system

Abstract

We provide the system. [Solution] means of collecting information, An analytical means for analyzing the collected information, An evaluation method for performing risk assessment based on analysis results, A notification means for generating a risk notification based on the assessment, 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 method for controlling a persona chatbot, which is 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 in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In conventional risk management systems, information collection is often performed manually, which is time-consuming and laborious, and there are problems such as collection omissions and easy overlooking of important risk factors. In addition, manual data analysis and risk assessment are prone to subjectivity, and it is difficult to evaluate with sufficient accuracy. Therefore, it is difficult to detect potential risks in business and investment at an early stage and appropriately address them. 【Means for Solving the Problems】 【0005】 The present invention provides a system comprising collection means for collecting information, analysis means for analyzing the collected information, evaluation means for performing a risk assessment based on the analysis results, and notification means for generating a risk notification based on the evaluation. This system automates information collection and analysis, and enables rapid and accurate risk assessment, making it possible to detect potential risks early and take appropriate countermeasures. 【0006】 "Collection means" refers to a device or program that has the function of automatically acquiring necessary data from a specified information source. 【0007】 "Analysis means" refers to a device or program equipped with functions for processing collected data and extracting and evaluating it as useful information. 【0008】 "Evaluation means" refers to a device or program used to quantitatively or qualitatively determine the degree and impact of risk based on the analyzed information. 【0009】 A "notification means" is a device or program equipped with the function of communicating risk information that has occurred under specific conditions to the user. [Brief explanation of the drawing] 【0010】 [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 the data processing device and 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0011】 Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings. 【0012】 First, let's explain the terminology used in the following explanation. 【0013】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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. 【0014】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0015】 In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. 【0016】 In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like. 【0017】 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." 【0018】 [First Embodiment] 【0019】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0020】 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. 【0021】 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). 【0022】 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. 【0023】 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. 【0024】 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. 【0025】 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. 【0026】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0027】 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. 【0028】 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. 【0029】 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. 【0030】 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". 【0031】 In implementing this invention, the system mainly consists of three components: a server, a terminal, and a user. The specific operation of this system is described below. 【0032】 The server first automatically retrieves necessary information from the internet and databases based on keywords and information sources set for information gathering. It efficiently collects data using web scraping techniques and API access. The collected data is then filtered to remove noise and irrelevant information. 【0033】 Next, the server uses advanced analytical tools and natural language processing techniques to analyze the collected information. From the results of this analysis, risk factors are extracted, and basic data is generated to evaluate their importance and urgency. 【0034】 In the evaluation process, risk scoring is performed based on the analysis results. If a risk exceeding the threshold is detected, that information is promptly transmitted to the relevant terminals via a notification system. 【0035】 The device receives notifications from the server and visually reports the risk situation to the user. This includes using graphs and charts that show risk scores and the scope of impact. Based on the information provided, the user can take appropriate measures as needed. 【0036】 As a concrete example, consider a case where a company needs to monitor compliance risks with new regulations. In this case, the user sets keywords related to the server, and the server collects and analyzes information 24 hours a day. When important information is detected, an alert is sent to the user's mobile device via the terminal, enabling a quick response. 【0037】 Thus, the present invention is a system that achieves faster and more accurate risk management by automating a series of processes from information gathering to analysis, evaluation, and notification. 【0038】 The following describes the processing flow. 【0039】 Step 1: 【0040】 The server automatically collects data from the internet and databases using keywords and information sources set by the user. It efficiently obtains information using web scraping and API access. 【0041】 Step 2: 【0042】 The server filters the collected data, removing irrelevant information that constitutes noise. Natural language processing is used to determine the relevance of the collected data. 【0043】 Step 3: 【0044】 The server analyzes the filtered data and identifies the risk factors involved. Generative AI models are used to understand the meaning of the data and create a foundation for risk assessment. 【0045】 Step 4: 【0046】 The server performs a risk assessment based on the analysis results. This assessment involves scoring based on importance and urgency. 【0047】 Step 5: 【0048】 If the server detects a risk exceeding a certain threshold, it generates risk information and promptly sends it to the terminal via a notification system. 【0049】 Step 6: 【0050】 The device receives notifications from the server and presents the user with the risk status. A visual representation showing the risk score and its scope of impact is displayed. 【0051】 Step 7: 【0052】 Based on the risk information provided by the device, users will consider and implement necessary countermeasures. 【0053】 (Example 1) 【0054】 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." 【0055】 In today's information society, vast amounts of data circulate via the internet, making it increasingly important for individuals and organizations to extract useful information and quickly assess risks. However, traditional methods require significant time and effort for information gathering and analysis, and the lack of means to quickly notify assessment results hinders rapid decision-making. Therefore, there is a need for systems that efficiently handle everything from data collection to analysis, evaluation, and notification. 【0056】 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. 【0057】 In this invention, the server includes information gathering means for automatically acquiring information based on relevant words and information sources received from the user, information filtering means for extracting useful information by excluding irrelevant data from the acquired information, and information analysis means for analyzing the filtered information using natural language processing technology to extract risk factors. This makes it possible to efficiently identify important risk information from the collected information and to quickly evaluate and notify it. 【0058】 "Information gathering methods" refer to techniques that automatically retrieve information from the internet or databases based on related terms and information sources specified by the user. 【0059】 "Information filtering means" refers to the process of removing irrelevant data from acquired information and extracting useful information. 【0060】 "Information analysis methods" refer to techniques that analyze filtered information using natural language processing technology and other methods to extract risk factors. 【0061】 A "risk assessment method" is a method for scoring and evaluating risks based on analysis results. 【0062】 An "information notification system" is a system for quickly notifying relevant terminals of evaluation results. 【0063】 "Visualization means" refers to methods for generating graphs and charts to visually present notified risk information to the user. 【0064】 A "settings management method" is an approach that includes a function that allows users to configure the frequency of information collection and related keywords. 【0065】 This invention is a system that automates the process from information gathering to risk assessment and notification, supporting rapid decision-making. This system primarily functions through three parties: a server, terminals, and users. Specific embodiments are described below. 【0066】 The server automatically retrieves information based on relevant keywords and information sources received from the user. Web scraping techniques are used for information gathering. Specifically, Python libraries such as BeautifulSoup and Scrapy are used to extract necessary data from web pages. Furthermore, information can be collected from social media and other data platforms via API access. 【0067】 The collected information is filtered to remove noise and unnecessary data. Regular expressions and natural language processing libraries (e.g., NLTK) are used for this purpose. Filtering ensures that only highly relevant information is selected. 【0068】 Next, the server analyzes the filtered information. Here, natural language processing technology is used, leveraging Google® Cloud Natural Language API and OpenAI® models to extract risk factors. 【0069】 Based on the analyzed data, the risk is assessed. The assessment involves scoring, and if a risk exceeding a certain threshold is detected, the server promptly notifies the relevant parties. This notification is sent to the relevant terminals in real time. 【0070】 The device visualizes the received risk information and presents it to the user. This involves generating graphs and charts using D3.js and Chart.js, displaying risk scores and impact scopes. Based on this information, the user can quickly consider countermeasures. 【0071】 As a concrete example, here is an example of a prompt message for a generative AI model: "Monitor risks related to new food safety regulations. Relevant keywords are 'food safety,' 'regulations,' and 'compliance.' Notify me if there is any high-risk information." 【0072】 Thus, the present invention achieves highly accurate risk management and rapid decision-making by efficiently handling the process from information gathering to analysis, evaluation, and notification. 【0073】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0074】 Step 1: 【0075】 The server receives a prompt message from the user and sets relevant terms and information sources for information gathering. This prompt message includes the themes and related keywords to be monitored. The user provides keywords such as "food safety," "regulations," and "compliance" as input, and the server uses this to determine the scope of information to be collected. The configured information is treated as foundational information for the information gathering mechanism. 【0076】 Step 2: 【0077】 The server automatically retrieves relevant information from configured sources using web scraping techniques and APIs. For example, it extracts data from web pages using Python's BeautifulSoup or Scrapy, and downloads tweets from social media using APIs. The input is the information sources configured in step 1, and the output is a set of raw data. This collected data may contain noise, so it is processed in the next step. 【0078】 Step 3: 【0079】 The server filters the collected information to remove noise and unnecessary details. This involves extracting only relevant sentences using regular expressions and natural language processing libraries (such as NLTK). The input is the raw data obtained in step 2, and the output is clean, informational data with noise removed. This process allows for efficient and accurate subsequent analysis. 【0080】 Step 4: 【0081】 The server uses natural language processing techniques to analyze filtered, clean information. It employs the Google Cloud Natural Language API and generative AI models to extract risk factors and assess their importance. The input is filtered information data, and the output is the risk factors and their scores. This score serves as foundational data for determining urgency and importance. 【0082】 Step 5: 【0083】 The server evaluates the scored risk based on the analysis results and selects the information to be notified. If the risk score exceeds the set criteria, that information is immediately treated as a notification. The input is the scoring result from step 4, and the output is a data package of risk information to be notified. 【0084】 Step 6: 【0085】 The terminal reports a visualized risk situation to the user based on risk information received from the server. Here, D3.js and Chart.js are used to generate graphs and charts showing risk scores and impact scope, and present them to the user. The input is notification data from the server, and the output is the graphs and charts displayed on the user interface. 【0086】 Step 7: 【0087】 Based on the visualized information, users plan and implement countermeasures as needed. The input is the risk information displayed on the terminal, and the output is the user's decision and the actions taken based on it. 【0088】 (Application Example 1) 【0089】 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." 【0090】 There is a challenge in accurately extracting risk factors from the vast and diverse information available on the internet and providing users with timely and accurate risk information. In particular, there is a need to efficiently collect, analyze, and notify users of the latest security information within limited time and resources. With existing technologies, information collection, analysis, and notification are often done manually, which makes it difficult to respond quickly. 【0091】 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. 【0092】 In this invention, the server includes means for collecting information, means for analyzing the information, and means for performing evaluations based on the analysis results. This makes it possible to efficiently and accurately collect, analyze, and evaluate information on the internet, and to quickly notify users of high-priority risk information. 【0093】 "Means for collecting information" refers to a mechanism that automatically retrieves data from the internet or databases based on specified arguments. 【0094】 "Means for analyzing information" refers to a mechanism that processes acquired data and transforms it into meaningful information using natural language processing and statistical analysis. 【0095】 "Means of evaluation" refers to a mechanism that measures risk based on analysis results and calculates an evaluation score. 【0096】 "Means for generating notifications" refers to a mechanism that creates alerts and informational notifications for users based on their evaluation scores. 【0097】 "Means for transmitting evaluation information to an instruction device" refers to a mechanism that transmits the generated evaluation information to the user's display device and provides visual feedback. 【0098】 A "visualization method" is a mechanism that displays data as graphs or charts in order to allow users to intuitively understand evaluation information. 【0099】 A "configuration mechanism" is a system that allows users to freely adjust the frequency and parameters of the information collected. 【0100】 To implement this invention, it is necessary to build a system in which three parties—a server, a terminal, and a user—work together. The server is the central component that automatically collects, analyzes, and evaluates information. Information collection is achieved by efficiently obtaining data from the internet based on specified arguments using web scraping tools or APIs. In this process, libraries such as Python's BeautifulSoup and Selenium are utilized. 【0101】 Next, the collected information is analyzed on the server using natural language processing technology. For this purpose, libraries such as Python's NLTK and spaCy are used to analyze text data and extract risk factors. The extracted information is evaluated by a machine learning model and quantitatively assessed as a risk score using scikit-learn. This evaluation result is generated as a notification and transmitted to the device via a real-time notification service such as Firebase Cloud Messaging. 【0102】 The device receives notifications from the server and displays visualized information to the user. This information is visualized as graphs and charts through an application using React Native, providing information in an easy-to-understand format for the user. As a specific example, information on phishing attacks in a certain region is collected, and the evaluation results are immediately notified to the user via smartphone. 【0103】 Users can review the information provided through their devices and take appropriate measures against risk situations as needed. Furthermore, users can customize the information collected by setting the frequency and parameters. These settings are configured via a device application and can be adjusted through an intuitive user interface. 【0104】 An example of a prompt might be: "Collect information from the internet about the latest security alerts, analyze the risks of phishing attacks and data breaches using natural language processing, and evaluate the risk score." This prompt is used to instruct the generative AI model on the information gathering and analysis steps. 【0105】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0106】 Step 1: 【0107】 The server takes the user-defined arguments as input and begins the information gathering process. It retrieves data from specified sources on the internet using web scraping tools (such as BeautifulSoup or Selenium) or APIs. This process collects relevant data, including information on phishing attacks and security threats. 【0108】 Step 2: 【0109】 The server performs natural language processing analysis on the collected raw data as input. Using Python libraries such as NLTK and spaCy, it analyzes the text data and extracts risk factors. This involves word tokenization, part-of-speech tagging, and contextual analysis, which highlights information related to risk. 【0110】 Step 3: 【0111】 The server performs an evaluation based on the analysis results. It uses scikit-learn to input the data into a machine learning model and calculate a risk score. This evaluation quantifies specific risk levels from the collected information and outputs them as evaluation results. 【0112】 Step 4: 【0113】 The server generates notifications based on the risk score. It uses notification services such as Firebase Cloud Messaging to create messages to inform devices of the risk information. These messages contain important information that should be provided to the user immediately. 【0114】 Step 5: 【0115】 The device receives notifications sent from the server. The application, developed with React Native, generates graphs, charts, and other visualizations based on the input notifications and presents them to the user. This allows the user to visually check risk information and understand the situation. 【0116】 Step 6: 【0117】 The user takes the information displayed on the terminal as input and implements risk mitigation measures as needed. If additional settings or changes to arguments are required, this can be done using the terminal's user interface. This allows the system to access the next data collection under improved conditions. 【0118】 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. 【0119】 The present invention aims to provide more interactive and effective risk management through a system that incorporates the ability to recognize user emotions in addition to information gathering, analysis, and risk assessment. This system consists of a server, terminals, and users. 【0120】 The server first automatically collects information from the internet and databases based on keywords and information sources set by the user. This collected information is filtered to remove noise and then analyzed to identify risk factors. 【0121】 The analysis utilizes natural language processing techniques and generative AI models to perform a risk assessment. Based on this assessment, a notification is generated and sent to the user's device. 【0122】 The emotion engine recognizes the user's emotions in real time via the device. This engine can analyze the user's emotional state based on their facial expressions, voice, and input data. 【0123】 For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the content of the notification and provides the user with information through a more appropriate interface. This notification may include suggestions for reducing stress or specific measures for risk avoidance. 【0124】 Furthermore, the emotion engine accumulates user emotion data, which is then analyzed by the server and used to improve the accuracy of future risk assessments. As a result, the system will be able to provide more personalized risk management to users over time. 【0125】 Thus, the present invention provides a more specific and flexible risk management solution tailored to user needs by combining information collection and analysis with interactive risk notifications based on sentiment data. 【0126】 The following describes the processing flow. 【0127】 Step 1: 【0128】 The server automatically collects information from the internet and databases based on keywords and information sources set by the user. This collection is efficiently carried out using web scraping and API access. 【0129】 Step 2: 【0130】 The server filters the collected information and removes irrelevant data. By utilizing natural language processing techniques to select highly relevant information, the accuracy of the data is improved. 【0131】 Step 3: 【0132】 The server analyzes the filtered data and uses a generative AI model to identify risk factors. These analysis results are then used as foundational data for risk assessment. 【0133】 Step 4: 【0134】 The server performs a risk assessment based on the analysis results. It scores each risk based on its importance and urgency, and determines its impact on the user. 【0135】 Step 5: 【0136】 The terminal notifies the user based on the risk assessment received from the server. The notification includes details of the risk and countermeasures, and is displayed on the user's terminal. 【0137】 Step 6: 【0138】 The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and voice data to understand their emotional state. This allows it to determine the user's stress level and level of interest. 【0139】 Step 7: 【0140】 The server adjusts risk notifications in a way that is best suited to the user's emotions, based on data obtained from the emotion engine. For example, if the user is stressed, the frequency and content of notifications are changed to reduce the burden on the user. 【0141】 Step 8: 【0142】 Users review the information and suggestions presented on their devices and consider specific actions to mitigate risks. Customized notifications based on sentiment data enable more effective decision-making. 【0143】 (Example 2) 【0144】 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". 【0145】 Traditional warning systems performed risk analysis and assessment based on information collected from users, but they struggled to recognize users' emotions in real time and flexibly adjust notification content accordingly. As a result, users may not receive appropriate notifications when they are emotionally distressed, leading to a problem where risk management does not function effectively. 【0146】 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. 【0147】 In this invention, the server includes means for collecting information, processing means for analyzing the collected information, evaluation means for evaluating the degree of risk based on the processing results, recognition means for recognizing the user's emotions, and adjustment means for adjusting the notification content based on the recognized emotions. This makes it possible to provide appropriate and personalized risk notifications according to the user's emotions. 【0148】 "Means of obtaining" refers to the collective set of processes and techniques used to collect information. 【0149】 "Processing means" refers to devices and algorithms used to analyze collected information and derive meaningful results from that data. 【0150】 "Evaluation methods" encompass criteria and techniques for determining the degree of risk based on analysis results. 【0151】 "Generation means" refers to a mechanism for creating risk notifications based on information obtained through evaluation. 【0152】 "Recognition means" refers to technologies used to sense and judge the emotional state of a user. 【0153】 "Adjustment means" refers to methods or devices for modifying the content or format of notifications based on perceived emotions. 【0154】 The system in this invention not only collects information, analyzes that information to assess risk, but is also capable of recognizing the user's emotions in real time and appropriately adjusting the content of notifications. A specific embodiment of this system is described below. 【0155】 The server first collects necessary information from the internet and databases based on keywords and information sources specified by the user. Web scraping libraries such as Python's Scrapy and BeautifulSoup can be used for information gathering. This makes it possible to efficiently obtain data from diverse information sources. 【0156】 Next, the server analyzes the collected information. This analysis utilizes natural language processing technology and a generative AI model such as GPT-4®. This model allows the server to automatically identify risk factors from the collected data and perform the necessary assessments. Based on the analysis results, the server generates a notification. This notification includes a risk overview, impact level, and suggested countermeasures. 【0157】 The server then sends the generated notification to the user's device. The device receives this notification and notifies the user visually or audibly. Possible notification formats include push notifications on smartphones and pop-up messages on PCs. 【0158】 Furthermore, the device is equipped with emotion recognition capabilities that analyze the user's facial expressions and voice input to evaluate their emotional state in real time. This may involve using facial recognition APIs or voice analysis software. This emotion data is sent to a server, and the content of notifications is tailored to the user's state. 【0159】 For example, if a user expresses concerns about "food safety," the system can collect and analyze relevant, up-to-date information and provide notifications to alleviate those concerns. An example of a prompt generated using an AI model might be: "If a user expresses concerns about food safety, please advise on what kind of reassuring notification should be sent." 【0160】 In this way, this system provides highly accurate and personalized risk management by handling everything from information gathering and analysis to adjusting notifications based on sentiment data. 【0161】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0162】 Step 1: 【0163】 The server receives keywords and information sources as input from the user. Based on this, it collects information from specified internet resources and databases. Specifically, it uses scraping tools such as Scrapy and BeautifulSoup to extract text data from web pages. The output of this process is a collection of collected text information. 【0164】 Step 2: 【0165】 The server receives the information obtained in Step 1 as input and performs filtering using regular expressions and text cleaning techniques. Specifically, it removes unnecessary noise and duplicate data. The output is a filtered and cleaned dataset. 【0166】 Step 3: 【0167】 The server performs analysis using filtered data as input. This analysis utilizes the generative AI model GPT-4, employing natural language processing techniques to identify risk factors. Specifically, it extracts highly relevant phrases and terms and evaluates their risk levels. The output consists of analysis results and risk assessment information. 【0168】 Step 4: 【0169】 The server generates a notification based on the output of step 3. Specifically, it determines the content and format of the information to be delivered to the user and creates a notification document that includes details about the risks and countermeasures. The output of this process is the generated notification message. 【0170】 Step 5: 【0171】 The device receives notifications sent from the server and displays them to the user visually or audibly. Specifically, this uses push notifications or application message display functions. The output of this step is a notification interface that the user can view. 【0172】 Step 6: 【0173】 The device collects user emotional data in real time using its camera and microphone. It acquires voice tone and facial expressions as input and uses an emotion recognition algorithm to evaluate the user's current emotional state. The output is data indicating the user's emotional state. 【0174】 Step 7: 【0175】 The server receives the emotion data obtained in step 6 as input and adjusts the notification. Specifically, it modifies the tone and content of the message according to the emotional state and reconstructs it to reduce psychological burden. The output of this step is the adjusted notification message. 【0176】 Step 8: 【0177】 The user receives a final notification message and takes appropriate action regarding the risk. Specifically, they make individual actions and decisions based on the notification content. This output represents the specific actions the user takes based on the information they have received. 【0178】 (Application Example 2) 【0179】 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". 【0180】 In modern society, there is a need to effectively manage important risk information amidst information overload. However, conventional risk management systems provide information without considering the user's emotional state, resulting in limitations in information acceptance and effectiveness. Furthermore, they lack the flexibility to respond to users' emotions in situations where they experience stress or anxiety. This invention aims to solve these problems and provide users with personalized information. 【0181】 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. 【0182】 In this invention, the server includes means for collecting information, means for analyzing the collected information, means for performing a risk assessment based on the analysis results, means for recognizing the user's emotions, and means for adjusting risk notifications according to the user's emotional state. This makes it possible to provide personalized risk information that takes the user's emotional state into consideration and to improve the effective receptivity of the information. 【0183】 "Means for collecting information" refers to a device or method that automatically acquires information from the internet, databases, etc., based on specified keywords. 【0184】 "Means for analyzing collected information" refers to a device or method that uses natural language processing techniques to analyze data in order to remove noise from the collected data and identify risk factors. 【0185】 "Means of risk assessment" refers to a device or method that determines potential hazards based on analyzed data and quantifies or qualitatively evaluates their importance and likelihood. 【0186】 "Means for generating risk notifications" refers to a device or method for generating messages to notify users of warnings or information based on the results of a risk assessment. 【0187】 "Emotion recognition means" refers to a device or method for recognizing a user's mental state and emotions in real time by analyzing the user's facial expressions, voice, and input data. 【0188】 "Means for adjusting risk notifications" refers to a device or method that optimizes the content and format of risk notifications according to the user's perceived emotional state, and provides information in the most effective way for the user. 【0189】 The system implementing this invention consists of multiple components. First, the server automatically collects relevant information from the internet and databases based on keywords set by the user. This could involve implementing web scraping technology using programming languages ​​such as Python or JavaScript (registered trademark). The collected information is then analyzed using natural language processing tools such as TENSORFLOW (registered trademark) to identify risk factors. 【0190】 Based on the analysis results, a risk assessment is performed, and a notification is created based on the assessment results. The notification content is generated by the server and then sent to the user's device. This device is a smartphone with an application installed that runs on the ANDROID® or iOS operating system. 【0191】 The device utilizes the smartphone's camera and microphone to recognize the user's emotional state in real time. Using Google Cloud's sentiment analysis API, the system analyzes the user's emotions from facial expressions and voice input. Based on this information, the server adjusts notifications and provides specific information and means to alleviate the user's stress and anxiety. 【0192】 As a concrete example, if a user sets the keyword "financial fraud," information on the latest fraud methods will be collected and analyzed. If the system determines through emotion recognition that the user is feeling anxious, a "music playlist to relax" or a "checklist to avoid fraud" will be displayed on the device. An example of a prompt to input into the generating AI model is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering their emotional state." 【0193】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0194】 Step 1: 【0195】 The server receives keywords set by the user. Based on these keywords, it collects relevant information from the internet and databases. The input is the user's keywords, and the output is the collected information. In this step, web scraping techniques are used to automatically retrieve the data. 【0196】 Step 2: 【0197】 The server analyzes the collected information. It filters the data to remove noise and uses natural language processing techniques to identify risk factors. The input is the collected information, and the output is the analyzed risk factors. Data analysis is performed using tools such as TensorFlow. 【0198】 Step 3: 【0199】 The server performs a risk assessment based on the analysis results. This assessment quantifies or qualitatively evaluates the importance and likelihood of the risks. The input is the risk factors, and the output is the risk assessment index. This process uses assessment algorithms to analyze the risks. 【0200】 Step 4: 【0201】 The server generates notifications based on the results of the risk assessment. It selects the information to convey to the user according to the assessment indicators and creates the notification message. The input is the risk assessment indicators, and the output is the notification message. The text of the notification is adapted to the context using a generative AI model. 【0202】 Step 5: 【0203】 The server sends a notification message to the terminal. On the terminal side, the notification is displayed to the user. The input is the notification message, and the output is the display screen. 【0204】 Step 6: 【0205】 The device recognizes the user's emotional state in real time. It uses the smartphone's camera and microphone to analyze facial expressions and voice data through Google Cloud's emotion analysis API. The input is the user's emotional data, and the output is the emotional state. 【0206】 Step 7: 【0207】 The server adjusts the notification content based on the results of sentiment recognition. It adds information to the risk notification to reduce the user's stress and anxiety. The input is the emotional state, and the output is the adjusted notification content. An example of a prompt is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering the emotional state." 【0208】 Step 8: 【0209】 The server resends the adjusted notification to the terminal, providing the user with the most relevant information. The input is the adjusted notification content, and the output is the final display. 【0210】 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. 【0211】 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. 【0212】 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. 【0213】 [Second Embodiment] 【0214】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0215】 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. 【0216】 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). 【0217】 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. 【0218】 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. 【0219】 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). 【0220】 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. 【0221】 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. 【0222】 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. 【0223】 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. 【0224】 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. 【0225】 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". 【0226】 In implementing this invention, the system mainly consists of three components: a server, a terminal, and a user. The specific operation of this system is described below. 【0227】 The server first automatically retrieves necessary information from the internet and databases based on keywords and information sources set for information gathering. It efficiently collects data using web scraping techniques and API access. The collected data is then filtered to remove noise and irrelevant information. 【0228】 Next, the server uses advanced analytical tools and natural language processing techniques to analyze the collected information. From the results of this analysis, risk factors are extracted, and basic data is generated to evaluate their importance and urgency. 【0229】 In the evaluation process, risk scoring is performed based on the analysis results. If a risk exceeding the threshold is detected, that information is promptly transmitted to the relevant terminals via a notification system. 【0230】 The device receives notifications from the server and visually reports the risk situation to the user. This includes using graphs and charts that show risk scores and the scope of impact. Based on the information provided, the user can take appropriate measures as needed. 【0231】 As a concrete example, consider a case where a company needs to monitor compliance risks with new regulations. In this case, the user sets keywords related to the server, and the server collects and analyzes information 24 hours a day. When important information is detected, an alert is sent to the user's mobile device via the terminal, enabling a quick response. 【0232】 Thus, the present invention is a system that achieves faster and more accurate risk management by automating a series of processes from information gathering to analysis, evaluation, and notification. 【0233】 The following describes the processing flow. 【0234】 Step 1: 【0235】 The server automatically collects data from the internet and databases using keywords and information sources set by the user. It efficiently obtains information using web scraping and API access. 【0236】 Step 2: 【0237】 The server filters the collected data, removing irrelevant information that constitutes noise. Natural language processing is used to determine the relevance of the collected data. 【0238】 Step 3: 【0239】 The server analyzes the filtered data and identifies the risk factors involved. Generative AI models are used to understand the meaning of the data and create a foundation for risk assessment. 【0240】 Step 4: 【0241】 The server performs a risk assessment based on the analysis results. This assessment involves scoring based on importance and urgency. 【0242】 Step 5: 【0243】 If the server detects a risk exceeding a certain threshold, it generates risk information and promptly sends it to the terminal via a notification system. 【0244】 Step 6: 【0245】 The device receives notifications from the server and presents the user with the risk status. A visual representation showing the risk score and its scope of impact is displayed. 【0246】 Step 7: 【0247】 Based on the risk information provided by the device, users will consider and implement necessary countermeasures. 【0248】 (Example 1) 【0249】 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." 【0250】 In today's information society, vast amounts of data circulate via the internet, making it increasingly important for individuals and organizations to extract useful information and quickly assess risks. However, traditional methods require significant time and effort for information gathering and analysis, and the lack of means to quickly notify assessment results hinders rapid decision-making. Therefore, there is a need for systems that efficiently handle everything from data collection to analysis, evaluation, and notification. 【0251】 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. 【0252】 In this invention, the server includes information gathering means for automatically acquiring information based on relevant words and information sources received from the user, information filtering means for extracting useful information by excluding irrelevant data from the acquired information, and information analysis means for analyzing the filtered information using natural language processing technology to extract risk factors. This makes it possible to efficiently identify important risk information from the collected information and to quickly evaluate and notify it. 【0253】 "Information gathering methods" refer to techniques that automatically retrieve information from the internet or databases based on related terms and information sources specified by the user. 【0254】 "Information filtering means" refers to the process of removing irrelevant data from acquired information and extracting useful information. 【0255】 "Information analysis methods" refer to techniques that analyze filtered information using natural language processing technology and other methods to extract risk factors. 【0256】 A "risk assessment method" is a method for scoring and evaluating risks based on analysis results. 【0257】 An "information notification system" is a system for quickly notifying relevant terminals of evaluation results. 【0258】 "Visualization means" refers to methods for generating graphs and charts to visually present notified risk information to the user. 【0259】 A "settings management method" is an approach that includes a function that allows users to configure the frequency of information collection and related keywords. 【0260】 This invention is a system that automates the process from information gathering to risk assessment and notification, supporting rapid decision-making. This system primarily functions through three parties: a server, terminals, and users. Specific embodiments are described below. 【0261】 The server automatically retrieves information based on relevant keywords and information sources received from the user. Web scraping techniques are used for information gathering. Specifically, Python libraries such as BeautifulSoup and Scrapy are used to extract necessary data from web pages. Furthermore, information can be collected from social media and other data platforms via API access. 【0262】 The collected information is filtered to remove noise and unnecessary data. Regular expressions and natural language processing libraries (e.g., NLTK) are used for this purpose. Filtering ensures that only highly relevant information is selected. 【0263】 Next, the server analyzes the filtered information. Here, natural language processing techniques are used, leveraging Google Cloud Natural Language API and OpenAI models to extract risk factors. 【0264】 Based on the analyzed data, the risk is assessed. The assessment involves scoring, and if a risk exceeding a certain threshold is detected, the server promptly notifies the relevant parties. This notification is sent to the relevant terminals in real time. 【0265】 The device visualizes the received risk information and presents it to the user. This involves generating graphs and charts using D3.js and Chart.js, displaying risk scores and impact scopes. Based on this information, the user can quickly consider countermeasures. 【0266】 As a concrete example, here is an example of a prompt message for a generative AI model: "Monitor risks related to new food safety regulations. Relevant keywords are 'food safety,' 'regulations,' and 'compliance.' Notify me if there is any high-risk information." 【0267】 Thus, the present invention achieves highly accurate risk management and rapid decision-making by efficiently handling the process from information gathering to analysis, evaluation, and notification. 【0268】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0269】 Step 1: 【0270】 The server receives a prompt message from the user and sets relevant terms and information sources for information gathering. This prompt message includes the themes and related keywords to be monitored. The user provides keywords such as "food safety," "regulations," and "compliance" as input, and the server uses this to determine the scope of information to be collected. The configured information is treated as foundational information for the information gathering mechanism. 【0271】 Step 2: 【0272】 The server automatically retrieves relevant information from configured sources using web scraping techniques and APIs. For example, it extracts data from web pages using Python's BeautifulSoup or Scrapy, and downloads tweets from social media using APIs. The input is the information sources configured in step 1, and the output is a set of raw data. This collected data may contain noise, so it is processed in the next step. 【0273】 Step 3: 【0274】 The server filters the collected information to remove noise and unnecessary details. This involves extracting only relevant sentences using regular expressions and natural language processing libraries (such as NLTK). The input is the raw data obtained in step 2, and the output is clean, informational data with noise removed. This process allows for efficient and accurate subsequent analysis. 【0275】 Step 4: 【0276】 The server uses natural language processing techniques to analyze filtered, clean information. It employs the Google Cloud Natural Language API and generative AI models to extract risk factors and assess their importance. The input is filtered information data, and the output is the risk factors and their scores. This score serves as foundational data for determining urgency and importance. 【0277】 Step 5: 【0278】 The server evaluates the scored risk based on the analysis results and selects the information to be notified. If the risk score exceeds the set criteria, that information is immediately treated as a notification. The input is the scoring result from step 4, and the output is a data package of risk information to be notified. 【0279】 Step 6: 【0280】 Based on the risk information received from the server, the terminal reports the visualized risk situation to the user. Here, D3.js or Chart.js is used to generate graphs and charts showing the risk score and the scope of influence, and present them to the user. The input is the notification data from the server, and the output is the graphs and charts displayed on the user interface. 【0281】 Step 7: 【0282】 Based on the visualized information, the user plans and executes countermeasures as needed. The input is the risk information displayed on the terminal, and the output is the user's decision-making and the actions based on it. 【0283】 (Application Example 1) 【0284】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0285】 There is a problem that it is difficult to accurately extract risk factors from the diverse and vast information on the Internet and provide accurate risk information to the user in real time. In particular, it is required to efficiently collect, analyze, and notify the latest security information within limited time and resources. In existing technologies, information collection, analysis, and notification are often performed manually, which makes it difficult to respond quickly. 【0286】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0287】 In this invention, the server includes means for collecting information, means for analyzing the information, and means for performing evaluations based on the analysis results. This makes it possible to efficiently and accurately collect, analyze, and evaluate information on the internet, and to quickly notify users of high-priority risk information. 【0288】 "Means for collecting information" refers to a mechanism that automatically retrieves data from the internet or databases based on specified arguments. 【0289】 "Means for analyzing information" refers to a mechanism that processes acquired data and transforms it into meaningful information using natural language processing and statistical analysis. 【0290】 "Means of evaluation" refers to a mechanism that measures risk based on analysis results and calculates an evaluation score. 【0291】 "Means for generating notifications" refers to a mechanism that creates alerts and informational notifications for users based on their evaluation scores. 【0292】 "Means for transmitting evaluation information to an instruction device" refers to a mechanism that transmits the generated evaluation information to the user's display device and provides visual feedback. 【0293】 A "visualization method" is a mechanism that displays data as graphs or charts in order to allow users to intuitively understand evaluation information. 【0294】 A "configuration mechanism" is a system that allows users to freely adjust the frequency and parameters of the information collected. 【0295】 To implement this invention, it is necessary to build a system in which three parties—a server, a terminal, and a user—work together. The server is the central component that automatically collects, analyzes, and evaluates information. Information collection is achieved by efficiently obtaining data from the internet based on specified arguments using web scraping tools or APIs. In this process, libraries such as Python's BeautifulSoup and Selenium are utilized. 【0296】 Next, the collected information is analyzed on the server using natural language processing technology. For this purpose, libraries such as Python's NLTK and spaCy are used to analyze text data and extract risk factors. The extracted information is evaluated by a machine learning model and quantitatively assessed as a risk score using scikit-learn. This evaluation result is generated as a notification and transmitted to the device via a real-time notification service such as Firebase Cloud Messaging. 【0297】 The device receives notifications from the server and displays visualized information to the user. This information is visualized as graphs and charts through an application using React Native, providing information in an easy-to-understand format for the user. As a specific example, information on phishing attacks in a certain region is collected, and the evaluation results are immediately notified to the user via smartphone. 【0298】 Users can review the information provided through their devices and take appropriate measures against risk situations as needed. Furthermore, users can customize the information collected by setting the frequency and parameters. These settings are configured via a device application and can be adjusted through an intuitive user interface. 【0299】 As an example of a prompt sentence, a format such as "Regarding the latest security alerts, please collect information on the Internet, analyze the risks of phishing attacks and data leaks using natural language processing, and evaluate the risk scores." is used. This prompt sentence is for instructing the information collection and analysis steps in the generative AI model. 【0300】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0301】 Step 1: 【0302】 The server starts the information collection process with the arguments set by the user as input. Data is obtained from the specified information sources on the Internet using a web scraping tool (BeautifulSoup or Selenium) or an API. Through this process, related data such as phishing attack and security information is collected. 【0303】 Step 2: 【0304】 The server performs natural language understanding analysis with the collected raw data as input. Using Python libraries NLTK or spaCy, the text data is analyzed to extract risk factors. Here, word tokenization, part-of-speech tagging, context analysis, etc. are performed, and information related to risks is thus highlighted. 【0305】 Step 3: 【0306】 The server conducts an evaluation based on the analysis results. Using scikit-learn, the data is input into a machine learning model to calculate the risk score. Through this evaluation, the specific risk level is quantified from the collected information and output as the evaluation result. 【0307】 Step 4: 【0308】 The server generates notifications based on the risk score. It uses notification services such as Firebase Cloud Messaging to create messages to inform devices of the risk information. These messages contain important information that should be provided to the user immediately. 【0309】 Step 5: 【0310】 The device receives notifications sent from the server. The application, developed with React Native, generates graphs, charts, and other visualizations based on the input notifications and presents them to the user. This allows the user to visually check risk information and understand the situation. 【0311】 Step 6: 【0312】 The user takes the information displayed on the terminal as input and implements risk mitigation measures as needed. If additional settings or changes to arguments are required, this can be done using the terminal's user interface. This allows the system to access the next data collection under improved conditions. 【0313】 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. 【0314】 The present invention aims to provide more interactive and effective risk management through a system that incorporates the ability to recognize user emotions in addition to information gathering, analysis, and risk assessment. This system consists of a server, terminals, and users. 【0315】 The server first automatically collects information from the internet and databases based on keywords and information sources set by the user. This collected information is filtered to remove noise and then analyzed to identify risk factors. 【0316】 The analysis utilizes natural language processing techniques and generative AI models to perform a risk assessment. Based on this assessment, a notification is generated and sent to the user's device. 【0317】 The emotion engine recognizes the user's emotions in real time via the device. This engine can analyze the user's emotional state based on their facial expressions, voice, and input data. 【0318】 For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the content of the notification and provides the user with information through a more appropriate interface. This notification may include suggestions for reducing stress or specific measures for risk avoidance. 【0319】 Furthermore, the emotion engine accumulates user emotion data, which is then analyzed by the server and used to improve the accuracy of future risk assessments. As a result, the system will be able to provide more personalized risk management to users over time. 【0320】 Thus, the present invention provides a more specific and flexible risk management solution tailored to user needs by combining information collection and analysis with interactive risk notifications based on sentiment data. 【0321】 The following describes the processing flow. 【0322】 Step 1: 【0323】 The server automatically collects information from the internet and databases based on keywords and information sources set by the user. This collection is efficiently carried out using web scraping and API access. 【0324】 Step 2: 【0325】 The server filters the collected information and removes irrelevant data. By utilizing natural language processing techniques to select highly relevant information, the accuracy of the data is improved. 【0326】 Step 3: 【0327】 The server analyzes the filtered data and uses a generative AI model to identify risk factors. These analysis results are then used as foundational data for risk assessment. 【0328】 Step 4: 【0329】 The server performs a risk assessment based on the analysis results. It scores each risk based on its importance and urgency, and determines its impact on the user. 【0330】 Step 5: 【0331】 The terminal notifies the user based on the risk assessment received from the server. The notification includes details of the risk and countermeasures, and is displayed on the user's terminal. 【0332】 Step 6: 【0333】 The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and voice data to understand their emotional state. This allows it to determine the user's stress level and level of interest. 【0334】 Step 7: 【0335】 The server adjusts risk notifications in a way that is best suited to the user's emotions, based on data obtained from the emotion engine. For example, if the user is stressed, the frequency and content of notifications are changed to reduce the burden on the user. 【0336】 Step 8: 【0337】 Users review the information and suggestions presented on their devices and consider specific actions to mitigate risks. Customized notifications based on sentiment data enable more effective decision-making. 【0338】 (Example 2) 【0339】 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". 【0340】 Traditional warning systems performed risk analysis and assessment based on information collected from users, but they struggled to recognize users' emotions in real time and flexibly adjust notification content accordingly. As a result, users may not receive appropriate notifications when they are emotionally distressed, leading to a problem where risk management does not function effectively. 【0341】 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. 【0342】 In this invention, the server includes means for collecting information, processing means for analyzing the collected information, evaluation means for evaluating the degree of risk based on the processing results, recognition means for recognizing the user's emotions, and adjustment means for adjusting the notification content based on the recognized emotions. This makes it possible to provide appropriate and personalized risk notifications according to the user's emotions. 【0343】 "Means of obtaining" refers to the collective set of processes and techniques used to collect information. 【0344】 "Processing means" refers to devices and algorithms used to analyze collected information and derive meaningful results from that data. 【0345】 "Evaluation methods" encompass criteria and techniques for determining the degree of risk based on analysis results. 【0346】 "Generation means" refers to a mechanism for creating risk notifications based on information obtained through evaluation. 【0347】 "Recognition means" refers to technologies used to sense and judge the emotional state of a user. 【0348】 "Adjustment means" refers to methods or devices for modifying the content or format of notifications based on perceived emotions. 【0349】 The system in this invention not only collects information, analyzes that information to assess risk, but is also capable of recognizing the user's emotions in real time and appropriately adjusting the content of notifications. A specific embodiment of this system is described below. 【0350】 The server first collects necessary information from the internet and databases based on keywords and information sources specified by the user. Web scraping libraries such as Python's Scrapy and BeautifulSoup can be used for information gathering. This makes it possible to efficiently obtain data from diverse information sources. 【0351】 Next, the server analyzes the collected information. This analysis utilizes natural language processing technology and generative AI models such as GPT-4. Using this model, risk factors can be automatically identified from the collected data, and the necessary assessments can be performed. Based on the analysis results, the server generates a notification. This notification includes a summary of the risk, its impact, and suggested countermeasures. 【0352】 The server then sends the generated notification to the user's device. The device receives this notification and notifies the user visually or audibly. Possible notification formats include push notifications on smartphones and pop-up messages on PCs. 【0353】 Furthermore, the device is equipped with emotion recognition capabilities that analyze the user's facial expressions and voice input to evaluate their emotional state in real time. This may involve using facial recognition APIs or voice analysis software. This emotion data is sent to a server, and the content of notifications is tailored to the user's state. 【0354】 For example, if a user expresses concerns about "food safety," the system can collect and analyze relevant, up-to-date information and provide notifications to alleviate those concerns. An example of a prompt generated using an AI model might be: "If a user expresses concerns about food safety, please advise on what kind of reassuring notification should be sent." 【0355】 In this way, this system provides highly accurate and personalized risk management by handling everything from information gathering and analysis to adjusting notifications based on sentiment data. 【0356】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0357】 Step 1: 【0358】 The server receives keywords and information sources as input from the user. Based on this, it collects information from specified internet resources and databases. Specifically, it uses scraping tools such as Scrapy and BeautifulSoup to extract text data from web pages. The output of this process is a collection of collected text information. 【0359】 Step 2: 【0360】 The server receives the information obtained in Step 1 as input and performs filtering using regular expressions and text cleaning techniques. Specifically, it removes unnecessary noise and duplicate data. The output is a filtered and cleaned dataset. 【0361】 Step 3: 【0362】 The server performs analysis using filtered data as input. This analysis utilizes the generative AI model GPT-4, employing natural language processing techniques to identify risk factors. Specifically, it extracts highly relevant phrases and terms and evaluates their risk levels. The output consists of analysis results and risk assessment information. 【0363】 Step 4: 【0364】 The server generates a notification based on the output of step 3. Specifically, it determines the content and format of the information to be delivered to the user and creates a notification document that includes details about the risks and countermeasures. The output of this process is the generated notification message. 【0365】 Step 5: 【0366】 The device receives notifications sent from the server and displays them to the user visually or audibly. Specifically, this uses push notifications or application message display functions. The output of this step is a notification interface that the user can view. 【0367】 Step 6: 【0368】 The device collects user emotional data in real time using its camera and microphone. It acquires voice tone and facial expressions as input and uses an emotion recognition algorithm to evaluate the user's current emotional state. The output is data indicating the user's emotional state. 【0369】 Step 7: 【0370】 The server receives the emotion data obtained in step 6 as input and adjusts the notification. Specifically, it modifies the tone and content of the message according to the emotional state and reconstructs it to reduce psychological burden. The output of this step is the adjusted notification message. 【0371】 Step 8: 【0372】 The user receives a final notification message and takes appropriate action regarding the risk. Specifically, they make individual actions and decisions based on the notification content. This output represents the specific actions the user takes based on the information they have received. 【0373】 (Application Example 2) 【0374】 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 as the "terminal". 【0375】 In modern society, there is a need to effectively manage important risk information amidst information overload. However, conventional risk management systems provide information without considering the user's emotional state, resulting in limitations in information acceptance and effectiveness. Furthermore, they lack the flexibility to respond to users' emotions in situations where they experience stress or anxiety. This invention aims to solve these problems and provide users with personalized information. 【0376】 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. 【0377】 In this invention, the server includes means for collecting information, means for analyzing the collected information, means for performing a risk assessment based on the analysis results, means for recognizing the user's emotions, and means for adjusting risk notifications according to the user's emotional state. This makes it possible to provide personalized risk information that takes the user's emotional state into consideration and to improve the effective receptivity of the information. 【0378】 "Means for collecting information" refers to a device or method that automatically acquires information from the internet, databases, etc., based on specified keywords. 【0379】 "Means for analyzing collected information" refers to a device or method that uses natural language processing techniques to analyze data in order to remove noise from the collected data and identify risk factors. 【0380】 "Means of risk assessment" refers to a device or method that determines potential hazards based on analyzed data and quantifies or qualitatively evaluates their importance and likelihood. 【0381】 "Means for generating risk notifications" refers to a device or method for generating messages to notify users of warnings or information based on the results of a risk assessment. 【0382】 "Emotion recognition means" refers to a device or method for recognizing a user's mental state and emotions in real time by analyzing the user's facial expressions, voice, and input data. 【0383】 "Means for adjusting risk notifications" refers to a device or method that optimizes the content and format of risk notifications according to the user's perceived emotional state, and provides information in the most effective way for the user. 【0384】 The system implementing this invention consists of multiple components. First, the server automatically collects relevant information from the internet and databases based on keywords set by the user. This could involve implementing web scraping techniques using programming languages ​​such as Python or JavaScript. The collected information is then analyzed using natural language processing tools such as TensorFlow to identify risk factors. 【0385】 Based on the analysis results, a risk assessment is performed, and a notification is created based on the assessment results. The notification content is generated by the server and then sent to the user's device. This device is a smartphone with an application installed that runs on the Android or iOS operating system. 【0386】 The device utilizes the smartphone's camera and microphone to recognize the user's emotional state in real time. Using Google Cloud's sentiment analysis API, the system analyzes the user's emotions from facial expressions and voice input. Based on this information, the server adjusts notifications and provides specific information and means to alleviate the user's stress and anxiety. 【0387】 As a concrete example, if a user sets the keyword "financial fraud," information on the latest fraud methods will be collected and analyzed. If the system determines through emotion recognition that the user is feeling anxious, a "music playlist to relax" or a "checklist to avoid fraud" will be displayed on the device. An example of a prompt to input into the generating AI model is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering their emotional state." 【0388】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0389】 Step 1: 【0390】 The server receives keywords set by the user. Based on these keywords, it collects relevant information from the internet and databases. The input is the user's keywords, and the output is the collected information. In this step, web scraping techniques are used to automatically retrieve the data. 【0391】 Step 2: 【0392】 The server analyzes the collected information. It filters the data to remove noise and uses natural language processing techniques to identify risk factors. The input is the collected information, and the output is the analyzed risk factors. Data analysis is performed using tools such as TensorFlow. 【0393】 Step 3: 【0394】 The server performs a risk assessment based on the analysis results. This assessment quantifies or qualitatively evaluates the importance and likelihood of the risks. The input is the risk factors, and the output is the risk assessment index. This process uses assessment algorithms to analyze the risks. 【0395】 Step 4: 【0396】 The server generates notifications based on the results of the risk assessment. It selects the information to convey to the user according to the assessment indicators and creates the notification message. The input is the risk assessment indicators, and the output is the notification message. The text of the notification is adapted to the context using a generative AI model. 【0397】 Step 5: 【0398】 The server sends a notification message to the terminal. On the terminal side, the notification is displayed to the user. The input is the notification message, and the output is the display screen. 【0399】 Step 6: 【0400】 The device recognizes the user's emotional state in real time. It uses the smartphone's camera and microphone to analyze facial expressions and voice data through Google Cloud's emotion analysis API. The input is the user's emotional data, and the output is the emotional state. 【0401】 Step 7: 【0402】 The server adjusts the notification content based on the results of sentiment recognition. It adds information to the risk notification to reduce the user's stress and anxiety. The input is the emotional state, and the output is the adjusted notification content. An example of a prompt is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering the emotional state." 【0403】 Step 8: 【0404】 The server resends the adjusted notification to the terminal, providing the user with the most relevant information. The input is the adjusted notification content, and the output is the final display. 【0405】 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. 【0406】 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. 【0407】 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. 【0408】 [Third Embodiment] 【0409】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0410】 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. 【0411】 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). 【0412】 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. 【0413】 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. 【0414】 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). 【0415】 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. 【0416】 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. 【0417】 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. 【0418】 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. 【0419】 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. 【0420】 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". 【0421】 In implementing this invention, the system mainly consists of three components: a server, a terminal, and a user. The specific operation of this system is described below. 【0422】 The server first automatically retrieves necessary information from the internet and databases based on keywords and information sources set for information gathering. It efficiently collects data using web scraping techniques and API access. The collected data is then filtered to remove noise and irrelevant information. 【0423】 Next, the server uses advanced analytical tools and natural language processing techniques to analyze the collected information. From the results of this analysis, risk factors are extracted, and basic data is generated to evaluate their importance and urgency. 【0424】 In the evaluation process, risk scoring is performed based on the analysis results. If a risk exceeding the threshold is detected, that information is promptly transmitted to the relevant terminals via a notification system. 【0425】 The device receives notifications from the server and visually reports the risk situation to the user. This includes using graphs and charts that show risk scores and the scope of impact. Based on the information provided, the user can take appropriate measures as needed. 【0426】 As a concrete example, consider a case where a company needs to monitor compliance risks with new regulations. In this case, the user sets keywords related to the server, and the server collects and analyzes information 24 hours a day. When important information is detected, an alert is sent to the user's mobile device via the terminal, enabling a quick response. 【0427】 Thus, the present invention is a system that achieves faster and more accurate risk management by automating a series of processes from information gathering to analysis, evaluation, and notification. 【0428】 The following describes the processing flow. 【0429】 Step 1: 【0430】 The server automatically collects data from the internet and databases using keywords and information sources set by the user. It efficiently obtains information using web scraping and API access. 【0431】 Step 2: 【0432】 The server filters the collected data, removing irrelevant information that constitutes noise. Natural language processing is used to determine the relevance of the collected data. 【0433】 Step 3: 【0434】 The server analyzes the filtered data and identifies the risk factors involved. Generative AI models are used to understand the meaning of the data and create a foundation for risk assessment. 【0435】 Step 4: 【0436】 The server performs a risk assessment based on the analysis results. This assessment involves scoring based on importance and urgency. 【0437】 Step 5: 【0438】 If the server detects a risk exceeding a certain threshold, it generates risk information and promptly sends it to the terminal via a notification system. 【0439】 Step 6: 【0440】 The device receives notifications from the server and presents the user with the risk status. A visual representation showing the risk score and its scope of impact is displayed. 【0441】 Step 7: 【0442】 Based on the risk information provided by the device, users will consider and implement necessary countermeasures. 【0443】 (Example 1) 【0444】 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." 【0445】 In today's information society, vast amounts of data circulate via the internet, making it increasingly important for individuals and organizations to extract useful information and quickly assess risks. However, traditional methods require significant time and effort for information gathering and analysis, and the lack of means to quickly notify assessment results hinders rapid decision-making. Therefore, there is a need for systems that efficiently handle everything from data collection to analysis, evaluation, and notification. 【0446】 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. 【0447】 In this invention, the server includes information gathering means for automatically acquiring information based on relevant words and information sources received from the user, information filtering means for extracting useful information by excluding irrelevant data from the acquired information, and information analysis means for analyzing the filtered information using natural language processing technology to extract risk factors. This makes it possible to efficiently identify important risk information from the collected information and to quickly evaluate and notify it. 【0448】 "Information gathering methods" refer to techniques that automatically retrieve information from the internet or databases based on related terms and information sources specified by the user. 【0449】 "Information filtering means" refers to the process of removing irrelevant data from acquired information and extracting useful information. 【0450】 "Information analysis methods" refer to techniques that analyze filtered information using natural language processing technology and other methods to extract risk factors. 【0451】 A "risk assessment method" is a method for scoring and evaluating risks based on analysis results. 【0452】 An "information notification system" is a system for quickly notifying relevant terminals of evaluation results. 【0453】 "Visualization means" refers to methods for generating graphs and charts to visually present notified risk information to the user. 【0454】 A "settings management method" is an approach that includes a function that allows users to configure the frequency of information collection and related keywords. 【0455】 This invention is a system that automates the process from information gathering to risk assessment and notification, supporting rapid decision-making. This system primarily functions through three parties: a server, terminals, and users. Specific embodiments are described below. 【0456】 The server automatically retrieves information based on relevant keywords and information sources received from the user. Web scraping techniques are used for information gathering. Specifically, Python libraries such as BeautifulSoup and Scrapy are used to extract necessary data from web pages. Furthermore, information can be collected from social media and other data platforms via API access. 【0457】 The collected information is filtered to remove noise and unnecessary data. Regular expressions and natural language processing libraries (e.g., NLTK) are used for this purpose. Filtering ensures that only highly relevant information is selected. 【0458】 Next, the server analyzes the filtered information. Here, natural language processing techniques are used, leveraging Google Cloud Natural Language API and OpenAI models to extract risk factors. 【0459】 Based on the analyzed data, the risk is assessed. The assessment involves scoring, and if a risk exceeding a certain threshold is detected, the server promptly notifies the relevant parties. This notification is sent to the relevant terminals in real time. 【0460】 The device visualizes the received risk information and presents it to the user. This involves generating graphs and charts using D3.js and Chart.js, displaying risk scores and impact scopes. Based on this information, the user can quickly consider countermeasures. 【0461】 As a concrete example, here is an example of a prompt message for a generative AI model: "Monitor risks related to new food safety regulations. Relevant keywords are 'food safety,' 'regulations,' and 'compliance.' Notify me if there is any high-risk information." 【0462】 Thus, the present invention achieves highly accurate risk management and rapid decision-making by efficiently handling the process from information gathering to analysis, evaluation, and notification. 【0463】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0464】 Step 1: 【0465】 The server receives a prompt message from the user and sets relevant terms and information sources for information gathering. This prompt message includes the themes and related keywords to be monitored. The user provides keywords such as "food safety," "regulations," and "compliance" as input, and the server uses this to determine the scope of information to be collected. The configured information is treated as foundational information for the information gathering mechanism. 【0466】 Step 2: 【0467】 The server automatically retrieves relevant information from configured sources using web scraping techniques and APIs. For example, it extracts data from web pages using Python's BeautifulSoup or Scrapy, and downloads tweets from social media using APIs. The input is the information sources configured in step 1, and the output is a set of raw data. This collected data may contain noise, so it is processed in the next step. 【0468】 Step 3: 【0469】 The server filters the collected information to remove noise and unnecessary details. This involves extracting only relevant sentences using regular expressions and natural language processing libraries (such as NLTK). The input is the raw data obtained in step 2, and the output is clean, informational data with noise removed. This process allows for efficient and accurate subsequent analysis. 【0470】 Step 4: 【0471】 The server uses natural language processing techniques to analyze filtered, clean information. It employs the Google Cloud Natural Language API and generative AI models to extract risk factors and assess their importance. The input is filtered information data, and the output is the risk factors and their scores. This score serves as foundational data for determining urgency and importance. 【0472】 Step 5: 【0473】 The server evaluates the scored risk based on the analysis results and selects the information to be notified. If the risk score exceeds the set criteria, that information is immediately treated as a notification. The input is the scoring result from step 4, and the output is a data package of risk information to be notified. 【0474】 Step 6: 【0475】 The terminal reports a visualized risk situation to the user based on risk information received from the server. Here, D3.js and Chart.js are used to generate graphs and charts showing risk scores and impact scope, and present them to the user. The input is notification data from the server, and the output is the graphs and charts displayed on the user interface. 【0476】 Step 7: 【0477】 Based on the visualized information, users plan and implement countermeasures as needed. The input is the risk information displayed on the terminal, and the output is the user's decision and the actions taken based on it. 【0478】 (Application Example 1) 【0479】 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." 【0480】 There is a challenge in accurately extracting risk factors from the vast and diverse information available on the internet and providing users with timely and accurate risk information. In particular, there is a need to efficiently collect, analyze, and notify users of the latest security information within limited time and resources. With existing technologies, information collection, analysis, and notification are often done manually, which makes it difficult to respond quickly. 【0481】 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. 【0482】 In this invention, the server includes means for collecting information, means for analyzing the information, and means for performing evaluations based on the analysis results. This makes it possible to efficiently and accurately collect, analyze, and evaluate information on the internet, and to quickly notify users of high-priority risk information. 【0483】 "Means for collecting information" refers to a mechanism that automatically retrieves data from the internet or databases based on specified arguments. 【0484】 "Means for analyzing information" refers to a mechanism that processes acquired data and transforms it into meaningful information using natural language processing and statistical analysis. 【0485】 "Means of evaluation" refers to a mechanism that measures risk based on analysis results and calculates an evaluation score. 【0486】 "Means for generating notifications" refers to a mechanism that creates alerts and informational notifications for users based on their evaluation scores. 【0487】 "Means for transmitting evaluation information to an instruction device" refers to a mechanism that transmits the generated evaluation information to the user's display device and provides visual feedback. 【0488】 A "visualization method" is a mechanism that displays data as graphs or charts in order to allow users to intuitively understand evaluation information. 【0489】 A "configuration mechanism" is a system that allows users to freely adjust the frequency and parameters of the information collected. 【0490】 To implement this invention, it is necessary to build a system in which three parties—a server, a terminal, and a user—work together. The server is the central component that automatically collects, analyzes, and evaluates information. Information collection is achieved by efficiently obtaining data from the internet based on specified arguments using web scraping tools or APIs. In this process, libraries such as Python's BeautifulSoup and Selenium are utilized. 【0491】 Next, the collected information is analyzed on the server using natural language processing technology. For this purpose, libraries such as Python's NLTK and spaCy are used to analyze text data and extract risk factors. The extracted information is evaluated by a machine learning model and quantitatively assessed as a risk score using scikit-learn. This evaluation result is generated as a notification and transmitted to the device via a real-time notification service such as Firebase Cloud Messaging. 【0492】 The device receives notifications from the server and displays visualized information to the user. This information is visualized as graphs and charts through an application using React Native, providing information in an easy-to-understand format for the user. As a specific example, information on phishing attacks in a certain region is collected, and the evaluation results are immediately notified to the user via smartphone. 【0493】 Users can review the information provided through their devices and take appropriate measures against risk situations as needed. Furthermore, users can customize the information collected by setting the frequency and parameters. These settings are configured via a device application and can be adjusted through an intuitive user interface. 【0494】 An example of a prompt might be: "Collect information from the internet about the latest security alerts, analyze the risks of phishing attacks and data breaches using natural language processing, and evaluate the risk score." This prompt is used to instruct the generative AI model on the information gathering and analysis steps. 【0495】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0496】 Step 1: 【0497】 The server takes the user-defined arguments as input and begins the information gathering process. It retrieves data from specified sources on the internet using web scraping tools (such as BeautifulSoup or Selenium) or APIs. This process collects relevant data, including information on phishing attacks and security threats. 【0498】 Step 2: 【0499】 The server performs natural language processing analysis on the collected raw data as input. Using Python libraries such as NLTK and spaCy, it analyzes the text data and extracts risk factors. This involves word tokenization, part-of-speech tagging, and contextual analysis, which highlights information related to risk. 【0500】 Step 3: 【0501】 The server performs an evaluation based on the analysis results. It uses scikit-learn to input the data into a machine learning model and calculate a risk score. This evaluation quantifies specific risk levels from the collected information and outputs them as evaluation results. 【0502】 Step 4: 【0503】 The server generates notifications based on the risk score. It uses notification services such as Firebase Cloud Messaging to create messages to inform devices of the risk information. These messages contain important information that should be provided to the user immediately. 【0504】 Step 5: 【0505】 The device receives notifications sent from the server. The application, developed with React Native, generates graphs, charts, and other visualizations based on the input notifications and presents them to the user. This allows the user to visually check risk information and understand the situation. 【0506】 Step 6: 【0507】 The user takes the information displayed on the terminal as input and implements risk mitigation measures as needed. If additional settings or changes to arguments are required, this can be done using the terminal's user interface. This allows the system to access the next data collection under improved conditions. 【0508】 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. 【0509】 The present invention aims to provide more interactive and effective risk management through a system that incorporates the ability to recognize user emotions in addition to information gathering, analysis, and risk assessment. This system consists of a server, terminals, and users. 【0510】 The server first automatically collects information from the internet and databases based on keywords and information sources set by the user. This collected information is filtered to remove noise and then analyzed to identify risk factors. 【0511】 The analysis utilizes natural language processing techniques and generative AI models to perform a risk assessment. Based on this assessment, a notification is generated and sent to the user's device. 【0512】 The emotion engine recognizes the user's emotions in real time via the device. This engine can analyze the user's emotional state based on their facial expressions, voice, and input data. 【0513】 For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the content of the notification and provides the user with information through a more appropriate interface. This notification may include suggestions for reducing stress or specific measures for risk avoidance. 【0514】 Furthermore, the emotion engine accumulates user emotion data, which is then analyzed by the server and used to improve the accuracy of future risk assessments. As a result, the system will be able to provide more personalized risk management to users over time. 【0515】 Thus, the present invention provides a more specific and flexible risk management solution tailored to user needs by combining information collection and analysis with interactive risk notifications based on sentiment data. 【0516】 The following describes the processing flow. 【0517】 Step 1: 【0518】 The server automatically collects information from the internet and databases based on keywords and information sources set by the user. This collection is efficiently carried out using web scraping and API access. 【0519】 Step 2: 【0520】 The server filters the collected information and removes irrelevant data. By utilizing natural language processing techniques to select highly relevant information, the accuracy of the data is improved. 【0521】 Step 3: 【0522】 The server analyzes the filtered data and uses a generative AI model to identify risk factors. These analysis results are then used as foundational data for risk assessment. 【0523】 Step 4: 【0524】 The server performs a risk assessment based on the analysis results. It scores each risk based on its importance and urgency, and determines its impact on the user. 【0525】 Step 5: 【0526】 The terminal notifies the user based on the risk assessment received from the server. The notification includes details of the risk and countermeasures, and is displayed on the user's terminal. 【0527】 Step 6: 【0528】 The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and voice data to understand their emotional state. This allows it to determine the user's stress level and level of interest. 【0529】 Step 7: 【0530】 The server adjusts risk notifications in a way that is best suited to the user's emotions, based on data obtained from the emotion engine. For example, if the user is stressed, the frequency and content of notifications are changed to reduce the burden on the user. 【0531】 Step 8: 【0532】 Users review the information and suggestions presented on their devices and consider specific actions to mitigate risks. Customized notifications based on sentiment data enable more effective decision-making. 【0533】 (Example 2) 【0534】 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." 【0535】 Traditional warning systems performed risk analysis and assessment based on information collected from users, but they struggled to recognize users' emotions in real time and flexibly adjust notification content accordingly. As a result, users may not receive appropriate notifications when they are emotionally distressed, leading to a problem where risk management does not function effectively. 【0536】 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. 【0537】 In this invention, the server includes means for collecting information, processing means for analyzing the collected information, evaluation means for evaluating the degree of risk based on the processing results, recognition means for recognizing the user's emotions, and adjustment means for adjusting the notification content based on the recognized emotions. This makes it possible to provide appropriate and personalized risk notifications according to the user's emotions. 【0538】 "Means of obtaining" refers to the collective set of processes and techniques used to collect information. 【0539】 "Processing means" refers to devices and algorithms used to analyze collected information and derive meaningful results from that data. 【0540】 "Evaluation methods" encompass criteria and techniques for determining the degree of risk based on analysis results. 【0541】 "Generation means" refers to a mechanism for creating risk notifications based on information obtained through evaluation. 【0542】 "Recognition means" refers to technologies used to sense and judge the emotional state of a user. 【0543】 "Adjustment means" refers to methods or devices for modifying the content or format of notifications based on perceived emotions. 【0544】 The system in this invention not only collects information, analyzes that information to assess risk, but is also capable of recognizing the user's emotions in real time and appropriately adjusting the content of notifications. A specific embodiment of this system is described below. 【0545】 The server first collects necessary information from the internet and databases based on keywords and information sources specified by the user. Web scraping libraries such as Python's Scrapy and BeautifulSoup can be used for information gathering. This makes it possible to efficiently obtain data from diverse information sources. 【0546】 Next, the server analyzes the collected information. This analysis utilizes natural language processing technology and generative AI models such as GPT-4. Using this model, risk factors can be automatically identified from the collected data, and the necessary assessments can be performed. Based on the analysis results, the server generates a notification. This notification includes a summary of the risk, its impact, and suggested countermeasures. 【0547】 The server then sends the generated notification to the user's device. The device receives this notification and notifies the user visually or audibly. Possible notification formats include push notifications on smartphones and pop-up messages on PCs. 【0548】 Furthermore, the device is equipped with emotion recognition capabilities that analyze the user's facial expressions and voice input to evaluate their emotional state in real time. This may involve using facial recognition APIs or voice analysis software. This emotion data is sent to a server, and the content of notifications is tailored to the user's state. 【0549】 For example, if a user expresses concerns about "food safety," the system can collect and analyze relevant, up-to-date information and provide notifications to alleviate those concerns. An example of a prompt generated using an AI model might be: "If a user expresses concerns about food safety, please advise on what kind of reassuring notification should be sent." 【0550】 In this way, this system provides highly accurate and personalized risk management by handling everything from information gathering and analysis to adjusting notifications based on sentiment data. 【0551】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0552】 Step 1: 【0553】 The server receives keywords and information sources as input from the user. Based on this, it collects information from specified internet resources and databases. Specifically, it uses scraping tools such as Scrapy and BeautifulSoup to extract text data from web pages. The output of this process is a collection of collected text information. 【0554】 Step 2: 【0555】 The server receives the information obtained in Step 1 as input and performs filtering using regular expressions and text cleaning techniques. Specifically, it removes unnecessary noise and duplicate data. The output is a filtered and cleaned dataset. 【0556】 Step 3: 【0557】 The server performs analysis using filtered data as input. This analysis utilizes the generative AI model GPT-4, employing natural language processing techniques to identify risk factors. Specifically, it extracts highly relevant phrases and terms and evaluates their risk levels. The output consists of analysis results and risk assessment information. 【0558】 Step 4: 【0559】 The server generates a notification based on the output of step 3. Specifically, it determines the content and format of the information to be delivered to the user and creates a notification document that includes details about the risks and countermeasures. The output of this process is the generated notification message. 【0560】 Step 5: 【0561】 The device receives notifications sent from the server and displays them to the user visually or audibly. Specifically, this uses push notifications or application message display functions. The output of this step is a notification interface that the user can view. 【0562】 Step 6: 【0563】 The device collects user emotional data in real time using its camera and microphone. It acquires voice tone and facial expressions as input and uses an emotion recognition algorithm to evaluate the user's current emotional state. The output is data indicating the user's emotional state. 【0564】 Step 7: 【0565】 The server receives the emotion data obtained in step 6 as input and adjusts the notification. Specifically, it modifies the tone and content of the message according to the emotional state and reconstructs it to reduce psychological burden. The output of this step is the adjusted notification message. 【0566】 Step 8: 【0567】 The user receives a final notification message and takes appropriate action regarding the risk. Specifically, they make individual actions and decisions based on the notification content. This output represents the specific actions the user takes based on the information they have received. 【0568】 (Application Example 2) 【0569】 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." 【0570】 In modern society, there is a need to effectively manage important risk information amidst information overload. However, conventional risk management systems provide information without considering the user's emotional state, resulting in limitations in information acceptance and effectiveness. Furthermore, they lack the flexibility to respond to users' emotions in situations where they experience stress or anxiety. This invention aims to solve these problems and provide users with personalized information. 【0571】 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. 【0572】 In this invention, the server includes means for collecting information, means for analyzing the collected information, means for performing a risk assessment based on the analysis results, means for recognizing the user's emotions, and means for adjusting risk notifications according to the user's emotional state. This makes it possible to provide personalized risk information that takes the user's emotional state into consideration and to improve the effective receptivity of the information. 【0573】 "Means for collecting information" refers to a device or method that automatically acquires information from the internet, databases, etc., based on specified keywords. 【0574】 "Means for analyzing collected information" refers to a device or method that uses natural language processing techniques to analyze data in order to remove noise from the collected data and identify risk factors. 【0575】 "Means of risk assessment" refers to a device or method that determines potential hazards based on analyzed data and quantifies or qualitatively evaluates their importance and likelihood. 【0576】 "Means for generating risk notifications" refers to a device or method for generating messages to notify users of warnings or information based on the results of a risk assessment. 【0577】 "Emotion recognition means" refers to a device or method for recognizing a user's mental state and emotions in real time by analyzing the user's facial expressions, voice, and input data. 【0578】 "Means for adjusting risk notifications" refers to a device or method that optimizes the content and format of risk notifications according to the user's perceived emotional state, and provides information in the most effective way for the user. 【0579】 The system implementing this invention consists of multiple components. First, the server automatically collects relevant information from the internet and databases based on keywords set by the user. This could involve implementing web scraping techniques using programming languages ​​such as Python or JavaScript. The collected information is then analyzed using natural language processing tools such as TensorFlow to identify risk factors. 【0580】 Based on the analysis results, a risk assessment is performed, and a notification is created based on the assessment results. The notification content is generated by the server and then sent to the user's device. This device is a smartphone with an application installed that runs on the Android or iOS operating system. 【0581】 The device utilizes the smartphone's camera and microphone to recognize the user's emotional state in real time. Using Google Cloud's sentiment analysis API, the system analyzes the user's emotions from facial expressions and voice input. Based on this information, the server adjusts notifications and provides specific information and means to alleviate the user's stress and anxiety. 【0582】 As a concrete example, if a user sets the keyword "financial fraud," information on the latest fraud methods will be collected and analyzed. If the system determines through emotion recognition that the user is feeling anxious, a "music playlist to relax" or a "checklist to avoid fraud" will be displayed on the device. An example of a prompt to input into the generating AI model is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering their emotional state." 【0583】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0584】 Step 1: 【0585】 The server receives keywords set by the user. Based on these keywords, it collects relevant information from the internet and databases. The input is the user's keywords, and the output is the collected information. In this step, web scraping techniques are used to automatically retrieve the data. 【0586】 Step 2: 【0587】 The server analyzes the collected information. It filters the data to remove noise and uses natural language processing techniques to identify risk factors. The input is the collected information, and the output is the analyzed risk factors. Data analysis is performed using tools such as TensorFlow. 【0588】 Step 3: 【0589】 The server performs a risk assessment based on the analysis results. This assessment quantifies or qualitatively evaluates the importance and likelihood of the risks. The input is the risk factors, and the output is the risk assessment index. This process uses assessment algorithms to analyze the risks. 【0590】 Step 4: 【0591】 The server generates notifications based on the results of the risk assessment. It selects the information to convey to the user according to the assessment indicators and creates the notification message. The input is the risk assessment indicators, and the output is the notification message. The text of the notification is adapted to the context using a generative AI model. 【0592】 Step 5: 【0593】 The server sends a notification message to the terminal. On the terminal side, the notification is displayed to the user. The input is the notification message, and the output is the display screen. 【0594】 Step 6: 【0595】 The device recognizes the user's emotional state in real time. It uses the smartphone's camera and microphone to analyze facial expressions and voice data through Google Cloud's emotion analysis API. The input is the user's emotional data, and the output is the emotional state. 【0596】 Step 7: 【0597】 The server adjusts the notification content based on the results of sentiment recognition. It adds information to the risk notification to reduce the user's stress and anxiety. The input is the emotional state, and the output is the adjusted notification content. An example of a prompt is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering the emotional state." 【0598】 Step 8: 【0599】 The server resends the adjusted notification to the terminal, providing the user with the most relevant information. The input is the adjusted notification content, and the output is the final display. 【0600】 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. 【0601】 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. 【0602】 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. 【0603】 [Fourth Embodiment] 【0604】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0605】 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. 【0606】 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). 【0607】 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. 【0608】 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. 【0609】 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). 【0610】 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. 【0611】 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. 【0612】 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. 【0613】 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. 【0614】 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. 【0615】 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. 【0616】 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". 【0617】 In implementing this invention, the system mainly consists of three components: a server, a terminal, and a user. The specific operation of this system is described below. 【0618】 The server first automatically retrieves necessary information from the internet and databases based on keywords and information sources set for information gathering. It efficiently collects data using web scraping techniques and API access. The collected data is then filtered to remove noise and irrelevant information. 【0619】 Next, the server uses advanced analytical tools and natural language processing techniques to analyze the collected information. From the results of this analysis, risk factors are extracted, and basic data is generated to evaluate their importance and urgency. 【0620】 In the evaluation process, risk scoring is performed based on the analysis results. If a risk exceeding the threshold is detected, that information is promptly transmitted to the relevant terminals via a notification system. 【0621】 The device receives notifications from the server and visually reports the risk situation to the user. This includes using graphs and charts that show risk scores and the scope of impact. Based on the information provided, the user can take appropriate measures as needed. 【0622】 As a concrete example, consider a case where a company needs to monitor compliance risks with new regulations. In this case, the user sets keywords related to the server, and the server collects and analyzes information 24 hours a day. When important information is detected, an alert is sent to the user's mobile device via the terminal, enabling a quick response. 【0623】 Thus, the present invention is a system that achieves faster and more accurate risk management by automating a series of processes from information gathering to analysis, evaluation, and notification. 【0624】 The following describes the processing flow. 【0625】 Step 1: 【0626】 The server automatically collects data from the internet and databases using keywords and information sources set by the user. It efficiently obtains information using web scraping and API access. 【0627】 Step 2: 【0628】 The server filters the collected data, removing irrelevant information that constitutes noise. Natural language processing is used to determine the relevance of the collected data. 【0629】 Step 3: 【0630】 The server analyzes the filtered data and identifies the risk factors involved. Generative AI models are used to understand the meaning of the data and create a foundation for risk assessment. 【0631】 Step 4: 【0632】 The server performs a risk assessment based on the analysis results. This assessment involves scoring based on importance and urgency. 【0633】 Step 5: 【0634】 If the server detects a risk exceeding a certain threshold, it generates risk information and promptly sends it to the terminal via a notification system. 【0635】 Step 6: 【0636】 The device receives notifications from the server and presents the user with the risk status. A visual representation showing the risk score and its scope of impact is displayed. 【0637】 Step 7: 【0638】 Based on the risk information provided by the device, users will consider and implement necessary countermeasures. 【0639】 (Example 1) 【0640】 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". 【0641】 In today's information society, vast amounts of data circulate via the internet, making it increasingly important for individuals and organizations to extract useful information and quickly assess risks. However, traditional methods require significant time and effort for information gathering and analysis, and the lack of means to quickly notify assessment results hinders rapid decision-making. Therefore, there is a need for systems that efficiently handle everything from data collection to analysis, evaluation, and notification. 【0642】 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. 【0643】 In this invention, the server includes information gathering means for automatically acquiring information based on relevant words and information sources received from the user, information filtering means for extracting useful information by excluding irrelevant data from the acquired information, and information analysis means for analyzing the filtered information using natural language processing technology to extract risk factors. This makes it possible to efficiently identify important risk information from the collected information and to quickly evaluate and notify it. 【0644】 "Information gathering methods" refer to techniques that automatically retrieve information from the internet or databases based on related terms and information sources specified by the user. 【0645】 "Information filtering means" refers to the process of removing irrelevant data from acquired information and extracting useful information. 【0646】 "Information analysis methods" refer to techniques that analyze filtered information using natural language processing technology and other methods to extract risk factors. 【0647】 A "risk assessment method" is a method for scoring and evaluating risks based on analysis results. 【0648】 An "information notification system" is a system for quickly notifying relevant terminals of evaluation results. 【0649】 "Visualization means" refers to methods for generating graphs and charts to visually present notified risk information to the user. 【0650】 A "settings management method" is an approach that includes a function that allows users to configure the frequency of information collection and related keywords. 【0651】 This invention is a system that automates the process from information gathering to risk assessment and notification, supporting rapid decision-making. This system primarily functions through three parties: a server, terminals, and users. Specific embodiments are described below. 【0652】 The server automatically retrieves information based on relevant keywords and information sources received from the user. Web scraping techniques are used for information gathering. Specifically, Python libraries such as BeautifulSoup and Scrapy are used to extract necessary data from web pages. Furthermore, information can be collected from social media and other data platforms via API access. 【0653】 The collected information is filtered to remove noise and unnecessary data. Regular expressions and natural language processing libraries (e.g., NLTK) are used for this purpose. Filtering ensures that only highly relevant information is selected. 【0654】 Next, the server analyzes the filtered information. Here, natural language processing techniques are used, leveraging Google Cloud Natural Language API and OpenAI models to extract risk factors. 【0655】 Based on the analyzed data, the risk is assessed. The assessment involves scoring, and if a risk exceeding a certain threshold is detected, the server promptly notifies the relevant parties. This notification is sent to the relevant terminals in real time. 【0656】 The device visualizes the received risk information and presents it to the user. This involves generating graphs and charts using D3.js and Chart.js, displaying risk scores and impact scopes. Based on this information, the user can quickly consider countermeasures. 【0657】 As a concrete example, here is an example of a prompt message for a generative AI model: "Monitor risks related to new food safety regulations. Relevant keywords are 'food safety,' 'regulations,' and 'compliance.' Notify me if there is any high-risk information." 【0658】 Thus, the present invention achieves highly accurate risk management and rapid decision-making by efficiently handling the process from information gathering to analysis, evaluation, and notification. 【0659】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0660】 Step 1: 【0661】 The server receives a prompt message from the user and sets relevant terms and information sources for information gathering. This prompt message includes the themes and related keywords to be monitored. The user provides keywords such as "food safety," "regulations," and "compliance" as input, and the server uses this to determine the scope of information to be collected. The configured information is treated as foundational information for the information gathering mechanism. 【0662】 Step 2: 【0663】 The server automatically retrieves relevant information from configured sources using web scraping techniques and APIs. For example, it extracts data from web pages using Python's BeautifulSoup or Scrapy, and downloads tweets from social media using APIs. The input is the information sources configured in step 1, and the output is a set of raw data. This collected data may contain noise, so it is processed in the next step. 【0664】 Step 3: 【0665】 The server filters the collected information to remove noise and unnecessary details. This involves extracting only relevant sentences using regular expressions and natural language processing libraries (such as NLTK). The input is the raw data obtained in step 2, and the output is clean, informational data with noise removed. This process allows for efficient and accurate subsequent analysis. 【0666】 Step 4: 【0667】 The server uses natural language processing techniques to analyze filtered, clean information. It employs the Google Cloud Natural Language API and generative AI models to extract risk factors and assess their importance. The input is filtered information data, and the output is the risk factors and their scores. This score serves as foundational data for determining urgency and importance. 【0668】 Step 5: 【0669】 The server evaluates the scored risk based on the analysis results and selects the information to be notified. If the risk score exceeds the set criteria, that information is immediately treated as a notification. The input is the scoring result from step 4, and the output is a data package of risk information to be notified. 【0670】 Step 6: 【0671】 The terminal reports a visualized risk situation to the user based on risk information received from the server. Here, D3.js and Chart.js are used to generate graphs and charts showing risk scores and impact scope, and present them to the user. The input is notification data from the server, and the output is the graphs and charts displayed on the user interface. 【0672】 Step 7: 【0673】 Based on the visualized information, users plan and implement countermeasures as needed. The input is the risk information displayed on the terminal, and the output is the user's decision and the actions taken based on it. 【0674】 (Application Example 1) 【0675】 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". 【0676】 There is a challenge in accurately extracting risk factors from the vast and diverse information available on the internet and providing users with timely and accurate risk information. In particular, there is a need to efficiently collect, analyze, and notify users of the latest security information within limited time and resources. With existing technologies, information collection, analysis, and notification are often done manually, which makes it difficult to respond quickly. 【0677】 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. 【0678】 In this invention, the server includes means for collecting information, means for analyzing the information, and means for performing evaluations based on the analysis results. This makes it possible to efficiently and accurately collect, analyze, and evaluate information on the internet, and to quickly notify users of high-priority risk information. 【0679】 "Means for collecting information" refers to a mechanism that automatically retrieves data from the internet or databases based on specified arguments. 【0680】 "Means for analyzing information" refers to a mechanism that processes acquired data and transforms it into meaningful information using natural language processing and statistical analysis. 【0681】 "Means of evaluation" refers to a mechanism that measures risk based on analysis results and calculates an evaluation score. 【0682】 "Means for generating notifications" refers to a mechanism that creates alerts and informational notifications for users based on their evaluation scores. 【0683】 "Means for transmitting evaluation information to an instruction device" refers to a mechanism that transmits the generated evaluation information to the user's display device and provides visual feedback. 【0684】 A "visualization method" is a mechanism that displays data as graphs or charts in order to allow users to intuitively understand evaluation information. 【0685】 A "configuration mechanism" is a system that allows users to freely adjust the frequency and parameters of the information collected. 【0686】 To implement this invention, it is necessary to build a system in which three parties—a server, a terminal, and a user—work together. The server is the central component that automatically collects, analyzes, and evaluates information. Information collection is achieved by efficiently obtaining data from the internet based on specified arguments using web scraping tools or APIs. In this process, libraries such as Python's BeautifulSoup and Selenium are utilized. 【0687】 Next, the collected information is analyzed on the server using natural language processing technology. For this purpose, libraries such as Python's NLTK and spaCy are used to analyze text data and extract risk factors. The extracted information is evaluated by a machine learning model and quantitatively assessed as a risk score using scikit-learn. This evaluation result is generated as a notification and transmitted to the device via a real-time notification service such as Firebase Cloud Messaging. 【0688】 The device receives notifications from the server and displays visualized information to the user. This information is visualized as graphs and charts through an application using React Native, providing information in an easy-to-understand format for the user. As a specific example, information on phishing attacks in a certain region is collected, and the evaluation results are immediately notified to the user via smartphone. 【0689】 Users can review the information provided through their devices and take appropriate measures against risk situations as needed. Furthermore, users can customize the information collected by setting the frequency and parameters. These settings are configured via a device application and can be adjusted through an intuitive user interface. 【0690】 An example of a prompt might be: "Collect information from the internet about the latest security alerts, analyze the risks of phishing attacks and data breaches using natural language processing, and evaluate the risk score." This prompt is used to instruct the generative AI model on the information gathering and analysis steps. 【0691】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0692】 Step 1: 【0693】 The server takes the user-defined arguments as input and begins the information gathering process. It retrieves data from specified sources on the internet using web scraping tools (such as BeautifulSoup or Selenium) or APIs. This process collects relevant data, including information on phishing attacks and security threats. 【0694】 Step 2: 【0695】 The server performs natural language processing analysis on the collected raw data as input. Using Python libraries such as NLTK and spaCy, it analyzes the text data and extracts risk factors. This involves word tokenization, part-of-speech tagging, and contextual analysis, which highlights information related to risk. 【0696】 Step 3: 【0697】 The server performs an evaluation based on the analysis results. It uses scikit-learn to input the data into a machine learning model and calculate a risk score. This evaluation quantifies specific risk levels from the collected information and outputs them as evaluation results. 【0698】 Step 4: 【0699】 The server generates notifications based on the risk score. It uses notification services such as Firebase Cloud Messaging to create messages to inform devices of the risk information. These messages contain important information that should be provided to the user immediately. 【0700】 Step 5: 【0701】 The device receives notifications sent from the server. The application, developed with React Native, generates graphs, charts, and other visualizations based on the input notifications and presents them to the user. This allows the user to visually check risk information and understand the situation. 【0702】 Step 6: 【0703】 The user takes the information displayed on the terminal as input and implements risk mitigation measures as needed. If additional settings or changes to arguments are required, this can be done using the terminal's user interface. This allows the system to access the next data collection under improved conditions. 【0704】 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. 【0705】 The present invention aims to provide more interactive and effective risk management through a system that incorporates the ability to recognize user emotions in addition to information gathering, analysis, and risk assessment. This system consists of a server, terminals, and users. 【0706】 The server first automatically collects information from the internet and databases based on keywords and information sources set by the user. This collected information is filtered to remove noise and then analyzed to identify risk factors. 【0707】 The analysis utilizes natural language processing techniques and generative AI models to perform a risk assessment. Based on this assessment, a notification is generated and sent to the user's device. 【0708】 The emotion engine recognizes the user's emotions in real time via the device. This engine can analyze the user's emotional state based on their facial expressions, voice, and input data. 【0709】 For example, if the emotion engine determines that a user is experiencing stress, the server adjusts the content of the notification and provides the user with information through a more appropriate interface. This notification may include suggestions for reducing stress or specific measures for risk avoidance. 【0710】 Furthermore, the emotion engine accumulates user emotion data, which is then analyzed by the server and used to improve the accuracy of future risk assessments. As a result, the system will be able to provide more personalized risk management to users over time. 【0711】 Thus, the present invention provides a more specific and flexible risk management solution tailored to user needs by combining information collection and analysis with interactive risk notifications based on sentiment data. 【0712】 The following describes the processing flow. 【0713】 Step 1: 【0714】 The server automatically collects information from the internet and databases based on keywords and information sources set by the user. This collection is efficiently carried out using web scraping and API access. 【0715】 Step 2: 【0716】 The server filters the collected information and removes irrelevant data. By utilizing natural language processing techniques to select highly relevant information, the accuracy of the data is improved. 【0717】 Step 3: 【0718】 The server analyzes the filtered data and uses a generative AI model to identify risk factors. These analysis results are then used as foundational data for risk assessment. 【0719】 Step 4: 【0720】 The server performs a risk assessment based on the analysis results. It scores each risk based on its importance and urgency, and determines its impact on the user. 【0721】 Step 5: 【0722】 The terminal notifies the user based on the risk assessment received from the server. The notification includes details of the risk and countermeasures, and is displayed on the user's terminal. 【0723】 Step 6: 【0724】 The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and voice data to understand their emotional state. This allows it to determine the user's stress level and level of interest. 【0725】 Step 7: 【0726】 The server adjusts risk notifications in a way that is best suited to the user's emotions, based on data obtained from the emotion engine. For example, if the user is stressed, the frequency and content of notifications are changed to reduce the burden on the user. 【0727】 Step 8: 【0728】 Users review the information and suggestions presented on their devices and consider specific actions to mitigate risks. Customized notifications based on sentiment data enable more effective decision-making. 【0729】 (Example 2) 【0730】 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". 【0731】 Traditional warning systems performed risk analysis and assessment based on information collected from users, but they struggled to recognize users' emotions in real time and flexibly adjust notification content accordingly. As a result, users may not receive appropriate notifications when they are emotionally distressed, leading to a problem where risk management does not function effectively. 【0732】 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. 【0733】 In this invention, the server includes means for collecting information, processing means for analyzing the collected information, evaluation means for evaluating the degree of risk based on the processing results, recognition means for recognizing the user's emotions, and adjustment means for adjusting the notification content based on the recognized emotions. This makes it possible to provide appropriate and personalized risk notifications according to the user's emotions. 【0734】 "Means of obtaining" refers to the collective set of processes and techniques used to collect information. 【0735】 "Processing means" refers to devices and algorithms used to analyze collected information and derive meaningful results from that data. 【0736】 "Evaluation methods" encompass criteria and techniques for determining the degree of risk based on analysis results. 【0737】 "Generation means" refers to a mechanism for creating risk notifications based on information obtained through evaluation. 【0738】 "Recognition means" refers to technologies used to sense and judge the emotional state of a user. 【0739】 "Adjustment means" refers to methods or devices for modifying the content or format of notifications based on perceived emotions. 【0740】 The system in this invention not only collects information, analyzes that information to assess risk, but is also capable of recognizing the user's emotions in real time and appropriately adjusting the content of notifications. A specific embodiment of this system is described below. 【0741】 The server first collects necessary information from the internet and databases based on keywords and information sources specified by the user. Web scraping libraries such as Python's Scrapy and BeautifulSoup can be used for information gathering. This makes it possible to efficiently obtain data from diverse information sources. 【0742】 Next, the server analyzes the collected information. This analysis utilizes natural language processing technology and generative AI models such as GPT-4. Using this model, risk factors can be automatically identified from the collected data, and the necessary assessments can be performed. Based on the analysis results, the server generates a notification. This notification includes a summary of the risk, its impact, and suggested countermeasures. 【0743】 The server then sends the generated notification to the user's device. The device receives this notification and notifies the user visually or audibly. Possible notification formats include push notifications on smartphones and pop-up messages on PCs. 【0744】 Furthermore, the device is equipped with emotion recognition capabilities that analyze the user's facial expressions and voice input to evaluate their emotional state in real time. This may involve using facial recognition APIs or voice analysis software. This emotion data is sent to a server, and the content of notifications is tailored to the user's state. 【0745】 For example, if a user expresses concerns about "food safety," the system can collect and analyze relevant, up-to-date information and provide notifications to alleviate those concerns. An example of a prompt generated using an AI model might be: "If a user expresses concerns about food safety, please advise on what kind of reassuring notification should be sent." 【0746】 In this way, this system provides highly accurate and personalized risk management by handling everything from information gathering and analysis to adjusting notifications based on sentiment data. 【0747】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0748】 Step 1: 【0749】 The server receives keywords and information sources as input from the user. Based on this, it collects information from specified internet resources and databases. Specifically, it uses scraping tools such as Scrapy and BeautifulSoup to extract text data from web pages. The output of this process is a collection of collected text information. 【0750】 Step 2: 【0751】 The server receives the information obtained in Step 1 as input and performs filtering using regular expressions and text cleaning techniques. Specifically, it removes unnecessary noise and duplicate data. The output is a filtered and cleaned dataset. 【0752】 Step 3: 【0753】 The server performs analysis using filtered data as input. This analysis utilizes the generative AI model GPT-4, employing natural language processing techniques to identify risk factors. Specifically, it extracts highly relevant phrases and terms and evaluates their risk levels. The output consists of analysis results and risk assessment information. 【0754】 Step 4: 【0755】 The server generates a notification based on the output of step 3. Specifically, it determines the content and format of the information to be delivered to the user and creates a notification document that includes details about the risks and countermeasures. The output of this process is the generated notification message. 【0756】 Step 5: 【0757】 The device receives notifications sent from the server and displays them to the user visually or audibly. Specifically, this uses push notifications or application message display functions. The output of this step is a notification interface that the user can view. 【0758】 Step 6: 【0759】 The device collects user emotional data in real time using its camera and microphone. It acquires voice tone and facial expressions as input and uses an emotion recognition algorithm to evaluate the user's current emotional state. The output is data indicating the user's emotional state. 【0760】 Step 7: 【0761】 The server receives the emotion data obtained in step 6 as input and adjusts the notification. Specifically, it modifies the tone and content of the message according to the emotional state and reconstructs it to reduce psychological burden. The output of this step is the adjusted notification message. 【0762】 Step 8: 【0763】 The user receives a final notification message and takes appropriate action regarding the risk. Specifically, they make individual actions and decisions based on the notification content. This output represents the specific actions the user takes based on the information they have received. 【0764】 (Application Example 2) 【0765】 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". 【0766】 In modern society, there is a need to effectively manage important risk information amidst information overload. However, conventional risk management systems provide information without considering the user's emotional state, resulting in limitations in information acceptance and effectiveness. Furthermore, they lack the flexibility to respond to users' emotions in situations where they experience stress or anxiety. This invention aims to solve these problems and provide users with personalized information. 【0767】 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. 【0768】 In this invention, the server includes means for collecting information, means for analyzing the collected information, means for performing a risk assessment based on the analysis results, means for recognizing the user's emotions, and means for adjusting risk notifications according to the user's emotional state. This makes it possible to provide personalized risk information that takes the user's emotional state into consideration and to improve the effective receptivity of the information. 【0769】 "Means for collecting information" refers to a device or method that automatically acquires information from the internet, databases, etc., based on specified keywords. 【0770】 "Means for analyzing collected information" refers to a device or method that uses natural language processing techniques to analyze data in order to remove noise from the collected data and identify risk factors. 【0771】 "Means of risk assessment" refers to a device or method that determines potential hazards based on analyzed data and quantifies or qualitatively evaluates their importance and likelihood. 【0772】 "Means for generating risk notifications" refers to a device or method for generating messages to notify users of warnings or information based on the results of a risk assessment. 【0773】 "Emotion recognition means" refers to a device or method for recognizing a user's mental state and emotions in real time by analyzing the user's facial expressions, voice, and input data. 【0774】 "Means for adjusting risk notifications" refers to a device or method that optimizes the content and format of risk notifications according to the user's perceived emotional state, and provides information in the most effective way for the user. 【0775】 The system implementing this invention consists of multiple components. First, the server automatically collects relevant information from the internet and databases based on keywords set by the user. This could involve implementing web scraping techniques using programming languages ​​such as Python or JavaScript. The collected information is then analyzed using natural language processing tools such as TensorFlow to identify risk factors. 【0776】 Based on the analysis results, a risk assessment is performed, and a notification is created based on the assessment results. The notification content is generated by the server and then sent to the user's device. This device is a smartphone with an application installed that runs on the Android or iOS operating system. 【0777】 The device utilizes the smartphone's camera and microphone to recognize the user's emotional state in real time. Using Google Cloud's sentiment analysis API, the system analyzes the user's emotions from facial expressions and voice input. Based on this information, the server adjusts notifications and provides specific information and means to alleviate the user's stress and anxiety. 【0778】 As a concrete example, if a user sets the keyword "financial fraud," information on the latest fraud methods will be collected and analyzed. If the system determines through emotion recognition that the user is feeling anxious, a "music playlist to relax" or a "checklist to avoid fraud" will be displayed on the device. An example of a prompt to input into the generating AI model is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering their emotional state." 【0779】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0780】 Step 1: 【0781】 The server receives keywords set by the user. Based on these keywords, it collects relevant information from the internet and databases. The input is the user's keywords, and the output is the collected information. In this step, web scraping techniques are used to automatically retrieve the data. 【0782】 Step 2: 【0783】 The server analyzes the collected information. It filters the data to remove noise and uses natural language processing techniques to identify risk factors. The input is the collected information, and the output is the analyzed risk factors. Data analysis is performed using tools such as TensorFlow. 【0784】 Step 3: 【0785】 The server performs a risk assessment based on the analysis results. This assessment quantifies or qualitatively evaluates the importance and likelihood of the risks. The input is the risk factors, and the output is the risk assessment index. This process uses assessment algorithms to analyze the risks. 【0786】 Step 4: 【0787】 The server generates notifications based on the results of the risk assessment. It selects the information to convey to the user according to the assessment indicators and creates the notification message. The input is the risk assessment indicators, and the output is the notification message. The text of the notification is adapted to the context using a generative AI model. 【0788】 Step 5: 【0789】 The server sends a notification message to the terminal. On the terminal side, the notification is displayed to the user. The input is the notification message, and the output is the display screen. 【0790】 Step 6: 【0791】 The device recognizes the user's emotional state in real time. It uses the smartphone's camera and microphone to analyze facial expressions and voice data through Google Cloud's emotion analysis API. The input is the user's emotional data, and the output is the emotional state. 【0792】 Step 7: 【0793】 The server adjusts the notification content based on the results of sentiment recognition. It adds information to the risk notification to reduce the user's stress and anxiety. The input is the emotional state, and the output is the adjusted notification content. An example of a prompt is, "Collect the latest security risk information based on the user's keywords and provide appropriate suggestions considering the emotional state." 【0794】 Step 8: 【0795】 The server resends the adjusted notification to the terminal, providing the user with the most relevant information. The input is the adjusted notification content, and the output is the final display. 【0796】 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. 【0797】 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. 【0798】 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 robot 414. 【0799】 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. 【0800】 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. 【0801】 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. 【0802】 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. 【0803】 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. 【0804】 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." 【0805】 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. 【0806】 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. 【0807】 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. 【0808】 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. 【0809】 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. 【0810】 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. 【0811】 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 this memory. 【0812】 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. 【0813】 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. 【0814】 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. 【0815】 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. 【0816】 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. 【0817】 The following is further disclosed regarding the embodiments described above. 【0818】 (Claim 1) 【0819】 means of collecting information, 【0820】 An analytical means for analyzing the collected information, 【0821】 An evaluation method for performing risk assessment based on analysis results, 【0822】 A notification means for generating a risk notification based on the assessment, 【0823】 A system that includes this. 【0824】 (Claim 2) 【0825】 The system according to claim 1, further comprising display means for displaying the generated risk notification to the user. 【0826】 (Claim 3) 【0827】 The system according to claim 1, further comprising setting means for setting the frequency of information collection and keywords. 【0828】 "Example 1" 【0829】 (Claim 1) 【0830】 Information gathering means for automatically obtaining information based on related words and information sources received from the user, 【0831】 Information filtering means for extracting useful information by eliminating irrelevant data from acquired information, 【0832】 An information analysis means for analyzing filtered information using natural language processing technology to extract risk factors, 【0833】 A risk assessment method for scoring and evaluating risks based on analysis results, 【0834】 A rapid information notification means for notifying relevant terminals of evaluation results, 【0835】 A system that includes this. 【0836】 (Claim 2) 【0837】 The system according to claim 1, further comprising visualization means for visually presenting notified risk information to the user. 【0838】 (Claim 3) 【0839】 The system according to claim 1, further comprising a setting management means for setting the frequency of information collection and related keywords. 【0840】 "Application Example 1" 【0841】 (Claim 1) 【0842】 Means for collecting information, 【0843】 Means for analyzing information, 【0844】 A means of performing evaluation based on the analysis results, 【0845】 Means for generating notifications based on evaluations, 【0846】 A means for transmitting evaluation information to an indicator device, 【0847】 A system that includes this. 【0848】 (Claim 2) 【0849】 The system according to claim 1, further comprising visualization means for displaying the generated notification to the user. 【0850】 (Claim 3) 【0851】 The system according to claim 1, further comprising setting means for setting the frequency of information collection and arguments. 【0852】 "Example 2 of combining an emotion engine" 【0853】 (Claim 1) 【0854】 The means of obtaining information, 【0855】 Processing means for analyzing the obtained information, 【0856】 An evaluation means for evaluating the degree of risk based on the processing results, 【0857】 A generation means for generating a risk level notification based on the said evaluation, 【0858】 A means of recognizing user emotions, 【0859】 A means of adjusting the notification content based on recognized emotions, 【0860】 A system that includes this. 【0861】 (Claim 2) 【0862】 The system according to claim 1, further comprising a display means for displaying the generated risk level notification. 【0863】 (Claim 3) 【0864】 The system according to claim 1, further comprising setting means for setting the frequency of information collection and the words to be used. 【0865】 "Application example 2 when combining with an emotional engine" 【0866】 (Claim 1) 【0867】 Means for collecting information, 【0868】 Means for analyzing the collected information, 【0869】 A means of conducting a risk assessment based on the analysis results, 【0870】 Means for generating a risk notification based on the assessment, 【0871】 A means of recognizing user emotions, 【0872】 A means of adjusting risk notifications according to the user's emotional state, 【0873】 A system that includes this. 【0874】 (Claim 2) 【0875】 The system according to claim 1, further comprising means for displaying the generated risk notification to the user, and optimizing the notification content based on the user's emotions. 【0876】 (Claim 3) 【0877】 The system according to claim 1, further comprising means for setting the frequency of information collection and keywords, and providing notifications appropriate to the emotional state using a generative AI model. [Explanation of symbols] 【0878】 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

[Claim 1] means of collecting information, An analytical means for analyzing the collected information, An evaluation method for performing risk assessment based on analysis results, A notification means for generating a risk notification based on the assessment, A system that includes this. [Claim 2] The system according to claim 1, further comprising display means for displaying the generated risk notification to the user. [Claim 3] The system according to claim 1, further comprising setting means for setting the frequency of information collection and keywords.

Images