system

Abstract

Provide a system. The method comprises: a means for a user terminal to collect user behavior data via the Internet; A means for comparing the behavioral data received by the server with a database containing past incident / accident / crime data; A means for the server to detect potential risks based on user behavior data and perform risk assessment; The server sends the risk assessment results to the user's terminal and notifies the user. A system including:

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, crimes and damages via the Internet have become more diverse and widespread, increasing the risk that users may unknowingly become involved in crimes such as fraud and phishing. These criminal acts cause economic and psychological harm to many people, and there is a need for methods to prevent them. However, current security software and filtering systems are often unable to adequately manage these risks. This leaves users with no means to safely use the Internet. [Means for solving the problem]

[0005] The present invention provides a system in which a user terminal collects user behavioral data via the Internet, and a server compares the received behavioral data with a database containing past incident, accident, and crime data. Furthermore, the server detects potential risks based on the user's behavioral data, performs a risk assessment, and notifies the user by sending the results to the user's terminal. This allows users to receive specific advice and warnings for safe Internet use, thereby reducing the risk of becoming involved in crime. Furthermore, data analysis using machine learning algorithms enables advanced risk detection and assessment, improving detection accuracy. Furthermore, by improving the system based on user feedback, it is possible to continuously enhance its functionality.

[0006] A "user terminal" is a device that has the function of collecting user behavior data via the Internet and transmitting it to a server.

[0007] A "server" is a device or system that analyzes behavioral data sent from user devices and compares it with past incident / accident / crime data to perform risk assessment.

[0008] "Behavioral data" is information about activities that users perform on the Internet, such as searching, posting, chatting, and receiving emails.

[0009] "Past incident, accident, and crime data" refers to the contents of a database that includes records and information on various incidents, accidents, and crimes that have occurred in the past.

[0010] "Database" means an information management system used by the server to hold past incident / accident / crime data and provide appropriate data in response to queries.

[0011] "Risk assessment" is the process of detecting potential risks based on user behavioral data and assessing the level of those risks.

[0012] A "machine learning algorithm" is a computational method for learning patterns from past data and making predictions and classifications for future data.

[0013] "Feedback" refers to information that results from the user's actual actions based on notifications and advice from the system. [Brief explanation of the drawings]

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

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

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

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

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

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks at an early stage. This system is composed of user terminals, a server, and a database, and these elements work together to ensure users' safe use of the Internet.

[0036] User behavior monitoring

[0037] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[0038] Data analysis

[0039] The server decodes the behavioral data it receives and compares it with a database of past incidents, accidents, and crimes. The server then analyzes the data using machine learning algorithms and rule-based systems to calculate a risk score. For example, the server may compare the keyword "large euro investment" with past fraud data and determine that it poses a high risk.

[0040] Risk Assessment

[0041] The server then performs a detailed assessment of the detected risk. This is the process of estimating the specific crime (e.g., investment fraud) and the potential amount of damage (e.g., 1 million yen) and determining the risk level. As a result of the assessment, a specific warning message is generated, such as "This search query carries a risk of fraud. Be cautious when investing."

[0042] User Notification

[0043] The server sends the risk assessment results to the user's device. The device notifies the user of the received assessment results and displays a warning in the form of a pop-up or alert. For example, the user might see a message saying, "This search query carries a risk associated with fraud. Be cautious when investing." The user can then review the warning and decide whether to reconsider their investment.

[0044] Gathering feedback

[0045] Users take action based on the warnings and advice provided by the system. For example, if a user avoids an investment, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[0046] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that monitor and analyze user behavior data, perform risk assessment, and notify users. The specific processing steps will be described later.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[0050] Step 2:

[0051] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server.

[0052] Step 3:

[0053] The server decodes the received behavioral data and places it in a processing queue for analysis.

[0054] Step 4:

[0055] The server launches an analysis engine and compares the behavioral data with a database containing data on past incidents, accidents, and crimes.

[0056] Step 5:

[0057] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data.

[0058] Step 6:

[0059] A detailed assessment is carried out for the risk detected on the server. Specifically, the potential crime and potential damage amount are calculated, and the risk level is assessed.

[0060] Step 7:

[0061] The server generates a warning message and workarounds for the user based on the risk assessment results.

[0062] Step 8:

[0063] The server transmits the generated evaluation results and warning messages to the user terminal.

[0064] Step 9:

[0065] The device will notify the user of the evaluation results received and display a warning in the form of a pop-up or alert.

[0066] Step 10:

[0067] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[0068] Step 11:

[0069] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[0070] Step 12:

[0071] The server receives and analyzes user feedback and reflects it in system improvements, a process that continuously improves the system's detection accuracy and risk assessment algorithms.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] In the current Internet usage environment, there are concerns that users may unintentionally engage in behavior that poses a high risk of crime. Furthermore, existing crime prevention systems have difficulty monitoring and analyzing user behavior in real time and detecting risks early. Furthermore, there is a lack of mechanisms for effectively collecting feedback based on user behavior to improve the accuracy of the system. As a result, the safety of Internet use remains insufficient.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for the user terminal to capture user behavioral data in real time via the Internet, encrypt it, and send it to the server, means for the server to decrypt the received encrypted behavioral data and compare it with a database containing past incident, accident, and crime data, means for the server to calculate a risk score based on the user behavioral data using a machine learning algorithm or a rule-based system and perform a risk assessment, means for the server to generate a warning message based on the risk assessment result and send it to the user terminal to notify the user, means for the user terminal to capture feedback regarding the user's behavior, encrypt it, and send it to the server, and means for the server to analyze the feedback received and use it to improve the system. This makes it possible to monitor and analyze user behavioral data in real time, detect and notify potential risks early, and improve the accuracy of the system based on the feedback.

[0077] "User terminal" refers to an electronic device that allows a user to perform operations or take actions via the Internet, including personal computers, smartphones, tablets, etc.

[0078] "Behavioral data" refers to data related to specific operations and activities that users perform on the Internet, such as searching, posting, chatting, and receiving emails.

[0079] A "server" is a central computer system that stores and processes data over a network, and analyzes and records data sent from user terminals.

[0080] "Encryption" is a security technology that converts data into a format that cannot be deciphered by third parties, and includes algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman).

[0081] A "database" is an information management system for storing and managing data on past incidents, accidents, and crimes, and it allows for efficient searching and matching of large amounts of information.

[0082] A "machine learning algorithm" is a program that automatically learns patterns and rules from data and makes predictions and classifications for new data, and includes decision trees, random forests, neural networks, etc.

[0083] A "rule-based system" is a system that analyzes and evaluates data based on pre-set rules and conditions, and makes inferences and judgments according to fixed rules.

[0084] A "risk score" is a number that indicates the degree of risk calculated based on a user's behavioral data, and is used to evaluate the level of criminal risk.

[0085] A "warning message" is a message that is generated based on the risk assessment results and is used to alert the user, and includes specific risk details and advice.

[0086] "Feedback" refers to information about actions taken by users in response to warnings and advice provided by the system, and is data used to improve and optimize the system.

[0087] The present invention is a system for strengthening crime prevention measures by monitoring users' Internet activity and detecting crime risks at an early stage. Specific procedures for implementing the present invention, as well as the hardware and software used, are described in detail below.

[0088] First, the user's device captures user behavior data in real time via the internet, using browser extensions or dedicated application programs. For example, when a user searches for "large euro investment," the search query is captured.

[0089] The captured behavioral data is then encrypted by the device using encryption techniques such as AES (Advanced Encryption Standard) and sent to a server using the HTTPS protocol.

[0090] The server then decrypts the encrypted data, again using AES, and compares it with a database containing past incident and crime data. This database could be an SQL database or a NoSQL database, for example.

[0091] The server uses machine learning algorithms and rule-based systems to further analyze the decrypted data. Specifically, it uses libraries such as Scikit-learn and TENSORFLOW®. Machine learning algorithms such as random forests and neural networks are applied. A risk score is calculated based on these algorithms.

[0092] The server then performs a specific risk assessment based on the risk score, including a specific crime (e.g., fraud) and potential damage amount (e.g., 1 million yen). Once the risk assessment is complete, a warning message is generated. For example, a specific message such as "This search query carries a risk of fraud. Be cautious when investing." is created.

[0093] The generated warning message is sent from the server to the user's device, and the device notifies the user. The notification is in the form of a pop-up or alert. The user's screen will display the message, "This search query carries a risk of fraud. Please invest with caution."

[0094] Any actions the user takes based on the system's warnings and advice are again captured by the device. The device encrypts this behavioral history and sends it to the server. The server receives, decrypts, and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. For example, it adds new user behavior patterns to the learning data and retrains the model.

[0095] Through these steps, the system can consistently monitor and analyze user behavior data from start to finish, quickly detecting and notifying users of risks. This process involves a series of processing interactions: capturing, encrypting, decrypting, analyzing, and notifying users of user behavior data.

[0096] Example prompts to be input to the generative AI model:

[0097] "Please conduct a risk assessment of the user's online search for 'high dollar euro investment' and inform the user of the results. Please also explain what data processing and algorithms you use."

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1:

[0100] When a user performs online activities such as searching, posting, chatting, or receiving emails on the Internet, this behavioral data is captured in real time by the user's device. Specifically, the behavioral data is acquired by browser extensions or dedicated applications. The input is the user's specific Internet activity, and the output is the captured behavioral data.

[0101] Step 2:

[0102] The captured behavioral data is encrypted by the device. Here, AES (Advanced Encryption Standard) is used. This process is performed to protect the data from being read by third parties. The input is the captured behavioral data, and the output is the encrypted data. Specifically, the device encrypts the data using the AES algorithm.

[0103] Step 3:

[0104] The encrypted data is sent to the server using the HTTPS protocol, which ensures data confidentiality and integrity. The input is the encrypted behavioral data, and the output is the data sent to the server. Specifically, the device establishes an HTTPS connection and sends the data.

[0105] Step 4:

[0106] The server decrypts the received encrypted data. AES is used again for decryption, which returns the data to the original behavioral data. The input is the encrypted data, and the output is the decrypted data. Specifically, the server decrypts the data using the AES algorithm.

[0107] Step 5:

[0108] The server compares the decoded data with a database containing data on past incidents, accidents, and crimes. The server analyzes this data and calculates a risk score. A machine learning algorithm (e.g., random forest or neural network) is used for the analysis. The input is the decoded behavioral data, and the output is a risk score. Specifically, the server inputs the data into a machine learning model and obtains a risk score.

[0109] Step 6:

[0110] The server performs a specific risk assessment based on the risk score, including the name of the crime and the potential damage amount. The server generates a warning message based on the risk assessment result. The input is the risk score and the output is the warning message. Specifically, the server classifies the risk based on the assessment criteria and creates an appropriate message.

[0111] Step 7:

[0112] The generated warning message is sent from the server to the user terminal. The terminal notifies the user of this message. The input is the warning message, and the output is the notification to the user. Specifically, the terminal displays the message in the form of a popup or alert.

[0113] Step 8:

[0114] The user takes action based on the system's warnings and advice. For example, if the user avoids an investment, the device captures the user's behavioral history. The input is the user's behavior, and the output is the captured behavioral history. Specifically, the device captures the behavioral data again.

[0115] Step 9:

[0116] The captured behavioral history is encrypted by the device and sent back to the server. The server decrypts and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. The input is the encrypted feedback data, and the output is an improved risk detection model. Specifically, the server uses the new data for learning and retrains the model.

[0117] (Application example 1)

[0118] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0119] User behavior on the Internet is becoming more diverse, and this includes criminal risks such as investment fraud and phishing. However, it is difficult for users to identify these risks themselves and respond appropriately. Therefore, there is a need for a system that can monitor users' online activities in real time, detect potential criminal risks early, and warn users. In particular, there is a need for a real-time warning system that uses smartphones.

[0120] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0121] In this invention, the server includes: a means for a user terminal to collect user behavioral data via the Internet; a means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; a means for the server to detect potential risks based on the user behavioral data and perform a risk assessment; a means for the server to send the risk assessment results to the user terminal and notify the user; and a means for the user terminal to display a warning message to the user based on the risk assessment results. This makes it possible to detect crime risks in real time while the user is using the Internet and to promptly display a warning.

[0122] A "user terminal" is a device such as a smartphone or computer that a user uses to access the Internet.

[0123] "Behavioral data" is data about activities you perform on the Internet, such as searching, browsing, chatting, and sending emails.

[0124] A "server" is a computer system that analyzes behavioral data received from user terminals and evaluates risks.

[0125] A "database" is a collection of information that stores and manages data on past incidents, accidents, and crimes, and is used by the server to collate the data.

[0126] "Potential risks" are risks of crime, fraud, and other potential future occurrences that are estimated based on user behavioral data.

[0127] "Risk assessment" is the process of analyzing user behavioral data and scoring the likelihood of a crime occurring based on that data.

[0128] A "warning message" is a specific warning message that is sent to the user based on the results of a risk assessment.

[0129] To implement the present invention, it is necessary to construct a system including a user terminal, a server, and a database.

[0130] First, the user's device must have a means of collecting user behavior data in real time via the internet. For example, if a user searches for "high dollar euro investment," the search query is captured. Data is also collected when the user browses the web, chats, or sends and receives emails. This data is encrypted and sent to a server.

[0131] The server decodes the received behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server uses Python and the requests library to collate and analyze the data. Specifically, it uses a machine learning algorithm to compare user behavior data with crime data and score potential risks. The server then performs a risk assessment based on the risk score and generates appropriate warning messages.

[0132] The warning message generated as a result of the risk assessment is sent back to the user's device and notified to the user. The user's device will display the warning message in the form of a pop-up or alert to inform the user of the risk. For example, a specific warning such as "This search query has a risk related to fraud. Please be cautious when investing" may be displayed.

[0133] Additionally, user behavioral feedback is also important. When a user takes action based on the warnings and advice provided by the system, the user's behavioral history is also captured by the user's device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[0134] Examples:

[0135] For example, if a user searches for the keyword "large euro investment," this search query is sent to the server. The server compares this with past fraud data and, if it determines that there is a high risk, returns a warning message to the user saying, "This search query carries a risk of fraud. Be cautious before investing." The user can acknowledge this warning and reconsider their investment.

[0136] Example prompts to input to the generative AI model:

[0137] Generate a program code that determines whether the search keyword "large euro investment" poses a risk of crime, and if so, display a warning message to the user.

[0138] This specific example and example prompt sentences will allow a clearer understanding of the embodiments of the invention.

[0139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0140] Step 1:

[0141] The user's device collects user behavior data via the Internet. Specifically, it captures data when the user conducts web searches, sends chat messages, or receives emails. For example, a search query such as "large euro investment" is received as input. The device processes this search query by encrypting it and outputs the encrypted data.

[0142] Step 2:

[0143] The user device sends the collected behavioral data to the server. The encrypted search query is input and sent as a POST request to the server's specified API endpoint. As a result, the server receives this data.

[0144] Step 3:

[0145] The server decrypts the behavioral data it receives. The input is the encrypted search query, which the server converts back to plain text using a decryption algorithm. The output is the decrypted search query. For example, "large euro investment" would be the decrypted search query.

[0146] Step 4:

[0147] The server compares the decrypted behavioral data with a database containing data on past incidents, accidents, and crimes. The decrypted search query is input, and the server compares the query with the data in the database. The database contains data on past fraud cases, etc., and checks for a match. The result of the comparison is a risk score. For example, if a match is found with a fraud-related query, a high risk score is obtained.

[0148] Step 5:

[0149] The server performs a risk assessment based on the risk score and generates a warning message. The risk score is the input, and the server determines the level and content of the warning depending on the score. For example, if the risk score is high, a warning message such as "This search query has a risk related to fraud. Be careful when investing" is generated. The warning message is the output.

[0150] Step 6:

[0151] The server sends the generated warning message to the user terminal. The warning message is the input, and is sent as an API request to the user terminal. The user terminal receives this message.

[0152] Step 7:

[0153] The user's device will notify the user of the warning message it has received. The warning message will be input, and the device will display it to the user in the form of a pop-up or alert. This allows the user to check the content of the notification. For example, a message such as "This search query has a risk related to fraud. Please be careful when investing" will be displayed.

[0154] Step 8:

[0155] The user takes action based on the warnings and advice provided by the system. After receiving the warning message, the user may take action, such as reconsidering an investment. This behavioral feedback is captured by the user's device. Behavioral data is input and output as new behavioral data.

[0156] Step 9:

[0157] The user device sends feedback data to the server. New behavioral data is input and sent to the server. The server receives this data.

[0158] Step 10:

[0159] The server analyzes the feedback data and uses it to improve the system. New behavioral data is input and analyzed by the server. The resulting data is used to continuously improve the system and output to improve the accuracy of risk detection.

[0160] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0161] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. This system is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to ensure safe internet use for users.

[0162] User behavior monitoring

[0163] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[0164] The role of the emotional engine

[0165] At the server, the behavioral data is received, decoded, and placed in a processing queue for analysis. Meanwhile, the emotion engine analyzes the user's behavioral data to recognize the user's emotional state. For example, if the user performs an action that indicates intense emotion, the emotion engine will recognize this as "anger."

[0166] Data analysis

[0167] The server combines the received behavioral data with the emotion data from the emotion engine for analysis. The analysis engine compares the behavioral data with a database of past incidents, accidents, and crimes to calculate a risk score. For example, the server compares the keyword "large euro investment" with past fraud data and determines it to be high risk.

[0168] Risk Assessment and Sentiment Analysis

[0169] The server performs a detailed assessment based on the detected risk and the user's emotional state. Specifically, it estimates the likely crime (e.g., investment fraud) and potential damage amount (e.g., 1 million yen) and determines the risk level. The analysis results of the emotion engine are also reflected in the risk assessment, and a risk message is generated taking into account the user's emotional state. As a result of the assessment, a specific warning message such as "This search query carries a risk related to fraud. Be cautious when investing" is generated.

[0170] User Notification

[0171] The server sends the risk assessment results and emotion analysis results to the user's device. The device then notifies the user of the received assessment results and emotion data, displaying a warning in the form of a pop-up or alert. For example, a message might be displayed to the user saying, "This search query carries a risk associated with fraud. Be cautious when investing," along with advice on how to respond appropriately based on the emotion. If the user is expressing anger, psychological advice on how to calm them down is also provided.

[0172] Gathering feedback

[0173] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[0174] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that simultaneously monitor and analyze user behavioral data and emotional data, evaluate risks, and notify users. Specific processing steps will be described later.

[0175] The processing flow will be explained below.

[0176] Step 1:

[0177] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[0178] Step 2:

[0179] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server, along with emotional data such as the user's facial expressions, typing speed, and language used.

[0180] Step 3:

[0181] The server decodes the received behavioral and emotional data and places it in a processing queue for analysis.

[0182] Step 4:

[0183] The emotion engine analyzes the user's behavioral data, facial expression data, and other emotional indicators to recognize the user's emotional state (e.g., anger, sadness, joy, etc.).

[0184] Step 5:

[0185] The server inputs the behavioral data into an analysis engine and compares it with a database containing data on past incidents, accidents, and crimes.

[0186] Step 6:

[0187] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data. For example, the keyword "large euro investment" is considered high risk.

[0188] Step 7:

[0189] The server performs a detailed risk assessment of the detected risk, taking into account the user's emotional state. For example, if there is a possibility of fraud and the emotional engine recognizes "anxiety," the server will raise the risk level.

[0190] Step 8:

[0191] The server generates specific warning messages and advice on how to avoid the risk based on the risk assessment and sentiment analysis results. For example, it generates a message saying, "This search query carries a high risk of fraud. If you are concerned, please consult a professional."

[0192] Step 9:

[0193] The server transmits the generated evaluation results and warning messages to the user terminal.

[0194] Step 10:

[0195] The device will notify the user of the evaluation results and sentiment data it has received and display a warning in the form of a pop-up or alert, such as "This search query carries a risk of fraud. Please be cautious with your investments. Please refer to this link for any concerns you may have."

[0196] Step 11:

[0197] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[0198] Step 12:

[0199] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[0200] Step 13:

[0201] The server receives and analyzes user behavioral feedback and reflects it in system improvements. This process continuously improves the accuracy of the system's risk detection and sentiment analysis.

[0202] Example 2

[0203] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0204] Criminal activities on the Internet are becoming more sophisticated every day, threatening users' safety. Online fraud and cybercrime, in particular, can have serious consequences for victims. Therefore, there is a need for an effective system that can monitor users' online activities and detect potential crime risks early. In addition, there is a need for a system that can analyze users' emotional state and provide appropriate risk assessments to provide more effective crime prevention measures.

[0205] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0206] In this invention, the server includes means for encrypting behavioral data captured by the user terminal and transmitting it to the server, means for the server to decrypt the behavioral data received and place it in a processing queue, means for the server to compare the behavioral data received with a database containing past incident / accident / crime data, means for an emotion engine to analyze the user's behavioral data and recognize the user's emotional state, means for the server to detect potential risks based on the user's behavioral data and emotional data and perform a risk assessment, and means for the server to transmit the risk assessment results and the user's emotional state to the user terminal and notify the user. This makes it possible to detect criminal risks in the user's online activities early and issue appropriate warnings.

[0207] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to access the Internet.

[0208] "Behavioral data" is information about the activities you perform online, such as searching, chatting, posting, and receiving emails.

[0209] "AES encryption" is a method of encrypting data using the Advanced Encryption Standard.

[0210] A "server" is a computer system that receives data from user terminals via a network, analyzes it, compares it with a database, and notifies the user.

[0211] A "processing queue" is a data structure that temporarily stores data waiting to be processed on a server.

[0212] A "database" is a system that systematically accumulates and manages data related to past incidents, accidents, and crimes.

[0213] An "emotion engine" is a combination of algorithms and software that analyzes user behavioral data and recognizes the user's emotional state.

[0214] "Emotional Data" is information about the user's emotional state analyzed by the emotion engine.

[0215] A "risk score" is a number that represents the degree of potential risk, calculated based on a user's behavioral and emotional data.

[0216] "Risk assessment" is the process of using risk scores and other analytical results to determine how risky a particular action is.

[0217] A "warning message" is a message containing a warning or advice that is sent to the user based on the results of a risk assessment.

[0218] The system of the present invention is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to enable users to engage in safe online activities.

[0219] User behavior monitoring

[0220] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time and encrypts it using AES encryption. The encrypted data is then sent to the server. For example, if a user enters the search query "large euro investment," the search query is captured by the device, encrypted, and sent to the server.

[0221] Receiving and Decrypting Data

[0222] The server receives the encrypted behavioral data from the user terminal, decrypts the received data using AES encryption, and places it in the processing queue. The server then removes the data from the processing queue.

[0223] Analysis by emotion engine

[0224] The server passes the extracted behavioral data to the emotion engine, which then analyzes the user's behavioral data to recognize the user's emotional state. For example, if a user frequently uses emotional words, the emotion engine will recognize this as "anger."

[0225] Risk Analysis

[0226] The server combines the emotional data received from the emotion engine with the behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server calculates a risk score based on the user's behavior and emotional state, and performs a risk assessment. This risk score indicates the potential risk level of the user's online behavior. For example, the keyword "large euro investment" matches past fraud data and is deemed high risk.

[0227] Risk assessment and warning message generation

[0228] The server then performs a specific risk assessment based on the calculated risk score and emotional state and generates a warning message, such as "This search query carries a risk associated with fraud. Be cautious when investing."

[0229] User Notification

[0230] The generated risk assessment results and sentiment data are sent from the server to the user's device, which then notifies the user in real time. The device then displays a message to the user in the form of a pop-up or alert. For example, a warning message such as "This search query carries a risk associated with fraud. Please invest with caution."

[0231] Gathering feedback

[0232] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured again by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[0233] Prompt Sentence Examples

[0234] Analyze user search history for "large euro investment" to calculate crime risk score and perform sentiment analysis.

[0235] "Analyze the relationship between the words used by users in chat and their emotions, and generate warning messages based on that."

[0236] As described above, the system of the present invention can simultaneously monitor and analyze user behavioral data and emotional data, perform risk assessment, and notify users, thereby reducing the risk of crime on the Internet. The specific processing steps will be described in detail below.

[0237] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0238] Step 1:

[0239] Users perform activities online such as searching, writing, chatting, and receiving emails.

[0240] Input: User behavior (e.g., search query "high dollar euro investment")

[0241] What happens: A user opens a web browser, enters specific keywords into the search bar, and performs a search.

[0242] Step 2:

[0243] The device captures user behavior data in real time and encrypts the captured data using the AES encryption method.

[0244] Input: User behavior data

[0245] Data processing: Capture and AES encryption of behavioral data

[0246] What it does: The device captures the user's search query and encodes the data using AES encryption.

[0247] Output: Encrypted behavioral data

[0248] Step 3:

[0249] The device transmits the encrypted behavioral data to the server.

[0250] Input: Encrypted behavioral data

[0251] What happens: Your device sends encrypted data over the internet to a server.

[0252] Output: Encrypted data received by the server

[0253] Step 4:

[0254] The server decodes the received behavioral data and places it in a processing queue.

[0255] Input: Encrypted behavioral data

[0256] Data processing: AES data decryption

[0257] What happens: The server decrypts the encrypted data and enqueues (places) it in the processing queue.

[0258] Output: Decoded behavioral data, data in the processing queue

[0259] Step 5:

[0260] The server passes the behavioral data to the emotion engine, which recognizes the user's emotional state.

[0261] Input: Behavioral data

[0262] Data Computation: Emotion Analysis with Emotion Engine

[0263] Specific operation: The server retrieves the behavioral data from the processing queue and passes it to the emotion engine to begin analysis. The emotion engine analyzes the data and assigns a label to the user's emotional state (e.g., anxiety, anger).

[0264] Output: Emotion data (e.g., user expresses emotion "anxiety")

[0265] Step 6:

[0266] The server compares the behavioral and emotional data with a database containing past incident, accident, and crime data to calculate a risk score.

[0267] Input: Behavioral data, emotion data

[0268] Data calculation: Matching with database, calculating risk score

[0269] Specific operation: The server compares the behavioral data of "large euro investment" and the emotional data of "anxiety" with fraud data in the database and calculates a score that qualifies as high risk.

[0270] Output: Risk score (e.g. 80 / 100)

[0271] Step 7:

[0272] The server generates a warning message based on the detected risk and emotional state.

[0273] Input: Risk score, sentiment data

[0274] Data calculations: risk assessment, message generation

[0275] What it does: Based on the risk score and sentiment data, the server generates a warning message saying, "This search query carries a risk of fraud. Invest with caution."

[0276] Output: Warning message

[0277] Step 8:

[0278] The server sends the warning message and emotion data to the user terminal.

[0279] Input: Warning message, emotion data

[0280] Specific operation: The server sends the generated message and emotion data to the user's device.

[0281] Output: Messages and data received by the user terminal

[0282] Step 9:

[0283] The device will notify the user of the received warning message.

[0284] Input: Warning message, emotion data

[0285] What happens: The user's device will display a pop-up message saying, "This search query carries the risk of fraud. Invest with caution."

[0286] Output: The warning message displayed to the user

[0287] Step 10:

[0288] The user may take action based on the warning, for example, by avoiding the investment.

[0289] Input: The warning message displayed to the user

[0290] Specific behavior: The user sees the warning message and takes action to avoid the investment based on its contents.

[0291] Output: The user's new behavior

[0292] Step 11:

[0293] The device captures the user's behavioral history and sends it to the server.

[0294] Input: New user action

[0295] Specific operation: The device captures the user's behavior again and sends it to the server as a behavior history.

[0296] Output: Action history received by the server

[0297] Step 12:

[0298] The server analyzes user behavior history and uses it to improve the system.

[0299] Input: User behavior history

[0300] Data Calculation: Feedback Analysis

[0301] What it does: The server analyzes user feedback data to help improve risk detection and sentiment analysis algorithms.

[0302] Output: Improved system algorithm

[0303] (Application example 2)

[0304] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0305] Conventional security systems for internet use can detect risks based on user behavior data, but they are unable to evaluate risks by taking into account the user's emotional state. This makes it difficult to provide appropriate warnings and advice based on the user's psychological state, and ultimately makes it impossible to present the best countermeasures for the user. Furthermore, the methods for presenting warning messages are limited, which sometimes does not lead to user understanding or behavioral changes. A new system is needed to solve these issues.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0307] In this invention, the server includes: means for a user terminal to collect user behavioral data via the Internet; means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; means for the server to detect potential risks and perform risk assessments based on the user behavioral data; means for an emotion engine to analyze the user behavioral data and recognize the user's emotional state; means for the server to transmit the risk assessment results and emotion analysis results to the user terminal and notify the user; and means for the user terminal to display warning messages in the form of pop-ups or alerts. This enables real-time risk assessments that take the user's emotional state into consideration and the provision of appropriate warning messages.

[0308] A "user terminal" is a device for collecting and displaying user behavior data via the Internet.

[0309] "Behavioral data" is information about what you do online, such as searches, posts, chats, and emails you receive.

[0310] The "server" is a central processing unit that analyzes behavioral data received from a user terminal and transmits the results to the user terminal.

[0311] A "database" is an information storage system that holds data on past incidents, accidents, and crimes, and allows the server to collate and analyze the data.

[0312] "Potential risk" refers to possible danger or crime that can be estimated based on behavioral data.

[0313] "Risk assessment" is the process by which the server compares behavioral data with a database to determine the severity and likelihood of potential risks.

[0314] An "emotion engine" is software that analyzes user behavioral data and recognizes their emotional state.

[0315] "Emotional state" refers to the psychological state or mood a user exhibits when engaging in online activities.

[0316] "Notification" refers to the act of informing the user of the risk assessment results and emotion analysis results received by the user's device from the server.

[0317] A "pop-up or alert-style warning message" is a message that is visually displayed on the user's device to warn or alert the user.

[0318] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. The system of this invention is composed of a user terminal, a server, a database, and an emotion engine, and each element works in cooperation to ensure safe internet use for users.

[0319] The user device collects real-time behavioral data, such as searches, posts, chats, and e-mails that the user conducts over the Internet. The user device also encrypts the collected behavioral data before sending it to the server, thereby ensuring data security while protecting the user's privacy.

[0320] The server decodes the received behavioral data in real time and compares it with a database of past incidents, accidents, and crimes. The server is equipped with a machine learning algorithm that learns from past data to detect potential risks and perform risk assessments. In addition, the server is equipped with an emotion engine that can analyze user behavioral data and recognize emotional states.

[0321] The server sends risk assessment results based on behavioral data and emotion analysis results to the user's device. The user's device notifies the user of the received risk assessment and emotion analysis results, displaying warning messages in the form of pop-ups or alerts. This allows the user to recognize the potential risks posed by their own behavior and take appropriate measures.

[0322] For example, if a user searches for "large euro investment," this search query is captured as user behavior data and sent to the server. The server compares this search query with past fraud data and evaluates it as high risk. At the same time, the emotion engine recognizes the user's emotional state as "neutral." As a result, the server sends a risk warning message to the user's device saying, "This search query carries a risk associated with fraud. Be cautious with your investments.", along with emotion-based advice such as, "Your emotions are currently stable. Please remain calm."

[0323] Example prompt sentence:

[0324] User Activity: Search

[0325] User Input: Large Euro Investment

[0326] Detected Emotion: Neutral

[0327] Risk assessment result: High

[0328] Server response message: "This search query carries a risk of fraud. Invest with caution.", "Emotions are currently stable. Please remain calm."

[0329] As described above, the system of the present invention simultaneously monitors and analyzes user behavioral data and emotional data, performs real-time risk assessment, and provides appropriate warning messages to users, thereby reducing the risk of crime on the Internet.

[0330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0331] Step 1:

[0332] When a user searches, posts, or chats on the Internet, the user device captures the behavioral data. At this point, the input is the user's online activity data, and the output is the captured behavioral data.

[0333] Step 2:

[0334] The user device encrypts the captured behavioral data and sends it to the server. The input is the captured behavioral data, and the output is the encrypted behavioral data. This behavioral data is transferred to the server via the network.

[0335] Step 3:

[0336] The server receives and decrypts the encrypted behavioral data. The input is the encrypted behavioral data and the output is the decrypted behavioral data. The decrypted data is queued within the server for analysis.

[0337] Step 4:

[0338] The machine learning algorithm in the server compares the decoded behavioral data with past incident / accident / crime data in the database to detect potential risks. The input is the decoded behavioral data and the data in the database, and the output is the risk assessment result. In this process, certain behaviors may be judged to be high risk because they match with past crime data.

[0339] Step 5:

[0340] The emotion engine analyzes the user's behavioral data to recognize the user's emotional state. The input is the decoded behavioral data, and the output is the emotional state data. The emotion engine identifies the specific emotion the user expressed (e.g., anger or neutral).

[0341] Step 6:

[0342] The server combines the risk assessment results and emotional state data to generate a comprehensive risk assessment message. The inputs are the risk assessment results and emotional state data, and the output is a warning message and emotion-based advice for the user.

[0343] Step 7:

[0344] The server generates risk assessment messages and sends advice based on emotions to the user terminal. The input is the generated message, and the output is the sent message.

[0345] Step 8:

[0346] The user device receives risk assessment messages and advice and notifies them to the user in the form of popups or alerts. The input is the received message, and the output is the displayed warning message and advice, so the user can take appropriate action.

[0347] For example, if a user searches for "high euro investment," the search query is captured, encrypted, and sent to the server. The server decrypts it, compares it with fraud data, and determines that it poses a high risk. The emotion engine then recognizes the user's emotion as "neutral." As a result, a message from the server warning the user that "This search query carries a fraud risk. Be cautious when investing," along with advice that "Emotions are currently stable. Please remain calm," is sent to the user's device and displayed to the user.

[0348] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0349] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0350] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0351] [Second embodiment]

[0352] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0353] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0354] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0355] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0356] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0357] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0358] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0359] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0360] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0361] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0362] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0363] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0364] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks at an early stage. This system is composed of user terminals, a server, and a database, and these elements work together to ensure users' safe use of the Internet.

[0365] User behavior monitoring

[0366] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[0367] Data analysis

[0368] The server decodes the behavioral data it receives and compares it with a database of past incidents, accidents, and crimes. The server then analyzes the data using machine learning algorithms and rule-based systems to calculate a risk score. For example, the server may compare the keyword "large euro investment" with past fraud data and determine that it poses a high risk.

[0369] Risk Assessment

[0370] The server then performs a detailed assessment of the detected risk. This is the process of estimating the specific crime (e.g., investment fraud) and the potential amount of damage (e.g., 1 million yen) and determining the risk level. As a result of the assessment, a specific warning message is generated, such as "This search query carries a risk of fraud. Be cautious when investing."

[0371] User Notification

[0372] The server sends the risk assessment results to the user's device. The device notifies the user of the received assessment results and displays a warning in the form of a pop-up or alert. For example, the user might see a message saying, "This search query carries a risk associated with fraud. Be cautious when investing." The user can then review the warning and decide whether to reconsider their investment.

[0373] Gathering feedback

[0374] Users take action based on the warnings and advice provided by the system. For example, if a user avoids an investment, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[0375] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that monitor and analyze user behavior data, perform risk assessment, and notify users. The specific processing steps will be described later.

[0376] The processing flow will be explained below.

[0377] Step 1:

[0378] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[0379] Step 2:

[0380] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server.

[0381] Step 3:

[0382] The server decodes the received behavioral data and places it in a processing queue for analysis.

[0383] Step 4:

[0384] The server launches an analysis engine and compares the behavioral data with a database containing data on past incidents, accidents, and crimes.

[0385] Step 5:

[0386] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data.

[0387] Step 6:

[0388] A detailed assessment is carried out for the risk detected on the server. Specifically, the potential crime and potential damage amount are calculated, and the risk level is assessed.

[0389] Step 7:

[0390] The server generates a warning message and workarounds for the user based on the risk assessment results.

[0391] Step 8:

[0392] The server transmits the generated evaluation results and warning messages to the user terminal.

[0393] Step 9:

[0394] The device will notify the user of the evaluation results received and display a warning in the form of a pop-up or alert.

[0395] Step 10:

[0396] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[0397] Step 11:

[0398] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[0399] Step 12:

[0400] The server receives and analyzes user feedback and reflects it in system improvements, a process that continuously improves the system's detection accuracy and risk assessment algorithms.

[0401] Example 1

[0402] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0403] In the current Internet usage environment, there are concerns that users may unintentionally engage in behavior that poses a high risk of crime. Furthermore, existing crime prevention systems have difficulty monitoring and analyzing user behavior in real time and detecting risks early. Furthermore, there is a lack of mechanisms for effectively collecting feedback based on user behavior to improve the accuracy of the system. As a result, the safety of Internet use remains insufficient.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0405] In this invention, the server includes means for the user terminal to capture user behavioral data in real time via the Internet, encrypt it, and send it to the server, means for the server to decrypt the received encrypted behavioral data and compare it with a database containing past incident, accident, and crime data, means for the server to calculate a risk score based on the user behavioral data using a machine learning algorithm or a rule-based system and perform a risk assessment, means for the server to generate a warning message based on the risk assessment result and send it to the user terminal to notify the user, means for the user terminal to capture feedback regarding the user's behavior, encrypt it, and send it to the server, and means for the server to analyze the feedback received and use it to improve the system. This makes it possible to monitor and analyze user behavioral data in real time, detect and notify potential risks early, and improve the accuracy of the system based on the feedback.

[0406] "User terminal" refers to an electronic device that allows a user to perform operations or take actions via the Internet, including personal computers, smartphones, tablets, etc.

[0407] "Behavioral data" refers to data related to specific operations and activities that users perform on the Internet, such as searching, posting, chatting, and receiving emails.

[0408] A "server" is a central computer system that stores and processes data over a network, and analyzes and records data sent from user terminals.

[0409] "Encryption" is a security technology that converts data into a format that cannot be deciphered by third parties, and includes algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman).

[0410] A "database" is an information management system for storing and managing data on past incidents, accidents, and crimes, and it allows for efficient searching and matching of large amounts of information.

[0411] A "machine learning algorithm" is a program that automatically learns patterns and rules from data and makes predictions and classifications for new data, and includes decision trees, random forests, neural networks, etc.

[0412] A "rule-based system" is a system that analyzes and evaluates data based on pre-set rules and conditions, and makes inferences and judgments according to fixed rules.

[0413] A "risk score" is a number that indicates the degree of risk calculated based on a user's behavioral data, and is used to evaluate the level of criminal risk.

[0414] A "warning message" is a message that is generated based on the risk assessment results and is used to alert the user, and includes specific risk details and advice.

[0415] "Feedback" refers to information about actions taken by users in response to warnings and advice provided by the system, and is data used to improve and optimize the system.

[0416] The present invention is a system for strengthening crime prevention measures by monitoring users' Internet activity and detecting crime risks at an early stage. Specific procedures for implementing the present invention, as well as the hardware and software used, are described in detail below.

[0417] First, the user's device captures user behavior data in real time via the internet, using browser extensions or dedicated application programs. For example, when a user searches for "large euro investment," the search query is captured.

[0418] The captured behavioral data is then encrypted by the device using encryption techniques such as AES (Advanced Encryption Standard) and sent to a server using the HTTPS protocol.

[0419] The server then decrypts the encrypted data, again using AES, and compares it with a database containing past incident and crime data. This database could be an SQL database or a NoSQL database, for example.

[0420] The server then uses machine learning algorithms and rule-based systems to further analyze the decrypted data, using libraries such as Scikit-learn and TensorFlow. Machine learning algorithms such as random forests and neural networks are used. A risk score is calculated based on these algorithms.

[0421] The server then performs a specific risk assessment based on the risk score, including a specific crime (e.g., fraud) and potential damage amount (e.g., 1 million yen). Once the risk assessment is complete, a warning message is generated. For example, a specific message such as "This search query carries a risk of fraud. Be cautious when investing." is created.

[0422] The generated warning message is sent from the server to the user's device, and the device notifies the user. The notification is in the form of a pop-up or alert. The user's screen will display the message, "This search query carries a risk of fraud. Please invest with caution."

[0423] Any actions the user takes based on the system's warnings and advice are again captured by the device. The device encrypts this behavioral history and sends it to the server. The server receives, decrypts, and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. For example, it adds new user behavior patterns to the learning data and retrains the model.

[0424] Through these steps, the system can consistently monitor and analyze user behavior data from start to finish, quickly detecting and notifying users of risks. This process involves a series of processing interactions: capturing, encrypting, decrypting, analyzing, and notifying users of user behavior data.

[0425] Example prompts to be input to the generative AI model:

[0426] "Please conduct a risk assessment of the user's online search for 'high dollar euro investment' and inform the user of the results. Please also explain what data processing and algorithms you use."

[0427] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0428] Step 1:

[0429] When a user performs online activities such as searching, posting, chatting, or receiving emails on the Internet, this behavioral data is captured in real time by the user's device. Specifically, the behavioral data is acquired by browser extensions or dedicated applications. The input is the user's specific Internet activity, and the output is the captured behavioral data.

[0430] Step 2:

[0431] The captured behavioral data is encrypted by the device. Here, AES (Advanced Encryption Standard) is used. This process is performed to protect the data from being read by third parties. The input is the captured behavioral data, and the output is the encrypted data. Specifically, the device encrypts the data using the AES algorithm.

[0432] Step 3:

[0433] The encrypted data is sent to the server using the HTTPS protocol, which ensures data confidentiality and integrity. The input is the encrypted behavioral data, and the output is the data sent to the server. Specifically, the device establishes an HTTPS connection and sends the data.

[0434] Step 4:

[0435] The server decrypts the received encrypted data. AES is used again for decryption, which returns the data to the original behavioral data. The input is the encrypted data, and the output is the decrypted data. Specifically, the server decrypts the data using the AES algorithm.

[0436] Step 5:

[0437] The server compares the decoded data with a database containing data on past incidents, accidents, and crimes. The server analyzes this data and calculates a risk score. A machine learning algorithm (e.g., random forest or neural network) is used for the analysis. The input is the decoded behavioral data, and the output is a risk score. Specifically, the server inputs the data into a machine learning model and obtains a risk score.

[0438] Step 6:

[0439] The server performs a specific risk assessment based on the risk score, including the name of the crime and the potential damage amount. The server generates a warning message based on the risk assessment result. The input is the risk score and the output is the warning message. Specifically, the server classifies the risk based on the assessment criteria and creates an appropriate message.

[0440] Step 7:

[0441] The generated warning message is sent from the server to the user terminal. The terminal notifies the user of this message. The input is the warning message, and the output is the notification to the user. Specifically, the terminal displays the message in the form of a popup or alert.

[0442] Step 8:

[0443] The user takes action based on the system's warnings and advice. For example, if the user avoids an investment, the device captures the user's behavioral history. The input is the user's behavior, and the output is the captured behavioral history. Specifically, the device captures the behavioral data again.

[0444] Step 9:

[0445] The captured behavioral history is encrypted by the device and sent back to the server. The server decrypts and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. The input is the encrypted feedback data, and the output is an improved risk detection model. Specifically, the server uses the new data for learning and retrains the model.

[0446] (Application example 1)

[0447] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0448] User behavior on the Internet is becoming more diverse, and this includes criminal risks such as investment fraud and phishing. However, it is difficult for users to identify these risks themselves and respond appropriately. Therefore, there is a need for a system that can monitor users' online activities in real time, detect potential criminal risks early, and warn users. In particular, there is a need for a real-time warning system that uses smartphones.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0450] In this invention, the server includes: a means for a user terminal to collect user behavioral data via the Internet; a means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; a means for the server to detect potential risks based on the user behavioral data and perform a risk assessment; a means for the server to send the risk assessment results to the user terminal and notify the user; and a means for the user terminal to display a warning message to the user based on the risk assessment results. This makes it possible to detect crime risks in real time while the user is using the Internet and to promptly display a warning.

[0451] A "user terminal" is a device such as a smartphone or computer that a user uses to access the Internet.

[0452] "Behavioral data" is data about activities you perform on the Internet, such as searching, browsing, chatting, and sending emails.

[0453] A "server" is a computer system that analyzes behavioral data received from user terminals and evaluates risks.

[0454] A "database" is a collection of information that stores and manages data on past incidents, accidents, and crimes, and is used by the server to collate the data.

[0455] "Potential risks" are risks of crime, fraud, and other potential future occurrences that are estimated based on user behavioral data.

[0456] "Risk assessment" is the process of analyzing user behavioral data and scoring the likelihood of a crime occurring based on that data.

[0457] A "warning message" is a specific warning message that is sent to the user based on the results of a risk assessment.

[0458] To implement the present invention, it is necessary to construct a system including a user terminal, a server, and a database.

[0459] First, the user's device must have a means of collecting user behavior data in real time via the internet. For example, if a user searches for "high dollar euro investment," the search query is captured. Data is also collected when the user browses the web, chats, or sends and receives emails. This data is encrypted and sent to a server.

[0460] The server decodes the received behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server uses Python and the requests library to collate and analyze the data. Specifically, it uses a machine learning algorithm to compare user behavior data with crime data and score potential risks. The server then performs a risk assessment based on the risk score and generates appropriate warning messages.

[0461] The warning message generated as a result of the risk assessment is sent back to the user's device and notified to the user. The user's device will display the warning message in the form of a pop-up or alert to inform the user of the risk. For example, a specific warning such as "This search query has a risk related to fraud. Please be cautious when investing" may be displayed.

[0462] Additionally, user behavioral feedback is also important. When a user takes action based on the warnings and advice provided by the system, the user's behavioral history is also captured by the user's device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[0463] Examples:

[0464] For example, if a user searches for the keyword "large euro investment," this search query is sent to the server. The server compares this with past fraud data and, if it determines that there is a high risk, returns a warning message to the user saying, "This search query carries a risk of fraud. Be cautious before investing." The user can acknowledge this warning and reconsider their investment.

[0465] Example prompts to input to the generative AI model:

[0466] Generate a program code that determines whether the search keyword "large euro investment" poses a risk related to crime, and if so, display a warning message to the user.

[0467] This specific example and example prompt sentences will allow a clearer understanding of the embodiments of the invention.

[0468] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0469] Step 1:

[0470] The user's device collects user behavior data via the Internet. Specifically, it captures data when the user conducts web searches, sends chat messages, or receives emails. For example, a search query such as "large euro investment" is received as input. The device processes this search query by encrypting it and outputs the encrypted data.

[0471] Step 2:

[0472] The user device sends the collected behavioral data to the server. The encrypted search query is input and sent as a POST request to the server's specified API endpoint. As a result, the server receives this data.

[0473] Step 3:

[0474] The server decrypts the behavioral data it receives. The input is the encrypted search query, which the server converts back to plain text using a decryption algorithm. The output is the decrypted search query. For example, "large euro investment" would be the decrypted search query.

[0475] Step 4:

[0476] The server compares the decrypted behavioral data with a database containing data on past incidents, accidents, and crimes. The decrypted search query is input, and the server compares the query with the data in the database. The database contains data on past fraud cases, etc., and checks for a match. The result of the comparison is a risk score. For example, if a match is found with a fraud-related query, a high risk score is obtained.

[0477] Step 5:

[0478] The server performs a risk assessment based on the risk score and generates a warning message. The risk score is the input, and the server determines the level and content of the warning depending on the score. For example, if the risk score is high, a warning message such as "This search query has a risk related to fraud. Be careful when investing" is generated. The warning message is the output.

[0479] Step 6:

[0480] The server sends the generated warning message to the user terminal. The warning message is the input, and is sent as an API request to the user terminal. The user terminal receives this message.

[0481] Step 7:

[0482] The user's device will notify the user of the warning message it has received. The warning message will be input, and the device will display it to the user in the form of a pop-up or alert. This allows the user to check the content of the notification. For example, a message such as "This search query has a risk related to fraud. Please be careful when investing" will be displayed.

[0483] Step 8:

[0484] The user takes action based on the warnings and advice provided by the system. After receiving the warning message, the user may take action, such as reconsidering an investment. This behavioral feedback is captured by the user's device. Behavioral data is input and output as new behavioral data.

[0485] Step 9:

[0486] The user device sends feedback data to the server. New behavioral data is input and sent to the server. The server receives this data.

[0487] Step 10:

[0488] The server analyzes the feedback data and uses it to improve the system. New behavioral data is input and analyzed by the server. The resulting data is used to continuously improve the system and output to improve the accuracy of risk detection.

[0489] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0490] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. This system is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to ensure safe internet use for users.

[0491] User behavior monitoring

[0492] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[0493] The role of the emotional engine

[0494] At the server, the behavioral data is received, decoded, and placed in a processing queue for analysis. Meanwhile, the emotion engine analyzes the user's behavioral data to recognize the user's emotional state. For example, if the user performs an action that indicates intense emotion, the emotion engine will recognize this as "anger."

[0495] Data analysis

[0496] The server combines the received behavioral data with the emotion data from the emotion engine for analysis. The analysis engine compares the behavioral data with a database of past incidents, accidents, and crimes to calculate a risk score. For example, the server compares the keyword "large euro investment" with past fraud data and determines it to be high risk.

[0497] Risk Assessment and Sentiment Analysis

[0498] The server performs a detailed assessment based on the detected risk and the user's emotional state. Specifically, it estimates the likely crime (e.g., investment fraud) and potential damage amount (e.g., 1 million yen) and determines the risk level. The analysis results of the emotion engine are also reflected in the risk assessment, and a risk message is generated taking into account the user's emotional state. As a result of the assessment, a specific warning message such as "This search query carries a risk related to fraud. Be cautious when investing" is generated.

[0499] User Notification

[0500] The server sends the risk assessment results and emotion analysis results to the user's device. The device then notifies the user of the received assessment results and emotion data, displaying a warning in the form of a pop-up or alert. For example, a message might be displayed to the user saying, "This search query carries a risk associated with fraud. Be cautious when investing," along with advice on how to respond appropriately based on the emotion. If the user is expressing anger, psychological advice on how to calm them down is also provided.

[0501] Gathering feedback

[0502] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[0503] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that simultaneously monitor and analyze user behavioral data and emotional data, evaluate risks, and notify users. Specific processing steps will be described later.

[0504] The processing flow will be explained below.

[0505] Step 1:

[0506] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[0507] Step 2:

[0508] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server, along with emotional data such as the user's facial expressions, typing speed, and language used.

[0509] Step 3:

[0510] The server decodes the received behavioral and emotional data and places it in a processing queue for analysis.

[0511] Step 4:

[0512] The emotion engine analyzes the user's behavioral data, facial expression data, and other emotional indicators to recognize the user's emotional state (e.g., anger, sadness, joy, etc.).

[0513] Step 5:

[0514] The server inputs the behavioral data into an analysis engine and compares it with a database containing data on past incidents, accidents, and crimes.

[0515] Step 6:

[0516] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data. For example, the keyword "large euro investment" is considered high risk.

[0517] Step 7:

[0518] The server performs a detailed risk assessment of the detected risk, taking into account the user's emotional state. For example, if there is a possibility of fraud and the emotional engine recognizes "anxiety," the server will raise the risk level.

[0519] Step 8:

[0520] The server generates specific warning messages and advice on how to avoid the risk based on the risk assessment and sentiment analysis results. For example, it generates a message saying, "This search query carries a high risk of fraud. If you are concerned, please consult a professional."

[0521] Step 9:

[0522] The server transmits the generated evaluation results and warning messages to the user terminal.

[0523] Step 10:

[0524] The device will notify the user of the evaluation results and sentiment data it has received and display a warning in the form of a pop-up or alert, such as "This search query carries a risk of fraud. Please be cautious with your investments. Please refer to this link for any concerns you may have."

[0525] Step 11:

[0526] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[0527] Step 12:

[0528] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[0529] Step 13:

[0530] The server receives and analyzes user behavioral feedback and reflects it in system improvements. This process continuously improves the accuracy of the system's risk detection and sentiment analysis.

[0531] Example 2

[0532] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0533] Criminal activities on the Internet are becoming more sophisticated every day, threatening users' safety. Online fraud and cybercrime, in particular, can have serious consequences for victims. Therefore, there is a need for an effective system that can monitor users' online activities and detect potential crime risks early. In addition, there is a need for a system that can analyze users' emotional state and provide appropriate risk assessments to provide more effective crime prevention measures.

[0534] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0535] In this invention, the server includes means for encrypting behavioral data captured by the user terminal and transmitting it to the server, means for the server to decrypt the behavioral data received and place it in a processing queue, means for the server to compare the behavioral data received with a database containing past incident / accident / crime data, means for an emotion engine to analyze the user's behavioral data and recognize the user's emotional state, means for the server to detect potential risks based on the user's behavioral data and emotional data and perform a risk assessment, and means for the server to transmit the risk assessment results and the user's emotional state to the user terminal and notify the user. This makes it possible to detect criminal risks in the user's online activities early and issue appropriate warnings.

[0536] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to access the Internet.

[0537] "Behavioral data" is information about the activities you perform online, such as searching, chatting, posting, and receiving emails.

[0538] "AES encryption" is a method of encrypting data using the Advanced Encryption Standard.

[0539] A "server" is a computer system that receives data from user terminals via a network, analyzes it, compares it with a database, and notifies the user.

[0540] A "processing queue" is a data structure that temporarily stores data waiting to be processed on a server.

[0541] A "database" is a system that systematically accumulates and manages data related to past incidents, accidents, and crimes.

[0542] An "emotion engine" is a combination of algorithms and software that analyzes user behavioral data and recognizes the user's emotional state.

[0543] "Emotional Data" is information about the user's emotional state analyzed by the emotion engine.

[0544] A "risk score" is a number that represents the degree of potential risk, calculated based on a user's behavioral and emotional data.

[0545] "Risk assessment" is the process of using risk scores and other analytical results to determine how risky a particular action is.

[0546] A "warning message" is a message containing a warning or advice that is sent to the user based on the results of a risk assessment.

[0547] The system of the present invention is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to enable users to engage in safe online activities.

[0548] User behavior monitoring

[0549] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time and encrypts it using AES encryption. The encrypted data is then sent to the server. For example, if a user enters the search query "large euro investment," the search query is captured by the device, encrypted, and sent to the server.

[0550] Receiving and Decrypting Data

[0551] The server receives the encrypted behavioral data from the user terminal, decrypts the received data using AES encryption, and places it in the processing queue. The server then removes the data from the processing queue.

[0552] Analysis by emotion engine

[0553] The server passes the extracted behavioral data to the emotion engine, which then analyzes the user's behavioral data to recognize the user's emotional state. For example, if a user frequently uses emotional words, the emotion engine will recognize this as "anger."

[0554] Risk Analysis

[0555] The server combines the emotional data received from the emotion engine with the behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server calculates a risk score based on the user's behavior and emotional state, and performs a risk assessment. This risk score indicates the potential risk level of the user's online behavior. For example, the keyword "large euro investment" matches past fraud data and is deemed high risk.

[0556] Risk assessment and warning message generation

[0557] The server then performs a specific risk assessment based on the calculated risk score and emotional state and generates a warning message, such as "This search query carries a risk associated with fraud. Be cautious when investing."

[0558] User Notification

[0559] The generated risk assessment results and sentiment data are sent from the server to the user's device, which then notifies the user in real time. The device then displays a message to the user in the form of a pop-up or alert. For example, a warning message such as "This search query carries a risk associated with fraud. Please invest with caution."

[0560] Gathering feedback

[0561] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured again by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[0562] Prompt Sentence Examples

[0563] Analyze user search history for "large euro investment" to calculate crime risk score and perform sentiment analysis.

[0564] "Analyze the relationship between the words used by users in chat and their emotions, and generate warning messages based on that."

[0565] As described above, the system of the present invention can simultaneously monitor and analyze user behavioral data and emotional data, perform risk assessment, and notify users, thereby reducing the risk of crime on the Internet. The specific processing steps will be described in detail below.

[0566] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0567] Step 1:

[0568] Users perform activities online such as searching, writing, chatting, and receiving emails.

[0569] Input: User behavior (e.g., search query "high dollar euro investment")

[0570] What happens: A user opens a web browser, enters specific keywords into the search bar, and performs a search.

[0571] Step 2:

[0572] The device captures user behavior data in real time and encrypts the captured data using the AES encryption method.

[0573] Input: User behavior data

[0574] Data processing: Capture and AES encryption of behavioral data

[0575] What it does: The device captures the user's search query and encodes the data using AES encryption.

[0576] Output: Encrypted behavioral data

[0577] Step 3:

[0578] The device transmits the encrypted behavioral data to the server.

[0579] Input: Encrypted behavioral data

[0580] What happens: Your device sends encrypted data over the internet to a server.

[0581] Output: Encrypted data received by the server

[0582] Step 4:

[0583] The server decodes the received behavioral data and places it in a processing queue.

[0584] Input: Encrypted behavioral data

[0585] Data processing: AES data decryption

[0586] What happens: The server decrypts the encrypted data and enqueues (places) it in the processing queue.

[0587] Output: Decoded behavioral data, data in the processing queue

[0588] Step 5:

[0589] The server passes the behavioral data to the emotion engine, which recognizes the user's emotional state.

[0590] Input: Behavioral data

[0591] Data Computation: Emotion Analysis with Emotion Engine

[0592] What happens: The server retrieves the behavioral data from the processing queue and passes it to the emotion engine to begin analysis. The emotion engine analyzes the data and assigns a label to the user's emotional state (e.g., anxiety, anger).

[0593] Output: Emotion data (e.g., user expresses emotion "anxiety")

[0594] Step 6:

[0595] The server compares the behavioral and emotional data with a database containing past incident, accident, and crime data to calculate a risk score.

[0596] Input: Behavioral data, emotion data

[0597] Data calculation: Matching with database, calculating risk score

[0598] Specific operation: The server compares the behavioral data of "large euro investment" and the emotional data of "anxiety" with fraud data in the database and calculates a score that qualifies as high risk.

[0599] Output: Risk score (e.g. 80 / 100)

[0600] Step 7:

[0601] The server generates a warning message based on the detected risk and emotional state.

[0602] Input: Risk score, sentiment data

[0603] Data calculations: risk assessment, message generation

[0604] What it does: Based on the risk score and sentiment data, the server generates a warning message saying, "This search query carries a risk of fraud. Invest with caution."

[0605] Output: Warning message

[0606] Step 8:

[0607] The server sends the warning message and emotion data to the user terminal.

[0608] Input: Warning message, emotion data

[0609] Specific operation: The server sends the generated message and emotion data to the user's device.

[0610] Output: Messages and data received by the user terminal

[0611] Step 9:

[0612] The device will notify the user of the received warning message.

[0613] Input: Warning message, emotion data

[0614] What happens: The user's device will display a pop-up message saying, "This search query carries the risk of fraud. Invest with caution."

[0615] Output: The warning message displayed to the user

[0616] Step 10:

[0617] The user may take action based on the warning, for example, by avoiding the investment.

[0618] Input: The warning message displayed to the user

[0619] Specific behavior: The user sees the warning message and takes action to avoid the investment based on its contents.

[0620] Output: The user's new behavior

[0621] Step 11:

[0622] The device captures the user's behavioral history and sends it to the server.

[0623] Input: New user action

[0624] Specific operation: The device captures the user's behavior again and sends it to the server as a behavior history.

[0625] Output: Action history received by the server

[0626] Step 12:

[0627] The server analyzes user behavior history and uses it to improve the system.

[0628] Input: User behavior history

[0629] Data Calculation: Feedback Analysis

[0630] What it does: The server analyzes user feedback data to help improve risk detection and sentiment analysis algorithms.

[0631] Output: Improved system algorithm

[0632] (Application example 2)

[0633] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0634] Conventional security systems for internet use can detect risks based on user behavior data, but they are unable to evaluate risks by taking into account the user's emotional state. This makes it difficult to provide appropriate warnings and advice based on the user's psychological state, and ultimately makes it impossible to present the best countermeasures for the user. Furthermore, the methods for presenting warning messages are limited, which sometimes does not lead to user understanding or behavioral changes. A new system is needed to solve these issues.

[0635] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0636] In this invention, the server includes: means for a user terminal to collect user behavioral data via the Internet; means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; means for the server to detect potential risks and perform risk assessments based on the user behavioral data; means for an emotion engine to analyze the user behavioral data and recognize the user's emotional state; means for the server to transmit the risk assessment results and emotion analysis results to the user terminal and notify the user; and means for the user terminal to display warning messages in the form of pop-ups or alerts. This enables real-time risk assessments that take the user's emotional state into consideration and provides appropriate warning messages.

[0637] A "user terminal" is a device for collecting and displaying user behavior data via the Internet.

[0638] "Behavioral data" is information about what you do online, such as searches, posts, chats, and emails you receive.

[0639] The "server" is a central processing unit that analyzes behavioral data received from a user terminal and transmits the results to the user terminal.

[0640] A "database" is an information storage system that holds data on past incidents, accidents, and crimes, and allows the server to collate and analyze the data.

[0641] "Potential risk" refers to possible danger or crime that can be estimated based on behavioral data.

[0642] "Risk assessment" is the process by which the server compares behavioral data with a database to determine the severity and likelihood of potential risks.

[0643] An "emotion engine" is software that analyzes user behavioral data and recognizes their emotional state.

[0644] "Emotional state" refers to the psychological state or mood a user exhibits when engaging in online activities.

[0645] "Notification" refers to the act of informing the user of the risk assessment results and emotion analysis results received by the user's device from the server.

[0646] A "pop-up or alert-style warning message" is a message that is visually displayed on the user's device to warn or alert the user.

[0647] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. The system of this invention is composed of a user terminal, a server, a database, and an emotion engine, and each element works in cooperation to ensure safe internet use for users.

[0648] The user device collects real-time behavioral data, such as searches, posts, chats, and e-mails that the user conducts over the Internet. The user device also encrypts the collected behavioral data before sending it to the server, thereby ensuring data security while protecting the user's privacy.

[0649] The server decodes the received behavioral data in real time and compares it with a database of past incidents, accidents, and crimes. The server is equipped with a machine learning algorithm that learns from past data to detect potential risks and perform risk assessments. In addition, the server is equipped with an emotion engine that can analyze user behavioral data and recognize emotional states.

[0650] The server sends risk assessment results based on behavioral data and emotion analysis results to the user's device. The user's device notifies the user of the received risk assessment and emotion analysis results, displaying warning messages in the form of pop-ups or alerts. This allows the user to recognize the potential risks posed by their own behavior and take appropriate measures.

[0651] For example, if a user searches for "large euro investment," this search query is captured as user behavior data and sent to the server. The server compares this search query with past fraud data and evaluates it as high risk. At the same time, the emotion engine recognizes the user's emotional state as "neutral." As a result, the server sends a risk warning message to the user's device saying, "This search query carries a risk associated with fraud. Be cautious with your investments.", along with emotion-based advice such as, "Your emotions are currently stable. Please remain calm."

[0652] Example prompt sentence:

[0653] User Activity: Search

[0654] User Input: Large Euro Investment

[0655] Detected Emotion: Neutral

[0656] Risk assessment result: High

[0657] Server response message: "This search query carries a risk of fraud. Invest with caution.", "Emotions are currently stable. Please remain calm."

[0658] As described above, the system of the present invention simultaneously monitors and analyzes user behavioral data and emotional data, performs real-time risk assessment, and provides appropriate warning messages to users, thereby reducing the risk of crime on the Internet.

[0659] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0660] Step 1:

[0661] When a user searches, posts, or chats on the Internet, the user device captures the behavioral data. At this point, the input is the user's online activity data, and the output is the captured behavioral data.

[0662] Step 2:

[0663] The user device encrypts the captured behavioral data and sends it to the server. The input is the captured behavioral data, and the output is the encrypted behavioral data. This behavioral data is transferred to the server via the network.

[0664] Step 3:

[0665] The server receives and decrypts the encrypted behavioral data. The input is the encrypted behavioral data and the output is the decrypted behavioral data. The decrypted data is queued within the server for analysis.

[0666] Step 4:

[0667] The machine learning algorithm in the server compares the decoded behavioral data with past incident / accident / crime data in the database to detect potential risks. The input is the decoded behavioral data and the data in the database, and the output is the risk assessment result. In this process, certain behaviors may be judged to be high risk because they match with past crime data.

[0668] Step 5:

[0669] The emotion engine analyzes the user's behavioral data to recognize the user's emotional state. The input is the decoded behavioral data, and the output is the emotional state data. The emotion engine identifies the specific emotion the user expressed (e.g., anger or neutral).

[0670] Step 6:

[0671] The server combines the risk assessment results and emotional state data to generate a comprehensive risk assessment message. The inputs are the risk assessment results and emotional state data, and the output is a warning message and emotion-based advice for the user.

[0672] Step 7:

[0673] The server generates risk assessment messages and sends advice based on emotions to the user terminal. The input is the generated message, and the output is the sent message.

[0674] Step 8:

[0675] The user device receives risk assessment messages and advice and notifies them to the user in the form of popups or alerts. The input is the received message, and the output is the displayed warning message and advice, so the user can take appropriate action.

[0676] For example, if a user searches for "high euro investment," the search query is captured, encrypted, and sent to the server. The server decrypts it, compares it with fraud data, and determines that it poses a high risk. The emotion engine then recognizes the user's emotion as "neutral." As a result, a message from the server warning the user that "This search query carries a fraud risk. Be cautious when investing," along with advice that "Emotions are currently stable. Please remain calm," is sent to the user's device and displayed to the user.

[0677] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0678] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0679] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0680] [Third embodiment]

[0681] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0682] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0683] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0684] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0685] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0686] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0687] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0688] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0689] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0690] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0691] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0692] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0693] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks at an early stage. This system is composed of user terminals, a server, and a database, and these elements work together to ensure users' safe use of the Internet.

[0694] User behavior monitoring

[0695] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[0696] Data analysis

[0697] The server decodes the behavioral data it receives and compares it with a database of past incidents, accidents, and crimes. The server then analyzes the data using machine learning algorithms and rule-based systems to calculate a risk score. For example, the server may compare the keyword "large euro investment" with past fraud data and determine that it poses a high risk.

[0698] Risk Assessment

[0699] The server then performs a detailed assessment of the detected risk. This is the process of estimating the specific crime (e.g., investment fraud) and the potential amount of damage (e.g., 1 million yen) and determining the risk level. As a result of the assessment, a specific warning message is generated, such as "This search query carries a risk of fraud. Be cautious when investing."

[0700] User Notification

[0701] The server sends the risk assessment results to the user's device. The device notifies the user of the received assessment results and displays a warning in the form of a pop-up or alert. For example, the user might see a message saying, "This search query carries a risk associated with fraud. Be cautious when investing." The user can then review the warning and decide whether to reconsider their investment.

[0702] Gathering feedback

[0703] Users take action based on the warnings and advice provided by the system. For example, if a user avoids an investment, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[0704] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that monitor and analyze user behavior data, perform risk assessment, and notify users. The specific processing steps will be described later.

[0705] The processing flow will be explained below.

[0706] Step 1:

[0707] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[0708] Step 2:

[0709] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server.

[0710] Step 3:

[0711] The server decodes the received behavioral data and places it in a processing queue for analysis.

[0712] Step 4:

[0713] The server launches an analysis engine and compares the behavioral data with a database containing data on past incidents, accidents, and crimes.

[0714] Step 5:

[0715] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data.

[0716] Step 6:

[0717] A detailed assessment is carried out for the risk detected on the server. Specifically, the potential crime and potential damage amount are calculated, and the risk level is assessed.

[0718] Step 7:

[0719] The server generates a warning message and workarounds for the user based on the risk assessment results.

[0720] Step 8:

[0721] The server transmits the generated evaluation results and warning messages to the user terminal.

[0722] Step 9:

[0723] The device will notify the user of the evaluation results received and display a warning in the form of a pop-up or alert.

[0724] Step 10:

[0725] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[0726] Step 11:

[0727] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[0728] Step 12:

[0729] The server receives and analyzes user feedback and reflects it in system improvements, a process that continuously improves the system's detection accuracy and risk assessment algorithms.

[0730] Example 1

[0731] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0732] In the current Internet usage environment, there are concerns that users may unintentionally engage in behavior that poses a high risk of crime. Furthermore, existing crime prevention systems have difficulty monitoring and analyzing user behavior in real time and detecting risks early. Furthermore, there is a lack of mechanisms for effectively collecting feedback based on user behavior to improve the accuracy of the system. As a result, the safety of Internet use remains insufficient.

[0733] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0734] In this invention, the server includes means for the user terminal to capture user behavioral data in real time via the Internet, encrypt it, and send it to the server, means for the server to decrypt the received encrypted behavioral data and compare it with a database containing past incident, accident, and crime data, means for the server to calculate a risk score based on the user behavioral data using a machine learning algorithm or a rule-based system and perform a risk assessment, means for the server to generate a warning message based on the risk assessment result and send it to the user terminal to notify the user, means for the user terminal to capture feedback regarding the user's behavior, encrypt it, and send it to the server, and means for the server to analyze the feedback received and use it to improve the system. This makes it possible to monitor and analyze user behavioral data in real time, detect and notify potential risks early, and improve the accuracy of the system based on the feedback.

[0735] "User terminal" refers to an electronic device that allows a user to perform operations or take actions via the Internet, including personal computers, smartphones, tablets, etc.

[0736] "Behavioral data" refers to data related to specific operations and activities that users perform on the Internet, such as searching, posting, chatting, and receiving emails.

[0737] A "server" is a central computer system that stores and processes data over a network, and analyzes and records data sent from user terminals.

[0738] "Encryption" is a security technology that converts data into a format that cannot be deciphered by third parties, and includes algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman).

[0739] A "database" is an information management system for storing and managing data on past incidents, accidents, and crimes, and it allows for efficient searching and matching of large amounts of information.

[0740] A "machine learning algorithm" is a program that automatically learns patterns and rules from data and makes predictions and classifications for new data, and includes decision trees, random forests, neural networks, etc.

[0741] A "rule-based system" is a system that analyzes and evaluates data based on pre-set rules and conditions, and makes inferences and judgments according to fixed rules.

[0742] A "risk score" is a number that indicates the degree of risk calculated based on a user's behavioral data, and is used to evaluate the level of criminal risk.

[0743] A "warning message" is a message that is generated based on the risk assessment results and is used to alert the user, and includes specific risk details and advice.

[0744] "Feedback" refers to information about actions taken by users in response to warnings and advice provided by the system, and is data used to improve and optimize the system.

[0745] The present invention is a system for strengthening crime prevention measures by monitoring users' Internet activity and detecting crime risks at an early stage. Specific procedures for implementing the present invention, as well as the hardware and software used, are described in detail below.

[0746] First, the user's device captures user behavior data in real time via the internet, using browser extensions or dedicated application programs. For example, when a user searches for "large euro investment," the search query is captured.

[0747] The captured behavioral data is then encrypted by the device using encryption techniques such as AES (Advanced Encryption Standard) and sent to a server using the HTTPS protocol.

[0748] The server then decrypts the encrypted data, again using AES, and compares it with a database containing past incident and crime data. This database could be an SQL database or a NoSQL database, for example.

[0749] The server then uses machine learning algorithms and rule-based systems to further analyze the decrypted data, using libraries such as Scikit-learn and TensorFlow. Machine learning algorithms such as random forests and neural networks are used. A risk score is calculated based on these algorithms.

[0750] The server then performs a specific risk assessment based on the risk score, including a specific crime (e.g., fraud) and potential damage amount (e.g., 1 million yen). Once the risk assessment is complete, a warning message is generated. For example, a specific message such as "This search query carries a risk of fraud. Be cautious when investing." is created.

[0751] The generated warning message is sent from the server to the user's device, and the device notifies the user. The notification is in the form of a pop-up or alert. The user's screen will display the message, "This search query carries a risk of fraud. Please invest with caution."

[0752] Any actions the user takes based on the system's warnings and advice are again captured by the device. The device encrypts this behavioral history and sends it to the server. The server receives, decrypts, and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. For example, it adds new user behavior patterns to the learning data and retrains the model.

[0753] Through these steps, the system can consistently monitor and analyze user behavior data from start to finish, quickly detecting and notifying users of risks. This process involves a series of processing interactions: capturing, encrypting, decrypting, analyzing, and notifying users of user behavior data.

[0754] Example prompts to be input to the generative AI model:

[0755] "Please conduct a risk assessment of the user's online search for 'high dollar euro investment' and inform the user of the results. Please also explain what data processing and algorithms you use."

[0756] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0757] Step 1:

[0758] When a user performs online activities such as searching, posting, chatting, or receiving emails on the Internet, this behavioral data is captured in real time by the user's device. Specifically, the behavioral data is acquired by browser extensions or dedicated applications. The input is the user's specific Internet activity, and the output is the captured behavioral data.

[0759] Step 2:

[0760] The captured behavioral data is encrypted by the device. Here, AES (Advanced Encryption Standard) is used. This process is performed to protect the data from being read by third parties. The input is the captured behavioral data, and the output is the encrypted data. Specifically, the device encrypts the data using the AES algorithm.

[0761] Step 3:

[0762] The encrypted data is sent to the server using the HTTPS protocol, which ensures data confidentiality and integrity. The input is the encrypted behavioral data, and the output is the data sent to the server. Specifically, the device establishes an HTTPS connection and sends the data.

[0763] Step 4:

[0764] The server decrypts the received encrypted data. AES is used again for decryption, which returns the data to the original behavioral data. The input is the encrypted data, and the output is the decrypted data. Specifically, the server decrypts the data using the AES algorithm.

[0765] Step 5:

[0766] The server compares the decoded data with a database containing data on past incidents, accidents, and crimes. The server analyzes this data and calculates a risk score. A machine learning algorithm (e.g., random forest or neural network) is used for the analysis. The input is the decoded behavioral data, and the output is a risk score. Specifically, the server inputs the data into a machine learning model and obtains a risk score.

[0767] Step 6:

[0768] The server performs a specific risk assessment based on the risk score, including the name of the crime and the potential damage amount. The server generates a warning message based on the risk assessment result. The input is the risk score and the output is the warning message. Specifically, the server classifies the risk based on the assessment criteria and creates an appropriate message.

[0769] Step 7:

[0770] The generated warning message is sent from the server to the user terminal. The terminal notifies the user of this message. The input is the warning message, and the output is the notification to the user. Specifically, the terminal displays the message in the form of a popup or alert.

[0771] Step 8:

[0772] The user takes action based on the system's warnings and advice. For example, if the user avoids an investment, the device captures the user's behavioral history. The input is the user's behavior, and the output is the captured behavioral history. Specifically, the device captures the behavioral data again.

[0773] Step 9:

[0774] The captured behavioral history is encrypted by the device and sent back to the server. The server decrypts and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. The input is the encrypted feedback data, and the output is an improved risk detection model. Specifically, the server uses the new data for learning and retrains the model.

[0775] (Application example 1)

[0776] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0777] User behavior on the Internet is becoming more diverse, and this includes criminal risks such as investment fraud and phishing. However, it is difficult for users to identify these risks themselves and respond appropriately. Therefore, there is a need for a system that can monitor users' online activities in real time, detect potential criminal risks early, and warn users. In particular, there is a need for a real-time warning system that uses smartphones.

[0778] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0779] In this invention, the server includes: a means for a user terminal to collect user behavioral data via the Internet; a means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; a means for the server to detect potential risks based on the user behavioral data and perform a risk assessment; a means for the server to send the risk assessment results to the user terminal and notify the user; and a means for the user terminal to display a warning message to the user based on the risk assessment results. This makes it possible to detect crime risks in real time while the user is using the Internet and to promptly display a warning.

[0780] A "user terminal" is a device such as a smartphone or computer that a user uses to access the Internet.

[0781] "Behavioral data" is data about activities you perform on the Internet, such as searching, browsing, chatting, and sending emails.

[0782] A "server" is a computer system that analyzes behavioral data received from user terminals and evaluates risks.

[0783] A "database" is a collection of information that stores and manages data on past incidents, accidents, and crimes, and is used by the server to collate the data.

[0784] "Potential risks" are risks of crime, fraud, and other potential future occurrences that are estimated based on user behavioral data.

[0785] "Risk assessment" is the process of analyzing user behavioral data and scoring the likelihood of a crime occurring based on that data.

[0786] A "warning message" is a specific warning message that is sent to the user based on the results of a risk assessment.

[0787] To implement the present invention, it is necessary to construct a system including a user terminal, a server, and a database.

[0788] First, the user's device must have a means of collecting user behavior data in real time via the internet. For example, if a user searches for "high dollar euro investment," the search query is captured. Data is also collected when the user browses the web, chats, or sends and receives emails. This data is encrypted and sent to a server.

[0789] The server decodes the received behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server uses Python and the requests library to collate and analyze the data. Specifically, it uses a machine learning algorithm to compare user behavior data with crime data and score potential risks. The server then performs a risk assessment based on the risk score and generates appropriate warning messages.

[0790] The warning message generated as a result of the risk assessment is sent back to the user's device and notified to the user. The user's device will display the warning message in the form of a pop-up or alert to inform the user of the risk. For example, a specific warning such as "This search query has a risk related to fraud. Please be cautious when investing" may be displayed.

[0791] Additionally, user behavioral feedback is also important. When a user takes action based on the warnings and advice provided by the system, the user's behavioral history is also captured by the user's device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[0792] Examples:

[0793] For example, if a user searches for the keyword "large euro investment," this search query is sent to the server. The server compares this with past fraud data and, if it determines that there is a high risk, returns a warning message to the user saying, "This search query carries a risk of fraud. Be cautious before investing." The user can acknowledge this warning and reconsider their investment.

[0794] Example prompts to input to the generative AI model:

[0795] Generate a program code that determines whether the search keyword "large euro investment" poses a risk of crime, and if so, display a warning message to the user.

[0796] This specific example and example prompt sentences will allow a clearer understanding of the embodiments of the invention.

[0797] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0798] Step 1:

[0799] The user's device collects user behavior data via the Internet. Specifically, it captures data when the user conducts web searches, sends chat messages, or receives emails. For example, a search query such as "large euro investment" is received as input. The device processes this search query by encrypting it and outputs the encrypted data.

[0800] Step 2:

[0801] The user device sends the collected behavioral data to the server. The encrypted search query is input and sent as a POST request to the server's specified API endpoint. As a result, the server receives this data.

[0802] Step 3:

[0803] The server decrypts the behavioral data it receives. The input is the encrypted search query, which the server converts back to plain text using a decryption algorithm. The output is the decrypted search query. For example, "large euro investment" would be the decrypted search query.

[0804] Step 4:

[0805] The server compares the decrypted behavioral data with a database containing data on past incidents, accidents, and crimes. The decrypted search query is input, and the server compares the query with the data in the database. The database contains data on past fraud cases, etc., and checks for a match. The result of the comparison is a risk score. For example, if a match is found with a fraud-related query, a high risk score is obtained.

[0806] Step 5:

[0807] The server performs a risk assessment based on the risk score and generates a warning message. The risk score is the input, and the server determines the level and content of the warning depending on the score. For example, if the risk score is high, a warning message such as "This search query has a risk related to fraud. Be careful when investing" is generated. The warning message is the output.

[0808] Step 6:

[0809] The server sends the generated warning message to the user terminal. The warning message is the input, and is sent as an API request to the user terminal. The user terminal receives this message.

[0810] Step 7:

[0811] The user's device will notify the user of the warning message it has received. The warning message will be input, and the device will display it to the user in the form of a pop-up or alert. This allows the user to check the content of the notification. For example, a message such as "This search query has a risk related to fraud. Please be careful when investing" will be displayed.

[0812] Step 8:

[0813] The user takes action based on the warnings and advice provided by the system. After receiving the warning message, the user may take action, such as reconsidering an investment. This behavioral feedback is captured by the user's device. Behavioral data is input and output as new behavioral data.

[0814] Step 9:

[0815] The user device sends feedback data to the server. New behavioral data is input and sent to the server. The server receives this data.

[0816] Step 10:

[0817] The server analyzes the feedback data and uses it to improve the system. New behavioral data is input and analyzed by the server. The resulting data is used to continuously improve the system and output to improve the accuracy of risk detection.

[0818] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0819] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. This system is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to ensure safe internet use for users.

[0820] User behavior monitoring

[0821] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[0822] The role of the emotional engine

[0823] At the server, the behavioral data is received, decoded, and placed in a processing queue for analysis. Meanwhile, the emotion engine analyzes the user's behavioral data to recognize the user's emotional state. For example, if the user performs an action that indicates intense emotion, the emotion engine will recognize this as "anger."

[0824] Data analysis

[0825] The server combines the received behavioral data with the emotion data from the emotion engine for analysis. The analysis engine compares the behavioral data with a database of past incidents, accidents, and crimes to calculate a risk score. For example, the server compares the keyword "large euro investment" with past fraud data and determines it to be high risk.

[0826] Risk Assessment and Sentiment Analysis

[0827] The server performs a detailed assessment based on the detected risk and the user's emotional state. Specifically, it estimates the likely crime (e.g., investment fraud) and potential damage amount (e.g., 1 million yen) and determines the risk level. The analysis results of the emotion engine are also reflected in the risk assessment, and a risk message is generated taking into account the user's emotional state. As a result of the assessment, a specific warning message such as "This search query carries a risk related to fraud. Be cautious when investing" is generated.

[0828] User Notification

[0829] The server sends the risk assessment results and emotion analysis results to the user's device. The device then notifies the user of the received assessment results and emotion data, displaying a warning in the form of a pop-up or alert. For example, a message might be displayed to the user saying, "This search query carries a risk associated with fraud. Be cautious when investing," along with advice on how to respond appropriately based on the emotion. If the user is expressing anger, psychological advice on how to calm them down is also provided.

[0830] Gathering feedback

[0831] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[0832] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that simultaneously monitor and analyze user behavioral data and emotional data, evaluate risks, and notify users. Specific processing steps will be described later.

[0833] The processing flow will be explained below.

[0834] Step 1:

[0835] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[0836] Step 2:

[0837] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server, along with emotional data such as the user's facial expressions, typing speed, and language used.

[0838] Step 3:

[0839] The server decodes the received behavioral and emotional data and places it in a processing queue for analysis.

[0840] Step 4:

[0841] The emotion engine analyzes the user's behavioral data, facial expression data, and other emotional indicators to recognize the user's emotional state (e.g., anger, sadness, joy, etc.).

[0842] Step 5:

[0843] The server inputs the behavioral data into an analysis engine and compares it with a database containing data on past incidents, accidents, and crimes.

[0844] Step 6:

[0845] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data. For example, the keyword "large euro investment" is considered high risk.

[0846] Step 7:

[0847] The server performs a detailed risk assessment of the detected risk, taking into account the user's emotional state. For example, if there is a possibility of fraud and the emotional engine recognizes "anxiety," the server will raise the risk level.

[0848] Step 8:

[0849] The server generates specific warning messages and advice on how to avoid the risk based on the risk assessment and sentiment analysis results. For example, it generates a message saying, "This search query carries a high risk of fraud. If you are concerned, please consult a professional."

[0850] Step 9:

[0851] The server transmits the generated evaluation results and warning messages to the user terminal.

[0852] Step 10:

[0853] The device will notify the user of the evaluation results and sentiment data it has received and display a warning in the form of a pop-up or alert, such as "This search query carries a risk of fraud. Please be cautious with your investments. Please refer to this link for any concerns you may have."

[0854] Step 11:

[0855] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[0856] Step 12:

[0857] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[0858] Step 13:

[0859] The server receives and analyzes user behavioral feedback and reflects it in system improvements. This process continuously improves the accuracy of the system's risk detection and sentiment analysis.

[0860] Example 2

[0861] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0862] Criminal activities on the Internet are becoming more sophisticated every day, threatening users' safety. Online fraud and cybercrime, in particular, can have serious consequences for victims. Therefore, there is a need for an effective system that can monitor users' online activities and detect potential crime risks early. In addition, there is a need for a system that can analyze users' emotional state and provide appropriate risk assessments to provide more effective crime prevention measures.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0864] In this invention, the server includes means for encrypting behavioral data captured by the user terminal and transmitting it to the server, means for the server to decrypt the behavioral data received and place it in a processing queue, means for the server to compare the behavioral data received with a database containing past incident / accident / crime data, means for an emotion engine to analyze the user's behavioral data and recognize the user's emotional state, means for the server to detect potential risks based on the user's behavioral data and emotional data and perform a risk assessment, and means for the server to transmit the risk assessment results and the user's emotional state to the user terminal and notify the user. This makes it possible to detect criminal risks in the user's online activities early and issue appropriate warnings.

[0865] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to access the Internet.

[0866] "Behavioral data" is information about the activities you perform online, such as searching, chatting, posting, and receiving emails.

[0867] "AES encryption" is a method of encrypting data using the Advanced Encryption Standard.

[0868] A "server" is a computer system that receives data from user terminals via a network, analyzes it, compares it with a database, and notifies the user.

[0869] A "processing queue" is a data structure that temporarily stores data waiting to be processed on a server.

[0870] A "database" is a system that systematically accumulates and manages data related to past incidents, accidents, and crimes.

[0871] An "emotion engine" is a combination of algorithms and software that analyzes user behavioral data and recognizes the user's emotional state.

[0872] "Emotional Data" is information about the user's emotional state analyzed by the emotion engine.

[0873] A "risk score" is a number that represents the degree of potential risk, calculated based on a user's behavioral and emotional data.

[0874] "Risk assessment" is the process of using risk scores and other analytical results to determine how risky a particular action is.

[0875] A "warning message" is a message containing a warning or advice that is sent to the user based on the results of a risk assessment.

[0876] The system of the present invention is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to enable users to engage in safe online activities.

[0877] User behavior monitoring

[0878] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time and encrypts it using AES encryption. The encrypted data is then sent to the server. For example, if a user enters the search query "large euro investment," the search query is captured by the device, encrypted, and sent to the server.

[0879] Receiving and Decrypting Data

[0880] The server receives the encrypted behavioral data from the user terminal, decrypts the received data using AES encryption, and places it in the processing queue. The server then removes the data from the processing queue.

[0881] Analysis by emotion engine

[0882] The server passes the extracted behavioral data to the emotion engine, which then analyzes the user's behavioral data to recognize the user's emotional state. For example, if a user frequently uses emotional words, the emotion engine will recognize this as "anger."

[0883] Risk Analysis

[0884] The server combines the emotional data received from the emotion engine with the behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server calculates a risk score based on the user's behavior and emotional state, and performs a risk assessment. This risk score indicates the potential risk level of the user's online behavior. For example, the keyword "large euro investment" matches past fraud data and is deemed high risk.

[0885] Risk assessment and warning message generation

[0886] The server then performs a specific risk assessment based on the calculated risk score and emotional state and generates a warning message, such as "This search query carries a risk associated with fraud. Be cautious when investing."

[0887] User Notification

[0888] The generated risk assessment results and sentiment data are sent from the server to the user's device, which then notifies the user in real time. The device then displays a message to the user in the form of a pop-up or alert. For example, a warning message such as "This search query carries a risk associated with fraud. Please invest with caution."

[0889] Gathering feedback

[0890] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured again by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[0891] Prompt Sentence Examples

[0892] Analyze user search history for "large euro investment" to calculate crime risk score and perform sentiment analysis.

[0893] "Analyze the relationship between the words used by users in chat and their emotions, and generate warning messages based on that."

[0894] As described above, the system of the present invention can simultaneously monitor and analyze user behavioral data and emotional data, perform risk assessment, and notify users, thereby reducing the risk of crime on the Internet. The specific processing steps will be described in detail below.

[0895] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0896] Step 1:

[0897] Users perform activities online such as searching, writing, chatting, and receiving emails.

[0898] Input: User behavior (e.g., search query "high dollar euro investment")

[0899] What happens: A user opens a web browser, enters specific keywords into the search bar, and performs a search.

[0900] Step 2:

[0901] The device captures user behavior data in real time and encrypts the captured data using the AES encryption method.

[0902] Input: User behavior data

[0903] Data processing: Capture and AES encryption of behavioral data

[0904] What it does: The device captures the user's search query and encodes the data using AES encryption.

[0905] Output: Encrypted behavioral data

[0906] Step 3:

[0907] The device transmits the encrypted behavioral data to the server.

[0908] Input: Encrypted behavioral data

[0909] What happens: Your device sends encrypted data over the internet to a server.

[0910] Output: Encrypted data received by the server

[0911] Step 4:

[0912] The server decodes the received behavioral data and places it in a processing queue.

[0913] Input: Encrypted behavioral data

[0914] Data processing: AES data decryption

[0915] What happens: The server decrypts the encrypted data and enqueues (places) it in the processing queue.

[0916] Output: Decoded behavioral data, data in the processing queue

[0917] Step 5:

[0918] The server passes the behavioral data to the emotion engine, which recognizes the user's emotional state.

[0919] Input: Behavioral data

[0920] Data Computation: Emotion Analysis with Emotion Engine

[0921] Specific operation: The server retrieves the behavioral data from the processing queue and passes it to the emotion engine to begin analysis. The emotion engine analyzes the data and assigns a label to the user's emotional state (e.g., anxiety, anger).

[0922] Output: Emotion data (e.g., user expresses emotion "anxiety")

[0923] Step 6:

[0924] The server compares the behavioral and emotional data with a database containing past incident, accident, and crime data to calculate a risk score.

[0925] Input: Behavioral data, emotion data

[0926] Data calculation: Matching with database, calculating risk score

[0927] Specific operation: The server compares the behavioral data of "large euro investment" and the emotional data of "anxiety" with fraud data in the database and calculates a score that qualifies as high risk.

[0928] Output: Risk score (e.g. 80 / 100)

[0929] Step 7:

[0930] The server generates a warning message based on the detected risk and emotional state.

[0931] Input: Risk score, sentiment data

[0932] Data calculations: risk assessment, message generation

[0933] What it does: Based on the risk score and sentiment data, the server generates a warning message saying, "This search query carries a risk of fraud. Invest with caution."

[0934] Output: Warning message

[0935] Step 8:

[0936] The server sends the warning message and emotion data to the user terminal.

[0937] Input: Warning message, emotion data

[0938] Specific operation: The server sends the generated message and emotion data to the user's device.

[0939] Output: Messages and data received by the user terminal

[0940] Step 9:

[0941] The device will notify the user of the received warning message.

[0942] Input: Warning message, emotion data

[0943] What happens: The user's device will display a pop-up message saying, "This search query carries the risk of fraud. Invest with caution."

[0944] Output: The warning message displayed to the user

[0945] Step 10:

[0946] The user may take action based on the warning, for example, by avoiding the investment.

[0947] Input: The warning message displayed to the user

[0948] Specific behavior: The user sees the warning message and takes action to avoid the investment based on its contents.

[0949] Output: The user's new behavior

[0950] Step 11:

[0951] The device captures the user's behavioral history and sends it to the server.

[0952] Input: New user action

[0953] Specific operation: The device captures the user's behavior again and sends it to the server as a behavior history.

[0954] Output: Action history received by the server

[0955] Step 12:

[0956] The server analyzes user behavior history and uses it to improve the system.

[0957] Input: User behavior history

[0958] Data Calculation: Feedback Analysis

[0959] What it does: The server analyzes user feedback data to help improve risk detection and sentiment analysis algorithms.

[0960] Output: Improved system algorithm

[0961] (Application example 2)

[0962] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0963] Conventional security systems for internet use can detect risks based on user behavior data, but they are unable to evaluate risks by taking into account the user's emotional state. This makes it difficult to provide appropriate warnings and advice based on the user's psychological state, and ultimately makes it impossible to present the best countermeasures for the user. Furthermore, the methods for presenting warning messages are limited, which sometimes does not lead to user understanding or behavioral changes. A new system is needed to solve these issues.

[0964] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0965] In this invention, the server includes: means for a user terminal to collect user behavioral data via the Internet; means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; means for the server to detect potential risks and perform risk assessments based on the user behavioral data; means for an emotion engine to analyze the user behavioral data and recognize the user's emotional state; means for the server to transmit the risk assessment results and emotion analysis results to the user terminal and notify the user; and means for the user terminal to display warning messages in the form of pop-ups or alerts. This enables real-time risk assessments that take the user's emotional state into consideration and the provision of appropriate warning messages.

[0966] A "user terminal" is a device for collecting and displaying user behavior data via the Internet.

[0967] "Behavioral data" is information about what you do online, such as searches, posts, chats, and emails you receive.

[0968] The "server" is a central processing unit that analyzes behavioral data received from a user terminal and transmits the results to the user terminal.

[0969] A "database" is an information storage system that holds data on past incidents, accidents, and crimes, and allows the server to collate and analyze the data.

[0970] "Potential risk" refers to possible danger or crime that can be estimated based on behavioral data.

[0971] "Risk assessment" is the process by which the server compares behavioral data with a database to determine the severity and likelihood of potential risks.

[0972] An "emotion engine" is software that analyzes user behavioral data and recognizes their emotional state.

[0973] "Emotional state" refers to the psychological state or mood a user exhibits when engaging in online activities.

[0974] "Notification" refers to the act of informing the user of the risk assessment results and emotion analysis results received by the user's device from the server.

[0975] A "pop-up or alert-style warning message" is a message that is visually displayed on the user's device to warn or alert the user.

[0976] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. The system of this invention is composed of a user terminal, a server, a database, and an emotion engine, and each element works in cooperation to ensure safe internet use for users.

[0977] The user device collects real-time behavioral data, such as searches, posts, chats, and e-mails that the user conducts over the Internet. The user device also encrypts the collected behavioral data before sending it to the server, thereby ensuring data security while protecting the user's privacy.

[0978] The server decodes the received behavioral data in real time and compares it with a database of past incidents, accidents, and crimes. The server is equipped with a machine learning algorithm that learns from past data to detect potential risks and perform risk assessments. In addition, the server is equipped with an emotion engine that can analyze user behavioral data and recognize emotional states.

[0979] The server sends risk assessment results based on behavioral data and emotion analysis results to the user's device. The user's device notifies the user of the received risk assessment and emotion analysis results, displaying warning messages in the form of pop-ups or alerts. This allows the user to recognize the potential risks posed by their own behavior and take appropriate measures.

[0980] For example, if a user searches for "large euro investment," this search query is captured as user behavior data and sent to the server. The server compares this search query with past fraud data and evaluates it as high risk. At the same time, the emotion engine recognizes the user's emotional state as "neutral." As a result, the server sends a risk warning message to the user's device saying, "This search query carries a risk associated with fraud. Be cautious with your investments.", along with emotion-based advice such as, "Your emotions are currently stable. Please remain calm."

[0981] Example prompt sentence:

[0982] User Activity: Search

[0983] User Input: Large Euro Investment

[0984] Detected Emotion: Neutral

[0985] Risk assessment result: High

[0986] Server response message: "This search query carries a risk of fraud. Invest with caution.", "Emotions are currently stable. Please remain calm."

[0987] As described above, the system of the present invention simultaneously monitors and analyzes user behavioral data and emotional data, performs real-time risk assessment, and provides appropriate warning messages to users, thereby reducing the risk of crime on the Internet.

[0988] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0989] Step 1:

[0990] When a user searches, posts, or chats on the Internet, the user device captures the behavioral data. At this point, the input is the user's online activity data, and the output is the captured behavioral data.

[0991] Step 2:

[0992] The user device encrypts the captured behavioral data and sends it to the server. The input is the captured behavioral data, and the output is the encrypted behavioral data. This behavioral data is transferred to the server via the network.

[0993] Step 3:

[0994] The server receives and decrypts the encrypted behavioral data. The input is the encrypted behavioral data and the output is the decrypted behavioral data. The decrypted data is queued within the server for analysis.

[0995] Step 4:

[0996] The machine learning algorithm in the server compares the decoded behavioral data with past incident / accident / crime data in the database to detect potential risks. The input is the decoded behavioral data and the data in the database, and the output is the risk assessment result. In this process, certain behaviors may be judged to be high risk because they match with past crime data.

[0997] Step 5:

[0998] The emotion engine analyzes the user's behavioral data to recognize the user's emotional state. The input is the decoded behavioral data, and the output is the emotional state data. The emotion engine identifies the specific emotion the user expressed (e.g., anger or neutral).

[0999] Step 6:

[1000] The server combines the risk assessment results and emotional state data to generate a comprehensive risk assessment message. The inputs are the risk assessment results and emotional state data, and the output is a warning message and emotion-based advice for the user.

[1001] Step 7:

[1002] The server generates risk assessment messages and sends advice based on emotions to the user terminal. The input is the generated message, and the output is the sent message.

[1003] Step 8:

[1004] The user device receives risk assessment messages and advice and notifies them to the user in the form of popups or alerts. The input is the received message, and the output is the displayed warning message and advice, so the user can take appropriate action.

[1005] For example, if a user searches for "high euro investment," the search query is captured, encrypted, and sent to the server. The server decrypts it, compares it with fraud data, and determines that it poses a high risk. The emotion engine then recognizes the user's emotion as "neutral." As a result, a message from the server warning the user that "This search query carries a fraud risk. Be cautious when investing," along with advice that "Emotions are currently stable. Please remain calm," is sent to the user's device and displayed to the user.

[1006] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1007] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1008] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1009] [Fourth embodiment]

[1010] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1011] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1012] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1013] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1014] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1015] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1016] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1017] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1018] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1019] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1020] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1021] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1022] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1023] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks at an early stage. This system is composed of user terminals, a server, and a database, and these elements work together to ensure users' safe use of the Internet.

[1024] User behavior monitoring

[1025] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[1026] Data analysis

[1027] The server decodes the behavioral data it receives and compares it with a database of past incidents, accidents, and crimes. The server then analyzes the data using machine learning algorithms and rule-based systems to calculate a risk score. For example, the server may compare the keyword "large euro investment" with past fraud data and determine that it poses a high risk.

[1028] Risk Assessment

[1029] The server then performs a detailed assessment of the detected risk. This is the process of estimating the specific crime (e.g., investment fraud) and the potential amount of damage (e.g., 1 million yen) and determining the risk level. As a result of the assessment, a specific warning message is generated, such as "This search query carries a risk of fraud. Be cautious when investing."

[1030] User Notification

[1031] The server sends the risk assessment results to the user's device. The device notifies the user of the received assessment results and displays a warning in the form of a pop-up or alert. For example, the user might see a message saying, "This search query carries a risk associated with fraud. Be cautious when investing." The user can then review the warning and decide whether to reconsider their investment.

[1032] Gathering feedback

[1033] Users take action based on the warnings and advice provided by the system. For example, if a user avoids an investment, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[1034] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that monitor and analyze user behavior data, perform risk assessment, and notify users. The specific processing steps will be described later.

[1035] The processing flow will be explained below.

[1036] Step 1:

[1037] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[1038] Step 2:

[1039] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server.

[1040] Step 3:

[1041] The server decodes the received behavioral data and places it in a processing queue for analysis.

[1042] Step 4:

[1043] The server launches an analysis engine and compares the behavioral data with a database containing data on past incidents, accidents, and crimes.

[1044] Step 5:

[1045] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data.

[1046] Step 6:

[1047] A detailed assessment is carried out for the risk detected on the server. Specifically, the potential crime and potential damage amount are calculated, and the risk level is assessed.

[1048] Step 7:

[1049] The server generates a warning message and workarounds for the user based on the risk assessment results.

[1050] Step 8:

[1051] The server transmits the generated evaluation results and warning messages to the user terminal.

[1052] Step 9:

[1053] The device will notify the user of the evaluation results received and display a warning in the form of a pop-up or alert.

[1054] Step 10:

[1055] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[1056] Step 11:

[1057] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[1058] Step 12:

[1059] The server receives and analyzes user feedback and reflects it in system improvements, a process that continuously improves the system's detection accuracy and risk assessment algorithms.

[1060] Example 1

[1061] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1062] In the current Internet usage environment, there are concerns that users may unintentionally engage in behavior that poses a high risk of crime. Furthermore, existing crime prevention systems have difficulty monitoring and analyzing user behavior in real time and detecting risks early. Furthermore, there is a lack of mechanisms for effectively collecting feedback based on user behavior to improve the accuracy of the system. As a result, the safety of Internet use remains insufficient.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1064] In this invention, the server includes means for the user terminal to capture user behavioral data in real time via the Internet, encrypt it, and send it to the server, means for the server to decrypt the received encrypted behavioral data and compare it with a database containing past incident, accident, and crime data, means for the server to calculate a risk score based on the user behavioral data using a machine learning algorithm or a rule-based system and perform a risk assessment, means for the server to generate a warning message based on the risk assessment result and send it to the user terminal to notify the user, means for the user terminal to capture feedback regarding the user's behavior, encrypt it, and send it to the server, and means for the server to analyze the feedback received and use it to improve the system. This makes it possible to monitor and analyze user behavioral data in real time, detect and notify potential risks early, and improve the accuracy of the system based on the feedback.

[1065] "User terminal" refers to an electronic device that allows a user to perform operations or take actions via the Internet, including personal computers, smartphones, tablets, etc.

[1066] "Behavioral data" refers to data related to specific operations and activities that users perform on the Internet, such as searching, posting, chatting, and receiving emails.

[1067] A "server" is a central computer system that stores and processes data over a network, and analyzes and records data sent from user terminals.

[1068] "Encryption" is a security technology that converts data into a format that cannot be deciphered by third parties, and includes algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman).

[1069] A "database" is an information management system for storing and managing data on past incidents, accidents, and crimes, and it allows for efficient searching and matching of large amounts of information.

[1070] A "machine learning algorithm" is a program that automatically learns patterns and rules from data and makes predictions and classifications for new data, and includes decision trees, random forests, neural networks, etc.

[1071] A "rule-based system" is a system that analyzes and evaluates data based on pre-set rules and conditions, and makes inferences and judgments according to fixed rules.

[1072] A "risk score" is a number that indicates the degree of risk calculated based on a user's behavioral data, and is used to evaluate the level of criminal risk.

[1073] A "warning message" is a message that is generated based on the risk assessment results and is used to alert the user, and includes specific risk details and advice.

[1074] "Feedback" refers to information about actions taken by users in response to warnings and advice provided by the system, and is data used to improve and optimize the system.

[1075] The present invention is a system for strengthening crime prevention measures by monitoring users' Internet activity and detecting crime risks at an early stage. Specific procedures for implementing the present invention, as well as the hardware and software used, are described in detail below.

[1076] First, the user's device captures user behavior data in real time via the internet, using browser extensions or dedicated application programs. For example, when a user searches for "large euro investment," the search query is captured.

[1077] The captured behavioral data is then encrypted by the device using encryption techniques such as AES (Advanced Encryption Standard) and sent to a server using the HTTPS protocol.

[1078] The server then decrypts the encrypted data, again using AES, and compares it with a database containing past incident and crime data. This database could be an SQL database or a NoSQL database, for example.

[1079] The server then uses machine learning algorithms and rule-based systems to further analyze the decrypted data, using libraries such as Scikit-learn and TensorFlow. Machine learning algorithms such as random forests and neural networks are used. A risk score is calculated based on these algorithms.

[1080] The server then performs a specific risk assessment based on the risk score, including a specific crime (e.g., fraud) and potential damage amount (e.g., 1 million yen). Once the risk assessment is complete, a warning message is generated. For example, a specific message such as "This search query carries a risk of fraud. Be cautious when investing." is created.

[1081] The generated warning message is sent from the server to the user's device, and the device notifies the user. The notification is in the form of a pop-up or alert. The user's screen will display the message, "This search query carries a risk of fraud. Please invest with caution."

[1082] Any actions the user takes based on the system's warnings and advice are again captured by the device. The device encrypts this behavioral history and sends it to the server. The server receives, decrypts, and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. For example, it adds new user behavior patterns to the learning data and retrains the model.

[1083] Through these steps, the system can consistently monitor and analyze user behavior data from start to finish, quickly detecting and notifying users of risks. This process involves a series of processing interactions: capturing, encrypting, decrypting, analyzing, and notifying users of user behavior data.

[1084] Example prompts to be input to the generative AI model:

[1085] "Please conduct a risk assessment of the user's online search for 'high dollar euro investment' and inform the user of the results. Please also explain what data processing and algorithms you use."

[1086] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1087] Step 1:

[1088] When a user performs online activities such as searching, posting, chatting, or receiving emails on the Internet, this behavioral data is captured in real time by the user's device. Specifically, the behavioral data is acquired by browser extensions or dedicated applications. The input is the user's specific Internet activity, and the output is the captured behavioral data.

[1089] Step 2:

[1090] The captured behavioral data is encrypted by the device. Here, AES (Advanced Encryption Standard) is used. This process is performed to protect the data from being read by third parties. The input is the captured behavioral data, and the output is the encrypted data. Specifically, the device encrypts the data using the AES algorithm.

[1091] Step 3:

[1092] The encrypted data is sent to the server using the HTTPS protocol, which ensures data confidentiality and integrity. The input is the encrypted behavioral data, and the output is the data sent to the server. Specifically, the device establishes an HTTPS connection and sends the data.

[1093] Step 4:

[1094] The server decrypts the received encrypted data. AES is used again for decryption, which returns the data to the original behavioral data. The input is the encrypted data, and the output is the decrypted data. Specifically, the server decrypts the data using the AES algorithm.

[1095] Step 5:

[1096] The server compares the decoded data with a database containing data on past incidents, accidents, and crimes. The server analyzes this data and calculates a risk score. A machine learning algorithm (e.g., random forest or neural network) is used for the analysis. The input is the decoded behavioral data, and the output is a risk score. Specifically, the server inputs the data into a machine learning model and obtains a risk score.

[1097] Step 6:

[1098] The server performs a specific risk assessment based on the risk score, including the name of the crime and the potential damage amount. The server generates a warning message based on the risk assessment result. The input is the risk score and the output is the warning message. Specifically, the server classifies the risk based on the assessment criteria and creates an appropriate message.

[1099] Step 7:

[1100] The generated warning message is sent from the server to the user terminal. The terminal notifies the user of this message. The input is the warning message, and the output is the notification to the user. Specifically, the terminal displays the message in the form of a popup or alert.

[1101] Step 8:

[1102] The user takes action based on the system's warnings and advice. For example, if the user avoids an investment, the device captures the user's behavioral history. The input is the user's behavior, and the output is the captured behavioral history. Specifically, the device captures the behavioral data again.

[1103] Step 9:

[1104] The captured behavioral history is encrypted by the device and sent back to the server. The server decrypts and analyzes this feedback data. Based on the analysis results, the system improves the risk detection algorithm. The input is the encrypted feedback data, and the output is an improved risk detection model. Specifically, the server uses the new data for learning and retrains the model.

[1105] (Application example 1)

[1106] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1107] User behavior on the Internet is becoming more diverse, and this includes criminal risks such as investment fraud and phishing. However, it is difficult for users to identify these risks themselves and respond appropriately. Therefore, there is a need for a system that can monitor users' online activities in real time, detect potential criminal risks early, and warn users. In particular, there is a need for a real-time warning system that uses smartphones.

[1108] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1109] In this invention, the server includes: a means for a user terminal to collect user behavioral data via the Internet; a means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; a means for the server to detect potential risks based on the user behavioral data and perform a risk assessment; a means for the server to send the risk assessment results to the user terminal and notify the user; and a means for the user terminal to display a warning message to the user based on the risk assessment results. This makes it possible to detect crime risks in real time while the user is using the Internet and to promptly display a warning.

[1110] A "user terminal" is a device such as a smartphone or computer that a user uses to access the Internet.

[1111] "Behavioral data" is data about activities you perform on the Internet, such as searching, browsing, chatting, and sending emails.

[1112] A "server" is a computer system that analyzes behavioral data received from user terminals and evaluates risks.

[1113] A "database" is a collection of information that stores and manages data on past incidents, accidents, and crimes, and is used by the server to collate the data.

[1114] "Potential risks" are risks of crime, fraud, and other potential future occurrences that are estimated based on user behavioral data.

[1115] "Risk assessment" is the process of analyzing user behavioral data and scoring the likelihood of a crime occurring based on that data.

[1116] A "warning message" is a specific warning message that is sent to the user based on the results of a risk assessment.

[1117] To implement the present invention, it is necessary to construct a system including a user terminal, a server, and a database.

[1118] First, the user's device must have a means of collecting user behavior data in real time via the internet. For example, if a user searches for "high dollar euro investment," the search query is captured. Data is also collected when the user browses the web, chats, or sends and receives emails. This data is encrypted and sent to a server.

[1119] The server decodes the received behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server uses Python and the requests library to collate and analyze the data. Specifically, it uses a machine learning algorithm to compare user behavior data with crime data and score potential risks. The server then performs a risk assessment based on the risk score and generates appropriate warning messages.

[1120] The warning message generated as a result of the risk assessment is sent back to the user's device and notified to the user. The user's device will display the warning message in the form of a pop-up or alert to inform the user of the risk. For example, a specific warning such as "This search query has a risk related to fraud. Please be cautious when investing" may be displayed.

[1121] Additionally, user behavioral feedback is also important. When a user takes action based on the warnings and advice provided by the system, the user's behavioral history is also captured by the user's device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection.

[1122] Examples:

[1123] For example, if a user searches for the keyword "large euro investment," this search query is sent to the server. The server compares this with past fraud data and, if it determines that there is a high risk, returns a warning message to the user saying, "This search query carries a risk of fraud. Be cautious before investing." The user can acknowledge this warning and reconsider their investment.

[1124] Example prompts to input to the generative AI model:

[1125] Generate a program code that determines whether the search keyword "large euro investment" poses a risk of crime, and if so, display a warning message to the user.

[1126] This specific example and example prompt sentences will allow a clearer understanding of the embodiments of the invention.

[1127] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1128] Step 1:

[1129] The user's device collects user behavior data via the Internet. Specifically, it captures data when the user conducts web searches, sends chat messages, or receives emails. For example, a search query such as "large euro investment" is received as input. The device processes this search query by encrypting it and outputs the encrypted data.

[1130] Step 2:

[1131] The user device sends the collected behavioral data to the server. The encrypted search query is input and sent as a POST request to the server's specified API endpoint. As a result, the server receives this data.

[1132] Step 3:

[1133] The server decrypts the behavioral data it receives. The input is the encrypted search query, which the server converts back to plain text using a decryption algorithm. The output is the decrypted search query. For example, "large euro investment" would be the decrypted search query.

[1134] Step 4:

[1135] The server compares the decrypted behavioral data with a database containing data on past incidents, accidents, and crimes. The decrypted search query is input, and the server compares the query with the data in the database. The database contains data on past fraud cases, etc., and checks for a match. The result of the comparison is a risk score. For example, if a match is found with a fraud-related query, a high risk score is obtained.

[1136] Step 5:

[1137] The server performs a risk assessment based on the risk score and generates a warning message. The risk score is the input, and the server determines the level and content of the warning depending on the score. For example, if the risk score is high, a warning message such as "This search query has a risk related to fraud. Be careful when investing" is generated. The warning message is the output.

[1138] Step 6:

[1139] The server sends the generated warning message to the user terminal. The warning message is the input, and is sent as an API request to the user terminal. The user terminal receives this message.

[1140] Step 7:

[1141] The user's device will notify the user of the warning message it has received. The warning message will be input, and the device will display it to the user in the form of a pop-up or alert. This allows the user to check the content of the notification. For example, a message such as "This search query has a risk related to fraud. Please be careful when investing" will be displayed.

[1142] Step 8:

[1143] The user takes action based on the warnings and advice provided by the system. After receiving the warning message, the user may take action, such as reconsidering an investment. This behavioral feedback is captured by the user's device. Behavioral data is input and output as new behavioral data.

[1144] Step 9:

[1145] The user device sends feedback data to the server. New behavioral data is input and sent to the server. The server receives this data.

[1146] Step 10:

[1147] The server analyzes the feedback data and uses it to improve the system. New behavioral data is input and analyzed by the server. The resulting data is used to continuously improve the system and output to improve the accuracy of risk detection.

[1148] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1149] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. This system is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to ensure safe internet use for users.

[1150] User behavior monitoring

[1151] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time, encrypts it, and sends it to the server. For example, when a user searches for "large euro investment," the search query is captured and sent to the server.

[1152] The role of the emotional engine

[1153] At the server, the behavioral data is received, decoded, and placed in a processing queue for analysis. Meanwhile, the emotion engine analyzes the user's behavioral data to recognize the user's emotional state. For example, if the user performs an action that indicates intense emotion, the emotion engine will recognize this as "anger."

[1154] Data analysis

[1155] The server combines the received behavioral data with the emotion data from the emotion engine for analysis. The analysis engine compares the behavioral data with a database of past incidents, accidents, and crimes to calculate a risk score. For example, the server compares the keyword "large euro investment" with past fraud data and determines it to be high risk.

[1156] Risk Assessment and Sentiment Analysis

[1157] The server performs a detailed assessment based on the detected risk and the user's emotional state. Specifically, it estimates the likely crime (e.g., investment fraud) and potential damage amount (e.g., 1 million yen) and determines the risk level. The analysis results of the emotion engine are also reflected in the risk assessment, and a risk message is generated taking into account the user's emotional state. As a result of the assessment, a specific warning message such as "This search query carries a risk related to fraud. Be cautious when investing" is generated.

[1158] User Notification

[1159] The server sends the risk assessment results and emotion analysis results to the user's device. The device then notifies the user of the received assessment results and emotion data, displaying a warning in the form of a pop-up or alert. For example, a message might be displayed to the user saying, "This search query carries a risk associated with fraud. Be cautious when investing," along with advice on how to respond appropriately based on the emotion. If the user is expressing anger, psychological advice on how to calm them down is also provided.

[1160] Gathering feedback

[1161] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[1162] As described above, the system according to the present invention reduces the risk of crime on the Internet through a series of processes that simultaneously monitor and analyze user behavioral data and emotional data, evaluate risks, and notify users. Specific processing steps will be described later.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] Users perform online activities such as searching, posting, chatting, and receiving emails on the Internet.

[1166] Step 2:

[1167] The device captures this behavioral data in real time, encrypts it, and transmits it securely to a server, along with emotional data such as the user's facial expressions, typing speed, and language used.

[1168] Step 3:

[1169] The server decodes the received behavioral and emotional data and places it in a processing queue for analysis.

[1170] Step 4:

[1171] The emotion engine analyzes the user's behavioral data, facial expression data, and other emotional indicators to recognize the user's emotional state (e.g., anger, sadness, joy, etc.).

[1172] Step 5:

[1173] The server inputs the behavioral data into an analysis engine and compares it with a database containing data on past incidents, accidents, and crimes.

[1174] Step 6:

[1175] The server uses machine learning algorithms and rule-based systems to calculate a risk score for the behavioral data. For example, the keyword "large euro investment" is considered high risk.

[1176] Step 7:

[1177] The server performs a detailed risk assessment of the detected risk, taking into account the user's emotional state. For example, if there is a possibility of fraud and the emotional engine recognizes "anxiety," the server will raise the risk level.

[1178] Step 8:

[1179] The server generates specific warning messages and advice on how to avoid the risk based on the risk assessment and sentiment analysis results. For example, it generates a message saying, "This search query carries a high risk of fraud. If you are concerned, please consult a professional."

[1180] Step 9:

[1181] The server transmits the generated evaluation results and warning messages to the user terminal.

[1182] Step 10:

[1183] The device will notify the user of the evaluation results and sentiment data it has received and display a warning in the form of a pop-up or alert, such as "This search query carries a risk of fraud. Please be cautious with your investments. Please refer to this link for any concerns you may have."

[1184] Step 11:

[1185] The user reviews the notification and takes action based on the instructions or advice provided, such as avoiding the investment or deleting the phishing email.

[1186] Step 12:

[1187] The device again captures feedback on the user's behavior and sends it to the server as behavioral history data.

[1188] Step 13:

[1189] The server receives and analyzes user behavioral feedback and reflects it in system improvements. This process continuously improves the accuracy of the system's risk detection and sentiment analysis.

[1190] Example 2

[1191] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1192] Criminal activities on the Internet are becoming more sophisticated every day, threatening users' safety. Online fraud and cybercrime, in particular, can have serious consequences for victims. Therefore, there is a need for an effective system that can monitor users' online activities and detect potential crime risks early. In addition, there is a need for a system that can analyze users' emotional state and provide appropriate risk assessments to provide more effective crime prevention measures.

[1193] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1194] In this invention, the server includes means for encrypting behavioral data captured by the user terminal and transmitting it to the server, means for the server to decrypt the behavioral data received and place it in a processing queue, means for the server to compare the behavioral data received with a database containing past incident / accident / crime data, means for an emotion engine to analyze the user's behavioral data and recognize the user's emotional state, means for the server to detect potential risks based on the user's behavioral data and emotional data and perform a risk assessment, and means for the server to transmit the risk assessment results and the user's emotional state to the user terminal and notify the user. This makes it possible to detect criminal risks in the user's online activities early and issue appropriate warnings.

[1195] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to access the Internet.

[1196] "Behavioral data" is information about the activities you perform online, such as searching, chatting, posting, and receiving emails.

[1197] "AES encryption" is a method of encrypting data using the Advanced Encryption Standard.

[1198] A "server" is a computer system that receives data from user terminals via a network, analyzes it, compares it with a database, and notifies the user.

[1199] A "processing queue" is a data structure that temporarily stores data waiting to be processed on a server.

[1200] A "database" is a system that systematically accumulates and manages data related to past incidents, accidents, and crimes.

[1201] An "emotion engine" is a combination of algorithms and software that analyzes user behavioral data and recognizes the user's emotional state.

[1202] "Emotional Data" is information about the user's emotional state analyzed by the emotion engine.

[1203] A "risk score" is a number that represents the degree of potential risk, calculated based on a user's behavioral and emotional data.

[1204] "Risk assessment" is the process of using risk scores and other analytical results to determine how risky a particular action is.

[1205] A "warning message" is a message containing a warning or advice that is sent to the user based on the results of a risk assessment.

[1206] The system of the present invention is composed of a user terminal, a server, a database, and an emotion engine, and these elements work together to enable users to engage in safe online activities.

[1207] User behavior monitoring

[1208] When a user searches, posts, chats, receives emails, or engages in other online activities, the device captures this behavioral data in real time and encrypts it using AES encryption. The encrypted data is then sent to the server. For example, if a user enters the search query "large euro investment," the search query is captured by the device, encrypted, and sent to the server.

[1209] Receiving and Decrypting Data

[1210] The server receives the encrypted behavioral data from the user terminal, decrypts the received data using AES encryption, and places it in the processing queue. The server then removes the data from the processing queue.

[1211] Analysis by emotion engine

[1212] The server passes the extracted behavioral data to the emotion engine, which then analyzes the user's behavioral data to recognize the user's emotional state. For example, if a user frequently uses emotional words, the emotion engine will recognize this as "anger."

[1213] Risk Analysis

[1214] The server combines the emotional data received from the emotion engine with the behavioral data and compares it with a database containing data on past incidents, accidents, and crimes. The server calculates a risk score based on the user's behavior and emotional state, and performs a risk assessment. This risk score indicates the potential risk level of the user's online behavior. For example, the keyword "large euro investment" matches past fraud data and is deemed high risk.

[1215] Risk assessment and warning message generation

[1216] The server then performs a specific risk assessment based on the calculated risk score and emotional state and generates a warning message, such as "This search query carries a risk associated with fraud. Be cautious when investing."

[1217] User Notification

[1218] The generated risk assessment results and sentiment data are sent from the server to the user's device, which then notifies the user in real time. The device then displays a message to the user in the form of a pop-up or alert. For example, a warning message such as "This search query carries a risk associated with fraud. Please invest with caution."

[1219] Gathering feedback

[1220] Users take action based on the warnings and advice provided by the system. For example, if a user avoids investing, their behavioral history is captured again by the device and sent to the server. The server analyzes this feedback and uses it to improve the system. This allows the system to continuously improve the accuracy of risk detection and sentiment analysis.

[1221] Prompt Sentence Examples

[1222] Analyze user search history for "large euro investment" to calculate crime risk score and perform sentiment analysis.

[1223] "Analyze the relationship between the words used by users in chat and their emotions, and generate warning messages based on that."

[1224] As described above, the system of the present invention can simultaneously monitor and analyze user behavioral data and emotional data, perform risk assessment, and notify users, thereby reducing the risk of crime on the Internet. The specific processing steps will be described in detail below.

[1225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1226] Step 1:

[1227] Users perform activities online such as searching, writing, chatting, and receiving emails.

[1228] Input: User behavior (e.g., search query "high dollar euro investment")

[1229] What happens: A user opens a web browser, enters specific keywords into the search bar, and performs a search.

[1230] Step 2:

[1231] The device captures user behavior data in real time and encrypts the captured data using the AES encryption method.

[1232] Input: User behavior data

[1233] Data processing: Capture and AES encryption of behavioral data

[1234] What it does: The device captures the user's search query and encodes the data using AES encryption.

[1235] Output: Encrypted behavioral data

[1236] Step 3:

[1237] The device transmits the encrypted behavioral data to the server.

[1238] Input: Encrypted behavioral data

[1239] What happens: Your device sends encrypted data over the internet to a server.

[1240] Output: Encrypted data received by the server

[1241] Step 4:

[1242] The server decodes the received behavioral data and places it in a processing queue.

[1243] Input: Encrypted behavioral data

[1244] Data processing: AES data decryption

[1245] What happens: The server decrypts the encrypted data and enqueues (places) it in the processing queue.

[1246] Output: Decoded behavioral data, data in the processing queue

[1247] Step 5:

[1248] The server passes the behavioral data to the emotion engine, which recognizes the user's emotional state.

[1249] Input: Behavioral data

[1250] Data Computation: Emotion Analysis with Emotion Engine

[1251] Specific operation: The server retrieves the behavioral data from the processing queue and passes it to the emotion engine to begin analysis. The emotion engine analyzes the data and assigns a label to the user's emotional state (e.g., anxiety, anger).

[1252] Output: Emotion data (e.g., user expresses emotion "anxiety")

[1253] Step 6:

[1254] The server compares the behavioral and emotional data with a database containing past incident, accident, and crime data to calculate a risk score.

[1255] Input: Behavioral data, emotion data

[1256] Data calculation: Matching with database, calculating risk score

[1257] Specific operation: The server compares the behavioral data of "large euro investment" and the emotional data of "anxiety" with fraud data in the database and calculates a score that qualifies as high risk.

[1258] Output: Risk score (e.g. 80 / 100)

[1259] Step 7:

[1260] The server generates a warning message based on the detected risk and emotional state.

[1261] Input: Risk score, sentiment data

[1262] Data calculations: risk assessment, message generation

[1263] What it does: Based on the risk score and sentiment data, the server generates a warning message saying, "This search query carries a risk of fraud. Invest with caution."

[1264] Output: Warning message

[1265] Step 8:

[1266] The server sends the warning message and emotion data to the user terminal.

[1267] Input: Warning message, emotion data

[1268] Specific operation: The server sends the generated message and emotion data to the user's device.

[1269] Output: Messages and data received by the user terminal

[1270] Step 9:

[1271] The device will notify the user of the received warning message.

[1272] Input: Warning message, emotion data

[1273] What happens: The user's device will display a pop-up message saying, "This search query carries the risk of fraud. Invest with caution."

[1274] Output: The warning message displayed to the user

[1275] Step 10:

[1276] The user may take action based on the warning, for example, by avoiding the investment.

[1277] Input: The warning message displayed to the user

[1278] Specific behavior: The user sees the warning message and takes action to avoid the investment based on its contents.

[1279] Output: The user's new behavior

[1280] Step 11:

[1281] The device captures the user's behavioral history and sends it to the server.

[1282] Input: New user action

[1283] Specific operation: The device captures the user's behavior again and sends it to the server as a behavior history.

[1284] Output: Action history received by the server

[1285] Step 12:

[1286] The server analyzes user behavior history and uses it to improve the system.

[1287] Input: User behavior history

[1288] Data Calculation: Feedback Analysis

[1289] What it does: The server analyzes user feedback data to help improve risk detection and sentiment analysis algorithms.

[1290] Output: Improved system algorithm

[1291] (Application example 2)

[1292] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1293] Conventional security systems for internet use can detect risks based on user behavior data, but they are unable to evaluate risks by taking into account the user's emotional state. This makes it difficult to provide appropriate warnings and advice based on the user's psychological state, and ultimately makes it impossible to present the best countermeasures for the user. Furthermore, the methods for presenting warning messages are limited, which sometimes does not lead to user understanding or behavioral changes. A new system is needed to solve these issues.

[1294] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1295] In this invention, the server includes: means for a user terminal to collect user behavioral data via the Internet; means for the server to compare the received behavioral data with a database containing past incident, accident, and crime data; means for the server to detect potential risks and perform risk assessments based on the user behavioral data; means for an emotion engine to analyze the user behavioral data and recognize the user's emotional state; means for the server to transmit the risk assessment results and emotion analysis results to the user terminal and notify the user; and means for the user terminal to display warning messages in the form of pop-ups or alerts. This enables real-time risk assessments that take the user's emotional state into consideration and the provision of appropriate warning messages.

[1296] A "user terminal" is a device for collecting and displaying user behavior data via the Internet.

[1297] "Behavioral data" is information about what you do online, such as searches, posts, chats, and emails you receive.

[1298] The "server" is a central processing unit that analyzes behavioral data received from a user terminal and transmits the results to the user terminal.

[1299] A "database" is an information storage system that holds data on past incidents, accidents, and crimes, and allows the server to collate and analyze the data.

[1300] "Potential risk" refers to possible danger or crime that can be estimated based on behavioral data.

[1301] "Risk assessment" is the process by which the server compares behavioral data with a database to determine the severity and likelihood of potential risks.

[1302] An "emotion engine" is software that analyzes user behavioral data and recognizes their emotional state.

[1303] "Emotional state" refers to the psychological state or mood a user exhibits when engaging in online activities.

[1304] "Notification" refers to the act of informing the user of the risk assessment results and emotion analysis results received by the user's device from the server.

[1305] A "pop-up or alert-style warning message" is a message that is visually displayed on the user's device to warn or alert the user.

[1306] This invention is a system that strengthens crime prevention measures by monitoring users' online activities and detecting crime risks and changes in emotions at an early stage. The system of this invention is composed of a user terminal, a server, a database, and an emotion engine, and each element works in cooperation to ensure safe internet use for users.

[1307] The user device collects real-time behavioral data, such as searches, posts, chats, and e-mails that the user conducts over the Internet. The user device also encrypts the collected behavioral data before sending it to the server, thereby ensuring data security while protecting the user's privacy.

[1308] The server decodes the received behavioral data in real time and compares it with a database of past incidents, accidents, and crimes. The server is equipped with a machine learning algorithm that learns from past data to detect potential risks and perform risk assessments. In addition, the server is equipped with an emotion engine that can analyze user behavioral data and recognize emotional states.

[1309] The server sends risk assessment results based on behavioral data and emotion analysis results to the user's device. The user's device notifies the user of the received risk assessment and emotion analysis results, displaying warning messages in the form of pop-ups or alerts. This allows the user to recognize the potential risks posed by their own behavior and take appropriate measures.

[1310] For example, if a user searches for "large euro investment," this search query is captured as user behavior data and sent to the server. The server compares this search query with past fraud data and evaluates it as high risk. At the same time, the emotion engine recognizes the user's emotional state as "neutral." As a result, the server sends a risk warning message to the user's device saying, "This search query carries a risk associated with fraud. Be cautious with your investments.", along with emotion-based advice such as, "Your emotions are currently stable. Please remain calm."

[1311] Example prompt sentence:

[1312] User Activity: Search

[1313] User Input: Large Euro Investment

[1314] Detected Emotion: Neutral

[1315] Risk assessment result: High

[1316] Server response message: "This search query carries a risk of fraud. Invest with caution.", "Emotions are currently stable. Please remain calm."

[1317] As described above, the system of the present invention simultaneously monitors and analyzes user behavioral data and emotional data, performs real-time risk assessment, and provides appropriate warning messages to users, thereby reducing the risk of crime on the Internet.

[1318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1319] Step 1:

[1320] When a user searches, posts, or chats on the Internet, the user device captures the behavioral data. At this point, the input is the user's online activity data, and the output is the captured behavioral data.

[1321] Step 2:

[1322] The user device encrypts the captured behavioral data and sends it to the server. The input is the captured behavioral data, and the output is the encrypted behavioral data. This behavioral data is transferred to the server via the network.

[1323] Step 3:

[1324] The server receives and decrypts the encrypted behavioral data. The input is the encrypted behavioral data and the output is the decrypted behavioral data. The decrypted data is queued within the server for analysis.

[1325] Step 4:

[1326] The machine learning algorithm in the server compares the decoded behavioral data with past incident / accident / crime data in the database to detect potential risks. The input is the decoded behavioral data and the data in the database, and the output is the risk assessment result. In this process, certain behaviors may be judged to be high risk because they match with past crime data.

[1327] Step 5:

[1328] The emotion engine analyzes the user's behavioral data to recognize the user's emotional state. The input is the decoded behavioral data, and the output is the emotional state data. The emotion engine identifies the specific emotion the user expressed (e.g., anger or neutral).

[1329] Step 6:

[1330] The server combines the risk assessment results and emotional state data to generate a comprehensive risk assessment message. The inputs are the risk assessment results and emotional state data, and the output is a warning message and emotion-based advice for the user.

[1331] Step 7:

[1332] The server generates risk assessment messages and sends advice based on emotions to the user terminal. The input is the generated message, and the output is the sent message.

[1333] Step 8:

[1334] The user device receives risk assessment messages and advice and notifies them to the user in the form of popups or alerts. The input is the received message, and the output is the displayed warning message and advice, so the user can take appropriate action.

[1335] For example, if a user searches for "high euro investment," the search query is captured, encrypted, and sent to the server. The server decrypts it, compares it with fraud data, and determines that it poses a high risk. The emotion engine then recognizes the user's emotion as "neutral." As a result, a message from the server warning the user that "This search query carries a fraud risk. Be cautious when investing," along with advice that "Emotions are currently stable. Please remain calm," is sent to the user's device and displayed to the user.

[1336] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1337] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1338] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1339] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1340] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1341] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1342] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1343] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1344] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1345] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1346] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1347] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1348] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1349] 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.

[1350] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1351] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1352] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1353] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1354] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1355] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1356] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1357] The following is further disclosed regarding the above embodiment.

[1358] (Claim 1)

[1359] A means for a user device to collect user behavior data via the Internet;

[1360] A means for comparing the behavioral data received by the server with a database containing past incident / accident / crime data;

[1361] A means for the server to detect potential risks based on user behavior data and perform risk assessment;

[1362] The server sends the risk assessment results to the user's terminal and notifies the user.

[1363] A system including:

[1364] (Claim 2)

[1365] The system of claim 1, wherein the server further comprises means for analyzing past incident / accident / crime data using a machine learning algorithm.

[1366] (Claim 3)

[1367] 10. The system of claim 1, further comprising means for the user terminal to send feedback regarding the user's behavior to the server, the server analyzing the feedback and using it to improve the system.

[1368] "Example 1"

[1369] (Claim 1)

[1370] A means for a user device to capture user behavior data in real time via the Internet, encrypt it, and send it to a server;

[1371] A means for the server to decrypt the encrypted behavioral data received and compare it with a database containing past incident / accident / crime data;

[1372] A means for the server to use a machine learning algorithm or a rule-based system to calculate a risk score based on the user's behavioral data and perform risk assessment;

[1373] The server generates a warning message based on the risk assessment result, sends it to the user's terminal, and notifies the user.

[1374] A means for the user device to capture feedback about the user's behavior, encrypt it, and transmit it to a server;

[1375] The server analyzes the feedback it receives and uses it to improve the system.

[1376] A system including:

[1377] (Claim 2)

[1378] The system of claim 1, further comprising means for the server to analyze past incident / accident / crime data using a machine learning algorithm and calculate a risk score.

[1379] (Claim 3)

[1380] 2. The system according to claim 1, further comprising means for the user terminal to encrypt feedback regarding the user's behavior and transmit the encrypted feedback to the server, and the server analyzes the received feedback and uses it to improve the system.

[1381] "Application Example 1"

[1382] (Claim 1)

[1383] A means for a user device to collect user behavior data via the Internet;

[1384] A means for comparing the behavioral data received by the server with a database containing past incident / accident / crime data;

[1385] A means for the server to detect potential risks based on user behavior data and perform risk assessment;

[1386] A means for the server to transmit the risk assessment result to the user terminal and notify the user;

[1387] a means for the user terminal to display a warning message to the user based on the risk assessment result;

[1388] A system including:

[1389] (Claim 2)

[1390] The system of claim 1, wherein the server further comprises means for analyzing past incident / accident / crime data using a machine learning algorithm.

[1391] (Claim 3)

[1392] 10. The system of claim 1, further comprising means for the user terminal to send feedback regarding the user's behavior to the server, the server analyzing the feedback and using it to improve the system.

[1393] "Example 2: Combining Emotion Engines"

[1394] (Claim 1)

[1395] A means for a user device to collect user behavior data via the Internet;

[1396] A means for encrypting the behavioral data captured by the device and transmitting the data to a server;

[1397] means for the server to decrypt the received behavioral data and place it in a processing queue;

[1398] A means for comparing the behavioral data received by the server with a database containing past incident / accident / crime data;

[1399] A means for the emotion engine to analyze user behavior data and recognize their emotional state;

[1400] A means for the server to detect potential risks and perform risk assessment based on the user's behavioral data and emotion data;

[1401] The system includes a server that transmits the risk assessment results and the emotional state to a user terminal and notifies the user.

[1402] (Claim 2)

[1403] The system of claim 1, wherein the server further comprises means for analyzing past incident / accident / crime data using a machine learning algorithm.

[1404] (Claim 3)

[1405] 10. The system of claim 1, further comprising means for the user terminal to send feedback regarding the user's behavior to the server, the server analyzing the feedback and using it to improve the system.

[1406] "Application example 2 when combining emotion engines"

[1407] (Claim 1)

[1408] A means for a user device to collect user behavior data via the Internet;

[1409] A means for comparing the behavioral data received by the server with a database containing past incident / accident / crime data;

[1410] A means for the server to detect potential risks and perform risk assessment based on user behavior data;

[1411] A means for the emotion engine to analyze the user's behavioral data and recognize the user's emotional state;

[1412] A means for the server to transmit the risk assessment result and the emotion analysis result to the user terminal and notify the user;

[1413] A means for the user device to display a warning message in the form of a pop-up or alert;

[1414] A system including:

[1415] (Claim 2)

[1416] The system of claim 1, wherein the server further comprises means for analyzing past incident / accident / crime data using a machine learning algorithm.

[1417] (Claim 3)

[1418] 10. The system of claim 1, further comprising means for the user terminal to send feedback regarding the user's behavior to the server, the server analyzing the feedback and using it to improve the system. [Explanation of symbols]

[1419] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a user device to collect user behavior data via the Internet; A means for comparing the behavioral data received by the server with a database containing past incident / accident / crime data; A means for the server to detect potential risks based on user behavior data and perform risk assessment; The server sends the risk assessment results to the user's terminal and notifies the user. A system including:

2. The system of claim 1 , wherein the server further comprises means for analyzing past incident / accident / crime data using a machine learning algorithm.

3. 10. The system of claim 1, further comprising means for the user terminal to send feedback regarding the user's behavior to the server, the server analyzing the feedback and using it to improve the system.

Images