system

Abstract

We provide the system. [Solution] With the user's permission, a means of collecting communication data in real time by linking with an external data platform, A means of preprocessing collected communication data and analyzing threats using a generative model, Based on the analysis results, a means to identify the level of threat and notify the user, Means to provide options to temporarily suspend or block communications depending on the level of threat, A means of providing users with educational information to improve their digital literacy, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Unexamined Patent Application Publication No. 2022 - 180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In conventional online communication platforms, it is difficult to detect threats such as inappropriate solicitations, fraud, harassment, and illegal transactions in real time and protect users. Also, in existing systems, users are often passively affected by threats, and there is a lack of immediate response and educational support. As a result, the construction of a safe and healthy online communication environment is insufficient. 【Means for Solving the Problems】 【0005】 This invention includes means for collecting data in real time by linking with an external data platform with the user's permission. This collected data is preprocessed, and inappropriate content is analyzed using a generative model. Furthermore, based on the analysis results, it provides means for identifying the threat level and immediately notifying the user. In addition, it provides users with the option to temporarily suspend or block communications depending on the severity of the threat, and also provides educational information for improving safe digital literacy, thereby realizing a system that enhances the health of online communication. 【0006】 A "user" refers to an individual or organization that uses communication or services through a digital platform. 【0007】 An "external data platform" refers to a foundation that provides systems and services for exchanging information with users over the internet. 【0008】 "Real-time" refers to the ability to process and analyze information and data as soon as it is input, and to provide results immediately. 【0009】 "Communication data" refers to digital data, including the content of messages and information exchanged between users. 【0010】 A "generative model" refers to an AI-based algorithm that learns from large amounts of data and identifies and generates specific patterns or features. 【0011】 A "threat" refers to inappropriate actions or content that cause harm or risk to users or systems. 【0012】 "Preprocessing" refers to the process of transforming data into a format suitable for analysis and modeling, which involves noise reduction and data formatting. 【0013】 "Analysis results" refer to conclusions and information obtained through data analysis and model processing. 【0014】 "Educational information" refers to content that provides knowledge and guidelines for users to communicate safely and consciously. 【0015】 "Digital literacy" refers to the ability to effectively use digital technologies and handle information safely and efficiently. 【Brief Explanation of Drawings】 【0016】 [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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. [[ID=…]] [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined. 【Mode for Carrying Out the Invention】 【0017】 Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0018】 First, the terms used in the following description will be explained. 【0019】 In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0020】 In the following embodiments, 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. 【0021】 In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0022】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0023】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0024】 [First Embodiment] 【0025】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0026】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0027】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0028】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0029】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0030】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0031】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0032】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0033】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0034】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0035】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0036】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0037】 This invention is a system that supports users in communicating safely and securely on online platforms. This system is primarily implemented through a server, terminal, and user interface. Its specific form is described below. 【0038】 Data collection: 【0039】 The user first grants the system permission to access their social networking service (SNS) accounts and messaging applications. Based on this permission, the server uses the SNS platform's API to collect messages and posts in real time. 【0040】 Data analysis: 【0041】 The collected communication data is preprocessed by the server and input into a generative model. The generative model uses machine learning algorithms to analyze the data and detect specific threat patterns. Threats here include inappropriate solicitation, fraud, harassment, and illegal transactions. 【0042】 Threat notification and intervention: 【0043】 The server determines the level of the threat based on the analysis results. If a threat is detected, the server immediately notifies the user and offers appropriate countermeasures. For example, it may offer the user the option to temporarily suspend or completely block the conversation. 【0044】 User education: 【0045】 The device provides users with educational information to improve their safe digital literacy. This information includes materials to deepen their understanding of threats and guidelines for specific countermeasures. It also provides interactive content to create an environment where users can learn at their own pace. 【0046】 Continuous learning: 【0047】 The server updates its generative model using user feedback and newly acquired data. This allows the system to constantly learn the latest threat patterns and continuously improve its detection accuracy. 【0048】 Specific example: 【0049】 For example, suppose a user receives a message from a friend on social media. If this message requests personal information, the server analyzes the message and determines that it may be a scam. It immediately issues a warning to the user, urging caution and advising them not to easily provide personal information. By promptly taking action based on this warning, the user can prevent potential harm. 【0050】 In this way, this system provides practical means for building a secure online environment through real-time data analysis and user education. 【0051】 The following describes the processing flow. 【0052】 Step 1: 【0053】 The user grants the system access permission to access their social media account. This permission allows the server to use the API to retrieve individual messages and posts in real time. 【0054】 Step 2: 【0055】 The server preprocesses the communication data collected from the SNS platform. Specifically, it removes noise from the data and formats it into a format suitable for analysis. This process includes removing emojis and parsing HTML tags. 【0056】 Step 3: 【0057】 The server inputs pre-processed data into a generative model. This model is trained on a large amount of known data and uses machine learning to detect inappropriate content and threats. As a result of the analysis, it determines whether the data is related to fraud, harassment, or other threats. 【0058】 Step 4: 【0059】 The server uses the output from the generative model to identify the threat level. This level is categorized into low, medium, and high, and different responses are required depending on the severity. 【0060】 Step 5: 【0061】 When a threat is detected, the server notifies the user of its details. The notification includes specific information about the threat and recommended actions to take. In some cases, options such as pausing or completely blocking the conversation may also be presented. 【0062】 Step 6: 【0063】 The device displays educational content to help users learn how to respond when faced with threats. This is provided as guidelines and interactive learning modules to support users in practicing safer communication. 【0064】 Step 7: 【0065】 The server continuously updates its generation model based on implemented countermeasures and user feedback. When new threat patterns are detected, this information is reflected in the system to provide more accurate threat detection capabilities. 【0066】 (Example 1) 【0067】 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." 【0068】 In recent years, with the widespread adoption of internet-based communication technologies, the security issues faced by users have increased. In particular, threats such as inappropriate solicitations, fraud, harassment, and illegal transactions exist, creating a need for systems that can detect and warn users in real time. However, existing technologies have challenges in terms of threat detection accuracy, timely notification, and the continuity of user education. 【0069】 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. 【0070】 In this invention, the server includes means for collecting communication information in real time in cooperation with an external information processing device with the user's permission, means for preprocessing the collected communication information and analyzing threats using a machine learning model, and means for identifying the level of the threat based on the analysis results and notifying the user. This allows the user to be quickly protected from potential threats and to always have access to the latest security measures. 【0071】 "Collecting communication information in real time in cooperation with an external information processing device with the user's permission" refers to the process of connecting the user's communication data to other computer systems and instantly acquiring information that occurs on the internet, after the user has given permission to access it. 【0072】 "Preprocessing collected communication information and analyzing threats using machine learning models" refers to the process of organizing the obtained communication-related data according to certain rules, and then using pre-built algorithms to identify potential risks. 【0073】 "Identifying the threat level based on analysis results and notifying users" means evaluating the results derived from data analysis, determining the severity of the threat, and then providing that information to users. 【0074】 "Providing the option to temporarily suspend or block communications depending on the level of threat" means offering users means to interrupt or completely stop continuous data exchange depending on the degree of identified dangerous behavior. 【0075】 "Providing users with educational data to improve their information technology literacy" means giving users educational materials aimed at improving their knowledge and skills for safe internet use. 【0076】 "Generating educational guidelines regarding inappropriate communication situations using analyzed information" means creating guidelines for users to avoid inappropriate situations themselves, based on the results of analyzing past data. 【0077】 "Continuously updating machine learning models based on analysis results and user feedback to improve threat detection accuracy" means using the obtained analytical data and user feedback to improve the effectiveness of the algorithm and enable more accurate identification of risks. 【0078】 "Accumulating information on detected threats and forming an information repository to identify new threat patterns" refers to building a database by storing data on previously identified risky behaviors and using that data to identify potential new risks. 【0079】 This invention provides a system that enables users to communicate safely and securely over the internet. The system mainly consists of a server, a terminal, and the user's device. 【0080】 The server first obtains permission from the user and then collects communication information in real time via an external information processing device. This process includes collecting data from the user's social media accounts and messaging applications. The collected information is preprocessed within the server and then input into a generative AI model, which is a machine learning model. 【0081】 This generative AI model analyzes collected data to detect potential threats. Examples of threats include inappropriate solicitation, fraud, harassment, and illegal transactions. Based on the analyzed data, the server determines the level of the threat and immediately notifies the user. 【0082】 The device provides users with digital literacy-enhancing content to facilitate safe online activities. This includes interactive guidelines and quizzes that users can use to improve their safety. 【0083】 A concrete example would be a user receiving a message on social media from a stranger asking for personal information. The server analyzes the message, and if it determines that it is highly likely to be a scam, it immediately sends a warning notification to the user. At the same time, it also advises the user to avoid providing personal information. 【0084】 An example of a prompt message is: "I've recently been asked for personal information by strangers on social media. Please tell me how I should deal with this." 【0085】 These features allow users to protect themselves from potential online harm and use the internet with peace of mind. The servers also update machine learning models based on analysis results and user feedback to maintain a constant response to the latest threats. 【0086】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0087】 Step 1: 【0088】 The server receives permission requests from users to access SNS accounts and messaging apps. The input is user-defined permission settings. Based on these permissions, the server collaborates with external information processing devices to collect communication information in real time. The output is the raw, unprocessed communication data. At this stage, the server calls the SNS platform's API to retrieve the latest communication content. 【0089】 Step 2: 【0090】 The server preprocesses the collected communication data. The input is the raw communication data collected in step 1. The server formats this data and filters out unnecessary information to convert it into a format suitable for the generating AI model. The output is a dataset that has been preprocessed and is suitable for analysis. Here, specific actions are performed, such as removing extraneous spaces and special characters, and extracting target text portions. 【0091】 Step 3: 【0092】 The server inputs the pre-processed data into a generative AI model for analysis. The input is the dataset prepared in step 2. The generative AI model utilizes machine learning algorithms to detect specific threat patterns within the data. The output is information about the characteristics and threat level of the detected threats. Specifically, the model identifies similar patterns and compares them with historical database data to determine the presence or absence of a threat. 【0093】 Step 4: 【0094】 Based on the analysis results, the server identifies the threat level and prepares to notify the user. The input is the analysis results from step 3. The server generates the severity of the threat and a description of it, and creates a warning message for the user. The output is the notification message, which is sent to the terminal. Specifically, this involves generating a message such as, "This may be a scam, so do not provide personal information to the sender." 【0095】 Step 5: 【0096】 The device provides users with educational content tailored to the threat. Input consists of the warning message created in step 4 and appropriate educational content based on its content. The device displays interactive guidelines and quiz-style educational materials, providing users with opportunities to deepen their understanding. Output is educational content displayed to the user. Specifically, it displays materials illustrating relevant harassment examples and coping strategies. 【0097】 Step 6: 【0098】 The server analyzes user feedback and newly collected data to continuously update the generated AI model. Input consists of user feedback and newly collected data. The server uses this information to adjust the model parameters and improve analysis accuracy. The output is the updated machine learning model. Specifically, it recalculates the algorithm's weights based on past false positives. 【0099】 (Application Example 1) 【0100】 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." 【0101】 In online communication, it is crucial to protect users from threats such as fraud, scams, and harassment. However, real-time threat detection is difficult with conventional monitoring methods, and it relies heavily on the user's own information literacy. Therefore, there is a need for a more rapid and accurate countermeasure system. Furthermore, in addition to defending against threats, educational support is also needed to help users take safe actions themselves. 【0102】 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. 【0103】 This invention includes a server that, with the user's permission, cooperates with an external information infrastructure to collect communication information in real time; a server that preprocesses the collected communication information and analyzes threats using a generative machine learning model; and a server that proposes specific countermeasures based on the detection of fraudulent activity and fraud based on the real-time analyzed communication information. This makes it possible to immediately detect risky communications and provide appropriate alerts and instructions to the user. Furthermore, by continuously learning the latest threat information, the system can constantly evolve while providing educational content that improves the user's information literacy. 【0104】 "User permission" means obtaining formal consent from the individual being investigated when collecting or analyzing information. 【0105】 "External information infrastructure" refers to external data platforms and communication networks that are linked to acquire communication information in real time. 【0106】 "Collecting communication information in real time" means the process of acquiring information instantly and without delay from the moment the data is generated. 【0107】 "Preprocessing" refers to the process of converting collected raw data into the necessary format and structure before analysis. 【0108】 A "generative machine learning model" is an AI-based algorithm that uses historical data and feedback to analyze and identify specific patterns and threats. 【0109】 "Threat analysis" is the process of examining collected communications information to identify potential risks and malicious activities. 【0110】 "Suggesting specific countermeasures" means recommending appropriate guidelines and actions to the user in response to detected threats. 【0111】 "Latest threat intelligence" refers to the most up-to-date knowledge and data on fraudulent activities and scams, which are constantly evolving. 【0112】 "Information literacy" refers to an individual's ability to use information safely and effectively on the internet and in communication. 【0113】 "Providing educational content" means presenting learning resources and guidelines to enable users to improve their knowledge and skills on their own. 【0114】 This invention is a system that enables users to communicate securely in an online environment, and its embodiments consist of multiple components. 【0115】 The server first obtains permission from the user, then connects with an external information infrastructure to collect communication information in real time. The collected communication information is preprocessed and input into a generative machine learning model. The generative machine learning model used here is built using tools such as TENSORFLOW® and PyTorch, and is responsible for analyzing specific threat patterns. 【0116】 Once the analysis is complete, the server will suggest specific actions to take to the user, depending on the level of the detected threat. For example, if malicious activity or fraud is detected in a message, a notification such as "This link is dangerous. Do not access it." will be sent. These specific instructions are intended to encourage the user to take prompt action. 【0117】 The device also provides users with educational content to improve their information literacy. This content includes learning resources in quiz and video formats, designed to help users learn about safe online behavior while having fun. 【0118】 Furthermore, the server continuously updates its machine learning model based on user feedback and new threat intelligence. This ensures that the system is always well-prepared to respond to the latest threats. 【0119】 For example, if a user receives a message on social media asking for their credit card information, this system will immediately detect the possibility of fraud and issue a warning. It will then send advice such as, "It is safer not to provide your personal information." 【0120】 An example of a prompt message for the AI ​​model might be a text input such as, "Is this message potentially a scam? 'Hello, we need your bank account information.'" In this way, the present invention provides an environment in which users can safely use digital platforms. 【0121】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0122】 Step 1: 【0123】 The server, with user permission, interacts with an external information infrastructure. At this stage, it collects communication information in real time using APIs from social networking services (SNS) and messaging platforms. The input requires the user's account information and API key, and the output is the collected, unprocessed communication information. 【0124】 Step 2: 【0125】 The server preprocesses the collected communication information. This includes noise reduction, data cleansing, and formatting. The input is the raw communication information obtained in step 1, and the output contains clean data suitable for analysis. Here, text data filtering and normalization are performed using Python scripts or similar tools. 【0126】 Step 3: 【0127】 The server inputs pre-processed communication data into a generating AI model for analysis. A machine learning model (e.g., one using TensorFlow or PyTorch) detects threat patterns from the data. The input is clean data, and the output generates an assessment of the threat level and type for each communication. 【0128】 Step 4: 【0129】 The server notifies the user of the threat based on the analysis results. If the analysis results are deemed high-risk, a warning message is sent to the user's device. The input is the analysis results from step 3, and the output is the specific warning content sent to the user. At this time, a prompt message is generated to form a phrase that will attract the user's attention. 【0130】 Step 5: 【0131】 The device provides users with educational content to improve their information literacy. This includes quizzes to test knowledge and training modules using simulated scenarios. The input is the system's database of educational content, and the output is appropriate training content tailored to the user's learning progress. 【0132】 Step 6: 【0133】 The server continuously updates the generated AI model based on user feedback and newly detected threat information. This process involves incorporating new data to retrain the learning model. The input is feedback data and new communication information, and the output is the updated machine learning model. Model updates are performed through periodic batch processing. 【0134】 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. 【0135】 This invention is a system that promotes safe and healthy communication on online platforms and incorporates an emotion recognition engine. This system operates via a server, terminal, and user interface. Detailed embodiments are described below. 【0136】 Data collection and emotion recognition: 【0137】 When a user grants the system access to their social media accounts, the server retrieves messages and posts in real time via an API. Simultaneously, based on the collected communication data, the server uses an emotion engine to infer the user's emotional state. This engine analyzes emotions from the text and identifies the user's emotional state. 【0138】 Data analysis and threat awareness: 【0139】 The server inputs communication data, incorporating emotion recognition, into a generative model to identify inappropriate content and threats. By taking emotional changes into account, threat detection becomes more accurate than usual. 【0140】 Notification and intervention: 【0141】 Based on information from the emotion engine, the server adjusts the content of threat notifications according to the user's psychological state. For example, if the user is stressed, the notification will be delivered in more mitigating language. Depending on the level of threat, the user is given the option to pause or block the conversation. 【0142】 User education and support: 【0143】 The device provides users with appropriate educational information. This information includes emotionally-based coping strategies and interactive content to improve digital literacy more effectively. This creates an environment where users can communicate intuitively and securely. 【0144】 Continuous learning and feedback: 【0145】 The server analyzes user feedback and sentiment data to continuously improve the accuracy of its generative models and sentiment engine. This allows it to learn new threat and sentiment patterns, further enhancing user protection. 【0146】 Specific example: 【0147】 For example, if a user feels anxious after seeing extreme comments on social media, the server's emotion engine instantly recognizes the user's emotions. If a threat is detected, the server notifies the user and displays specific steps and countermeasures on their device to help them calm down. This allows the user to continue communicating with peace of mind. 【0148】 Thus, the present invention provides a more personalized and secure online environment through real-time sentiment analysis and data analysis. 【0149】 The following describes the processing flow. 【0150】 Step 1: 【0151】 The user grants the system permission to access their social media accounts and analyze sentiment data. Based on this permission, the server uses the social media platform's API to retrieve messages and posts in real time. 【0152】 Step 2: 【0153】 The server preprocesses the collected communication data. Specifically, it removes noisy elements from the text, tokenizes it, and converts it into a parseable format. At this stage, the sentiment engine also performs sentiment analysis on the text data. 【0154】 Step 3: 【0155】 The server inputs pre-processed data into a generative model to determine messages that may contain inappropriate content or threats. It also evaluates the results of the emotion engine's analysis to analyze the psychological impact on users in communications. 【0156】 Step 4: 【0157】 The server identifies the presence and level of threats based on the output of the generative model and sentiment analysis. The threat level is further categorized into low, medium, and high, depending on the user's emotional state. 【0158】 Step 5: 【0159】 The server sends notifications to users based on the nature and level of the threat. These notifications use language that is sensitive to the user's emotional state and explain appropriate countermeasures and recommended actions. For example, if a user is feeling anxious, the server will choose more polite and reassuring language. 【0160】 Step 6: 【0161】 The device displays educational information tailored to the user's emotions and the type of threat. This information is provided as guidelines for effective countermeasures and content aimed at improving digital literacy. Based on this information, users can avoid danger and continue to communicate effectively. 【0162】 Step 7: 【0163】 The server accumulates user feedback and sentiment data, and regularly updates its generative models and sentiment engine. This continuous learning process improves the system's threat detection accuracy and sentiment analysis capabilities, resulting in more effective protection and support. 【0164】 (Example 2) 【0165】 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 will be referred to as the "terminal." 【0166】 Online communication, while convenient, often exposes users to inappropriate content and threats. Furthermore, simplistic threat notifications that fail to consider the user's psychological state can cause additional stress. This invention aims to solve these problems through a system that utilizes sentiment analysis to achieve more accurate threat recognition and provide psychologically appropriate responses to users. 【0167】 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. 【0168】 In this invention, the server includes means for collecting communication information in real time in cooperation with an information processing infrastructure with the user's permission, means for preprocessing the collected communication information and evaluating the user's psychological state using sentiment analysis technology, and means for analyzing threats using a generative model based on the evaluation results and improving the accuracy of the threat by reflecting specific emotional changes. This enables more precise threat recognition in accordance with the user's emotional state and the provision of psychologically appropriate threat notifications and countermeasures. 【0169】 A "user" is an individual or group that interacts with a system through an interface. 【0170】 An "information processing infrastructure" is a collection of hardware and software used to collect, store, and analyze data. 【0171】 "Real-time" refers to the concept where data acquisition and processing occur almost simultaneously, providing users with information instantly. 【0172】 "Communication information" refers to data such as messages and posts exchanged on online platforms. 【0173】 "Emotion analysis technology" refers to methods and algorithms for analyzing text data and identifying the emotions and sensibilities contained within it. 【0174】 "Psychological state" refers to the state of emotions and consciousness, and is the internal state of the user identified through emotion analysis. 【0175】 A "generative model" is a statistical model that uses machine learning and artificial intelligence technologies to learn patterns from data and generate new data or results. 【0176】 A "threat" refers to inappropriate content or activities that could have a negative impact on users. 【0177】 "Threat accuracy" is an indicator that refers to the precision and reliability with which a system identifies threats. 【0178】 A "threat notification" is an alert or message that communicates information about an identified threat to the user. 【0179】 This invention is a system that promotes safe and healthy communication on online platforms. This system operates by combining sentiment analysis technology and generative AI models, with servers, terminals, and users as its main components. 【0180】 The server, through user-authorized access, utilizes APIs from social networking services (SNS) and messaging services as its information processing infrastructure to collect communication information in real time. This information collection is carried out efficiently using RESTful APIs and WebSocket technology. The collected information is stored on the server as text data. 【0181】 Next, the server processes this text data using sentiment analysis technology. It uses natural language processing (NLP) libraries to evaluate the emotions contained in the text. Specifically, it identifies the user's psychological state using open-source sentiment analysis tools or proprietary algorithms. 【0182】 The user's psychological state, as revealed by the analysis, is further evaluated in detail by a generative AI model. This model learns known threat patterns and improves threat accuracy by incorporating the results of sentiment analysis. The generative model utilizes deep learning frameworks and common machine learning tools. 【0183】 Based on the user's psychological state and threat level, the server provides a flexible notification mechanism. Notifications are sent using wording that takes the user's emotional state into consideration. These notifications are displayed to the user via their device, prompting specific actions. For example, if the user is under high stress, the notification might suggest a calm response as a "step to calm down." 【0184】 The device interactively provides users with educational information and coping strategies based on sentiment analysis. This allows users to improve their digital literacy and ensure safer online communication. 【0185】 For example, if a user detects an offensive post on social media, the server immediately performs sentiment analysis and recognizes that the user is feeling stressed. Depending on the situation, the device will display advice such as, "Take a deep breath and then check the message again." 【0186】 An example of a prompt might be: "If a user discovers a post on social media that makes them feel uneasy, how can the sentiment engine identify that emotion and provide a safe notification?" 【0187】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0188】 Step 1: 【0189】 The server, based on user permission, interacts with the information processing infrastructure to collect communication information in real time. Inputs include the user's SNS account and access rights to messaging platforms. The server retrieves data via APIs and stores it in text format. At this stage, raw message data is obtained as output. 【0190】 Step 2: 【0191】 The server preprocesses the acquired communication information using an emotion analysis engine. The input is the text data collected in step 1. The server uses natural language processing techniques to identify emotions from the text and classify them into emotional states such as joy, sadness, anger, and anxiety. The output is the analyzed emotion data. 【0192】 Step 3: 【0193】 The server performs threat analysis using a generative AI model based on the analyzed sentiment data. The input is the sentiment data obtained in step 2. The server uses the trained generative model to evaluate potential threats in the text and improves the accuracy of the threat assessment by incorporating the sentiment analysis results. The output is the threat assessment result. 【0194】 Step 4: 【0195】 The server sends a threat notification to the user based on the threat assessment results and sentiment data. The input is the threat assessment results and sentiment state from step 3. The server takes the user's psychological state into consideration and adjusts the notification method and content. The output is the adjusted notification message sent to the user's terminal. 【0196】 Step 5: 【0197】 The device displays the received notification message to the user and prompts them to take specific action. The input is the notification message sent in step 4. The device displays suggestions and actions in language that reduces the user's psychological burden. The output is a visual and textual notification to the user. 【0198】 Step 6: 【0199】 The server receives user feedback and threat assessment data to continuously update its generative model and sentiment analysis engine. Input consists of user feedback and threat assessment data. The server analyzes this data to improve the accuracy of the AI ​​model and identify new threat patterns. The output is an updated model and analysis engine. 【0200】 (Application Example 2) 【0201】 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". 【0202】 In online communication, users may experience a lack of detection and response to threats or inappropriate information that could potentially harm them. Furthermore, the lack of appropriate intervention and support tailored to their psychological state can negatively impact users' mental health. In addition, a lack of digital literacy makes it difficult for users to independently identify and address threats. To address these issues, there is a need for systems that promote safe and healthy communication utilizing sentiment recognition technology. 【0203】 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. 【0204】 In this invention, the server includes means for inferring the user's psychological state using an emotion analysis engine and providing appropriate information, means for collecting information in real time in cooperation with an information processing device with the user's permission, and means for preprocessing the collected information and analyzing threats using a generated mathematical model. This enables the appropriate provision of educational information tailored to the user's psychological state, as well as more accurate threat detection and rapid response. 【0205】 An "information processing device" is a device that processes various types of data based on user permission and acquires and analyzes information in cooperation with an external data platform. 【0206】 A "generated mathematical model" is a model formed through data analysis and used to evaluate and detect online threats. 【0207】 An "emotion analysis engine" is an engine that analyzes a user's communication and uses the information obtained from it to infer their psychological state. 【0208】 "Threat level" is a measure that indicates the degree of risk to users, as identified as a result of analysis by an information processing device. 【0209】 "Educational information" refers to information that provides users with the knowledge and skills necessary to improve their digital literacy and maintain a safe online environment. 【0210】 The system implementing this invention features a complex mechanism combining sentiment analysis technology and a generated mathematical model to improve the security of communication on online platforms. The server interacts in real time with an external data platform authorized by the user to collect information. This information is preprocessed using an information processing device, and threats are analyzed using the generated mathematical model. Furthermore, a sentiment analysis engine is used to infer the user's psychological state and provide appropriate information. 【0211】 Based on these analysis results, the server identifies the threat level and notifies the user in an appropriate manner. Users are presented with options to temporarily suspend or block communications as countermeasures appropriate to the threat level. Furthermore, educational information is provided to improve users' digital literacy, helping them to communicate securely. 【0212】 As a concrete example, if a user encounters inappropriate comments on social media, the server immediately detects the user's anxiety through sentiment analysis and, based on the results, notifies them with a "guide to calm down." At the same time, it presents appropriate educational information according to the user's emotional state, enabling them to continue safer and healthier online interactions. 【0213】 An example of a prompt message generated using an AI model would be: "Generate a notification using gentle language to alleviate anxiety, taking into account the user's psychological state. For example, what words should be used if the user is feeling anxious?" This makes notifications to users more personalized and provides a sense of security. 【0214】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0215】 Step 1: 【0216】 The server, with user permission, interacts with an external data platform to collect data in real time. The input is communication data from the platform, and the output is data converted into a processable format. The server extracts the data using an API and formats it for easier analysis. 【0217】 Step 2: 【0218】 The server preprocesses the collected communication data and analyzes threats using the generated mathematical model. The input is formatted communication data, and the output is the analysis results, including a threat assessment. This process uses natural language processing techniques to analyze text and identify potential threats. 【0219】 Step 3: 【0220】 The server uses an emotion analysis engine to infer the user's psychological state. The input consists of communication content with the user and its metadata, and the output is the inferred emotional state. Emotion analysis uses machine learning algorithms to extract emotional characteristics from text. 【0221】 Step 4: 【0222】 The server identifies the threat level based on the analysis results and notifies the user. The input is the result of threat analysis and sentiment inference, and the output is a customized notification message. The server utilizes prompts to generate the most appropriate notification content for the user. 【0223】 Step 5: 【0224】 The server provides the user with the option to temporarily suspend or block communications. The input is the identified threat level, and the output is the control option the user can select. The user receives a notification and can take appropriate action. 【0225】 Step 6: 【0226】 The device provides users with educational information to improve their digital literacy. Input is the user's psychological state and threat level, and output is the corresponding educational content. The educational content is interactive instructional material designed using a generative AI model. 【0227】 Step 7: 【0228】 The server continuously updates the mathematical model generated based on user feedback, improving its accuracy. Input is analysis and user feedback data, and output is the updated model. This enhances the system's ability to respond to new threat patterns. 【0229】 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. 【0230】 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. 【0231】 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. 【0232】 [Second Embodiment] 【0233】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0234】 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. 【0235】 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). 【0236】 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. 【0237】 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. 【0238】 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). 【0239】 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. 【0240】 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. 【0241】 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. 【0242】 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. 【0243】 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. 【0244】 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". 【0245】 This invention is a system that supports users in communicating safely and securely on online platforms. This system is primarily implemented through a server, terminal, and user interface. Its specific form is described below. 【0246】 Data collection: 【0247】 The user first grants the system permission to access their social networking service (SNS) accounts and messaging applications. Based on this permission, the server uses the SNS platform's API to collect messages and posts in real time. 【0248】 Data analysis: 【0249】 The collected communication data is preprocessed by the server and input into a generative model. The generative model uses machine learning algorithms to analyze the data and detect specific threat patterns. Threats here include inappropriate solicitation, fraud, harassment, and illegal transactions. 【0250】 Threat notification and intervention: 【0251】 The server determines the level of the threat based on the analysis results. If a threat is detected, the server immediately notifies the user and offers appropriate countermeasures. For example, it may offer the user the option to temporarily suspend or completely block the conversation. 【0252】 User education: 【0253】 The device provides users with educational information to improve their safe digital literacy. This information includes materials to deepen their understanding of threats and guidelines for specific countermeasures. It also provides interactive content to create an environment where users can learn at their own pace. 【0254】 Continuous learning: 【0255】 The server updates its generative model using user feedback and newly acquired data. This allows the system to constantly learn the latest threat patterns and continuously improve its detection accuracy. 【0256】 Specific example: 【0257】 For example, suppose a user receives a message from a friend on social media. If this message requests personal information, the server analyzes the message and determines that it may be a scam. It immediately issues a warning to the user, urging caution and advising them not to easily provide personal information. By promptly taking action based on this warning, the user can prevent potential harm. 【0258】 In this way, this system provides practical means for building a secure online environment through real-time data analysis and user education. 【0259】 The following describes the processing flow. 【0260】 Step 1: 【0261】 The user grants the system access permission to access their social media account. This permission allows the server to use the API to retrieve individual messages and posts in real time. 【0262】 Step 2: 【0263】 The server preprocesses the communication data collected from the SNS platform. Specifically, it removes noise from the data and formats it into a format suitable for analysis. This process includes removing emojis and parsing HTML tags. 【0264】 Step 3: 【0265】 The server inputs pre-processed data into a generative model. This model is trained on a large amount of known data and uses machine learning to detect inappropriate content and threats. As a result of the analysis, it determines whether the data is related to fraud, harassment, or other threats. 【0266】 Step 4: 【0267】 The server uses the output from the generative model to identify the threat level. This level is categorized into low, medium, and high, and different responses are required depending on the severity. 【0268】 Step 5: 【0269】 When a threat is detected, the server notifies the user of its details. The notification includes specific information about the threat and recommended actions to take. In some cases, options such as pausing or completely blocking the conversation may also be presented. 【0270】 Step 6: 【0271】 The device displays educational content to help users learn how to respond when faced with threats. This is provided as guidelines and interactive learning modules to support users in practicing safer communication. 【0272】 Step 7: 【0273】 The server continuously updates its generation model based on implemented countermeasures and user feedback. When new threat patterns are detected, this information is reflected in the system to provide more accurate threat detection capabilities. 【0274】 (Example 1) 【0275】 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". 【0276】 In recent years, with the widespread adoption of internet-based communication technologies, the security issues faced by users have increased. In particular, threats such as inappropriate solicitations, fraud, harassment, and illegal transactions exist, creating a need for systems that can detect and warn users in real time. However, existing technologies have challenges in terms of threat detection accuracy, timely notification, and the continuity of user education. 【0277】 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. 【0278】 In this invention, the server includes means for collecting communication information in real time in cooperation with an external information processing device with the user's permission, means for preprocessing the collected communication information and analyzing threats using a machine learning model, and means for identifying the level of the threat based on the analysis results and notifying the user. This allows the user to be quickly protected from potential threats and to always have access to the latest security measures. 【0279】 "Collecting communication information in real time in cooperation with an external information processing device with the user's permission" refers to the process of connecting the user's communication data to other computer systems and instantly acquiring information that occurs on the internet, after the user has given permission to access it. 【0280】 "Preprocessing collected communication information and analyzing threats using machine learning models" refers to the process of organizing the obtained communication-related data according to certain rules, and then using pre-built algorithms to identify potential risks. 【0281】 "Identifying the threat level based on analysis results and notifying users" means evaluating the results derived from data analysis, determining the severity of the threat, and then providing that information to users. 【0282】 "To provide options to temporarily suspend or block communication according to the level of threat" means to propose to the user a means to interrupt or completely stop the continuous data exchange according to the degree of identified dangerous behavior. 【0283】 "To provide educational data for improving user information technology literacy" means to provide the user with teaching materials aimed at improving the knowledge and skills for safe Internet use. 【0284】 "To generate educational guidelines on inappropriate communication situations using the analyzed information" means to create guidelines for the user to avoid inappropriate situations based on the analysis results of past data. 【0285】 "To continuously update the machine learning model based on the analysis results and user feedback and improve the threat detection accuracy" means to use the obtained analysis data and opinions from the user to improve the effectiveness of the algorithm and enable more accurate identification of risks. 【0286】 "To accumulate information on the detected threats and form an information repository for identifying new threat patterns" means to store data on previously identified dangerous behaviors and build a database using it to identify newly emerging potential risks. 【0287】 This invention provides a system for users to communicate safely and securely on the Internet. The system mainly consists of a server, a terminal, and the user's device. 【0288】 The server first obtains permission from the user and collects communication information in real time via an external information processing device. This process includes data collection from the user's SNS account and message applications. The collected information is pre-processed in the server and input into the generative AI model, which is a machine learning model. 【0289】 This generative AI model analyzes collected data to detect potential threats. Examples of threats include inappropriate solicitation, fraud, harassment, and illegal transactions. Based on the analyzed data, the server determines the level of the threat and immediately notifies the user. 【0290】 The device provides users with digital literacy-enhancing content to facilitate safe online activities. This includes interactive guidelines and quizzes that users can use to improve their safety. 【0291】 A concrete example would be a user receiving a message on social media from a stranger asking for personal information. The server analyzes the message, and if it determines that it is highly likely to be a scam, it immediately sends a warning notification to the user. At the same time, it also advises the user to avoid providing personal information. 【0292】 An example of a prompt message is: "I've recently been asked for personal information by strangers on social media. Please tell me how I should deal with this." 【0293】 These features allow users to protect themselves from potential online harm and use the internet with peace of mind. The servers also update machine learning models based on analysis results and user feedback to maintain a constant response to the latest threats. 【0294】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0295】 Step 1: 【0296】 The server receives permission requests from users to access SNS accounts and messaging apps. The input is user-defined permission settings. Based on these permissions, the server collaborates with external information processing devices to collect communication information in real time. The output is the raw, unprocessed communication data. At this stage, the server calls the SNS platform's API to retrieve the latest communication content. 【0297】 Step 2: 【0298】 The server preprocesses the collected communication data. The input is the raw communication data collected in step 1. The server formats this data and filters out unnecessary information to convert it into a format suitable for the generating AI model. The output is a dataset that has been preprocessed and is suitable for analysis. Here, specific actions are performed, such as removing extraneous spaces and special characters, and extracting target text portions. 【0299】 Step 3: 【0300】 The server inputs the pre-processed data into a generative AI model for analysis. The input is the dataset prepared in step 2. The generative AI model utilizes machine learning algorithms to detect specific threat patterns within the data. The output is information about the characteristics and threat level of the detected threats. Specifically, the model identifies similar patterns and compares them with historical database data to determine the presence or absence of a threat. 【0301】 Step 4: 【0302】 Based on the analysis results, the server identifies the threat level and prepares to notify the user. The input is the analysis results from step 3. The server generates the severity of the threat and a description of it, and creates a warning message for the user. The output is the notification message, which is sent to the terminal. Specifically, this involves generating a message such as, "This may be a scam, so do not provide personal information to the sender." 【0303】 Step 5: 【0304】 Provide educational content corresponding to the threat to the user on the terminal. The input is the warning message created in Step 4 and appropriate educational content based on its content. The terminal displays interactive guidelines and educational materials in the form of quizzes, providing the user with an opportunity to deepen their understanding. The output is the educational content displayed to the user. As a specific operation, display materials showing relevant harassment cases and countermeasures. 【0305】 Step 6: 【0306】 The server analyzes the feedback from the user and newly collected data, and continuously updates the generated AI model. The input is the user's feedback information and newly collected data. The server uses this information to adjust the parameters of the model and improve the analysis accuracy. The output is the updated machine learning model. As a specific operation, perform a process of recalculating the weights of the algorithm referring to past false detection examples. 【0307】 (Application Example 1) 【0308】 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". 【0309】 In online communication, it is important to protect users from threats such as improper behavior, fraud, and harassment. However, it is difficult to detect threats in real time with ordinary monitoring means, and it largely depends on the user's own information literacy, so the construction of a more rapid and accurate countermeasure system is required. Furthermore, not only defense against threats but also educational support for users to take safe actions themselves is needed. 【0310】 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. 【0311】 This invention includes a server that, with the user's permission, cooperates with an external information infrastructure to collect communication information in real time; a server that preprocesses the collected communication information and analyzes threats using a generative machine learning model; and a server that proposes specific countermeasures based on the detection of fraudulent activity and fraud based on the real-time analyzed communication information. This makes it possible to immediately detect risky communications and provide appropriate alerts and instructions to the user. Furthermore, by continuously learning the latest threat information, the system can constantly evolve while providing educational content that improves the user's information literacy. 【0312】 "User permission" means obtaining formal consent from the individual being investigated when collecting or analyzing information. 【0313】 "External information infrastructure" refers to external data platforms and communication networks that are linked to acquire communication information in real time. 【0314】 "Collecting communication information in real time" means the process of acquiring information instantly and without delay from the moment the data is generated. 【0315】 "Preprocessing" refers to the process of converting collected raw data into the necessary format and structure before analysis. 【0316】 A "generative machine learning model" is an AI-based algorithm that uses historical data and feedback to analyze and identify specific patterns and threats. 【0317】 "Threat analysis" is the process of examining collected communications information to identify potential risks and malicious activities. 【0318】 "Suggesting specific countermeasures" means recommending appropriate guidelines and actions to the user in response to detected threats. 【0319】 "Latest threat intelligence" refers to the most up-to-date knowledge and data on fraudulent activities and scams, which are constantly evolving. 【0320】 "Information literacy" refers to an individual's ability to use information safely and effectively on the internet and in communication. 【0321】 "Providing educational content" means presenting learning resources and guidelines to enable users to improve their knowledge and skills on their own. 【0322】 This invention is a system that enables users to communicate securely in an online environment, and its embodiments consist of multiple components. 【0323】 The server first obtains permission from the user, then connects with an external information infrastructure to collect communication information in real time. The collected communication information is preprocessed and then input into a generative machine learning model. The generative machine learning model used here is built using TensorFlow, PyTorch, etc., and is responsible for analyzing specific threat patterns. 【0324】 Once the analysis is complete, the server will suggest specific actions to take to the user, depending on the level of the detected threat. For example, if malicious activity or fraud is detected in a message, a notification such as "This link is dangerous. Do not access it." will be sent. These specific instructions are intended to encourage the user to take prompt action. 【0325】 The device also provides users with educational content to improve their information literacy. This content includes learning resources in quiz and video formats, designed to help users learn about safe online behavior while having fun. 【0326】 Furthermore, the server continuously updates its machine learning model based on user feedback and new threat intelligence. This ensures that the system is always well-prepared to respond to the latest threats. 【0327】 For example, if a user receives a message on social media asking for their credit card information, this system will immediately detect the possibility of fraud and issue a warning. It will then send advice such as, "It is safer not to provide your personal information." 【0328】 An example of a prompt message for the AI ​​model might be a text input such as, "Is this message potentially a scam? 'Hello, we need your bank account information.'" In this way, the present invention provides an environment in which users can safely use digital platforms. 【0329】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0330】 Step 1: 【0331】 The server, with user permission, interacts with an external information infrastructure. At this stage, it collects communication information in real time using APIs from social networking services (SNS) and messaging platforms. The input requires the user's account information and API key, and the output is the collected, unprocessed communication information. 【0332】 Step 2: 【0333】 The server preprocesses the collected communication information. This includes noise reduction, data cleansing, and formatting. The input is the raw communication information obtained in step 1, and the output contains clean data suitable for analysis. Here, text data filtering and normalization are performed using Python scripts or similar tools. 【0334】 Step 3: 【0335】 The server inputs pre-processed communication data into a generating AI model for analysis. A machine learning model (e.g., one using TensorFlow or PyTorch) detects threat patterns from the data. The input is clean data, and the output generates an assessment of the threat level and type for each communication. 【0336】 Step 4: 【0337】 The server notifies the user of the threat based on the analysis results. If the analysis results are deemed high-risk, a warning message is sent to the user's device. The input is the analysis results from step 3, and the output is the specific warning content sent to the user. At this time, a prompt message is generated to form a phrase that will attract the user's attention. 【0338】 Step 5: 【0339】 The device provides users with educational content to improve their information literacy. This includes quizzes to test knowledge and training modules using simulated scenarios. The input is the system's database of educational content, and the output is appropriate training content tailored to the user's learning progress. 【0340】 Step 6: 【0341】 The server continuously updates the generated AI model based on user feedback and newly detected threat information. This process involves incorporating new data to retrain the learning model. The input is feedback data and new communication information, and the output is the updated machine learning model. Model updates are performed through periodic batch processing. 【0342】 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. 【0343】 This invention is a system that promotes safe and healthy communication on online platforms and incorporates an emotion recognition engine. This system operates via a server, terminal, and user interface. Detailed embodiments are described below. 【0344】 Data collection and emotion recognition: 【0345】 When a user grants the system access to their social media accounts, the server retrieves messages and posts in real time via an API. Simultaneously, based on the collected communication data, the server uses an emotion engine to infer the user's emotional state. This engine analyzes emotions from the text and identifies the user's emotional state. 【0346】 Data analysis and threat awareness: 【0347】 The server inputs communication data, incorporating emotion recognition, into a generative model to identify inappropriate content and threats. By taking emotional changes into account, threat detection becomes more accurate than usual. 【0348】 Notification and intervention: 【0349】 Based on information from the emotion engine, the server adjusts the content of threat notifications according to the user's psychological state. For example, if the user is stressed, the notification will be delivered in more mitigating language. Depending on the level of threat, the user is given the option to pause or block the conversation. 【0350】 User education and support: 【0351】 The device provides users with appropriate educational information. This information includes emotionally-based coping strategies and interactive content to improve digital literacy more effectively. This creates an environment where users can communicate intuitively and securely. 【0352】 Continuous learning and feedback: 【0353】 The server analyzes user feedback and sentiment data to continuously improve the accuracy of its generative models and sentiment engine. This allows it to learn new threat and sentiment patterns, further enhancing user protection. 【0354】 Specific example: 【0355】 For example, if a user feels anxious after seeing extreme comments on social media, the server's emotion engine instantly recognizes the user's emotions. If a threat is detected, the server notifies the user and displays specific steps and countermeasures on their device to help them calm down. This allows the user to continue communicating with peace of mind. 【0356】 Thus, the present invention provides a more personalized and secure online environment through real-time sentiment analysis and data analysis. 【0357】 The following describes the processing flow. 【0358】 Step 1: 【0359】 The user grants the system permission to access their social media accounts and analyze sentiment data. Based on this permission, the server uses the social media platform's API to retrieve messages and posts in real time. 【0360】 Step 2: 【0361】 The server preprocesses the collected communication data. Specifically, it removes noisy elements from the text, tokenizes it, and converts it into a parseable format. At this stage, the sentiment engine also performs sentiment analysis on the text data. 【0362】 Step 3: 【0363】 The server inputs pre-processed data into a generative model to determine messages that may contain inappropriate content or threats. It also evaluates the results of the sentiment engine's analysis to analyze the psychological impact on users in communications. 【0364】 Step 4: 【0365】 The server identifies the presence and level of threats based on the output of the generative model and sentiment analysis. The threat level is further categorized into low, medium, and high, depending on the user's emotional state. 【0366】 Step 5: 【0367】 The server sends notifications to users based on the nature and level of the threat. These notifications use language that is sensitive to the user's emotional state and explain appropriate countermeasures and recommended actions. For example, if a user is feeling anxious, the server will choose more polite and reassuring language. 【0368】 Step 6: 【0369】 The device displays educational information tailored to the user's emotions and the type of threat. This information is provided as guidelines for effective countermeasures and content aimed at improving digital literacy. Based on this information, users can avoid danger and continue to communicate effectively. 【0370】 Step 7: 【0371】 The server accumulates user feedback and sentiment data, and regularly updates its generative models and sentiment engine. This continuous learning process improves the system's threat detection accuracy and sentiment analysis capabilities, resulting in more effective protection and support. 【0372】 (Example 2) 【0373】 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". 【0374】 Online communication, while convenient, often exposes users to inappropriate content and threats. Furthermore, simplistic threat notifications that fail to consider the user's psychological state can cause additional stress. This invention aims to solve these problems through a system that utilizes sentiment analysis to achieve more accurate threat recognition and provide psychologically appropriate responses to users. 【0375】 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. 【0376】 In this invention, the server includes means for collecting communication information in real time in cooperation with an information processing infrastructure with the user's permission, means for preprocessing the collected communication information and evaluating the user's psychological state using sentiment analysis technology, and means for analyzing threats using a generative model based on the evaluation results and improving the accuracy of the threat by reflecting specific emotional changes. This enables more precise threat recognition in accordance with the user's emotional state and the provision of psychologically appropriate threat notifications and countermeasures. 【0377】 A "user" is an individual or group that interacts with a system through an interface. 【0378】 An "information processing infrastructure" is a collection of hardware and software used to collect, store, and analyze data. 【0379】 "Real-time" refers to the concept where data acquisition and processing occur almost simultaneously, and information is provided to the user immediately. 【0380】 "Communication information" refers to data such as messages and posts exchanged on online platforms. 【0381】 "Emotion analysis technology" refers to methods and algorithms for analyzing text data and identifying the emotions and sensibilities contained within it. 【0382】 "Psychological state" refers to the state of emotions and consciousness, and is the internal state of the user identified through emotion analysis. 【0383】 A "generative model" is a statistical model that uses machine learning and artificial intelligence technologies to learn patterns from data and generate new data or results. 【0384】 A "threat" refers to inappropriate content or activities that could have a negative impact on users. 【0385】 "Threat accuracy" is an indicator that refers to the precision and reliability with which a system identifies threats. 【0386】 A "threat notification" is an alert or message that communicates information about an identified threat to the user. 【0387】 This invention is a system that promotes safe and healthy communication on online platforms. This system operates by combining sentiment analysis technology and generative AI models, with servers, terminals, and users as its main components. 【0388】 The server, through user-authorized access, utilizes APIs from social networking services (SNS) and messaging services as its information processing infrastructure to collect communication information in real time. This information collection is carried out efficiently using RESTful APIs and WebSocket technology. The collected information is stored on the server as text data. 【0389】 Next, the server processes this text data using sentiment analysis technology. It uses natural language processing (NLP) libraries to evaluate the emotions contained in the text. Specifically, it identifies the user's psychological state using open-source sentiment analysis tools or proprietary algorithms. 【0390】 The user's psychological state, as revealed by the analysis, is further evaluated in detail by a generative AI model. This model learns known threat patterns and improves threat accuracy by incorporating the results of sentiment analysis. The generative model utilizes deep learning frameworks and common machine learning tools. 【0391】 Based on the user's psychological state and threat level, the server provides a flexible notification mechanism. Notifications are sent using wording that takes the user's emotional state into consideration. These notifications are displayed to the user via their device, prompting specific actions. For example, if the user is under high stress, the notification might suggest a calm response as a "step to calm down." 【0392】 The device interactively provides users with educational information and coping strategies based on sentiment analysis. This allows users to improve their digital literacy and ensure safer online communication. 【0393】 For example, if a user detects an offensive post on social media, the server immediately performs sentiment analysis and recognizes that the user is feeling stressed. Depending on the situation, the device will display advice such as, "Take a deep breath and then check the message again." 【0394】 An example of a prompt might be: "If a user discovers a post on social media that makes them feel uneasy, how can the sentiment engine identify that emotion and provide a safe notification?" 【0395】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0396】 Step 1: 【0397】 The server, based on user permission, interacts with the information processing infrastructure to collect communication information in real time. Inputs include the user's SNS account and access rights to messaging platforms. The server retrieves data via APIs and stores it in text format. At this stage, raw message data is obtained as output. 【0398】 Step 2: 【0399】 The server preprocesses the acquired communication information using an emotion analysis engine. The input is the text data collected in step 1. The server uses natural language processing techniques to identify emotions from the text and classify them into emotional states such as joy, sadness, anger, and anxiety. The output is the analyzed emotion data. 【0400】 Step 3: 【0401】 The server performs threat analysis using a generative AI model based on the analyzed sentiment data. The input is the sentiment data obtained in step 2. The server uses the trained generative model to evaluate potential threats in the text and improves the accuracy of the threat assessment by incorporating the sentiment analysis results. The output is the threat assessment result. 【0402】 Step 4: 【0403】 The server sends a threat notification to the user based on the threat assessment results and sentiment data. The input is the threat assessment results and sentiment state from step 3. The server takes the user's psychological state into consideration and adjusts the notification method and content. The output is the adjusted notification message sent to the user's terminal. 【0404】 Step 5: 【0405】 The device displays the received notification message to the user and prompts them to take specific action. The input is the notification message sent in step 4. The device displays suggestions and actions in language that reduces the user's psychological burden. The output is a visual and textual notification to the user. 【0406】 Step 6: 【0407】 The server receives user feedback and threat assessment data to continuously update its generative model and sentiment analysis engine. Input consists of user feedback and threat assessment data. The server analyzes this data to improve the accuracy of the AI ​​model and identify new threat patterns. The output is an updated model and analysis engine. 【0408】 (Application Example 2) 【0409】 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". 【0410】 In online communication, users may experience a lack of detection and response to threats or inappropriate information that could potentially harm them. Furthermore, the lack of appropriate intervention and support tailored to their psychological state can negatively impact users' mental health. In addition, a lack of digital literacy makes it difficult for users to independently identify and address threats. To address these issues, there is a need for systems that promote safe and healthy communication utilizing sentiment recognition technology. 【0411】 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. 【0412】 In this invention, the server includes means for inferring the user's psychological state using an emotion analysis engine and providing appropriate information, means for collecting information in real time in cooperation with an information processing device with the user's permission, and means for preprocessing the collected information and analyzing threats using a generated mathematical model. This enables the appropriate provision of educational information tailored to the user's psychological state, as well as more accurate threat detection and rapid response. 【0413】 An "information processing device" is a device that processes various types of data based on user permission and acquires and analyzes information in cooperation with an external data platform. 【0414】 A "generated mathematical model" is a model formed through data analysis and used to evaluate and detect online threats. 【0415】 An "emotion analysis engine" is an engine that analyzes a user's communication and uses the information obtained from it to infer their psychological state. 【0416】 "Threat level" is a measure that indicates the degree of risk to users, as identified as a result of analysis by an information processing device. 【0417】 "Educational information" refers to information that provides users with the knowledge and skills necessary to improve their digital literacy and maintain a safe online environment. 【0418】 The system implementing this invention features a complex mechanism combining sentiment analysis technology and a generated mathematical model to improve the security of communication on online platforms. The server interacts in real time with an external data platform authorized by the user to collect information. This information is preprocessed using an information processing device, and threats are analyzed using the generated mathematical model. Furthermore, a sentiment analysis engine is used to infer the user's psychological state and provide appropriate information. 【0419】 Based on these analysis results, the server identifies the threat level and notifies the user in an appropriate manner. Users are presented with options to temporarily suspend or block communications as countermeasures appropriate to the threat level. Furthermore, educational information is provided to improve users' digital literacy, helping them to communicate securely. 【0420】 As a concrete example, if a user encounters inappropriate comments on social media, the server immediately detects the user's anxiety through sentiment analysis and, based on the results, notifies them with a "guide to calm down." At the same time, it presents appropriate educational information according to the user's emotional state, enabling them to continue safer and healthier online interactions. 【0421】 An example of a prompt message generated using an AI model would be: "Generate a notification using gentle language to alleviate anxiety, taking into account the user's psychological state. For example, what words should be used if the user is feeling anxious?" This makes notifications to users more personalized and provides a sense of security. 【0422】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0423】 Step 1: 【0424】 The server, with user permission, interacts with an external data platform to collect data in real time. The input is communication data from the platform, and the output is data converted into a processable format. The server extracts the data using an API and formats it for easier analysis. 【0425】 Step 2: 【0426】 The server preprocesses the collected communication data and analyzes threats using the generated mathematical model. The input is formatted communication data, and the output is the analysis results, including a threat assessment. This process uses natural language processing techniques to analyze text and identify potential threats. 【0427】 Step 3: 【0428】 The server uses an emotion analysis engine to infer the user's psychological state. The input consists of communication content with the user and its metadata, and the output is the inferred emotional state. Emotion analysis uses machine learning algorithms to extract emotional characteristics from text. 【0429】 Step 4: 【0430】 The server identifies the threat level based on the analysis results and notifies the user. The input is the result of threat analysis and sentiment inference, and the output is a customized notification message. The server utilizes prompts to generate the most appropriate notification content for the user. 【0431】 Step 5: 【0432】 The server provides the user with the option to temporarily suspend or block communications. The input is the identified threat level, and the output is the control option the user can select. The user receives a notification and can take appropriate action. 【0433】 Step 6: 【0434】 The device provides users with educational information to improve their digital literacy. Input is the user's psychological state and threat level, and output is the corresponding educational content. The educational content is interactive instructional material designed using a generative AI model. 【0435】 Step 7: 【0436】 The server continuously updates the mathematical model generated based on user feedback, improving its accuracy. Input is analysis and user feedback data, and output is the updated model. This enhances the system's ability to respond to new threat patterns. 【0437】 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. 【0438】 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. 【0439】 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. 【0440】 [Third Embodiment] 【0441】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0442】 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. 【0443】 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). 【0444】 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. 【0445】 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. 【0446】 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). 【0447】 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. 【0448】 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. 【0449】 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. 【0450】 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. 【0451】 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. 【0452】 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". 【0453】 This invention is a system that supports users in communicating safely and securely on online platforms. This system is primarily implemented through a server, terminal, and user interface. Its specific form is described below. 【0454】 Data collection: 【0455】 The user first grants the system permission to access their social networking service (SNS) accounts and messaging applications. Based on this permission, the server uses the SNS platform's API to collect messages and posts in real time. 【0456】 Data analysis: 【0457】 The collected communication data is preprocessed by the server and input into a generative model. The generative model uses machine learning algorithms to analyze the data and detect specific threat patterns. Threats here include inappropriate solicitation, fraud, harassment, and illegal transactions. 【0458】 Threat notification and intervention: 【0459】 The server determines the level of the threat based on the analysis results. If a threat is detected, the server immediately notifies the user and offers appropriate countermeasures. For example, it may offer the user the option to temporarily suspend or completely block the conversation. 【0460】 User education: 【0461】 The device provides users with educational information to improve their safe digital literacy. This information includes materials to deepen their understanding of threats and guidelines for specific countermeasures. It also provides interactive content to create an environment where users can learn at their own pace. 【0462】 Continuous learning: 【0463】 The server updates its generative model using user feedback and newly acquired data. This allows the system to constantly learn the latest threat patterns and continuously improve its detection accuracy. 【0464】 Specific example: 【0465】 For example, suppose a user receives a message from a friend on social media. If this message requests personal information, the server analyzes the message and determines that it may be a scam. It immediately issues a warning to the user, urging caution and advising them not to easily provide personal information. By promptly taking action based on this warning, the user can prevent potential harm. 【0466】 In this way, this system provides practical means for building a secure online environment through real-time data analysis and user education. 【0467】 The following describes the processing flow. 【0468】 Step 1: 【0469】 The user grants the system access permission to access their social media account. This permission allows the server to use the API to retrieve individual messages and posts in real time. 【0470】 Step 2: 【0471】 The server preprocesses the communication data collected from the SNS platform. Specifically, it removes noise from the data and formats it into a format suitable for analysis. This process includes removing emojis and parsing HTML tags. 【0472】 Step 3: 【0473】 The server inputs pre-processed data into a generative model. This model is trained on a large amount of known data and uses machine learning to detect inappropriate content and threats. As a result of the analysis, it determines whether the data is related to fraud, harassment, or other threats. 【0474】 Step 4: 【0475】 The server uses the output from the generative model to identify the threat level. This level is categorized into low, medium, and high, and different responses are required depending on the severity. 【0476】 Step 5: 【0477】 When a threat is detected, the server notifies the user of its details. The notification includes specific information about the threat and recommended actions to take. In some cases, options such as pausing or completely blocking the conversation may also be presented. 【0478】 Step 6: 【0479】 The device displays educational content to help users learn how to respond when faced with threats. This is provided as guidelines and interactive learning modules to support users in practicing safer communication. 【0480】 Step 7: 【0481】 The server continuously updates its generation model based on implemented countermeasures and user feedback. When new threat patterns are detected, this information is reflected in the system to provide more accurate threat detection capabilities. 【0482】 (Example 1) 【0483】 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." 【0484】 In recent years, with the widespread adoption of internet-based communication technologies, the security issues faced by users have increased. In particular, threats such as inappropriate solicitations, fraud, harassment, and illegal transactions exist, creating a need for systems that can detect and warn users in real time. However, existing technologies have challenges in terms of threat detection accuracy, timely notification, and the continuity of user education. 【0485】 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. 【0486】 In this invention, the server includes means for collecting communication information in real time in cooperation with an external information processing device with the user's permission, means for preprocessing the collected communication information and analyzing threats using a machine learning model, and means for identifying the level of the threat based on the analysis results and notifying the user. This allows the user to be quickly protected from potential threats and to always have access to the latest security measures. 【0487】 "Collecting communication information in real time in cooperation with an external information processing device with the user's permission" refers to the process of connecting the user's communication data to other computer systems and instantly acquiring information that occurs on the internet, after the user has given permission to access it. 【0488】 "Preprocessing collected communication information and analyzing threats using machine learning models" refers to the process of organizing the obtained communication-related data according to certain rules, and then using pre-built algorithms to identify potential risks. 【0489】 "Identifying the threat level based on analysis results and notifying users" means evaluating the results derived from data analysis, determining the severity of the threat, and then providing that information to users. 【0490】 "Providing the option to temporarily suspend or block communications depending on the level of threat" means offering users means to interrupt or completely stop continuous data exchange depending on the degree of identified dangerous behavior. 【0491】 "Providing users with educational data to improve their information technology literacy" means giving users educational materials aimed at improving their knowledge and skills for safe internet use. 【0492】 "Generating educational guidelines regarding inappropriate communication situations using analyzed information" means creating guidelines for users to avoid inappropriate situations themselves, based on the results of analyzing past data. 【0493】 "Continuously updating machine learning models based on analysis results and user feedback to improve threat detection accuracy" means using the obtained analytical data and user feedback to improve the effectiveness of the algorithm and enable more accurate identification of risks. 【0494】 "Accumulating information on detected threats and forming an information repository to identify new threat patterns" refers to building a database by storing data on previously identified risky behaviors and using that data to identify potential new risks. 【0495】 This invention provides a system that enables users to communicate safely and securely over the internet. The system mainly consists of a server, a terminal, and the user's device. 【0496】 The server first obtains permission from the user and then collects communication information in real time via an external information processing device. This process includes collecting data from the user's social media accounts and messaging applications. The collected information is preprocessed within the server and then input into a generative AI model, which is a machine learning model. 【0497】 This generative AI model analyzes collected data to detect potential threats. Examples of threats include inappropriate solicitation, fraud, harassment, and illegal transactions. Based on the analyzed data, the server determines the level of the threat and immediately notifies the user. 【0498】 The device provides users with digital literacy-enhancing content to facilitate safe online activities. This includes interactive guidelines and quizzes that users can use to improve their safety. 【0499】 A concrete example would be a user receiving a message on social media from a stranger asking for personal information. The server analyzes the message, and if it determines that it is highly likely to be a scam, it immediately sends a warning notification to the user. At the same time, it also advises the user to avoid providing personal information. 【0500】 An example of a prompt message is: "I've recently been asked for personal information by strangers on social media. Please tell me how I should deal with this." 【0501】 These features allow users to protect themselves from potential online harm and use the internet with peace of mind. The servers also update machine learning models based on analysis results and user feedback to maintain a constant response to the latest threats. 【0502】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0503】 Step 1: 【0504】 The server receives permission requests from users to access SNS accounts and messaging apps. The input is user-defined permission settings. Based on these permissions, the server collaborates with external information processing devices to collect communication information in real time. The output is the raw, unprocessed communication data. At this stage, the server calls the SNS platform's API to retrieve the latest communication content. 【0505】 Step 2: 【0506】 The server preprocesses the collected communication data. The input is the raw communication data collected in step 1. The server formats this data and filters out unnecessary information to convert it into a format suitable for the generating AI model. The output is a dataset that has been preprocessed and is suitable for analysis. Here, specific actions are performed, such as removing extraneous spaces and special characters, and extracting target text portions. 【0507】 Step 3: 【0508】 The server inputs the pre-processed data into a generative AI model for analysis. The input is the dataset prepared in step 2. The generative AI model utilizes machine learning algorithms to detect specific threat patterns within the data. The output is information about the characteristics and threat level of the detected threats. Specifically, the model identifies similar patterns and compares them with historical database data to determine the presence or absence of a threat. 【0509】 Step 4: 【0510】 Based on the analysis results, the server identifies the threat level and prepares to notify the user. The input is the analysis results from step 3. The server generates the severity of the threat and a description of it, and creates a warning message for the user. The output is the notification message, which is sent to the terminal. Specifically, this involves generating a message such as, "This may be a scam, so do not provide personal information to the sender." 【0511】 Step 5: 【0512】 The device provides users with educational content tailored to the threat. Input consists of the warning message created in step 4 and appropriate educational content based on its content. The device displays interactive guidelines and quiz-style educational materials, providing users with opportunities to deepen their understanding. Output is educational content displayed to the user. Specifically, it displays materials illustrating relevant harassment examples and coping strategies. 【0513】 Step 6: 【0514】 The server analyzes user feedback and newly collected data to continuously update the generated AI model. Input consists of user feedback and newly collected data. The server uses this information to adjust the model parameters and improve analysis accuracy. The output is the updated machine learning model. Specifically, it recalculates the algorithm's weights based on past false positives. 【0515】 (Application Example 1) 【0516】 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." 【0517】 In online communication, it is crucial to protect users from threats such as fraud, scams, and harassment. However, real-time threat detection is difficult with conventional monitoring methods, and it relies heavily on the user's own information literacy. Therefore, there is a need for a more rapid and accurate countermeasure system. Furthermore, in addition to defending against threats, educational support is also needed to help users take safe actions themselves. 【0518】 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. 【0519】 This invention includes a server that, with the user's permission, cooperates with an external information infrastructure to collect communication information in real time; a server that preprocesses the collected communication information and analyzes threats using a generative machine learning model; and a server that proposes specific countermeasures based on the detection of fraudulent activity and fraud based on the real-time analyzed communication information. This makes it possible to immediately detect risky communications and provide appropriate alerts and instructions to the user. Furthermore, by continuously learning the latest threat information, the system can constantly evolve while providing educational content that improves the user's information literacy. 【0520】 "User permission" means obtaining formal consent from the individual being investigated when collecting or analyzing information. 【0521】 "External information infrastructure" refers to external data platforms and communication networks that are linked to acquire communication information in real time. 【0522】 "Collecting communication information in real time" means the process of acquiring information instantly and without delay from the moment the data is generated. 【0523】 "Preprocessing" refers to the process of converting collected raw data into the necessary format and structure before analysis. 【0524】 A "generative machine learning model" is an AI-based algorithm that uses historical data and feedback to analyze and identify specific patterns and threats. 【0525】 "Threat analysis" is the process of examining collected communications information to identify potential risks and malicious activities. 【0526】 "Suggesting specific countermeasures" means recommending appropriate guidelines and actions to the user in response to detected threats. 【0527】 "Latest threat intelligence" refers to the most up-to-date knowledge and data on fraudulent activities and scams, which are constantly evolving. 【0528】 "Information literacy" refers to an individual's ability to use information safely and effectively on the internet and in communication. 【0529】 "Providing educational content" means presenting learning resources and guidelines to enable users to improve their knowledge and skills on their own. 【0530】 This invention is a system that enables users to communicate securely in an online environment, and its embodiments consist of multiple components. 【0531】 The server first obtains permission from the user, then connects with an external information infrastructure to collect communication information in real time. The collected communication information is preprocessed and then input into a generative machine learning model. The generative machine learning model used here is built using TensorFlow, PyTorch, etc., and is responsible for analyzing specific threat patterns. 【0532】 Once the analysis is complete, the server will suggest specific actions to take to the user, depending on the level of the detected threat. For example, if malicious activity or fraud is detected in a message, a notification such as "This link is dangerous. Do not access it." will be sent. These specific instructions are intended to encourage the user to take prompt action. 【0533】 The device also provides users with educational content to improve their information literacy. This content includes learning resources in quiz and video formats, designed to help users learn about safe online behavior while having fun. 【0534】 Furthermore, the server continuously updates its machine learning model based on user feedback and new threat intelligence. This ensures that the system is always well-prepared to respond to the latest threats. 【0535】 For example, if a user receives a message on social media asking for their credit card information, this system will immediately detect the possibility of fraud and issue a warning. It will then send advice such as, "It is safer not to provide your personal information." 【0536】 An example of a prompt message for the AI ​​model might be a text input such as, "Is this message potentially a scam? 'Hello, we need your bank account information.'" In this way, the present invention provides an environment in which users can safely use digital platforms. 【0537】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0538】 Step 1: 【0539】 The server, with user permission, interacts with an external information infrastructure. At this stage, it collects communication information in real time using APIs from social networking services (SNS) and messaging platforms. The input requires the user's account information and API key, and the output is the collected, unprocessed communication information. 【0540】 Step 2: 【0541】 The server preprocesses the collected communication information. This includes noise reduction, data cleansing, and formatting. The input is the raw communication information obtained in step 1, and the output contains clean data suitable for analysis. Here, text data filtering and normalization are performed using Python scripts or similar tools. 【0542】 Step 3: 【0543】 The server inputs pre-processed communication data into a generating AI model for analysis. A machine learning model (e.g., one using TensorFlow or PyTorch) detects threat patterns from the data. The input is clean data, and the output generates an assessment of the threat level and type for each communication. 【0544】 Step 4: 【0545】 The server notifies the user of the threat based on the analysis results. If the analysis results are deemed high-risk, a warning message is sent to the user's device. The input is the analysis results from step 3, and the output is the specific warning content sent to the user. At this time, a prompt message is generated to form a phrase that will attract the user's attention. 【0546】 Step 5: 【0547】 The device provides users with educational content to improve their information literacy. This includes quizzes to test knowledge and training modules using simulated scenarios. The input is the system's database of educational content, and the output is appropriate training content tailored to the user's learning progress. 【0548】 Step 6: 【0549】 The server continuously updates the generated AI model based on user feedback and newly detected threat information. This process involves incorporating new data to retrain the learning model. The input is feedback data and new communication information, and the output is the updated machine learning model. Model updates are performed through periodic batch processing. 【0550】 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. 【0551】 This invention is a system that promotes safe and healthy communication on online platforms and incorporates an emotion recognition engine. This system operates via a server, terminal, and user interface. Detailed embodiments are described below. 【0552】 Data collection and emotion recognition: 【0553】 When a user grants the system access to their social media accounts, the server retrieves messages and posts in real time via an API. Simultaneously, based on the collected communication data, the server uses an emotion engine to infer the user's emotional state. This engine analyzes emotions from the text and identifies the user's emotional state. 【0554】 Data analysis and threat awareness: 【0555】 The server inputs communication data, incorporating emotion recognition, into a generative model to identify inappropriate content and threats. By taking emotional changes into account, threat detection becomes more accurate than usual. 【0556】 Notification and intervention: 【0557】 Based on information from the emotion engine, the server adjusts the content of threat notifications according to the user's psychological state. For example, if the user is stressed, the notification will be delivered in more mitigating language. Depending on the level of threat, the user is given the option to pause or block the conversation. 【0558】 User education and support: 【0559】 The device provides users with appropriate educational information. This information includes emotionally-based coping strategies and interactive content to improve digital literacy more effectively. This creates an environment where users can communicate intuitively and securely. 【0560】 Continuous learning and feedback: 【0561】 The server analyzes user feedback and sentiment data to continuously improve the accuracy of its generative models and sentiment engine. This allows it to learn new threat and sentiment patterns, further enhancing user protection. 【0562】 Specific example: 【0563】 For example, if a user feels anxious after seeing extreme comments on social media, the server's emotion engine instantly recognizes the user's emotions. If a threat is detected, the server notifies the user and displays specific steps and countermeasures on their device to help them calm down. This allows the user to continue communicating with peace of mind. 【0564】 Thus, the present invention provides a more personalized and secure online environment through real-time sentiment analysis and data analysis. 【0565】 The following describes the processing flow. 【0566】 Step 1: 【0567】 The user grants the system permission to access their social media accounts and analyze sentiment data. Based on this permission, the server uses the social media platform's API to retrieve messages and posts in real time. 【0568】 Step 2: 【0569】 The server preprocesses the collected communication data. Specifically, it removes noisy elements from the text, tokenizes it, and converts it into a parseable format. At this stage, the sentiment engine also performs sentiment analysis on the text data. 【0570】 Step 3: 【0571】 The server inputs pre-processed data into a generative model to determine messages that may contain inappropriate content or threats. It also evaluates the results of the sentiment engine's analysis to analyze the psychological impact on users in communications. 【0572】 Step 4: 【0573】 The server identifies the presence and level of threats based on the output of the generative model and sentiment analysis. The threat level is further categorized into low, medium, and high, depending on the user's emotional state. 【0574】 Step 5: 【0575】 The server sends notifications to users based on the nature and level of the threat. These notifications use language that is sensitive to the user's emotional state and explain appropriate countermeasures and recommended actions. For example, if a user is feeling anxious, the server will choose more polite and reassuring language. 【0576】 Step 6: 【0577】 The device displays educational information tailored to the user's emotions and the type of threat. This information is provided as guidelines for effective countermeasures and content aimed at improving digital literacy. Based on this information, users can avoid danger and continue to communicate effectively. 【0578】 Step 7: 【0579】 The server accumulates user feedback and sentiment data, and regularly updates its generative models and sentiment engine. This continuous learning process improves the system's threat detection accuracy and sentiment analysis capabilities, resulting in more effective protection and support. 【0580】 (Example 2) 【0581】 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." 【0582】 Online communication, while convenient, often exposes users to inappropriate content and threats. Furthermore, simplistic threat notifications that fail to consider the user's psychological state can cause additional stress. This invention aims to solve these problems through a system that utilizes sentiment analysis to achieve more accurate threat recognition and provide psychologically appropriate responses to users. 【0583】 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. 【0584】 In this invention, the server includes means for collecting communication information in real time in cooperation with an information processing infrastructure with the user's permission, means for preprocessing the collected communication information and evaluating the user's psychological state using sentiment analysis technology, and means for analyzing threats using a generative model based on the evaluation results and improving the accuracy of the threat by reflecting specific emotional changes. This enables more precise threat recognition in accordance with the user's emotional state and the provision of psychologically appropriate threat notifications and countermeasures. 【0585】 A "user" is an individual or group that interacts with a system through an interface. 【0586】 An "information processing infrastructure" is a collection of hardware and software used to collect, store, and analyze data. 【0587】 "Real-time" refers to the concept where data acquisition and processing occur almost simultaneously, and information is provided to the user immediately. 【0588】 "Communication information" refers to data such as messages and posts exchanged on online platforms. 【0589】 "Emotion analysis technology" refers to methods and algorithms for analyzing text data and identifying the emotions and sensibilities contained within it. 【0590】 "Psychological state" refers to the state of emotions and consciousness, and is the internal state of the user identified through emotion analysis. 【0591】 A "generative model" is a statistical model that uses machine learning and artificial intelligence technologies to learn patterns from data and generate new data or results. 【0592】 A "threat" refers to inappropriate content or activities that could have a negative impact on users. 【0593】 "Threat accuracy" is an indicator that refers to the precision and reliability with which a system identifies threats. 【0594】 A "threat notification" is an alert or message that communicates information about an identified threat to the user. 【0595】 This invention is a system that promotes safe and healthy communication on online platforms. This system operates by combining sentiment analysis technology and generative AI models, with servers, terminals, and users as its main components. 【0596】 The server, through user-authorized access, utilizes APIs from social networking services (SNS) and messaging services as its information processing infrastructure to collect communication information in real time. This information collection is carried out efficiently using RESTful APIs and WebSocket technology. The collected information is stored on the server as text data. 【0597】 Next, the server processes this text data using sentiment analysis technology. It uses natural language processing (NLP) libraries to evaluate the emotions contained in the text. Specifically, it identifies the user's psychological state using open-source sentiment analysis tools or proprietary algorithms. 【0598】 The user's psychological state, as revealed by the analysis, is further evaluated in detail by a generative AI model. This model learns known threat patterns and improves threat accuracy by incorporating the results of sentiment analysis. The generative model utilizes deep learning frameworks and common machine learning tools. 【0599】 Based on the user's psychological state and threat level, the server provides a flexible notification mechanism. Notifications are sent using wording that takes the user's emotional state into consideration. These notifications are displayed to the user via their device, prompting specific actions. For example, if the user is under high stress, the notification might suggest a calm response as a "step to calm down." 【0600】 The device interactively provides users with educational information and coping strategies based on sentiment analysis. This allows users to improve their digital literacy and ensure safer online communication. 【0601】 For example, if a user detects an offensive post on social media, the server immediately performs sentiment analysis and recognizes that the user is feeling stressed. Depending on the situation, the device will display advice such as, "Take a deep breath and then check the message again." 【0602】 An example of a prompt might be: "If a user discovers a post on social media that makes them feel uneasy, how can the sentiment engine identify that emotion and provide a safe notification?" 【0603】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0604】 Step 1: 【0605】 The server, based on user permission, interacts with the information processing infrastructure to collect communication information in real time. Inputs include the user's SNS account and access rights to messaging platforms. The server retrieves data via APIs and stores it in text format. At this stage, raw message data is obtained as output. 【0606】 Step 2: 【0607】 The server preprocesses the acquired communication information using an emotion analysis engine. The input is the text data collected in step 1. The server uses natural language processing techniques to identify emotions from the text and classify them into emotional states such as joy, sadness, anger, and anxiety. The output is the analyzed emotion data. 【0608】 Step 3: 【0609】 The server performs threat analysis using a generative AI model based on the analyzed sentiment data. The input is the sentiment data obtained in step 2. The server uses the trained generative model to evaluate potential threats in the text and improves the accuracy of the threat assessment by incorporating the sentiment analysis results. The output is the threat assessment result. 【0610】 Step 4: 【0611】 The server sends a threat notification to the user based on the threat assessment results and sentiment data. The input is the threat assessment results and sentiment state from step 3. The server takes the user's psychological state into consideration and adjusts the notification method and content. The output is the adjusted notification message sent to the user's terminal. 【0612】 Step 5: 【0613】 The device displays the received notification message to the user and prompts them to take specific action. The input is the notification message sent in step 4. The device displays suggestions and actions in language that reduces the user's psychological burden. The output is a visual and textual notification to the user. 【0614】 Step 6: 【0615】 The server receives user feedback and threat assessment data to continuously update its generative model and sentiment analysis engine. Input consists of user feedback and threat assessment data. The server analyzes this data to improve the accuracy of the AI ​​model and identify new threat patterns. The output is an updated model and analysis engine. 【0616】 (Application Example 2) 【0617】 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." 【0618】 In online communication, users may experience a lack of detection and response to threats or inappropriate information that could potentially harm them. Furthermore, the lack of appropriate intervention and support tailored to their psychological state can negatively impact users' mental health. In addition, a lack of digital literacy makes it difficult for users to independently identify and address threats. To address these issues, there is a need for systems that promote safe and healthy communication utilizing sentiment recognition technology. 【0619】 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. 【0620】 In this invention, the server includes means for inferring the user's psychological state using an emotion analysis engine and providing appropriate information, means for collecting information in real time in cooperation with an information processing device with the user's permission, and means for preprocessing the collected information and analyzing threats using a generated mathematical model. This enables the appropriate provision of educational information tailored to the user's psychological state, as well as more accurate threat detection and rapid response. 【0621】 An "information processing device" is a device that processes various types of data based on user permission and acquires and analyzes information in cooperation with an external data platform. 【0622】 A "generated mathematical model" is a model formed through data analysis and used to evaluate and detect online threats. 【0623】 An "emotion analysis engine" is an engine that analyzes a user's communication and uses the information obtained from it to infer their psychological state. 【0624】 "Threat level" is a measure that indicates the degree of risk to users, as identified as a result of analysis by an information processing device. 【0625】 "Educational information" refers to information that provides users with the knowledge and skills necessary to improve their digital literacy and maintain a safe online environment. 【0626】 The system implementing this invention features a complex mechanism combining sentiment analysis technology and a generated mathematical model to improve the security of communication on online platforms. The server interacts in real time with an external data platform authorized by the user to collect information. This information is preprocessed using an information processing device, and threats are analyzed using the generated mathematical model. Furthermore, a sentiment analysis engine is used to infer the user's psychological state and provide appropriate information. 【0627】 Based on these analysis results, the server identifies the threat level and notifies the user in an appropriate manner. Users are presented with options to temporarily suspend or block communications as countermeasures appropriate to the threat level. Furthermore, educational information is provided to improve users' digital literacy, helping them to communicate securely. 【0628】 As a concrete example, if a user encounters inappropriate comments on social media, the server immediately detects the user's anxiety through sentiment analysis and, based on the results, notifies them with a "guide to calm down." At the same time, it presents appropriate educational information according to the user's emotional state, enabling them to continue safer and healthier online interactions. 【0629】 An example of a prompt message generated using an AI model would be: "Generate a notification using gentle language to alleviate anxiety, taking into account the user's psychological state. For example, what words should be used if the user is feeling anxious?" This makes notifications to users more personalized and provides a sense of security. 【0630】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0631】 Step 1: 【0632】 The server, with user permission, interacts with an external data platform to collect data in real time. The input is communication data from the platform, and the output is data converted into a processable format. The server extracts the data using an API and formats it for easier analysis. 【0633】 Step 2: 【0634】 The server preprocesses the collected communication data and analyzes threats using the generated mathematical model. The input is formatted communication data, and the output is the analysis results, including a threat assessment. This process uses natural language processing techniques to analyze text and identify potential threats. 【0635】 Step 3: 【0636】 The server uses an emotion analysis engine to infer the user's psychological state. The input consists of communication content with the user and its metadata, and the output is the inferred emotional state. Emotion analysis uses machine learning algorithms to extract emotional characteristics from text. 【0637】 Step 4: 【0638】 The server identifies the threat level based on the analysis results and notifies the user. The input is the result of threat analysis and sentiment inference, and the output is a customized notification message. The server utilizes prompts to generate the most appropriate notification content for the user. 【0639】 Step 5: 【0640】 The server provides the user with the option to temporarily suspend or block communications. The input is the identified threat level, and the output is the control option the user can select. The user receives a notification and can take appropriate action. 【0641】 Step 6: 【0642】 The device provides users with educational information to improve their digital literacy. Input is the user's psychological state and threat level, and output is the corresponding educational content. The educational content is interactive instructional material designed using a generative AI model. 【0643】 Step 7: 【0644】 The server continuously updates the mathematical model generated based on user feedback, improving its accuracy. Input is analysis and user feedback data, and output is the updated model. This enhances the system's ability to respond to new threat patterns. 【0645】 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. 【0646】 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. 【0647】 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. 【0648】 [Fourth Embodiment] 【0649】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0650】 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. 【0651】 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). 【0652】 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. 【0653】 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. 【0654】 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). 【0655】 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. 【0656】 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. 【0657】 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. 【0658】 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. 【0659】 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. 【0660】 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. 【0661】 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". 【0662】 This invention is a system that supports users in communicating safely and securely on online platforms. This system is primarily implemented through a server, terminal, and user interface. Its specific form is described below. 【0663】 Data collection: 【0664】 The user first grants the system permission to access their social networking service (SNS) accounts and messaging applications. Based on this permission, the server uses the SNS platform's API to collect messages and posts in real time. 【0665】 Data analysis: 【0666】 The collected communication data is preprocessed by the server and input into a generative model. The generative model uses machine learning algorithms to analyze the data and detect specific threat patterns. Threats here include inappropriate solicitation, fraud, harassment, and illegal transactions. 【0667】 Threat notification and intervention: 【0668】 The server determines the level of the threat based on the analysis results. If a threat is detected, the server immediately notifies the user and offers appropriate countermeasures. For example, it may offer the user the option to temporarily suspend or completely block the conversation. 【0669】 User education: 【0670】 The device provides users with educational information to improve their safe digital literacy. This information includes materials to deepen their understanding of threats and guidelines for specific countermeasures. It also provides interactive content to create an environment where users can learn at their own pace. 【0671】 Continuous learning: 【0672】 The server updates its generative model using user feedback and newly acquired data. This allows the system to constantly learn the latest threat patterns and continuously improve its detection accuracy. 【0673】 Specific example: 【0674】 For example, suppose a user receives a message from a friend on social media. If this message requests personal information, the server analyzes the message and determines that it may be a scam. It immediately issues a warning to the user, urging caution and advising them not to easily provide personal information. By promptly taking action based on this warning, the user can prevent potential harm. 【0675】 In this way, this system provides practical means for building a secure online environment through real-time data analysis and user education. 【0676】 The following describes the processing flow. 【0677】 Step 1: 【0678】 The user grants the system access permission to access their social media account. This permission allows the server to use the API to retrieve individual messages and posts in real time. 【0679】 Step 2: 【0680】 The server preprocesses the communication data collected from the SNS platform. Specifically, it removes noise from the data and formats it into a format suitable for analysis. This process includes removing emojis and parsing HTML tags. 【0681】 Step 3: 【0682】 The server inputs pre-processed data into a generative model. This model is trained on a large amount of known data and uses machine learning to detect inappropriate content and threats. As a result of the analysis, it determines whether the data is related to fraud, harassment, or other threats. 【0683】 Step 4: 【0684】 The server uses the output from the generative model to identify the threat level. This level is categorized into low, medium, and high, and different responses are required depending on the severity. 【0685】 Step 5: 【0686】 When a threat is detected, the server notifies the user of its details. The notification includes specific information about the threat and recommended actions to take. In some cases, options such as pausing or completely blocking the conversation may also be presented. 【0687】 Step 6: 【0688】 The device displays educational content to help users learn how to respond when faced with threats. This is provided as guidelines and interactive learning modules to support users in practicing safer communication. 【0689】 Step 7: 【0690】 The server continuously updates its generation model based on implemented countermeasures and user feedback. When new threat patterns are detected, this information is reflected in the system to provide more accurate threat detection capabilities. 【0691】 (Example 1) 【0692】 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". 【0693】 In recent years, with the widespread adoption of internet-based communication technologies, the security issues faced by users have increased. In particular, threats such as inappropriate solicitations, fraud, harassment, and illegal transactions exist, creating a need for systems that can detect and warn users in real time. However, existing technologies have challenges in terms of threat detection accuracy, timely notification, and the continuity of user education. 【0694】 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. 【0695】 In this invention, the server includes means for collecting communication information in real time in cooperation with an external information processing device with the user's permission, means for preprocessing the collected communication information and analyzing threats using a machine learning model, and means for identifying the level of the threat based on the analysis results and notifying the user. This allows the user to be quickly protected from potential threats and to always have access to the latest security measures. 【0696】 "Collecting communication information in real time in cooperation with an external information processing device with the user's permission" refers to the process of connecting the user's communication data to other computer systems and instantly acquiring information that occurs on the internet, after the user has given permission to access it. 【0697】 "Preprocessing collected communication information and analyzing threats using machine learning models" refers to the process of organizing the obtained communication-related data according to certain rules, and then using pre-built algorithms to identify potential risks. 【0698】 "Identifying the threat level based on analysis results and notifying users" means evaluating the results derived from data analysis, determining the severity of the threat, and then providing that information to users. 【0699】 "Providing the option to temporarily suspend or block communications depending on the level of threat" means offering users means to interrupt or completely stop continuous data exchange depending on the degree of identified dangerous behavior. 【0700】 "Providing users with educational data to improve their information technology literacy" means giving users educational materials aimed at improving their knowledge and skills for safe internet use. 【0701】 "Generating educational guidelines regarding inappropriate communication situations using analyzed information" means creating guidelines for users to avoid inappropriate situations themselves, based on the results of analyzing past data. 【0702】 "Continuously updating machine learning models based on analysis results and user feedback to improve threat detection accuracy" means using the obtained analytical data and user feedback to improve the effectiveness of the algorithm and enable more accurate identification of risks. 【0703】 "Accumulating information on detected threats and forming an information repository to identify new threat patterns" refers to building a database by storing data on previously identified risky behaviors and using that data to identify potential new risks. 【0704】 This invention provides a system that enables users to communicate safely and securely over the internet. The system mainly consists of a server, a terminal, and the user's device. 【0705】 The server first obtains permission from the user and then collects communication information in real time via an external information processing device. This process includes collecting data from the user's social media accounts and messaging applications. The collected information is preprocessed within the server and then input into a generative AI model, which is a machine learning model. 【0706】 This generative AI model analyzes collected data to detect potential threats. Examples of threats include inappropriate solicitation, fraud, harassment, and illegal transactions. Based on the analyzed data, the server determines the level of the threat and immediately notifies the user. 【0707】 The device provides users with digital literacy-enhancing content to facilitate safe online activities. This includes interactive guidelines and quizzes that users can use to improve their safety. 【0708】 A concrete example would be a user receiving a message on social media from a stranger asking for personal information. The server analyzes the message, and if it determines that it is highly likely to be a scam, it immediately sends a warning notification to the user. At the same time, it also advises the user to avoid providing personal information. 【0709】 An example of a prompt message is: "I've recently been asked for personal information by strangers on social media. Please tell me how I should deal with this." 【0710】 These features allow users to protect themselves from potential online harm and use the internet with peace of mind. The servers also update machine learning models based on analysis results and user feedback to maintain a constant response to the latest threats. 【0711】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0712】 Step 1: 【0713】 The server receives permission requests from users to access SNS accounts and messaging apps. The input is user-defined permission settings. Based on these permissions, the server collaborates with external information processing devices to collect communication information in real time. The output is the raw, unprocessed communication data. At this stage, the server calls the SNS platform's API to retrieve the latest communication content. 【0714】 Step 2: 【0715】 The server preprocesses the collected communication data. The input is the raw communication data collected in step 1. The server formats this data and filters out unnecessary information to convert it into a format suitable for the generating AI model. The output is a dataset that has been preprocessed and is suitable for analysis. Here, specific actions are performed, such as removing extraneous spaces and special characters, and extracting target text portions. 【0716】 Step 3: 【0717】 The server inputs the pre-processed data into a generative AI model for analysis. The input is the dataset prepared in step 2. The generative AI model utilizes machine learning algorithms to detect specific threat patterns within the data. The output is information about the characteristics and threat level of the detected threats. Specifically, the model identifies similar patterns and compares them with historical database data to determine the presence or absence of a threat. 【0718】 Step 4: 【0719】 Based on the analysis results, the server identifies the threat level and prepares to notify the user. The input is the analysis results from step 3. The server generates the severity of the threat and a description of it, and creates a warning message for the user. The output is the notification message, which is sent to the terminal. Specifically, this involves generating a message such as, "This may be a scam, so do not provide personal information to the sender." 【0720】 Step 5: 【0721】 The device provides users with educational content tailored to the threat. Input consists of the warning message created in step 4 and appropriate educational content based on its content. The device displays interactive guidelines and quiz-style educational materials, providing users with opportunities to deepen their understanding. Output is educational content displayed to the user. Specifically, it displays materials illustrating relevant harassment examples and coping strategies. 【0722】 Step 6: 【0723】 The server analyzes user feedback and newly collected data to continuously update the generated AI model. Input consists of user feedback and newly collected data. The server uses this information to adjust the model parameters and improve analysis accuracy. The output is the updated machine learning model. Specifically, it recalculates the algorithm's weights based on past false positives. 【0724】 (Application Example 1) 【0725】 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". 【0726】 In online communication, it is crucial to protect users from threats such as fraud, scams, and harassment. However, real-time threat detection is difficult with conventional monitoring methods, and it relies heavily on the user's own information literacy. Therefore, there is a need for a more rapid and accurate countermeasure system. Furthermore, in addition to defending against threats, educational support is also needed to help users take safe actions themselves. 【0727】 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. 【0728】 This invention includes a server that, with the user's permission, cooperates with an external information infrastructure to collect communication information in real time; a server that preprocesses the collected communication information and analyzes threats using a generative machine learning model; and a server that proposes specific countermeasures based on the detection of fraudulent activity and fraud based on the real-time analyzed communication information. This makes it possible to immediately detect risky communications and provide appropriate alerts and instructions to the user. Furthermore, by continuously learning the latest threat information, the system can constantly evolve while providing educational content that improves the user's information literacy. 【0729】 "User permission" means obtaining formal consent from the individual being investigated when collecting or analyzing information. 【0730】 "External information infrastructure" refers to external data platforms and communication networks that are linked to acquire communication information in real time. 【0731】 "Collecting communication information in real time" means the process of acquiring information instantly and without delay from the moment the data is generated. 【0732】 "Preprocessing" refers to the process of converting collected raw data into the necessary format and structure before analysis. 【0733】 A "generative machine learning model" is an AI-based algorithm that uses historical data and feedback to analyze and identify specific patterns and threats. 【0734】 "Threat analysis" is the process of examining collected communications information to identify potential risks and malicious activities. 【0735】 "Suggesting specific countermeasures" means recommending appropriate guidelines and actions to the user in response to detected threats. 【0736】 "Latest threat intelligence" refers to the most up-to-date knowledge and data on fraudulent activities and scams, which are constantly evolving. 【0737】 "Information literacy" refers to an individual's ability to use information safely and effectively on the internet and in communication. 【0738】 "Providing educational content" means presenting learning resources and guidelines to enable users to improve their knowledge and skills on their own. 【0739】 This invention is a system that enables users to communicate securely in an online environment, and its embodiments consist of multiple components. 【0740】 The server first obtains permission from the user, then connects with an external information infrastructure to collect communication information in real time. The collected communication information is preprocessed and then input into a generative machine learning model. The generative machine learning model used here is built using TensorFlow, PyTorch, etc., and is responsible for analyzing specific threat patterns. 【0741】 Once the analysis is complete, the server will suggest specific actions to take to the user, depending on the level of the detected threat. For example, if malicious activity or fraud is detected in a message, a notification such as "This link is dangerous. Do not access it." will be sent. These specific instructions are intended to encourage the user to take prompt action. 【0742】 The device also provides users with educational content to improve their information literacy. This content includes learning resources in quiz and video formats, designed to help users learn about safe online behavior while having fun. 【0743】 Furthermore, the server continuously updates its machine learning model based on user feedback and new threat intelligence. This ensures that the system is always well-prepared to respond to the latest threats. 【0744】 For example, if a user receives a message on social media asking for their credit card information, this system will immediately detect the possibility of fraud and issue a warning. It will then send advice such as, "It is safer not to provide your personal information." 【0745】 An example of a prompt message for the AI ​​model might be a text input such as, "Is this message potentially a scam? 'Hello, we need your bank account information.'" In this way, the present invention provides an environment in which users can safely use digital platforms. 【0746】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0747】 Step 1: 【0748】 The server, with user permission, interacts with an external information infrastructure. At this stage, it collects communication information in real time using APIs from social networking services (SNS) and messaging platforms. The input requires the user's account information and API key, and the output is the collected, unprocessed communication information. 【0749】 Step 2: 【0750】 The server preprocesses the collected communication information. This includes noise reduction, data cleansing, and formatting. The input is the raw communication information obtained in step 1, and the output contains clean data suitable for analysis. Here, text data filtering and normalization are performed using Python scripts or similar tools. 【0751】 Step 3: 【0752】 The server inputs pre-processed communication data into a generating AI model for analysis. A machine learning model (e.g., one using TensorFlow or PyTorch) detects threat patterns from the data. The input is clean data, and the output generates an assessment of the threat level and type for each communication. 【0753】 Step 4: 【0754】 The server notifies the user of the threat based on the analysis results. If the analysis results are deemed high-risk, a warning message is sent to the user's device. The input is the analysis results from step 3, and the output is the specific warning content sent to the user. At this time, a prompt message is generated to form a phrase that will attract the user's attention. 【0755】 Step 5: 【0756】 The device provides users with educational content to improve their information literacy. This includes quizzes to test knowledge and training modules using simulated scenarios. The input is the system's database of educational content, and the output is appropriate training content tailored to the user's learning progress. 【0757】 Step 6: 【0758】 The server continuously updates the generated AI model based on user feedback and newly detected threat information. This process involves incorporating new data to retrain the learning model. The input is feedback data and new communication information, and the output is the updated machine learning model. Model updates are performed through periodic batch processing. 【0759】 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. 【0760】 This invention is a system that promotes safe and healthy communication on online platforms and incorporates an emotion recognition engine. This system operates via a server, terminal, and user interface. Detailed embodiments are described below. 【0761】 Data collection and emotion recognition: 【0762】 When a user grants the system access to their social media accounts, the server retrieves messages and posts in real time via an API. Simultaneously, based on the collected communication data, the server uses an emotion engine to infer the user's emotional state. This engine analyzes emotions from the text and identifies the user's emotional state. 【0763】 Data analysis and threat awareness: 【0764】 The server inputs communication data, incorporating emotion recognition, into a generative model to identify inappropriate content and threats. By taking emotional changes into account, threat detection becomes more accurate than usual. 【0765】 Notification and intervention: 【0766】 Based on information from the emotion engine, the server adjusts the content of threat notifications according to the user's psychological state. For example, if the user is stressed, the notification will be delivered in more mitigating language. Depending on the level of threat, the user is given the option to pause or block the conversation. 【0767】 User education and support: 【0768】 The device provides users with appropriate educational information. This information includes emotionally-based coping strategies and interactive content to improve digital literacy more effectively. This creates an environment where users can communicate intuitively and securely. 【0769】 Continuous learning and feedback: 【0770】 The server analyzes user feedback and sentiment data to continuously improve the accuracy of its generative models and sentiment engine. This allows it to learn new threat and sentiment patterns, further enhancing user protection. 【0771】 Specific example: 【0772】 For example, if a user feels anxious after seeing extreme comments on social media, the server's emotion engine instantly recognizes the user's emotions. If a threat is detected, the server notifies the user and displays specific steps and countermeasures on their device to help them calm down. This allows the user to continue communicating with peace of mind. 【0773】 Thus, the present invention provides a more personalized and secure online environment through real-time sentiment analysis and data analysis. 【0774】 The following describes the processing flow. 【0775】 Step 1: 【0776】 The user grants the system permission to access their social media accounts and analyze sentiment data. Based on this permission, the server uses the social media platform's API to retrieve messages and posts in real time. 【0777】 Step 2: 【0778】 The server preprocesses the collected communication data. Specifically, it removes noisy elements from the text, tokenizes it, and converts it into a parseable format. At this stage, the sentiment engine also performs sentiment analysis on the text data. 【0779】 Step 3: 【0780】 The server inputs pre-processed data into a generative model to determine messages that may contain inappropriate content or threats. It also evaluates the results of the sentiment engine's analysis to analyze the psychological impact on users in communications. 【0781】 Step 4: 【0782】 The server identifies the presence and level of threats based on the output of the generative model and sentiment analysis. The threat level is further categorized into low, medium, and high, depending on the user's emotional state. 【0783】 Step 5: 【0784】 The server sends notifications to users based on the nature and level of the threat. These notifications use language that is sensitive to the user's emotional state and explain appropriate countermeasures and recommended actions. For example, if a user is feeling anxious, the server will choose more polite and reassuring language. 【0785】 Step 6: 【0786】 The device displays educational information tailored to the user's emotions and the type of threat. This information is provided as guidelines for effective countermeasures and content aimed at improving digital literacy. Based on this information, users can avoid danger and continue to communicate effectively. 【0787】 Step 7: 【0788】 The server accumulates user feedback and sentiment data, and regularly updates its generative models and sentiment engine. This continuous learning process improves the system's threat detection accuracy and sentiment analysis capabilities, resulting in more effective protection and support. 【0789】 (Example 2) 【0790】 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". 【0791】 Online communication, while convenient, often exposes users to inappropriate content and threats. Furthermore, simplistic threat notifications that fail to consider the user's psychological state can cause additional stress. This invention aims to solve these problems through a system that utilizes sentiment analysis to achieve more accurate threat recognition and provide psychologically appropriate responses to users. 【0792】 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. 【0793】 In this invention, the server includes means for collecting communication information in real time in cooperation with an information processing infrastructure with the user's permission, means for preprocessing the collected communication information and evaluating the user's psychological state using sentiment analysis technology, and means for analyzing threats using a generative model based on the evaluation results and improving the accuracy of the threat by reflecting specific emotional changes. This enables more precise threat recognition in accordance with the user's emotional state and the provision of psychologically appropriate threat notifications and countermeasures. 【0794】 A "user" is an individual or group that interacts with a system through an interface. 【0795】 An "information processing infrastructure" is a collection of hardware and software used to collect, store, and analyze data. 【0796】 "Real-time" refers to the concept where data acquisition and processing occur almost simultaneously, and information is provided to the user immediately. 【0797】 "Communication information" refers to data such as messages and posts exchanged on online platforms. 【0798】 "Emotion analysis technology" refers to methods and algorithms for analyzing text data and identifying the emotions and sensibilities contained within it. 【0799】 "Psychological state" refers to the state of emotions and consciousness, and is the internal state of the user identified through emotion analysis. 【0800】 A "generative model" is a statistical model that uses machine learning and artificial intelligence technologies to learn patterns from data and generate new data or results. 【0801】 A "threat" refers to inappropriate content or activities that could have a negative impact on users. 【0802】 "Threat accuracy" is an indicator that refers to the precision and reliability with which a system identifies threats. 【0803】 A "threat notification" is an alert or message that communicates information about an identified threat to the user. 【0804】 This invention is a system that promotes safe and healthy communication on online platforms. This system operates by combining sentiment analysis technology and generative AI models, with servers, terminals, and users as its main components. 【0805】 The server, through user-authorized access, utilizes APIs from social networking services (SNS) and messaging services as its information processing infrastructure to collect communication information in real time. This information collection is carried out efficiently using RESTful APIs and WebSocket technology. The collected information is stored on the server as text data. 【0806】 Next, the server processes this text data using sentiment analysis technology. It uses natural language processing (NLP) libraries to evaluate the emotions contained in the text. Specifically, it identifies the user's psychological state using open-source sentiment analysis tools or proprietary algorithms. 【0807】 The user's psychological state, as revealed by the analysis, is further evaluated in detail by a generative AI model. This model learns known threat patterns and improves threat accuracy by incorporating the results of sentiment analysis. The generative model utilizes deep learning frameworks and common machine learning tools. 【0808】 Based on the user's psychological state and threat level, the server provides a flexible notification mechanism. Notifications are sent using wording that takes the user's emotional state into consideration. These notifications are displayed to the user via their device, prompting specific actions. For example, if the user is under high stress, the notification might suggest a calm response as a "step to calm down." 【0809】 The device interactively provides users with educational information and coping strategies based on sentiment analysis. This allows users to improve their digital literacy and ensure safer online communication. 【0810】 For example, if a user detects an offensive post on social media, the server immediately performs sentiment analysis and recognizes that the user is feeling stressed. Depending on the situation, the device will display advice such as, "Take a deep breath and then check the message again." 【0811】 An example of a prompt might be: "If a user discovers a post on social media that makes them feel uneasy, how can the sentiment engine identify that emotion and provide a safe notification?" 【0812】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0813】 Step 1: 【0814】 The server, based on user permission, interacts with the information processing infrastructure to collect communication information in real time. Inputs include the user's SNS account and access rights to messaging platforms. The server retrieves data via APIs and stores it in text format. At this stage, raw message data is obtained as output. 【0815】 Step 2: 【0816】 The server preprocesses the acquired communication information using an emotion analysis engine. The input is the text data collected in step 1. The server uses natural language processing techniques to identify emotions from the text and classify them into emotional states such as joy, sadness, anger, and anxiety. The output is the analyzed emotion data. 【0817】 Step 3: 【0818】 The server performs threat analysis using a generative AI model based on the analyzed sentiment data. The input is the sentiment data obtained in step 2. The server uses the trained generative model to evaluate potential threats in the text and improves the accuracy of the threat assessment by incorporating the sentiment analysis results. The output is the threat assessment result. 【0819】 Step 4: 【0820】 The server sends a threat notification to the user based on the threat assessment results and sentiment data. The input is the threat assessment results and sentiment state from step 3. The server takes the user's psychological state into consideration and adjusts the notification method and content. The output is the adjusted notification message sent to the user's terminal. 【0821】 Step 5: 【0822】 The device displays the received notification message to the user and prompts them to take specific action. The input is the notification message sent in step 4. The device displays suggestions and actions in language that reduces the user's psychological burden. The output is a visual and textual notification to the user. 【0823】 Step 6: 【0824】 The server receives user feedback and threat assessment data to continuously update its generative model and sentiment analysis engine. Input consists of user feedback and threat assessment data. The server analyzes this data to improve the accuracy of the AI ​​model and identify new threat patterns. The output is an updated model and analysis engine. 【0825】 (Application Example 2) 【0826】 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". 【0827】 In online communication, users may experience a lack of detection and response to threats or inappropriate information that could potentially harm them. Furthermore, the lack of appropriate intervention and support tailored to their psychological state can negatively impact users' mental health. In addition, a lack of digital literacy makes it difficult for users to independently identify and address threats. To address these issues, there is a need for systems that promote safe and healthy communication utilizing sentiment recognition technology. 【0828】 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. 【0829】 In this invention, the server includes means for inferring the user's psychological state using an emotion analysis engine and providing appropriate information, means for collecting information in real time in cooperation with an information processing device with the user's permission, and means for preprocessing the collected information and analyzing threats using a generated mathematical model. This enables the appropriate provision of educational information tailored to the user's psychological state, as well as more accurate threat detection and rapid response. 【0830】 An "information processing device" is a device that processes various types of data based on user permission and acquires and analyzes information in cooperation with an external data platform. 【0831】 A "generated mathematical model" is a model formed through data analysis and used to evaluate and detect online threats. 【0832】 An "emotion analysis engine" is an engine that analyzes a user's communication and uses the information obtained from it to infer their psychological state. 【0833】 "Threat level" is a measure that indicates the degree of risk to users, as identified as a result of analysis by an information processing device. 【0834】 "Educational information" refers to information that provides users with the knowledge and skills necessary to improve their digital literacy and maintain a safe online environment. 【0835】 The system implementing this invention features a complex mechanism combining sentiment analysis technology and a generated mathematical model to improve the security of communication on online platforms. The server interacts in real time with an external data platform authorized by the user to collect information. This information is preprocessed using an information processing device, and threats are analyzed using the generated mathematical model. Furthermore, a sentiment analysis engine is used to infer the user's psychological state and provide appropriate information. 【0836】 Based on these analysis results, the server identifies the threat level and notifies the user in an appropriate manner. Users are presented with options to temporarily suspend or block communications as countermeasures appropriate to the threat level. Furthermore, educational information is provided to improve users' digital literacy, helping them to communicate securely. 【0837】 As a concrete example, if a user encounters inappropriate comments on social media, the server immediately detects the user's anxiety through sentiment analysis and, based on the results, notifies them with a "guide to calm down." At the same time, it presents appropriate educational information according to the user's emotional state, enabling them to continue safer and healthier online interactions. 【0838】 An example of a prompt message generated using an AI model would be: "Generate a notification using gentle language to alleviate anxiety, taking into account the user's psychological state. For example, what words should be used if the user is feeling anxious?" This makes notifications to users more personalized and provides a sense of security. 【0839】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0840】 Step 1: 【0841】 The server, with user permission, interacts with an external data platform to collect data in real time. The input is communication data from the platform, and the output is data converted into a processable format. The server extracts the data using an API and formats it for easier analysis. 【0842】 Step 2: 【0843】 The server preprocesses the collected communication data and analyzes threats using the generated mathematical model. The input is formatted communication data, and the output is the analysis results, including a threat assessment. This process uses natural language processing techniques to analyze text and identify potential threats. 【0844】 Step 3: 【0845】 The server uses an emotion analysis engine to infer the user's psychological state. The input consists of communication content with the user and its metadata, and the output is the inferred emotional state. Emotion analysis uses machine learning algorithms to extract emotional characteristics from text. 【0846】 Step 4: 【0847】 The server identifies the threat level based on the analysis results and notifies the user. The input is the result of threat analysis and sentiment inference, and the output is a customized notification message. The server utilizes prompts to generate the most appropriate notification content for the user. 【0848】 Step 5: 【0849】 The server provides the user with the option to temporarily suspend or block communications. The input is the identified threat level, and the output is the control option the user can select. The user receives a notification and can take appropriate action. 【0850】 Step 6: 【0851】 The device provides users with educational information to improve their digital literacy. Input is the user's psychological state and threat level, and output is the corresponding educational content. The educational content is interactive instructional material designed using a generative AI model. 【0852】 Step 7: 【0853】 The server continuously updates the mathematical model generated based on user feedback, improving its accuracy. Input is analysis and user feedback data, and output is the updated model. This enhances the system's ability to respond to new threat patterns. 【0854】 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. 【0855】 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. 【0856】 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. 【0857】 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. 【0858】 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. 【0859】 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. 【0860】 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. 【0861】 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. 【0862】 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." 【0863】 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. 【0864】 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. 【0865】 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. 【0866】 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. 【0867】 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. 【0868】 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. 【0869】 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. 【0870】 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. 【0871】 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. 【0872】 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. 【0873】 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. 【0874】 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. 【0875】 The following is further disclosed regarding the embodiments described above. 【0876】 (Claim 1) 【0877】 With the user's permission, a means of collecting communication data in real time by linking with an external data platform, 【0878】 A means of preprocessing collected communication data and analyzing threats using a generative model, 【0879】 Based on the analysis results, a means to identify the level of threat and notify the user, 【0880】 Means to provide options to temporarily suspend or block communications depending on the level of threat, 【0881】 A means of providing users with educational information to improve their digital literacy, 【0882】 A system that includes this. 【0883】 (Claim 2) 【0884】 The system according to claim 1, which continuously updates the generative model based on analysis results and user feedback to improve the accuracy of threat detection. 【0885】 (Claim 3) 【0886】 The system according to claim 1, which stores information on detected threats and forms a database for identifying new threat patterns. 【0887】 "Example 1" 【0888】 (Claim 1) 【0889】 A means of collecting communication information in real time by cooperating with an external information processing device with the user's permission, 【0890】 A method for preprocessing collected communication information and analyzing threats using machine learning models, 【0891】 Based on the analysis results, a means to identify the level of threat and notify users, 【0892】 Means to provide options to temporarily suspend or block communications depending on the level of threat, 【0893】 A means of providing users with educational data to improve their information technology literacy, 【0894】 A means of generating educational guidelines regarding inappropriate communication conditions using the analyzed information, 【0895】 A system that includes this. 【0896】 (Claim 2) 【0897】 The system according to claim 1, which continuously updates the machine learning model based on analysis results and user feedback to improve the accuracy of threat detection. 【0898】 (Claim 3) 【0899】 The system according to claim 1, which stores information on detected threats and forms an information repository for identifying new threat patterns. 【0900】 "Application Example 1" 【0901】 (Claim 1) 【0902】 A means of collecting communication information in real time by linking with an external information infrastructure with the user's permission, 【0903】 A means of preprocessing collected communication information and analyzing threats using a generative machine learning model, 【0904】 Based on the analysis results, a means to identify the level of threat and notify the user, 【0905】 Means to provide options to temporarily suspend or block communications depending on the level of threat, 【0906】 A means of providing users with educational information to improve their information literacy, 【0907】 A means of proposing specific countermeasures based on the detection of fraudulent activity and fraud in real-time analyzed communication information, 【0908】 A system that includes this. 【0909】 (Claim 2) 【0910】 The system according to claim 1, which continuously updates the generated machine learning model based on analysis results and user feedback to improve the accuracy of threat detection, and periodically downloads the latest threat information. 【0911】 (Claim 3) 【0912】 The system according to claim 1, which stores information on detected threats, forms a data structure for identifying new threat patterns, and provides users with periodic educational modules for safe operation. 【0913】 "Example 2 of combining an emotion engine" 【0914】 (Claim 1) 【0915】 A means of collecting communication information in real time in cooperation with an information processing infrastructure, with the user's permission, 【0916】 A means for preprocessing collected communication information and evaluating psychological state using emotion analysis technology, 【0917】 Based on the evaluation results, a generative model is used to analyze the threat, and a means to improve the accuracy of the threat by reflecting specific emotional changes, 【0918】 A means to identify the level of threat based on analysis results and emotional changes, and to adjust the expression used when notifying the user according to their emotional state, 【0919】 A means of providing users with the option to temporarily suspend or block communications depending on the level of threat, 【0920】 A means of improving digital literacy by providing users with educational information and coping strategies based on sentiment analysis, 【0921】 A system that includes this. 【0922】 (Claim 2) 【0923】 The system according to claim 1, which continuously updates the generative model and sentiment analysis technology based on evaluation results and user feedback to improve the accuracy of threat detection. 【0924】 (Claim 3) 【0925】 The system according to claim 1, which stores information on detected threats and emotional states and forms a data record for identifying new threat patterns. 【0926】 "Application example 2 when combining with an emotional engine" 【0927】 (Claim 1) 【0928】 A means of collecting information in real time by cooperating with an information processing device with the user's permission, 【0929】 A means of preprocessing collected information and analyzing threats using the generated mathematical model, 【0930】 Based on the analysis results, a means of identifying the threat level and notifying humans, 【0931】 Means to provide options to temporarily suspend or block communications depending on the level of threat, 【0932】 A means of providing users with educational resources to improve their information literacy, 【0933】 A means of using an emotion analysis engine to infer the user's psychological state and provide appropriate information, 【0934】 A means of selecting and providing educational information that is appropriate to the user's psychological state, 【0935】 A lineage that includes this. 【0936】 (Claim 2) 【0937】 The system according to claim 1, which continuously updates the generated mathematical model based on analysis results and user feedback to improve the accuracy of threat detection. 【0938】 (Claim 3) 【0939】 The system according to claim 1, which accumulates data on detected threats and forms an information set for identifying new threat patterns. [Explanation of symbols] 【0940】 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] With the user's permission, a means of collecting communication data in real time by linking with an external data platform, A means of preprocessing collected communication data and analyzing threats using a generative model, Based on the analysis results, a means to identify the level of threat and notify the user, Means to provide options to temporarily suspend or block communications depending on the level of threat, A means of providing users with educational information to improve their digital literacy, A system that includes this. [Claim 2] The system according to claim 1, which continuously updates the generative model based on analysis results and user feedback to improve the accuracy of threat detection. [Claim 3] The system according to claim 1, which stores information on detected threats and forms a database for identifying new threat patterns.

Images