System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and storing user information in a database; means for analyzing the received user information using generative artificial intelligence and artificial general intelligence; means for generating customized recommendations based on the analyzing; means for communicating the generated recommendations to user terminals; and means for receiving and storing feedback from users in the database and adjusting the recommendations in real-time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's world, there is a growing need for personalized advice based on individual lifestyle habits and preferences. However, existing systems lack the data collection and analysis capabilities to meet individual needs, and lack specific suggestions for improving health management and time efficiency in daily life. In particular, it is difficult to provide precise recommendations based on user preferences and behavioral patterns, creating a demand for systems that can continuously collect data and make adjustments in real time. [Means for solving the problem]

[0005] The present invention relates to a system for providing customized recommendations based on an individual's lifestyle. Specifically, the system includes a means for receiving user information and recording it in a database, a means for analyzing data using generative artificial intelligence and general artificial intelligence (AI) based on the received user information, a means for generating customized recommendations based on the analysis results, a means for notifying a user terminal of the generated recommendations, and a means for receiving feedback from the user, recording it in a database, and adjusting the recommendations in real time. This system allows users to receive suggestions based on their individual preferences and lifestyle, enabling them to live a healthy and efficient life.

[0006] "User Information" is data that the system obtains from a user, including basic personal information, profile details, and activity data.

[0007] "Generative artificial intelligence" is an AI technology that can learn patterns based on large amounts of data and generate new information.

[0008] "General artificial intelligence" is a high-performance AI technology that can flexibly perform a wide variety of tasks and is not limited to any specific use.

[0009] "Recommendations" are personalized suggestions generated based on a user's preferences and behavioral patterns.

[0010] "User terminal" refers to a digital device used by a user, such as a smartphone, tablet, or PC.

[0011] "Feedback" refers to opinions and evaluation information provided by users to the system. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The system of the present invention provides customized recommendations based on a user's lifestyle. The system operates through a series of steps: collecting user information, analyzing the data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), generating recommendations, notifying users, and collecting and adjusting feedback in real time.

[0034] Collection and management of user information

[0035] When a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals). This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[0036] Data analysis using AI models

[0037] The server analyzes the received user information and activity data using generative AI and AGI algorithms, learning the user's behavioral patterns and preferences and extracting individual characteristics. For example, this can reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[0038] Generating customized recommendations

[0039] The server generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[0040] User interface presentation

[0041] The recommendation generated by the server is pushed to the user's device. The device receives the notification and displays it to the user. The user can then check the notification and take specific action. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[0042] Real-time feedback and adjustments

[0043] Users can provide feedback on recommendations on their devices. This feedback is received by the server and recorded in a database. The server then updates the AI ​​model in real time based on the feedback and reflects it in the next recommendation. This ensures that the system always provides the latest and most optimal suggestions.

[0044] Specific examples

[0045] For example, User A registers with the system and provides the following information:

[0046] Name: User A

[0047] Age: 35

[0048] Gender: Female

[0049] Eating habits: Health-conscious, vegetarian

[0050] Hobbies: Watching movies, running

[0051] Health goals: weight management, stress reduction

[0052] When User A connects a wearable fitness tracker, the server receives and records data from the wearable device (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[0053] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[0054] In this way, the system supports efficient and fulfilling daily life by providing sophisticated recommendations based on the user's individual preferences and lifestyle.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, this information is transferred to the server, which verifies the received information and records it in a database.

[0058] Step 2:

[0059] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the data and presses the submit button. The server receives these details and stores them in a database.

[0060] Step 3:

[0061] When a user connects a wearable device (such as a fitness tracker or smartwatch) to the system, the server periodically receives activity data (such as steps, heart rate, and sleep data) from the device, and the received data is recorded in a database.

[0062] Step 4:

[0063] The server retrieves user information and activity data from the database and performs data cleansing and pre-processing, including removing duplicate data and imputing missing values.

[0064] Step 5:

[0065] The server analyzes the preprocessed data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI) algorithms. Specifically, it learns each user's behavioral patterns and preferences and extracts features. This analysis allows it to understand the user's specific behavioral patterns (e.g., preference for certain foods on certain days of the week) and health status (e.g., high stress on certain days).

[0066] Step 6:

[0067] Based on the AI ​​analysis results, the server generates personalized recommendations for each user, including meal plans that match the user's health goals, entertainment suggestions based on the user's hobbies, and reminders for optimal schedule management.

[0068] Step 7:

[0069] The device receives the recommendations generated by the server via push notification and displays them to the user, who can then check the notification and take specific actions based on the recommendations.

[0070] Step 8:

[0071] The user provides feedback on the recommendation (e.g., "very satisfied," "satisfied," "unsatisfied," etc.) through the device. The device receives this feedback information and forwards it to the server.

[0072] Step 9:

[0073] The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process ensures that the system always provides the latest and most optimal suggestions.

[0074] Example 1

[0075] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0076] Conventional recommendation systems have difficulty providing customized recommendations based on a user's individual preferences and lifestyle. Furthermore, they lack the functionality to reflect user feedback in real time and improve the content of future recommendations. This results in low user satisfaction and makes it difficult to encourage continued use.

[0077] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0078] In this invention, the server includes means for receiving user information and recording it in a database, means for displaying a form for inputting detailed profile information and recording the detailed information in the database, means for receiving and recording activity data from the wearable device, means for integrating the received user information and activity data and analyzing the data using generative artificial intelligence and general artificial intelligence, means for generating customized recommendations based on the analysis results, means for notifying the user terminal of the generated recommendations, and means for receiving feedback from the user and recording it in the database, updating the generative artificial intelligence and general artificial intelligence models in real time to reflect the feedback in the next recommendation. This makes it possible to provide sophisticated recommendations based on the individual preferences and lifestyle of the user and reflect user feedback in real time.

[0079] "User Information" refers to basic information such as a user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[0080] "Database" refers to systems and software used to record and store information, such as user information and activity data.

[0081] "Form" refers to an interface that provides a screen layout and input fields for a user to enter detailed profile information.

[0082] "Wearable devices" refers to various electronic devices that are worn on the body, such as fitness trackers and smartwatches.

[0083] "Activity data" refers to information about a user's activities, such as steps, heart rate, and sleep data obtained from a wearable device.

[0084] "Generative artificial intelligence (generative AI)" refers to artificial intelligence that has the ability to generate new information based on large amounts of data.

[0085] "Artificial general intelligence (AGI)" refers to advanced artificial intelligence that can handle a wide range of tasks and functions, rather than specific tasks.

[0086] "Recommendations" refers to suggested actions, products, services, information, etc., based on a user's specific circumstances or preferences.

[0087] "Push notification" refers to an automatic message notification sent from a server to a user device.

[0088] "Feedback" refers to the rating and comment information provided by a user in response to a recommendation they receive.

[0089] "Real-time" refers to processing and information being reflected immediately without delay.

[0090] "Update" refers to correcting or supplementing existing data or models with new information.

[0091] The system of the present invention provides customized recommendations based on a user's lifestyle. The system performs a series of data collection, analysis, recommendation generation, notification, feedback collection, and real-time adjustment through interactions between a server, a terminal, and a user.

[0092] First, when a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. Next, the device displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), and the user is prompted to enter the details. This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[0093] The server analyzes the received user information and activity data using generative artificial intelligence (AI) and artificial general intelligence (AGI) algorithms. This analysis learns the user's behavioral patterns and preferences and extracts individual characteristics. For example, it may reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[0094] The server then generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[0095] The generated recommendation is pushed from the server to the user's device. The device receives the notification and displays the notification content to the user. The user can check the notification and take specific actions. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[0096] Users provide feedback on recommendations via their devices. This feedback is received by the server and recorded in a database. The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. This makes it possible to always provide users with the latest and most optimal suggestions.

[0097] As a concrete example, suppose User A newly registers with the system and provides the following information:

[0098] Name: User A

[0099] Age: 35

[0100] Gender: Female

[0101] Eating habits: Health-conscious, vegetarian

[0102] Hobbies: Watching movies, running

[0103] Health goals: weight management, stress reduction

[0104] When User A connects a fitness tracker, the server receives and records data from the fitness tracker (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[0105] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[0106] An example of a prompt for a generative AI model is:

[0107] "Based on the new user's information, we suggest healthy vegetarian recipes and relaxing movies."

[0108] Through the above process, the system can provide precise recommendations based on the user's individual preferences and lifestyle, supporting an efficient and fulfilling daily life.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1: User registration and receipt of basic information

[0111] When a user signs up to the system, the server receives basic information (such as name, age, gender, and email address) that is provided as input in a form. The server records this information in a database to create a basic profile of the user.

[0112] Specifically, the user enters basic information into the form and clicks the "Submit" button. The entered basic information is sent to the server and saved in the database.

[0113] Step 2: Collect detailed profile information

[0114] The device displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the details, which are then sent to the server and recorded in a database.

[0115] Specifically, the user enters information such as eating habits and hobbies into a form on the device and clicks the "Submit" button. The server receives this information and stores it in a database.

[0116] Step 3: Connect your wearable device

[0117] Users connect their fitness trackers, smartwatches, etc. to the system, and the server periodically receives activity data (such as steps, heart rate, and sleep data) from the connected devices and records it in a database.

[0118] Specifically, the user clicks the "Link Device" button on the app's settings screen and follows the instructions to link the device. The server receives activity data from the device every hour and stores it in a database.

[0119] Step 4: Data analysis with generative AI

[0120] The server integrates the received user information and activity data and analyzes the data using a generative AI model. Basic information, detailed profile information, and activity data are provided as input data to the generative AI. The generative AI learns the user's behavioral patterns and preferences and extracts features.

[0121] Specifically, the server inputs data into a generative AI model and generates results using prompts such as "Tell me about the user's weekend eating patterns." The output is the user's behavioral patterns.

[0122] Step 5: Learning behavioral patterns using general artificial intelligence

[0123] The server inputs the analysis results of the generative AI into the AGI algorithm to learn detailed behavioral patterns and improve the model. The results of the generative AI are given as input data to the AGI for further advanced analysis.

[0124] Specifically, the server passes the output of the generation AI to the AGI, and inputs a prompt such as "Please learn more detailed behavioral patterns." The output is a more detailed behavioral pattern.

[0125] Step 6: Generate customized recommendations

[0126] The server generates customized recommendations based on the analysis results of the generative AI and AGI. The analysis results are used as input data. The output is suggestions tailored to each user.

[0127] Specifically, the server creates recommendations based on the results of generative AI and AGI. The recommendations are created using prompts such as "Please suggest healthy vegetarian recipes for user A on busy weekdays."

[0128] Step 7: Recommendation Notification

[0129] The server pushes the generated recommendations to the user device. The generated recommendations are used as input. The output is a notification message sent to the user device.

[0130] Specifically, the server will push a message to User A such as, "Here are some vegetarian recipes to recommend for busy days."

[0131] Step 8: Gather user feedback

[0132] The user provides feedback on the recommendation at the terminal. The feedback the user returns is used as input. The server receives this feedback and records it in a database.

[0133] Specifically, User A inputs feedback such as "This recipe was easy and delicious" and presses the "Send" button on the device. The server receives this and stores it in the database.

[0134] Step 9: Real-time model updates

[0135] The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. The feedback data is used as input. The output is an updated AI model.

[0136] Specifically, based on User A's feedback, the server inputs prompts such as "Please continue to suggest easy and delicious recipes for busy days" into the generation AI and updates the model.

[0137] (Application example 1)

[0138] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0139] Conventional recommendation systems only provide general recommendations without taking into account the user's lifestyle or health condition. This makes it difficult to provide optimal recommendations tailored to individual needs, and fails to improve user satisfaction. Furthermore, health data has rarely been utilized to provide real-time recommendations for lifestyle improvements, and these systems have not contributed sufficiently to users' health management. Furthermore, there has been a lack of a way to link these recommendations to specific actions (e.g., online purchases or reservations), resulting in low user convenience.

[0140] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0141] In this invention, the server includes: means for receiving user information and recording it in a database; means for analyzing data using generative artificial intelligence and general artificial intelligence based on the received user information; means for generating customized recommendations based on the analysis results; means for notifying the user terminal of the generated recommendations; means for receiving feedback from the user, recording it in a database, and adjusting the recommendations in real time; and means for receiving health data acquired from a smart device, using the data to evaluate the user's health status, and suggesting related products and services through electronic payment. This enables precise recommendations based on the user's individual health status and lifestyle, significantly improving user satisfaction and convenience. Furthermore, by linking the recommendations to specific actions, it becomes possible to make suggestions that are directly useful to the user's real life.

[0142] "User information" refers to basic information such as the user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[0143] "Database" refers to the storage device within the system that records and stores user information, health data, feedback information, etc.

[0144] "Generative AI" refers to AI that has the ability to generate new information and value based on specific data and patterns.

[0145] "General artificial intelligence" refers to artificial intelligence that is not specialized in any particular task and has broad knowledge and cognitive capabilities.

[0146] "Data analysis" refers to the process of analyzing collected data and extracting meaningful patterns and information from it.

[0147] "Customized recommendations" refers to suggestions that are specifically designed based on an individual user's behavioral patterns, preferences, and health status.

[0148] "Notification" refers to the process of sending information to a user terminal in real time and displaying it.

[0149] "Feedback" refers to reactions and opinions on recommendations provided by users.

[0150] "Real-time adjustment" refers to the process of immediately incorporating feedback to improve future recommendations.

[0151] "Smart devices" refers to devices such as smartwatches and fitness trackers that have internet connectivity and can collect and transmit user health data.

[0152] "Health Assessment" refers to the process of analyzing the User's physical and mental condition based on the collected health data.

[0153] "Electronic payments" refers to digital payment methods for paying for goods and services online.

[0154] "Suggesting related products and services" refers to the process of recommending specific products and services based on the user's health condition and lifestyle, and encouraging them to purchase or use them.

[0155] The system of the present invention includes the following means for providing customized recommendations based on a user's lifestyle:

[0156] First, the server receives user information and records it in a database. This user information includes basic information such as name, age, gender, and email address, as well as detailed profile information (e.g., eating habits, hobbies, work schedule, health goals, etc.). It also receives health data obtained from smart devices such as smartwatches and fitness trackers. This health data includes daily step counts, heart rate, sleep data, etc.

[0157] The server then analyzes the received user information and health data using generative artificial intelligence and general artificial intelligence. This evaluates the user's behavioral patterns, preferences, and health status. Based on the analysis results, it generates customized recommendations. Meal recommendations suggest menus based on the user's health goals (e.g., weight management, muscle building, etc.). Specifically, it generates online purchasing links for foods and ingredients related to the suggested meal menu.

[0158] The generated recommendations are sent to the user's device. For example, a push notification is sent to the user's smartphone, allowing the user to take specific action by checking the notification. In addition, when it comes to exercise recommendations, the system provides a function that allows users to easily book and pay for lessons at exercise studios and gyms.

[0159] Users can provide feedback on the recommendations they receive. This feedback is received by the server and recorded in a database. The server updates the AI ​​model in real time based on the feedback, and the feedback is reflected in the next recommendation, allowing the server to make suggestions that are more suited to the individual needs of the user.

[0160] Specific hardware and software used in this invention include a backend API (e.g., api.smarthealthapp.com) that manages user information and health data, a generation AI server (e.g., ai.smarthealthapp.com), and an online supermarket API (e.g., api.onlinesupermarket.com). Through these systems, users can easily take specific actions necessary to improve their lives.

[0161] As a concrete example, suppose User A provides the following information:

[0162] Name: User A

[0163] Age: 35

[0164] Gender: Female

[0165] Eating habits: Health-conscious, vegetarian

[0166] Hobbies: Watching movies, running

[0167] Health goals: weight management, stress reduction

[0168] When User A connects their smartwatch, the server receives and records data from the smartwatch (e.g., daily steps, heart rate, sleep data). The generation AI analyzes this data and evaluates User A's behavioral patterns and health status. For example, it can obtain information such as, "User A runs on weekends, but exercises less on days when stress is high."

[0169] Based on the results of this analysis, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can then take the suggested actions and provide feedback, further improving the accuracy of the next recommendation.

[0170] Example prompts for the generative AI:

[0171] "Create customized diet and exercise suggestions based on your current user profile and health data."

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The server receives user information and records it in a database. The received user information includes basic data such as name, age, gender, and email address, as well as detailed profile information such as eating habits, hobbies, work schedule, and health goals. The input is the individual information provided by the user, and the output is that it is stored in the database.

[0175] Step 2:

[0176] When users connect smart devices such as smartwatches and fitness trackers, the server periodically receives and records activity data from these devices, including daily steps, heart rate, sleep data, etc. The input is the real-time data sent from the smart devices, and the output is that the health data is stored in a database.

[0177] Step 3:

[0178] The server analyzes the collected user information and health data using generative artificial intelligence and general artificial intelligence. The AI ​​processes the received data and evaluates the user's behavioral patterns and health status. For example, it evaluates behavioral patterns such as "tends to eat out on weekends" and health status such as "exercises less on days with high stress." The input is user information and health data recorded in the database, and the output is the evaluation results of behavioral patterns and health status.

[0179] Step 4:

[0180] The generative AI generates customized recommendations based on the evaluation results, providing specific suggestions such as meal plans, exercise advice, and relaxation methods. The input is the evaluation results obtained in Step 3, and the output is a recommendation customized for each user.

[0181] Step 5:

[0182] The generated recommendation is pushed to the user's device. The device receives this notification and displays it to the user. For example, it may recommend a healthy vegetarian dinner recipe or a relaxing movie. The input is the recommendation generated in step 4, and the output is the notification displayed on the user's device.

[0183] Step 6:

[0184] The user provides feedback on the notified recommendation. The device acquires this feedback and sends it to the server. The input is the feedback information from the user, and the output is that the feedback is recorded in the server.

[0185] Step 7:

[0186] The server updates the AI ​​model in real time based on the received feedback. The feedback data is then analyzed again by the AI ​​and reflected in the next recommendation. This process improves the system so that it can make suggestions that are more suited to the individual preferences and needs of each user. The input is feedback information from the user, and the output is an updated AI model and the next recommendation.

[0187] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0188] The system of the present invention provides customized recommendations based on the user's lifestyle, and in particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment.

[0189] Collection and management of user information

[0190] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[0191] Emotion recognition by emotion engine

[0192] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[0193] Data analysis using AI models

[0194] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0195] Generating customized recommendations

[0196] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[0197] User interface presentation

[0198] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0199] Real-time feedback and adjustments

[0200] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[0201] Specific examples

[0202] User B newly registers with the system and provides the following information:

[0203] Name: User B

[0204] Age: 40

[0205] Gender: Male

[0206] Eating habits: Balanced diet

[0207] Hobbies: Reading, watching movies

[0208] Health goals: Stress management, improved sleep quality

[0209] When User B connects a wearable fitness tracker and the system uses emotion recognition to collect real-time emotional data, the server uses this data to learn User B's behavioral patterns. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "Reading helps him relax."

[0210] Based on the analysis results, the server suggests to User B "a relaxing breakfast menu for Monday morning" and "the best time to read." Furthermore, through the emotion engine, recommendations are generated, including "relaxation exercises that User B should do when he feels stressed." User B can review these and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation will be further improved.

[0211] In this way, by using the emotion engine, this system can provide sophisticated recommendations that take into account the user's emotional state, supporting a more efficient and fulfilling daily life.

[0212] The processing flow will be explained below.

[0213] Step 1:

[0214] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, the server receives this information and records it in a database.

[0215] Step 2:

[0216] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) Once the user enters the information and presses the submit button, the server receives this information and stores it in a database.

[0217] Step 3:

[0218] When a user connects a wearable device (e.g., fitness tracker, smart watch) to the system, the server periodically receives activity data (e.g., steps, heart rate, sleep data) from the device and records it in a database.

[0219] Step 4:

[0220] The device collects emotional data in real time from the user's facial expressions and voice using emotion recognition technology using a camera and microphone, and transmits the collected emotional data to a server.

[0221] Step 5:

[0222] The server performs data cleansing and preprocessing based on the received user information, activity data, and sentiment data, including removing duplicate data and imputing missing values.

[0223] Step 6:

[0224] The server uses generative AI and AGI algorithms to analyze the preprocessed data. Based on the analysis results, features related to the user's behavioral patterns and emotional state are extracted. For example, information such as "the user is prone to stress on Mondays" can be obtained.

[0225] Step 7:

[0226] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Meal menus are suggested based on the user's health goals and real-time emotional state. For example, a user feeling stressed will be recommended a meal that will help them relax.

[0227] Step 8:

[0228] The device receives the recommendations generated by the server via push notification and displays them to the user. The user can then confirm the notification and act on the suggestions, for example, cooking a relaxing breakfast menu.

[0229] Step 9:

[0230] The user provides feedback on the recommendation on the device, which may be about changes in emotional state or satisfaction with the recommendation. The device then forwards this feedback information to the server.

[0231] Step 10:

[0232] The server records the received feedback in a database and updates the generative AI and AGI models in real time, allowing the system to further refine its next recommendation. For example, if a user enjoyed a particular meal, it might suggest similar dishes in the future.

[0233] In this way, a system incorporating an emotion engine can provide customized recommendations that take into account the user's emotional state, helping users lead more comfortable and efficient daily lives.

[0234] Example 2

[0235] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0236] While most conventional recommendation systems make suggestions based on a user's basic information, they are unable to reflect the user's real-time emotional state, making them unable to adequately address individual needs. In particular, for stress management and achieving health goals, precise recommendations that take into account the user's emotional state are important, but existing systems have not been able to achieve this.

[0237] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information and emotion data collected in real time, means for generating customized recommendations based on the analysis results, means for notifying the user's terminal of the generated recommendations, means for receiving feedback from the user and recording it in a database and adjusting the recommendations in real time, and means for collecting emotion data from facial expressions, voice, and text messages. This makes it possible to reflect the user's emotional state in real time and provide more personalized and sophisticated recommendations.

[0238] "User Information" is data including basic information (such as name, age, gender, and email address) and detailed profile information (such as eating habits, hobbies, work schedule, and health goals) provided by a user when signing up to the system.

[0239] A "database" is a data management structure within a system that records and stores user information, emotional data, and feedback information, and uses this information to perform data analysis and generate recommendations.

[0240] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that includes algorithms and models for generating new information and recommendations based on data.

[0241] "Artificial general intelligence (AGI)" is a general-purpose artificial intelligence system that can handle a wide range of tasks, not just specific ones, and is a technology for performing advanced analysis based on various user data.

[0242] "Emotion data" refers to data that indicates the user's emotional state collected in real time from facial expressions, voice, text messages, and the like.

[0243] "Features" are information extracted and quantified in data analysis, such as a user's behavioral patterns, preferences, and emotional state.

[0244] "Recommendations" refers to suggestions and advice customized for each user based on collected data and analysis results.

[0245] "Push notification" is a communication method in which information or alerts are automatically sent from a server to a device to notify the user.

[0246] "Feedback" refers to user-provided ratings and opinions on recommendations, data that the system uses to improve future suggestions.

[0247] "Emotion engine" refers to technology that recognizes and evaluates a user's emotional state in real time from their facial expressions, voice, and text messages.

[0248] This invention relates to a system for providing customized recommendations based on a user's lifestyle. In particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. The specific form of this system is described below.

[0249] Collection and management of user information

[0250] When a user signs up for the system, the device displays an input form on the screen to collect basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the server receives this information and records it in a database. The device then displays an additional form to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), making it easier for the user to enter more information. This information is also sent to the server and stored in the database.

[0251] Emotion recognition by emotion engine

[0252] The emotion engine is built into the device and uses a camera and microphone to collect real-time emotion data from the user's facial expressions, voice, and text messages. The server receives this emotion data, evaluates the user's emotional state, and records it in a database. The emotion engine uses facial expression recognition technology and voice tone analysis technology.

[0253] Data analysis using AI models

[0254] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, preferences, and even emotional state are extracted. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0255] Generating customized recommendations

[0256] The server generates personalized recommendations for each user based on the results of AI analysis and the output of the emotion engine. Specifically, meal suggestions provide menus based on the user's health goals and real-time emotional state. Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also include reminders and task management that take emotional state into account.

[0257] Presentation in the user interface

[0258] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0259] Real-time feedback and adjustments

[0260] Users can provide feedback on recommendations on their devices, which collect and forward the feedback information to the server, which records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of future recommendations.

[0261] Specific examples

[0262] For example, User B registers with the system and provides the following information:

[0263] Name: User B

[0264] Age: 40

[0265] Gender: Male

[0266] Eating habits: Balanced diet

[0267] Hobbies: Reading, watching movies

[0268] Health goals: Stress management, improved sleep quality

[0269] When User B connects a wearable fitness tracker, the system uses emotion recognition to collect real-time emotional data. The server uses this data to learn User B's behavioral patterns. The generation AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "a relaxing breakfast menu for Monday mornings" and "the best time to read." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement them based on his emotional state. Providing feedback further improves the quality of the next recommendation. An example of this prompt might be, "Please suggest a relaxing breakfast menu."

[0270] Thus, by using the emotion engine, the system of the present invention provides sophisticated recommendations that take into account the user's emotional state, supporting an efficient and fulfilling daily life.

[0271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0272] Step 1:

[0273] The terminal displays a form for the user to enter basic information (such as name, age, gender, and email address). When the user enters this information and presses the submit button, the input data is sent from the terminal to the server. The server verifies the received user information and records it in a database. For example, it checks whether the name, age, and gender are in an existing database and registers the user as a new user.

[0274] Input: User basic information

[0275] Output: Verified user information is saved in the database

[0276] Step 2:

[0277] The device displays an additional form for entering detailed profile information (eating habits, hobbies, work schedule, health goals, etc.). After the user enters the details and presses the submit button, the input data is sent back to the server. The server receives it and stores it in a database as detailed profile information. This information is used for analysis by the generative AI and AGI.

[0278] Input: User's detailed profile information

[0279] Output: Detailed profile information is saved in the database

[0280] Step 3:

[0281] The device collects emotional data in real time using a camera and microphone. The emotion engine analyzes the user's facial expressions and voice and extracts their emotional state from text messages. The collected emotional data is sent from the device to a server. The server receives the data, evaluates the emotional state, and records it in a database.

[0282] Input: Real-time user facial expressions, voice, and text messages

[0283] Output: Real-time emotion data is stored in a database

[0284] Step 4:

[0285] The server uses the collected user information and emotional data to analyze the data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, emotional state, and preferences are extracted. For example, it may become clear that a user is more likely to feel stressed on certain days of the week, or that certain foods improve their mood.

[0286] Input: User information, real-time emotion data

[0287] Output: Features related to behavioral patterns and emotional states

[0288] Step 5:

[0289] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Specific suggestions include meal plans based on health goals and real-time emotional states, and entertainment content tailored to individual interests. The generated recommendations are then sent from the server to the device.

[0290] Input: Analysis results, emotion engine output

[0291] Output: Customized recommendations

[0292] Step 6:

[0293] The device receives the recommendations sent from the server and displays them to the user, who can then review the notifications and take specific actions, such as viewing recipes, choosing a movie, or performing a mindfulness exercise.

[0294] Input: Recommendation notification from the server

[0295] Output: The user initiates a specific action.

[0296] Step 7:

[0297] Users input feedback on recommendations on their devices. The devices then send the feedback information to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time based on that feedback. This improves the accuracy of the next recommendation.

[0298] Input: User feedback

[0299] Output: Update the AI ​​model based on the feedback

[0300] (Application example 2)

[0301] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0302] Conventional recommendation systems make recommendations based on a user's basic personal information and past behavioral history, but this lack of proposals that adequately reflect the user's real-time emotional state. As a result, recommendations cannot be tailored to the user's current mood or stress level, making it difficult to provide a more personalized service. It is also difficult to reflect user feedback in real time and readjust the system.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0304] In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information, emotion recognition means for recognizing the emotional state of the user, means for generating customized recommendations based on the analysis results and the emotion recognition results, means for notifying the generated recommendations to the user terminal, and means for receiving feedback from the user, recording it in the database, and adjusting the recommendations in real time, thereby enabling more personalized recommendations that are suited to the emotional state of the user.

[0305] The "means for receiving user information and recording it in a database" refers to a means for collecting basic information and detailed profile information of a user and storing it in a database.

[0306] "Generative artificial intelligence" is an artificial intelligence technology that can generate new data and patterns based on large amounts of data.

[0307] "General artificial intelligence" is an artificial intelligence technology with flexible intelligence that can handle a variety of tasks, not just specific ones.

[0308] "Means for analyzing data" refers to means for analyzing collected user information and extracting useful information and patterns.

[0309] The "emotion recognition means" is a means for analyzing the user's facial expressions and voice using a camera and microphone to recognize the user's emotional state in real time.

[0310] The "means for generating customized recommendations" refers to a means for generating advice and suggestions that are optimized for each user based on the analysis results and emotion recognition results.

[0311] The "means for notifying the user terminal of the generated recommendation" refers to a means for transmitting the generated recommendation to the terminal used by the user in the form of a push notification or the like.

[0312] "Means for receiving feedback, recording it in a database, and adjusting recommendations in real time" refers to means for collecting feedback from users and using that feedback to improve the accuracy of recommendations in real time.

[0313] The system of the present invention provides customized recommendations based on a user's lifestyle and combines an emotion engine to realize suggestions that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. A detailed embodiment of the system is described below.

[0314] Collection and management of user information

[0315] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[0316] Emotion recognition by emotion engine

[0317] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[0318] Data analysis using AI models

[0319] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0320] Generating customized recommendations

[0321] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[0322] User interface presentation

[0323] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0324] Real-time feedback and adjustments

[0325] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[0326] Specific examples

[0327] User B newly registers with the system and provides the following information:

[0328] Name: User B

[0329] Age: 40

[0330] Gender: Male

[0331] Eating habits: Balanced diet

[0332] Hobbies: Reading, watching movies

[0333] Health goals: Stress management, improved sleep quality

[0334] When User B connects a wearable fitness tracker and the system uses the emotion recognition function to collect real-time emotional data, the server learns User B's behavioral patterns based on this data. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "breakfast menus that have a relaxing effect on Monday mornings" and "optimal times for reading." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation can be further improved.

[0335] Example prompts to input to a generative AI model:

[0336] User: 40-year-old male. Hobbies include reading and watching movies. His goals are stress management and improving sleep quality. He tends to feel stressed on Monday mornings. Please suggest a breakfast menu that will help him relax.

[0337] In this way, the system can provide more personalized recommendations based on the user's emotional state and lifestyle.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] When a user signs up for the system, the terminal displays a form for inputting basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the entered information is sent to the server. The server receives it, verifies it, and records it in a database. The input here is the user's basic information, and the output is the verified user information stored in the database.

[0341] Step 2:

[0342] The device then displays the form again for entering detailed profile information (e.g., eating habits, hobbies, health goals, etc.). The user enters additional information and presses the submit button, which again sends the details to the server. The server receives the submitted details and stores them in a database. The input here is the detailed profile information, and the output is the details stored in the database.

[0343] Step 3:

[0344] Users collect emotional data using wearable devices or smartphones. This involves using a camera and microphone to recognize emotional states by analyzing facial expressions, voice, and text messages. The device processes this data in real time using an emotion engine and sends the emotional data to a server. The input is the collected emotional data, and the output is the emotional state data sent to the server.

[0345] Step 4:

[0346] The server uses generative AI and general-purpose AI algorithms to analyze the collected user information and emotional data. During this process, it extracts features based on the user's behavioral patterns, preferences, and emotional state. The input is the user information and emotional data stored in the database, and the output is the analysis of the user's behavioral patterns and emotional state.

[0347] Step 5:

[0348] The server generates customized recommendations based on the analysis results and emotion recognition data. For example, it suggests meal menus based on the user's health goals and real-time emotional state, or entertainment content based on their hobbies. The input is the analysis results and emotion data, and the output is customized recommendations.

[0349] Step 6:

[0350] The generated recommendations are sent from the server to the user's device via push notification. The device receives the notification and displays the recommendations to the user. The user checks the notification and takes specific actions (e.g., looking at recipes, choosing a movie, performing a mindfulness exercise, etc.). The input here is the generated recommendations, and the output is the display to the user.

[0351] Step 7:

[0352] The user provides feedback on the provided recommendations. The device collects the feedback information and sends it back to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time, thereby improving the accuracy of the next recommendation. The input is the feedback information from the user, and the output is the model and database updated in real time.

[0353] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0354] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0355] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0356] [Second embodiment]

[0357] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0358] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0359] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0360] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0361] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0362] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0363] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0364] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0365] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0366] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0367] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0368] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0369] The system of the present invention provides customized recommendations based on a user's lifestyle. The system operates through a series of steps: collecting user information, analyzing the data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), generating recommendations, notifying users, and collecting and adjusting feedback in real time.

[0370] Collection and management of user information

[0371] When a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals). This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[0372] Data analysis using AI models

[0373] The server analyzes the received user information and activity data using generative AI and AGI algorithms, learning the user's behavioral patterns and preferences and extracting individual characteristics. For example, this can reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[0374] Generating customized recommendations

[0375] The server generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[0376] User interface presentation

[0377] The recommendation generated by the server is pushed to the user's device. The device receives the notification and displays it to the user. The user can then check the notification and take specific action. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[0378] Real-time feedback and adjustments

[0379] Users can provide feedback on recommendations on their devices. This feedback is received by the server and recorded in a database. The server then updates the AI ​​model in real time based on the feedback and reflects it in the next recommendation. This ensures that the system always provides the latest and most optimal suggestions.

[0380] Specific examples

[0381] For example, User A registers with the system and provides the following information:

[0382] Name: User A

[0383] Age: 35

[0384] Gender: Female

[0385] Eating habits: Health-conscious, vegetarian

[0386] Hobbies: Watching movies, running

[0387] Health goals: weight management, stress reduction

[0388] When User A connects a wearable fitness tracker, the server receives and records data from the wearable device (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[0389] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[0390] In this way, the system supports efficient and fulfilling daily life by providing sophisticated recommendations based on the user's individual preferences and lifestyle.

[0391] The processing flow will be explained below.

[0392] Step 1:

[0393] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, this information is transferred to the server, which verifies the received information and records it in a database.

[0394] Step 2:

[0395] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the data and presses the submit button. The server receives these details and stores them in a database.

[0396] Step 3:

[0397] When a user connects a wearable device (such as a fitness tracker or smartwatch) to the system, the server periodically receives activity data (such as steps, heart rate, and sleep data) from the device, and the received data is recorded in a database.

[0398] Step 4:

[0399] The server retrieves user information and activity data from the database and performs data cleansing and pre-processing, including removing duplicate data and imputing missing values.

[0400] Step 5:

[0401] The server analyzes the preprocessed data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI) algorithms. Specifically, it learns each user's behavioral patterns and preferences and extracts features. This analysis allows it to understand the user's specific behavioral patterns (e.g., preference for certain foods on certain days of the week) and health status (e.g., high stress on certain days).

[0402] Step 6:

[0403] Based on the AI ​​analysis results, the server generates personalized recommendations for each user, including meal plans that match the user's health goals, entertainment suggestions based on the user's hobbies, and reminders for optimal schedule management.

[0404] Step 7:

[0405] The device receives the recommendations generated by the server via push notification and displays them to the user, who can then check the notification and take specific actions based on the recommendations.

[0406] Step 8:

[0407] The user provides feedback on the recommendation (e.g., "very satisfied," "satisfied," "unsatisfied," etc.) through the device. The device receives this feedback information and forwards it to the server.

[0408] Step 9:

[0409] The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process ensures that the system always provides the latest and most optimal suggestions.

[0410] Example 1

[0411] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0412] Conventional recommendation systems have difficulty providing customized recommendations based on a user's individual preferences and lifestyle. Furthermore, they lack the functionality to reflect user feedback in real time and improve the content of future recommendations. This results in low user satisfaction and makes it difficult to encourage continued use.

[0413] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0414] In this invention, the server includes means for receiving user information and recording it in a database, means for displaying a form for inputting detailed profile information and recording the detailed information in the database, means for receiving and recording activity data from the wearable device, means for integrating the received user information and activity data and analyzing the data using generative artificial intelligence and general artificial intelligence, means for generating customized recommendations based on the analysis results, means for notifying the user terminal of the generated recommendations, and means for receiving feedback from the user and recording it in the database, updating the generative artificial intelligence and general artificial intelligence models in real time to reflect the feedback in the next recommendation. This makes it possible to provide sophisticated recommendations based on the individual preferences and lifestyle of the user and reflect user feedback in real time.

[0415] "User Information" refers to basic information such as a user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[0416] "Database" refers to systems and software used to record and store information, such as user information and activity data.

[0417] "Form" refers to an interface that provides a screen layout and input fields for a user to enter detailed profile information.

[0418] "Wearable devices" refers to various electronic devices that are worn on the body, such as fitness trackers and smartwatches.

[0419] "Activity data" refers to information about a user's activities, such as steps, heart rate, and sleep data obtained from a wearable device.

[0420] "Generative artificial intelligence (generative AI)" refers to artificial intelligence that has the ability to generate new information based on large amounts of data.

[0421] "Artificial general intelligence (AGI)" refers to advanced artificial intelligence that can handle a wide range of tasks and functions, rather than specific tasks.

[0422] "Recommendations" refers to suggested actions, products, services, information, etc., based on a user's specific circumstances or preferences.

[0423] "Push notification" refers to an automatic message notification sent from a server to a user device.

[0424] "Feedback" refers to the rating and comment information provided by a user in response to a recommendation they receive.

[0425] "Real-time" refers to processing and information being reflected immediately without delay.

[0426] "Update" refers to correcting or supplementing existing data or models with new information.

[0427] The system of the present invention provides customized recommendations based on a user's lifestyle. The system performs a series of data collection, analysis, recommendation generation, notification, feedback collection, and real-time adjustment through interactions between a server, a terminal, and a user.

[0428] First, when a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. Next, the device displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), and the user is prompted to enter the details. This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[0429] The server analyzes the received user information and activity data using generative artificial intelligence (AI) and artificial general intelligence (AGI) algorithms. This analysis learns the user's behavioral patterns and preferences and extracts individual characteristics. For example, it may reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[0430] The server then generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[0431] The generated recommendation is pushed from the server to the user's device. The device receives the notification and displays the notification content to the user. The user can check the notification and take specific actions. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[0432] Users provide feedback on recommendations via their devices. This feedback is received by the server and recorded in a database. The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. This makes it possible to always provide users with the latest and most optimal suggestions.

[0433] As a concrete example, suppose User A newly registers with the system and provides the following information:

[0434] Name: User A

[0435] Age: 35

[0436] Gender: Female

[0437] Eating habits: Health-conscious, vegetarian

[0438] Hobbies: Watching movies, running

[0439] Health goals: weight management, stress reduction

[0440] When User A connects a fitness tracker, the server receives and records data from the fitness tracker (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[0441] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[0442] An example of a prompt for a generative AI model is:

[0443] "Based on the new user's information, we suggest healthy vegetarian recipes and relaxing movies."

[0444] Through the above process, the system can provide precise recommendations based on the user's individual preferences and lifestyle, supporting an efficient and fulfilling daily life.

[0445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0446] Step 1: User registration and receipt of basic information

[0447] When a user signs up to the system, the server receives basic information (such as name, age, gender, and email address) that is provided as input in a form. The server records this information in a database to create a basic profile of the user.

[0448] Specifically, the user enters basic information into the form and clicks the "Submit" button. The entered basic information is sent to the server and saved in the database.

[0449] Step 2: Collect detailed profile information

[0450] The device displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the details, which are then sent to the server and recorded in a database.

[0451] Specifically, the user enters information such as eating habits and hobbies into a form on the device and clicks the "Submit" button. The server receives this information and stores it in a database.

[0452] Step 3: Connect your wearable device

[0453] Users connect their fitness trackers, smartwatches, etc. to the system, and the server periodically receives activity data (such as steps, heart rate, and sleep data) from the connected devices and records it in a database.

[0454] Specifically, the user clicks the "Link Device" button on the app's settings screen and follows the instructions to link the device. The server receives activity data from the device every hour and stores it in a database.

[0455] Step 4: Data analysis with generative AI

[0456] The server integrates the received user information and activity data and analyzes the data using a generative AI model. Basic information, detailed profile information, and activity data are provided as input data to the generative AI. The generative AI learns the user's behavioral patterns and preferences and extracts features.

[0457] Specifically, the server inputs data into a generative AI model and generates results using prompts such as "Tell me about the user's weekend eating patterns." The output is the user's behavioral patterns.

[0458] Step 5: Learning behavioral patterns using general artificial intelligence

[0459] The server inputs the analysis results of the generative AI into the AGI algorithm to learn detailed behavioral patterns and improve the model. The results of the generative AI are given as input data to the AGI for further advanced analysis.

[0460] Specifically, the server passes the output of the generation AI to the AGI, and inputs a prompt such as "Please learn more detailed behavioral patterns." The output is a more detailed behavioral pattern.

[0461] Step 6: Generate customized recommendations

[0462] The server generates customized recommendations based on the analysis results of the generative AI and AGI. The analysis results are used as input data. The output is suggestions tailored to each user.

[0463] Specifically, the server creates recommendations based on the results of generative AI and AGI. The recommendations are created using prompts such as "Please suggest healthy vegetarian recipes for user A on busy weekdays."

[0464] Step 7: Recommendation Notification

[0465] The server pushes the generated recommendations to the user device. The generated recommendations are used as input. The output is a notification message sent to the user device.

[0466] Specifically, the server will push a message to User A such as, "Here are some vegetarian recipes to recommend for busy days."

[0467] Step 8: Gather user feedback

[0468] The user provides feedback on the recommendation at the terminal. The feedback the user returns is used as input. The server receives this feedback and records it in a database.

[0469] Specifically, User A inputs feedback such as "This recipe was easy and delicious" and presses the "Send" button on the device. The server receives this and stores it in the database.

[0470] Step 9: Real-time model updates

[0471] The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. The feedback data is used as input. The output is an updated AI model.

[0472] Specifically, based on User A's feedback, the server inputs prompts such as "Please continue to suggest easy and delicious recipes for busy days" into the generation AI and updates the model.

[0473] (Application example 1)

[0474] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0475] Conventional recommendation systems only provide general recommendations without taking into account the user's lifestyle or health condition. This makes it difficult to provide optimal recommendations tailored to individual needs, and fails to improve user satisfaction. Furthermore, health data has rarely been utilized to provide real-time recommendations for lifestyle improvements, and these systems have not contributed sufficiently to users' health management. Furthermore, there has been a lack of a way to link these recommendations to specific actions (e.g., online purchases or reservations), resulting in low user convenience.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0477] In this invention, the server includes: means for receiving user information and recording it in a database; means for analyzing data using generative artificial intelligence and general artificial intelligence based on the received user information; means for generating customized recommendations based on the analysis results; means for notifying the user terminal of the generated recommendations; means for receiving feedback from the user, recording it in a database, and adjusting the recommendations in real time; and means for receiving health data acquired from a smart device, using the data to evaluate the user's health status, and suggesting related products and services through electronic payment. This enables precise recommendations based on the user's individual health status and lifestyle, significantly improving user satisfaction and convenience. Furthermore, by linking the recommendations to specific actions, it becomes possible to make suggestions that are directly useful to the user's real life.

[0478] "User information" refers to basic information such as the user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[0479] "Database" refers to the storage device within the system that records and stores user information, health data, feedback information, etc.

[0480] "Generative AI" refers to AI that has the ability to generate new information and value based on specific data and patterns.

[0481] "General artificial intelligence" refers to artificial intelligence that is not specialized in any particular task and has broad knowledge and cognitive capabilities.

[0482] "Data analysis" refers to the process of analyzing collected data and extracting meaningful patterns and information from it.

[0483] "Customized recommendations" refers to suggestions that are specifically designed based on an individual user's behavioral patterns, preferences, and health status.

[0484] "Notification" refers to the process of sending information to a user terminal in real time and displaying it.

[0485] "Feedback" refers to reactions and opinions on recommendations provided by users.

[0486] "Real-time adjustment" refers to the process of immediately incorporating feedback to improve future recommendations.

[0487] "Smart devices" refers to devices such as smartwatches and fitness trackers that have internet connectivity and can collect and transmit user health data.

[0488] "Health Assessment" refers to the process of analyzing the User's physical and mental condition based on the collected health data.

[0489] "Electronic payments" refers to digital payment methods for paying for goods and services online.

[0490] "Suggesting related products and services" refers to the process of recommending specific products and services based on the user's health condition and lifestyle, and encouraging them to purchase or use them.

[0491] The system of the present invention includes the following means for providing customized recommendations based on a user's lifestyle:

[0492] First, the server receives user information and records it in a database. This user information includes basic information such as name, age, gender, and email address, as well as detailed profile information (e.g., eating habits, hobbies, work schedule, health goals, etc.). It also receives health data obtained from smart devices such as smartwatches and fitness trackers. This health data includes daily step counts, heart rate, sleep data, etc.

[0493] The server then analyzes the received user information and health data using generative artificial intelligence and general artificial intelligence. This evaluates the user's behavioral patterns, preferences, and health status. Based on the analysis results, it generates customized recommendations. Meal recommendations suggest menus based on the user's health goals (e.g., weight management, muscle building, etc.). Specifically, it generates online purchasing links for foods and ingredients related to the suggested meal menu.

[0494] The generated recommendations are sent to the user's device. For example, a push notification is sent to the user's smartphone, allowing the user to take specific action by checking the notification. In addition, when it comes to exercise recommendations, the system provides a function that allows users to easily book and pay for lessons at exercise studios and gyms.

[0495] Users can provide feedback on the recommendations they receive. This feedback is received by the server and recorded in a database. The server updates the AI ​​model in real time based on the feedback, and the feedback is reflected in the next recommendation, allowing the server to make suggestions that are more suited to the individual needs of the user.

[0496] Specific hardware and software used in this invention include a backend API (e.g., api.smarthealthapp.com) that manages user information and health data, a generation AI server (e.g., ai.smarthealthapp.com), and an online supermarket API (e.g., api.onlinesupermarket.com). Through these systems, users can easily take specific actions necessary to improve their lives.

[0497] As a concrete example, suppose User A provides the following information:

[0498] Name: User A

[0499] Age: 35

[0500] Gender: Female

[0501] Eating habits: Health-conscious, vegetarian

[0502] Hobbies: Watching movies, running

[0503] Health goals: weight management, stress reduction

[0504] When User A connects their smartwatch, the server receives and records data from the smartwatch (e.g., daily steps, heart rate, sleep data). The generation AI analyzes this data and evaluates User A's behavioral patterns and health status. For example, it can obtain information such as, "User A runs on weekends, but exercises less on days when stress is high."

[0505] Based on the results of this analysis, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can then take the suggested actions and provide feedback, further improving the accuracy of the next recommendation.

[0506] Example prompts for the generative AI:

[0507] "Create customized diet and exercise suggestions based on your current user profile and health data."

[0508] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0509] Step 1:

[0510] The server receives user information and records it in a database. The received user information includes basic data such as name, age, gender, and email address, as well as detailed profile information such as eating habits, hobbies, work schedule, and health goals. The input is the individual information provided by the user, and the output is that it is stored in the database.

[0511] Step 2:

[0512] When users connect smart devices such as smartwatches and fitness trackers, the server periodically receives and records activity data from these devices, including daily steps, heart rate, sleep data, etc. The input is the real-time data sent from the smart devices, and the output is that the health data is stored in a database.

[0513] Step 3:

[0514] The server analyzes the collected user information and health data using generative artificial intelligence and general artificial intelligence. The AI ​​processes the received data and evaluates the user's behavioral patterns and health status. For example, it evaluates behavioral patterns such as "tends to eat out on weekends" and health status such as "exercises less on days with high stress." The input is user information and health data recorded in the database, and the output is the evaluation results of behavioral patterns and health status.

[0515] Step 4:

[0516] The generative AI generates customized recommendations based on the evaluation results, providing specific suggestions such as meal plans, exercise advice, and relaxation methods. The input is the evaluation results obtained in Step 3, and the output is a recommendation customized for each user.

[0517] Step 5:

[0518] The generated recommendation is pushed to the user's device. The device receives this notification and displays it to the user. For example, it may recommend a healthy vegetarian dinner recipe or a relaxing movie. The input is the recommendation generated in step 4, and the output is the notification displayed on the user's device.

[0519] Step 6:

[0520] The user provides feedback on the notified recommendation. The device acquires this feedback and sends it to the server. The input is the feedback information from the user, and the output is that the feedback is recorded in the server.

[0521] Step 7:

[0522] The server updates the AI ​​model in real time based on the received feedback. The feedback data is then analyzed again by the AI ​​and reflected in the next recommendation. This process improves the system so that it can make suggestions that are more suited to the individual preferences and needs of each user. The input is feedback information from the user, and the output is an updated AI model and the next recommendation.

[0523] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0524] The system of the present invention provides customized recommendations based on the user's lifestyle, and in particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment.

[0525] Collection and management of user information

[0526] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[0527] Emotion recognition by emotion engine

[0528] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[0529] Data analysis using AI models

[0530] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0531] Generating customized recommendations

[0532] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[0533] User interface presentation

[0534] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0535] Real-time feedback and adjustments

[0536] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[0537] Specific examples

[0538] User B newly registers with the system and provides the following information:

[0539] Name: User B

[0540] Age: 40

[0541] Gender: Male

[0542] Eating habits: Balanced diet

[0543] Hobbies: Reading, watching movies

[0544] Health goals: Stress management, improved sleep quality

[0545] When User B connects a wearable fitness tracker and the system uses emotion recognition to collect real-time emotional data, the server uses this data to learn User B's behavioral patterns. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "Reading helps him relax."

[0546] Based on the analysis results, the server suggests to User B "a relaxing breakfast menu for Monday morning" and "the best time to read." Furthermore, through the emotion engine, recommendations are generated, including "relaxation exercises that User B should do when he feels stressed." User B can review these and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation will be further improved.

[0547] In this way, by using the emotion engine, this system can provide sophisticated recommendations that take into account the user's emotional state, supporting a more efficient and fulfilling daily life.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, the server receives this information and records it in a database.

[0551] Step 2:

[0552] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) Once the user enters the information and presses the submit button, the server receives this information and stores it in a database.

[0553] Step 3:

[0554] When a user connects a wearable device (e.g., fitness tracker, smart watch) to the system, the server periodically receives activity data (e.g., steps, heart rate, sleep data) from the device and records it in a database.

[0555] Step 4:

[0556] The device collects emotional data in real time from the user's facial expressions and voice using emotion recognition technology using a camera and microphone, and transmits the collected emotional data to a server.

[0557] Step 5:

[0558] The server performs data cleansing and preprocessing based on the received user information, activity data, and sentiment data, including removing duplicate data and imputing missing values.

[0559] Step 6:

[0560] The server uses generative AI and AGI algorithms to analyze the preprocessed data. Based on the analysis results, features related to the user's behavioral patterns and emotional state are extracted. For example, information such as "the user is prone to stress on Mondays" can be obtained.

[0561] Step 7:

[0562] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Meal menus are suggested based on the user's health goals and real-time emotional state. For example, a user feeling stressed will be recommended a meal that will help them relax.

[0563] Step 8:

[0564] The device receives the recommendations generated by the server via push notification and displays them to the user. The user can then confirm the notification and act on the suggestions, for example, cooking a relaxing breakfast menu.

[0565] Step 9:

[0566] The user provides feedback on the recommendation on the device, which may be about changes in emotional state or satisfaction with the recommendation. The device then forwards this feedback information to the server.

[0567] Step 10:

[0568] The server records the received feedback in a database and updates the generative AI and AGI models in real time, allowing the system to further refine its next recommendation. For example, if a user enjoyed a particular meal, it might suggest similar dishes in the future.

[0569] In this way, a system incorporating an emotion engine can provide customized recommendations that take into account the user's emotional state, helping users lead more comfortable and efficient daily lives.

[0570] Example 2

[0571] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0572] While most conventional recommendation systems make suggestions based on a user's basic information, they are unable to reflect the user's real-time emotional state, making them unable to adequately address individual needs. In particular, for stress management and achieving health goals, precise recommendations that take into account the user's emotional state are important, but existing systems have not been able to achieve this.

[0573] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information and emotion data collected in real time, means for generating customized recommendations based on the analysis results, means for notifying the user's terminal of the generated recommendations, means for receiving feedback from the user and recording it in a database and adjusting the recommendations in real time, and means for collecting emotion data from facial expressions, voice, and text messages. This makes it possible to reflect the user's emotional state in real time and provide more personalized and sophisticated recommendations.

[0574] "User Information" is data including basic information (such as name, age, gender, and email address) and detailed profile information (such as eating habits, hobbies, work schedule, and health goals) provided by a user when signing up to the system.

[0575] A "database" is a data management structure within a system that records and stores user information, emotional data, and feedback information, and uses this information to perform data analysis and generate recommendations.

[0576] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that includes algorithms and models for generating new information and recommendations based on data.

[0577] "Artificial general intelligence (AGI)" is a general-purpose artificial intelligence system that can handle a wide range of tasks, not just specific ones, and is a technology for performing advanced analysis based on various user data.

[0578] "Emotion data" refers to data that indicates the user's emotional state collected in real time from facial expressions, voice, text messages, and the like.

[0579] "Features" are information extracted and quantified in data analysis, such as a user's behavioral patterns, preferences, and emotional state.

[0580] "Recommendations" refers to suggestions and advice customized for each user based on collected data and analysis results.

[0581] "Push notification" is a communication method in which information or alerts are automatically sent from a server to a device to notify the user.

[0582] "Feedback" refers to user-provided ratings and opinions on recommendations, data that the system uses to improve future suggestions.

[0583] "Emotion engine" refers to technology that recognizes and evaluates a user's emotional state in real time from their facial expressions, voice, and text messages.

[0584] This invention relates to a system for providing customized recommendations based on a user's lifestyle. In particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. The specific form of this system is described below.

[0585] Collection and management of user information

[0586] When a user signs up for the system, the device displays an input form on the screen to collect basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the server receives this information and records it in a database. The device then displays an additional form to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), making it easier for the user to enter more information. This information is also sent to the server and stored in the database.

[0587] Emotion recognition by emotion engine

[0588] The emotion engine is built into the device and uses a camera and microphone to collect real-time emotion data from the user's facial expressions, voice, and text messages. The server receives this emotion data, evaluates the user's emotional state, and records it in a database. The emotion engine uses facial expression recognition technology and voice tone analysis technology.

[0589] Data analysis using AI models

[0590] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, preferences, and even emotional state are extracted. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0591] Generating customized recommendations

[0592] The server generates personalized recommendations for each user based on the results of AI analysis and the output of the emotion engine. Specifically, meal suggestions provide menus based on the user's health goals and real-time emotional state. Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also include reminders and task management that take emotional state into account.

[0593] Presentation in the user interface

[0594] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0595] Real-time feedback and adjustments

[0596] Users can provide feedback on recommendations on their devices, which collect and forward the feedback information to the server, which records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of future recommendations.

[0597] Specific examples

[0598] For example, User B registers with the system and provides the following information:

[0599] Name: User B

[0600] Age: 40

[0601] Gender: Male

[0602] Eating habits: Balanced diet

[0603] Hobbies: Reading, watching movies

[0604] Health goals: Stress management, improved sleep quality

[0605] When User B connects a wearable fitness tracker, the system uses emotion recognition to collect real-time emotional data. The server uses this data to learn User B's behavioral patterns. The generation AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "a relaxing breakfast menu for Monday mornings" and "the best time to read." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement them based on his emotional state. Providing feedback further improves the quality of the next recommendation. An example of this prompt might be, "Please suggest a relaxing breakfast menu."

[0606] Thus, by using the emotion engine, the system of the present invention provides sophisticated recommendations that take into account the user's emotional state, supporting an efficient and fulfilling daily life.

[0607] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0608] Step 1:

[0609] The terminal displays a form for the user to enter basic information (such as name, age, gender, and email address). When the user enters this information and presses the submit button, the input data is sent from the terminal to the server. The server verifies the received user information and records it in a database. For example, it checks whether the name, age, and gender are in an existing database and registers the user as a new user.

[0610] Input: User basic information

[0611] Output: Verified user information is saved in the database

[0612] Step 2:

[0613] The device displays an additional form for entering detailed profile information (eating habits, hobbies, work schedule, health goals, etc.). After the user enters the details and presses the submit button, the input data is sent back to the server. The server receives it and stores it in a database as detailed profile information. This information is used for analysis by the generative AI and AGI.

[0614] Input: User's detailed profile information

[0615] Output: Detailed profile information is saved in the database

[0616] Step 3:

[0617] The device collects emotional data in real time using a camera and microphone. The emotion engine analyzes the user's facial expressions and voice and extracts their emotional state from text messages. The collected emotional data is sent from the device to a server. The server receives the data, evaluates the emotional state, and records it in a database.

[0618] Input: Real-time user facial expressions, voice, and text messages

[0619] Output: Real-time emotion data is stored in a database

[0620] Step 4:

[0621] The server uses the collected user information and emotional data to analyze the data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, emotional state, and preferences are extracted. For example, it may become clear that a user is more likely to feel stressed on certain days of the week, or that certain foods improve their mood.

[0622] Input: User information, real-time emotion data

[0623] Output: Features related to behavioral patterns and emotional states

[0624] Step 5:

[0625] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Specific suggestions include meal plans based on health goals and real-time emotional states, and entertainment content tailored to individual interests. The generated recommendations are then sent from the server to the device.

[0626] Input: Analysis results, emotion engine output

[0627] Output: Customized recommendations

[0628] Step 6:

[0629] The device receives the recommendations sent from the server and displays them to the user, who can then review the notifications and take specific actions, such as viewing recipes, choosing a movie, or performing a mindfulness exercise.

[0630] Input: Recommendation notification from the server

[0631] Output: The user initiates a specific action.

[0632] Step 7:

[0633] Users input feedback on recommendations on their devices. The devices then send the feedback information to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time based on that feedback. This improves the accuracy of the next recommendation.

[0634] Input: User feedback

[0635] Output: Update the AI ​​model based on the feedback

[0636] (Application example 2)

[0637] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0638] Conventional recommendation systems make recommendations based on a user's basic personal information and past behavioral history, but this lack of proposals that adequately reflect the user's real-time emotional state. As a result, recommendations cannot be tailored to the user's current mood or stress level, making it difficult to provide a more personalized service. It is also difficult to reflect user feedback in real time and readjust the system.

[0639] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0640] In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information, emotion recognition means for recognizing the emotional state of the user, means for generating customized recommendations based on the analysis results and the emotion recognition results, means for notifying the generated recommendations to the user terminal, and means for receiving feedback from the user, recording it in the database, and adjusting the recommendations in real time, thereby enabling more personalized recommendations that are suited to the emotional state of the user.

[0641] The "means for receiving user information and recording it in a database" refers to a means for collecting basic information and detailed profile information of a user and storing it in a database.

[0642] "Generative artificial intelligence" is an artificial intelligence technology that can generate new data and patterns based on large amounts of data.

[0643] "General artificial intelligence" is an artificial intelligence technology with flexible intelligence that can handle a variety of tasks, not just specific ones.

[0644] "Means for analyzing data" refers to means for analyzing collected user information and extracting useful information and patterns.

[0645] The "emotion recognition means" is a means for analyzing the user's facial expressions and voice using a camera and microphone to recognize the user's emotional state in real time.

[0646] The "means for generating customized recommendations" refers to a means for generating advice and suggestions that are optimized for each user based on the analysis results and emotion recognition results.

[0647] The "means for notifying the user terminal of the generated recommendation" refers to a means for transmitting the generated recommendation to the terminal used by the user in the form of a push notification or the like.

[0648] "Means for receiving feedback, recording it in a database, and adjusting recommendations in real time" refers to means for collecting feedback from users and using that feedback to improve the accuracy of recommendations in real time.

[0649] The system of the present invention provides customized recommendations based on a user's lifestyle and combines an emotion engine to realize suggestions that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. A detailed embodiment of the system is described below.

[0650] Collection and management of user information

[0651] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[0652] Emotion recognition by emotion engine

[0653] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[0654] Data analysis using AI models

[0655] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0656] Generating customized recommendations

[0657] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[0658] User interface presentation

[0659] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0660] Real-time feedback and adjustments

[0661] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[0662] Specific examples

[0663] User B newly registers with the system and provides the following information:

[0664] Name: User B

[0665] Age: 40

[0666] Gender: Male

[0667] Eating habits: Balanced diet

[0668] Hobbies: Reading, watching movies

[0669] Health goals: Stress management, improved sleep quality

[0670] When User B connects a wearable fitness tracker and the system uses the emotion recognition function to collect real-time emotional data, the server learns User B's behavioral patterns based on this data. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "breakfast menus that have a relaxing effect on Monday mornings" and "optimal times for reading." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation can be further improved.

[0671] Example prompts to input to a generative AI model:

[0672] User: 40-year-old male. Hobbies include reading and watching movies. His goals are stress management and improving sleep quality. He tends to feel stressed on Monday mornings. Please suggest a breakfast menu that will help him relax.

[0673] In this way, the system can provide more personalized recommendations based on the user's emotional state and lifestyle.

[0674] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0675] Step 1:

[0676] When a user signs up for the system, the terminal displays a form for inputting basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the entered information is sent to the server. The server receives it, verifies it, and records it in a database. The input here is the user's basic information, and the output is the verified user information stored in the database.

[0677] Step 2:

[0678] The device then displays the form again for entering detailed profile information (e.g., eating habits, hobbies, health goals, etc.). The user enters additional information and presses the submit button, which again sends the details to the server. The server receives the submitted details and stores them in a database. The input here is the detailed profile information, and the output is the details stored in the database.

[0679] Step 3:

[0680] Users collect emotional data using wearable devices or smartphones. This involves using a camera and microphone to recognize emotional states by analyzing facial expressions, voice, and text messages. The device processes this data in real time using an emotion engine and sends the emotional data to a server. The input is the collected emotional data, and the output is the emotional state data sent to the server.

[0681] Step 4:

[0682] The server uses generative AI and general-purpose AI algorithms to analyze the collected user information and emotional data. During this process, it extracts features based on the user's behavioral patterns, preferences, and emotional state. The input is the user information and emotional data stored in the database, and the output is the analysis of the user's behavioral patterns and emotional state.

[0683] Step 5:

[0684] The server generates customized recommendations based on the analysis results and emotion recognition data. For example, it suggests meal menus based on the user's health goals and real-time emotional state, or entertainment content based on their hobbies. The input is the analysis results and emotion data, and the output is customized recommendations.

[0685] Step 6:

[0686] The generated recommendations are sent from the server to the user's device via push notification. The device receives the notification and displays the recommendations to the user. The user checks the notification and takes specific actions (e.g., looking at recipes, choosing a movie, performing a mindfulness exercise, etc.). The input here is the generated recommendations, and the output is the display to the user.

[0687] Step 7:

[0688] The user provides feedback on the provided recommendations. The device collects the feedback information and sends it back to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time, thereby improving the accuracy of the next recommendation. The input is the feedback information from the user, and the output is the model and database updated in real time.

[0689] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0690] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0691] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0695] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0696] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0697] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0698] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0699] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0700] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0701] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0702] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0703] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0704] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0705] The system of the present invention provides customized recommendations based on a user's lifestyle. The system operates through a series of steps: collecting user information, analyzing the data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), generating recommendations, notifying users, and collecting and adjusting feedback in real time.

[0706] Collection and management of user information

[0707] When a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals). This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[0708] Data analysis using AI models

[0709] The server analyzes the received user information and activity data using generative AI and AGI algorithms, learning the user's behavioral patterns and preferences and extracting individual characteristics. For example, this can reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[0710] Generating customized recommendations

[0711] The server generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[0712] User interface presentation

[0713] The recommendation generated by the server is pushed to the user's device. The device receives the notification and displays it to the user. The user can then check the notification and take specific action. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[0714] Real-time feedback and adjustments

[0715] Users can provide feedback on recommendations on their devices. This feedback is received by the server and recorded in a database. The server then updates the AI ​​model in real time based on the feedback and reflects it in the next recommendation. This ensures that the system always provides the latest and most optimal suggestions.

[0716] Specific examples

[0717] For example, User A registers with the system and provides the following information:

[0718] Name: User A

[0719] Age: 35

[0720] Gender: Female

[0721] Eating habits: Health-conscious, vegetarian

[0722] Hobbies: Watching movies, running

[0723] Health goals: weight management, stress reduction

[0724] When User A connects a wearable fitness tracker, the server receives and records data from the wearable device (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[0725] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[0726] In this way, the system supports efficient and fulfilling daily life by providing sophisticated recommendations based on the user's individual preferences and lifestyle.

[0727] The processing flow will be explained below.

[0728] Step 1:

[0729] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, this information is transferred to the server, which verifies the received information and records it in a database.

[0730] Step 2:

[0731] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the data and presses the submit button. The server receives these details and stores them in a database.

[0732] Step 3:

[0733] When a user connects a wearable device (such as a fitness tracker or smartwatch) to the system, the server periodically receives activity data (such as steps, heart rate, and sleep data) from the device, and the received data is recorded in a database.

[0734] Step 4:

[0735] The server retrieves user information and activity data from the database and performs data cleansing and pre-processing, including removing duplicate data and imputing missing values.

[0736] Step 5:

[0737] The server analyzes the preprocessed data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI) algorithms. Specifically, it learns each user's behavioral patterns and preferences and extracts features. This analysis allows it to understand the user's specific behavioral patterns (e.g., preference for certain foods on certain days of the week) and health status (e.g., high stress on certain days).

[0738] Step 6:

[0739] Based on the AI ​​analysis results, the server generates personalized recommendations for each user, including meal plans that match the user's health goals, entertainment suggestions based on the user's hobbies, and reminders for optimal schedule management.

[0740] Step 7:

[0741] The device receives the recommendations generated by the server via push notification and displays them to the user, who can then check the notification and take specific actions based on the recommendations.

[0742] Step 8:

[0743] The user provides feedback on the recommendation (e.g., "very satisfied," "satisfied," "unsatisfied," etc.) through the device. The device receives this feedback information and forwards it to the server.

[0744] Step 9:

[0745] The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process ensures that the system always provides the latest and most optimal suggestions.

[0746] Example 1

[0747] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0748] Conventional recommendation systems have difficulty providing customized recommendations based on a user's individual preferences and lifestyle. Furthermore, they lack the functionality to reflect user feedback in real time and improve the content of future recommendations. This results in low user satisfaction and makes it difficult to encourage continued use.

[0749] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0750] In this invention, the server includes means for receiving user information and recording it in a database, means for displaying a form for inputting detailed profile information and recording the detailed information in the database, means for receiving and recording activity data from the wearable device, means for integrating the received user information and activity data and analyzing the data using generative artificial intelligence and general artificial intelligence, means for generating customized recommendations based on the analysis results, means for notifying the user terminal of the generated recommendations, and means for receiving feedback from the user and recording it in the database, updating the generative artificial intelligence and general artificial intelligence models in real time to reflect the feedback in the next recommendation. This makes it possible to provide sophisticated recommendations based on the individual preferences and lifestyle of the user and reflect user feedback in real time.

[0751] "User Information" refers to basic information such as a user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[0752] "Database" refers to systems and software used to record and store information, such as user information and activity data.

[0753] "Form" refers to an interface that provides a screen layout and input fields for a user to enter detailed profile information.

[0754] "Wearable devices" refers to various electronic devices that are worn on the body, such as fitness trackers and smartwatches.

[0755] "Activity data" refers to information about a user's activities, such as steps, heart rate, and sleep data obtained from a wearable device.

[0756] "Generative artificial intelligence (generative AI)" refers to artificial intelligence that has the ability to generate new information based on large amounts of data.

[0757] "Artificial general intelligence (AGI)" refers to advanced artificial intelligence that can handle a wide range of tasks and functions, rather than specific tasks.

[0758] "Recommendations" refers to suggested actions, products, services, information, etc., based on a user's specific circumstances or preferences.

[0759] "Push notification" refers to an automatic message notification sent from a server to a user device.

[0760] "Feedback" refers to the rating and comment information provided by a user in response to a recommendation they receive.

[0761] "Real-time" refers to processing and information being reflected immediately without delay.

[0762] "Update" refers to correcting or supplementing existing data or models with new information.

[0763] The system of the present invention provides customized recommendations based on a user's lifestyle. The system performs a series of data collection, analysis, recommendation generation, notification, feedback collection, and real-time adjustment through interactions between a server, a terminal, and a user.

[0764] First, when a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. Next, the device displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), and the user is prompted to enter the details. This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[0765] The server analyzes the received user information and activity data using generative artificial intelligence (AI) and artificial general intelligence (AGI) algorithms. This analysis learns the user's behavioral patterns and preferences and extracts individual characteristics. For example, it may reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[0766] The server then generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[0767] The generated recommendation is pushed from the server to the user's device. The device receives the notification and displays the notification content to the user. The user can check the notification and take specific actions. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[0768] Users provide feedback on recommendations via their devices. This feedback is received by the server and recorded in a database. The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. This makes it possible to always provide users with the latest and most optimal suggestions.

[0769] As a concrete example, suppose User A newly registers with the system and provides the following information:

[0770] Name: User A

[0771] Age: 35

[0772] Gender: Female

[0773] Eating habits: Health-conscious, vegetarian

[0774] Hobbies: Watching movies, running

[0775] Health goals: weight management, stress reduction

[0776] When User A connects a fitness tracker, the server receives and records data from the fitness tracker (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[0777] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[0778] An example of a prompt for a generative AI model is:

[0779] "Based on the new user's information, we suggest healthy vegetarian recipes and relaxing movies."

[0780] Through the above process, the system can provide precise recommendations based on the user's individual preferences and lifestyle, supporting an efficient and fulfilling daily life.

[0781] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0782] Step 1: User registration and receipt of basic information

[0783] When a user signs up to the system, the server receives basic information (such as name, age, gender, and email address) that is provided as input in a form. The server records this information in a database to create a basic profile of the user.

[0784] Specifically, the user enters basic information into the form and clicks the "Submit" button. The entered basic information is sent to the server and saved in the database.

[0785] Step 2: Collect detailed profile information

[0786] The device displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the details, which are then sent to the server and recorded in a database.

[0787] Specifically, the user enters information such as eating habits and hobbies into a form on the device and clicks the "Submit" button. The server receives this information and stores it in a database.

[0788] Step 3: Connect your wearable device

[0789] Users connect their fitness trackers, smartwatches, etc. to the system, and the server periodically receives activity data (such as steps, heart rate, and sleep data) from the connected devices and records it in a database.

[0790] Specifically, the user clicks the "Link Device" button on the app's settings screen and follows the instructions to link the device. The server receives activity data from the device every hour and stores it in a database.

[0791] Step 4: Data analysis with generative AI

[0792] The server integrates the received user information and activity data and analyzes the data using a generative AI model. Basic information, detailed profile information, and activity data are provided as input data to the generative AI. The generative AI learns the user's behavioral patterns and preferences and extracts features.

[0793] Specifically, the server inputs data into a generative AI model and generates results using prompts such as "Tell me about the user's weekend eating patterns." The output is the user's behavioral patterns.

[0794] Step 5: Learning behavioral patterns using general artificial intelligence

[0795] The server inputs the analysis results of the generative AI into the AGI algorithm to learn detailed behavioral patterns and improve the model. The results of the generative AI are given as input data to the AGI for further advanced analysis.

[0796] Specifically, the server passes the output of the generation AI to the AGI, and inputs a prompt such as "Please learn more detailed behavioral patterns." The output is a more detailed behavioral pattern.

[0797] Step 6: Generate customized recommendations

[0798] The server generates customized recommendations based on the analysis results of the generative AI and AGI. The analysis results are used as input data. The output is suggestions tailored to each user.

[0799] Specifically, the server creates recommendations based on the results of generative AI and AGI. The recommendations are created using prompts such as "Please suggest healthy vegetarian recipes for user A on busy weekdays."

[0800] Step 7: Recommendation Notification

[0801] The server pushes the generated recommendations to the user device. The generated recommendations are used as input. The output is a notification message sent to the user device.

[0802] Specifically, the server will push a message to User A such as, "Here are some vegetarian recipes to recommend for busy days."

[0803] Step 8: Gather user feedback

[0804] The user provides feedback on the recommendation at the terminal. The feedback the user returns is used as input. The server receives this feedback and records it in a database.

[0805] Specifically, User A inputs feedback such as "This recipe was easy and delicious" and presses the "Send" button on the device. The server receives this and stores it in the database.

[0806] Step 9: Real-time model updates

[0807] The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. The feedback data is used as input. The output is an updated AI model.

[0808] Specifically, based on User A's feedback, the server inputs prompts such as "Please continue to suggest easy and delicious recipes for busy days" into the generation AI and updates the model.

[0809] (Application example 1)

[0810] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0811] Conventional recommendation systems only provide general recommendations without taking into account the user's lifestyle or health condition. This makes it difficult to provide optimal recommendations tailored to individual needs, and fails to improve user satisfaction. Furthermore, health data has rarely been utilized to provide real-time recommendations for lifestyle improvements, and these systems have not contributed sufficiently to users' health management. Furthermore, there has been a lack of a way to link these recommendations to specific actions (e.g., online purchases or reservations), resulting in low user convenience.

[0812] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0813] In this invention, the server includes: means for receiving user information and recording it in a database; means for analyzing data using generative artificial intelligence and general artificial intelligence based on the received user information; means for generating customized recommendations based on the analysis results; means for notifying the user terminal of the generated recommendations; means for receiving feedback from the user, recording it in a database, and adjusting the recommendations in real time; and means for receiving health data acquired from a smart device, using the data to evaluate the user's health status, and suggesting related products and services through electronic payment. This enables precise recommendations based on the user's individual health status and lifestyle, significantly improving user satisfaction and convenience. Furthermore, by linking the recommendations to specific actions, it becomes possible to make suggestions that are directly useful to the user's real life.

[0814] "User information" refers to basic information such as the user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[0815] "Database" refers to the storage device within the system that records and stores user information, health data, feedback information, etc.

[0816] "Generative AI" refers to AI that has the ability to generate new information and value based on specific data and patterns.

[0817] "General artificial intelligence" refers to artificial intelligence that is not specialized in any particular task and has broad knowledge and cognitive capabilities.

[0818] "Data analysis" refers to the process of analyzing collected data and extracting meaningful patterns and information from it.

[0819] "Customized recommendations" refers to suggestions that are specifically designed based on an individual user's behavioral patterns, preferences, and health status.

[0820] "Notification" refers to the process of sending information to a user terminal in real time and displaying it.

[0821] "Feedback" refers to reactions and opinions on recommendations provided by users.

[0822] "Real-time adjustment" refers to the process of immediately incorporating feedback to improve future recommendations.

[0823] "Smart devices" refers to devices such as smartwatches and fitness trackers that have internet connectivity and can collect and transmit user health data.

[0824] "Health Assessment" refers to the process of analyzing the User's physical and mental condition based on the collected health data.

[0825] "Electronic payments" refers to digital payment methods for paying for goods and services online.

[0826] "Suggesting related products and services" refers to the process of recommending specific products and services based on the user's health condition and lifestyle, and encouraging them to purchase or use them.

[0827] The system of the present invention includes the following means for providing customized recommendations based on a user's lifestyle:

[0828] First, the server receives user information and records it in a database. This user information includes basic information such as name, age, gender, and email address, as well as detailed profile information (e.g., eating habits, hobbies, work schedule, health goals, etc.). It also receives health data obtained from smart devices such as smartwatches and fitness trackers. This health data includes daily step counts, heart rate, sleep data, etc.

[0829] The server then analyzes the received user information and health data using generative artificial intelligence and general artificial intelligence. This evaluates the user's behavioral patterns, preferences, and health status. Based on the analysis results, it generates customized recommendations. Meal recommendations suggest menus based on the user's health goals (e.g., weight management, muscle building, etc.). Specifically, it generates online purchasing links for foods and ingredients related to the suggested meal menu.

[0830] The generated recommendations are sent to the user's device. For example, a push notification is sent to the user's smartphone, allowing the user to take specific action by checking the notification. In addition, when it comes to exercise recommendations, the system provides a function that allows users to easily book and pay for lessons at exercise studios and gyms.

[0831] Users can provide feedback on the recommendations they receive. This feedback is received by the server and recorded in a database. The server updates the AI ​​model in real time based on the feedback, and the feedback is reflected in the next recommendation, allowing the server to make suggestions that are more suited to the individual needs of the user.

[0832] Specific hardware and software used in this invention include a backend API (e.g., api.smarthealthapp.com) that manages user information and health data, a generation AI server (e.g., ai.smarthealthapp.com), and an online supermarket API (e.g., api.onlinesupermarket.com). Through these systems, users can easily take specific actions necessary to improve their lives.

[0833] As a concrete example, suppose User A provides the following information:

[0834] Name: User A

[0835] Age: 35

[0836] Gender: Female

[0837] Eating habits: Health-conscious, vegetarian

[0838] Hobbies: Watching movies, running

[0839] Health goals: weight management, stress reduction

[0840] When User A connects their smartwatch, the server receives and records data from the smartwatch (e.g., daily steps, heart rate, sleep data). The generation AI analyzes this data and evaluates User A's behavioral patterns and health status. For example, it can obtain information such as, "User A runs on weekends, but exercises less on days when stress is high."

[0841] Based on the results of this analysis, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can then take the suggested actions and provide feedback, further improving the accuracy of the next recommendation.

[0842] Example prompts for the generative AI:

[0843] "Create customized diet and exercise suggestions based on your current user profile and health data."

[0844] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0845] Step 1:

[0846] The server receives user information and records it in a database. The received user information includes basic data such as name, age, gender, and email address, as well as detailed profile information such as eating habits, hobbies, work schedule, and health goals. The input is the individual information provided by the user, and the output is that it is stored in the database.

[0847] Step 2:

[0848] When users connect smart devices such as smartwatches and fitness trackers, the server periodically receives and records activity data from these devices, including daily steps, heart rate, sleep data, etc. The input is the real-time data sent from the smart devices, and the output is that the health data is stored in a database.

[0849] Step 3:

[0850] The server analyzes the collected user information and health data using generative artificial intelligence and general artificial intelligence. The AI ​​processes the received data and evaluates the user's behavioral patterns and health status. For example, it evaluates behavioral patterns such as "tends to eat out on weekends" and health status such as "exercises less on days with high stress." The input is user information and health data recorded in the database, and the output is the evaluation results of behavioral patterns and health status.

[0851] Step 4:

[0852] The generative AI generates customized recommendations based on the evaluation results, providing specific suggestions such as meal plans, exercise advice, and relaxation methods. The input is the evaluation results obtained in Step 3, and the output is a recommendation customized for each user.

[0853] Step 5:

[0854] The generated recommendation is pushed to the user's device. The device receives this notification and displays it to the user. For example, it may recommend a healthy vegetarian dinner recipe or a relaxing movie. The input is the recommendation generated in step 4, and the output is the notification displayed on the user's device.

[0855] Step 6:

[0856] The user provides feedback on the notified recommendation. The device acquires this feedback and sends it to the server. The input is the feedback information from the user, and the output is that the feedback is recorded in the server.

[0857] Step 7:

[0858] The server updates the AI ​​model in real time based on the received feedback. The feedback data is then analyzed again by the AI ​​and reflected in the next recommendation. This process improves the system so that it can make suggestions that are more suited to the individual preferences and needs of each user. The input is feedback information from the user, and the output is an updated AI model and the next recommendation.

[0859] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0860] The system of the present invention provides customized recommendations based on the user's lifestyle, and in particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment.

[0861] Collection and management of user information

[0862] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[0863] Emotion recognition by emotion engine

[0864] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[0865] Data analysis using AI models

[0866] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0867] Generating customized recommendations

[0868] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[0869] User interface presentation

[0870] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0871] Real-time feedback and adjustments

[0872] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[0873] Specific examples

[0874] User B newly registers with the system and provides the following information:

[0875] Name: User B

[0876] Age: 40

[0877] Gender: Male

[0878] Eating habits: Balanced diet

[0879] Hobbies: Reading, watching movies

[0880] Health goals: Stress management, improved sleep quality

[0881] When User B connects a wearable fitness tracker and the system uses emotion recognition to collect real-time emotional data, the server uses this data to learn User B's behavioral patterns. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "Reading helps him relax."

[0882] Based on the analysis results, the server suggests to User B "a relaxing breakfast menu for Monday morning" and "the best time to read." Furthermore, through the emotion engine, recommendations are generated, including "relaxation exercises that User B should do when he feels stressed." User B can review these and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation will be further improved.

[0883] In this way, by using the emotion engine, this system can provide sophisticated recommendations that take into account the user's emotional state, supporting a more efficient and fulfilling daily life.

[0884] The processing flow will be explained below.

[0885] Step 1:

[0886] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, the server receives this information and records it in a database.

[0887] Step 2:

[0888] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) Once the user enters the information and presses the submit button, the server receives this information and stores it in a database.

[0889] Step 3:

[0890] When a user connects a wearable device (e.g., fitness tracker, smart watch) to the system, the server periodically receives activity data (e.g., steps, heart rate, sleep data) from the device and records it in a database.

[0891] Step 4:

[0892] The device collects emotional data in real time from the user's facial expressions and voice using emotion recognition technology using a camera and microphone, and transmits the collected emotional data to a server.

[0893] Step 5:

[0894] The server performs data cleansing and preprocessing based on the received user information, activity data, and sentiment data, including removing duplicate data and imputing missing values.

[0895] Step 6:

[0896] The server uses generative AI and AGI algorithms to analyze the preprocessed data. Based on the analysis results, features related to the user's behavioral patterns and emotional state are extracted. For example, information such as "the user is prone to stress on Mondays" can be obtained.

[0897] Step 7:

[0898] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Meal menus are suggested based on the user's health goals and real-time emotional state. For example, a user feeling stressed will be recommended a meal that will help them relax.

[0899] Step 8:

[0900] The device receives the recommendations generated by the server via push notification and displays them to the user. The user can then confirm the notification and act on the suggestions, for example, cooking a relaxing breakfast menu.

[0901] Step 9:

[0902] The user provides feedback on the recommendation on the device, which may be about changes in emotional state or satisfaction with the recommendation. The device then forwards this feedback information to the server.

[0903] Step 10:

[0904] The server records the received feedback in a database and updates the generative AI and AGI models in real time, allowing the system to further refine its next recommendation. For example, if a user enjoyed a particular meal, it might suggest similar dishes in the future.

[0905] In this way, a system incorporating an emotion engine can provide customized recommendations that take into account the user's emotional state, helping users lead more comfortable and efficient daily lives.

[0906] Example 2

[0907] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0908] While most conventional recommendation systems make suggestions based on a user's basic information, they are unable to reflect the user's real-time emotional state, making them unable to adequately address individual needs. In particular, for stress management and achieving health goals, precise recommendations that take into account the user's emotional state are important, but existing systems have not been able to achieve this.

[0909] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information and emotion data collected in real time, means for generating customized recommendations based on the analysis results, means for notifying the user's terminal of the generated recommendations, means for receiving feedback from the user and recording it in a database and adjusting the recommendations in real time, and means for collecting emotion data from facial expressions, voice, and text messages. This makes it possible to reflect the user's emotional state in real time and provide more personalized and sophisticated recommendations.

[0910] "User Information" is data including basic information (such as name, age, gender, and email address) and detailed profile information (such as eating habits, hobbies, work schedule, and health goals) provided by a user when signing up to the system.

[0911] A "database" is a data management structure within a system that records and stores user information, emotional data, and feedback information, and uses this information to perform data analysis and generate recommendations.

[0912] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that includes algorithms and models for generating new information and recommendations based on data.

[0913] "Artificial general intelligence (AGI)" is a general-purpose artificial intelligence system that can handle a wide range of tasks, not just specific ones, and is a technology for performing advanced analysis based on various user data.

[0914] "Emotion data" refers to data that indicates the user's emotional state collected in real time from facial expressions, voice, text messages, and the like.

[0915] "Features" are information extracted and quantified in data analysis, such as a user's behavioral patterns, preferences, and emotional state.

[0916] "Recommendations" refers to suggestions and advice customized for each user based on collected data and analysis results.

[0917] "Push notification" is a communication method in which information or alerts are automatically sent from a server to a device to notify the user.

[0918] "Feedback" refers to user-provided ratings and opinions on recommendations, data that the system uses to improve future suggestions.

[0919] "Emotion engine" refers to technology that recognizes and evaluates a user's emotional state in real time from their facial expressions, voice, and text messages.

[0920] This invention relates to a system for providing customized recommendations based on a user's lifestyle. In particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. The specific form of this system is described below.

[0921] Collection and management of user information

[0922] When a user signs up for the system, the device displays an input form on the screen to collect basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the server receives this information and records it in a database. The device then displays an additional form to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), making it easier for the user to enter more information. This information is also sent to the server and stored in the database.

[0923] Emotion recognition by emotion engine

[0924] The emotion engine is built into the device and uses a camera and microphone to collect real-time emotion data from the user's facial expressions, voice, and text messages. The server receives this emotion data, evaluates the user's emotional state, and records it in a database. The emotion engine uses facial expression recognition technology and voice tone analysis technology.

[0925] Data analysis using AI models

[0926] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, preferences, and even emotional state are extracted. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0927] Generating customized recommendations

[0928] The server generates personalized recommendations for each user based on the results of AI analysis and the output of the emotion engine. Specifically, meal suggestions provide menus based on the user's health goals and real-time emotional state. Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also include reminders and task management that take emotional state into account.

[0929] Presentation in the user interface

[0930] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0931] Real-time feedback and adjustments

[0932] Users can provide feedback on recommendations on their devices, which collect and forward the feedback information to the server, which records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of future recommendations.

[0933] Specific examples

[0934] For example, User B registers with the system and provides the following information:

[0935] Name: User B

[0936] Age: 40

[0937] Gender: Male

[0938] Eating habits: Balanced diet

[0939] Hobbies: Reading, watching movies

[0940] Health goals: Stress management, improved sleep quality

[0941] When User B connects a wearable fitness tracker, the system uses emotion recognition to collect real-time emotional data. The server uses this data to learn User B's behavioral patterns. The generation AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "a relaxing breakfast menu for Monday mornings" and "the best time to read." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement them based on his emotional state. Providing feedback further improves the quality of the next recommendation. An example of this prompt might be, "Please suggest a relaxing breakfast menu."

[0942] Thus, by using the emotion engine, the system of the present invention provides sophisticated recommendations that take into account the user's emotional state, supporting an efficient and fulfilling daily life.

[0943] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0944] Step 1:

[0945] The terminal displays a form for the user to enter basic information (such as name, age, gender, and email address). When the user enters this information and presses the submit button, the input data is sent from the terminal to the server. The server verifies the received user information and records it in a database. For example, it checks whether the name, age, and gender are in an existing database and registers the user as a new user.

[0946] Input: User basic information

[0947] Output: Verified user information is saved in the database

[0948] Step 2:

[0949] The device displays an additional form for entering detailed profile information (eating habits, hobbies, work schedule, health goals, etc.). After the user enters the details and presses the submit button, the input data is sent back to the server. The server receives it and stores it in a database as detailed profile information. This information is used for analysis by the generative AI and AGI.

[0950] Input: User's detailed profile information

[0951] Output: Detailed profile information is saved in the database

[0952] Step 3:

[0953] The device collects emotional data in real time using a camera and microphone. The emotion engine analyzes the user's facial expressions and voice and extracts their emotional state from text messages. The collected emotional data is sent from the device to a server. The server receives the data, evaluates the emotional state, and records it in a database.

[0954] Input: Real-time user facial expressions, voice, and text messages

[0955] Output: Real-time emotion data is stored in a database

[0956] Step 4:

[0957] The server uses the collected user information and emotional data to analyze the data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, emotional state, and preferences are extracted. For example, it may become clear that a user is more likely to feel stressed on certain days of the week, or that certain foods improve their mood.

[0958] Input: User information, real-time emotion data

[0959] Output: Features related to behavioral patterns and emotional states

[0960] Step 5:

[0961] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Specific suggestions include meal plans based on health goals and real-time emotional states, and entertainment content tailored to individual interests. The generated recommendations are then sent from the server to the device.

[0962] Input: Analysis results, emotion engine output

[0963] Output: Customized recommendations

[0964] Step 6:

[0965] The device receives the recommendations sent from the server and displays them to the user, who can then review the notifications and take specific actions, such as viewing recipes, choosing a movie, or performing a mindfulness exercise.

[0966] Input: Recommendation notification from the server

[0967] Output: The user initiates a specific action.

[0968] Step 7:

[0969] Users input feedback on recommendations on their devices. The devices then send the feedback information to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time based on that feedback. This improves the accuracy of the next recommendation.

[0970] Input: User feedback

[0971] Output: Update the AI ​​model based on the feedback

[0972] (Application example 2)

[0973] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0974] Conventional recommendation systems make recommendations based on a user's basic personal information and past behavioral history, but this lack of proposals that adequately reflect the user's real-time emotional state. As a result, recommendations cannot be tailored to the user's current mood or stress level, making it difficult to provide a more personalized service. It is also difficult to reflect user feedback in real time and readjust the system.

[0975] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0976] In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information, emotion recognition means for recognizing the emotional state of the user, means for generating customized recommendations based on the analysis results and the emotion recognition results, means for notifying the generated recommendations to the user terminal, and means for receiving feedback from the user, recording it in the database, and adjusting the recommendations in real time, thereby enabling more personalized recommendations that are suited to the emotional state of the user.

[0977] The "means for receiving user information and recording it in a database" refers to a means for collecting basic information and detailed profile information of a user and storing it in a database.

[0978] "Generative artificial intelligence" is an artificial intelligence technology that can generate new data and patterns based on large amounts of data.

[0979] "General artificial intelligence" is an artificial intelligence technology with flexible intelligence that can handle a variety of tasks, not just specific ones.

[0980] "Means for analyzing data" refers to means for analyzing collected user information and extracting useful information and patterns.

[0981] The "emotion recognition means" is a means for analyzing the user's facial expressions and voice using a camera and microphone to recognize the user's emotional state in real time.

[0982] The "means for generating customized recommendations" refers to a means for generating advice and suggestions that are optimized for each user based on the analysis results and emotion recognition results.

[0983] The "means for notifying the user terminal of the generated recommendation" refers to a means for transmitting the generated recommendation to the terminal used by the user in the form of a push notification or the like.

[0984] "Means for receiving feedback, recording it in a database, and adjusting recommendations in real time" refers to means for collecting feedback from users and using that feedback to improve the accuracy of recommendations in real time.

[0985] The system of the present invention provides customized recommendations based on a user's lifestyle and combines an emotion engine to realize suggestions that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. A detailed embodiment of the system is described below.

[0986] Collection and management of user information

[0987] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[0988] Emotion recognition by emotion engine

[0989] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[0990] Data analysis using AI models

[0991] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[0992] Generating customized recommendations

[0993] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[0994] User interface presentation

[0995] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[0996] Real-time feedback and adjustments

[0997] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[0998] Specific examples

[0999] User B newly registers with the system and provides the following information:

[1000] Name: User B

[1001] Age: 40

[1002] Gender: Male

[1003] Eating habits: Balanced diet

[1004] Hobbies: Reading, watching movies

[1005] Health goals: Stress management, improved sleep quality

[1006] When User B connects a wearable fitness tracker and the system uses the emotion recognition function to collect real-time emotional data, the server learns User B's behavioral patterns based on this data. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "breakfast menus that have a relaxing effect on Monday mornings" and "optimal times for reading." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation can be further improved.

[1007] Example prompts to input to a generative AI model:

[1008] User: 40-year-old male. Hobbies include reading and watching movies. His goals are stress management and improving sleep quality. He tends to feel stressed on Monday mornings. Please suggest a breakfast menu that will help him relax.

[1009] In this way, the system can provide more personalized recommendations based on the user's emotional state and lifestyle.

[1010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1011] Step 1:

[1012] When a user signs up for the system, the terminal displays a form for inputting basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the entered information is sent to the server. The server receives it, verifies it, and records it in a database. The input here is the user's basic information, and the output is the verified user information stored in the database.

[1013] Step 2:

[1014] The device then displays the form again for entering detailed profile information (e.g., eating habits, hobbies, health goals, etc.). The user enters additional information and presses the submit button, which again sends the details to the server. The server receives the submitted details and stores them in a database. The input here is the detailed profile information, and the output is the details stored in the database.

[1015] Step 3:

[1016] Users collect emotional data using wearable devices or smartphones. This involves using a camera and microphone to recognize emotional states by analyzing facial expressions, voice, and text messages. The device processes this data in real time using an emotion engine and sends the emotional data to a server. The input is the collected emotional data, and the output is the emotional state data sent to the server.

[1017] Step 4:

[1018] The server uses generative AI and general-purpose AI algorithms to analyze the collected user information and emotional data. During this process, it extracts features based on the user's behavioral patterns, preferences, and emotional state. The input is the user information and emotional data stored in the database, and the output is the analysis of the user's behavioral patterns and emotional state.

[1019] Step 5:

[1020] The server generates customized recommendations based on the analysis results and emotion recognition data. For example, it suggests meal menus based on the user's health goals and real-time emotional state, or entertainment content based on their hobbies. The input is the analysis results and emotion data, and the output is customized recommendations.

[1021] Step 6:

[1022] The generated recommendations are sent from the server to the user's device via push notification. The device receives the notification and displays the recommendations to the user. The user checks the notification and takes specific actions (e.g., looking at recipes, choosing a movie, performing a mindfulness exercise, etc.). The input here is the generated recommendations, and the output is the display to the user.

[1023] Step 7:

[1024] The user provides feedback on the provided recommendations. The device collects the feedback information and sends it back to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time, thereby improving the accuracy of the next recommendation. The input is the feedback information from the user, and the output is the model and database updated in real time.

[1025] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1026] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1027] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1028] [Fourth embodiment]

[1029] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1030] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1032] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1033] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1034] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1036] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1037] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1038] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1040] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1042] The system of the present invention provides customized recommendations based on a user's lifestyle. The system operates through a series of steps: collecting user information, analyzing the data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), generating recommendations, notifying users, and collecting and adjusting feedback in real time.

[1043] Collection and management of user information

[1044] When a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals). This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[1045] Data analysis using AI models

[1046] The server analyzes the received user information and activity data using generative AI and AGI algorithms, learning the user's behavioral patterns and preferences and extracting individual characteristics. For example, this can reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[1047] Generating customized recommendations

[1048] The server generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[1049] User interface presentation

[1050] The recommendation generated by the server is pushed to the user's device. The device receives the notification and displays it to the user. The user can then check the notification and take specific action. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[1051] Real-time feedback and adjustments

[1052] Users can provide feedback on recommendations on their devices. This feedback is received by the server and recorded in a database. The server then updates the AI ​​model in real time based on the feedback and reflects it in the next recommendation. This ensures that the system always provides the latest and most optimal suggestions.

[1053] Specific examples

[1054] For example, User A registers with the system and provides the following information:

[1055] Name: User A

[1056] Age: 35

[1057] Gender: Female

[1058] Eating habits: Health-conscious, vegetarian

[1059] Hobbies: Watching movies, running

[1060] Health goals: weight management, stress reduction

[1061] When User A connects a wearable fitness tracker, the server receives and records data from the wearable device (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[1062] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[1063] In this way, the system supports efficient and fulfilling daily life by providing sophisticated recommendations based on the user's individual preferences and lifestyle.

[1064] The processing flow will be explained below.

[1065] Step 1:

[1066] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, this information is transferred to the server, which verifies the received information and records it in a database.

[1067] Step 2:

[1068] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the data and presses the submit button. The server receives these details and stores them in a database.

[1069] Step 3:

[1070] When a user connects a wearable device (such as a fitness tracker or smartwatch) to the system, the server periodically receives activity data (such as steps, heart rate, and sleep data) from the device, and the received data is recorded in a database.

[1071] Step 4:

[1072] The server retrieves user information and activity data from the database and performs data cleansing and pre-processing, including removing duplicate data and imputing missing values.

[1073] Step 5:

[1074] The server analyzes the preprocessed data using generative artificial intelligence (generative AI) and artificial general intelligence (AGI) algorithms. Specifically, it learns each user's behavioral patterns and preferences and extracts features. This analysis allows it to understand the user's specific behavioral patterns (e.g., preference for certain foods on certain days of the week) and health status (e.g., high stress on certain days).

[1075] Step 6:

[1076] Based on the AI ​​analysis results, the server generates personalized recommendations for each user, including meal plans that match the user's health goals, entertainment suggestions based on the user's hobbies, and reminders for optimal schedule management.

[1077] Step 7:

[1078] The device receives the recommendations generated by the server via push notification and displays them to the user, who can then check the notification and take specific actions based on the recommendations.

[1079] Step 8:

[1080] The user provides feedback on the recommendation (e.g., "very satisfied," "satisfied," "unsatisfied," etc.) through the device. The device receives this feedback information and forwards it to the server.

[1081] Step 9:

[1082] The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process ensures that the system always provides the latest and most optimal suggestions.

[1083] Example 1

[1084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1085] Conventional recommendation systems have difficulty providing customized recommendations based on a user's individual preferences and lifestyle. Furthermore, they lack the functionality to reflect user feedback in real time and improve the content of future recommendations. This results in low user satisfaction and makes it difficult to encourage continued use.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1087] In this invention, the server includes means for receiving user information and recording it in a database, means for displaying a form for inputting detailed profile information and recording the detailed information in the database, means for receiving and recording activity data from the wearable device, means for integrating the received user information and activity data and analyzing the data using generative artificial intelligence and general artificial intelligence, means for generating customized recommendations based on the analysis results, means for notifying the user terminal of the generated recommendations, and means for receiving feedback from the user and recording it in the database, updating the generative artificial intelligence and general artificial intelligence models in real time to reflect the feedback in the next recommendation. This makes it possible to provide sophisticated recommendations based on the individual preferences and lifestyle of the user and reflect user feedback in real time.

[1088] "User Information" refers to basic information such as a user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[1089] "Database" refers to systems and software used to record and store information, such as user information and activity data.

[1090] "Form" refers to an interface that provides a screen layout and input fields for a user to enter detailed profile information.

[1091] "Wearable devices" refers to various electronic devices that are worn on the body, such as fitness trackers and smartwatches.

[1092] "Activity data" refers to information about a user's activities, such as steps, heart rate, and sleep data obtained from a wearable device.

[1093] "Generative artificial intelligence (generative AI)" refers to artificial intelligence that has the ability to generate new information based on large amounts of data.

[1094] "Artificial general intelligence (AGI)" refers to advanced artificial intelligence that can handle a wide range of tasks and functions, rather than specific tasks.

[1095] "Recommendations" refers to suggested actions, products, services, information, etc., based on a user's specific circumstances or preferences.

[1096] "Push notification" refers to an automatic message notification sent from a server to a user device.

[1097] "Feedback" refers to the rating and comment information provided by a user in response to a recommendation they receive.

[1098] "Real-time" refers to processing and information being reflected immediately without delay.

[1099] "Update" refers to correcting or supplementing existing data or models with new information.

[1100] The system of the present invention provides customized recommendations based on a user's lifestyle. The system performs a series of data collection, analysis, recommendation generation, notification, feedback collection, and real-time adjustment through interactions between a server, a terminal, and a user.

[1101] First, when a user signs up for the system, the server receives the user's basic information (such as name, age, gender, and email address) and records it in a database. Next, the device displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), and the user is prompted to enter the details. This allows the user's individual information to be stored in a database. Furthermore, if the user connects devices such as fitness trackers or smartwatches, the server periodically receives and records activity data from these devices.

[1102] The server analyzes the received user information and activity data using generative artificial intelligence (AI) and artificial general intelligence (AGI) algorithms. This analysis learns the user's behavioral patterns and preferences and extracts individual characteristics. For example, it may reveal that the user prefers certain foods on weekends or exercises on certain days during the week.

[1103] The server then generates customized recommendations based on the AI ​​analysis results. Meal suggestions provide menus based on the user's health goals (e.g., weight management, muscle building, etc.). Entertainment suggestions recommend movies and events based on the user's hobbies and past behavioral patterns. Furthermore, time management suggestions provide reminders and task management features to optimize the user's schedule.

[1104] The generated recommendation is pushed from the server to the user's device. The device receives the notification and displays the notification content to the user. The user can check the notification and take specific actions. For example, they can check the recommended meal recipe and purchase the necessary ingredients, or go to the recommended movie.

[1105] Users provide feedback on recommendations via their devices. This feedback is received by the server and recorded in a database. The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. This makes it possible to always provide users with the latest and most optimal suggestions.

[1106] As a concrete example, suppose User A newly registers with the system and provides the following information:

[1107] Name: User A

[1108] Age: 35

[1109] Gender: Female

[1110] Eating habits: Health-conscious, vegetarian

[1111] Hobbies: Watching movies, running

[1112] Health goals: weight management, stress reduction

[1113] When User A connects a fitness tracker, the server receives and records data from the fitness tracker (e.g., daily steps, heart rate, and sleep data). The generation AI analyzes this data and learns User A's behavioral patterns. For example, it can learn information such as "User A eats a lot of green and yellow vegetables on weekdays, but enjoys eating out on weekends," or "User A runs three times a week, but exercises less on days when stress is high."

[1114] Based on the analysis results, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can review the recommendations and take the suggested actions. Furthermore, by providing feedback on these recommendations, the accuracy of the next recommendation can be further improved.

[1115] An example of a prompt for a generative AI model is:

[1116] "Based on the new user's information, we suggest healthy vegetarian recipes and relaxing movies."

[1117] Through the above process, the system can provide precise recommendations based on the user's individual preferences and lifestyle, supporting an efficient and fulfilling daily life.

[1118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1119] Step 1: User registration and receipt of basic information

[1120] When a user signs up to the system, the server receives basic information (such as name, age, gender, and email address) that is provided as input in a form. The server records this information in a database to create a basic profile of the user.

[1121] Specifically, the user enters basic information into the form and clicks the "Submit" button. The entered basic information is sent to the server and saved in the database.

[1122] Step 2: Collect detailed profile information

[1123] The device displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) The user enters the details, which are then sent to the server and recorded in a database.

[1124] Specifically, the user enters information such as eating habits and hobbies into a form on the device and clicks the "Submit" button. The server receives this information and stores it in a database.

[1125] Step 3: Connect your wearable device

[1126] Users connect their fitness trackers, smartwatches, etc. to the system, and the server periodically receives activity data (such as steps, heart rate, and sleep data) from the connected devices and records it in a database.

[1127] Specifically, the user clicks the "Link Device" button on the app's settings screen and follows the instructions to link the device. The server receives activity data from the device every hour and stores it in a database.

[1128] Step 4: Data analysis with generative AI

[1129] The server integrates the received user information and activity data and analyzes the data using a generative AI model. Basic information, detailed profile information, and activity data are provided as input data to the generative AI. The generative AI learns the user's behavioral patterns and preferences and extracts features.

[1130] Specifically, the server inputs data into a generative AI model and generates results using prompts such as "Tell me about the user's weekend eating patterns." The output is the user's behavioral patterns.

[1131] Step 5: Learning behavioral patterns using general artificial intelligence

[1132] The server inputs the analysis results of the generative AI into the AGI algorithm to learn detailed behavioral patterns and improve the model. The results of the generative AI are given as input data to the AGI for further advanced analysis.

[1133] Specifically, the server passes the output of the generation AI to the AGI, and inputs a prompt such as "Please learn more detailed behavioral patterns." The output is a more detailed behavioral pattern.

[1134] Step 6: Generate customized recommendations

[1135] The server generates customized recommendations based on the analysis results of the generative AI and AGI. The analysis results are used as input data. The output is suggestions tailored to each user.

[1136] Specifically, the server creates recommendations based on the results of generative AI and AGI. The recommendations are created using prompts such as "Please suggest healthy vegetarian recipes for user A on busy weekdays."

[1137] Step 7: Recommendation Notification

[1138] The server pushes the generated recommendations to the user device. The generated recommendations are used as input. The output is a notification message sent to the user device.

[1139] Specifically, the server will push a message to User A such as, "Here are some vegetarian recipes to recommend for busy days."

[1140] Step 8: Gather user feedback

[1141] The user provides feedback on the recommendation at the terminal. The feedback the user returns is used as input. The server receives this feedback and records it in a database.

[1142] Specifically, User A inputs feedback such as "This recipe was easy and delicious" and presses the "Send" button on the device. The server receives this and stores it in the database.

[1143] Step 9: Real-time model updates

[1144] The server updates the generative AI and AGI models in real time based on the feedback and reflects it in the next recommendation. The feedback data is used as input. The output is an updated AI model.

[1145] Specifically, based on User A's feedback, the server inputs prompts such as "Please continue to suggest easy and delicious recipes for busy days" into the generation AI and updates the model.

[1146] (Application example 1)

[1147] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1148] Conventional recommendation systems only provide general recommendations without taking into account the user's lifestyle or health condition. This makes it difficult to provide optimal recommendations tailored to individual needs, and fails to improve user satisfaction. Furthermore, health data has rarely been utilized to provide real-time recommendations for lifestyle improvements, and these systems have not contributed sufficiently to users' health management. Furthermore, there has been a lack of a way to link these recommendations to specific actions (e.g., online purchases or reservations), resulting in low user convenience.

[1149] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1150] In this invention, the server includes: means for receiving user information and recording it in a database; means for analyzing data using generative artificial intelligence and general artificial intelligence based on the received user information; means for generating customized recommendations based on the analysis results; means for notifying the user terminal of the generated recommendations; means for receiving feedback from the user, recording it in a database, and adjusting the recommendations in real time; and means for receiving health data acquired from a smart device, using the data to evaluate the user's health status, and suggesting related products and services through electronic payment. This enables precise recommendations based on the user's individual health status and lifestyle, significantly improving user satisfaction and convenience. Furthermore, by linking the recommendations to specific actions, it becomes possible to make suggestions that are directly useful to the user's real life.

[1151] "User information" refers to basic information such as the user's name, age, gender, and email address, as well as detailed profile information (eating habits, hobbies, work schedule, health goals, etc.).

[1152] "Database" refers to the storage device within the system that records and stores user information, health data, feedback information, etc.

[1153] "Generative AI" refers to AI that has the ability to generate new information and value based on specific data and patterns.

[1154] "General artificial intelligence" refers to artificial intelligence that is not specialized in any particular task and has broad knowledge and cognitive capabilities.

[1155] "Data analysis" refers to the process of analyzing collected data and extracting meaningful patterns and information from it.

[1156] "Customized recommendations" refers to suggestions that are specifically designed based on an individual user's behavioral patterns, preferences, and health status.

[1157] "Notification" refers to the process of sending information to a user terminal in real time and displaying it.

[1158] "Feedback" refers to reactions and opinions on recommendations provided by users.

[1159] "Real-time adjustment" refers to the process of immediately incorporating feedback to improve future recommendations.

[1160] "Smart devices" refers to devices such as smartwatches and fitness trackers that have internet connectivity and can collect and transmit user health data.

[1161] "Health Assessment" refers to the process of analyzing the User's physical and mental condition based on the collected health data.

[1162] "Electronic payments" refers to digital payment methods for paying for goods and services online.

[1163] "Suggesting related products and services" refers to the process of recommending specific products and services based on the user's health condition and lifestyle, and encouraging them to purchase or use them.

[1164] The system of the present invention includes the following means for providing customized recommendations based on a user's lifestyle:

[1165] First, the server receives user information and records it in a database. This user information includes basic information such as name, age, gender, and email address, as well as detailed profile information (e.g., eating habits, hobbies, work schedule, health goals, etc.). It also receives health data obtained from smart devices such as smartwatches and fitness trackers. This health data includes daily step counts, heart rate, sleep data, etc.

[1166] The server then analyzes the received user information and health data using generative artificial intelligence and general artificial intelligence. This evaluates the user's behavioral patterns, preferences, and health status. Based on the analysis results, it generates customized recommendations. Meal recommendations suggest menus based on the user's health goals (e.g., weight management, muscle building, etc.). Specifically, it generates online purchasing links for foods and ingredients related to the suggested meal menu.

[1167] The generated recommendations are sent to the user's device. For example, a push notification is sent to the user's smartphone, allowing the user to take specific action by checking the notification. In addition, when it comes to exercise recommendations, the system provides a function that allows users to easily book and pay for lessons at exercise studios and gyms.

[1168] Users can provide feedback on the recommendations they receive. This feedback is received by the server and recorded in a database. The server updates the AI ​​model in real time based on the feedback, and the feedback is reflected in the next recommendation, allowing the server to make suggestions that are more suited to the individual needs of the user.

[1169] Specific hardware and software used in this invention include a backend API (e.g., api.smarthealthapp.com) that manages user information and health data, a generation AI server (e.g., ai.smarthealthapp.com), and an online supermarket API (e.g., api.onlinesupermarket.com). Through these systems, users can easily take specific actions necessary to improve their lives.

[1170] As a concrete example, suppose User A provides the following information:

[1171] Name: User A

[1172] Age: 35

[1173] Gender: Female

[1174] Eating habits: Health-conscious, vegetarian

[1175] Hobbies: Watching movies, running

[1176] Health goals: weight management, stress reduction

[1177] When User A connects their smartwatch, the server receives and records data from the smartwatch (e.g., daily steps, heart rate, sleep data). The generation AI analyzes this data and evaluates User A's behavioral patterns and health status. For example, it can obtain information such as, "User A runs on weekends, but exercises less on days when stress is high."

[1178] Based on the results of this analysis, the server generates customized recommendations for User A, such as "easy and healthy vegetarian recipes for busy weekday dinners" or "recommended movies to watch on the weekend," and notifies the device. User A can then take the suggested actions and provide feedback, further improving the accuracy of the next recommendation.

[1179] Example prompts for the generative AI:

[1180] "Create customized diet and exercise suggestions based on your current user profile and health data."

[1181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1182] Step 1:

[1183] The server receives user information and records it in a database. The received user information includes basic data such as name, age, gender, and email address, as well as detailed profile information such as eating habits, hobbies, work schedule, and health goals. The input is the individual information provided by the user, and the output is that it is stored in the database.

[1184] Step 2:

[1185] When users connect smart devices such as smartwatches and fitness trackers, the server periodically receives and records activity data from these devices, including daily steps, heart rate, sleep data, etc. The input is the real-time data sent from the smart devices, and the output is that the health data is stored in a database.

[1186] Step 3:

[1187] The server analyzes the collected user information and health data using generative artificial intelligence and general artificial intelligence. The AI ​​processes the received data and evaluates the user's behavioral patterns and health status. For example, it evaluates behavioral patterns such as "tends to eat out on weekends" and health status such as "exercises less on days with high stress." The input is user information and health data recorded in the database, and the output is the evaluation results of behavioral patterns and health status.

[1188] Step 4:

[1189] The generative AI generates customized recommendations based on the evaluation results, providing specific suggestions such as meal plans, exercise advice, and relaxation methods. The input is the evaluation results obtained in Step 3, and the output is a recommendation customized for each user.

[1190] Step 5:

[1191] The generated recommendation is pushed to the user's device. The device receives this notification and displays it to the user. For example, it may recommend a healthy vegetarian dinner recipe or a relaxing movie. The input is the recommendation generated in step 4, and the output is the notification displayed on the user's device.

[1192] Step 6:

[1193] The user provides feedback on the notified recommendation. The device acquires this feedback and sends it to the server. The input is the feedback information from the user, and the output is that the feedback is recorded in the server.

[1194] Step 7:

[1195] The server updates the AI ​​model in real time based on the received feedback. The feedback data is then analyzed again by the AI ​​and reflected in the next recommendation. This process improves the system so that it can make suggestions that are more suited to the individual preferences and needs of each user. The input is feedback information from the user, and the output is an updated AI model and the next recommendation.

[1196] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1197] The system of the present invention provides customized recommendations based on the user's lifestyle, and in particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment.

[1198] Collection and management of user information

[1199] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[1200] Emotion recognition by emotion engine

[1201] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[1202] Data analysis using AI models

[1203] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[1204] Generating customized recommendations

[1205] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[1206] User interface presentation

[1207] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[1208] Real-time feedback and adjustments

[1209] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[1210] Specific examples

[1211] User B newly registers with the system and provides the following information:

[1212] Name: User B

[1213] Age: 40

[1214] Gender: Male

[1215] Eating habits: Balanced diet

[1216] Hobbies: Reading, watching movies

[1217] Health goals: Stress management, improved sleep quality

[1218] When User B connects a wearable fitness tracker and the system uses emotion recognition to collect real-time emotional data, the server uses this data to learn User B's behavioral patterns. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "Reading helps him relax."

[1219] Based on the analysis results, the server suggests to User B "a relaxing breakfast menu for Monday morning" and "the best time to read." Furthermore, through the emotion engine, recommendations are generated, including "relaxation exercises that User B should do when he feels stressed." User B can review these and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation will be further improved.

[1220] In this way, by using the emotion engine, this system can provide sophisticated recommendations that take into account the user's emotional state, supporting a more efficient and fulfilling daily life.

[1221] The processing flow will be explained below.

[1222] Step 1:

[1223] When a user signs up to the system, the terminal collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. When the user enters the information and presses the submit button, the server receives this information and records it in a database.

[1224] Step 2:

[1225] The device then displays a form for the user to enter detailed profile information (eating habits, hobbies, work schedule, health goals, etc.) Once the user enters the information and presses the submit button, the server receives this information and stores it in a database.

[1226] Step 3:

[1227] When a user connects a wearable device (e.g., fitness tracker, smart watch) to the system, the server periodically receives activity data (e.g., steps, heart rate, sleep data) from the device and records it in a database.

[1228] Step 4:

[1229] The device collects emotional data in real time from the user's facial expressions and voice using emotion recognition technology using a camera and microphone, and transmits the collected emotional data to a server.

[1230] Step 5:

[1231] The server performs data cleansing and preprocessing based on the received user information, activity data, and sentiment data, including removing duplicate data and imputing missing values.

[1232] Step 6:

[1233] The server uses generative AI and AGI algorithms to analyze the preprocessed data. Based on the analysis results, features related to the user's behavioral patterns and emotional state are extracted. For example, information such as "the user is prone to stress on Mondays" can be obtained.

[1234] Step 7:

[1235] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Meal menus are suggested based on the user's health goals and real-time emotional state. For example, a user feeling stressed will be recommended a meal that will help them relax.

[1236] Step 8:

[1237] The device receives the recommendations generated by the server via push notification and displays them to the user. The user can then confirm the notification and act on the suggestions, for example, cooking a relaxing breakfast menu.

[1238] Step 9:

[1239] The user provides feedback on the recommendation on the device, which may be about changes in emotional state or satisfaction with the recommendation. The device then forwards this feedback information to the server.

[1240] Step 10:

[1241] The server records the received feedback in a database and updates the generative AI and AGI models in real time, allowing the system to further refine its next recommendation. For example, if a user enjoyed a particular meal, it might suggest similar dishes in the future.

[1242] In this way, a system incorporating an emotion engine can provide customized recommendations that take into account the user's emotional state, helping users lead more comfortable and efficient daily lives.

[1243] Example 2

[1244] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1245] While most conventional recommendation systems make suggestions based on a user's basic information, they are unable to reflect the user's real-time emotional state, making them unable to adequately address individual needs. In particular, for stress management and achieving health goals, precise recommendations that take into account the user's emotional state are important, but existing systems have not been able to achieve this.

[1246] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information and emotion data collected in real time, means for generating customized recommendations based on the analysis results, means for notifying the user's terminal of the generated recommendations, means for receiving feedback from the user and recording it in a database and adjusting the recommendations in real time, and means for collecting emotion data from facial expressions, voice, and text messages. This makes it possible to reflect the user's emotional state in real time and provide more personalized and sophisticated recommendations.

[1247] "User Information" is data including basic information (such as name, age, gender, and email address) and detailed profile information (such as eating habits, hobbies, work schedule, and health goals) provided by a user when signing up to the system.

[1248] A "database" is a data management structure within a system that records and stores user information, emotional data, and feedback information, and uses this information to perform data analysis and generate recommendations.

[1249] "Generative artificial intelligence (generative AI)" is an artificial intelligence technology that includes algorithms and models for generating new information and recommendations based on data.

[1250] "Artificial general intelligence (AGI)" is a general-purpose artificial intelligence system that can handle a wide range of tasks, not just specific ones, and is a technology for performing advanced analysis based on various user data.

[1251] "Emotion data" refers to data that indicates the user's emotional state collected in real time from facial expressions, voice, text messages, and the like.

[1252] "Features" are information extracted and quantified in data analysis, such as a user's behavioral patterns, preferences, and emotional state.

[1253] "Recommendations" refers to suggestions and advice customized for each user based on collected data and analysis results.

[1254] "Push notification" is a communication method in which information or alerts are automatically sent from a server to a device to notify the user.

[1255] "Feedback" refers to user-provided ratings and opinions on recommendations, data that the system uses to improve future suggestions.

[1256] "Emotion engine" refers to technology that recognizes and evaluates a user's emotional state in real time from their facial expressions, voice, and text messages.

[1257] This invention relates to a system for providing customized recommendations based on a user's lifestyle. In particular, by combining an emotion engine, it realizes proposals that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. The specific form of this system is described below.

[1258] Collection and management of user information

[1259] When a user signs up for the system, the device displays an input form on the screen to collect basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the server receives this information and records it in a database. The device then displays an additional form to enter detailed profile information (such as eating habits, hobbies, work schedule, and health goals), making it easier for the user to enter more information. This information is also sent to the server and stored in the database.

[1260] Emotion recognition by emotion engine

[1261] The emotion engine is built into the device and uses a camera and microphone to collect real-time emotion data from the user's facial expressions, voice, and text messages. The server receives this emotion data, evaluates the user's emotional state, and records it in a database. The emotion engine uses facial expression recognition technology and voice tone analysis technology.

[1262] Data analysis using AI models

[1263] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, preferences, and even emotional state are extracted. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[1264] Generating customized recommendations

[1265] The server generates personalized recommendations for each user based on the results of AI analysis and the output of the emotion engine. Specifically, meal suggestions provide menus based on the user's health goals and real-time emotional state. Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also include reminders and task management that take emotional state into account.

[1266] Presentation in the user interface

[1267] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[1268] Real-time feedback and adjustments

[1269] Users can provide feedback on recommendations on their devices, which collect and forward the feedback information to the server, which records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of future recommendations.

[1270] Specific examples

[1271] For example, User B registers with the system and provides the following information:

[1272] Name: User B

[1273] Age: 40

[1274] Gender: Male

[1275] Eating habits: Balanced diet

[1276] Hobbies: Reading, watching movies

[1277] Health goals: Stress management, improved sleep quality

[1278] When User B connects a wearable fitness tracker, the system uses emotion recognition to collect real-time emotional data. The server uses this data to learn User B's behavioral patterns. The generation AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "a relaxing breakfast menu for Monday mornings" and "the best time to read." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement them based on his emotional state. Providing feedback further improves the quality of the next recommendation. An example of this prompt might be, "Please suggest a relaxing breakfast menu."

[1279] Thus, by using the emotion engine, the system of the present invention provides sophisticated recommendations that take into account the user's emotional state, supporting an efficient and fulfilling daily life.

[1280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1281] Step 1:

[1282] The terminal displays a form for the user to enter basic information (such as name, age, gender, and email address). When the user enters this information and presses the submit button, the input data is sent from the terminal to the server. The server verifies the received user information and records it in a database. For example, it checks whether the name, age, and gender are in an existing database and registers the user as a new user.

[1283] Input: User basic information

[1284] Output: Verified user information is saved in the database

[1285] Step 2:

[1286] The device displays an additional form for entering detailed profile information (eating habits, hobbies, work schedule, health goals, etc.). After the user enters the details and presses the submit button, the input data is sent back to the server. The server receives it and stores it in a database as detailed profile information. This information is used for analysis by the generative AI and AGI.

[1287] Input: User's detailed profile information

[1288] Output: Detailed profile information is saved in the database

[1289] Step 3:

[1290] The device collects emotional data in real time using a camera and microphone. The emotion engine analyzes the user's facial expressions and voice and extracts their emotional state from text messages. The collected emotional data is sent from the device to a server. The server receives the data, evaluates the emotional state, and records it in a database.

[1291] Input: Real-time user facial expressions, voice, and text messages

[1292] Output: Real-time emotion data is stored in a database

[1293] Step 4:

[1294] The server uses the collected user information and emotional data to analyze the data using generative AI and AGI algorithms. At this stage, features based on the user's behavioral patterns, emotional state, and preferences are extracted. For example, it may become clear that a user is more likely to feel stressed on certain days of the week, or that certain foods improve their mood.

[1295] Input: User information, real-time emotion data

[1296] Output: Features related to behavioral patterns and emotional states

[1297] Step 5:

[1298] The server generates personalized recommendations based on the AI ​​analysis results and the output of the emotion engine. Specific suggestions include meal plans based on health goals and real-time emotional states, and entertainment content tailored to individual interests. The generated recommendations are then sent from the server to the device.

[1299] Input: Analysis results, emotion engine output

[1300] Output: Customized recommendations

[1301] Step 6:

[1302] The device receives the recommendations sent from the server and displays them to the user, who can then review the notifications and take specific actions, such as viewing recipes, choosing a movie, or performing a mindfulness exercise.

[1303] Input: Recommendation notification from the server

[1304] Output: The user initiates a specific action.

[1305] Step 7:

[1306] Users input feedback on recommendations on their devices. The devices then send the feedback information to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time based on that feedback. This improves the accuracy of the next recommendation.

[1307] Input: User feedback

[1308] Output: Update the AI ​​model based on the feedback

[1309] (Application example 2)

[1310] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] Conventional recommendation systems make recommendations based on a user's basic personal information and past behavioral history, but this lack of proposals that adequately reflect the user's real-time emotional state. As a result, recommendations cannot be tailored to the user's current mood or stress level, making it difficult to provide a more personalized service. It is also difficult to reflect user feedback in real time and readjust the system.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1313] In this invention, the server includes means for receiving user information and recording it in a database, means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information, emotion recognition means for recognizing the emotional state of the user, means for generating customized recommendations based on the analysis results and the emotion recognition results, means for notifying the generated recommendations to the user terminal, and means for receiving feedback from the user, recording it in the database, and adjusting the recommendations in real time, thereby enabling more personalized recommendations that are suited to the emotional state of the user.

[1314] The "means for receiving user information and recording it in a database" refers to a means for collecting basic information and detailed profile information of a user and storing it in a database.

[1315] "Generative artificial intelligence" is an artificial intelligence technology that can generate new data and patterns based on large amounts of data.

[1316] "General artificial intelligence" is an artificial intelligence technology with flexible intelligence that can handle a variety of tasks, not just specific ones.

[1317] "Means for analyzing data" refers to means for analyzing collected user information and extracting useful information and patterns.

[1318] The "emotion recognition means" is a means for analyzing the user's facial expressions and voice using a camera and microphone to recognize the user's emotional state in real time.

[1319] The "means for generating customized recommendations" refers to a means for generating advice and suggestions that are optimized for each user based on the analysis results and emotion recognition results.

[1320] The "means for notifying the user terminal of the generated recommendation" refers to a means for transmitting the generated recommendation to the terminal used by the user in the form of a push notification or the like.

[1321] "Means for receiving feedback, recording it in a database, and adjusting recommendations in real time" refers to means for collecting feedback from users and using that feedback to improve the accuracy of recommendations in real time.

[1322] The system of the present invention provides customized recommendations based on a user's lifestyle and combines an emotion engine to realize suggestions that take into account the user's emotional state. This system operates through a series of steps: collecting user information, emotion recognition, data analysis using generative artificial intelligence (generative AI) and artificial general intelligence (AGI), recommendation generation, notification, feedback collection, and real-time adjustment. A detailed embodiment of the system is described below.

[1323] Collection and management of user information

[1324] When a user signs up to the system, the device collects basic information (such as name, age, gender, and email address) and displays an input form on the screen. After the user enters the information and presses the submit button, the server verifies this information and records it in a database. The device then displays a form for the user to enter detailed profile information (such as eating habits, hobbies, and health goals), allowing the user to enter more information. This information is also sent to the server and stored in the database.

[1325] Emotion recognition by emotion engine

[1326] The device is equipped with an emotion engine that collects real-time emotional data from users' facial expressions, voice, text messages, etc. This data is collected using emotion recognition technology that utilizes cameras and microphones. The server receives this emotional data, evaluates the user's emotional state, and records it in a database.

[1327] Data analysis using AI models

[1328] The server analyzes the collected user information and emotional data using generative AI and AGI algorithms. This allows it to extract features based on the user's behavioral patterns, preferences, and even emotional state. For example, it can reveal whether a user is prone to stress on certain days of the week or whether certain foods improve their mood.

[1329] Generating customized recommendations

[1330] The server generates personalized recommendations for each user based on the AI ​​analysis results and the output of the emotion engine. Meal suggestions provide menus based on the user's health goals and real-time emotional state (e.g., stress reduction and relaxation). Entertainment suggestions recommend appropriate entertainment content based on the user's hobbies and emotional state. Time management suggestions also take emotional state into account for reminders and task management.

[1331] User interface presentation

[1332] The generated recommendations are sent to the user's device via push notification, which the device receives and displays. The user can then view the notification and take specific actions (e.g., view recipes, choose a movie, perform a mindfulness exercise, etc.).

[1333] Real-time feedback and adjustments

[1334] Users can provide feedback on recommendations on their devices. The devices collect the feedback information and forward it to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time to improve the accuracy of the next recommendation. This process allows the system to always provide the latest and most optimal suggestions.

[1335] Specific examples

[1336] User B newly registers with the system and provides the following information:

[1337] Name: User B

[1338] Age: 40

[1339] Gender: Male

[1340] Eating habits: Balanced diet

[1341] Hobbies: Reading, watching movies

[1342] Health goals: Stress management, improved sleep quality

[1343] When User B connects a wearable fitness tracker and the system uses the emotion recognition function to collect real-time emotional data, the server learns User B's behavioral patterns based on this data. The generative AI and AGI discover patterns such as "User B tends to feel stressed on Monday mornings" and "reading helps him relax." Based on this analysis, the server suggests to User B "breakfast menus that have a relaxing effect on Monday mornings" and "optimal times for reading." Furthermore, the emotion engine generates recommendations, including "relaxation exercises that User B should do when he feels stressed." User B can review these recommendations and implement the optimized suggestions based on his emotional state. Furthermore, by providing feedback, the quality of the next recommendation can be further improved.

[1344] Example prompts to input to a generative AI model:

[1345] User: 40-year-old male. Hobbies include reading and watching movies. His goals are stress management and improving sleep quality. He tends to feel stressed on Monday mornings. Please suggest a breakfast menu that will help him relax.

[1346] In this way, the system can provide more personalized recommendations based on the user's emotional state and lifestyle.

[1347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1348] Step 1:

[1349] When a user signs up for the system, the terminal displays a form for inputting basic information (such as name, age, gender, and email address). After the user enters the information and presses the submit button, the entered information is sent to the server. The server receives it, verifies it, and records it in a database. The input here is the user's basic information, and the output is the verified user information stored in the database.

[1350] Step 2:

[1351] The device then displays the form again for entering detailed profile information (e.g., eating habits, hobbies, health goals, etc.). The user enters additional information and presses the submit button, which again sends the details to the server. The server receives the submitted details and stores them in a database. The input here is the detailed profile information, and the output is the details stored in the database.

[1352] Step 3:

[1353] Users collect emotional data using wearable devices or smartphones. This involves using a camera and microphone to recognize emotional states by analyzing facial expressions, voice, and text messages. The device processes this data in real time using an emotion engine and sends the emotional data to a server. The input is the collected emotional data, and the output is the emotional state data sent to the server.

[1354] Step 4:

[1355] The server uses generative AI and general-purpose AI algorithms to analyze the collected user information and emotional data. During this process, it extracts features based on the user's behavioral patterns, preferences, and emotional state. The input is the user information and emotional data stored in the database, and the output is the analysis of the user's behavioral patterns and emotional state.

[1356] Step 5:

[1357] The server generates customized recommendations based on the analysis results and emotion recognition data. For example, it suggests meal menus based on the user's health goals and real-time emotional state, or entertainment content based on their hobbies. The input is the analysis results and emotion data, and the output is customized recommendations.

[1358] Step 6:

[1359] The generated recommendations are sent from the server to the user's device via push notification. The device receives the notification and displays the recommendations to the user. The user checks the notification and takes specific actions (e.g., looking at recipes, choosing a movie, performing a mindfulness exercise, etc.). The input here is the generated recommendations, and the output is the display to the user.

[1360] Step 7:

[1361] The user provides feedback on the provided recommendations. The device collects the feedback information and sends it back to the server. The server records the received feedback in a database and updates the generative AI and AGI models in real time, thereby improving the accuracy of the next recommendation. The input is the feedback information from the user, and the output is the model and database updated in real time.

[1362] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1363] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1364] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1365] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1366] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1367] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1368] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1369] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1370] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1371] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1372] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1373] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1374] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1375] 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.

[1376] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1377] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1378] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1379] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1380] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1381] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1382] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1383] The following is further disclosed regarding the above embodiment.

[1384] (Claim 1)

[1385] means for receiving and recording user information in a database;

[1386] A means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information;

[1387] a means for generating customized recommendations based on the analysis results;

[1388] a means for notifying a user terminal of the generated recommendation;

[1389] A means of receiving and recording user feedback in a database to adjust recommendations in real time; and

[1390] A system including:

[1391] (Claim 2)

[1392] 10. The system of claim 1, which suggests meal menus based on health goals.

[1393] (Claim 3)

[1394] 10. The system of claim 1, wherein entertainment suggestions are made based on the user's interests.

[1395] "Example 1"

[1396] (Claim 1)

[1397] means for receiving and recording user information in a database;

[1398] a means for displaying a form for inputting detailed profile information and recording the details in a database;

[1399] means for receiving and recording activity data from the wearable device;

[1400] a means for integrating the received user information and activity data and analyzing the data using generative artificial intelligence and general artificial intelligence;

[1401] a means for generating customized recommendations based on the analysis results;

[1402] a means for notifying a user terminal of the generated recommendation;

[1403] A means for receiving user feedback, recording it in a database, and updating the generative artificial intelligence and general artificial intelligence models in real time to reflect it in the next recommendation;

[1404] A system including:

[1405] (Claim 2)

[1406] 10. The system of claim 1, which suggests meal menus based on health goals.

[1407] (Claim 3)

[1408] 10. The system of claim 1, wherein entertainment suggestions are made based on the user's interests.

[1409] "Application Example 1"

[1410] (Claim 1)

[1411] means for receiving and recording user information in a database;

[1412] A means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information;

[1413] a means for generating customized recommendations based on the analysis results;

[1414] a means for notifying a user terminal of the generated recommendation;

[1415] A means of receiving and recording user feedback in a database to adjust recommendations in real time; and

[1416] a means for receiving health data obtained from a smart device, using the data to assess health status, and suggesting related products and services through electronic payment;

[1417] A system including:

[1418] (Claim 2)

[1419] The system of claim 1, wherein the system suggests a meal menu based on health goals and generates online purchasing links for foods and ingredients associated with the suggested meal menu.

[1420] (Claim 3)

[1421] 10. The system of claim 1, wherein the system provides entertainment suggestions based on the user's interests and provides service collaboration including reservations and payments for the suggested entertainment activities.

[1422] "Example 2: Combining Emotion Engines"

[1423] (Claim 1)

[1424] means for receiving and recording user information in a database;

[1425] A means for analyzing data using a generative artificial intelligence and a general artificial intelligence using the received user information and emotion data collected in real time;

[1426] a means for generating customized recommendations based on the analysis results;

[1427] A means for notifying a user of the generated recommendation on the user's terminal;

[1428] A means of receiving and recording user feedback in a database to adjust recommendations in real time; and

[1429] A means of collecting emotional data from facial expressions, voice, and text messages;

[1430] A system including:

[1431] (Claim 2)

[1432] 10. The system of claim 1, wherein the system suggests meal menus based on health goals and real-time emotional state.

[1433] (Claim 3)

[1434] 10. The system of claim 1, wherein entertainment suggestions are based on the user's hobbies and emotional state.

[1435] "Application example 2 when combining emotion engines"

[1436] Rewrite

[1437] (Claim 1)

[1438] means for receiving and recording user information in a database;

[1439] A means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information;

[1440] emotion recognition means for recognizing an emotional state of a user;

[1441] means for generating customized recommendations based on the analysis results and emotion recognition results;

[1442] a means for notifying a user terminal of the generated recommendation;

[1443] A means of receiving and recording user feedback in a database to adjust recommendations in real time; and

[1444] A system including:

[1445] (Claim 2)

[1446] 10. The system of claim 1, wherein the system suggests meal menus based on health goals and real-time emotional state.

[1447] (Claim 3)

[1448] 10. The system of claim 1, wherein entertainment suggestions are based on the user's hobbies and emotional state. [Explanation of symbols]

[1449] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving and recording user information in a database; A means for analyzing data using generative artificial intelligence and general artificial intelligence using the received user information; a means for generating customized recommendations based on the analysis results; a means for notifying a user terminal of the generated recommendation; A means of receiving and recording user feedback in a database to adjust recommendations in real time; and A system including:

2. The system of claim 1 , wherein the system suggests meal menus based on health goals.

3. The system of claim 1, wherein entertainment suggestions are made based on the user's interests.

Images