feedback triggers system improvements and reanalysis, and the server keeps itself constantly up-to-date by collecting and analyzing new data.

[0444] As a concrete example, when a user checks the directors of a certain company, they enter the company name into the system, and the server collects and analyzes relevant information, displaying a network diagram on the terminal that shows potential connections with anti-social forces. This allows the user to quickly identify problematic relationships and take appropriate action.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The server collects data from information sources on the internet. Here, the server uses web scraping and API access to automatically retrieve necessary data from news articles, official company announcements, social media posts, and legal databases.

[0448] Step 2:

[0449] The server preprocesses the collected data. Preprocessing involves data cleansing, noise removal, formatting standardization, and conversion into an analyzable format.

[0450] Step 3:

[0451] The server inputs pre-processed data into a generative model. The generative model uses a multi-layer neural network to automatically analyze potential relationships and connections within the data.

[0452] Step 4:

[0453] The server converts the analysis results into visual data. Specifically, it generates a relationship network diagram, visually representing the relationships between individuals and organizations using points and lines.

[0454] Step 5:

[0455] The server generates visual data and sends it to the user's terminal. The terminal receives this data and displays it on the user interface, allowing the user to intuitively understand the risks.

[0456] Step 6:

[0457] Users review the information displayed on their devices and provide feedback to the server as needed. This feedback is used to improve the system and trigger new data collection.

[0458] Step 7:

[0459] The server collects new data and re-analyzes it based on user feedback. This ensures the system always handles the latest information and can continuously check for risks related to anti-social forces quickly and accurately.

[0460] (Example 1)

[0461] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0462] In modern society, it is extremely important to quickly identify and sever ties with anti-social forces, but manual verification is time-consuming and labor-intensive, making an efficient automated system necessary.

[0463] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0464] In this invention, the server includes means for automatically acquiring information from a network information collection using an information gathering device, means for organizing the acquired information and converting it into an analyzable format, and means for inputting the organized information into a generating AI model to analyze relationships. This makes it possible to automatically and efficiently detect relationships with anti-social forces and provide that information quickly.

[0465] An "information gathering device" is a mechanism for automatically acquiring necessary information from a network.

[0466] An "information collection" is a group of data consisting of various sources of information that exist on the internet, such as news articles, official announcements, social media posts, and legal databases.

[0467] "Organization" is the process of converting acquired information into an analyzable format by cleansing, removing noise, and standardizing the format.

[0468] A "generative AI model" is an analytical algorithm that uses a multi-layer neural network to detect latent relationships within data.

[0469] "Visual information" refers to information that visually represents analysis results and outputs them as graphs or network diagrams.

[0470] A "computer device" is a terminal device that allows users to visually confirm the analysis results.

[0471] This invention is an automated checking system for severing ties with anti-social forces. This system primarily consists of server, terminal, and user components.

[0472] The server automatically retrieves data from information collections on the internet using information gathering devices. The server efficiently collects target information from sources such as news articles, social media posts, and legal databases using tools like web crawlers. Specifically, the Python BeautifulSoup library is used for this purpose.

[0473] The acquired information is organized by the server and input into the generative AI model. The server cleanses the data using regular expressions and NLP tools to remove noise and standardize the format. This transforms the data into a format suitable for analysis. The generative AI model utilizes deep learning libraries such as TensorFlow and PyTorch, and uses multi-layer neural networks to analyze latent relationships in the data.

[0474] The analysis results are generated as visual information by the server and sent to the user's terminal. This visual information is represented as a relationship network diagram using NetworkX or Matplotlib. Through this, users can quickly grasp the risks. In addition, the generating AI model quantifies the strength of relationships and provides ranked results. This allows users to understand relationships that require particular attention.

[0475] Users can view analysis results via their devices and send feedback to the system. This feedback is processed on the server and used to collect new information and perform further analysis, ensuring the system is always up-to-date.

[0476] As a concrete example, when checking a company's directors, the user might enter a prompt such as, "Please check the connections between the directors of Company XYZ and anti-social forces." In response to this request, the server collects and analyzes data and provides the user's terminal with a network diagram visually showing the relationships. This allows the user to identify problematic relationships and quickly decide on appropriate actions.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The server automatically acquires data from information collections on the network using information gathering devices. Specifically, the server uses web crawlers to collect target information from news articles, social media posts, and legal databases. The input is unstructured data from the internet, and the output is raw data stored within the server.

[0480] Step 2:

[0481] The server organizes the acquired raw data. This process involves removing unnecessary text using regular expressions and tokenizing and structuring the data using NLP tools. The input is the raw data obtained in step 1, and the output is clean data that can be analyzed.

[0482] Step 3:

[0483] The server inputs clean data into a generating AI model to analyze relationships. Specifically, it uses a multi-layer neural network with TensorFlow to perform calculations that detect latent relationships in the data. The input is clean data, and the output is a relevance score and relationship determination as the analysis result.

[0484] Step 4:

[0485] The server generates visual information based on the analysis results. It visually displays the analysis results by drawing a relevance network diagram using NetworkX or Matplotlib. The input is the analysis results from step 3, and the output is the visualized relevance network diagram.

[0486] Step 5:

[0487] The server quantifies the strength of relevance to the generated visual information and ranks it. It evaluates the relationships using the score of the generating AI model and sorts them in order of importance. The input is the visual information from step 4, and the output is the ranked relationship information.

[0488] Step 6:

[0489] Users view visual information via their terminals and send feedback to the server. Based on network diagrams, users can evaluate relationships with antisocial forces and send suggestions for improvement and feedback to the system. Inputs are visual information and user feedback, while outputs are instructions for system updates or reanalysis that reflect the feedback.

[0490] (Application Example 1)

[0491] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0492] In modern society, the ability of companies and individuals to quickly assess the trustworthiness of their relationships with third parties is increasingly important from a risk management perspective. However, the sheer volume and fragmentation of information presents challenges, as manual checks require considerable effort and time. Furthermore, identifying potential connections with anti-social forces requires sophisticated analytical capabilities, but conventional methods often lack sufficient accuracy.

[0493] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0494] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relationships, means for generating visual data and creating a visual relationship diagram based on the results of the analysis, means for outputting the visual data and visual relationship diagram via a communication device and providing a user interface that allows for the evaluation of relationships with third parties, means for evaluating the strength of the relationships analyzed by the generative model, ranking them, and identifying high-risk relationships, and means for receiving responses from users, collecting and re-analyzing new information, and updating based on the latest situation. This enables companies and individuals to efficiently evaluate their relationships with third parties, quickly grasp potential risks, and make reliable decisions.

[0495] "Internet information sources" refer to online platforms where diverse information is aggregated, such as websites, news feeds, and social media.

[0496] "Automatically acquiring data" refers to the process by which programs or systems collect information from the internet without human intervention.

[0497] "Preprocessing" refers to a series of processes performed to convert acquired data into a format that can be analyzed, and mainly includes data cleansing and formatting standardization.

[0498] A "generative model" is a pre-trained algorithm that uses a neural network to analyze data and reveal underlying patterns and relationships.

[0499] "Analyzing relationships" is the process of analyzing the relationships and correlations between elements using acquired and pre-processed data.

[0500] "Visual data" refers to information that visualizes analysis results so that users can intuitively understand them, and it mainly takes the form of graphs and charts.

[0501] A "visual relationship diagram" is a diagram that uses dots and lines to show the relationships between individual elements or subjects, and it focuses on displaying particularly important relationships.

[0502] A "communication device" is a device used for sending and receiving data, and primarily has the function of transmitting information via a network.

[0503] A "user interface" is an interface that provides screens and operational elements for a user to interact with a system, enabling the display and input of information.

[0504] "Evaluating the strength of relevance and ranking it" is the process of quantifying the importance and reliability of each relationship obtained through analysis and determining its priority.

[0505] "Receiving responses from users" means that the system accepts feedback and additional information input from users.

[0506] "Collecting and reanalyzing new information" refers to the process of gathering new data as needed based on feedback, and then processing and analyzing that information again.

[0507] The system for implementing this invention is particularly useful for enabling companies and individuals to efficiently evaluate their relationships with third parties. The server basically has the following main functions:

[0508] First, data is automatically retrieved. The server uses a Python program to collect data from multiple sources on the internet via an API. The retrieved information comes from a wide range of sources, including news sites, social media, and official announcements.

[0509] Next, preprocessing is performed. Data cleansing is carried out on the server using the Pandas library. This is a process that removes noise from the data and converts it into a standardized, analyzable format.

[0510] The pre-processed data is then input into a generative AI model. A model consisting of a multi-layered neural network using PyTorch is used to detect latent relationships in the data.

[0511] The analysis results are generated as visual data, and a visual relationship diagram is created. Using the D3.js library, it is visualized as an interactive network graph.

[0512] This visualized information is sent to the user's terminal via a communication device. The user can then review the information through a smartphone application with an intuitive user interface and evaluate their relationship with a third party.

[0513] For example, when a company evaluates the potential risks of a new business partner, the user enters the business partner's name into the system. The server collects relevant information, analyzes it using an AI model, and generates visual data. This allows the user to quickly grasp the risks of relationships with third parties and make reliable business decisions.

[0514] An example of a prompt to input into the generating AI model is, "Please check for any ties between our new business partner, XYZ Corporation, and anti-social forces."

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The server automatically retrieves data from internet sources. Specifically, it uses a Python program and APIs to collect information from news sites and social media. The input is the URL or API key of the data to be collected, and the output is raw text data.

[0518] Step 2:

[0519] The server preprocesses the acquired raw data. Using the Pandas library, it performs data cleansing, removing unwanted noise and standardizing the format. This process transforms the data into a parseable format. The input is raw text data, and the output is cleansed text data.

[0520] Step 3:

[0521] The server inputs pre-processed data into a generating AI model. A PyTorch-based multilayer neural network analyzes this data and detects potential associations with antisocial forces. The input is cleansed text data, and the output is the analyzed association score.

[0522] Step 4:

[0523] The server generates a visual relationship diagram based on the analysis results. It utilizes the D3.js library to visualize the relationships as a network graph connecting points and lines. The input is the analyzed relationship score, and the output is HTML and related scripts representing the visual relationship diagram.

[0524] Step 5:

[0525] The terminal receives visual data sent from the server and displays it on the user interface. Through the terminal, the user can evaluate relationships with third parties. The input is visual relationship diagram data from the server, and the output is a graph displayed on the terminal's interface.

[0526] Step 6:

[0527] Based on the displayed relationship diagram, the user provides feedback to the system to make trading decisions and evaluate relationship risks. The user enters additional views and comments in the input fields. The input is the user's feedback, and the output is the user response data sent to the server.

[0528] Step 7:

[0529] The server receives feedback from users and collects and re-analyzes new information. This ensures the system constantly updates and provides users with information based on the latest situation. Input is user feedback data, and output is updated analysis data and visual relationship diagrams.

[0530] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0531] This invention combines an automated checking system for severing ties with anti-social forces with an emotion engine that recognizes the user's emotions. A detailed embodiment is shown below.

[0532] This system automatically collects information from data sources on the internet. This information includes news articles, official company announcements, social media posts, and legal databases. The collected data is regularly updated to enable analysis based on the latest trends.

[0533] The acquired data is preprocessed by the server and converted into an analyzable format. The preprocessing process includes data cleansing, noise reduction, and formatting standardization. This optimizes the data for input to generative models.

[0534] Next, the server inputs the preprocessed data into a generative model, which analyzes the relationships within the data. The generative model uses a multi-layer neural network to process the data and automatically detect potential connections with antisocial forces.

[0535] The analysis results are generated as visual data by the server and sent to the user's terminal. The terminal receives this data and displays it on the user interface. The visual data includes a correlation network diagram, which allows the user to intuitively grasp the risks.

[0536] Furthermore, the system incorporates an emotion engine that analyzes user feedback to infer user emotions. Based on this emotion recognition, the way information is presented is modified. For example, if a user is highly anxious, the information presentation is adjusted to be more detailed and easier to understand. The emotion engine can also dynamically adjust the priority of presented content by evaluating the strength of relevance based on user reactions.

[0537] As a concrete example, when conducting an investigation of a company's board of directors, the user enters the company name into the system, and the server collects and analyzes relevant information. When the resulting network diagram is displayed on the user's terminal, the user's reactions are monitored, and if there are areas of particular interest, for example, the emotion engine highlights that information or presents additional information. In this way, the system is capable of flexibly presenting information while taking the user's emotions into consideration.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] The server automatically collects data from internet sources. Here, the server uses API access and web scraping to target news articles, company reports, and social media posts to obtain the necessary information.

[0541] Step 2:

[0542] The server preprocesses the collected data. Specifically, it performs tasks such as denoising text, standardizing formats, and translating languages, converting the data into a format that can be input into the analysis model.

[0543] Step 3:

[0544] The server inputs pre-processed data into a generative model and performs relevance analysis. The generative model uses proper nouns and contextual information within the data to detect relationship patterns and identify connections to antisocial forces.

[0545] Step 4:

[0546] The server generates a visual network diagram based on the analysis results. The network diagram visually displays the relationships between individuals and organizations, and elements of the diagram are highlighted according to the strength of their relationships.

[0547] Step 5:

[0548] The server generates a visual network diagram and sends it to the terminal. The terminal receives this and displays it in its user interface, allowing the user to intuitively understand the situation.

[0549] Step 6:

[0550] Users can review the network diagram displayed on their device and provide feedback to the server. They can also request additional information on specific points of interest.

[0551] Step 7:

[0552] The server evaluates user feedback and analyzes the user's emotional state using an emotion engine. The emotion engine feeds back the user's response as data and adjusts the output accordingly.

[0553] Step 8:

[0554] The server dynamically adjusts how information is presented based on the sentiment analysis results. For example, if user anxiety is detected, the server will present information in more detail and modify the output to provide a sense of reassurance.

[0555] Step 9:

[0556] By considering newly collected data and reanalysis results from the server, and updating information that focuses on specific relevances that users are concerned about, the system ensures that users always receive up-to-date and reliable information.

[0557] (Example 2)

[0558] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0559] Currently, there is a lack of efficient means to acquire information about organizations and individuals suspected of having ties to anti-social forces and to present it to users in a visually and emotionally appropriate manner. This results in the problem of cumbersome and non-intuitive risk assessment. Furthermore, there is the challenge of flexibly adjusting information presentation based on user reactions and feedback.

[0560] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0561] In this invention, the server includes means for automatically collecting data from information sources on an information storage device, means for preprocessing the collected data and converting it into an analyzable format, and means for dynamically adjusting the presented information through sentiment analysis. This makes it possible to present information regarding antisocial risks to the user in an effective and adaptive manner.

[0562] An "information storage device" is a device used to store and manage various types of data, and servers and cloud storage fall into this category.

[0563] "Means of collection" refers to a device or program for automatically retrieving data that matches a specific purpose from an information source on an information storage device.

[0564] "Preprocessing" is the process of removing unnecessary information and standardizing the format of collected data so that it is suitable for analysis.

[0565] A "model" is a mathematical or statistical method used to analyze the relationships and characteristics of data, and includes generative AI models, among others.

[0566] "Visual information" refers to data that is visually represented in the form of diagrams, graphs, etc., to make the analysis results easier to understand.

[0567] An "output device" is a hardware device such as a display or tablet used to present information transmitted from a server to the user.

[0568] "Emotion analysis" is a technology that infers a user's emotional state from their input and responses, and dynamically adjusts information based on the results.

[0569] "Means of dynamic adjustment" refers to a function that changes the way information is presented and the content of that information in real time, based on analysis results and user responses.

[0570] This invention comprises a system having a server, a terminal, and a user interface. This system automatically evaluates relationships with anti-social forces and provides intuitive and emotionally resonant information.

[0571] The server uses an internet-connected storage device to collect data. Specifically, it retrieves articles using news APIs and collects publicly available information using web crawlers. It also uses social media APIs to retrieve relevant posts, thereby improving the comprehensiveness of the information.

[0572] The collected data is preprocessed on the server. This processing includes database unification, cleansing of unnecessary information, and formatting standardization. The preprocessed data is then input into a generative AI model using a multi-layer neural network for correlation analysis.

[0573] The resulting visual information is constructed as network diagrams and graphs. The server transmits this visual information to an output device, which the terminal receives and presents to the user. The presented information is dynamically adjusted based on sentiment analysis to match the user's current emotional state.

[0574] Users can interactively manipulate information through their devices, and feedback from these interactions is sent back to the server. This feedback is analyzed by the system's emotion engine, and continuous adjustments are made to further refine the information presentation.

[0575] As a concrete example, if a user wants to perform a risk assessment of an organization, they would enter the organization's name into the system. A possible prompt might be, "I would like to obtain the latest information on the association of Organization X with anti-social forces." The server would then automatically collect relevant information and present the analysis results to the user. In this process, information would be highlighted or detailed information provided based on the user's responses, aiding in understanding the information.

[0576] This system allows users to quickly and accurately grasp risk information, which supports better decision-making.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The server collects data from publicly available information stored in an information storage device via an internet connection. The input is a prompt statement provided by the user, for example, "I would like to obtain the latest information on the association of Organization X with anti-social forces." Based on this, an automated crawler calls news APIs and social media APIs to retrieve relevant articles and posts. The output is a collection of the collected raw data.

[0580] Step 2:

[0581] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. At this stage, unnecessary information is cleansed and the data is converted into a unified format that can be parsed (such as JSON). Processing includes text normalization and deduplication. The output is a formatted, clean dataset.

[0582] Step 3:

[0583] The server inputs pre-processed data into a generating AI model and performs correlation analysis. The input is clean data that has undergone pre-processing. Using a multi-layer neural network, it analyzes the potential relationships and importance contained in the collected data and calculates correlation scores. The output is the analyzed correlation scores.

[0584] Step 4:

[0585] The server generates visual information based on the analysis results. The input is the relevance score obtained in step 3. Using a visualization library, it generates relevance network diagrams and graphs, and formats them into a user-friendly format. The output is visually formatted data.

[0586] Step 5:

[0587] The terminal displays visual information sent from the server on its user interface. The input is the visual data generated in step 4. The terminal uses the received data to display an interactive user interface, allowing the user to manipulate the network diagram. The output is the network diagram visually displayed on the screen.

[0588] Step 6:

[0589] The user reacts to information presented through the terminal and provides feedback. The input is the presented visual information. The user can select specific nodes or input responses in text. The terminal collects this feedback and sends it to the server. The output is the user's interaction data.

[0590] Step 7:

[0591] The server performs sentiment analysis based on user feedback and dynamically adjusts the information presentation. The input is the user interaction data obtained in step 6. Using the sentiment analysis engine, it infers the user's emotional state and decides whether to highlight information or provide additional information based on the results. The output is the adjusted information display settings.

[0592] (Application Example 2)

[0593] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0594] The challenge is to enable more effective and user-friendly security management by automatically detecting relationships with anti-social forces, allowing users to intuitively understand the risks, and dynamically adjusting information presentation based on user emotions.

[0595] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0596] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relevance, and means for monitoring user responses and automatically adjusting settings for prioritizing the display of information. This enables users to more effectively recognize risks and select appropriate responses.

[0597] An "automatic data acquisition method" is a mechanism for collecting necessary data from various information sources on the internet without user intervention.

[0598] A "preprocessing means" is a mechanism that performs processing to cleanse the acquired data and convert it into a format suitable for analysis.

[0599] A "generative model" is an algorithm, based on multilayer neural networks and other methods, used to analyze the relationships between input data.

[0600] A "visual data generation means" is a mechanism for converting analyzed data into a visually easy-to-understand format and presenting it.

[0601] A "user emotion analysis tool" is a mechanism that monitors user reactions to infer their emotional state and appropriately adjust the way information is presented.

[0602] An "information priority display adjustment mechanism" is a system that analyzes user interests and attention and dynamically sets the display priority of information according to its importance.

[0603] In the system implementing this invention, the server first automatically retrieves data from internet information sources. During this process, it efficiently collects relevant information using news article APIs and social networking service APIs. The retrieved data is then preprocessed by the server. This preprocessing includes using Python to cleanse the data and convert it into a parseable format.

[0604] The transformed data is analyzed by a generative model built with TensorFlow. This generative model, which uses a multi-layer neural network, has the ability to automatically detect connections to antisocial forces. The analysis results are generated as visual data by the server and sent to the user via the terminal. The visual data is provided in the form of network diagrams and other diagrams that show the connections.

[0605] Furthermore, the device utilizes Microsoft's Azure Text Analytics API to analyze user reactions and adaptively adjust information presentation based on those emotions. If the user's anxiety level is high, important information will be displayed in more detail, and actions such as adding suggested solutions will be taken.

[0606] As a concrete example, a company's security officer could use this system to investigate relationships with new business partners. When the officer enters the business partner's name, the server analyzes the relevant information and presents comprehensive visual data outlining the risks. During this process, if the user shows strong interest in specific information, that information is prioritized and highlighted.

[0607] An example of a prompt for a generative AI model is: "Collect the latest news articles about this company and analyze any associations with anti-social forces. Also, analyze the user's concerns and tailor the information presentation accordingly."

[0608] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0609] Step 1:

[0610] The server automatically retrieves data from internet sources. When a user enters the name of a company or subject, the server calls news article APIs and social media APIs to collect relevant information. Based on this input, the server retrieves raw data such as news articles and social media posts.

[0611] Step 2:

[0612] The server preprocesses the acquired data. Specifically, it uses Python to cleanse the data and remove noise. It also performs text normalization to unify data in different formats. This results in outputting data in a parseable format suitable for generative models.

[0613] Step 3:

[0614] The server inputs preprocessed data into a generative model for analysis. The TensorFlow-based generative model utilizes a multi-layer neural network to extract connections to antisocial forces from the data. It analyzes the input, standardized data, determines whether a connection exists, and outputs the result.

[0615] Step 4:

[0616] The server generates the analyzed results as visual data and sends it to the terminal. Based on the analysis results, it creates intuitively understandable visual data such as network diagrams. The generated visual data is sent to the user's terminal.

[0617] Step 5:

[0618] The device uses Microsoft's Azure Text Analytics API to analyze user emotions. When a user responds to visual data, it extracts emotional indicators from their facial expressions and text input to evaluate the user's emotions, such as anxiety or reassurance. Based on these analysis results, the information presentation method is dynamically adjusted.

[0619] Step 6:

[0620] Based on user sentiment analysis results, the information displayed is adaptively changed. The device highlights more detailed explanations and additional information for information that the user is highly anxious about or interested in. This action prioritizes information that is important to the user, enabling appropriate responses according to the risk.

[0621] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0622] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0623] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0624] [Fourth Embodiment]

[0625] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0626] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0627] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0628] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0629] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0630] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0631] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0632] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0633] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0634] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0635] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0636] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0637] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0638] This invention relates to an automated checking system for severing ties with anti-social forces, and a detailed embodiment thereof is shown below.

[0639] This system automatically collects necessary data from internet sources via a server. The collected data includes news articles, official company announcements, social media posts, and legal databases. The server periodically retrieves this information, enabling analysis based on the latest information.

[0640] The acquired data is preprocessed by the server and converted into an analyzable format. Preprocessing includes data cleansing, noise reduction, and formatting standardization. This makes the data suitable for input into generative models, improving the accuracy of the analysis.

[0641] The server inputs pre-processed data into a generative model to analyze its connections to anti-social forces. The generative model utilizes a multi-layered neural network to automatically detect potential relationships within the data. This process reveals the extent to which companies and individuals are associated with anti-social forces.

[0642] The analysis results are generated as visual data by the server and sent to the user's terminal. This visual data includes a relevance network diagram, which allows the user to quickly grasp the risks. The network diagram represents the relationships between individuals and organizations using dots and lines, and is displayed with key relationships highlighted.

[0643] Furthermore, the server uses a generative model to quantify and rank the strength of relationships. This makes it easy for users to understand which relationships require particular attention.

[0644] Users can view information via their devices and provide feedback to the server. This feedback triggers system improvements and reanalysis, and the server keeps itself constantly up-to-date by collecting and analyzing new data.

[0645] As a concrete example, when a user checks the directors of a certain company, they enter the company name into the system, and the server collects and analyzes relevant information, displaying a network diagram on the terminal that shows potential connections with anti-social forces. This allows the user to quickly identify problematic relationships and take appropriate action.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The server collects data from information sources on the internet. Here, the server uses web scraping and API access to automatically retrieve necessary data from news articles, official company announcements, social media posts, and legal databases.

[0649] Step 2:

[0650] The server preprocesses the collected data. Preprocessing involves data cleansing, noise removal, formatting standardization, and conversion into an analyzable format.

[0651] Step 3:

[0652] The server inputs pre-processed data into a generative model. The generative model uses a multi-layer neural network to automatically analyze potential relationships and connections within the data.

[0653] Step 4:

[0654] The server converts the analysis results into visual data. Specifically, it generates a relationship network diagram, visually representing the relationships between individuals and organizations using points and lines.

[0655] Step 5:

[0656] The server generates visual data and sends it to the user's terminal. The terminal receives this data and displays it on the user interface, allowing the user to intuitively understand the risks.

[0657] Step 6:

[0658] Users review the information displayed on their devices and provide feedback to the server as needed. This feedback is used to improve the system and trigger new data collection.

[0659] Step 7:

[0660] The server collects new data and re-analyzes it based on user feedback. This ensures the system always handles the latest information and can continuously check for risks related to anti-social forces quickly and accurately.

[0661] (Example 1)

[0662] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In modern society, it is extremely important to quickly identify and sever ties with anti-social forces, but manual verification is time-consuming and labor-intensive, making an efficient automated system necessary.

[0664] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0665] In this invention, the server includes means for automatically acquiring information from a network information collection using an information gathering device, means for organizing the acquired information and converting it into an analyzable format, and means for inputting the organized information into a generating AI model to analyze relationships. This makes it possible to automatically and efficiently detect relationships with anti-social forces and provide that information quickly.

[0666] An "information gathering device" is a mechanism for automatically acquiring necessary information from a network.

[0667] An "information collection" is a group of data consisting of various sources of information that exist on the internet, such as news articles, official announcements, social media posts, and legal databases.

[0668] "Organization" is the process of converting acquired information into an analyzable format by cleansing, removing noise, and standardizing the format.

[0669] A "generative AI model" is an analytical algorithm that uses a multi-layer neural network to detect latent relationships within data.

[0670] "Visual information" refers to information that visually represents analysis results and outputs them as graphs or network diagrams.

[0671] A "computer device" is a terminal device that allows users to visually confirm the analysis results.

[0672] This invention is an automated checking system for severing ties with anti-social forces. This system primarily consists of server, terminal, and user components.

[0673] The server automatically retrieves data from information collections on the internet using information gathering devices. The server efficiently collects target information from sources such as news articles, social media posts, and legal databases using tools like web crawlers. Specifically, the Python BeautifulSoup library is used for this purpose.

[0674] The acquired information is organized by the server and input into the generative AI model. The server cleanses the data using regular expressions and NLP tools to remove noise and standardize the format. This transforms the data into a format suitable for analysis. The generative AI model utilizes deep learning libraries such as TensorFlow and PyTorch, and uses multi-layer neural networks to analyze latent relationships in the data.

[0675] The analysis results are generated as visual information by the server and sent to the user's terminal. This visual information is represented as a relationship network diagram using NetworkX or Matplotlib. Through this, users can quickly grasp the risks. In addition, the generating AI model quantifies the strength of relationships and provides ranked results. This allows users to understand relationships that require particular attention.

[0676] Users can view analysis results via their devices and send feedback to the system. This feedback is processed on the server and used to collect new information and perform further analysis, ensuring the system is always up-to-date.

[0677] As a concrete example, when checking a company's directors, the user might enter a prompt such as, "Please check the connections between the directors of Company XYZ and anti-social forces." In response to this request, the server collects and analyzes data and provides the user's terminal with a network diagram visually showing the relationships. This allows the user to identify problematic relationships and quickly decide on appropriate actions.

[0678] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0679] Step 1:

[0680] The server automatically acquires data from information collections on the network using information gathering devices. Specifically, the server uses web crawlers to collect target information from news articles, social media posts, and legal databases. The input is unstructured data from the internet, and the output is raw data stored within the server.

[0681] Step 2:

[0682] The server organizes the acquired raw data. This process involves removing unnecessary text using regular expressions and tokenizing and structuring the data using NLP tools. The input is the raw data obtained in step 1, and the output is clean data that can be analyzed.

[0683] Step 3:

[0684] The server inputs clean data into a generating AI model to analyze relationships. Specifically, it uses a multi-layer neural network with TensorFlow to perform calculations that detect latent relationships in the data. The input is clean data, and the output is a relevance score and relationship determination as the analysis result.

[0685] Step 4:

[0686] The server generates visual information based on the analysis results. It visually displays the analysis results by drawing a relevance network diagram using NetworkX or Matplotlib. The input is the analysis results from step 3, and the output is the visualized relevance network diagram.

[0687] Step 5:

[0688] The server quantifies the strength of relevance to the generated visual information and ranks it. It evaluates the relationships using the score of the generating AI model and sorts them in order of importance. The input is the visual information from step 4, and the output is the ranked relationship information.

[0689] Step 6:

[0690] Users view visual information via their terminals and send feedback to the server. Based on network diagrams, users can evaluate relationships with antisocial forces and send suggestions for improvement and feedback to the system. Inputs are visual information and user feedback, while outputs are instructions for system updates or reanalysis that reflect the feedback.

[0691] (Application Example 1)

[0692] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] In modern society, the ability of companies and individuals to quickly assess the trustworthiness of their relationships with third parties is increasingly important from a risk management perspective. However, the sheer volume and fragmentation of information presents challenges, as manual checks require considerable effort and time. Furthermore, identifying potential connections with anti-social forces requires sophisticated analytical capabilities, but conventional methods often lack sufficient accuracy.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0695] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relationships, means for generating visual data and creating a visual relationship diagram based on the results of the analysis, means for outputting the visual data and visual relationship diagram via a communication device and providing a user interface that allows for the evaluation of relationships with third parties, means for evaluating the strength of the relationships analyzed by the generative model, ranking them, and identifying high-risk relationships, and means for receiving responses from users, collecting and re-analyzing new information, and updating based on the latest situation. This enables companies and individuals to efficiently evaluate their relationships with third parties, quickly grasp potential risks, and make reliable decisions.

[0696] "Internet information sources" refer to online platforms where diverse information is aggregated, such as websites, news feeds, and social media.

[0697] "Automatically acquiring data" refers to the process by which programs or systems collect information from the internet without human intervention.

[0698] "Preprocessing" refers to a series of processes performed to convert acquired data into a format that can be analyzed, and mainly includes data cleansing and formatting standardization.

[0699] A "generative model" is a pre-trained algorithm that uses a neural network to analyze data and reveal underlying patterns and relationships.

[0700] "Analyzing relationships" is the process of analyzing the relationships and correlations between elements using acquired and pre-processed data.

[0701] "Visual data" refers to information that visualizes analysis results so that users can intuitively understand them, and it mainly takes the form of graphs and charts.

[0702] A "visual relationship diagram" is a diagram that uses dots and lines to show the relationships between individual elements or subjects, and it focuses on displaying particularly important relationships.

[0703] A "communication device" is a device used for sending and receiving data, and primarily has the function of transmitting information via a network.

[0704] A "user interface" is an interface that provides screens and operational elements for a user to interact with a system, enabling the display and input of information.

[0705] "Evaluating the strength of relevance and ranking it" is the process of quantifying the importance and reliability of each relationship obtained through analysis and determining its priority.

[0706] "Receiving responses from users" means that the system accepts feedback and additional information input from users.

[0707] "Collecting and reanalyzing new information" refers to the process of gathering new data as needed based on feedback, and then processing and analyzing that information again.

[0708] The system for implementing this invention is particularly useful for enabling companies and individuals to efficiently evaluate their relationships with third parties. The server basically has the following main functions:

[0709] First, data is automatically retrieved. The server uses a Python program to collect data from multiple sources on the internet via an API. The retrieved information comes from a wide range of sources, including news sites, social media, and official announcements.

[0710] Next, preprocessing is performed. Data cleansing is carried out on the server using the Pandas library. This is a process that removes noise from the data and converts it into a standardized, analyzable format.

[0711] The pre-processed data is then input into a generative AI model. A model consisting of a multi-layered neural network using PyTorch is used to detect latent relationships in the data.

[0712] The analysis results are generated as visual data, and a visual relationship diagram is created. Using the D3.js library, it is visualized as an interactive network graph.

[0713] This visualized information is sent to the user's terminal via a communication device. The user can then review the information through a smartphone application with an intuitive user interface and evaluate their relationship with a third party.

[0714] For example, when a company evaluates the potential risks of a new business partner, the user enters the business partner's name into the system. The server collects relevant information, analyzes it using an AI model, and generates visual data. This allows the user to quickly grasp the risks of relationships with third parties and make reliable business decisions.

[0715] An example of a prompt to input into the generating AI model is, "Please check for any ties between our new business partner, XYZ Corporation, and anti-social forces."

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] The server automatically retrieves data from internet sources. Specifically, it uses a Python program and APIs to collect information from news sites and social media. The input is the URL or API key of the data to be collected, and the output is raw text data.

[0719] Step 2:

[0720] The server preprocesses the acquired raw data. Using the Pandas library, it performs data cleansing, removing unwanted noise and standardizing the format. This process transforms the data into a parseable format. The input is raw text data, and the output is cleansed text data.

[0721] Step 3:

[0722] The server inputs pre-processed data into a generating AI model. A PyTorch-based multilayer neural network analyzes this data and detects potential associations with antisocial forces. The input is cleansed text data, and the output is the analyzed association score.

[0723] Step 4:

[0724] The server generates a visual relationship diagram based on the analysis results. It utilizes the D3.js library to visualize the relationships as a network graph connecting points and lines. The input is the analyzed relationship score, and the output is HTML and related scripts representing the visual relationship diagram.

[0725] Step 5:

[0726] The terminal receives visual data sent from the server and displays it on the user interface. Through the terminal, the user can evaluate relationships with third parties. The input is visual relationship diagram data from the server, and the output is a graph displayed on the terminal's interface.

[0727] Step 6:

[0728] Based on the displayed relationship diagram, the user provides feedback to the system to make trading decisions and evaluate relationship risks. The user enters additional views and comments in the input fields. The input is the user's feedback, and the output is the user response data sent to the server.

[0729] Step 7:

[0730] The server receives feedback from users and collects and re-analyzes new information. This ensures the system constantly updates and provides users with information based on the latest situation. Input is user feedback data, and output is updated analysis data and visual relationship diagrams.

[0731] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0732] This invention combines an automated checking system for severing ties with anti-social forces with an emotion engine that recognizes the user's emotions. A detailed embodiment is shown below.

[0733] This system automatically collects information from data sources on the internet. This information includes news articles, official company announcements, social media posts, and legal databases. The collected data is regularly updated to enable analysis based on the latest trends.

[0734] The acquired data is preprocessed by the server and converted into an analyzable format. The preprocessing process includes data cleansing, noise reduction, and formatting standardization. This optimizes the data for input to generative models.

[0735] Next, the server inputs the preprocessed data into a generative model, which analyzes the relationships within the data. The generative model uses a multi-layer neural network to process the data and automatically detect potential connections with antisocial forces.

[0736] The analysis results are generated as visual data by the server and sent to the user's terminal. The terminal receives this data and displays it on the user interface. The visual data includes a correlation network diagram, which allows the user to intuitively grasp the risks.

[0737] Furthermore, the system incorporates an emotion engine that analyzes user feedback to infer user emotions. Based on this emotion recognition, the way information is presented is modified. For example, if a user is highly anxious, the information presentation is adjusted to be more detailed and easier to understand. The emotion engine can also dynamically adjust the priority of presented content by evaluating the strength of relevance based on user reactions.

[0738] As a concrete example, when conducting an investigation of a company's board of directors, the user enters the company name into the system, and the server collects and analyzes relevant information. When the resulting network diagram is displayed on the user's terminal, the user's reactions are monitored, and if there are areas of particular interest, for example, the emotion engine highlights that information or presents additional information. In this way, the system is capable of flexibly presenting information while taking the user's emotions into consideration.

[0739] The following describes the processing flow.

[0740] Step 1:

[0741] The server automatically collects data from internet sources. Here, the server uses API access and web scraping to target news articles, company reports, and social media posts to obtain the necessary information.

[0742] Step 2:

[0743] The server preprocesses the collected data. Specifically, it performs tasks such as denoising text, standardizing formats, and translating languages, converting the data into a format that can be input into the analysis model.

[0744] Step 3:

[0745] The server inputs pre-processed data into a generative model and performs relevance analysis. The generative model uses proper nouns and contextual information within the data to detect relationship patterns and identify connections to antisocial forces.

[0746] Step 4:

[0747] The server generates a visual network diagram based on the analysis results. The network diagram visually displays the relationships between individuals and organizations, and elements of the diagram are highlighted according to the strength of their relationships.

[0748] Step 5:

[0749] The server generates a visual network diagram and sends it to the terminal. The terminal receives this and displays it in its user interface, allowing the user to intuitively understand the situation.

[0750] Step 6:

[0751] Users can review the network diagram displayed on their device and provide feedback to the server. They can also request additional information on specific points of interest.

[0752] Step 7:

[0753] The server evaluates user feedback and analyzes the user's emotional state using an emotion engine. The emotion engine feeds back the user's response as data and adjusts the output accordingly.

[0754] Step 8:

[0755] The server dynamically adjusts how information is presented based on the sentiment analysis results. For example, if user anxiety is detected, the server will present information in more detail and modify the output to provide a sense of reassurance.

[0756] Step 9:

[0757] By considering newly collected data and reanalysis results from the server, and updating information that focuses on specific relevances that users are concerned about, the system ensures that users always receive up-to-date and reliable information.

[0758] (Example 2)

[0759] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0760] Currently, there is a lack of efficient means to acquire information about organizations and individuals suspected of having ties to anti-social forces and to present it to users in a visually and emotionally appropriate manner. This results in the problem of cumbersome and non-intuitive risk assessment. Furthermore, there is the challenge of flexibly adjusting information presentation based on user reactions and feedback.

[0761] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0762] In this invention, the server includes means for automatically collecting data from information sources on an information storage device, means for preprocessing the collected data and converting it into an analyzable format, and means for dynamically adjusting the presented information through sentiment analysis. This makes it possible to present information regarding antisocial risks to the user in an effective and adaptive manner.

[0763] An "information storage device" is a device used to store and manage various types of data, and servers and cloud storage fall into this category.

[0764] "Means of collection" refers to a device or program for automatically retrieving data that matches a specific purpose from an information source on an information storage device.

[0765] "Preprocessing" is the process of removing unnecessary information and standardizing the format of collected data so that it is suitable for analysis.

[0766] A "model" is a mathematical or statistical method used to analyze the relationships and characteristics of data, and includes generative AI models, among others.

[0767] "Visual information" refers to data that is visually represented in the form of diagrams, graphs, etc., to make the analysis results easier to understand.

[0768] An "output device" is a hardware device such as a display or tablet used to present information transmitted from a server to the user.

[0769] "Emotion analysis" is a technology that infers a user's emotional state from their input and responses, and dynamically adjusts information based on the results.

[0770] "Means of dynamic adjustment" refers to a function that changes the way information is presented and the content of that information in real time, based on analysis results and user responses.

[0771] This invention comprises a system having a server, a terminal, and a user interface. This system automatically evaluates relationships with anti-social forces and provides intuitive and emotionally resonant information.

[0772] The server uses an internet-connected storage device to collect data. Specifically, it retrieves articles using news APIs and collects publicly available information using web crawlers. It also uses social media APIs to retrieve relevant posts, thereby improving the comprehensiveness of the information.

[0773] The collected data is preprocessed on the server. This processing includes database unification, cleansing of unnecessary information, and formatting standardization. The preprocessed data is then input into a generative AI model using a multi-layer neural network for correlation analysis.

[0774] The resulting visual information is constructed as network diagrams and graphs. The server transmits this visual information to an output device, which the terminal receives and presents to the user. The presented information is dynamically adjusted based on sentiment analysis to match the user's current emotional state.

[0775] Users can interactively manipulate information through their devices, and feedback from these interactions is sent back to the server. This feedback is analyzed by the system's emotion engine, and continuous adjustments are made to further refine the information presentation.

[0776] As a concrete example, if a user wants to perform a risk assessment of an organization, they would enter the organization's name into the system. A possible prompt might be, "I would like to obtain the latest information on the association of Organization X with anti-social forces." The server would then automatically collect relevant information and present the analysis results to the user. In this process, information would be highlighted or detailed information provided based on the user's responses, aiding in understanding the information.

[0777] This system allows users to quickly and accurately grasp risk information, which supports better decision-making.

[0778] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0779] Step 1:

[0780] The server collects data from publicly available information stored in an information storage device via an internet connection. The input is a prompt statement provided by the user, for example, "I would like to obtain the latest information on the association of Organization X with anti-social forces." Based on this, an automated crawler calls news APIs and social media APIs to retrieve relevant articles and posts. The output is a collection of the collected raw data.

[0781] Step 2:

[0782] The server preprocesses the collected raw data. The input is the raw data obtained in step 1. At this stage, unnecessary information is cleansed and the data is converted into a unified format that can be parsed (such as JSON). Processing includes text normalization and deduplication. The output is a formatted, clean dataset.

[0783] Step 3:

[0784] The server inputs pre-processed data into a generating AI model and performs correlation analysis. The input is clean data that has undergone pre-processing. Using a multi-layer neural network, it analyzes the potential relationships and importance contained in the collected data and calculates correlation scores. The output is the analyzed correlation scores.

[0785] Step 4:

[0786] The server generates visual information based on the analysis results. The input is the relevance score obtained in step 3. Using a visualization library, it generates relevance network diagrams and graphs, and formats them into a user-friendly format. The output is visually formatted data.

[0787] Step 5:

[0788] The terminal displays visual information sent from the server on its user interface. The input is the visual data generated in step 4. The terminal uses the received data to display an interactive user interface, allowing the user to manipulate the network diagram. The output is the network diagram visually displayed on the screen.

[0789] Step 6:

[0790] The user reacts to information presented through the terminal and provides feedback. The input is the presented visual information. The user can select specific nodes or input responses in text. The terminal collects this feedback and sends it to the server. The output is the user's interaction data.

[0791] Step 7:

[0792] The server performs sentiment analysis based on user feedback and dynamically adjusts the information presentation. The input is the user interaction data obtained in step 6. Using the sentiment analysis engine, it infers the user's emotional state and decides whether to highlight information or provide additional information based on the results. The output is the adjusted information display settings.

[0793] (Application Example 2)

[0794] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0795] The challenge is to enable more effective and user-friendly security management by automatically detecting relationships with anti-social forces, allowing users to intuitively understand the risks, and dynamically adjusting information presentation based on user emotions.

[0796] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0797] In this invention, the server includes means for automatically acquiring data from information sources on the Internet, means for preprocessing the acquired data and converting it into an analyzable format, means for inputting the preprocessed data into a generative model and analyzing its relevance, and means for monitoring user responses and automatically adjusting settings for prioritizing the display of information. This enables users to more effectively recognize risks and select appropriate responses.

[0798] An "automatic data acquisition method" is a mechanism for collecting necessary data from various information sources on the internet without user intervention.

[0799] A "preprocessing means" is a mechanism that performs processing to cleanse the acquired data and convert it into a format suitable for analysis.

[0800] A "generative model" is an algorithm, based on multilayer neural networks and other methods, used to analyze the relationships between input data.

[0801] A "visual data generation means" is a mechanism for converting analyzed data into a visually easy-to-understand format and presenting it.

[0802] A "user emotion analysis tool" is a mechanism that monitors user reactions to infer their emotional state and appropriately adjust the way information is presented.

[0803] An "information priority display adjustment mechanism" is a system that analyzes user interests and attention and dynamically sets the display priority of information according to its importance.

[0804] In the system implementing this invention, the server first automatically retrieves data from internet information sources. During this process, it efficiently collects relevant information using news article APIs and social networking service APIs. The retrieved data is then preprocessed by the server. This preprocessing includes using Python to cleanse the data and convert it into a parseable format.

[0805] The transformed data is analyzed by a generative model built with TensorFlow. This generative model, which uses a multi-layer neural network, has the ability to automatically detect connections to antisocial forces. The analysis results are generated as visual data by the server and sent to the user via the terminal. The visual data is provided in the form of network diagrams and other diagrams that show the connections.

[0806] Furthermore, the device utilizes Microsoft's Azure Text Analytics API to analyze user reactions and adaptively adjust information presentation based on those emotions. If the user's anxiety level is high, important information will be displayed in more detail, and actions such as adding suggested solutions will be taken.

[0807] As a concrete example, a company's security officer could use this system to investigate relationships with new business partners. When the officer enters the business partner's name, the server analyzes the relevant information and presents comprehensive visual data outlining the risks. During this process, if the user shows strong interest in specific information, that information is prioritized and highlighted.

[0808] An example of a prompt for a generative AI model is: "Collect the latest news articles about this company and analyze any associations with anti-social forces. Also, analyze the user's concerns and tailor the information presentation accordingly."

[0809] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0810] Step 1:

[0811] The server automatically retrieves data from internet sources. When a user enters the name of a company or subject, the server calls news article APIs and social media APIs to collect relevant information. Based on this input, the server retrieves raw data such as news articles and social media posts.

[0812] Step 2:

[0813] The server preprocesses the acquired data. Specifically, it uses Python to cleanse the data and remove noise. It also performs text normalization to unify data in different formats. This results in outputting data in a parseable format suitable for generative models.

[0814] Step 3:

[0815] The server inputs preprocessed data into a generative model for analysis. The TensorFlow-based generative model utilizes a multi-layer neural network to extract connections to antisocial forces from the data. It analyzes the input, standardized data, determines whether a connection exists, and outputs the result.

[0816] Step 4:

[0817] The server generates the analyzed results as visual data and sends it to the terminal. Based on the analysis results, it creates intuitively understandable visual data such as network diagrams. The generated visual data is sent to the user's terminal.

[0818] Step 5:

[0819] The device uses Microsoft's Azure Text Analytics API to analyze user emotions. When a user responds to visual data, it extracts emotional indicators from their facial expressions and text input to evaluate the user's emotions, such as anxiety or reassurance. Based on these analysis results, the information presentation method is dynamically adjusted.

[0820] Step 6:

[0821] Based on user sentiment analysis results, the information displayed is adaptively changed. The device highlights more detailed explanations and additional information for information that the user is highly anxious about or interested in. This action prioritizes information that is important to the user, enabling appropriate responses according to the risk.

[0822] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0823] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0824] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0825] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0826] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0827] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0828] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0829] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0830] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0831] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0832] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0833] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0834] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0835] 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.

[0836] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0837] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0838] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0839] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0840] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0841] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0842] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0843] The following is further disclosed regarding the embodiments described above.

[0844] (Claim 1)

[0845] A means of automatically obtaining data from internet information sources,

[0846] Means for preprocessing the acquired data and converting it into an analyzable format,

[0847] A means of inputting preprocessed data into a generative model and analyzing its relationships,

[0848] A means for generating visual data based on the results of the analysis,

[0849] A means for outputting the visual data via a terminal,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, further comprising means for evaluating and ranking the strength of the relationships analyzed by a generative model.

[0853] (Claim 3)

[0854] The system according to claim 1, further comprising means for receiving user feedback and for collecting and reanalyzing new data.

[0855] "Example 1"

[0856] (Claim 1)

[0857] A means of automatically acquiring information from a collection of information on a network using an information gathering device,

[0858] A means for organizing the acquired information and converting it into an analyzable format,

[0859] A means of inputting organized information into a generating AI model to analyze relationships,

[0860] A means for creating visual information based on the results of the analysis,

[0861] Means for outputting the visual information via a computer device,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, further comprising means for quantifying and ranking the strength of relationships analyzed by a generative AI model.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising means for receiving feedback from users and for collecting and reanalyzing new information.

[0867] "Application Example 1"

[0868] (Claim 1)

[0869] A means of automatically obtaining data from internet information sources,

[0870] Means for preprocessing the acquired data and converting it into an analyzable format,

[0871] A means of inputting preprocessed data into a generative model and analyzing its relationships,

[0872] A means for generating visual data and creating a visual relationship diagram based on the results of the analysis,

[0873] A means for outputting the visual data and visual relationship diagram via a communication device and providing a user interface that allows evaluation of the relationship with a third party,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, further comprising means for evaluating the strength of relationships analyzed by a generative model, ranking them, and identifying high-risk relationships.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for receiving responses from users, collecting and reanalyzing new information, and updating based on the latest situation.

[0879] "Example 2 of combining an emotion engine"

[0880] (Claim 1)

[0881] A means for automatically collecting data from information sources on an information storage device,

[0882] Means for preprocessing the collected data and converting it into an analyzable format,

[0883] A means of inputting preprocessed data into a model and analyzing its relationships,

[0884] A means for converting the results of the analysis into visual information,

[0885] A means for presenting the visual information via an output device,

[0886] A means of dynamically adjusting the presented information through emotion analysis,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, further comprising means for evaluating the importance of relationships analyzed by a generative model and dynamically adjusting the presentation order.

[0890] (Claim 3)

[0891] The system according to claim 1, further comprising means for obtaining user feedback and for collecting and reanalyzing new data.

[0892] "Application example 2 of combining emotional engines"

[0893] (Claim 1)

[0894] A means of automatically obtaining data from internet information sources,

[0895] Means for preprocessing the acquired data and converting it into an analyzable format,

[0896] A means of inputting preprocessed data into a generative model and analyzing its relationships,

[0897] A means for generating visual data based on the results of the analysis,

[0898] A means for outputting the visual data via a terminal,

[0899] A means to monitor user reactions and automatically adjust settings to prioritize the display of information,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising means for evaluating and ranking the strength of relevance analyzed by a generative model, and means for adaptively presenting output information by analyzing the user's emotions.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising means for receiving user feedback, collecting and reanalyzing new data, and dynamically adjusting the order in which information is presented based on predicted user-important information. [Explanation of symbols]

[0905] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically obtaining data from internet information sources, Means for preprocessing the acquired data and converting it into an analyzable format, A means of inputting preprocessed data into a generative model and analyzing its relationships, A means for generating visual data based on the results of the analysis, A means for outputting the visual data via a terminal, A system that includes this.

2. The system according to claim 1, further comprising means for evaluating and ranking the strength of the relationships analyzed by a generative model.

3. The system according to claim 1, further comprising means for receiving user feedback and for collecting and reanalyzing new data.

Images