system

Abstract

We provide the system. [Solution] A means of obtaining communication data from the user's terminal, A means of detecting fraudulent activity by analyzing acquired communication data, A means of generating warnings and notifying parents based on detected misconduct, A means of correcting the analysis method using feedback data, A system that includes means for presenting analysis results and recommended actions.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, when minors use the Internet and SNS, problems such as slander, leakage of personal information, and exposure to inappropriate content have been increasing. Such problems often exceed the monitoring ability of parents, and real-time monitoring and response are required. In addition, there is also a concern about privacy infringement due to false detection and excessive monitoring. A method for effectively solving these problems is needed.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for acquiring communication data from a user terminal, means for analyzing the acquired data to detect inappropriate behavior, means for generating warnings based on the detection results and notifying parents, means for correcting the analysis method using feedback data, and means for presenting the analysis results and recommended actions. This system makes it possible to effectively monitor the online activities of minors, quickly detect and respond to abnormal or dangerous behaviors, and support the monitoring capabilities of parents. Furthermore, the accuracy of the monitoring system can be improved through the feedback function.

[0006] A "user terminal" is an electronic device used to connect to the internet or social networking services (SNS) and communicate, and is operated by the user.

[0007] "Communication data" refers to information sent and received from a user's terminal, including messages, access history, and connection destination information.

[0008] "Fraudulent activity" refers to unusual behavior that deviates from normal usage patterns or actions that pose security risks.

[0009] A "guardian" is an adult who has the responsibility to protect the safety of a minor child and is in a position to monitor and guide them.

[0010] A "warning" is a notification generated to alert parents when misconduct or risky behavior is detected.

[0011] "Feedback data" refers to information collected from parents' responses and evaluations of warnings generated by the system, and is used to improve the system's accuracy.

[0012] "Analysis results" refer to the judgments regarding the presence or absence of fraudulent activity or risks, obtained through the analysis of communication data.

[0013] "Recommended actions" are behavioral guidelines that propose measures and guidance methods that parents should take based on the analysis results. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a 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.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The system of this invention aims to monitor the online activities of minors, identify risky behaviors, and notify parents. Below, we generate a program for this system and describe its processing in natural language.

[0036] Data collection and transmission

[0037] First, the device monitors communication data generated through the user's activities in real time. This data includes URLs of visited websites, metadata of messages on social media, and usage time. The collected data is encrypted to protect privacy and then sent to the server.

[0038] Data analysis and anomaly detection

[0039] The server performs real-time analysis based on the received communication data. Using machine learning models, abnormal behavior that deviates from normal usage patterns is detected. These models are built on historical data and expert advice. For example, if a user frequently accesses dangerous websites late at night, the server recognizes this behavior as a risk.

[0040] Alert generation and notification

[0041] When abnormal behavior is detected, the server immediately notifies parents. The alert includes specific details of the abnormal behavior, the time it occurred, and recommended actions to take. For example, it may include specific wording such as, "Access to inappropriate content on a specific social media platform has been detected."

[0042] Feedback and system improvements

[0043] Users can provide guidance to their children based on the alerts they receive, and can also provide feedback to the system. This feedback may include suggestions regarding the accuracy of the alerts and new behaviors that should be detected. The server collects this feedback and uses it to improve the accuracy of the analysis model.

[0044] Thus, the system of the present invention can provide a safe environment for minors to use the internet and reduce the burden on parents. A specific example of use is when a device detects access to inappropriate content late on a Sunday night, and an immediate warning is sent to the parent via the server. In this case, the parent can take appropriate action quickly.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The device monitors the user's online activity. This is done by collecting communication data in real time from the websites the user visits and the social networking applications they use. The collected data is processed using strong encryption technology to protect privacy.

[0048] Step 2:

[0049] The device transmits the collected encrypted data to the server via the internet. This data transmission is performed periodically or immediately in the event of suspected abnormal behavior.

[0050] Step 3:

[0051] The server decompresses the received data and decrypts it back to its original content. After saving the decrypted data to the database, it quickly starts the analysis process.

[0052] Step 4:

[0053] The server uses machine learning models to analyze communication data. Here, with the aim of detecting abnormal behavior, it compares the data against normal usage patterns and identifies actions that exceed a threshold. Detectable abnormal behaviors include late-night access and the detection of aggressive message content.

[0054] Step 5:

[0055] When abnormal behavior is detected, the server immediately generates an alert for the parent or guardian. The alert includes a detailed description of the abnormal behavior, along with recommended actions to take.

[0056] Step 6:

[0057] The server sends generated alerts to users in real time. Users can receive alerts via their smartphones or PCs.

[0058] Step 7:

[0059] Based on the alerts they receive, users can monitor their child's online activities and take necessary guidance or action. They can also provide feedback on the accuracy of the alerts.

[0060] Step 8:

[0061] The server analyzes user feedback and uses it to improve the overall monitoring accuracy of the system and the machine learning models. This improves the system's accuracy and enables more accurate anomaly detection.

[0062] (Example 1)

[0063] 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."

[0064] A challenge exists in that parents lack the means to quickly and accurately identify dangerous behaviors in minors' online activities and take appropriate action. Furthermore, existing monitoring systems suffer from frequent false positives and inappropriate alerts, placing a heavy burden on users.

[0065] 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.

[0066] In this invention, the server includes means for acquiring information about user operations, means for analyzing the acquired information using a generative AI model to detect abnormal behavior, and means for generating warnings based on the detection of abnormal behavior and providing them to guardians. This makes it possible to detect inappropriate online activities of minors with high accuracy and to quickly notify guardians.

[0067] "Information about user actions" refers to data related to the user's online activities, specifically including the addresses of websites accessed, connection times and durations, and applications used.

[0068] A "generative AI model" is a digital model built on machine learning technology that learns patterns from past data and analyzes newly acquired data to detect abnormal behavior.

[0069] "Abnormal behavior" refers to online activities that are judged to deviate significantly from normal usage patterns, including viewing inappropriate content and using the internet outside of normal usage hours.

[0070] "Generating and providing warnings to parents" refers to a series of processes that create notifications, including explanations of the content and location, based on detected abnormal behavior, and promptly send them to parents' communication devices.

[0071] "Evaluation information" refers to user opinions and evaluations regarding the accuracy and usefulness of the system, and analyzing this information contributes to improving the system's performance.

[0072] This invention provides a system for appropriately monitoring the online activities of minors, identifying risks, and notifying parents. This system is based on a terminal used by the user and a server that processes the data.

[0073] The device acquires information about underage users' online activities in real time. This information includes the addresses of visited web pages, metadata of messages on social networking services (SNS), and application usage. The device securely transmits this information to the server using AES-256 encryption technology. The HTTPS protocol is used to ensure security during transmission.

[0074] The server decrypts the received encrypted information and analyzes it using a generative AI model. This model is designed to detect abnormal behavior that deviates from normal usage patterns and utilizes algorithms learned from historical data. When abnormal behavior is detected, the server generates a warning based on it and provides it to the parent or guardian. The warning includes the specific nature and time of the abnormal behavior and recommended actions, and is sent via email or a dedicated app notification.

[0075] Parents, as users, can provide guidance to minors based on the warnings they receive and, if necessary, return evaluation information to the system. This evaluation information is collected to improve the system's performance and enable more accurate analysis.

[0076] As a concrete example, imagine a scenario where, one Sunday night, a device detects access to inappropriate content, and the server immediately sends a warning to the parent. In this case, the parent can take appropriate action quickly. This system makes it possible to more effectively protect the safety of minors.

[0077] An example of a prompt is as follows: "Please describe in detail the content of the warning message that the server sends to parents when the system detects access to an inappropriate website late at night."

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The device acquires data about the user's online activity. Inputs include web page addresses, social media metadata, and application usage. This data is monitored and collected in real time. By collecting data incrementally, the device can continuously monitor user activity and gain a comprehensive overview. The collected data is encrypted using AES-256 encryption technology. The output is an encrypted, secure data packet, ready to be sent to the server.

[0081] Step 2:

[0082] The server receives encrypted data sent from the terminal. The input is encrypted data packets, which are then decrypted to reconstruct the original data. The server decrypts the data using a secure decryption protocol and restores the user's behavior history. This process allows the server to understand the details of the actual user behavior. The decrypted output is then analyzed by a generative AI model.

[0083] Step 3:

[0084] The server analyzes the decoded user behavior data using a generating AI model. The input is the decoded user behavior data, and the model detects abnormal behavior by comparing it with pre-trained normal behavior patterns. Specifically, examples include accessing inappropriate websites late at night. The machine learning algorithm identifies this as abnormal. The output is a list of detected abnormal behaviors, which are used in the next step.

[0085] Step 4:

[0086] The server generates alerts based on detected abnormal behavior. The input is a list of abnormal behaviors, each accompanied by a detailed description and recommended countermeasures. The alerts include the specific inappropriate behavior and the time it occurred. The generated alerts are formatted as information to be provided to parents. The output is an alert message formatted for sending to parents.

[0087] Step 5:

[0088] The user (parent / guardian) receives warning messages sent from the server. The input is a warning of specific abnormal behavior, which is used to provide appropriate guidance to the child. In addition, evaluation information regarding the accuracy of the warnings and the system's usefulness can be returned to the system. This feedback information contributes to improving the system's accuracy. The output is user feedback information used to improve the system's performance.

[0089] (Application Example 1)

[0090] 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."

[0091] The challenge lies in efficiently and quickly identifying risky behaviors in minors' online activities and notifying parents at the appropriate time to ensure the safety of internet use. Furthermore, it is necessary to enable parents to monitor their children's internet activities without unnecessary effort.

[0092] 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.

[0093] In this invention, the server includes means for collecting communication information from user devices, means for analyzing the collected communication information and detecting risky behavior, and means for automatically issuing risky behavior notifications on mobile information terminals such as smartphones. This makes it possible to automatically and in real time detect security risks in the online activities of minors and to quickly notify parents.

[0094] A "user device" is a terminal device that has the function of providing communication information in real time.

[0095] "Communication information" refers to data related to online operations, including information such as the URLs of visited websites and metadata for social media.

[0096] "Risk behavior" refers to online actions that pose a potential threat to the safety of minors.

[0097] A "guardian" is a person who is responsible for supervising a minor, or who fulfills that role.

[0098] "Feedback information" refers to information provided by parents based on warnings issued by the system, and is used to improve the system.

[0099] An "analysis method" refers to an algorithm or method used to analyze communication information and detect unusual behavior.

[0100] "Encryption" is the process of transforming data to enhance security and protect communication information from unauthorized use.

[0101] A "portable information terminal" refers to a portable information processing device, such as a smartphone, that has the function of providing notifications to the user.

[0102] "Real-time" refers to processing data and providing information at a speed that is almost identical to real-world time.

[0103] In the system that implements this application, a terminal device collects communication information in real time and sends encrypted data to a server. The server decrypts the received encrypted data and analyzes it using a generative AI model. This determines whether or not risky behavior has occurred, and if a risk is detected, a notification is immediately sent to the parent or guardian.

[0104] The system uses mobile devices such as smartphones as hardware, and programming languages ​​such as Python as software. Scripts are used to collect data, including browser history and SNS usage metadata, and the Fernet library is used for encryption. On the server side, machine learning frameworks such as TENSORFLOW® and PyTorch are used for anomaly detection.

[0105] For example, if a minor attempts to access an unauthorized website late at night, this activity could be immediately detected, and the parent or guardian could receive a notification via their smartphone. This notification would include a specific message such as, "An inappropriate website was accessed late at night. Please take action."

[0106] An example of a prompt message provided to the generating AI model would be: "Create what alert message Family Security Watch should send to parents when a minor accesses unauthorized content. Include details about the specific times and situations in which warnings should be issued."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The device monitors the user's online activity in real time. Inputs include URLs of visited websites and social media metadata. This data is collected and encrypted using an encryption library. The output is encrypted data in a secure state.

[0110] Step 2:

[0111] The terminal sends encrypted data to the server. The input is encrypted communication information, and the output is the data received by the server, in a state where it has been securely transferred to the server.

[0112] Step 3:

[0113] The server decrypts the received encrypted data. The input is encrypted data, and by using the encryption key to decrypt the data, the server obtains the original decrypted communication information as output.

[0114] Step 4:

[0115] The server analyzes the decoded data using a generative AI model. The input is decoded communication information, which is then compared to normal usage patterns to detect abnormal behavior. The output, if any risky behavior is detected, is the corresponding behavioral data.

[0116] Step 5:

[0117] The server sends a notification to the parent or guardian when risky behavior is detected. The input is data on the risky behavior, and the output is an alert message sent to the parent or guardian's mobile device as a notification.

[0118] Step 6:

[0119] The user (parent / guardian) takes appropriate action regarding their child based on the notification they receive. They also send feedback back to the server. The input includes information about the notified risk behavior and the parent / guardian's response, and the output is feedback information sent to the server.

[0120] Step 7:

[0121] The server analyzes user feedback and uses it to improve its analysis methods. User feedback is used as input, and by retraining the generated AI model with this feedback, it updates the anomaly detection model to produce a more accurate output.

[0122] 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.

[0123] This invention combines a system for monitoring the online activities of minors with an emotion engine that recognizes user emotions. This allows for evaluation of how online behavior relates to user emotions, enabling more advanced monitoring and alerts.

[0124] Data collection and emotion recognition

[0125] First, the device collects data related to the user's emotions along with their online activity. This data includes the content of text messages, typing speed, and tone of voice used, and is used to estimate the user's emotional state.

[0126] The server analyzes the received data and uses an emotion engine to determine the user's emotional state. The emotion engine is built using machine learning techniques and can identify emotions such as positive, negative, and neutral. For example, if a user frequently uses terms that express dissatisfaction or anger, the emotion engine will detect a negative emotion.

[0127] Anomaly detection and alert generation

[0128] The server not only detects abnormal behavior in normal communication data, but also incorporates emotional information determined by the emotion engine into its analysis. In particular, if negative emotions increase and dangerous behavior is detected at the same time, the risk score is raised. As a result, if the existing threshold is exceeded, a warning is generated.

[0129] The generated warnings will notify parents along with the emotional state of the user. For example, if an aggressive message is being sent while the user is expressing anxiety or anger, the warning will include an explanation of the emotional state along with a cautionary message.

[0130] Feedback and system optimization

[0131] Users can review the warning information they receive and, if necessary, take appropriate action such as providing guidance or imposing restrictions. They can also provide feedback on their evaluation of the emotion detection results and their experience using the system. The server analyzes this feedback and uses it to improve the accuracy of the emotion engine's recognition and the overall system performance.

[0132] As a concrete example, if a device detects that a user's social media posts suddenly become aggressive, and the emotion engine simultaneously detects strong negative emotions, the server will notify the parent or guardian, prompting them to take immediate action. In this way, the present invention is a system that, by combining emotion analysis, enables a deeper understanding of user activity and allows for appropriate support and monitoring.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The device collects communication data and sentiment-related data related to the user's online activities. Sentiment data includes metrics such as the content of text messages, voice tone, and typing speed. This data is encrypted to protect personal information.

[0136] Step 2:

[0137] The device transmits encrypted communication data and emotional data to a server via the internet. This communication occurs in real time or periodically.

[0138] Step 3:

[0139] The server decodes the received data and analyzes the user's emotional state using an emotion engine. The emotion engine uses machine learning algorithms to determine whether the emotion is positive, negative, or neutral.

[0140] Step 4:

[0141] The server applies a machine learning model to analyze the decrypted communication data and detect abnormal behavior. This model identifies anomalies that exceed a threshold by comparing them against known malicious behavior patterns.

[0142] Step 5:

[0143] The server integrates the results of the emotion engine analysis and the abnormal behavior analysis to perform a comprehensive risk assessment. In particular, if negative emotions and abnormal behavior are detected simultaneously, the risk score is increased, indicating a high-priority warning.

[0144] Step 6:

[0145] Based on the risk assessment, the server generates a detailed alert. The alert includes the user's emotional state, the nature of the misconduct, and recommended countermeasures.

[0146] Step 7:

[0147] The server sends generated warnings to users in real time. Users can receive the warnings and check the situation via their smartphones or PCs.

[0148] Step 8:

[0149] Users take prompt action based on the warning message and provide feedback to the server. This feedback is used to improve the system's accuracy and enhance the sentiment engine.

[0150] In this way, the system, which incorporates an emotion engine, can achieve advanced monitoring based on the user's emotional state and provide more appropriate warnings and countermeasures.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] The increasing prevalence of dangerous behaviors and inappropriate emotional states in minors' online activities highlights the growing need for parents and administrators to properly monitor and address these issues promptly. While traditional systems have focused on behavioral monitoring, there is a growing demand for more sophisticated risk assessments that take into account users' emotional states.

[0154] 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.

[0155] In this invention, the server includes means for collecting information from user devices, means for analyzing the collected information and determining the emotional state using machine learning techniques, and means for generating a warning based on the determined emotional state and the detection results of abnormal behavior, and notifying the administrator. This makes it possible to comprehensively monitor both user activity and emotional state and provide the administrator with appropriate warnings before dangerous behavior occurs.

[0156] "User equipment" refers to all electronic devices used by users to conduct online activities, and includes terminals that enable data collection.

[0157] "Collecting information" refers to the act of gathering data about user activity, such as text, typing speed, and tone of voice, from the user's device.

[0158] "Machine learning technology" refers to techniques that enable computers to process large amounts of data and automatically learn patterns and rules.

[0159] "Emotional state" refers to information that represents psychological states such as joy, anger, and sadness, which is analyzed from the user's text data.

[0160] A "server" is a computer system used to process and analyze information on a network, and is a device that performs data analysis and notification management.

[0161] "Generating warnings and notifying administrators" refers to the process of creating an alarm when an anomaly is detected and communicating that information to the administrator.

[0162] This invention is a system for monitoring the online activities of minors and analyzing the emotional state of users. The system primarily functions through data exchange and analysis between terminals and servers.

[0163] The terminal is an electronic device used by the user, and it collects information generated through communication applications and social networking services (SNS). Specifically, it collects data such as the content of text messages, typing speed, and the tone of the words used. The terminal is responsible for monitoring this information in real time and transmitting the data to the server.

[0164] The server receives information sent from the terminal and analyzes the collected data. This analysis uses a machine learning tool called an emotion engine. This emotion engine analyzes the user's text data and classifies their emotional state as positive, negative, or neutral. For example, if a user frequently uses words expressing "anger" or "sadness," the engine can determine that this is a negative emotion.

[0165] The server detects deviations from the user's normal behavior patterns and generates warnings as needed. These warnings are sent to administrators (such as parents) and include detailed analysis of the user's emotional state, enabling administrators to address problems early.

[0166] The system can also improve analysis accuracy through a feedback loop. The sentiment engine and anomaly detection algorithms are continuously improved by users and administrators providing feedback on the accuracy of the warnings.

[0167] As a concrete example, if a user sends a message containing inappropriate content during a social networking exchange, and the sentiment engine detects an increase in negative emotions, the server immediately generates a warning and notifies the administrator. In this way, the system functions to keep minors' online activities safe.

[0168] Examples of input prompts for a generated AI model include: "Explain how you monitor minors' online activities and how the emotion engine evaluates their emotional state. Also, include specific use cases." These prompts serve as a tool to facilitate understanding of the system's implementation.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The device collects information through the user's online activities. Input includes text messages sent and received via social networking services and chat applications, typing speed, and tone of voice used. This data is collected in real time, compiled into communication packets, and prepared for transmission to the server.

[0172] Step 2:

[0173] The server receives data packets from the terminal. The input includes communication data sent from the terminal. The server prepares this data for analysis and supplies it to the emotion engine. During this process, data format conversion and preprocessing (e.g., string normalization) are performed.

[0174] Step 3:

[0175] The emotion engine on the server receives text data to be analyzed as input. The emotion engine uses machine learning algorithms to analyze the emotional state of the text. Specifically, the text is processed through a natural language processing module to calculate emotional scores such as positive, negative, and neutral. This output is generated as an emotional state report.

[0176] Step 4:

[0177] The server detects abnormal behavior based on the output of the emotion engine. Inputs include an emotional state report and a database of normal behavioral patterns for comparison. The server uses this to assess whether the user's current emotional state and behavior deviate from the norm. If an abnormality is detected, a risk score is calculated, triggering a warning.

[0178] Step 5:

[0179] The server generates an alert based on the generated risk score and notifies the administrator. The input includes the results of abnormal behavior detection and the risk score. The alert message includes a diagnosis of the emotional state and recommended administrator actions. This alert is sent to the administrator's terminal.

[0180] Step 6:

[0181] The user receives warning notifications from the server and provides feedback as needed. As input, the user receives warning messages and analysis results. Through feedback, the user sends information to the server regarding the effectiveness of the warnings and the accuracy of the analysis. This output is used to improve the server's analysis methods.

[0182] (Application Example 2)

[0183] 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".

[0184] There is a need to effectively monitor the misconduct and emotional state of minors in online environments and to warn parents at the appropriate time in order to protect their safety. However, conventional systems have the challenge of being unable to adequately recognize emotional states and making it difficult to monitor emotional changes in conjunction with behavior.

[0185] 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.

[0186] In this invention, the server includes means for acquiring communication data and emotion-related information from a user terminal, means for analyzing the acquired communication data and emotion information to detect misconduct and emotional states, and means for generating warnings based on the detected misconduct and emotional states and notifying parents. This makes it possible to detect misconduct and emotional changes in minors' online activities in real time and warn parents at an appropriate time.

[0187] A "user terminal" is an information processing device used by an individual to conduct online activities, and is capable of sending and receiving data.

[0188] "Communication data" refers to information sent and received via a user's terminal, including messages and internet browsing history.

[0189] "Emotion-related information" refers to data necessary to estimate the user's emotional state, including typing speed and tone of voice used.

[0190] "Misconduct" refers to unauthorized or unsafe actions, including inappropriate remarks or behavior online.

[0191] "Emotional state" refers to the tendencies of an individual's inner emotions, and is classified as positive, negative, or neutral.

[0192] A "warning" is a notification generated when misconduct or negative emotional states are detected, and it includes content that prompts parents to take notice.

[0193] "Feedback data" refers to information provided by users or guardians, including analysis results and feedback on the system.

[0194] "Analysis methods" refer to methods for evaluating fraudulent behavior and emotional states based on acquired data, and include algorithms and machine learning techniques.

[0195] An "emotion recognition method" is a technique for analyzing and recognizing a user's emotional state, and includes processes involving data analysis and machine learning.

[0196] An "information processing device" is a device used to collect, process, and output data, and includes computers used in homes.

[0197] This invention is a system for monitoring the online activities of minors and evaluating their emotional state. The server acquires communication data and emotion-related information from the user's terminal. This includes the user's online activities, message sending history, typing speed, and tone of voice used.

[0198] The device collects this data in real time and sends it to the server. The server analyzes the data and uses an emotion engine to determine the user's emotional state. The emotion engine, which utilizes machine learning technology, identifies emotions such as positive, negative, and neutral, and generates a corresponding warning if negative emotions are particularly heightened.

[0199] For example, if a user frequently makes aggressive remarks while playing online games and a negative emotional state is detected, the server will quickly generate a warning and send a verbal notification to the parent or guardian via a home information processing device. This system runs on a small computer such as a Raspberry Pi using a Python program.

[0200] Furthermore, feedback data provided by users and guardians is used to improve the accuracy of emotion recognition and to refine the analysis methods. This process continuously optimizes the system's performance, resulting in more accurate monitoring and notifications.

[0201] Further improvements can be made using a generative AI model through prompts such as: "Please explain how the robot can detect emotions from a minor's online activities, what kind of notification it will send if a negative situation is detected, and how it will warn parents."

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The device collects communication data and sentiment-related information from the user's online activity. Specifically, input includes messages sent by the user, text communications with each other, typing speed, and tone of voice used. This input data is temporarily stored on the device and then sent to the server for subsequent processing.

[0205] Step 2:

[0206] The server receives data sent from the terminal and begins analysis. Using an emotion engine, it identifies the user's emotional state from the input communication data. Emotion labels such as positive, negative, and neutral are generated as output. Specifically, machine learning techniques are used to extract features and perform pattern matching and classification.

[0207] Step 3:

[0208] Based on the analysis results, the server evaluates whether the user's behavior is fraudulent and whether their emotional state is negative. In particular, if negative emotions and fraudulent behavior are detected simultaneously, a risk score is calculated, and a warning is generated if it exceeds a threshold. Thresholding and scoring models are applied in this step.

[0209] Step 4:

[0210] The generated alerts are sent from the server to the home information processing unit. The specific alert message includes a summary of the detected emotional state or behavior, and, if necessary, recommended actions. The information processing unit verbally notifies the parent or guardian of this message to help them take prompt action.

[0211] Step 5:

[0212] Feedback from users and guardians is sent to the server. The server uses this feedback to continuously improve its analysis methods and sentiment recognition methods. Specifically, feedback information is received as input, and through algorithm adjustments and model retraining, it leads to improved system accuracy as output.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] The system of this invention aims to monitor the online activities of minors, identify risky behaviors, and notify parents. Below, we generate a program for this system and describe its processing in natural language.

[0230] Data collection and transmission

[0231] First, the device monitors communication data generated through the user's activities in real time. This data includes URLs of visited websites, metadata of messages on social media, and usage time. The collected data is encrypted to protect privacy and then sent to the server.

[0232] Data analysis and anomaly detection

[0233] The server performs real-time analysis based on the received communication data. Using machine learning models, abnormal behavior that deviates from normal usage patterns is detected. These models are built on historical data and expert advice. For example, if a user frequently accesses dangerous websites late at night, the server recognizes this behavior as a risk.

[0234] Alert generation and notification

[0235] When abnormal behavior is detected, the server immediately notifies parents. The alert includes specific details of the abnormal behavior, the time it occurred, and recommended actions to take. For example, it may include specific wording such as, "Access to inappropriate content on a specific social media platform has been detected."

[0236] Feedback and system improvements

[0237] Users can provide guidance to their children based on the alerts they receive, and can also provide feedback to the system. This feedback may include suggestions regarding the accuracy of the alerts and new behaviors that should be detected. The server collects this feedback and uses it to improve the accuracy of the analysis model.

[0238] Thus, the system of the present invention can provide a safe environment for minors to use the internet and reduce the burden on parents. A specific example of use is when a device detects access to inappropriate content late on a Sunday night, and an immediate warning is sent to the parent via the server. In this case, the parent can take appropriate action quickly.

[0239] The following describes the processing flow.

[0240] Step 1:

[0241] The device monitors the user's online activity. This is done by collecting communication data in real time from the websites the user visits and the social networking applications they use. The collected data is processed using strong encryption technology to protect privacy.

[0242] Step 2:

[0243] The device transmits the collected encrypted data to the server via the internet. This data transmission is performed periodically or immediately in the event of suspected abnormal behavior.

[0244] Step 3:

[0245] The server decompresses the received data and decrypts it back to its original content. After saving the decrypted data to the database, it quickly starts the analysis process.

[0246] Step 4:

[0247] The server uses machine learning models to analyze communication data. Here, with the aim of detecting abnormal behavior, it compares the data against normal usage patterns and identifies actions that exceed a threshold. Detectable abnormal behaviors include late-night access and the detection of aggressive message content.

[0248] Step 5:

[0249] When abnormal behavior is detected, the server immediately generates an alert for the parent or guardian. The alert includes a detailed description of the abnormal behavior, along with recommended actions to take.

[0250] Step 6:

[0251] The server sends generated alerts to users in real time. Users can receive alerts via their smartphones or PCs.

[0252] Step 7:

[0253] Based on the alerts they receive, users can monitor their child's online activities and take necessary guidance or action. They can also provide feedback on the accuracy of the alerts.

[0254] Step 8:

[0255] The server analyzes user feedback and uses it to improve the overall monitoring accuracy of the system and the machine learning models. This improves the system's accuracy and enables more accurate anomaly detection.

[0256] (Example 1)

[0257] 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."

[0258] A challenge exists in that parents lack the means to quickly and accurately identify dangerous behaviors in minors' online activities and take appropriate action. Furthermore, existing monitoring systems suffer from frequent false positives and inappropriate alerts, placing a heavy burden on users.

[0259] 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.

[0260] In this invention, the server includes means for acquiring information about user operations, means for analyzing the acquired information using a generative AI model to detect abnormal behavior, and means for generating warnings based on the detection of abnormal behavior and providing them to guardians. This makes it possible to detect inappropriate online activities of minors with high accuracy and to quickly notify guardians.

[0261] "Information about user actions" refers to data related to the user's online activities, specifically including the addresses of websites accessed, connection times and durations, and applications used.

[0262] A "generative AI model" is a digital model built on machine learning technology that learns patterns from past data and analyzes newly acquired data to detect abnormal behavior.

[0263] "Abnormal behavior" refers to online activities that are judged to deviate significantly from normal usage patterns, including viewing inappropriate content and using the internet outside of normal usage hours.

[0264] "Generating and providing warnings to parents" refers to a series of processes that create notifications, including explanations of the content and location, based on detected abnormal behavior, and promptly send them to parents' communication devices.

[0265] "Evaluation information" refers to user opinions and evaluations regarding the accuracy and usefulness of the system, and analyzing this information contributes to improving the system's performance.

[0266] This invention provides a system for appropriately monitoring the online activities of minors, identifying risks, and notifying parents. This system is based on a terminal used by the user and a server that processes the data.

[0267] The device acquires information about underage users' online activities in real time. This information includes the addresses of visited web pages, metadata of messages on social networking services (SNS), and application usage. The device securely transmits this information to the server using AES-256 encryption technology. The HTTPS protocol is used to ensure security during transmission.

[0268] The server decrypts the received encrypted information and analyzes it using a generative AI model. This model is designed to detect abnormal behavior that deviates from normal usage patterns and utilizes algorithms learned from historical data. When abnormal behavior is detected, the server generates a warning based on it and provides it to the parent or guardian. The warning includes the specific nature and time of the abnormal behavior and recommended actions, and is sent via email or a dedicated app notification.

[0269] Parents, as users, can provide guidance to minors based on the warnings they receive and, if necessary, return evaluation information to the system. This evaluation information is collected to improve the system's performance and enable more accurate analysis.

[0270] As a concrete example, imagine a scenario where, one Sunday night, a device detects access to inappropriate content, and the server immediately sends a warning to the parent. In this case, the parent can take appropriate action quickly. This system makes it possible to more effectively protect the safety of minors.

[0271] An example of a prompt is as follows: "Please describe in detail the content of the warning message that the server sends to parents when the system detects access to an inappropriate website late at night."

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The device acquires data about the user's online activity. Inputs include web page addresses, social media metadata, and application usage. This data is monitored and collected in real time. By collecting data incrementally, the device can continuously monitor user activity and gain a comprehensive overview. The collected data is encrypted using AES-256 encryption technology. The output is an encrypted, secure data packet, ready to be sent to the server.

[0275] Step 2:

[0276] The server receives encrypted data sent from the terminal. The input is encrypted data packets, which are then decrypted to reconstruct the original data. The server decrypts the data using a secure decryption protocol and restores the user's behavior history. This process allows the server to understand the details of the actual user behavior. The decrypted output is then analyzed by a generative AI model.

[0277] Step 3:

[0278] The server analyzes the decoded user behavior data using a generating AI model. The input is the decoded user behavior data, and the model detects abnormal behavior by comparing it with pre-trained normal behavior patterns. Specifically, examples include accessing inappropriate websites late at night. The machine learning algorithm identifies this as abnormal. The output is a list of detected abnormal behaviors, which are used in the next step.

[0279] Step 4:

[0280] The server generates a warning based on the detected abnormal behavior. The input is a list of abnormal behaviors, with a detailed description and recommended countermeasures appended to each behavior. The warning includes the content of the specific inappropriate behavior and the time when it occurred. The generated warning is shaped as information to be provided to the guardian. The output is a warning message formatted in a format that can be sent to the guardian.

[0281] Step 5:

[0282] The user, who is the guardian, receives the warning message sent from the server. The input is a warning of specific abnormal behavior, based on which appropriate guidance is given to the child. In addition, evaluation information regarding the accuracy of the warning content and the usefulness of the system can be returned to the system. This feedback information contributes to improving the accuracy of the system. The output is the user's feedback information that is utilized for improving the performance of the system.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] The issue is to ensure the safety of Internet use by efficiently and quickly identifying risky behaviors in the online activities of minors and notifying guardians at an appropriate time. It is also required to enable guardians to monitor their children's Internet activities without expending unnecessary effort.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0287] In this invention, the server includes means for collecting communication information from user devices, means for analyzing the collected communication information and detecting risky behavior, and means for automatically issuing risky behavior notifications on mobile information terminals such as smartphones. This makes it possible to automatically and in real time detect security risks in the online activities of minors and to quickly notify parents.

[0288] A "user device" is a terminal device that has the function of providing communication information in real time.

[0289] "Communication information" refers to data related to online operations, including information such as the URLs of visited websites and metadata for social media.

[0290] "Risk behavior" refers to online actions that pose a potential threat to the safety of minors.

[0291] A "guardian" is a person who is responsible for supervising a minor, or who fulfills that role.

[0292] "Feedback information" refers to information provided by parents based on warnings issued by the system, and is used to improve the system.

[0293] An "analysis method" refers to an algorithm or method used to analyze communication information and detect unusual behavior.

[0294] "Encryption" is the process of transforming data to enhance security and protect communication information from unauthorized use.

[0295] A "portable information terminal" refers to a portable information processing device, such as a smartphone, that has the function of providing notifications to the user.

[0296] "Real-time" refers to processing data and providing information at a speed that is almost identical to real-world time.

[0297] In the system that implements this application, a terminal device collects communication information in real time and sends encrypted data to a server. The server decrypts the received encrypted data and analyzes it using a generative AI model. This determines whether or not risky behavior has occurred, and if a risk is detected, a notification is immediately sent to the parent or guardian.

[0298] The system uses mobile devices such as smartphones as hardware, and programming languages ​​such as Python as software. Scripts are used to collect data, including browser history and SNS usage metadata, and the Fernet library is used for encryption. On the server side, machine learning frameworks such as TensorFlow and PyTorch are used for anomaly detection.

[0299] For example, if a minor attempts to access an unauthorized website late at night, this activity could be immediately detected, and the parent or guardian could receive a notification via their smartphone. This notification would include a specific message such as, "An inappropriate website was accessed late at night. Please take action."

[0300] An example of a prompt message provided to the generating AI model would be: "Create what alert message Family Security Watch should send to parents when a minor accesses unauthorized content. Include details about the specific times and situations in which warnings should be issued."

[0301] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0302] Step 1:

[0303] The terminal monitors the user's online activities in real time. The inputs include the URL of the visited website and the metadata of the SNS. These data are collected and encrypted using an encryption library. The output is the encrypted data in a secure state.

[0304] Step 2:

[0305] The terminal sends the encrypted data to the server. The input is the encrypted communication information, and the output is the server-side received data in a state where it is securely transferred to the server.

[0306] Step 3:

[0307] The server decrypts the received encrypted data. The input is the encrypted data, and by decrypting the data using the encryption key, the original communication information after decryption is obtained as the output.

[0308] Step 4:

[0309] The server analyzes the decrypted data using a generated AI model. The input is the decrypted communication information, and abnormal behaviors are detected by comparing with normal usage patterns. The output is the corresponding action data if a risk behavior is detected.

[0310] Step 5:

[0311] The server sends a notification to the guardian if a risk behavior is detected. The input is the data of the risk behavior, and the output is an alert message sent to the guardian's mobile information terminal as the notification content.

[0312] Step 6:

[0313] The user (parent / guardian) takes appropriate action regarding their child based on the notification they receive. They also send feedback back to the server. The input includes information about the notified risk behavior and the parent / guardian's response, and the output is feedback information sent to the server.

[0314] Step 7:

[0315] The server analyzes user feedback and uses it to improve its analysis methods. User feedback is used as input, and by retraining the generated AI model with this feedback, it updates the anomaly detection model to produce a more accurate output.

[0316] 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.

[0317] This invention combines a system for monitoring the online activities of minors with an emotion engine that recognizes user emotions. This allows for evaluation of how online behavior relates to user emotions, enabling more advanced monitoring and alerts.

[0318] Data collection and emotion recognition

[0319] First, the device collects data related to the user's emotions along with their online activity. This data includes the content of text messages, typing speed, and tone of voice used, and is used to estimate the user's emotional state.

[0320] The server analyzes the received data and uses an emotion engine to determine the user's emotional state. The emotion engine is built using machine learning techniques and can identify emotions such as positive, negative, and neutral. For example, if a user frequently uses terms that express dissatisfaction or anger, the emotion engine will detect a negative emotion.

[0321] Anomaly detection and alert generation

[0322] The server not only detects abnormal behavior in normal communication data, but also incorporates emotional information determined by the emotion engine into its analysis. In particular, if negative emotions increase and dangerous behavior is detected at the same time, the risk score is raised. As a result, if the existing threshold is exceeded, a warning is generated.

[0323] The generated warnings will notify parents along with the emotional state of the user. For example, if an aggressive message is being sent while the user is expressing anxiety or anger, the warning will include an explanation of the emotional state along with a cautionary message.

[0324] Feedback and system optimization

[0325] Users can review the warning information they receive and, if necessary, take appropriate action such as providing guidance or imposing restrictions. They can also provide feedback on their evaluation of the emotion detection results and their experience using the system. The server analyzes this feedback and uses it to improve the accuracy of the emotion engine's recognition and the overall system performance.

[0326] As a concrete example, if a device detects that a user's social media posts suddenly become aggressive, and the emotion engine simultaneously detects strong negative emotions, the server will notify the parent or guardian, prompting them to take immediate action. In this way, the present invention is a system that, by combining emotion analysis, enables a deeper understanding of user activity and allows for appropriate support and monitoring.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The device collects communication data and sentiment-related data related to the user's online activities. Sentiment data includes metrics such as the content of text messages, voice tone, and typing speed. This data is encrypted to protect personal information.

[0330] Step 2:

[0331] The device transmits encrypted communication data and emotional data to a server via the internet. This communication occurs in real time or periodically.

[0332] Step 3:

[0333] The server decodes the received data and analyzes the user's emotional state using an emotion engine. The emotion engine uses machine learning algorithms to determine whether the emotion is positive, negative, or neutral.

[0334] Step 4:

[0335] The server applies a machine learning model to analyze the decrypted communication data and detect abnormal behavior. This model identifies anomalies that exceed a threshold by comparing them against known malicious behavior patterns.

[0336] Step 5:

[0337] The server integrates the results of the emotion engine analysis and the abnormal behavior analysis to perform a comprehensive risk assessment. In particular, if negative emotions and abnormal behavior are detected simultaneously, the risk score is increased, indicating a high-priority warning.

[0338] Step 6:

[0339] Based on the risk assessment, the server generates a detailed alert. The alert includes the user's emotional state, the nature of the misconduct, and recommended countermeasures.

[0340] Step 7:

[0341] The server sends generated warnings to users in real time. Users can receive the warnings and check the situation via their smartphones or PCs.

[0342] Step 8:

[0343] Users take prompt action based on the warning message and provide feedback to the server. This feedback is used to improve the system's accuracy and enhance the sentiment engine.

[0344] In this way, the system, which incorporates an emotion engine, can achieve advanced monitoring based on the user's emotional state and provide more appropriate warnings and countermeasures.

[0345] (Example 2)

[0346] 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".

[0347] The increasing prevalence of dangerous behaviors and inappropriate emotional states in minors' online activities highlights the growing need for parents and administrators to properly monitor and address these issues promptly. While traditional systems have focused on behavioral monitoring, there is a growing demand for more sophisticated risk assessments that take into account users' emotional states.

[0348] 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.

[0349] In this invention, the server includes means for collecting information from user devices, means for analyzing the collected information and determining the emotional state using machine learning techniques, and means for generating a warning based on the determined emotional state and the detection results of abnormal behavior, and notifying the administrator. This makes it possible to comprehensively monitor both user activity and emotional state and provide the administrator with appropriate warnings before dangerous behavior occurs.

[0350] "User equipment" refers to all electronic devices used by users to conduct online activities, and includes terminals that enable data collection.

[0351] "Collecting information" refers to the act of gathering data about user activity, such as text, typing speed, and tone of voice, from the user's device.

[0352] "Machine learning technology" refers to techniques that enable computers to process large amounts of data and automatically learn patterns and rules.

[0353] "Emotional state" refers to information that represents psychological states such as joy, anger, and sadness, which is analyzed from the user's text data.

[0354] A "server" is a computer system used to process and analyze information on a network, and is a device that performs data analysis and notification management.

[0355] "Generating warnings and notifying administrators" refers to the process of creating an alarm when an anomaly is detected and communicating that information to the administrator.

[0356] This invention is a system for monitoring the online activities of minors and analyzing the emotional state of users. The system primarily functions through data exchange and analysis between terminals and servers.

[0357] The terminal is an electronic device used by the user, and it collects information generated through communication applications and social networking services (SNS). Specifically, it collects data such as the content of text messages, typing speed, and the tone of the words used. The terminal is responsible for monitoring this information in real time and transmitting the data to the server.

[0358] The server receives information sent from the terminal and analyzes the collected data. This analysis uses a machine learning tool called an emotion engine. This emotion engine analyzes the user's text data and classifies their emotional state as positive, negative, or neutral. For example, if a user frequently uses words expressing "anger" or "sadness," the engine can determine that this is a negative emotion.

[0359] The server detects deviations from the user's normal behavior patterns and generates warnings as needed. These warnings are sent to administrators (such as parents) and include detailed analysis of the user's emotional state, enabling administrators to address problems early.

[0360] The system can also improve analysis accuracy through a feedback loop. The sentiment engine and anomaly detection algorithms are continuously improved by users and administrators providing feedback on the accuracy of the warnings.

[0361] As a concrete example, if a user sends a message containing inappropriate content during a social networking exchange, and the sentiment engine detects an increase in negative emotions, the server immediately generates a warning and notifies the administrator. In this way, the system functions to keep minors' online activities safe.

[0362] Examples of input prompts for a generated AI model include: "Explain how you monitor minors' online activities and how the emotion engine evaluates their emotional state. Also, include specific use cases." These prompts serve as a tool to facilitate understanding of the system's implementation.

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] The device collects information through the user's online activities. Input includes text messages sent and received via social networking services and chat applications, typing speed, and tone of voice used. This data is collected in real time, compiled into communication packets, and prepared for transmission to the server.

[0366] Step 2:

[0367] The server receives data packets from the terminal. The input includes communication data sent from the terminal. The server prepares this data for analysis and supplies it to the emotion engine. During this process, data format conversion and preprocessing (e.g., string normalization) are performed.

[0368] Step 3:

[0369] The emotion engine on the server receives text data to be analyzed as input. The emotion engine uses machine learning algorithms to analyze the emotional state of the text. Specifically, the text is processed through a natural language processing module to calculate emotional scores such as positive, negative, and neutral. This output is generated as an emotional state report.

[0370] Step 4:

[0371] The server detects abnormal behavior based on the output of the emotion engine. Inputs include an emotional state report and a database of normal behavioral patterns for comparison. The server uses this to assess whether the user's current emotional state and behavior deviate from the norm. If an abnormality is detected, a risk score is calculated, triggering a warning.

[0372] Step 5:

[0373] The server generates an alert based on the generated risk score and notifies the administrator. The input includes the results of abnormal behavior detection and the risk score. The alert message includes a diagnosis of the emotional state and recommended administrator actions. This alert is sent to the administrator's terminal.

[0374] Step 6:

[0375] The user receives warning notifications from the server and provides feedback as needed. As input, the user receives warning messages and analysis results. Through feedback, the user sends information to the server regarding the effectiveness of the warnings and the accuracy of the analysis. This output is used to improve the server's analysis methods.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] There is a need to effectively monitor the misconduct and emotional state of minors in online environments and to warn parents at the appropriate time in order to protect their safety. However, conventional systems have the challenge of being unable to adequately recognize emotional states and making it difficult to monitor emotional changes in conjunction with behavior.

[0379] 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.

[0380] In this invention, the server includes means for acquiring communication data and emotion-related information from a user terminal, means for analyzing the acquired communication data and emotion information to detect misconduct and emotional states, and means for generating warnings based on the detected misconduct and emotional states and notifying parents. This makes it possible to detect misconduct and emotional changes in minors' online activities in real time and warn parents at an appropriate time.

[0381] A "user terminal" is an information processing device used by an individual to conduct online activities, and is capable of sending and receiving data.

[0382] "Communication data" refers to information sent and received via a user's terminal, including messages and internet browsing history.

[0383] "Emotion-related information" refers to data necessary to estimate the user's emotional state, including typing speed and tone of voice used.

[0384] "Misconduct" refers to unauthorized or unsafe actions, including inappropriate remarks or behavior online.

[0385] "Emotional state" refers to the tendencies of an individual's inner emotions, and is classified as positive, negative, or neutral.

[0386] A "warning" is a notification generated when misconduct or negative emotional states are detected, and it includes content that prompts parents to take notice.

[0387] "Feedback data" refers to information provided by users or guardians, including analysis results and feedback on the system.

[0388] "Analysis methods" refer to methods for evaluating fraudulent behavior and emotional states based on acquired data, and include algorithms and machine learning techniques.

[0389] An "emotion recognition method" is a technique for analyzing and recognizing a user's emotional state, and includes processes involving data analysis and machine learning.

[0390] An "information processing device" is a device used to collect, process, and output data, and includes computers used in homes.

[0391] This invention is a system for monitoring the online activities of minors and evaluating their emotional state. The server acquires communication data and emotion-related information from the user's terminal. This includes the user's online activities, message sending history, typing speed, and tone of voice used.

[0392] The device collects this data in real time and sends it to the server. The server analyzes the data and uses an emotion engine to determine the user's emotional state. The emotion engine, which utilizes machine learning technology, identifies emotions such as positive, negative, and neutral, and generates a corresponding warning if negative emotions are particularly heightened.

[0393] For example, if a user frequently makes aggressive remarks while playing online games and a negative emotional state is detected, the server will quickly generate a warning and send a verbal notification to the parent or guardian via a home information processing device. This system runs on a small computer such as a Raspberry Pi using a Python program.

[0394] Furthermore, feedback data provided by users and guardians is used to improve the accuracy of emotion recognition and to refine the analysis methods. This process continuously optimizes the system's performance, resulting in more accurate monitoring and notifications.

[0395] Further improvements can be made using a generative AI model through prompts such as: "Please explain how the robot can detect emotions from a minor's online activities, what kind of notification it will send if a negative situation is detected, and how it will warn parents."

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The device collects communication data and sentiment-related information from the user's online activity. Specifically, input includes messages sent by the user, text communications with each other, typing speed, and tone of voice used. This input data is temporarily stored on the device and then sent to the server for subsequent processing.

[0399] Step 2:

[0400] The server receives data sent from the terminal and begins analysis. Using an emotion engine, it identifies the user's emotional state from the input communication data. Emotion labels such as positive, negative, and neutral are generated as output. Specifically, machine learning techniques are used to extract features and perform pattern matching and classification.

[0401] Step 3:

[0402] Based on the analysis results, the server evaluates whether the user's behavior is fraudulent and whether their emotional state is negative. In particular, if negative emotions and fraudulent behavior are detected simultaneously, a risk score is calculated, and a warning is generated if it exceeds a threshold. Thresholding and scoring models are applied in this step.

[0403] Step 4:

[0404] The generated alerts are sent from the server to the home information processing unit. The specific alert message includes a summary of the detected emotional state or behavior, and, if necessary, recommended actions. The information processing unit verbally notifies the parent or guardian of this message to help them take prompt action.

[0405] Step 5:

[0406] Feedback from users and guardians is sent to the server. The server uses this feedback to continuously improve its analysis methods and sentiment recognition methods. Specifically, feedback information is received as input, and through algorithm adjustments and model retraining, it leads to improved system accuracy as output.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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".

[0423] The system of this invention aims to monitor the online activities of minors, identify risky behaviors, and notify parents. Below, we generate a program for this system and describe its processing in natural language.

[0424] Data collection and transmission

[0425] First, the device monitors communication data generated through the user's activities in real time. This data includes URLs of visited websites, metadata of messages on social media, and usage time. The collected data is encrypted to protect privacy and then sent to the server.

[0426] Data analysis and anomaly detection

[0427] The server performs real-time analysis based on the received communication data. Using machine learning models, abnormal behavior that deviates from normal usage patterns is detected. These models are built on historical data and expert advice. For example, if a user frequently accesses dangerous websites late at night, the server recognizes this behavior as a risk.

[0428] Alert generation and notification

[0429] When abnormal behavior is detected, the server immediately notifies parents. The alert includes specific details of the abnormal behavior, the time it occurred, and recommended actions to take. For example, it may include specific wording such as, "Access to inappropriate content on a specific social media platform has been detected."

[0430] Feedback and system improvements

[0431] Users can provide guidance to their children based on the alerts they receive, and can also provide feedback to the system. This feedback may include suggestions regarding the accuracy of the alerts and new behaviors that should be detected. The server collects this feedback and uses it to improve the accuracy of the analysis model.

[0432] Thus, the system of the present invention can provide a safe environment for minors to use the internet and reduce the burden on parents. A specific example of use is when a device detects access to inappropriate content late on a Sunday night, and an immediate warning is sent to the parent via the server. In this case, the parent can take appropriate action quickly.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] The device monitors the user's online activity. This is done by collecting communication data in real time from the websites the user visits and the social networking applications they use. The collected data is processed using strong encryption technology to protect privacy.

[0436] Step 2:

[0437] The device transmits the collected encrypted data to the server via the internet. This data transmission is performed periodically or immediately in the event of suspected abnormal behavior.

[0438] Step 3:

[0439] The server decompresses the received data and decrypts it back to its original content. After saving the decrypted data to the database, it quickly starts the analysis process.

[0440] Step 4:

[0441] The server uses machine learning models to analyze communication data. Here, with the aim of detecting abnormal behavior, it compares the data against normal usage patterns and identifies actions that exceed a threshold. Detectable abnormal behaviors include late-night access and the detection of aggressive message content.

[0442] Step 5:

[0443] When abnormal behavior is detected, the server immediately generates an alert for the parent or guardian. The alert includes a detailed description of the abnormal behavior, along with recommended actions to take.

[0444] Step 6:

[0445] The server sends generated alerts to users in real time. Users can receive alerts via their smartphones or PCs.

[0446] Step 7:

[0447] Based on the alerts they receive, users can monitor their child's online activities and take necessary guidance or action. They can also provide feedback on the accuracy of the alerts.

[0448] Step 8:

[0449] The server analyzes user feedback and uses it to improve the overall monitoring accuracy of the system and the machine learning models. This improves the system's accuracy and enables more accurate anomaly detection.

[0450] (Example 1)

[0451] 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."

[0452] A challenge exists in that parents lack the means to quickly and accurately identify dangerous behaviors in minors' online activities and take appropriate action. Furthermore, existing monitoring systems suffer from frequent false positives and inappropriate alerts, placing a heavy burden on users.

[0453] 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.

[0454] In this invention, the server includes means for acquiring information about user operations, means for analyzing the acquired information using a generative AI model to detect abnormal behavior, and means for generating warnings based on the detection of abnormal behavior and providing them to guardians. This makes it possible to detect inappropriate online activities of minors with high accuracy and to quickly notify guardians.

[0455] "Information about user actions" refers to data related to the user's online activities, specifically including the addresses of websites accessed, connection times and durations, and applications used.

[0456] A "generative AI model" is a digital model built on machine learning technology that learns patterns from past data and analyzes newly acquired data to detect abnormal behavior.

[0457] "Abnormal behavior" refers to online activities that are judged to deviate significantly from normal usage patterns, including viewing inappropriate content and using the internet outside of normal usage hours.

[0458] "Generating and providing warnings to parents" refers to a series of processes that create notifications, including explanations of the content and location, based on detected abnormal behavior, and promptly send them to parents' communication devices.

[0459] "Evaluation information" refers to user opinions and evaluations regarding the accuracy and usefulness of the system, and analyzing this information contributes to improving the system's performance.

[0460] This invention provides a system for appropriately monitoring the online activities of minors, identifying risks, and notifying parents. This system is based on a terminal used by the user and a server that processes the data.

[0461] The device acquires information about underage users' online activities in real time. This information includes the addresses of visited web pages, metadata of messages on social networking services (SNS), and application usage. The device securely transmits this information to the server using AES-256 encryption technology. The HTTPS protocol is used to ensure security during transmission.

[0462] The server decrypts the received encrypted information and analyzes it using a generative AI model. This model is designed to detect abnormal behavior that deviates from normal usage patterns and utilizes algorithms learned from historical data. When abnormal behavior is detected, the server generates a warning based on it and provides it to the parent or guardian. The warning includes the specific nature and time of the abnormal behavior and recommended actions, and is sent via email or a dedicated app notification.

[0463] Parents, as users, can provide guidance to minors based on the warnings they receive and, if necessary, return evaluation information to the system. This evaluation information is collected to improve the system's performance and enable more accurate analysis.

[0464] As a concrete example, imagine a scenario where, one Sunday night, a device detects access to inappropriate content, and the server immediately sends a warning to the parent. In this case, the parent can take appropriate action quickly. This system makes it possible to more effectively protect the safety of minors.

[0465] An example of a prompt is as follows: "Please describe in detail the content of the warning message that the server sends to parents when the system detects access to an inappropriate website late at night."

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] Step 1:

[0468] The device acquires data about the user's online activity. Inputs include web page addresses, social media metadata, and application usage. This data is monitored and collected in real time. By collecting data incrementally, the device can continuously monitor user activity and gain a comprehensive overview. The collected data is encrypted using AES-256 encryption technology. The output is an encrypted, secure data packet, ready to be sent to the server.

[0469] Step 2:

[0470] The server receives encrypted data sent from the terminal. The input is encrypted data packets, which are then decrypted to reconstruct the original data. The server decrypts the data using a secure decryption protocol and restores the user's behavior history. This process allows the server to understand the details of the actual user behavior. The decrypted output is then analyzed by a generative AI model.

[0471] Step 3:

[0472] The server analyzes the decoded user behavior data using a generating AI model. The input is the decoded user behavior data, and the model detects abnormal behavior by comparing it with pre-trained normal behavior patterns. Specifically, examples include accessing inappropriate websites late at night. The machine learning algorithm identifies this as abnormal. The output is a list of detected abnormal behaviors, which are used in the next step.

[0473] Step 4:

[0474] The server generates alerts based on detected abnormal behavior. The input is a list of abnormal behaviors, each accompanied by a detailed description and recommended countermeasures. The alerts include the specific inappropriate behavior and the time it occurred. The generated alerts are formatted as information to be provided to parents. The output is an alert message formatted for sending to parents.

[0475] Step 5:

[0476] The user (parent / guardian) receives warning messages sent from the server. The input is a warning of specific abnormal behavior, which is used to provide appropriate guidance to the child. In addition, evaluation information regarding the accuracy of the warnings and the system's usefulness can be returned to the system. This feedback information contributes to improving the system's accuracy. The output is user feedback information used to improve the system's performance.

[0477] (Application Example 1)

[0478] 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."

[0479] The challenge lies in efficiently and quickly identifying risky behaviors in minors' online activities and notifying parents at the appropriate time to ensure the safety of internet use. Furthermore, it is necessary to enable parents to monitor their children's internet activities without unnecessary effort.

[0480] 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.

[0481] In this invention, the server includes means for collecting communication information from user devices, means for analyzing the collected communication information and detecting risky behavior, and means for automatically issuing risky behavior notifications on mobile information terminals such as smartphones. This makes it possible to automatically and in real time detect security risks in the online activities of minors and to quickly notify parents.

[0482] A "user device" is a terminal device that has the function of providing communication information in real time.

[0483] "Communication information" refers to data related to online operations, including information such as the URLs of visited websites and metadata for social media.

[0484] "Risk behavior" refers to online actions that pose a potential threat to the safety of minors.

[0485] A "guardian" is a person who is responsible for supervising a minor, or who fulfills that role.

[0486] "Feedback information" refers to information provided by parents based on warnings issued by the system, and is used to improve the system.

[0487] An "analysis method" refers to an algorithm or method used to analyze communication information and detect unusual behavior.

[0488] "Encryption" is the process of transforming data to enhance security and protect communication information from unauthorized use.

[0489] A "portable information terminal" refers to a portable information processing device, such as a smartphone, that has the function of providing notifications to the user.

[0490] "Real-time" refers to processing data and providing information at a speed that is almost identical to real-world time.

[0491] In the system that implements this application, a terminal device collects communication information in real time and sends encrypted data to a server. The server decrypts the received encrypted data and analyzes it using a generative AI model. This determines whether or not risky behavior has occurred, and if a risk is detected, a notification is immediately sent to the parent or guardian.

[0492] The system uses mobile devices such as smartphones as hardware, and programming languages ​​such as Python as software. Scripts are used to collect data, including browser history and SNS usage metadata, and the Fernet library is used for encryption. On the server side, machine learning frameworks such as TensorFlow and PyTorch are used for anomaly detection.

[0493] For example, if a minor attempts to access an unauthorized website late at night, this activity could be immediately detected, and the parent or guardian could receive a notification via their smartphone. This notification would include a specific message such as, "An inappropriate website was accessed late at night. Please take action."

[0494] An example of a prompt message provided to the generating AI model would be: "Create what alert message Family Security Watch should send to parents when a minor accesses unauthorized content. Include details about the specific times and situations in which warnings should be issued."

[0495] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0496] Step 1:

[0497] The device monitors the user's online activity in real time. Inputs include URLs of visited websites and social media metadata. This data is collected and encrypted using an encryption library. The output is encrypted data in a secure state.

[0498] Step 2:

[0499] The terminal sends encrypted data to the server. The input is encrypted communication information, and the output is the data received by the server, in a state where it has been securely transferred to the server.

[0500] Step 3:

[0501] The server decrypts the received encrypted data. The input is encrypted data, and by using the encryption key to decrypt the data, the server obtains the original decrypted communication information as output.

[0502] Step 4:

[0503] The server analyzes the decoded data using a generative AI model. The input is decoded communication information, which is then compared to normal usage patterns to detect abnormal behavior. The output, if any risky behavior is detected, is the corresponding behavioral data.

[0504] Step 5:

[0505] The server sends a notification to the parent or guardian when risky behavior is detected. The input is data on the risky behavior, and the output is an alert message sent to the parent or guardian's mobile device as a notification.

[0506] Step 6:

[0507] The user (parent / guardian) takes appropriate action regarding their child based on the notification they receive. They also send feedback back to the server. The input includes information about the notified risk behavior and the parent / guardian's response, and the output is feedback information sent to the server.

[0508] Step 7:

[0509] The server analyzes user feedback and uses it to improve its analysis methods. User feedback is used as input, and by retraining the generated AI model with this feedback, it updates the anomaly detection model to produce a more accurate output.

[0510] 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.

[0511] This invention combines a system for monitoring the online activities of minors with an emotion engine that recognizes user emotions. This allows for evaluation of how online behavior relates to user emotions, enabling more advanced monitoring and alerts.

[0512] Data collection and emotion recognition

[0513] First, the device collects data related to the user's emotions along with their online activity. This data includes the content of text messages, typing speed, and tone of voice used, and is used to estimate the user's emotional state.

[0514] The server analyzes the received data and uses an emotion engine to determine the user's emotional state. The emotion engine is built using machine learning techniques and can identify emotions such as positive, negative, and neutral. For example, if a user frequently uses terms that express dissatisfaction or anger, the emotion engine will detect a negative emotion.

[0515] Anomaly detection and alert generation

[0516] The server not only detects abnormal behavior in normal communication data, but also incorporates emotional information determined by the emotion engine into its analysis. In particular, if negative emotions increase and dangerous behavior is detected at the same time, the risk score is raised. As a result, if the existing threshold is exceeded, a warning is generated.

[0517] The generated warnings will notify parents along with the emotional state of the user. For example, if an aggressive message is being sent while the user is expressing anxiety or anger, the warning will include an explanation of the emotional state along with a cautionary message.

[0518] Feedback and system optimization

[0519] Users can review the warning information they receive and, if necessary, take appropriate action such as providing guidance or imposing restrictions. They can also provide feedback on their evaluation of the emotion detection results and their experience using the system. The server analyzes this feedback and uses it to improve the accuracy of the emotion engine's recognition and the overall system performance.

[0520] As a concrete example, if a device detects that a user's social media posts suddenly become aggressive, and the emotion engine simultaneously detects strong negative emotions, the server will notify the parent or guardian, prompting them to take immediate action. In this way, the present invention is a system that, by combining emotion analysis, enables a deeper understanding of user activity and allows for appropriate support and monitoring.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The device collects communication data and sentiment-related data related to the user's online activities. Sentiment data includes metrics such as the content of text messages, voice tone, and typing speed. This data is encrypted to protect personal information.

[0524] Step 2:

[0525] The device transmits encrypted communication data and emotional data to a server via the internet. This communication occurs in real time or periodically.

[0526] Step 3:

[0527] The server decodes the received data and analyzes the user's emotional state using an emotion engine. The emotion engine uses machine learning algorithms to determine whether the emotion is positive, negative, or neutral.

[0528] Step 4:

[0529] The server applies a machine learning model to analyze the decrypted communication data and detect abnormal behavior. This model identifies anomalies that exceed a threshold by comparing them against known malicious behavior patterns.

[0530] Step 5:

[0531] The server integrates the results of the emotion engine analysis and the abnormal behavior analysis to perform a comprehensive risk assessment. In particular, if negative emotions and abnormal behavior are detected simultaneously, the risk score is increased, indicating a high-priority warning.

[0532] Step 6:

[0533] Based on the risk assessment, the server generates a detailed alert. The alert includes the user's emotional state, the nature of the misconduct, and recommended countermeasures.

[0534] Step 7:

[0535] The server sends generated warnings to users in real time. Users can receive the warnings and check the situation via their smartphones or PCs.

[0536] Step 8:

[0537] Users take prompt action based on the warning message and provide feedback to the server. This feedback is used to improve the system's accuracy and enhance the sentiment engine.

[0538] In this way, the system, which incorporates an emotion engine, can achieve advanced monitoring based on the user's emotional state and provide more appropriate warnings and countermeasures.

[0539] (Example 2)

[0540] 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."

[0541] The increasing prevalence of dangerous behaviors and inappropriate emotional states in minors' online activities highlights the growing need for parents and administrators to properly monitor and address these issues promptly. While traditional systems have focused on behavioral monitoring, there is a growing demand for more sophisticated risk assessments that take into account users' emotional states.

[0542] 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.

[0543] In this invention, the server includes means for collecting information from user devices, means for analyzing the collected information and determining the emotional state using machine learning techniques, and means for generating a warning based on the determined emotional state and the detection results of abnormal behavior, and notifying the administrator. This makes it possible to comprehensively monitor both user activity and emotional state and provide the administrator with appropriate warnings before dangerous behavior occurs.

[0544] "User equipment" refers to all electronic devices used by users to conduct online activities, and includes terminals that enable data collection.

[0545] "Collecting information" refers to the act of gathering data about user activity, such as text, typing speed, and tone of voice, from the user's device.

[0546] "Machine learning technology" refers to techniques that enable computers to process large amounts of data and automatically learn patterns and rules.

[0547] "Emotional state" refers to information that represents psychological states such as joy, anger, and sadness, which is analyzed from the user's text data.

[0548] A "server" is a computer system used to process and analyze information on a network, and is a device that performs data analysis and notification management.

[0549] "Generating warnings and notifying administrators" refers to the process of creating an alarm when an anomaly is detected and communicating that information to the administrator.

[0550] This invention is a system for monitoring the online activities of minors and analyzing the emotional state of users. The system primarily functions through data exchange and analysis between terminals and servers.

[0551] The terminal is an electronic device used by the user, and it collects information generated through communication applications and social networking services (SNS). Specifically, it collects data such as the content of text messages, typing speed, and the tone of the words used. The terminal is responsible for monitoring this information in real time and transmitting the data to the server.

[0552] The server receives information sent from the terminal and analyzes the collected data. This analysis uses a machine learning tool called an emotion engine. This emotion engine analyzes the user's text data and classifies their emotional state as positive, negative, or neutral. For example, if a user frequently uses words expressing "anger" or "sadness," the engine can determine that this is a negative emotion.

[0553] The server detects deviations from the user's normal behavior patterns and generates warnings as needed. These warnings are sent to administrators (such as parents) and include detailed analysis of the user's emotional state, enabling administrators to address problems early.

[0554] The system can also improve analysis accuracy through a feedback loop. The sentiment engine and anomaly detection algorithms are continuously improved by users and administrators providing feedback on the accuracy of the warnings.

[0555] As a concrete example, if a user sends a message containing inappropriate content during a social networking exchange, and the sentiment engine detects an increase in negative emotions, the server immediately generates a warning and notifies the administrator. In this way, the system functions to keep minors' online activities safe.

[0556] Examples of input prompts for a generated AI model include: "Explain how you monitor minors' online activities and how the emotion engine evaluates their emotional state. Also, include specific use cases." These prompts serve as a tool to facilitate understanding of the system's implementation.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] The device collects information through the user's online activities. Input includes text messages sent and received via social networking services and chat applications, typing speed, and tone of voice used. This data is collected in real time, compiled into communication packets, and prepared for transmission to the server.

[0560] Step 2:

[0561] The server receives data packets from the terminal. The input includes communication data sent from the terminal. The server prepares this data for analysis and supplies it to the emotion engine. During this process, data format conversion and preprocessing (e.g., string normalization) are performed.

[0562] Step 3:

[0563] The emotion engine on the server receives text data to be analyzed as input. The emotion engine uses machine learning algorithms to analyze the emotional state of the text. Specifically, the text is processed through a natural language processing module to calculate emotional scores such as positive, negative, and neutral. This output is generated as an emotional state report.

[0564] Step 4:

[0565] The server detects abnormal behavior based on the output of the emotion engine. Inputs include an emotional state report and a database of normal behavioral patterns for comparison. The server uses this to assess whether the user's current emotional state and behavior deviate from the norm. If an abnormality is detected, a risk score is calculated, triggering a warning.

[0566] Step 5:

[0567] The server generates an alert based on the generated risk score and notifies the administrator. The input includes the results of abnormal behavior detection and the risk score. The alert message includes a diagnosis of the emotional state and recommended administrator actions. This alert is sent to the administrator's terminal.

[0568] Step 6:

[0569] The user receives warning notifications from the server and provides feedback as needed. As input, the user receives warning messages and analysis results. Through feedback, the user sends information to the server regarding the effectiveness of the warnings and the accuracy of the analysis. This output is used to improve the server's analysis methods.

[0570] (Application Example 2)

[0571] 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."

[0572] There is a need to effectively monitor the misconduct and emotional state of minors in online environments and to warn parents at the appropriate time in order to protect their safety. However, conventional systems have the challenge of being unable to adequately recognize emotional states and making it difficult to monitor emotional changes in conjunction with behavior.

[0573] 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.

[0574] In this invention, the server includes means for acquiring communication data and emotion-related information from a user terminal, means for analyzing the acquired communication data and emotion information to detect misconduct and emotional states, and means for generating warnings based on the detected misconduct and emotional states and notifying parents. This makes it possible to detect misconduct and emotional changes in minors' online activities in real time and warn parents at an appropriate time.

[0575] A "user terminal" is an information processing device used by an individual to conduct online activities, and is capable of sending and receiving data.

[0576] "Communication data" refers to information sent and received via a user's terminal, including messages and internet browsing history.

[0577] "Emotion-related information" refers to data necessary to estimate the user's emotional state, including typing speed and tone of voice used.

[0578] "Misconduct" refers to unauthorized or unsafe actions, including inappropriate remarks or behavior online.

[0579] "Emotional state" refers to the tendencies of an individual's inner emotions, and is classified as positive, negative, or neutral.

[0580] A "warning" is a notification generated when misconduct or negative emotional states are detected, and it includes content that prompts parents to take notice.

[0581] "Feedback data" refers to information provided by users or guardians, including analysis results and feedback on the system.

[0582] "Analysis methods" refer to methods for evaluating fraudulent behavior and emotional states based on acquired data, and include algorithms and machine learning techniques.

[0583] An "emotion recognition method" is a technique for analyzing and recognizing a user's emotional state, and includes processes involving data analysis and machine learning.

[0584] An "information processing device" is a device used to collect, process, and output data, and includes computers used in homes.

[0585] This invention is a system for monitoring the online activities of minors and evaluating their emotional state. The server acquires communication data and emotion-related information from the user's terminal. This includes the user's online activities, message sending history, typing speed, and tone of voice used.

[0586] The device collects this data in real time and sends it to the server. The server analyzes the data and uses an emotion engine to determine the user's emotional state. The emotion engine, which utilizes machine learning technology, identifies emotions such as positive, negative, and neutral, and generates a corresponding warning if negative emotions are particularly heightened.

[0587] For example, if a user frequently makes aggressive remarks while playing online games and a negative emotional state is detected, the server will quickly generate a warning and send a verbal notification to the parent or guardian via a home information processing device. This system runs on a small computer such as a Raspberry Pi using a Python program.

[0588] Furthermore, feedback data provided by users and guardians is used to improve the accuracy of emotion recognition and to refine the analysis methods. This process continuously optimizes the system's performance, resulting in more accurate monitoring and notifications.

[0589] Further improvements can be made using a generative AI model through prompts such as: "Please explain how the robot can detect emotions from a minor's online activities, what kind of notification it will send if a negative situation is detected, and how it will warn parents."

[0590] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0591] Step 1:

[0592] The device collects communication data and sentiment-related information from the user's online activity. Specifically, input includes messages sent by the user, text communications with each other, typing speed, and tone of voice used. This input data is temporarily stored on the device and then sent to the server for subsequent processing.

[0593] Step 2:

[0594] The server receives data sent from the terminal and begins analysis. Using an emotion engine, it identifies the user's emotional state from the input communication data. Emotion labels such as positive, negative, and neutral are generated as output. Specifically, machine learning techniques are used to extract features and perform pattern matching and classification.

[0595] Step 3:

[0596] Based on the analysis results, the server evaluates whether the user's behavior is fraudulent and whether their emotional state is negative. In particular, if negative emotions and fraudulent behavior are detected simultaneously, a risk score is calculated, and a warning is generated if it exceeds a threshold. Thresholding and scoring models are applied in this step.

[0597] Step 4:

[0598] The generated alerts are sent from the server to the home information processing unit. The specific alert message includes a summary of the detected emotional state or behavior, and, if necessary, recommended actions. The information processing unit verbally notifies the parent or guardian of this message to help them take prompt action.

[0599] Step 5:

[0600] Feedback from users and guardians is sent to the server. The server uses this feedback to continuously improve its analysis methods and sentiment recognition methods. Specifically, feedback information is received as input, and through algorithm adjustments and model retraining, it leads to improved system accuracy as output.

[0601] 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.

[0602] 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.

[0603] 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.

[0604] [Fourth Embodiment]

[0605] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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).

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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".

[0618] The system of this invention aims to monitor the online activities of minors, identify risky behaviors, and notify parents. Below, we generate a program for this system and describe its processing in natural language.

[0619] Data collection and transmission

[0620] First, the device monitors communication data generated through the user's activities in real time. This data includes URLs of visited websites, metadata of messages on social media, and usage time. The collected data is encrypted to protect privacy and then sent to the server.

[0621] Data analysis and anomaly detection

[0622] The server performs real-time analysis based on the received communication data. Using machine learning models, abnormal behavior that deviates from normal usage patterns is detected. These models are built on historical data and expert advice. For example, if a user frequently accesses dangerous websites late at night, the server recognizes this behavior as a risk.

[0623] Alert generation and notification

[0624] When abnormal behavior is detected, the server immediately notifies parents. The alert includes specific details of the abnormal behavior, the time it occurred, and recommended actions to take. For example, it may include specific wording such as, "Access to inappropriate content on a specific social media platform has been detected."

[0625] Feedback and system improvements

[0626] Users can provide guidance to their children based on the alerts they receive, and can also provide feedback to the system. This feedback may include suggestions regarding the accuracy of the alerts and new behaviors that should be detected. The server collects this feedback and uses it to improve the accuracy of the analysis model.

[0627] Thus, the system of the present invention can provide a safe environment for minors to use the internet and reduce the burden on parents. A specific example of use is when a device detects access to inappropriate content late on a Sunday night, and an immediate warning is sent to the parent via the server. In this case, the parent can take appropriate action quickly.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The device monitors the user's online activity. This is done by collecting communication data in real time from the websites the user visits and the social networking applications they use. The collected data is processed using strong encryption technology to protect privacy.

[0631] Step 2:

[0632] The device transmits the collected encrypted data to the server via the internet. This data transmission is performed periodically or immediately in the event of suspected abnormal behavior.

[0633] Step 3:

[0634] The server decompresses the received data and decrypts it back to its original content. After saving the decrypted data to the database, it quickly starts the analysis process.

[0635] Step 4:

[0636] The server uses machine learning models to analyze communication data. Here, with the aim of detecting abnormal behavior, it compares the data against normal usage patterns and identifies actions that exceed a threshold. Detectable abnormal behaviors include late-night access and the detection of aggressive message content.

[0637] Step 5:

[0638] When abnormal behavior is detected, the server immediately generates an alert for the parent or guardian. The alert includes a detailed description of the abnormal behavior, along with recommended actions to take.

[0639] Step 6:

[0640] The server sends generated alerts to users in real time. Users can receive alerts via their smartphones or PCs.

[0641] Step 7:

[0642] Based on the alerts they receive, users can monitor their child's online activities and take necessary guidance or action. They can also provide feedback on the accuracy of the alerts.

[0643] Step 8:

[0644] The server analyzes user feedback and uses it to improve the overall monitoring accuracy of the system and the machine learning models. This improves the system's accuracy and enables more accurate anomaly detection.

[0645] (Example 1)

[0646] 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".

[0647] A challenge exists in that parents lack the means to quickly and accurately identify dangerous behaviors in minors' online activities and take appropriate action. Furthermore, existing monitoring systems suffer from frequent false positives and inappropriate alerts, placing a heavy burden on users.

[0648] 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.

[0649] In this invention, the server includes means for acquiring information about user operations, means for analyzing the acquired information using a generative AI model to detect abnormal behavior, and means for generating warnings based on the detection of abnormal behavior and providing them to guardians. This makes it possible to detect inappropriate online activities of minors with high accuracy and to quickly notify guardians.

[0650] "Information about user actions" refers to data related to the user's online activities, specifically including the addresses of websites accessed, connection times and durations, and applications used.

[0651] A "generative AI model" is a digital model built on machine learning technology that learns patterns from past data and analyzes newly acquired data to detect abnormal behavior.

[0652] "Abnormal behavior" refers to online activities that are judged to deviate significantly from normal usage patterns, including viewing inappropriate content and using the internet outside of normal usage hours.

[0653] "Generating and providing warnings to parents" refers to a series of processes that create notifications, including explanations of the content and location, based on detected abnormal behavior, and promptly send them to parents' communication devices.

[0654] "Evaluation information" refers to user opinions and evaluations regarding the accuracy and usefulness of the system, and analyzing this information contributes to improving the system's performance.

[0655] This invention provides a system for appropriately monitoring the online activities of minors, identifying risks, and notifying parents. This system is based on a terminal used by the user and a server that processes the data.

[0656] The device acquires information about underage users' online activities in real time. This information includes the addresses of visited web pages, metadata of messages on social networking services (SNS), and application usage. The device securely transmits this information to the server using AES-256 encryption technology. The HTTPS protocol is used to ensure security during transmission.

[0657] The server decrypts the received encrypted information and analyzes it using a generative AI model. This model is designed to detect abnormal behavior that deviates from normal usage patterns and utilizes algorithms learned from historical data. When abnormal behavior is detected, the server generates a warning based on it and provides it to the parent or guardian. The warning includes the specific nature and time of the abnormal behavior and recommended actions, and is sent via email or a dedicated app notification.

[0658] Parents, as users, can provide guidance to minors based on the warnings they receive and, if necessary, return evaluation information to the system. This evaluation information is collected to improve the system's performance and enable more accurate analysis.

[0659] As a concrete example, imagine a scenario where, one Sunday night, a device detects access to inappropriate content, and the server immediately sends a warning to the parent. In this case, the parent can take appropriate action quickly. This system makes it possible to more effectively protect the safety of minors.

[0660] An example of a prompt is as follows: "Please describe in detail the content of the warning message that the server sends to parents when the system detects access to an inappropriate website late at night."

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1:

[0663] The device acquires data about the user's online activity. Inputs include web page addresses, social media metadata, and application usage. This data is monitored and collected in real time. By collecting data incrementally, the device can continuously monitor user activity and gain a comprehensive overview. The collected data is encrypted using AES-256 encryption technology. The output is an encrypted, secure data packet, ready to be sent to the server.

[0664] Step 2:

[0665] The server receives encrypted data sent from the terminal. The input is encrypted data packets, which are then decrypted to reconstruct the original data. The server decrypts the data using a secure decryption protocol and restores the user's behavior history. This process allows the server to understand the details of the actual user behavior. The decrypted output is then analyzed by a generative AI model.

[0666] Step 3:

[0667] The server analyzes the decoded user behavior data using a generating AI model. The input is the decoded user behavior data, and the model detects abnormal behavior by comparing it with pre-trained normal behavior patterns. Specifically, examples include accessing inappropriate websites late at night. The machine learning algorithm identifies this as abnormal. The output is a list of detected abnormal behaviors, which are used in the next step.

[0668] Step 4:

[0669] The server generates alerts based on detected abnormal behavior. The input is a list of abnormal behaviors, each accompanied by a detailed description and recommended countermeasures. The alerts include the specific inappropriate behavior and the time it occurred. The generated alerts are formatted as information to be provided to parents. The output is an alert message formatted for sending to parents.

[0670] Step 5:

[0671] The user (parent / guardian) receives warning messages sent from the server. The input is a warning of specific abnormal behavior, which is used to provide appropriate guidance to the child. In addition, evaluation information regarding the accuracy of the warnings and the system's usefulness can be returned to the system. This feedback information contributes to improving the system's accuracy. The output is user feedback information used to improve the system's performance.

[0672] (Application Example 1)

[0673] 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".

[0674] The challenge lies in efficiently and quickly identifying risky behaviors in minors' online activities and notifying parents at the appropriate time to ensure the safety of internet use. Furthermore, it is necessary to enable parents to monitor their children's internet activities without unnecessary effort.

[0675] 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.

[0676] In this invention, the server includes means for collecting communication information from user devices, means for analyzing the collected communication information and detecting risky behavior, and means for automatically issuing risky behavior notifications on mobile information terminals such as smartphones. This makes it possible to automatically and in real time detect security risks in the online activities of minors and to quickly notify parents.

[0677] A "user device" is a terminal device that has the function of providing communication information in real time.

[0678] "Communication information" refers to data related to online operations, including information such as the URLs of visited websites and metadata for social media.

[0679] "Risk behavior" refers to online actions that pose a potential threat to the safety of minors.

[0680] A "guardian" is a person who is responsible for supervising a minor, or who fulfills that role.

[0681] "Feedback information" refers to information provided by parents based on warnings issued by the system, and is used to improve the system.

[0682] An "analysis method" refers to an algorithm or method used to analyze communication information and detect unusual behavior.

[0683] "Encryption" is the process of transforming data to enhance security and protect communication information from unauthorized use.

[0684] A "portable information terminal" refers to a portable information processing device, such as a smartphone, that has the function of providing notifications to the user.

[0685] "Real-time" refers to processing data and providing information at a speed that is almost identical to real-world time.

[0686] In the system that implements this application, a terminal device collects communication information in real time and sends encrypted data to a server. The server decrypts the received encrypted data and analyzes it using a generative AI model. This determines whether or not risky behavior has occurred, and if a risk is detected, a notification is immediately sent to the parent or guardian.

[0687] The system uses mobile devices such as smartphones as hardware, and programming languages ​​such as Python as software. Scripts are used to collect data, including browser history and SNS usage metadata, and the Fernet library is used for encryption. On the server side, machine learning frameworks such as TensorFlow and PyTorch are used for anomaly detection.

[0688] For example, if a minor attempts to access an unauthorized website late at night, this activity could be immediately detected, and the parent or guardian could receive a notification via their smartphone. This notification would include a specific message such as, "An inappropriate website was accessed late at night. Please take action."

[0689] An example of a prompt message provided to the generating AI model would be: "Create what alert message Family Security Watch should send to parents when a minor accesses unauthorized content. Include details about the specific times and situations in which warnings should be issued."

[0690] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0691] Step 1:

[0692] The device monitors the user's online activity in real time. Inputs include URLs of visited websites and social media metadata. This data is collected and encrypted using an encryption library. The output is encrypted data in a secure state.

[0693] Step 2:

[0694] The terminal sends encrypted data to the server. The input is encrypted communication information, and the output is the data received by the server, in a state where it has been securely transferred to the server.

[0695] Step 3:

[0696] The server decrypts the received encrypted data. The input is encrypted data, and by using the encryption key to decrypt the data, the server obtains the original decrypted communication information as output.

[0697] Step 4:

[0698] The server analyzes the decoded data using a generative AI model. The input is decoded communication information, which is then compared to normal usage patterns to detect abnormal behavior. The output, if any risky behavior is detected, is the corresponding behavioral data.

[0699] Step 5:

[0700] The server sends a notification to the parent or guardian when risky behavior is detected. The input is data on the risky behavior, and the output is an alert message sent to the parent or guardian's mobile device as a notification.

[0701] Step 6:

[0702] The user (parent / guardian) takes appropriate action regarding their child based on the notification they receive. They also send feedback back to the server. The input includes information about the notified risk behavior and the parent / guardian's response, and the output is feedback information sent to the server.

[0703] Step 7:

[0704] The server analyzes user feedback and uses it to improve its analysis methods. User feedback is used as input, and by retraining the generated AI model with this feedback, it updates the anomaly detection model to produce a more accurate output.

[0705] 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.

[0706] This invention combines a system for monitoring the online activities of minors with an emotion engine that recognizes user emotions. This allows for evaluation of how online behavior relates to user emotions, enabling more advanced monitoring and alerts.

[0707] Data collection and emotion recognition

[0708] First, the device collects data related to the user's emotions along with their online activity. This data includes the content of text messages, typing speed, and tone of voice used, and is used to estimate the user's emotional state.

[0709] The server analyzes the received data and uses an emotion engine to determine the user's emotional state. The emotion engine is built using machine learning techniques and can identify emotions such as positive, negative, and neutral. For example, if a user frequently uses terms that express dissatisfaction or anger, the emotion engine will detect a negative emotion.

[0710] Anomaly detection and alert generation

[0711] The server not only detects abnormal behavior in normal communication data, but also incorporates emotional information determined by the emotion engine into its analysis. In particular, if negative emotions increase and dangerous behavior is detected at the same time, the risk score is raised. As a result, if the existing threshold is exceeded, a warning is generated.

[0712] The generated warnings will notify parents along with the emotional state of the user. For example, if an aggressive message is being sent while the user is expressing anxiety or anger, the warning will include an explanation of the emotional state along with a cautionary message.

[0713] Feedback and system optimization

[0714] Users can review the warning information they receive and, if necessary, take appropriate action such as providing guidance or imposing restrictions. They can also provide feedback on their evaluation of the emotion detection results and their experience using the system. The server analyzes this feedback and uses it to improve the accuracy of the emotion engine's recognition and the overall system performance.

[0715] As a concrete example, if a device detects that a user's social media posts suddenly become aggressive, and the emotion engine simultaneously detects strong negative emotions, the server will notify the parent or guardian, prompting them to take immediate action. In this way, the present invention is a system that, by combining emotion analysis, enables a deeper understanding of user activity and allows for appropriate support and monitoring.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The device collects communication data and sentiment-related data related to the user's online activities. Sentiment data includes metrics such as the content of text messages, voice tone, and typing speed. This data is encrypted to protect personal information.

[0719] Step 2:

[0720] The device transmits encrypted communication data and emotional data to a server via the internet. This communication occurs in real time or periodically.

[0721] Step 3:

[0722] The server decodes the received data and analyzes the user's emotional state using an emotion engine. The emotion engine uses machine learning algorithms to determine whether the emotion is positive, negative, or neutral.

[0723] Step 4:

[0724] The server applies a machine learning model to analyze the decrypted communication data and detect abnormal behavior. This model identifies anomalies that exceed a threshold by comparing them against known malicious behavior patterns.

[0725] Step 5:

[0726] The server integrates the results of the emotion engine analysis and the abnormal behavior analysis to perform a comprehensive risk assessment. In particular, if negative emotions and abnormal behavior are detected simultaneously, the risk score is increased, indicating a high-priority warning.

[0727] Step 6:

[0728] Based on the risk assessment, the server generates a detailed alert. The alert includes the user's emotional state, the nature of the misconduct, and recommended countermeasures.

[0729] Step 7:

[0730] The server sends generated warnings to users in real time. Users can receive the warnings and check the situation via their smartphones or PCs.

[0731] Step 8:

[0732] Users take prompt action based on the warning message and provide feedback to the server. This feedback is used to improve the system's accuracy and enhance the sentiment engine.

[0733] In this way, the system, which incorporates an emotion engine, can achieve advanced monitoring based on the user's emotional state and provide more appropriate warnings and countermeasures.

[0734] (Example 2)

[0735] 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".

[0736] The increasing prevalence of dangerous behaviors and inappropriate emotional states in minors' online activities highlights the growing need for parents and administrators to properly monitor and address these issues promptly. While traditional systems have focused on behavioral monitoring, there is a growing demand for more sophisticated risk assessments that take into account users' emotional states.

[0737] 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.

[0738] In this invention, the server includes means for collecting information from user devices, means for analyzing the collected information and determining the emotional state using machine learning techniques, and means for generating a warning based on the determined emotional state and the detection results of abnormal behavior, and notifying the administrator. This makes it possible to comprehensively monitor both user activity and emotional state and provide the administrator with appropriate warnings before dangerous behavior occurs.

[0739] "User equipment" refers to all electronic devices used by users to conduct online activities, and includes terminals that enable data collection.

[0740] "Collecting information" refers to the act of gathering data about user activity, such as text, typing speed, and tone of voice, from the user's device.

[0741] "Machine learning technology" refers to techniques that enable computers to process large amounts of data and automatically learn patterns and rules.

[0742] "Emotional state" refers to information that represents psychological states such as joy, anger, and sadness, which is analyzed from the user's text data.

[0743] A "server" is a computer system used to process and analyze information on a network, and is a device that performs data analysis and notification management.

[0744] "Generating warnings and notifying administrators" refers to the process of creating an alarm when an anomaly is detected and communicating that information to the administrator.

[0745] This invention is a system for monitoring the online activities of minors and analyzing the emotional state of users. The system primarily functions through data exchange and analysis between terminals and servers.

[0746] The terminal is an electronic device used by the user, and it collects information generated through communication applications and social networking services (SNS). Specifically, it collects data such as the content of text messages, typing speed, and the tone of the words used. The terminal is responsible for monitoring this information in real time and transmitting the data to the server.

[0747] The server receives information sent from the terminal and analyzes the collected data. This analysis uses a machine learning tool called an emotion engine. This emotion engine analyzes the user's text data and classifies their emotional state as positive, negative, or neutral. For example, if a user frequently uses words expressing "anger" or "sadness," the engine can determine that this is a negative emotion.

[0748] The server detects deviations from the user's normal behavior patterns and generates warnings as needed. These warnings are sent to administrators (such as parents) and include detailed analysis of the user's emotional state, enabling administrators to address problems early.

[0749] The system can also improve analysis accuracy through a feedback loop. The sentiment engine and anomaly detection algorithms are continuously improved by users and administrators providing feedback on the accuracy of the warnings.

[0750] As a concrete example, if a user sends a message containing inappropriate content during a social networking exchange, and the sentiment engine detects an increase in negative emotions, the server immediately generates a warning and notifies the administrator. In this way, the system functions to keep minors' online activities safe.

[0751] Examples of input prompts for a generated AI model include: "Explain how you monitor minors' online activities and how the emotion engine evaluates their emotional state. Also, include specific use cases." These prompts serve as a tool to facilitate understanding of the system's implementation.

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] The device collects information through the user's online activities. Input includes text messages sent and received via social networking services and chat applications, typing speed, and tone of voice used. This data is collected in real time, compiled into communication packets, and prepared for transmission to the server.

[0755] Step 2:

[0756] The server receives data packets from the terminal. The input includes communication data sent from the terminal. The server prepares this data for analysis and supplies it to the emotion engine. During this process, data format conversion and preprocessing (e.g., string normalization) are performed.

[0757] Step 3:

[0758] The emotion engine on the server receives text data to be analyzed as input. The emotion engine uses machine learning algorithms to analyze the emotional state of the text. Specifically, the text is processed through a natural language processing module to calculate emotional scores such as positive, negative, and neutral. This output is generated as an emotional state report.

[0759] Step 4:

[0760] The server detects abnormal behavior based on the output of the emotion engine. Inputs include an emotional state report and a database of normal behavioral patterns for comparison. The server uses this to assess whether the user's current emotional state and behavior deviate from the norm. If an abnormality is detected, a risk score is calculated, triggering a warning.

[0761] Step 5:

[0762] The server generates an alert based on the generated risk score and notifies the administrator. The input includes the results of abnormal behavior detection and the risk score. The alert message includes a diagnosis of the emotional state and recommended administrator actions. This alert is sent to the administrator's terminal.

[0763] Step 6:

[0764] The user receives warning notifications from the server and provides feedback as needed. As input, the user receives warning messages and analysis results. Through feedback, the user sends information to the server regarding the effectiveness of the warnings and the accuracy of the analysis. This output is used to improve the server's analysis methods.

[0765] (Application Example 2)

[0766] 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".

[0767] There is a need to effectively monitor the misconduct and emotional state of minors in online environments and to warn parents at the appropriate time in order to protect their safety. However, conventional systems have the challenge of being unable to adequately recognize emotional states and making it difficult to monitor emotional changes in conjunction with behavior.

[0768] 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.

[0769] In this invention, the server includes means for acquiring communication data and emotion-related information from a user terminal, means for analyzing the acquired communication data and emotion information to detect misconduct and emotional states, and means for generating warnings based on the detected misconduct and emotional states and notifying parents. This makes it possible to detect misconduct and emotional changes in minors' online activities in real time and warn parents at an appropriate time.

[0770] A "user terminal" is an information processing device used by an individual to conduct online activities, and is capable of sending and receiving data.

[0771] "Communication data" refers to information sent and received via a user's terminal, including messages and internet browsing history.

[0772] "Emotion-related information" refers to data necessary to estimate the user's emotional state, including typing speed and tone of voice used.

[0773] "Misconduct" refers to unauthorized or unsafe actions, including inappropriate remarks or behavior online.

[0774] "Emotional state" refers to the tendencies of an individual's inner emotions, and is classified as positive, negative, or neutral.

[0775] A "warning" is a notification generated when misconduct or negative emotional states are detected, and it includes content that prompts parents to take notice.

[0776] "Feedback data" refers to information provided by users or guardians, including analysis results and feedback on the system.

[0777] "Analysis methods" refer to methods for evaluating fraudulent behavior and emotional states based on acquired data, and include algorithms and machine learning techniques.

[0778] An "emotion recognition method" is a technique for analyzing and recognizing a user's emotional state, and includes processes involving data analysis and machine learning.

[0779] An "information processing device" is a device used to collect, process, and output data, and includes computers used in homes.

[0780] This invention is a system for monitoring the online activities of minors and evaluating their emotional state. The server acquires communication data and emotion-related information from the user's terminal. This includes the user's online activities, message sending history, typing speed, and tone of voice used.

[0781] The device collects this data in real time and sends it to the server. The server analyzes the data and uses an emotion engine to determine the user's emotional state. The emotion engine, which utilizes machine learning technology, identifies emotions such as positive, negative, and neutral, and generates a corresponding warning if negative emotions are particularly heightened.

[0782] For example, if a user frequently makes aggressive remarks while playing online games and a negative emotional state is detected, the server will quickly generate a warning and send a verbal notification to the parent or guardian via a home information processing device. This system runs on a small computer such as a Raspberry Pi using a Python program.

[0783] Furthermore, feedback data provided by users and guardians is used to improve the accuracy of emotion recognition and to refine the analysis methods. This process continuously optimizes the system's performance, resulting in more accurate monitoring and notifications.

[0784] Further improvements can be made using a generative AI model through prompts such as: "Please explain how the robot can detect emotions from a minor's online activities, what kind of notification it will send if a negative situation is detected, and how it will warn parents."

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The device collects communication data and sentiment-related information from the user's online activity. Specifically, input includes messages sent by the user, text communications with each other, typing speed, and tone of voice used. This input data is temporarily stored on the device and then sent to the server for subsequent processing.

[0788] Step 2:

[0789] The server receives data sent from the terminal and begins analysis. Using an emotion engine, it identifies the user's emotional state from the input communication data. Emotion labels such as positive, negative, and neutral are generated as output. Specifically, machine learning techniques are used to extract features and perform pattern matching and classification.

[0790] Step 3:

[0791] Based on the analysis results, the server evaluates whether the user's behavior is fraudulent and whether their emotional state is negative. In particular, if negative emotions and fraudulent behavior are detected simultaneously, a risk score is calculated, and a warning is generated if it exceeds a threshold. Thresholding and scoring models are applied in this step.

[0792] Step 4:

[0793] The generated alerts are sent from the server to the home information processing unit. The specific alert message includes a summary of the detected emotional state or behavior, and, if necessary, recommended actions. The information processing unit verbally notifies the parent or guardian of this message to help them take prompt action.

[0794] Step 5:

[0795] Feedback from users and guardians is sent to the server. The server uses this feedback to continuously improve its analysis methods and sentiment recognition methods. Specifically, feedback information is received as input, and through algorithm adjustments and model retraining, it leads to improved system accuracy as output.

[0796] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0797] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0798] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0799] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0800] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0801] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0802] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0803] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0804] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0805] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0806] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0807] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0808] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0809] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0810] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0811] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0812] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0813] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0814] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0815] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0816] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0817] The following is further disclosed regarding the embodiments described above.

[0818] (Claim 1)

[0819] A means of obtaining communication data from the user's terminal,

[0820] A means of detecting fraudulent activity by analyzing acquired communication data,

[0821] A means of generating warnings and notifying parents based on detected misconduct,

[0822] A means of correcting the analysis method using feedback data,

[0823] A system that includes means for presenting analysis results and recommended actions.

[0824] (Claim 2)

[0825] The system according to claim 1, which further detects fraudulent behavior by storing behavioral history based on communication data and comparing it with past behavioral patterns.

[0826] (Claim 3)

[0827] The system according to claim 1, which prioritizes the detection of fraudulent activity at night by adjusting the analysis threshold according to the time of day.

[0828] "Example 1"

[0829] (Claim 1)

[0830] Means for obtaining information about user operations,

[0831] A means of analyzing acquired information using a generative AI model to detect abnormal behavior,

[0832] A means of generating and providing warnings to guardians based on the detection of abnormal behavior,

[0833] A means of improving the analysis method by utilizing evaluation information from users,

[0834] A system that includes means for displaying the results of an analysis process and recommended actions.

[0835] (Claim 2)

[0836] The system according to claim 1, further detecting abnormal behavior by saving a history based on information about the operation and comparing it with previous behavior patterns.

[0837] (Claim 3)

[0838] The system according to claim 1, which adjusts the analysis criteria according to the time of day and prioritizes the detection of abnormal behavior during a specific time period.

[0839] "Application Example 1"

[0840] (Claim 1)

[0841] A means for collecting communication information from user equipment,

[0842] A means of analyzing collected communication information to detect risky behavior,

[0843] A means of generating warnings and notifying parents based on detected risky behaviors,

[0844] A means of correcting the analysis method using feedback information,

[0845] A means of displaying analysis results and recommended actions,

[0846] A means of encrypting the collected data and sending it to an external server,

[0847] A means of automatically issuing risk behavior notifications on mobile information terminals such as smartphones,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, which further detects risky behaviors by storing behavioral history based on communication information and comparing it with past behavioral patterns.

[0851] (Claim 3)

[0852] The system according to claim 1, which prioritizes the detection of nighttime risk behavior by adjusting the analysis threshold according to the time of day.

[0853] "Example 2 of combining an emotion engine"

[0854] (Claim 1)

[0855] Means for collecting information from user devices,

[0856] A means of analyzing collected information and determining emotional states using machine learning techniques,

[0857] A means of generating a warning and notifying the administrator based on the determined emotional state and the detection results of abnormal behavior,

[0858] A means of improving the analysis algorithm using feedback data,

[0859] A system that includes means for providing analysis results and recommended actions.

[0860] (Claim 2)

[0861] The system according to claim 1, which further detects abnormal behavior by saving an information-based activity history and comparing it with past patterns.

[0862] (Claim 3)

[0863] The system according to claim 1, which prioritizes the detection of abnormal behavior during specific time periods by adjusting the analysis criteria according to the time.

[0864] "Application example 2 when combining with an emotional engine"

[0865] (Claim 1)

[0866] A means of obtaining communication data and emotion-related information from a user's terminal,

[0867] A means for detecting fraudulent behavior and emotional states by analyzing acquired communication data and emotional information,

[0868] A means of generating warnings and notifying parents based on detected misconduct and emotional states,

[0869] A means for correcting analysis methods and emotion recognition methods using feedback data,

[0870] A system that presents analysis results and recommended actions, and includes means of verbally communicating them to parents via an information processing device within the home.

[0871] (Claim 2)

[0872] The system according to claim 1, further detecting misconduct and negative emotions by storing behavioral history based on communication data and emotional information and comparing it with past behavioral patterns and emotional tendencies.

[0873] (Claim 3)

[0874] The system according to claim 1, which prioritizes the detection of nighttime misconduct and negative emotions by adjusting the analysis and emotion recognition thresholds according to the time of day. [Explanation of symbols]

[0875] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining communication data from the user's terminal, A means of detecting fraudulent activity by analyzing acquired communication data, A means of generating warnings and notifying parents based on detected misconduct, A means of correcting the analysis method using feedback data, A system that includes means for presenting analysis results and recommended actions.

2. The system according to claim 1, which further detects fraudulent behavior by saving a history of actions based on communication data and comparing it with past behavior patterns.

3. The system according to claim 1, which prioritizes the detection of fraudulent activity at night by adjusting the analysis threshold according to the time of day.

Images