system

Abstract

We provide the system. [Solution] A means of collecting information, which is installed on an information processing device and based on permission from the user to share information, A means for analyzing the collected information and modeling the user's behavioral tendencies and interests, A means of comparing the modeled behavioral tendencies with external information sources to assess risk, Based on the aforementioned evaluation results, a means of providing personalized safety advice to users via push notifications, A method for evaluating safety information using an artificial intelligence model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, individuals using information communication terminals routinely use a variety of applications, and the usage information reflects their individual living habits and interests. However, there is a lack of technology that can fully utilize such a vast amount of data to provide specific advice tailored to individual needs. In addition, the response to the risk of crime caused by careless behavior or insufficient information is also inadequate. To solve these problems, there is a need for a mechanism that can comprehensively utilize personal data and provide appropriate advice.

Means for Solving the Problems

[0005] This invention utilizes an information processing device to collect information within the scope permitted by the user, and includes means for analyzing the collected data to model the user's behavioral patterns and interests. The resulting model is then compared with an external database, particularly information related to safety and crime, to evaluate the potential risks to the user's behavior. Furthermore, based on this evaluation, the invention provides specific advice to the user and includes means for collecting feedback to improve the accuracy of that advice. In this way, this invention contributes to improving the user's quality of life and enhancing safety.

[0006] An "information processing device" is a device that has the function of electronically processing, managing, and temporarily or permanently storing data.

[0007] "Permission to share data" refers to the act or state in which a user consents to their information being provided to a third party or system for use.

[0008] "Analysis" is the process of breaking down collected data and extracting, understanding, and interpreting information based on specific rules or algorithms.

[0009] "Behavioral patterns" refer to a temporal and contextual description of the tendencies in the behaviors and reactions that users exhibit on a daily basis.

[0010] "Modeling" means abstracting real-world phenomena and activities using mathematical formulas and algorithms, and representing them in a form that can be understood by a system.

[0011] An "external database" is an external information aggregation system accessible to a system, which has a structure that allows it to store and retrieve specific information.

[0012] "Risk assessment" is the process of analyzing whether a particular action or situation is potentially harmful and determining its likelihood and impact.

[0013] "Providing advice" means offering suggestions and instructions to help users make better decisions based on the information collected and its analysis.

[0014] "Feedback collection" refers to the actions and processes of gathering user reactions and opinions on information and services they have received. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention relates to a system that provides personalized advice to users using a generative AI application that operates on an information processing device. In this system, the user first installs a dedicated application on their smartphone and sets the scope of data sharing through that application. Here, the user can select the data to share, such as location information, app usage history, and call records, thereby making it possible to provide necessary information while protecting personal privacy.

[0037] Data collection and transmission

[0038] Device: Based on the configured data range, the device periodically collects information in a predetermined manner. This includes methods for obtaining data through location services and app usage history APIs. The collected data is encrypted using AES or similar encryption and sent to the server via the HTTPS protocol.

[0039] Data Analysis

[0040] Server: When analyzing received data, machine learning algorithms are used to reveal user behavior patterns and interests. Clustering techniques and inference models are commonly used for this purpose. Individual profiles are generated based on the analysis results, and these profiles are used for further, more detailed analysis.

[0041] Risk assessment and advice generation

[0042] Server: The generated profile information is compared with an external database to perform a risk assessment. This database includes local security information and the latest crime trends. Based on the assessment, the AI ​​model generates safety-conscious advice for the user's actions. For example, if the user plans to visit a certain area late at night, the AI ​​will advise them to re-evaluate their actions based on the latest security information for that area.

[0043] Providing advice

[0044] Terminal: Advice sent from the server is visually displayed in the user interface. Furthermore, it includes a feature to immediately inform the user via push notifications based on urgency and importance.

[0045] Feedback and system improvements

[0046] User: Submits feedback on the advice provided. This feedback contributes to improving the application's usability and the accuracy of the advice. The feedback is collected on the server and used for future system improvements.

[0047] For example, if a user enters "I have a trip planned to a foreign country tomorrow," the server will analyze the safety situation and health information of the destination and generate and provide advice for safe travel. Through this series of processes, the present invention can contribute to improving the user's quality of life and ensuring their safety.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] User: Install the dedicated AI generation application on your smartphone. After installation, launch the app and perform the initial setup. Here, the user selects the data to share (e.g., location information, app usage history, call history, etc.). Review the terms of service and privacy policy and set the data sharing permission.

[0051] Step 2:

[0052] Device: Activates the function to collect user-selected data. Location information is obtained from GPS, and app usage history is collected through the OS API. The collected data is encrypted using the AES encryption algorithm to ensure data security.

[0053] Step 3:

[0054] Terminal: Sends encrypted data to the server using the HTTPS protocol. Transmission is performed periodically to ensure that the server always receives the latest data.

[0055] Step 4:

[0056] Server: Decrypts received encrypted data and stores it in the database. This data is then subjected to subsequent analysis and used to understand user behavior patterns.

[0057] Step 5:

[0058] Server: Uses machine learning algorithms to analyze information stored in the database. Through clustering techniques and regression analysis, it clarifies user behavior patterns and interests and generates individual profiles.

[0059] Step 6:

[0060] Server: The generated profile is compared against an external crime information database to assess the inherent risks in the user's behavior. Based on this assessment, the server quantitatively determines the level of caution required if a risk exists.

[0061] Step 7:

[0062] Server: Receives the user's planned activities entered into the app and generates specific advice based on that information. Natural language generation technology is used to create concise and easy-to-understand messages for advice generation.

[0063] Step 8:

[0064] Server: Sends generated advice to the terminal. Considering safety and usefulness, push notifications are sent as urgent information if necessary.

[0065] Step 9:

[0066] Terminal: Displays received advice on the user interface. Users can review the displayed information and use it in their daily lives.

[0067] Step 10:

[0068] User: Provides feedback on the advice provided. The feedback is sent to the server via the app and used to improve the system and the accuracy of the advice in the future.

[0069] (Example 1)

[0070] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0071] In modern society, there is a need to create an environment where users can safely receive personalized information and instructions. However, concerns remain regarding information privacy and security, and ensuring the safety and accuracy of collected information when analyzing and effectively utilizing it is a particular challenge.

[0072] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0073] In this invention, the server is installed in an information processing device and includes means for acquiring information based on permission from the user to share information, means for analyzing the acquired information and modeling the user's behavior patterns and interests, and means for comparing the modeled behavior patterns with an external information aggregation environment and evaluating risks. This enables the user to receive personalized information safely and accurately.

[0074] An "information processing device" refers to an electronic device for receiving, analyzing, and transmitting data, and is a computer system capable of executing programs.

[0075] "Permission to share information" refers to the act of a user authorizing the sharing of their information with a third party, and includes the right to choose which information to share and to what extent.

[0076] "Means of acquiring information" refers to a series of methods and devices for collecting data on an information processing device, and includes a mechanism that allows necessary information to be acquired as appropriate through user operation and settings.

[0077] "Analysis" refers to the process of examining data in detail based on collected information to find meaning and patterns.

[0078] "Behavioral patterns" refer to characteristic movements and selection histories that demonstrate the consistency and repetition of a user's actions, and include the user's habits and behavioral tendencies revealed through analysis.

[0079] "Interests" refer to the specific interests and preferences that individual users exhibit, and are inferred from the user's past actions and choices.

[0080] "Modeling" refers to the process of formalizing user behavior and interests based on data obtained through analysis, and transforming them into an understandable format.

[0081] An "information aggregation environment" refers to a platform for collecting data from multiple sources and performing analysis and evaluation, enabling comparison and matching with external data.

[0082] "Means of risk assessment" refers to a system that identifies potential risks by comparing the user's actions and interests with information obtained from the external environment.

[0083] "Encryption" refers to the process of transforming information to make it unreadable in order to ensure the security of data, and is a technology used to prevent eavesdropping and tampering with information.

[0084] "Instructions" refer to messages, including specific actions and warnings, provided to users based on analysis results and evaluations.

[0085] "Response" refers to the opinions and impressions that users give in response to the instructions provided, and includes feedback that is used to improve the system.

[0086] This invention is a system that provides personalized instructions to users. This system functions through a dedicated application installed on an information processing device. First, the user installs this application on their device and sets the scope of information sharing. As a result, information such as location information, app usage history, and call records are collected within the specified scope.

[0087] Data collection and encryption processing

[0088] Device: Based on the user's set scope of information sharing, the device periodically collects data using location services, etc. The collected data is encrypted using AES encryption technology. This protects the information from unauthorized access.

[0089] Data Analysis

[0090] Server: Encrypted data is sent to the server via the HTTPS protocol. The server analyzes the data using machine learning algorithms to model user behavior patterns and interests. Clustering techniques and inference models are used in this analysis. The analyzed data is compiled into personalized profiles for each user by a generative AI model.

[0091] Risk assessment and directive generation

[0092] Server: Based on profile information, the server compares it with an external information aggregation environment to assess the current risk level. By utilizing databases of local safety information and social trends, it evaluates the risks to the user's actions and generates appropriate instructions. The generating AI model provides specific and responsive instructions based on the prompt. An example of instructions would be given in response to a prompt such as, "I'm planning to visit a new restaurant this weekend. Please give me some safety advice."

[0093] Providing instructions and feedback

[0094] Terminal: The generated instructions are provided to the user through the terminal application. The instructions are displayed visually and, in some cases, have the functionality to be delivered immediately as push notifications. This allows the user to receive important information in real time.

[0095] User: Users who receive instructions provide feedback on their content through the application. This feedback is sent to the server and used to improve the accuracy of system analysis and the user experience.

[0096] Through this series of processes, the present invention makes it possible to provide users with highly accurate and personalized instructions, thereby improving their quality of life and safety.

[0097] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0098] Step 1:

[0099] Application installation and configuration

[0100] User: Install the dedicated application on your device and launch it. An interface will appear where you can set the scope of information sharing. You will then enter the necessary permissions for collecting information such as location information, app usage history, and call records. This setting allows the application to explicitly recognize the scope of personal information that the user will provide.

[0101] Step 2:

[0102] Information gathering and encryption

[0103] Device: Installed applications periodically collect information based on user settings. This includes GPS data from location services and data from app usage history APIs. This data is encrypted using AES encryption technology to ensure security and data preservation. The encrypted data is then ready to be sent to the server.

[0104] Step 3:

[0105] Data transmission

[0106] Terminal: Encrypted data is sent to the server via the HTTPS protocol. This protocol ensures a high level of security against unauthorized external access during data transmission. The input here is encrypted user information, and the output is data securely stored on the server.

[0107] Step 4:

[0108] Data analysis and profile generation

[0109] Server: Uses machine learning algorithms to analyze the received data. Clustering techniques are used to analyze user behavior patterns and interests based on the input data. This generates a profile for each user. The output of the analysis is a user profile that reflects behavior patterns and interests.

[0110] Step 5:

[0111] Risk assessment and directive generation

[0112] Server: Based on the generated profile, it compares data with an external information aggregation environment and performs a risk assessment. Using local safety information and relevant databases, it generates appropriate instructions for user behavior using an AI model. The inputs are the profile and external data, and the output is personalized instructions for the user.

[0113] Step 6:

[0114] Providing instructions and collecting feedback

[0115] Terminal: Provides instructions from the server to the user. These are presented visually through an interface, and push notifications may be used depending on the urgency. During this process, information necessary for the user's actions is output.

[0116] User: Receives the provided instructions and sends feedback on them to the server via the terminal. This feedback serves as input for future system improvements.

[0117] This workflow allows the system to provide users with safe and useful instructions, improving safety and quality of life in real time.

[0118] (Application Example 1)

[0119] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0120] Ensuring safety in people's living environments is a crucial issue today, but there is a lack of systems that can provide real-time safety advice tailored to individual circumstances. Furthermore, effectively utilizing necessary information to provide personalized advice while protecting user privacy is a challenging task.

[0121] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0122] In this invention, the server includes means for collecting information based on permission to share information, means for analyzing the collected information and modeling behavioral trends, and means for comparing the modeled behavioral trends with an external information collection and evaluating risk. This makes it possible to provide personalized safety advice to users via push notifications and ensure safety in real time.

[0123] An "information processing device" is an electronic device used for inputting, analyzing, and outputting data, and is used to execute applications and programs.

[0124] "Permission to share information" is the act of a user authorizing an application to collect and use their information.

[0125] "Behavioral tendencies" refer to a series of behavioral patterns shown by a user's movements and habits, and are information used to infer the user's characteristics and preferences based on these patterns.

[0126] An "external information collection" is a set of data obtained from external databases and information sources, and is used to assess the risks that may affect user behavior.

[0127] "Push notifications" are a communication method used to present information to users in real time from applications installed on their devices.

[0128] An "artificial intelligence model" is a set of mathematical methods and algorithms designed to analyze and predict data, and it operates using machine learning techniques.

[0129] This invention provides a system that delivers personalized safety advice to users. The system mainly consists of an information processing device, a server, and a user terminal.

[0130] The device collects location information and behavioral patterns based on the user's consent. This collection includes obtaining data through location services and application usage history APIs. For example, applications installed on a smartphone perform this task. The collected information is encrypted with AES to ensure communication security and sent to the server via the HTTPS protocol.

[0131] The server uses Google Cloud Platform and other services to analyze the received information. The analysis models behavioral trends and uses artificial intelligence models (e.g., TENSORFLOW®) to compare them with external data sets and assess risk. These external data sets include local crime information and weather data, which can be obtained using APIs available on the market. This assessment generates personalized safety advice.

[0132] The server sends the generated advice to the user's device as a push notification. For this purpose, it uses real-time communication services such as Firebase Cloud Messaging. As a result, users can receive specific and personalized advice tailored to their environment, which helps them take safe actions.

[0133] For example, if a user inputs into the system that they plan to walk around the city in the evening while traveling, the server will analyze the latest safety information for that destination and immediately provide advice such as, "There have been recent theft incidents in that area, so please be careful and it is recommended that you return home early." An example of a prompt in such a specific case would be, "Based on the user's current location and planned activities, please conduct a safety assessment and provide advice based on the latest safety information as needed."

[0134] This system will enable users to always receive the latest information and appropriate instructions, allowing them to live a safe and secure life.

[0135] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0136] Step 1:

[0137] Based on user consent, the device collects location information and usage patterns through location services and application usage history APIs. Inputs include the user's current geographical coordinates and application usage frequency. The collected data is temporarily stored on the device for later analysis.

[0138] Step 2:

[0139] The device encrypts the collected data using AES and securely transmits it to the server using the HTTPS protocol. Input includes unencrypted user location information and usage patterns, while output is encrypted data securely transmitted to the server. Throughout this process, an encryption algorithm is applied to maintain data security.

[0140] Step 3:

[0141] The server decrypts the received encrypted data and performs analysis to model user behavior patterns. Inputs include decrypted user location information and usage patterns. The data is analyzed using machine learning algorithms, and a behavioral trend model is generated as output.

[0142] Step 4:

[0143] The server compares the generated behavioral trend model with external information sources to assess risk. Inputs include modeled user behavioral trends and external security data and local information. The comparison evaluates the potential risks associated with the user's behavior, and the risk assessment result is output. Here, a generative AI model is used to analyze prompt messages, resulting in a highly accurate assessment.

[0144] Step 5:

[0145] The server generates safety advice for the user based on the risk assessment results. The input is the risk assessment results, and the output is specific safety instructions sent to the user. In this process, an artificial intelligence model is used to create advice in a way that is easy for the user to understand.

[0146] Step 6:

[0147] The server pushes the generated advice to the user's device via a real-time communication service such as Firebase Cloud Messaging. The input is the generated safety advice, and the output is the notification data received on the user's device. This allows the user to instantly receive safe instructions regarding their actions.

[0148] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0149] This invention relates to a system that incorporates an emotion engine into a generative AI application installed in an information processing device, enabling it to provide users with more personalized advice.

[0150] Installation and setup

[0151] User: Download and install the AI ​​generation application on your smartphone. After launching the app, when setting the range of data to be used, the user can choose whether or not to use the emotion engine. Emotion recognition is performed based on voice input and text input.

[0152] Data collection and emotion recognition

[0153] Device: Based on the set range, in addition to normal data (location information and app usage history), the emotional state is analyzed from voice tone and word choice through the emotion engine. This identifies what emotions the user is feeling while using the app.

[0154] Data analysis and profiling

[0155] Server: Receives data sent from terminals, decrypts it, and performs analysis. It uses emotional information obtained from the emotion engine to generate detailed behavioral patterns and emotional profiles for each user. This provides a deeper understanding by adding emotional elements to models of normal behavioral patterns.

[0156] Risk assessment and advice generation

[0157] Server: The server compares behavioral patterns and emotional profiles with external crime information databases to assess risk. The risk assessment particularly considers cases where emotional state negatively impacts decision-making. Based on this, it generates flexible advice tailored to the emotional state. For example, it provides advice encouraging calmer behavior to users experiencing stress.

[0158] Providing advice and feedback

[0159] Terminal: Displays advice received from the server. The advice is presented using a display method that suits the user's emotional state. For example, a calm user will receive advice with more information, while a calmer user will receive simpler advice.

[0160] Emotional feedback and improvement

[0161] User: Enters their reactions and opinions on the advice provided as feedback into the app. This feedback is sent to the server, and the system uses this data to improve the accuracy of the advice.

[0162] For example, if a user inputs "I'm very tired from work," the emotion engine will determine that this emotion represents a stressful state. Based on this information, the server will advise on the current need for rest and suggest nearby relaxation spots and relaxation methods. In this way, the present invention can provide more appropriate advice by taking into account the user's state and emotions.

[0163] The following describes the processing flow.

[0164] Step 1:

[0165] User: Download and install the AI ​​generation application on your smartphone. Launch the app, review the terms of service and privacy policy, and then configure whether to share data and whether to use the emotion engine.

[0166] Step 2:

[0167] Device: Collects data permitted by the user. This includes location information, app usage history, and sentiment information based on voice and text input. The sentiment engine estimates emotional states from voice tone and keywords.

[0168] Step 3:

[0169] Terminal: Collected data is encrypted using encryption technologies such as AES and sent to the server via the HTTPS protocol. This ensures data security.

[0170] Step 4:

[0171] Server: Decodes received data and stores it in a database. Machine learning algorithms are used for analysis to process the data and generate behavioral patterns and emotional profiles.

[0172] Step 5:

[0173] Server: The server cross-references behavioral patterns and emotional profiles with external crime information databases to assess the risks associated with the user's behavior. This process particularly considers how recognized emotional states have an impact.

[0174] Step 6:

[0175] Server: Generates appropriate advice for the user based on risk assessment and emotional profile. The generated advice is personalized by adjusting the content and expression according to the emotional state.

[0176] Step 7:

[0177] Server: Sends the generated advice to the terminal. The advice is then formatted to be easily understood by the user.

[0178] Step 8:

[0179] Terminal: Displays received advice in the user interface. Users can review the displayed advice and decide on actions based on it.

[0180] Step 9:

[0181] User: Provides feedback by responding to the advice given. This feedback is sent to the server via the terminal and used to improve the system.

[0182] Step 10:

[0183] Server: Analyzes feedback to improve the accuracy of advice and sentiment recognition. The system learns to provide more personalized services in subsequent uses.

[0184] (Example 2)

[0185] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0186] In modern information processing systems, it is difficult to analyze not only users' behavioral patterns but also their emotional states in real time and provide advice based on that analysis. Furthermore, this advice must be adapted to individual situations and provided in a highly reliable manner. Moreover, realizing a mechanism that continuously incorporates user feedback while ensuring the security of information is also a challenging task.

[0187] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0188] In this invention, the server is installed on an information processing device and includes means for collecting information based on permission from the user to share information; means incorporating an emotion engine that analyzes voice characteristics and language choices based on the collected information to identify the user's emotional state; and means for comparing the identified emotional state and behavioral patterns with an external database to evaluate risk. This makes it possible to provide personalized advice that takes the user's emotional state into consideration.

[0189] "Information processing equipment" is a general term for electronic devices that can collect, analyze, and transmit data.

[0190] "Information" refers to data used to identify a user's behavioral history and emotional state.

[0191] "Emotional state" refers to an internal psychological state identified based on the user's vocal characteristics and language choices.

[0192] An "emotion engine" is a technology that identifies a user's emotional state by analyzing voice characteristics and language selection data.

[0193] An "external database" is an external source of information used to match user behavior patterns and emotional states.

[0194] "Risk assessment" is the process of evaluating potential risks to users based on identified behavioral patterns and emotional states.

[0195] "Advice" refers to recommended actions or guidelines provided to users based on the results of a risk assessment.

[0196] "Feedback" refers to the collection of responses and opinions from users regarding the advice they receive.

[0197] A "generative AI model" is an artificial intelligence technology that utilizes machine learning algorithms for data analysis and providing advice.

[0198] A "prompt message" is an instruction or question designed to prompt the user to enter information.

[0199] The system in this invention uses a generative AI model incorporated into an information processing device to provide personalized advice based on the user's emotional state. Specifically, information gathering, sentiment analysis, risk assessment, and advice provision are performed through the interaction of a server, a terminal, and the user.

[0200] Server: The server receives encrypted information sent from the terminal and analyzes it using a generative AI model. It analyzes the user's voice characteristics and language choices through an emotion engine to identify the user's emotional state. Based on this information, it cross-references it with an external database to assess related risks. It then generates advice tailored to those risks and sends it to the terminal.

[0201] Terminal: The terminal analyzes voice and text input provided by the user using an emotion engine to identify the emotional state. It then encrypts the necessary data before sending it to the server for security. It receives advice from the server, visualizes it for the user, and displays the content in an easy-to-understand manner. The way the advice is displayed is adjusted according to the user's current emotional state.

[0202] User: The user interacts with the application and provides input through prompts. For example, they can respond to a prompt such as, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" As a result, the system can perform a more accurate analysis of the user's emotional state and provide personalized advice. By providing feedback on the advice the user receives, the system's generated AI model is continuously improved.

[0203] For example, if a user enters "I'm very tired from work" into the application, the emotion engine will determine the emotional state as stress and display advice such as, "Get enough rest. How about taking a walk in a nearby park or trying some relaxation exercises?" In this way, it is possible to provide specific responses tailored to the user's emotions and situation.

[0204] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0205] Step 1:

[0206] User: The user launches the application and, based on prompts, inputs their current emotions and situation via voice or text. The prompts are in the format of, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" The input data serves as foundational data for emotion recognition.

[0207] Step 2:

[0208] Terminal: The terminal receives input from the user and uses an emotion engine to analyze voice features and language choices to identify the emotional state. The data received as input is converted into text and emotion-tagged using speech recognition and natural language processing techniques. The output is the identified emotional state (e.g., stress, joy, sadness).

[0209] Step 3:

[0210] The device combines identified emotional states with user behavior data (such as location information and app usage history) to create packets for transmission to the server. This includes encryption to ensure the security of the information. The output is an encrypted data packet.

[0211] Step 4:

[0212] Server: The server receives encrypted data sent from the terminal and performs decryption processing. It analyzes the data packets received as input to obtain emotional state and behavioral data. This results in a user profile that includes emotional state.

[0213] Step 5:

[0214] Server: The server analyzes the acquired emotional profiles using a generating AI model and performs a risk assessment by comparing them with an external database. In this process, it considers the impact of emotional states on user decision-making and evaluates potential risks. The output includes the risk assessment results and appropriate advice candidates.

[0215] Step 6:

[0216] Server: The server generates advice tailored to the user based on the risk assessment results. The generation AI model selects the best advice from multiple options and formats it into a concrete action plan. The output provides the advice that should be provided to the user.

[0217] Step 7:

[0218] Terminal: Receives advice sent from the server and displays it to the user. The display method of the advice (e.g., text, audio, visual) is adjusted according to the user's current emotional state. Input includes generated advice data, and output is the displayed advice for the user.

[0219] Step 8:

[0220] User: The user responds to the advice received and inputs feedback into the application. This feedback is important for generating advice in the future. As output, the feedback data is sent to the server.

[0221] (Application Example 2)

[0222] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0223] In today's world, there is a need to accurately understand the emotional state of users and provide appropriate advice accordingly. However, conventional systems can only evaluate users based on their behavioral patterns, making it difficult to provide detailed support tailored to the emotional state of the user.

[0224] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0225] In this invention, the server includes means for recognizing the user's emotional state based on voice input or text input, means for comparing the user's behavioral patterns and emotional state with an external database to evaluate risk, and means for generating and providing advice tailored to the user's emotional state based on the evaluation results. This makes it possible to provide personalized advice from both the user's emotional and behavioral perspectives.

[0226] An "information processing device" is a device equipped with the technical means for processing and analyzing data.

[0227] "Means of data collection" refers to methods and devices for collecting various types of information obtained from users.

[0228] "Means of data analysis" refer to methods and devices for analyzing collected data in detail and extracting meaningful information.

[0229] A "behavioral pattern" is a model that represents the typical behavioral tendencies and characteristics of a user.

[0230] "Emotional state" refers to the state of the user's emotions and is data determined from voice and text.

[0231] An "external database" is a system that stores information and holds data for later retrieval and comparison.

[0232] "Means of risk assessment" are methods and devices for analyzing users' behavior and emotional states to predict potential problems.

[0233] "Means for generating advice" refers to methods or devices for creating helpful suggestions for users based on analysis results.

[0234] In this embodiment of the invention, the application installed on the information processing device is central. The system is downloaded and installed on the user's smartphone or similar device. When the application is launched, the user configures data sharing settings and selects to use the emotion recognition engine.

[0235] The device uses Google Cloud's language API to analyze the user's emotional state using voice and text input. The information entered by the user is encrypted and sent to the server.

[0236] The server analyzes the received data and generates detailed behavioral patterns and emotional profiles, including emotional states. These profiles are then compared against a database using analysis tools such as Scikit-learn.

[0237] Subsequently, the server generates personalized advice based on the information obtained, taking into account the user's current emotional state, and sends it to the device. This advice is created using a generative AI model that provides appropriate suggestions using prompt sentences.

[0238] For example, if a user types "I'm feeling very irritated today," the system recognizes this emotion and provides advice such as, "Try taking a few deep breaths to calm yourself down."

[0239] An example of a prompt in this invention is, "Based on the user's current emotional state, please suggest an appropriate relaxation method." This allows for the provision of flexible advice tailored to the user's emotions.

[0240] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0241] Step 1:

[0242] The user launches an application installed on their smartphone and uses voice or text input. During this process, the user inputs information about their emotions and state of mind. This input data is initially received by the application.

[0243] Step 2:

[0244] The device sends voice and text input from the user to Google Cloud's Language API for sentiment analysis. Based on the input data, this API outputs a sentiment score. Specifically, it analyzes the balance of positive and negative sentiment in the text from the input content and outputs it as a sentiment score.

[0245] Step 3:

[0246] The device encrypts and sends the analyzed sentiment score to the server. At this point, the data may also include location information and usage history based on the user's permission. Upon receiving the data, the server decrypts it and prepares it for analysis.

[0247] Step 4:

[0248] The server profiles the received sentiment scores and other behavioral data using machine learning libraries such as Scikit-learn. This profile includes the user's behavioral patterns and emotional states. Specific data processing includes cluster analysis and regression analysis to generate detailed user profiles.

[0249] Step 5:

[0250] The server performs a risk assessment by cross-referencing the generated profile with an external database. The assessment includes an analysis of how the user's emotional state influences the assessment. The output is the results of the risk assessment.

[0251] Step 6:

[0252] Based on the evaluation results and emotion score, the server receives prompt text using a generative AI model and generates personalized advice. Specifically, suggestions recommending appropriate actions and relaxation techniques are created based on successful examples in similar contexts.

[0253] Step 7:

[0254] The server sends the generated advice to the user's device. The device displays the advice to the user through an application. The user can then take action based on the advice.

[0255] Step 8:

[0256] Users can provide feedback on the advice provided through the application. This feedback is sent back to the server, and the system uses this information to improve the accuracy of the advice it provides. For example, if the feedback is positive, the model is adjusted to strengthen the methodology.

[0257] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0258] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0259] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0260] [Second Embodiment]

[0261] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0262] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0263] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0264] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0265] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0266] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0267] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0268] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0269] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0270] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0271] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0272] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0273] This invention relates to a system that provides personalized advice to users using a generative AI application that operates on an information processing device. In this system, the user first installs a dedicated application on their smartphone and sets the scope of data sharing through that application. Here, the user can select the data to share, such as location information, app usage history, and call records, thereby making it possible to provide necessary information while protecting personal privacy.

[0274] Data collection and transmission

[0275] Device: Based on the configured data range, the device periodically collects information in a predetermined manner. This includes methods for obtaining data through location services and app usage history APIs. The collected data is encrypted using AES or similar encryption and sent to the server via the HTTPS protocol.

[0276] Data Analysis

[0277] Server: When analyzing received data, machine learning algorithms are used to reveal user behavior patterns and interests. Clustering techniques and inference models are commonly used for this purpose. Individual profiles are generated based on the analysis results, and these profiles are used for further, more detailed analysis.

[0278] Risk assessment and advice generation

[0279] Server: The generated profile information is compared with an external database to perform a risk assessment. This database includes local security information and the latest crime trends. Based on the assessment, the AI ​​model generates safety-conscious advice for the user's actions. For example, if the user plans to visit a certain area late at night, the AI ​​will advise them to re-evaluate their actions based on the latest security information for that area.

[0280] Providing advice

[0281] Terminal: Advice sent from the server is visually displayed in the user interface. Furthermore, it includes a feature to immediately inform the user via push notifications based on urgency and importance.

[0282] Feedback and system improvements

[0283] User: Submits feedback on the advice provided. This feedback contributes to improving the application's usability and the accuracy of the advice. The feedback is collected on the server and used for future system improvements.

[0284] As a specific example, when a user inputs "I am planning a trip abroad tomorrow", the server analyzes the security situation and health information of the destination for this action and generates and provides advice for a safe trip. Through this series of processes, the present invention can contribute to improving the quality of life and ensuring the safety of the user.

[0285] The following describes the processing flow.

[0286] Step 1:

[0287] User: Install a dedicated generation AI application on the smartphone. After installation, start the application and perform initial settings. Here, the user selects the data to be linked (e.g., location information, application usage history, call history, etc.). Check the terms of use and privacy policy and set permission for data sharing.

[0288] Step 2:

[0289] Terminal: Activate the function to collect the data selected by the user. The location information is obtained from GPS, and the application usage history is collected through the API of the operating system. The collected data is encrypted using the AES encryption algorithm to ensure data security.

[0290] Step 3:

[0291] Terminal: Send the encrypted data to the server using the HTTPS protocol. The transmission is performed regularly to ensure that the server is always supplied with the latest data.

[0292] Step 4:

[0293] Server: Decrypt the received encrypted data and store it in the database. These data will be the target of subsequent analysis processing and will be used to understand the user's behavior pattern.

[0294] Step 5:

[0295] Server: Uses machine learning algorithms to analyze information stored in the database. Through clustering techniques and regression analysis, it clarifies user behavior patterns and interests and generates individual profiles.

[0296] Step 6:

[0297] Server: The generated profile is compared against an external crime information database to assess the inherent risks in the user's behavior. Based on this assessment, the server quantitatively determines the level of caution required if a risk exists.

[0298] Step 7:

[0299] Server: Receives the user's planned activities entered into the app and generates specific advice based on that information. Natural language generation technology is used to create concise and easy-to-understand messages for advice generation.

[0300] Step 8:

[0301] Server: Sends generated advice to the terminal. Considering safety and usefulness, push notifications are sent as urgent information if necessary.

[0302] Step 9:

[0303] Terminal: Displays received advice on the user interface. Users can review the displayed information and use it in their daily lives.

[0304] Step 10:

[0305] User: Provides feedback on the advice provided. The feedback is sent to the server via the app and used to improve the system and the accuracy of the advice in the future.

[0306] (Example 1)

[0307] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0308] In modern society, there is a demand for constructing an environment in which users can safely receive individualized information and instructions. However, there are concerns about information privacy and security, and in particular, it is an issue to ensure the safety and accuracy when analyzing and effectively utilizing the collected information.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0310] In this invention, the server includes means for acquiring information based on permission for information sharing from a user, installed in an information processing device, means for analyzing the acquired information and modeling the user's operation pattern and interests, and means for collating the modeled operation pattern with an external information aggregation environment and evaluating risks. Thereby, the user can receive individualized information safely and accurately.

[0311] The "information processing device" is an electronic device for receiving, analyzing, and transmitting data, and refers to a computer system capable of executing a program.

[0312] The "permission for information sharing" refers to an act of a user approving to share his or her own information with a third party, and includes the right to select which information to share and within what range.

[0313] The "means for acquiring information" refers to a series of methods and devices for collecting data on an information processing device, and has a mechanism for appropriately acquiring necessary information according to the user's operations and settings.

[0314] "Analysis" refers to a process of examining data in detail based on the collected information to find meaning and patterns.

[0315] "Behavioral patterns" refer to characteristic movements and selection histories that demonstrate the consistency and repetition of a user's actions, and include the user's habits and behavioral tendencies revealed through analysis.

[0316] "Interests" refer to the specific interests and preferences that individual users exhibit, and are inferred from the user's past actions and choices.

[0317] "Modeling" refers to the process of formalizing user behavior and interests based on data obtained through analysis, and transforming them into an understandable format.

[0318] An "information aggregation environment" refers to a platform for collecting data from multiple sources and performing analysis and evaluation, enabling comparison and matching with external data.

[0319] "Means of risk assessment" refers to a system that identifies potential risks by comparing the user's actions and interests with information obtained from the external environment.

[0320] "Encryption" refers to the process of transforming information to make it unreadable in order to ensure the security of data, and is a technology used to prevent eavesdropping and tampering with information.

[0321] "Instructions" refer to messages, including specific actions and warnings, provided to users based on analysis results and evaluations.

[0322] "Response" refers to the opinions and impressions that users give in response to the instructions provided, and includes feedback that is used to improve the system.

[0323] This invention is a system that provides personalized instructions to users. This system functions through a dedicated application installed on an information processing device. First, the user installs this application on their device and sets the scope of information sharing. As a result, information such as location information, app usage history, and call records are collected within the specified scope.

[0324] Data collection and encryption processing

[0325] Device: Based on the user's set scope of information sharing, the device periodically collects data using location services, etc. The collected data is encrypted using AES encryption technology. This protects the information from unauthorized access.

[0326] Data Analysis

[0327] Server: Encrypted data is sent to the server via the HTTPS protocol. The server analyzes the data using machine learning algorithms to model user behavior patterns and interests. Clustering techniques and inference models are used in this analysis. The analyzed data is compiled into personalized profiles for each user by a generative AI model.

[0328] Risk assessment and directive generation

[0329] Server: Based on profile information, the server compares it with an external information aggregation environment to assess the current risk level. By utilizing databases of local safety information and social trends, it evaluates the risks to the user's actions and generates appropriate instructions. The generating AI model provides specific and responsive instructions based on the prompt. An example of instructions would be given in response to a prompt such as, "I'm planning to visit a new restaurant this weekend. Please give me some safety advice."

[0330] Providing instructions and feedback

[0331] Terminal: The generated instructions are provided to the user through the terminal application. The instructions are displayed visually and, in some cases, have the functionality to be delivered immediately as push notifications. This allows the user to receive important information in real time.

[0332] User: Users who receive instructions provide feedback on their content through the application. This feedback is sent to the server and used to improve the accuracy of system analysis and the user experience.

[0333] Through this series of processes, the present invention makes it possible to provide users with highly accurate and personalized instructions, thereby improving their quality of life and safety.

[0334] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0335] Step 1:

[0336] Application installation and configuration

[0337] User: Install the dedicated application on your device and launch it. An interface will appear where you can set the scope of information sharing. You will then enter the necessary permissions for collecting information such as location information, app usage history, and call records. This setting allows the application to explicitly recognize the scope of personal information that the user will provide.

[0338] Step 2:

[0339] Information gathering and encryption

[0340] Device: Installed applications periodically collect information based on user settings. This includes GPS data from location services and data from app usage history APIs. This data is encrypted using AES encryption technology to ensure security and data preservation. The encrypted data is then ready to be sent to the server.

[0341] Step 3:

[0342] Data transmission

[0343] Terminal: Encrypted data is sent to the server via the HTTPS protocol. This protocol ensures a high level of security against unauthorized external access during data transmission. The input here is encrypted user information, and the output is data securely stored on the server.

[0344] Step 4:

[0345] Data analysis and profile generation

[0346] Server: Uses machine learning algorithms to analyze the received data. Clustering techniques are used to analyze user behavior patterns and interests based on the input data. This generates a profile for each user. The output of the analysis is a user profile that reflects behavior patterns and interests.

[0347] Step 5:

[0348] Risk assessment and directive generation

[0349] Server: Based on the generated profile, it compares data with an external information aggregation environment and performs a risk assessment. Using local safety information and relevant databases, it generates appropriate instructions for user behavior using an AI model. The inputs are the profile and external data, and the output is personalized instructions for the user.

[0350] Step 6:

[0351] Providing instructions and collecting feedback

[0352] Terminal: Provides instructions from the server to the user. These are presented visually through an interface, and push notifications may be used depending on the urgency. During this process, information necessary for the user's actions is output.

[0353] User: Receives the provided instructions and sends feedback on them to the server via the terminal. This feedback serves as input for future system improvements.

[0354] This workflow allows the system to provide users with safe and useful instructions, improving safety and quality of life in real time.

[0355] (Application Example 1)

[0356] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0357] Ensuring safety in people's living environments is a crucial issue today, but there is a lack of systems that can provide real-time safety advice tailored to individual circumstances. Furthermore, effectively utilizing necessary information to provide personalized advice while protecting user privacy is a challenging task.

[0358] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0359] In this invention, the server includes means for collecting information based on permission to share information, means for analyzing the collected information and modeling behavioral trends, and means for comparing the modeled behavioral trends with an external information collection and evaluating risk. This makes it possible to provide personalized safety advice to users via push notifications and ensure safety in real time.

[0360] An "information processing device" is an electronic device used for inputting, analyzing, and outputting data, and is used to execute applications and programs.

[0361] "Permission to share information" is the act of a user authorizing an application to collect and use their information.

[0362] "Behavioral tendencies" refer to a series of behavioral patterns shown by a user's movements and habits, and are information used to infer the user's characteristics and preferences based on these patterns.

[0363] An "external information collection" is a set of data obtained from external databases and information sources, and is used to assess the risks that may affect user behavior.

[0364] "Push notifications" are a communication method used to present information to users in real time from applications installed on their devices.

[0365] An "artificial intelligence model" is a set of mathematical methods and algorithms designed to analyze and predict data, and it operates using machine learning techniques.

[0366] This invention provides a system that delivers personalized safety advice to users. The system mainly consists of an information processing device, a server, and a user terminal.

[0367] The device collects location information and behavioral patterns based on the user's consent. This collection includes obtaining data through location services and application usage history APIs. For example, applications installed on a smartphone perform this task. The collected information is encrypted with AES to ensure communication security and sent to the server via the HTTPS protocol.

[0368] The server uses Google Cloud Platform and other resources to analyze the received information. The analysis models behavioral trends and uses artificial intelligence models (e.g., TensorFlow) to compare them with external data sets and assess risk. These external data sets include local crime information and weather data, obtained using readily available APIs. This assessment generates personalized safety advice.

[0369] The server sends the generated advice to the user's device as a push notification. For this purpose, it uses real-time communication services such as Firebase Cloud Messaging. As a result, users can receive specific and personalized advice tailored to their environment, which helps them take safe actions.

[0370] For example, if a user inputs into the system that they plan to walk around the city in the evening while traveling, the server will analyze the latest safety information for that destination and immediately provide advice such as, "There have been recent theft incidents in that area, so please be careful and it is recommended that you return home early." An example of a prompt in such a specific case would be, "Based on the user's current location and planned activities, please conduct a safety assessment and provide advice based on the latest safety information as needed."

[0371] This system will enable users to always receive the latest information and appropriate instructions, allowing them to live a safe and secure life.

[0372] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0373] Step 1:

[0374] Based on user consent, the device collects location information and usage patterns through location services and application usage history APIs. Inputs include the user's current geographical coordinates and application usage frequency. The collected data is temporarily stored on the device for later analysis.

[0375] Step 2:

[0376] The device encrypts the collected data using AES and securely transmits it to the server using the HTTPS protocol. Input includes unencrypted user location information and usage patterns, while output is encrypted data securely transmitted to the server. Throughout this process, an encryption algorithm is applied to maintain data security.

[0377] Step 3:

[0378] The server decrypts the received encrypted data and performs analysis to model user behavior patterns. Inputs include decrypted user location information and usage patterns. The data is analyzed using machine learning algorithms, and a behavioral trend model is generated as output.

[0379] Step 4:

[0380] The server compares the generated behavioral trend model with external information sources to assess risk. Inputs include modeled user behavioral trends and external security data and local information. The comparison evaluates the potential risks associated with the user's behavior, and the risk assessment result is output. Here, a generative AI model is used to analyze prompt messages, resulting in a highly accurate assessment.

[0381] Step 5:

[0382] The server generates safety advice for the user based on the risk assessment results. The input is the risk assessment results, and the output is specific safety instructions sent to the user. In this process, an artificial intelligence model is used to create advice in a way that is easy for the user to understand.

[0383] Step 6:

[0384] The server pushes the generated advice to the user's device via a real-time communication service such as Firebase Cloud Messaging. The input is the generated safety advice, and the output is the notification data received on the user's device. This allows the user to instantly receive safe instructions regarding their actions.

[0385] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0386] This invention relates to a system that incorporates an emotion engine into a generative AI application installed in an information processing device, enabling it to provide users with more personalized advice.

[0387] Installation and setup

[0388] User: Download and install the AI ​​generation application on your smartphone. After launching the app, when setting the range of data to be used, the user can choose whether or not to use the emotion engine. Emotion recognition is performed based on voice input and text input.

[0389] Data collection and emotion recognition

[0390] Device: Based on the set range, in addition to normal data (location information and app usage history), the emotional state is analyzed from voice tone and word choice through the emotion engine. This identifies what emotions the user is feeling while using the app.

[0391] Data analysis and profiling

[0392] Server: Receives data sent from terminals, decrypts it, and performs analysis. It uses emotional information obtained from the emotion engine to generate detailed behavioral patterns and emotional profiles for each user. This provides a deeper understanding by adding emotional elements to models of normal behavioral patterns.

[0393] Risk assessment and advice generation

[0394] Server: The server compares behavioral patterns and emotional profiles with external crime information databases to assess risk. The risk assessment particularly considers cases where emotional state negatively impacts decision-making. Based on this, it generates flexible advice tailored to the emotional state. For example, it provides advice encouraging calmer behavior to users experiencing stress.

[0395] Providing advice and feedback

[0396] Terminal: Displays advice received from the server. The advice is presented using a display method that suits the user's emotional state. For example, a calm user will receive advice with more information, while a calmer user will receive simpler advice.

[0397] Emotional feedback and improvement

[0398] User: Enters their reactions and opinions on the advice provided as feedback into the app. This feedback is sent to the server, and the system uses this data to improve the accuracy of the advice.

[0399] For example, if a user inputs "I'm very tired from work," the emotion engine will determine that this emotion represents a stressful state. Based on this information, the server will advise on the current need for rest and suggest nearby relaxation spots and relaxation methods. In this way, the present invention can provide more appropriate advice by taking into account the user's state and emotions.

[0400] The following describes the processing flow.

[0401] Step 1:

[0402] User: Download and install the AI ​​generation application on your smartphone. Launch the app, review the terms of service and privacy policy, and then configure whether to share data and whether to use the emotion engine.

[0403] Step 2:

[0404] Device: Collects data permitted by the user. This includes location information, app usage history, and sentiment information based on voice and text input. The sentiment engine estimates emotional states from voice tone and keywords.

[0405] Step 3:

[0406] Terminal: Collected data is encrypted using encryption technologies such as AES and sent to the server via the HTTPS protocol. This ensures data security.

[0407] Step 4:

[0408] Server: Decodes received data and stores it in a database. Machine learning algorithms are used for analysis to process the data and generate behavioral patterns and emotional profiles.

[0409] Step 5:

[0410] Server: The server cross-references behavioral patterns and emotional profiles with external crime information databases to assess the risks associated with the user's behavior. This process particularly considers how recognized emotional states have an impact.

[0411] Step 6:

[0412] Server: Generates appropriate advice for the user based on risk assessment and emotional profile. The generated advice is personalized by adjusting the content and expression according to the emotional state.

[0413] Step 7:

[0414] Server: Sends the generated advice to the terminal. The advice is then formatted to be easily understood by the user.

[0415] Step 8:

[0416] Terminal: Displays received advice in the user interface. Users can review the displayed advice and decide on actions based on it.

[0417] Step 9:

[0418] User: Provides feedback by responding to the advice given. This feedback is sent to the server via the terminal and used to improve the system.

[0419] Step 10:

[0420] Server: Analyzes feedback to improve the accuracy of advice and sentiment recognition. The system learns to provide more personalized services in subsequent uses.

[0421] (Example 2)

[0422] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0423] In modern information processing systems, it is difficult to analyze not only users' behavioral patterns but also their emotional states in real time and provide advice based on that analysis. Furthermore, this advice must be adapted to individual situations and provided in a highly reliable manner. Moreover, realizing a mechanism that continuously incorporates user feedback while ensuring the security of information is also a challenging task.

[0424] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0425] In this invention, the server is installed on an information processing device and includes means for collecting information based on permission from the user to share information; means incorporating an emotion engine that analyzes voice characteristics and language choices based on the collected information to identify the user's emotional state; and means for comparing the identified emotional state and behavioral patterns with an external database to evaluate risk. This makes it possible to provide personalized advice that takes the user's emotional state into consideration.

[0426] "Information processing equipment" is a general term for electronic devices that can collect, analyze, and transmit data.

[0427] "Information" refers to data used to identify a user's behavioral history and emotional state.

[0428] "Emotional state" refers to an internal psychological state identified based on the user's vocal characteristics and language choices.

[0429] An "emotion engine" is a technology that identifies a user's emotional state by analyzing voice characteristics and language selection data.

[0430] An "external database" is an external source of information used to match user behavior patterns and emotional states.

[0431] "Risk assessment" is the process of evaluating potential risks to users based on identified behavioral patterns and emotional states.

[0432] "Advice" refers to recommended actions or guidelines provided to users based on the results of a risk assessment.

[0433] "Feedback" refers to the collection of responses and opinions from users regarding the advice they receive.

[0434] A "generative AI model" is an artificial intelligence technology that utilizes machine learning algorithms for data analysis and providing advice.

[0435] A "prompt message" is an instruction or question designed to prompt the user to enter information.

[0436] The system in this invention uses a generative AI model incorporated into an information processing device to provide personalized advice based on the user's emotional state. Specifically, information gathering, sentiment analysis, risk assessment, and advice provision are performed through the interaction of a server, a terminal, and the user.

[0437] Server: The server receives encrypted information sent from the terminal and analyzes it using a generative AI model. It analyzes the user's voice characteristics and language choices through an emotion engine to identify the user's emotional state. Based on this information, it cross-references it with an external database to assess related risks. It then generates advice tailored to those risks and sends it to the terminal.

[0438] Terminal: The terminal analyzes voice and text input provided by the user using an emotion engine to identify the emotional state. It then encrypts the necessary data before sending it to the server for security. It receives advice from the server, visualizes it for the user, and displays the content in an easy-to-understand manner. The way the advice is displayed is adjusted according to the user's current emotional state.

[0439] User: The user interacts with the application and provides input through prompts. For example, they can respond to a prompt such as, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" As a result, the system can perform a more accurate analysis of the user's emotional state and provide personalized advice. By providing feedback on the advice the user receives, the system's generated AI model is continuously improved.

[0440] For example, if a user enters "I'm very tired from work" into the application, the emotion engine will determine the emotional state as stress and display advice such as, "Get enough rest. How about taking a walk in a nearby park or trying some relaxation exercises?" In this way, it is possible to provide specific responses tailored to the user's emotions and situation.

[0441] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0442] Step 1:

[0443] User: The user launches the application and, based on prompts, inputs their current emotions and situation via voice or text. The prompts are in the format of, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" The input data serves as foundational data for emotion recognition.

[0444] Step 2:

[0445] Terminal: The terminal receives input from the user and uses an emotion engine to analyze voice features and language choices to identify the emotional state. The data received as input is converted into text and emotion-tagged using speech recognition and natural language processing techniques. The output is the identified emotional state (e.g., stress, joy, sadness).

[0446] Step 3:

[0447] The device combines identified emotional states with user behavior data (such as location information and app usage history) to create packets for transmission to the server. This includes encryption to ensure the security of the information. The output is an encrypted data packet.

[0448] Step 4:

[0449] Server: The server receives encrypted data sent from the terminal and performs decryption processing. It analyzes the data packets received as input to obtain emotional state and behavioral data. This results in a user profile that includes emotional state.

[0450] Step 5:

[0451] Server: The server analyzes the acquired emotional profiles using a generating AI model and performs a risk assessment by comparing them with an external database. In this process, it considers the impact of emotional states on user decision-making and evaluates potential risks. The output includes the risk assessment results and appropriate advice candidates.

[0452] Step 6:

[0453] Server: The server generates advice tailored to the user based on the risk assessment results. The generation AI model selects the best advice from multiple options and formats it into a concrete action plan. The output provides the advice that should be provided to the user.

[0454] Step 7:

[0455] Terminal: Receives advice sent from the server and displays it to the user. The display method of the advice (e.g., text, audio, visual) is adjusted according to the user's current emotional state. Input includes generated advice data, and output is the displayed advice for the user.

[0456] Step 8:

[0457] User: The user responds to the advice received and inputs feedback into the application. This feedback is important for generating advice in the future. As output, the feedback data is sent to the server.

[0458] (Application Example 2)

[0459] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0460] In today's world, there is a need to accurately understand the emotional state of users and provide appropriate advice accordingly. However, conventional systems can only evaluate users based on their behavioral patterns, making it difficult to provide detailed support tailored to the emotional state of the user.

[0461] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0462] In this invention, the server includes means for recognizing the user's emotional state based on voice input or text input, means for comparing the user's behavioral patterns and emotional state with an external database to evaluate risk, and means for generating and providing advice tailored to the user's emotional state based on the evaluation results. This makes it possible to provide personalized advice from both the user's emotional and behavioral perspectives.

[0463] An "information processing device" is a device equipped with the technical means for processing and analyzing data.

[0464] "Means of data collection" refers to methods and devices for collecting various types of information obtained from users.

[0465] "Means of data analysis" refer to methods and devices for analyzing collected data in detail and extracting meaningful information.

[0466] A "behavioral pattern" is a model that represents the typical behavioral tendencies and characteristics of a user.

[0467] "Emotional state" refers to the state of the user's emotions and is data determined from voice and text.

[0468] An "external database" is a system that stores information and holds data for later retrieval and comparison.

[0469] "Means of risk assessment" are methods and devices for analyzing users' behavior and emotional states to predict potential problems.

[0470] "Means for generating advice" refers to methods or devices for creating helpful suggestions for users based on analysis results.

[0471] In this embodiment of the invention, the application installed on the information processing device is central. The system is downloaded and installed on the user's smartphone or similar device. When the application is launched, the user configures data sharing settings and selects to use the emotion recognition engine.

[0472] The device uses Google Cloud's language API to analyze the user's emotional state using voice and text input. The information entered by the user is encrypted and sent to the server.

[0473] The server analyzes the received data and generates detailed behavioral patterns and emotional profiles, including emotional states. These profiles are then compared against a database using analysis tools such as Scikit-learn.

[0474] Subsequently, the server generates personalized advice based on the information obtained, taking into account the user's current emotional state, and sends it to the device. This advice is created using a generative AI model that provides appropriate suggestions using prompt sentences.

[0475] For example, if a user types "I'm feeling very irritated today," the system recognizes this emotion and provides advice such as, "Try taking a few deep breaths to calm yourself down."

[0476] An example of a prompt in this invention is, "Based on the user's current emotional state, please suggest an appropriate relaxation method." This allows for the provision of flexible advice tailored to the user's emotions.

[0477] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0478] Step 1:

[0479] The user launches an application installed on their smartphone and uses voice or text input. During this process, the user inputs information about their emotions and state of mind. This input data is initially received by the application.

[0480] Step 2:

[0481] The device sends voice and text input from the user to Google Cloud's Language API for sentiment analysis. Based on the input data, this API outputs a sentiment score. Specifically, it analyzes the balance of positive and negative sentiment in the text from the input content and outputs it as a sentiment score.

[0482] Step 3:

[0483] The device encrypts and sends the analyzed sentiment score to the server. At this point, the data may also include location information and usage history based on the user's permission. Upon receiving the data, the server decrypts it and prepares it for analysis.

[0484] Step 4:

[0485] The server profiles the received sentiment scores and other behavioral data using machine learning libraries such as Scikit-learn. This profile includes the user's behavioral patterns and emotional states. Specific data processing includes cluster analysis and regression analysis to generate detailed user profiles.

[0486] Step 5:

[0487] The server performs a risk assessment by cross-referencing the generated profile with an external database. The assessment includes an analysis of how the user's emotional state influences the assessment. The output is the results of the risk assessment.

[0488] Step 6:

[0489] Based on the evaluation results and emotion score, the server receives prompt text using a generative AI model and generates personalized advice. Specifically, suggestions recommending appropriate actions and relaxation techniques are created based on successful examples in similar contexts.

[0490] Step 7:

[0491] The server sends the generated advice to the user's device. The device displays the advice to the user through an application. The user can then take action based on the advice.

[0492] Step 8:

[0493] Users can provide feedback on the advice provided through the application. This feedback is sent back to the server, and the system uses this information to improve the accuracy of the advice it provides. For example, if the feedback is positive, the model is adjusted to strengthen the methodology.

[0494] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0495] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0496] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0497] [Third Embodiment]

[0498] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0499] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0500] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0501] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0502] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0504] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0505] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0506] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0507] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0508] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0509] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0510] This invention relates to a system that provides personalized advice to users using a generative AI application that operates on an information processing device. In this system, the user first installs a dedicated application on their smartphone and sets the scope of data sharing through that application. Here, the user can select the data to share, such as location information, app usage history, and call records, thereby making it possible to provide necessary information while protecting personal privacy.

[0511] Data collection and transmission

[0512] Device: Based on the configured data range, the device periodically collects information in a predetermined manner. This includes methods for obtaining data through location services and app usage history APIs. The collected data is encrypted using AES or similar encryption and sent to the server via the HTTPS protocol.

[0513] Data Analysis

[0514] Server: When analyzing received data, machine learning algorithms are used to reveal user behavior patterns and interests. Clustering techniques and inference models are commonly used for this purpose. Individual profiles are generated based on the analysis results, and these profiles are used for further, more detailed analysis.

[0515] Risk assessment and advice generation

[0516] Server: The generated profile information is compared with an external database to perform a risk assessment. This database includes local security information and the latest crime trends. Based on the assessment, the AI ​​model generates safety-conscious advice for the user's actions. For example, if the user plans to visit a certain area late at night, the AI ​​will advise them to re-evaluate their actions based on the latest security information for that area.

[0517] Providing advice

[0518] Terminal: Advice sent from the server is visually displayed in the user interface. Furthermore, it includes a feature to immediately inform the user via push notifications based on urgency and importance.

[0519] Feedback and system improvements

[0520] User: Submits feedback on the advice provided. This feedback contributes to improving the application's usability and the accuracy of the advice. The feedback is collected on the server and used for future system improvements.

[0521] For example, if a user enters "I have a trip planned to a foreign country tomorrow," the server will analyze the safety situation and health information of the destination and generate and provide advice for safe travel. Through this series of processes, the present invention can contribute to improving the user's quality of life and ensuring their safety.

[0522] The following describes the processing flow.

[0523] Step 1:

[0524] User: Install the dedicated AI generation application on your smartphone. After installation, launch the app and perform the initial setup. Here, the user selects the data to share (e.g., location information, app usage history, call history, etc.). Review the terms of service and privacy policy and set the data sharing permission.

[0525] Step 2:

[0526] Device: Activates the function to collect user-selected data. Location information is obtained from GPS, and app usage history is collected through the OS API. The collected data is encrypted using the AES encryption algorithm to ensure data security.

[0527] Step 3:

[0528] Terminal: Sends encrypted data to the server using the HTTPS protocol. Transmission is performed periodically to ensure that the server always receives the latest data.

[0529] Step 4:

[0530] Server: Decrypts received encrypted data and stores it in the database. This data is then subjected to subsequent analysis and used to understand user behavior patterns.

[0531] Step 5:

[0532] Server: Uses machine learning algorithms to analyze information stored in the database. Through clustering techniques and regression analysis, it clarifies user behavior patterns and interests and generates individual profiles.

[0533] Step 6:

[0534] Server: The generated profile is compared against an external crime information database to assess the inherent risks in the user's behavior. Based on this assessment, the server quantitatively determines the level of caution required if a risk exists.

[0535] Step 7:

[0536] Server: Receives the user's planned activities entered into the app and generates specific advice based on that information. Natural language generation technology is used to create concise and easy-to-understand messages for advice generation.

[0537] Step 8:

[0538] Server: Sends generated advice to the terminal. Considering safety and usefulness, push notifications are sent as urgent information if necessary.

[0539] Step 9:

[0540] Terminal: Displays received advice on the user interface. Users can review the displayed information and use it in their daily lives.

[0541] Step 10:

[0542] User: Provides feedback on the advice provided. The feedback is sent to the server via the app and used to improve the system and the accuracy of the advice in the future.

[0543] (Example 1)

[0544] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0545] In modern society, there is a need to create an environment where users can safely receive personalized information and instructions. However, concerns remain regarding information privacy and security, and ensuring the safety and accuracy of collected information when analyzing and effectively utilizing it is a particular challenge.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0547] In this invention, the server is installed in an information processing device and includes means for acquiring information based on permission from the user to share information, means for analyzing the acquired information and modeling the user's behavior patterns and interests, and means for comparing the modeled behavior patterns with an external information aggregation environment and evaluating risks. This enables the user to receive personalized information safely and accurately.

[0548] An "information processing device" refers to an electronic device for receiving, analyzing, and transmitting data, and is a computer system capable of executing programs.

[0549] "Permission to share information" refers to the act of a user authorizing the sharing of their information with a third party, and includes the right to choose which information to share and to what extent.

[0550] "Means of acquiring information" refers to a series of methods and devices for collecting data on an information processing device, and includes a mechanism that allows necessary information to be acquired as appropriate through user operation and settings.

[0551] "Analysis" refers to the process of examining data in detail based on collected information to find meaning and patterns.

[0552] "Behavioral patterns" refer to characteristic movements and selection histories that demonstrate the consistency and repetition of a user's actions, and include the user's habits and behavioral tendencies revealed through analysis.

[0553] "Interests" refer to the specific interests and preferences that individual users exhibit, and are inferred from the user's past actions and choices.

[0554] "Modeling" refers to the process of formalizing user behavior and interests based on data obtained through analysis, and transforming them into an understandable format.

[0555] An "information aggregation environment" refers to a platform for collecting data from multiple sources and performing analysis and evaluation, enabling comparison and matching with external data.

[0556] "Means of risk assessment" refers to a system that identifies potential risks by comparing the user's actions and interests with information obtained from the external environment.

[0557] "Encryption" refers to the process of transforming information to make it unreadable in order to ensure the security of data, and is a technology used to prevent eavesdropping and tampering with information.

[0558] "Instructions" refer to messages, including specific actions and warnings, provided to users based on analysis results and evaluations.

[0559] "Response" refers to the opinions and impressions that users give in response to the instructions provided, and includes feedback that is used to improve the system.

[0560] This invention is a system that provides personalized instructions to users. This system functions through a dedicated application installed on an information processing device. First, the user installs this application on their device and sets the scope of information sharing. As a result, information such as location information, app usage history, and call records are collected within the specified scope.

[0561] Data collection and encryption processing

[0562] Device: Based on the user's set scope of information sharing, the device periodically collects data using location services, etc. The collected data is encrypted using AES encryption technology. This protects the information from unauthorized access.

[0563] Data Analysis

[0564] Server: Encrypted data is sent to the server via the HTTPS protocol. The server analyzes the data using machine learning algorithms to model user behavior patterns and interests. Clustering techniques and inference models are used in this analysis. The analyzed data is compiled into personalized profiles for each user by a generative AI model.

[0565] Risk assessment and directive generation

[0566] Server: Based on profile information, the server compares it with an external information aggregation environment to assess the current risk level. By utilizing databases of local safety information and social trends, it evaluates the risks to the user's actions and generates appropriate instructions. The generating AI model provides specific and responsive instructions based on the prompt. An example of instructions would be given in response to a prompt such as, "I'm planning to visit a new restaurant this weekend. Please give me some safety advice."

[0567] Providing instructions and feedback

[0568] Terminal: The generated instructions are provided to the user through the terminal application. The instructions are displayed visually and, in some cases, have the functionality to be delivered immediately as push notifications. This allows the user to receive important information in real time.

[0569] User: Users who receive instructions provide feedback on their content through the application. This feedback is sent to the server and used to improve the accuracy of system analysis and the user experience.

[0570] Through this series of processes, the present invention makes it possible to provide users with highly accurate and personalized instructions, thereby improving their quality of life and safety.

[0571] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0572] Step 1:

[0573] Application installation and configuration

[0574] User: Install the dedicated application on your device and launch it. An interface will appear where you can set the scope of information sharing. You will then enter the necessary permissions for collecting information such as location information, app usage history, and call records. This setting allows the application to explicitly recognize the scope of personal information that the user will provide.

[0575] Step 2:

[0576] Information gathering and encryption

[0577] Device: Installed applications periodically collect information based on user settings. This includes GPS data from location services and data from app usage history APIs. This data is encrypted using AES encryption technology to ensure security and data preservation. The encrypted data is then ready to be sent to the server.

[0578] Step 3:

[0579] Data transmission

[0580] Terminal: Encrypted data is sent to the server via the HTTPS protocol. This protocol ensures a high level of security against unauthorized external access during data transmission. The input here is encrypted user information, and the output is data securely stored on the server.

[0581] Step 4:

[0582] Data analysis and profile generation

[0583] Server: Uses machine learning algorithms to analyze the received data. Clustering techniques are used to analyze user behavior patterns and interests based on the input data. This generates a profile for each user. The output of the analysis is a user profile that reflects behavior patterns and interests.

[0584] Step 5:

[0585] Risk assessment and directive generation

[0586] Server: Based on the generated profile, it compares data with an external information aggregation environment and performs a risk assessment. Using local safety information and relevant databases, it generates appropriate instructions for user behavior using an AI model. The inputs are the profile and external data, and the output is personalized instructions for the user.

[0587] Step 6:

[0588] Providing instructions and collecting feedback

[0589] Terminal: Provides instructions from the server to the user. These are presented visually through an interface, and push notifications may be used depending on the urgency. During this process, information necessary for the user's actions is output.

[0590] User: Receives the provided instructions and sends feedback on them to the server via the terminal. This feedback serves as input for future system improvements.

[0591] This workflow allows the system to provide users with safe and useful instructions, improving safety and quality of life in real time.

[0592] (Application Example 1)

[0593] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0594] Ensuring safety in people's living environments is a crucial issue today, but there is a lack of systems that can provide real-time safety advice tailored to individual circumstances. Furthermore, effectively utilizing necessary information to provide personalized advice while protecting user privacy is a challenging task.

[0595] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0596] In this invention, the server includes means for collecting information based on permission to share information, means for analyzing the collected information and modeling behavioral trends, and means for comparing the modeled behavioral trends with an external information collection and evaluating risk. This makes it possible to provide personalized safety advice to users via push notifications and ensure safety in real time.

[0597] An "information processing device" is an electronic device used for inputting, analyzing, and outputting data, and is used to execute applications and programs.

[0598] "Permission to share information" is the act of a user authorizing an application to collect and use their information.

[0599] "Behavioral tendencies" refer to a series of behavioral patterns shown by a user's movements and habits, and are information used to infer the user's characteristics and preferences based on these patterns.

[0600] An "external information collection" is a set of data obtained from external databases and information sources, and is used to assess the risks that may affect user behavior.

[0601] "Push notifications" are a communication method used to present information to users in real time from applications installed on their devices.

[0602] An "artificial intelligence model" is a set of mathematical methods and algorithms designed to analyze and predict data, and it operates using machine learning techniques.

[0603] This invention provides a system that delivers personalized safety advice to users. The system mainly consists of an information processing device, a server, and a user terminal.

[0604] The device collects location information and behavioral patterns based on the user's consent. This collection includes obtaining data through location services and application usage history APIs. For example, applications installed on a smartphone perform this task. The collected information is encrypted with AES to ensure communication security and sent to the server via the HTTPS protocol.

[0605] The server uses Google Cloud Platform and other resources to analyze the received information. The analysis models behavioral trends and uses artificial intelligence models (e.g., TensorFlow) to compare them with external data sets and assess risk. These external data sets include local crime information and weather data, obtained using readily available APIs. This assessment generates personalized safety advice.

[0606] The server sends the generated advice to the user's device as a push notification. For this purpose, it uses real-time communication services such as Firebase Cloud Messaging. As a result, users can receive specific and personalized advice tailored to their environment, which helps them take safe actions.

[0607] For example, if a user inputs into the system that they plan to walk around the city in the evening while traveling, the server will analyze the latest safety information for that destination and immediately provide advice such as, "There have been recent theft incidents in that area, so please be careful and it is recommended that you return home early." An example of a prompt in such a specific case would be, "Based on the user's current location and planned activities, please conduct a safety assessment and provide advice based on the latest safety information as needed."

[0608] This system will enable users to always receive the latest information and appropriate instructions, allowing them to live a safe and secure life.

[0609] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0610] Step 1:

[0611] Based on user consent, the device collects location information and usage patterns through location services and application usage history APIs. Inputs include the user's current geographical coordinates and application usage frequency. The collected data is temporarily stored on the device for later analysis.

[0612] Step 2:

[0613] The device encrypts the collected data using AES and securely transmits it to the server using the HTTPS protocol. Input includes unencrypted user location information and usage patterns, while output is encrypted data securely transmitted to the server. Throughout this process, an encryption algorithm is applied to maintain data security.

[0614] Step 3:

[0615] The server decrypts the received encrypted data and performs analysis to model user behavior patterns. Inputs include decrypted user location information and usage patterns. The data is analyzed using machine learning algorithms, and a behavioral trend model is generated as output.

[0616] Step 4:

[0617] The server compares the generated behavioral trend model with external information sources to assess risk. Inputs include modeled user behavioral trends and external security data and local information. The comparison evaluates the potential risks associated with the user's behavior, and the risk assessment result is output. Here, a generative AI model is used to analyze prompt messages, resulting in a highly accurate assessment.

[0618] Step 5:

[0619] The server generates safety advice for the user based on the risk assessment results. The input is the risk assessment results, and the output is specific safety instructions sent to the user. In this process, an artificial intelligence model is used to create advice in a way that is easy for the user to understand.

[0620] Step 6:

[0621] The server pushes the generated advice to the user's device via a real-time communication service such as Firebase Cloud Messaging. The input is the generated safety advice, and the output is the notification data received on the user's device. This allows the user to instantly receive safe instructions regarding their actions.

[0622] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0623] This invention relates to a system that incorporates an emotion engine into a generative AI application installed in an information processing device, enabling it to provide users with more personalized advice.

[0624] Installation and setup

[0625] User: Download and install the AI ​​generation application on your smartphone. After launching the app, when setting the range of data to be used, the user can choose whether or not to use the emotion engine. Emotion recognition is performed based on voice input and text input.

[0626] Data collection and emotion recognition

[0627] Device: Based on the set range, in addition to normal data (location information and app usage history), the emotional state is analyzed from voice tone and word choice through the emotion engine. This identifies what emotions the user is feeling while using the app.

[0628] Data analysis and profiling

[0629] Server: Receives data sent from terminals, decrypts it, and performs analysis. It uses emotional information obtained from the emotion engine to generate detailed behavioral patterns and emotional profiles for each user. This provides a deeper understanding by adding emotional elements to models of normal behavioral patterns.

[0630] Risk assessment and advice generation

[0631] Server: The server compares behavioral patterns and emotional profiles with external crime information databases to assess risk. The risk assessment particularly considers cases where emotional state negatively impacts decision-making. Based on this, it generates flexible advice tailored to the emotional state. For example, it provides advice encouraging calmer behavior to users experiencing stress.

[0632] Providing advice and feedback

[0633] Terminal: Displays advice received from the server. The advice is presented using a display method that suits the user's emotional state. For example, a calm user will receive advice with more information, while a calmer user will receive simpler advice.

[0634] Emotional feedback and improvement

[0635] User: Enters their reactions and opinions on the advice provided as feedback into the app. This feedback is sent to the server, and the system uses this data to improve the accuracy of the advice.

[0636] For example, if a user inputs "I'm very tired from work," the emotion engine will determine that this emotion represents a stressful state. Based on this information, the server will advise on the current need for rest and suggest nearby relaxation spots and relaxation methods. In this way, the present invention can provide more appropriate advice by taking into account the user's state and emotions.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] User: Download and install the AI ​​generation application on your smartphone. Launch the app, review the terms of service and privacy policy, and then configure whether to share data and whether to use the emotion engine.

[0640] Step 2:

[0641] Device: Collects data permitted by the user. This includes location information, app usage history, and sentiment information based on voice and text input. The sentiment engine estimates emotional states from voice tone and keywords.

[0642] Step 3:

[0643] Terminal: Collected data is encrypted using encryption technologies such as AES and sent to the server via the HTTPS protocol. This ensures data security.

[0644] Step 4:

[0645] Server: Decodes received data and stores it in a database. Machine learning algorithms are used for analysis to process the data and generate behavioral patterns and emotional profiles.

[0646] Step 5:

[0647] Server: The server cross-references behavioral patterns and emotional profiles with external crime information databases to assess the risks associated with the user's behavior. This process particularly considers how recognized emotional states have an impact.

[0648] Step 6:

[0649] Server: Generates appropriate advice for the user based on risk assessment and emotional profile. The generated advice is personalized by adjusting the content and expression according to the emotional state.

[0650] Step 7:

[0651] Server: Sends the generated advice to the terminal. The advice is then formatted to be easily understood by the user.

[0652] Step 8:

[0653] Terminal: Displays received advice in the user interface. Users can review the displayed advice and decide on actions based on it.

[0654] Step 9:

[0655] User: Provides feedback by responding to the advice given. This feedback is sent to the server via the terminal and used to improve the system.

[0656] Step 10:

[0657] Server: Analyzes feedback to improve the accuracy of advice and sentiment recognition. The system learns to provide more personalized services in subsequent uses.

[0658] (Example 2)

[0659] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0660] In modern information processing systems, it is difficult to analyze not only users' behavioral patterns but also their emotional states in real time and provide advice based on that analysis. Furthermore, this advice must be adapted to individual situations and provided in a highly reliable manner. Moreover, realizing a mechanism that continuously incorporates user feedback while ensuring the security of information is also a challenging task.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0662] In this invention, the server is installed on an information processing device and includes means for collecting information based on permission from the user to share information; means incorporating an emotion engine that analyzes voice characteristics and language choices based on the collected information to identify the user's emotional state; and means for comparing the identified emotional state and behavioral patterns with an external database to evaluate risk. This makes it possible to provide personalized advice that takes the user's emotional state into consideration.

[0663] "Information processing equipment" is a general term for electronic devices that can collect, analyze, and transmit data.

[0664] "Information" refers to data used to identify a user's behavioral history and emotional state.

[0665] "Emotional state" refers to an internal psychological state identified based on the user's vocal characteristics and language choices.

[0666] An "emotion engine" is a technology that identifies a user's emotional state by analyzing voice characteristics and language selection data.

[0667] An "external database" is an external source of information used to match user behavior patterns and emotional states.

[0668] "Risk assessment" is the process of evaluating potential risks to users based on identified behavioral patterns and emotional states.

[0669] "Advice" refers to recommended actions or guidelines provided to users based on the results of a risk assessment.

[0670] "Feedback" refers to the collection of responses and opinions from users regarding the advice they receive.

[0671] A "generative AI model" is an artificial intelligence technology that utilizes machine learning algorithms for data analysis and providing advice.

[0672] A "prompt message" is an instruction or question designed to prompt the user to enter information.

[0673] The system in this invention uses a generative AI model incorporated into an information processing device to provide personalized advice based on the user's emotional state. Specifically, information gathering, sentiment analysis, risk assessment, and advice provision are performed through the interaction of a server, a terminal, and the user.

[0674] Server: The server receives encrypted information sent from the terminal and analyzes it using a generative AI model. It analyzes the user's voice characteristics and language choices through an emotion engine to identify the user's emotional state. Based on this information, it cross-references it with an external database to assess related risks. It then generates advice tailored to those risks and sends it to the terminal.

[0675] Terminal: The terminal analyzes voice and text input provided by the user using an emotion engine to identify the emotional state. It then encrypts the necessary data before sending it to the server for security. It receives advice from the server, visualizes it for the user, and displays the content in an easy-to-understand manner. The way the advice is displayed is adjusted according to the user's current emotional state.

[0676] User: The user interacts with the application and provides input through prompts. For example, they can respond to a prompt such as, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" As a result, the system can perform a more accurate analysis of the user's emotional state and provide personalized advice. By providing feedback on the advice the user receives, the system's generated AI model is continuously improved.

[0677] For example, if a user enters "I'm very tired from work" into the application, the emotion engine will determine the emotional state as stress and display advice such as, "Get enough rest. How about taking a walk in a nearby park or trying some relaxation exercises?" In this way, it is possible to provide specific responses tailored to the user's emotions and situation.

[0678] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0679] Step 1:

[0680] User: The user launches the application and, based on prompts, inputs their current emotions and situation via voice or text. The prompts are in the format of, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" The input data serves as foundational data for emotion recognition.

[0681] Step 2:

[0682] Terminal: The terminal receives input from the user and uses an emotion engine to analyze voice features and language choices to identify the emotional state. The data received as input is converted into text and emotion-tagged using speech recognition and natural language processing techniques. The output is the identified emotional state (e.g., stress, joy, sadness).

[0683] Step 3:

[0684] The device combines identified emotional states with user behavior data (such as location information and app usage history) to create packets for transmission to the server. This includes encryption to ensure the security of the information. The output is an encrypted data packet.

[0685] Step 4:

[0686] Server: The server receives encrypted data sent from the terminal and performs decryption processing. It analyzes the data packets received as input to obtain emotional state and behavioral data. This results in a user profile that includes emotional state.

[0687] Step 5:

[0688] Server: The server analyzes the acquired emotional profiles using a generating AI model and performs a risk assessment by comparing them with an external database. In this process, it considers the impact of emotional states on user decision-making and evaluates potential risks. The output includes the risk assessment results and appropriate advice candidates.

[0689] Step 6:

[0690] Server: The server generates advice tailored to the user based on the risk assessment results. The generation AI model selects the best advice from multiple options and formats it into a concrete action plan. The output provides the advice that should be provided to the user.

[0691] Step 7:

[0692] Terminal: Receives advice sent from the server and displays it to the user. The display method of the advice (e.g., text, audio, visual) is adjusted according to the user's current emotional state. Input includes generated advice data, and output is the displayed advice for the user.

[0693] Step 8:

[0694] User: The user responds to the advice received and inputs feedback into the application. This feedback is important for generating advice in the future. As output, the feedback data is sent to the server.

[0695] (Application Example 2)

[0696] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0697] In today's world, there is a need to accurately understand the emotional state of users and provide appropriate advice accordingly. However, conventional systems can only evaluate users based on their behavioral patterns, making it difficult to provide detailed support tailored to the emotional state of the user.

[0698] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0699] In this invention, the server includes means for recognizing the user's emotional state based on voice input or text input, means for comparing the user's behavioral patterns and emotional state with an external database to evaluate risk, and means for generating and providing advice tailored to the user's emotional state based on the evaluation results. This makes it possible to provide personalized advice from both the user's emotional and behavioral perspectives.

[0700] An "information processing device" is a device equipped with the technical means for processing and analyzing data.

[0701] "Means of data collection" refers to methods and devices for collecting various types of information obtained from users.

[0702] "Means of data analysis" refer to methods and devices for analyzing collected data in detail and extracting meaningful information.

[0703] A "behavioral pattern" is a model that represents the typical behavioral tendencies and characteristics of a user.

[0704] "Emotional state" refers to the state of the user's emotions and is data determined from voice and text.

[0705] An "external database" is a system that stores information and holds data for later retrieval and comparison.

[0706] "Means of risk assessment" are methods and devices for analyzing users' behavior and emotional states to predict potential problems.

[0707] "Means for generating advice" refers to methods or devices for creating helpful suggestions for users based on analysis results.

[0708] In this embodiment of the invention, the application installed on the information processing device is central. The system is downloaded and installed on the user's smartphone or similar device. When the application is launched, the user configures data sharing settings and selects to use the emotion recognition engine.

[0709] The device uses Google Cloud's language API to analyze the user's emotional state using voice and text input. The information entered by the user is encrypted and sent to the server.

[0710] The server analyzes the received data and generates detailed behavioral patterns and emotional profiles, including emotional states. These profiles are then compared against a database using analysis tools such as Scikit-learn.

[0711] Subsequently, the server generates personalized advice based on the information obtained, taking into account the user's current emotional state, and sends it to the device. This advice is created using a generative AI model that provides appropriate suggestions using prompt sentences.

[0712] For example, if a user types "I'm feeling very irritated today," the system recognizes this emotion and provides advice such as, "Try taking a few deep breaths to calm yourself down."

[0713] An example of a prompt in this invention is, "Based on the user's current emotional state, please suggest an appropriate relaxation method." This allows for the provision of flexible advice tailored to the user's emotions.

[0714] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0715] Step 1:

[0716] The user launches an application installed on their smartphone and uses voice or text input. During this process, the user inputs information about their emotions and state of mind. This input data is initially received by the application.

[0717] Step 2:

[0718] The device sends voice and text input from the user to Google Cloud's Language API for sentiment analysis. Based on the input data, this API outputs a sentiment score. Specifically, it analyzes the balance of positive and negative sentiment in the text from the input content and outputs it as a sentiment score.

[0719] Step 3:

[0720] The device encrypts and sends the analyzed sentiment score to the server. At this point, the data may also include location information and usage history based on the user's permission. Upon receiving the data, the server decrypts it and prepares it for analysis.

[0721] Step 4:

[0722] The server profiles the received sentiment scores and other behavioral data using machine learning libraries such as Scikit-learn. This profile includes the user's behavioral patterns and emotional states. Specific data processing includes cluster analysis and regression analysis to generate detailed user profiles.

[0723] Step 5:

[0724] The server performs a risk assessment by cross-referencing the generated profile with an external database. The assessment includes an analysis of how the user's emotional state influences the assessment. The output is the results of the risk assessment.

[0725] Step 6:

[0726] Based on the evaluation results and emotion score, the server receives prompt text using a generative AI model and generates personalized advice. Specifically, suggestions recommending appropriate actions and relaxation techniques are created based on successful examples in similar contexts.

[0727] Step 7:

[0728] The server sends the generated advice to the user's device. The device displays the advice to the user through an application. The user can then take action based on the advice.

[0729] Step 8:

[0730] Users can provide feedback on the advice provided through the application. This feedback is sent back to the server, and the system uses this information to improve the accuracy of the advice it provides. For example, if the feedback is positive, the model is adjusted to strengthen the methodology.

[0731] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0732] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0733] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0734] [Fourth Embodiment]

[0735] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0736] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0737] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0738] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0739] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0740] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0741] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0742] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0743] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0744] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0745] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0746] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0747] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0748] This invention relates to a system that provides personalized advice to users using a generative AI application that operates on an information processing device. In this system, the user first installs a dedicated application on their smartphone and sets the scope of data sharing through that application. Here, the user can select the data to share, such as location information, app usage history, and call records, thereby making it possible to provide necessary information while protecting personal privacy.

[0749] Data collection and transmission

[0750] Device: Based on the configured data range, the device periodically collects information in a predetermined manner. This includes methods for obtaining data through location services and app usage history APIs. The collected data is encrypted using AES or similar encryption and sent to the server via the HTTPS protocol.

[0751] Data Analysis

[0752] Server: When analyzing received data, machine learning algorithms are used to reveal user behavior patterns and interests. Clustering techniques and inference models are commonly used for this purpose. Individual profiles are generated based on the analysis results, and these profiles are used for further, more detailed analysis.

[0753] Risk assessment and advice generation

[0754] Server: The generated profile information is compared with an external database to perform a risk assessment. This database includes local security information and the latest crime trends. Based on the assessment, the AI ​​model generates safety-conscious advice for the user's actions. For example, if the user plans to visit a certain area late at night, the AI ​​will advise them to re-evaluate their actions based on the latest security information for that area.

[0755] Providing advice

[0756] Terminal: Advice sent from the server is visually displayed in the user interface. Furthermore, it includes a feature to immediately inform the user via push notifications based on urgency and importance.

[0757] Feedback and system improvements

[0758] User: Submits feedback on the advice provided. This feedback contributes to improving the application's usability and the accuracy of the advice. The feedback is collected on the server and used for future system improvements.

[0759] For example, if a user enters "I have a trip planned to a foreign country tomorrow," the server will analyze the safety situation and health information of the destination and generate and provide advice for safe travel. Through this series of processes, the present invention can contribute to improving the user's quality of life and ensuring their safety.

[0760] The following describes the processing flow.

[0761] Step 1:

[0762] User: Install the dedicated AI generation application on your smartphone. After installation, launch the app and perform the initial setup. Here, the user selects the data to share (e.g., location information, app usage history, call history, etc.). Review the terms of service and privacy policy and set the data sharing permission.

[0763] Step 2:

[0764] Device: Activates the function to collect user-selected data. Location information is obtained from GPS, and app usage history is collected through the OS API. The collected data is encrypted using the AES encryption algorithm to ensure data security.

[0765] Step 3:

[0766] Terminal: Sends encrypted data to the server using the HTTPS protocol. Transmission is performed periodically to ensure that the server always receives the latest data.

[0767] Step 4:

[0768] Server: Decrypts received encrypted data and stores it in the database. This data is then subjected to subsequent analysis and used to understand user behavior patterns.

[0769] Step 5:

[0770] Server: Uses machine learning algorithms to analyze information stored in the database. Through clustering techniques and regression analysis, it clarifies user behavior patterns and interests and generates individual profiles.

[0771] Step 6:

[0772] Server: The generated profile is compared against an external crime information database to assess the inherent risks in the user's behavior. Based on this assessment, the server quantitatively determines the level of caution required if a risk exists.

[0773] Step 7:

[0774] Server: Receives the user's planned activities entered into the app and generates specific advice based on that information. Natural language generation technology is used to create concise and easy-to-understand messages for advice generation.

[0775] Step 8:

[0776] Server: Sends generated advice to the terminal. Considering safety and usefulness, push notifications are sent as urgent information if necessary.

[0777] Step 9:

[0778] Terminal: Displays received advice on the user interface. Users can review the displayed information and use it in their daily lives.

[0779] Step 10:

[0780] User: Provides feedback on the advice provided. The feedback is sent to the server via the app and used to improve the system and the accuracy of the advice in the future.

[0781] (Example 1)

[0782] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0783] In modern society, there is a need to create an environment where users can safely receive personalized information and instructions. However, concerns remain regarding information privacy and security, and ensuring the safety and accuracy of collected information when analyzing and effectively utilizing it is a particular challenge.

[0784] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0785] In this invention, the server is installed in an information processing device and includes means for acquiring information based on permission from the user to share information, means for analyzing the acquired information and modeling the user's behavior patterns and interests, and means for comparing the modeled behavior patterns with an external information aggregation environment and evaluating risks. This enables the user to receive personalized information safely and accurately.

[0786] An "information processing device" refers to an electronic device for receiving, analyzing, and transmitting data, and is a computer system capable of executing programs.

[0787] "Permission to share information" refers to the act of a user authorizing the sharing of their information with a third party, and includes the right to choose which information to share and to what extent.

[0788] "Means of acquiring information" refers to a series of methods and devices for collecting data on an information processing device, and includes a mechanism that allows necessary information to be acquired as appropriate through user operation and settings.

[0789] "Analysis" refers to the process of examining data in detail based on collected information to find meaning and patterns.

[0790] "Behavioral patterns" refer to characteristic movements and selection histories that demonstrate the consistency and repetition of a user's actions, and include the user's habits and behavioral tendencies revealed through analysis.

[0791] "Interests" refer to the specific interests and preferences that individual users exhibit, and are inferred from the user's past actions and choices.

[0792] "Modeling" refers to the process of formalizing user behavior and interests based on data obtained through analysis, and transforming them into an understandable format.

[0793] An "information aggregation environment" refers to a platform for collecting data from multiple sources and performing analysis and evaluation, enabling comparison and matching with external data.

[0794] "Means of risk assessment" refers to a system that identifies potential risks by comparing the user's actions and interests with information obtained from the external environment.

[0795] "Encryption" refers to the process of transforming information to make it unreadable in order to ensure the security of data, and is a technology used to prevent eavesdropping and tampering with information.

[0796] "Instructions" refer to messages, including specific actions and warnings, provided to users based on analysis results and evaluations.

[0797] "Response" refers to the opinions and impressions that users give in response to the instructions provided, and includes feedback that is used to improve the system.

[0798] This invention is a system that provides personalized instructions to users. This system functions through a dedicated application installed on an information processing device. First, the user installs this application on their device and sets the scope of information sharing. As a result, information such as location information, app usage history, and call records are collected within the specified scope.

[0799] Data collection and encryption processing

[0800] Device: Based on the user's set scope of information sharing, the device periodically collects data using location services, etc. The collected data is encrypted using AES encryption technology. This protects the information from unauthorized access.

[0801] Data Analysis

[0802] Server: Encrypted data is sent to the server via the HTTPS protocol. The server analyzes the data using machine learning algorithms to model user behavior patterns and interests. Clustering techniques and inference models are used in this analysis. The analyzed data is compiled into personalized profiles for each user by a generative AI model.

[0803] Risk assessment and directive generation

[0804] Server: Based on profile information, the server compares it with an external information aggregation environment to assess the current risk level. By utilizing databases of local safety information and social trends, it evaluates the risks to the user's actions and generates appropriate instructions. The generating AI model provides specific and responsive instructions based on the prompt. An example of instructions would be given in response to a prompt such as, "I'm planning to visit a new restaurant this weekend. Please give me some safety advice."

[0805] Providing instructions and feedback

[0806] Terminal: The generated instructions are provided to the user through the terminal application. The instructions are displayed visually and, in some cases, have the functionality to be delivered immediately as push notifications. This allows the user to receive important information in real time.

[0807] User: Users who receive instructions provide feedback on their content through the application. This feedback is sent to the server and used to improve the accuracy of system analysis and the user experience.

[0808] Through this series of processes, the present invention makes it possible to provide users with highly accurate and personalized instructions, thereby improving their quality of life and safety.

[0809] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0810] Step 1:

[0811] Application installation and configuration

[0812] User: Install the dedicated application on your device and launch it. An interface will appear where you can set the scope of information sharing. You will then enter the necessary permissions for collecting information such as location information, app usage history, and call records. This setting allows the application to explicitly recognize the scope of personal information that the user will provide.

[0813] Step 2:

[0814] Information gathering and encryption

[0815] Device: Installed applications periodically collect information based on user settings. This includes GPS data from location services and data from app usage history APIs. This data is encrypted using AES encryption technology to ensure security and data preservation. The encrypted data is then ready to be sent to the server.

[0816] Step 3:

[0817] Data transmission

[0818] Terminal: Encrypted data is sent to the server via the HTTPS protocol. This protocol ensures a high level of security against unauthorized external access during data transmission. The input here is encrypted user information, and the output is data securely stored on the server.

[0819] Step 4:

[0820] Data analysis and profile generation

[0821] Server: Uses machine learning algorithms to analyze the received data. Clustering techniques are used to analyze user behavior patterns and interests based on the input data. This generates a profile for each user. The output of the analysis is a user profile that reflects behavior patterns and interests.

[0822] Step 5:

[0823] Risk assessment and directive generation

[0824] Server: Based on the generated profile, it compares data with an external information aggregation environment and performs a risk assessment. Using local safety information and relevant databases, it generates appropriate instructions for user behavior using an AI model. The inputs are the profile and external data, and the output is personalized instructions for the user.

[0825] Step 6:

[0826] Providing instructions and collecting feedback

[0827] Terminal: Provides instructions from the server to the user. These are presented visually through an interface, and push notifications may be used depending on the urgency. During this process, information necessary for the user's actions is output.

[0828] User: Receives the provided instructions and sends feedback on them to the server via the terminal. This feedback serves as input for future system improvements.

[0829] This workflow allows the system to provide users with safe and useful instructions, improving safety and quality of life in real time.

[0830] (Application Example 1)

[0831] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0832] Ensuring safety in people's living environments is a crucial issue today, but there is a lack of systems that can provide real-time safety advice tailored to individual circumstances. Furthermore, effectively utilizing necessary information to provide personalized advice while protecting user privacy is a challenging task.

[0833] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0834] In this invention, the server includes means for collecting information based on permission to share information, means for analyzing the collected information and modeling behavioral trends, and means for comparing the modeled behavioral trends with an external information collection and evaluating risk. This makes it possible to provide personalized safety advice to users via push notifications and ensure safety in real time.

[0835] An "information processing device" is an electronic device used for inputting, analyzing, and outputting data, and is used to execute applications and programs.

[0836] "Permission to share information" is the act of a user authorizing an application to collect and use their information.

[0837] "Behavioral tendencies" refer to a series of behavioral patterns shown by a user's movements and habits, and are information used to infer the user's characteristics and preferences based on these patterns.

[0838] An "external information collection" is a set of data obtained from external databases and information sources, and is used to assess the risks that may affect user behavior.

[0839] "Push notifications" are a communication method used to present information to users in real time from applications installed on their devices.

[0840] An "artificial intelligence model" is a set of mathematical methods and algorithms designed to analyze and predict data, and it operates using machine learning techniques.

[0841] This invention provides a system that delivers personalized safety advice to users. The system mainly consists of an information processing device, a server, and a user terminal.

[0842] The device collects location information and behavioral patterns based on the user's consent. This collection includes obtaining data through location services and application usage history APIs. For example, applications installed on a smartphone perform this task. The collected information is encrypted with AES to ensure communication security and sent to the server via the HTTPS protocol.

[0843] The server uses Google Cloud Platform and other resources to analyze the received information. The analysis models behavioral trends and uses artificial intelligence models (e.g., TensorFlow) to compare them with external data sets and assess risk. These external data sets include local crime information and weather data, obtained using readily available APIs. This assessment generates personalized safety advice.

[0844] The server sends the generated advice to the user's device as a push notification. For this purpose, it uses real-time communication services such as Firebase Cloud Messaging. As a result, users can receive specific and personalized advice tailored to their environment, which helps them take safe actions.

[0845] For example, if a user inputs into the system that they plan to walk around the city in the evening while traveling, the server will analyze the latest safety information for that destination and immediately provide advice such as, "There have been recent theft incidents in that area, so please be careful and it is recommended that you return home early." An example of a prompt in such a specific case would be, "Based on the user's current location and planned activities, please conduct a safety assessment and provide advice based on the latest safety information as needed."

[0846] This system will enable users to always receive the latest information and appropriate instructions, allowing them to live a safe and secure life.

[0847] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0848] Step 1:

[0849] Based on user consent, the device collects location information and usage patterns through location services and application usage history APIs. Inputs include the user's current geographical coordinates and application usage frequency. The collected data is temporarily stored on the device for later analysis.

[0850] Step 2:

[0851] The device encrypts the collected data using AES and securely transmits it to the server using the HTTPS protocol. Input includes unencrypted user location information and usage patterns, while output is encrypted data securely transmitted to the server. Throughout this process, an encryption algorithm is applied to maintain data security.

[0852] Step 3:

[0853] The server decrypts the received encrypted data and performs analysis to model user behavior patterns. Inputs include decrypted user location information and usage patterns. The data is analyzed using machine learning algorithms, and a behavioral trend model is generated as output.

[0854] Step 4:

[0855] The server compares the generated behavioral trend model with external information sources to assess risk. Inputs include modeled user behavioral trends and external security data and local information. The comparison evaluates the potential risks associated with the user's behavior, and the risk assessment result is output. Here, a generative AI model is used to analyze prompt messages, resulting in a highly accurate assessment.

[0856] Step 5:

[0857] The server generates safety advice for the user based on the risk assessment results. The input is the risk assessment results, and the output is specific safety instructions sent to the user. In this process, an artificial intelligence model is used to create advice in a way that is easy for the user to understand.

[0858] Step 6:

[0859] The server pushes the generated advice to the user's device via a real-time communication service such as Firebase Cloud Messaging. The input is the generated safety advice, and the output is the notification data received on the user's device. This allows the user to instantly receive safe instructions regarding their actions.

[0860] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0861] This invention relates to a system that incorporates an emotion engine into a generative AI application installed in an information processing device, enabling it to provide users with more personalized advice.

[0862] Installation and setup

[0863] User: Download and install the AI ​​generation application on your smartphone. After launching the app, when setting the range of data to be used, the user can choose whether or not to use the emotion engine. Emotion recognition is performed based on voice input and text input.

[0864] Data collection and emotion recognition

[0865] Device: Based on the set range, in addition to normal data (location information and app usage history), the emotional state is analyzed from voice tone and word choice through the emotion engine. This identifies what emotions the user is feeling while using the app.

[0866] Data analysis and profiling

[0867] Server: Receives data sent from terminals, decrypts it, and performs analysis. It uses emotional information obtained from the emotion engine to generate detailed behavioral patterns and emotional profiles for each user. This provides a deeper understanding by adding emotional elements to models of normal behavioral patterns.

[0868] Risk assessment and advice generation

[0869] Server: The server compares behavioral patterns and emotional profiles with external crime information databases to assess risk. The risk assessment particularly considers cases where emotional state negatively impacts decision-making. Based on this, it generates flexible advice tailored to the emotional state. For example, it provides advice encouraging calmer behavior to users experiencing stress.

[0870] Providing advice and feedback

[0871] Terminal: Displays advice received from the server. The advice is presented using a display method that suits the user's emotional state. For example, a calm user will receive advice with more information, while a calmer user will receive simpler advice.

[0872] Emotional feedback and improvement

[0873] User: Enters their reactions and opinions on the advice provided as feedback into the app. This feedback is sent to the server, and the system uses this data to improve the accuracy of the advice.

[0874] For example, if a user inputs "I'm very tired from work," the emotion engine will determine that this emotion represents a stressful state. Based on this information, the server will advise on the current need for rest and suggest nearby relaxation spots and relaxation methods. In this way, the present invention can provide more appropriate advice by taking into account the user's state and emotions.

[0875] The following describes the processing flow.

[0876] Step 1:

[0877] User: Download and install the AI ​​generation application on your smartphone. Launch the app, review the terms of service and privacy policy, and then configure whether to share data and whether to use the emotion engine.

[0878] Step 2:

[0879] Device: Collects data permitted by the user. This includes location information, app usage history, and sentiment information based on voice and text input. The sentiment engine estimates emotional states from voice tone and keywords.

[0880] Step 3:

[0881] Terminal: Collected data is encrypted using encryption technologies such as AES and sent to the server via the HTTPS protocol. This ensures data security.

[0882] Step 4:

[0883] Server: Decodes received data and stores it in a database. Machine learning algorithms are used for analysis to process the data and generate behavioral patterns and emotional profiles.

[0884] Step 5:

[0885] Server: The server cross-references behavioral patterns and emotional profiles with external crime information databases to assess the risks associated with the user's behavior. This process particularly considers how recognized emotional states have an impact.

[0886] Step 6:

[0887] Server: Generates appropriate advice for the user based on risk assessment and emotional profile. The generated advice is personalized by adjusting the content and expression according to the emotional state.

[0888] Step 7:

[0889] Server: Sends the generated advice to the terminal. The advice is then formatted to be easily understood by the user.

[0890] Step 8:

[0891] Terminal: Displays received advice in the user interface. Users can review the displayed advice and decide on actions based on it.

[0892] Step 9:

[0893] User: Provides feedback by responding to the advice given. This feedback is sent to the server via the terminal and used to improve the system.

[0894] Step 10:

[0895] Server: Analyzes feedback to improve the accuracy of advice and sentiment recognition. The system learns to provide more personalized services in subsequent uses.

[0896] (Example 2)

[0897] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0898] In modern information processing systems, it is difficult to analyze not only users' behavioral patterns but also their emotional states in real time and provide advice based on that analysis. Furthermore, this advice must be adapted to individual situations and provided in a highly reliable manner. Moreover, realizing a mechanism that continuously incorporates user feedback while ensuring the security of information is also a challenging task.

[0899] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0900] In this invention, the server is installed on an information processing device and includes means for collecting information based on permission from the user to share information; means incorporating an emotion engine that analyzes voice characteristics and language choices based on the collected information to identify the user's emotional state; and means for comparing the identified emotional state and behavioral patterns with an external database to evaluate risk. This makes it possible to provide personalized advice that takes the user's emotional state into consideration.

[0901] "Information processing equipment" is a general term for electronic devices that can collect, analyze, and transmit data.

[0902] "Information" refers to data used to identify a user's behavioral history and emotional state.

[0903] "Emotional state" refers to an internal psychological state identified based on the user's vocal characteristics and language choices.

[0904] An "emotion engine" is a technology that identifies a user's emotional state by analyzing voice characteristics and language selection data.

[0905] An "external database" is an external source of information used to match user behavior patterns and emotional states.

[0906] "Risk assessment" is the process of evaluating potential risks to users based on identified behavioral patterns and emotional states.

[0907] "Advice" refers to recommended actions or guidelines provided to users based on the results of a risk assessment.

[0908] "Feedback" refers to the collection of responses and opinions from users regarding the advice they receive.

[0909] A "generative AI model" is an artificial intelligence technology that utilizes machine learning algorithms for data analysis and providing advice.

[0910] A "prompt message" is an instruction or question designed to prompt the user to enter information.

[0911] The system in this invention uses a generative AI model incorporated into an information processing device to provide personalized advice based on the user's emotional state. Specifically, information gathering, sentiment analysis, risk assessment, and advice provision are performed through the interaction of a server, a terminal, and the user.

[0912] Server: The server receives encrypted information sent from the terminal and analyzes it using a generative AI model. It analyzes the user's voice characteristics and language choices through an emotion engine to identify the user's emotional state. Based on this information, it cross-references it with an external database to assess related risks. It then generates advice tailored to those risks and sends it to the terminal.

[0913] Terminal: The terminal analyzes voice and text input provided by the user using an emotion engine to identify the emotional state. It then encrypts the necessary data before sending it to the server for security. It receives advice from the server, visualizes it for the user, and displays the content in an easy-to-understand manner. The way the advice is displayed is adjusted according to the user's current emotional state.

[0914] User: The user interacts with the application and provides input through prompts. For example, they can respond to a prompt such as, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" As a result, the system can perform a more accurate analysis of the user's emotional state and provide personalized advice. By providing feedback on the advice the user receives, the system's generated AI model is continuously improved.

[0915] For example, if a user enters "I'm very tired from work" into the application, the emotion engine will determine the emotional state as stress and display advice such as, "Get enough rest. How about taking a walk in a nearby park or trying some relaxation exercises?" In this way, it is possible to provide specific responses tailored to the user's emotions and situation.

[0916] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0917] Step 1:

[0918] User: The user launches the application and, based on prompts, inputs their current emotions and situation via voice or text. The prompts are in the format of, "Please tell us how you are feeling right now. Is there anything in particular that has happened recently that has left a lasting impression on you?" The input data serves as foundational data for emotion recognition.

[0919] Step 2:

[0920] Terminal: The terminal receives input from the user and uses an emotion engine to analyze voice features and language choices to identify the emotional state. The data received as input is converted into text and emotion-tagged using speech recognition and natural language processing techniques. The output is the identified emotional state (e.g., stress, joy, sadness).

[0921] Step 3:

[0922] The device combines identified emotional states with user behavior data (such as location information and app usage history) to create packets for transmission to the server. This includes encryption to ensure the security of the information. The output is an encrypted data packet.

[0923] Step 4:

[0924] Server: The server receives encrypted data sent from the terminal and performs decryption processing. It analyzes the data packets received as input to obtain emotional state and behavioral data. This results in a user profile that includes emotional state.

[0925] Step 5:

[0926] Server: The server analyzes the acquired emotional profiles using a generating AI model and performs a risk assessment by comparing them with an external database. In this process, it considers the impact of emotional states on user decision-making and evaluates potential risks. The output includes the risk assessment results and appropriate advice candidates.

[0927] Step 6:

[0928] Server: The server generates advice tailored to the user based on the risk assessment results. The generation AI model selects the best advice from multiple options and formats it into a concrete action plan. The output provides the advice that should be provided to the user.

[0929] Step 7:

[0930] Terminal: Receives advice sent from the server and displays it to the user. The display method of the advice (e.g., text, audio, visual) is adjusted according to the user's current emotional state. Input includes generated advice data, and output is the displayed advice for the user.

[0931] Step 8:

[0932] User: The user responds to the advice received and inputs feedback into the application. This feedback is important for generating advice in the future. As output, the feedback data is sent to the server.

[0933] (Application Example 2)

[0934] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0935] In today's world, there is a need to accurately understand the emotional state of users and provide appropriate advice accordingly. However, conventional systems can only evaluate users based on their behavioral patterns, making it difficult to provide detailed support tailored to the emotional state of the user.

[0936] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0937] In this invention, the server includes means for recognizing the user's emotional state based on voice input or text input, means for comparing the user's behavioral patterns and emotional state with an external database to evaluate risk, and means for generating and providing advice tailored to the user's emotional state based on the evaluation results. This makes it possible to provide personalized advice from both the user's emotional and behavioral perspectives.

[0938] An "information processing device" is a device equipped with the technical means for processing and analyzing data.

[0939] "Means of data collection" refers to methods and devices for collecting various types of information obtained from users.

[0940] "Means of data analysis" refer to methods and devices for analyzing collected data in detail and extracting meaningful information.

[0941] A "behavioral pattern" is a model that represents the typical behavioral tendencies and characteristics of a user.

[0942] "Emotional state" refers to the state of the user's emotions and is data determined from voice and text.

[0943] An "external database" is a system that stores information and holds data for later retrieval and comparison.

[0944] "Means of risk assessment" are methods and devices for analyzing users' behavior and emotional states to predict potential problems.

[0945] "Means for generating advice" refers to methods or devices for creating helpful suggestions for users based on analysis results.

[0946] In this embodiment of the invention, the application installed on the information processing device is central. The system is downloaded and installed on the user's smartphone or similar device. When the application is launched, the user configures data sharing settings and selects to use the emotion recognition engine.

[0947] The device uses Google Cloud's language API to analyze the user's emotional state using voice and text input. The information entered by the user is encrypted and sent to the server.

[0948] The server analyzes the received data and generates detailed behavioral patterns and emotional profiles, including emotional states. These profiles are then compared against a database using analysis tools such as Scikit-learn.

[0949] Subsequently, the server generates personalized advice based on the information obtained, taking into account the user's current emotional state, and sends it to the device. This advice is created using a generative AI model that provides appropriate suggestions using prompt sentences.

[0950] For example, if a user types "I'm feeling very irritated today," the system recognizes this emotion and provides advice such as, "Try taking a few deep breaths to calm yourself down."

[0951] An example of a prompt in this invention is, "Based on the user's current emotional state, please suggest an appropriate relaxation method." This allows for the provision of flexible advice tailored to the user's emotions.

[0952] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0953] Step 1:

[0954] The user launches an application installed on their smartphone and uses voice or text input. During this process, the user inputs information about their emotions and state of mind. This input data is initially received by the application.

[0955] Step 2:

[0956] The device sends voice and text input from the user to Google Cloud's Language API for sentiment analysis. Based on the input data, this API outputs a sentiment score. Specifically, it analyzes the balance of positive and negative sentiment in the text from the input content and outputs it as a sentiment score.

[0957] Step 3:

[0958] The device encrypts and sends the analyzed sentiment score to the server. At this point, the data may also include location information and usage history based on the user's permission. Upon receiving the data, the server decrypts it and prepares it for analysis.

[0959] Step 4:

[0960] The server profiles the received sentiment scores and other behavioral data using machine learning libraries such as Scikit-learn. This profile includes the user's behavioral patterns and emotional states. Specific data processing includes cluster analysis and regression analysis to generate detailed user profiles.

[0961] Step 5:

[0962] The server performs a risk assessment by cross-referencing the generated profile with an external database. The assessment includes an analysis of how the user's emotional state influences the assessment. The output is the results of the risk assessment.

[0963] Step 6:

[0964] Based on the evaluation results and emotion score, the server receives prompt text using a generative AI model and generates personalized advice. Specifically, suggestions recommending appropriate actions and relaxation techniques are created based on successful examples in similar contexts.

[0965] Step 7:

[0966] The server sends the generated advice to the user's device. The device displays the advice to the user through an application. The user can then take action based on the advice.

[0967] Step 8:

[0968] Users can provide feedback on the advice provided through the application. This feedback is sent back to the server, and the system uses this information to improve the accuracy of the advice it provides. For example, if the feedback is positive, the model is adjusted to strengthen the methodology.

[0969] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0970] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0971] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0972] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0973] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0974] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0975] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0976] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0977] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0978] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0979] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0980] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0981] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0982] 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.

[0983] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0984] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0985] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0986] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0987] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0988] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0989] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0990] The following is further disclosed regarding the embodiments described above.

[0991] (Claim 1)

[0992] A means of collecting data, which is installed on an information processing device and is based on permission from the user to share data,

[0993] A means of analyzing the aforementioned collected data and modeling user behavior patterns and interests,

[0994] A means for comparing the modeled behavioral patterns with an external database and evaluating the risks,

[0995] A means of providing advice to users based on the aforementioned evaluation results,

[0996] A system that includes this.

[0997] (Claim 2)

[0998] The system according to claim 1, further comprising means for encrypting data in order to securely transmit information.

[0999] (Claim 3)

[1000] The system according to claim 1, comprising means for collecting feedback from users and improving the accuracy of the advice provided based on that feedback.

[1001] "Example 1"

[1002] (Claim 1)

[1003] A means of acquiring information, which is installed on an information processing device and based on permission from the user to share information,

[1004] A means for analyzing the acquired information and modeling the user's behavior patterns and interests,

[1005] A means for comparing the modeled operating pattern with an external information aggregation environment and evaluating the risk,

[1006] Based on the aforementioned evaluation results, a means for providing instructions to the user,

[1007] A means of aggregating information based on the scope of information sharing set by the user and communicating it in an encrypted state,

[1008] A system that includes this.

[1009] (Claim 2)

[1010] The system according to claim 1, further comprising means for encrypting information in order to ensure the secure transmission of information.

[1011] (Claim 3)

[1012] The system according to claim 1, comprising means for collecting user feedback and improving the accuracy of instructions provided based on that feedback.

[1013] "Application Example 1"

[1014] (Claim 1)

[1015] A means of collecting information, which is installed on an information processing device and based on permission from the user to share information,

[1016] A means for analyzing the collected information and modeling the user's behavioral tendencies and interests,

[1017] A means of comparing the modeled behavioral tendencies with external information sources to assess risk,

[1018] Based on the aforementioned evaluation results, a means of providing personalized safety advice to users via push notifications,

[1019] A method for evaluating safety information using an artificial intelligence model,

[1020] A system that includes this.

[1021] (Claim 2)

[1022] The system according to claim 1, further comprising means for encrypting information in order to securely transmit the information.

[1023] (Claim 3)

[1024] The system according to claim 1, comprising means for collecting opinions from users and improving the accuracy of advice provided based on those opinions.

[1025] "Example 2 of combining an emotion engine"

[1026] (Claim 1)

[1027] A means of collecting information that is installed on information processing equipment and based on permission from the user to share information,

[1028] Based on the information collected, a means incorporating an emotion engine that analyzes voice features and language selection to identify the user's emotional state,

[1029] A means of assessing risk by comparing identified emotional states and behavioral patterns with an external database,

[1030] Based on the aforementioned evaluation results, a means for generating and providing advice to the user according to their emotional state,

[1031] A system that includes this.

[1032] (Claim 2)

[1033] The system according to claim 1, further comprising means for encrypting information in order to securely transmit the information.

[1034] (Claim 3)

[1035] The system according to claim 1, comprising means for collecting user feedback and improving the accuracy of advice provided using a generated AI model based on that feedback.

[1036] "Application example 2 when combining with an emotional engine"

[1037] (Claim 1)

[1038] A means of collecting data, which is installed on an information processing device and is based on permission from the user to share data,

[1039] A means of analyzing the aforementioned collected data and modeling user behavior patterns and interests,

[1040] A means of recognizing the emotional state based on the user's voice input or text input,

[1041] A means for comparing the modeled behavioral patterns and emotional states with an external database and evaluating the risk,

[1042] Based on the aforementioned evaluation results, a means for generating and providing advice tailored to the user's emotional state,

[1043] A system that includes this.

[1044] (Claim 2)

[1045] The system according to claim 1, further comprising means for encrypting data in order to securely transmit information.

[1046] (Claim 3)

[1047] The system according to claim 1, comprising means for collecting feedback from users and improving the accuracy of the advice provided based on that feedback. [Explanation of Symbols]

[1048] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting information, which is installed on an information processing device and based on permission from the user to share information, A means for analyzing the collected information and modeling the user's behavioral tendencies and interests, A means of comparing the modeled behavioral tendencies with external information sources to assess risk, Based on the aforementioned evaluation results, a means of providing personalized safety advice to users via push notifications, A method for evaluating safety information using an artificial intelligence model, A system that includes this.

2. The system according to claim 1, further comprising means for encrypting information in order to securely transmit the information.

3. The system according to claim 1, comprising means for collecting opinions from users and improving the accuracy of advice provided based on those opinions.

Images