System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting lifestyle data of a user; means for analyzing the collected lifestyle data; means for generating a personalized recommendation based on the analysis; means for notifying the user of the generated recommendation; and means for modifying the recommendation based on user feedback.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 modern society, many people seek to live healthier and more efficient lives, but it is difficult to obtain specific advice to achieve these goals. While there are many commercially available health management devices, they are specialized for individual functions and do not improve overall quality of life. Furthermore, existing devices do not adequately adjust their advice based on user feedback. Therefore, there is a need for a system that can support users' overall lifestyles and provide specific advice tailored to their individual needs. [Means for solving the problem]

[0005] The present invention provides a system including means for collecting a user's lifestyle data, means for analyzing the collected lifestyle data, means for generating personalized suggestions based on the analysis results, means for notifying the user of the generated suggestions, and means for revising the suggestions based on the user's feedback. In particular, the system collects data on the user's daily activities, eating habits, exercise history, and hobbies, and uses artificial intelligence for the analysis to generate appropriate suggestions. The system also notifies the user of the suggestions via voice and analyzes the user's feedback to regenerate the suggestions, thereby providing personalized support tailored to the user's needs. The system also includes means for making restaurant reservations based on the analysis results and means for tracking the implementation of the suggestions and providing appropriate feedback. This allows users to easily make healthy choices in their daily lives and achieve a higher quality of life.

[0006] A "user" is someone who uses the system and provides their lifestyle data.

[0007] "Lifestyle data" is information about a user's daily activities, eating habits, exercise history, hobbies, etc.

[0008] "Means" refers to methods, devices, software, algorithms, etc. for achieving a specific purpose.

[0009] "Collecting" refers to the process of obtaining and recording data.

[0010] "Analyzing" means processing collected data and understanding its meaning and trends.

[0011] "Suggestions" are specific actions or options provided to users based on the analysis results.

[0012] "Notifying" refers to the act of informing the user of the proposed content.

[0013] "Feedback" refers to the response or reply that a user gives to a suggestion.

[0014] "Modify" refers to changing a proposal based on feedback.

[0015] "Artificial intelligence" refers to advanced computer programming techniques used to analyze data and generate recommendations.

[0016] The "Internet" is a communications network that connects computer networks around the world.

[0017] A "server" is a computer system that manages data, performs calculations, and communicates with terminals.

[0018] A "terminal" is a device that a user directly operates and that communicates with a server. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention is a system that collects and analyzes a user's lifestyle data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. The system includes programs for executing the processes of collection, analysis, suggestion, notification, and feedback.

[0041] 1. Collection of lifestyle data

[0042] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0043] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[0044] For example, if a user logs the contents of their meal on a smartphone app, the data is automatically sent from the device to the server.

[0045] 2. Data Analysis

[0046] The server analyzes the life data sent from the device.

[0047] This analysis uses artificial intelligence to extract insights and trends from user data.

[0048] For example, it analyzes a user's dietary history to determine whether their nutritional balance is unbalanced.

[0049] 3. Proposal Generation

[0050] The server generates personalized offers based on the analysis results.

[0051] Suggestions include exercise plans and dietary advice to help manage your health, as well as support on how to enjoy hobbies.

[0052] For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to get more vegetables."

[0053] 4. Notification of Proposal

[0054] The terminal notifies the user of the proposal received from the server.

[0055] Notifications are delivered via audio, allowing users to actually interact with the device.

[0056] For example, the device might say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[0057] 5. User Feedback

[0058] Users provide feedback on the suggestions.

[0059] The feedback is sent to the server through the device.

[0060] For example, a user might provide feedback like, "The salad sounds good, but can you recommend a dressing?"

[0061] 6. Proposal Modifications

[0062] The server then modifies the suggestions based on user feedback.

[0063] The revised suggestions will be notified to the user again via the device.

[0064] For example, the server reproduces the content "We recommend olive oil and lemon dressing for your salad," and the terminal notifies this.

[0065] As a specific example, consider the following case.

[0066] Specific examples

[0067] Meal suggestion examples

[0068] 1. Data Collection

[0069] A user logs into a smartphone app, "I had pizza for dinner last night."

[0070] 2. Data Analysis

[0071] The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.).

[0072] 3. Proposal generation

[0073] The server generates a suggestion like, "Since you had pizza yesterday, we recommend you choose a salad today to get more vegetables."

[0074] 4. Proposal Notice

[0075] The device will announce in a voice message, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[0076] 5. User Feedback

[0077] The user replies, "Salad sounds good, but can you recommend a dressing?"

[0078] 6. Proposal modification

[0079] The server corrects the suggestion to "I recommend olive oil and lemon dressing for the salad" and notifies again.

[0080] This allows users to easily make balanced dietary choices, and by repeating this cycle, the accuracy of the suggestions will improve, allowing for more useful advice to be provided to users.

[0081] The processing flow will be explained below.

[0082] Step 1:

[0083] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[0084] Step 2:

[0085] The device sends the collected lifestyle data to a server, and the device uploads log data to the server via the Internet. This data includes meal contents, meal times, and meal amounts.

[0086] Step 3:

[0087] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and also references past data to evaluate the user's nutritional intake balance.

[0088] Step 4:

[0089] The server generates a suggestion based on the analysis results, such as "Since you ate pizza yesterday, we recommend you choose a salad today to get more vegetables."

[0090] Step 5:

[0091] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[0092] Step 6:

[0093] The device will notify the user of the received suggestion by voice. The device will notify, "Since you had pizza yesterday, I recommend you eat a salad today. What do you think?" The user can listen to the suggestion by voice.

[0094] Step 7:

[0095] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[0096] Step 8:

[0097] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[0098] Step 9:

[0099] The server modifies the suggestion based on the user's feedback. The server regenerates the suggestion, "I recommend olive oil and lemon dressing for your salad," and sends it to the device.

[0100] Step 10:

[0101] The device will then re-promote the revised suggestion to the user, saying, "We recommend olive oil and lemon dressing on your salad."

[0102] Through these steps, the Audio Glasses system provides users with continuously optimized health advice to improve the quality of their daily lives.

[0103] Example 1

[0104] 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."

[0105] In today's busy lifestyles, supporting users in managing their health and improving their lifestyles requires suggestions tailored to their individual circumstances. However, conventional systems do not adequately analyze the data collected from users, resulting in insufficient individualization of suggestions and insufficient reflection of feedback. This makes it difficult to provide effective support for users in managing their health and improving their lifestyles, and reduces the accuracy and usefulness of suggestions.

[0106] 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.

[0107] In this invention, the server includes a means for collecting user lifestyle data, a means for storing the collected lifestyle data in a database, a means for analyzing the lifestyle data using an artificial intelligence model to extract insights, and a means for personalizing suggestions based on the user's preferences and behavioral data, thereby enabling highly accurate personalized suggestions to be provided to the user and for suggestions to be revised based on feedback.

[0108] "User" refers to an individual who uses this system.

[0109] "Lifestyle Data" refers to data including information about a user's daily activities, eating habits, exercise history, and hobbies.

[0110] "Means of collection" refers to the devices and applications used to collect users' lifestyle data.

[0111] "Means of storage" refers to the means for storing collected lifestyle data in a database or the like.

[0112] "Means of analysis" refers to artificial intelligence and data processing technologies used to analyze collected lifestyle data and extract insights and trends.

[0113] "Means for generating suggestions" refers to means for creating suggestions suitable for the user based on the analysis results.

[0114] "Means for notifying suggestions" refers to means for notifying a user of generated suggestions.

[0115] "Means for modifying suggestions based on feedback" refers to means for analyzing user feedback and modifying suggestions based on the results of that analysis.

[0116] "Database" refers to a system for storing and managing collected lifestyle data.

[0117] "Artificial intelligence model" refers to the machine learning models and algorithms used to analyze life data, extract insights, and generate recommendations.

[0118] "Means of extracting insights" refers to techniques for finding important information and trends from analyzed data.

[0119] "Personalization" refers to customizing recommendations based on a user's specific preferences and behavior.

[0120] The present invention is a system that collects and analyzes users' life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. Specific embodiments are described below.

[0121] 1. Collection of lifestyle data

[0122] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies. Data collection is done through devices such as smartphone apps, smartwatches, and fitness trackers. For example, when a user enters their meal history into a smartphone app, the data is automatically sent from the device to a server.

[0123] 2. Data storage

[0124] The server stores the lifestyle data sent from the device in a database for later analysis. For example, the server stores a user's exercise history for one week in a database.

[0125] 3. Data Analysis

[0126] The server analyzes the stored lifestyle data. This analysis uses artificial intelligence (generative AI models) to extract insights and trends from the data. For example, it can determine whether a user's nutritional balance is unbalanced based on their dietary history.

[0127] 4. Proposal Generation

[0128] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[0129] 5. Notification of Proposal

[0130] The device notifies the user of the suggestions received from the server. The notification is done through voice, so the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[0131] 6. User Feedback

[0132] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[0133] 7. Proposal Modifications

[0134] The server then modifies the suggestions based on the user's feedback. The modified suggestions are then sent to the user via the device. For example, the server might regenerate a suggestion such as "We recommend olive oil and lemon dressing for your salad," and the device would then notify the user.

[0135] Specific examples

[0136] For example, suppose a user logs into a smartphone app that they "ate pizza for dinner yesterday." The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.). As a result, the server generates a suggestion such as, "Since you ate pizza yesterday, I recommend you choose a salad today to get more vegetables." The device then notifies the user by voice, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?" The user responds, "Salads sound good, but could you also recommend a dressing?" Based on this feedback, the server modifies the suggestion to, "I recommend olive oil and lemon dressing for the salad," and notifies them again.

[0137] Prompt Sentence Examples

[0138] "Please explain how to build a system that collects and analyzes lifestyle data and generates optimal health management suggestions for users."

[0139] "Please give us a concrete example of a system that collects and analyzes food logs and provides personalized meal suggestions."

[0140] This invention allows users to easily choose a balanced diet and adopt healthy lifestyle habits. Furthermore, by repeating this cycle, the accuracy of the suggestions will improve, making it possible to provide more useful advice to users.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1: Collecting lifestyle data

[0143] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0144] Input: Data recorded by users via smartphone apps, smartwatches, and fitness trackers.

[0145] What it does: The phone receives data from these devices via Bluetooth or Wi-Fi and stores it in a formatted form on its internal memory.

[0146] Output: The collected user lifestyle data is temporarily stored on the device.

[0147] Step 2: Send the data log

[0148] The terminal transmits the collected data to the server in real time.

[0149] Input: Life data stored on the device.

[0150] How it works: The device sends life data to the server at regular intervals or when the data is updated. Data transfer is encrypted and protected using the HTTPS protocol.

[0151] Output: The collected data is transferred to the server.

[0152] Step 3: Save your data

[0153] The server stores the received data in a database.

[0154] Input: Life data sent from the device.

[0155] Specific operation: The server stores the received data using a database management system (e.g., MySQL or PostgreSQL). The data integrity is checked and invalid data is removed.

[0156] Output: Life data is accurately stored in the database.

[0157] Step 4: Preprocessing the data

[0158] The server cleans the collected data and converts it into a format suitable for analysis.

[0159] Input: Life data stored in a database.

[0160] What it does: The server imputes missing values ​​from the data, removes noise, and normalizes the data, for example, correcting anomalous numerical data and encoding categorical data.

[0161] Output: A preprocessed and clean dataset.

[0162] Step 5: Analyze the data

[0163] The server uses the pre-processed data to analyze it using a generative AI model.

[0164] Input: Preprocessed lifestyle dataset.

[0165] Specific operation: The server inputs data into a machine learning model (e.g., a deep learning model) and performs analysis, thereby extracting trends in the user's behavioral patterns and health status.

[0166] Output: The insights and trends extracted as a result of the analysis.

[0167] Step 6: Generate proposals

[0168] The server generates personalized offers based on the analysis results.

[0169] Input: Insights and trends based on analytical results.

[0170] Specific operation: The server uses a proposal generation algorithm to create specific proposals that will help the user manage their health and improve their lifestyle. For example, a proposal might be generated such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[0171] Output: The individual suggestions generated.

[0172] Step 7: Prepare your proposal

[0173] The server formats the proposals to be sent to the user and converts them into a format that can be sent to the terminal.

[0174] Input: Generated suggestions.

[0175] Specific operation: The proposal content is converted into natural language that is easy for the user to understand, and speech synthesis data is also prepared if necessary.

[0176] Output: Formatted proposal data.

[0177] Step 8: Sending notifications

[0178] The device notifies the user of the received proposal.

[0179] Input: Formatted proposal data.

[0180] What it does: The device notifies the user of the suggestion using voice or text message, for example, "You had pizza yesterday, so I suggest you have a salad today."

[0181] Output: The suggestion that was notified to the user.

[0182] Step 9: Accepting feedback

[0183] Users provide feedback on the suggestions.

[0184] Input: User response based on suggestions.

[0185] What happens: The user provides feedback via voice or text, such as a request like, "The salad is great, but can you recommend a dressing?"

[0186] Output: User feedback data.

[0187] Step 10: Submit your feedback

[0188] The device sends the feedback from the user to the server.

[0189] Input: User feedback data.

[0190] Specific operation: The terminal sends feedback data to the server using the HTTPS protocol.

[0191] Output: Feedback data sent to the server.

[0192] Step 11: Analyze feedback

[0193] The server analyzes the received feedback to help refine the proposal.

[0194] Input: User feedback data.

[0195] Specific operation: The server uses natural language processing technology to analyze the content of the feedback and extract the user's requests and comments.

[0196] Output: Insights for revision based on feedback.

[0197] Step 12: Modifying the proposal

[0198] The server then modifies the suggestions based on user feedback.

[0199] Input: Insights based on feedback.

[0200] What happens: The server reapplies the suggestion generation algorithm to create a new suggestion that reflects the user's requests and comments, e.g., "I recommend olive oil and lemon dressing for salads."

[0201] Output: The revised proposal.

[0202] Step 13: Send a reminder

[0203] The device will notify the user again with the revised suggestions.

[0204] Input: Revised proposal.

[0205] What happens: The device notifies the user using voice or text message with the revised suggestion, for example, reminding them, "We recommend olive oil and lemon dressing on your salad."

[0206] Output: The suggestion that was snoozed to the user.

[0207] (Application example 1)

[0208] 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."

[0209] In modern society, health management tailored to individual lifestyles and eating habits is considered important, but there is a problem in that generic health suggestions cannot meet the different needs of each user. In particular, the lack of specific suggestions for dietary habits makes it difficult for individual users to maintain appropriate eating habits. In addition, the lack of advice on specific seasonings and ingredient selection for meals makes it difficult for users to eat a diet that suits their own health condition.

[0210] 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.

[0211] In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual suggestions based on the analysis results, means for notifying the user of the generated suggestions, means for modifying the suggestions based on the user's feedback, means for generating and notifying specific meal suggestions based on the lifestyle data, and means for analyzing the feedback content selected by the user based on the suggestions and suggesting seasonings suitable for the meal menu. This enables users to receive optimal health management and specific meal suggestions tailored to their individual lifestyles and eating habits.

[0212] "User lifestyle data" refers to information related to a user's daily activities, eating habits, exercise history, hobbies, etc.

[0213] "Means of collection" refers to devices and methods for obtaining and recording users' lifestyle data.

[0214] "Means for analysis" refers to systems and methods for processing collected lifestyle data and extracting useful information and trends.

[0215] "Means for generating recommendations" refers to a process or device that generates personalized advice or recommendations based on the results of the analysis.

[0216] "Means for notifying suggestions" refers to the functions and devices used to communicate the generated suggestions to users.

[0217] "Means for revising suggestions" refers to a method or system for revising existing suggestions based on user feedback.

[0218] "Specific meal suggestions" refers to advice recommending specific ingredients and menus based on the user's lifestyle data.

[0219] The "means for suggesting seasonings" refers to a function or method for providing seasonings and seasoning methods suitable for the proposed meal menu.

[0220] The present invention is a system that collects and analyzes users' lifestyle data, and generates, notifies, and modifies personalized suggestions based on that data. Specifically, the system is comprised of the following processes:

[0221] 1. System Programming

[0222] The system has the following main program flow:

[0223] Collection of lifestyle data

[0224] Devices (such as smartphones, smartwatches, and fitness trackers) collect data about users' daily activities, eating habits, exercise history, and hobbies. For example, a user logs in a smartphone app that they "ate pizza for dinner last night." This data is then sent from the device to a server.

[0225] Data analysis

[0226] The server receives and analyzes the lifestyle data sent from the device. This analysis uses a generative AI model to extract insights and trends from the user's lifestyle data. For example, it can evaluate the nutritional content (calories, fat, carbohydrates, etc.) of a pizza to determine whether it is nutritionally unbalanced.

[0227] Proposal Generation

[0228] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, a suggestion might be, "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[0229] Proposal Notification

[0230] The device notifies the user of the suggestions received from the server. The notification is done through voice, and the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[0231] User Feedback

[0232] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[0233] Proposal amendments

[0234] The server then modifies the suggestions based on the user's feedback, and the modified suggestions are then sent to the user via the device. For example, the server might regenerate the suggestion, "We recommend olive oil and lemon dressing for your salad," and the device would notify the user.

[0235] 2. Hardware and Software Used

[0236] This system uses the following hardware and software:

[0237] Smartphone: A device for inputting user data (such as meal contents).

[0238] Server: Analyzes data, generates suggestions, and manages feedback.

[0239] Generative AI models: Used to analyze data and generate recommendations.

[0240] For example: Machine learning libraries such as TensorFlow, Keras, etc.

[0241] 3. Examples and prompts

[0242] If a user inputs "I had pizza for dinner last night," the system will proceed as follows: The server will analyze the nutritional information (calories, fat, carbohydrates, etc.) of the pizza and generate a suggestion, for example using the following prompt:

[0243] Example prompt sentence:

[0244] The user ate pizza yesterday. It was high in calories, so we recommend a meal with lots of vegetables today.

[0245] The system provides users with specific and personalized suggestions for living a healthy life, enabling them to receive optimal health management tailored to their individual lifestyles and eating habits.

[0246] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0247] Step 1:

[0248] The user enters meal information into the app.

[0249] Input: The user enters meal details (e.g., "I had pizza for dinner last night") into a smartphone app.

[0250] Processing: The smartphone app sends the entered meal information to the server.

[0251] Output: The server receives the meal data and stores it in a database.

[0252] Step 2:

[0253] The server analyzes lifestyle data.

[0254] Input: The server retrieves the user's lifestyle data from the database.

[0255] Processing: The server analyzes the acquired data using a generative AI model. Specifically, it evaluates nutritional components (calories, fat, carbohydrates, etc.) and determines the user's nutritional balance.

[0256] Output: A report is generated based on the analysis results, which contains details of the user's nutritional balance.

[0257] Step 3:

[0258] The server generates personalized offers.

[0259] Input: Analysis results (report)

[0260] Processing: The server uses the generative AI model based on the analysis results to create personalized meal recommendations, such as "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[0261] Output: The generated proposal is added to the notification queue.

[0262] Step 4:

[0263] The device will notify the user of the suggestion.

[0264] Input: Notification queue proposal data

[0265] Processing: The smartphone app will notify the user of the suggestion by voice, for example, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[0266] Output: The user receives the suggestions aloud.

[0267] Step 5:

[0268] Users provide feedback.

[0269] Input: User feedback on the suggestion (e.g., "The salad sounds good, but could you recommend a dressing?")

[0270] Processing: The user enters feedback via the smartphone app and sends it to the server.

[0271] Output: The feedback data is received by the server and added to the feedback queue.

[0272] Step 6:

[0273] The server modifies the proposal based on the feedback.

[0274] Input: Feedback data

[0275] Processing: The server analyzes the feedback data and uses a generative AI model to refine the suggestions, for example, creating a new suggestion such as "I recommend olive oil and lemon dressing for your salad."

[0276] Output: The revised proposal is added back to the notification queue.

[0277] Step 7:

[0278] The device will notify the user again with the revised suggestion.

[0279] Input: Proposed correction data

[0280] Action: The smartphone app will re-announce the suggested revision to the user, for example, "We recommend olive oil and lemon dressing for your salad."

[0281] Output: The user receives the revised suggestion aloud.

[0282] 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.

[0283] The present invention is a system that collects and analyzes users' daily life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. This system also combines an emotion engine that recognizes users' emotions to provide more appropriate and personalized suggestions to users.

[0284] 1. Collection of lifestyle data

[0285] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0286] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[0287] For example, if a user logs the contents of their meal in a smartphone app, the data is sent from the device to a server.

[0288] 2. Collecting Emotional Data

[0289] The device utilizes an emotion engine to collect user emotion data.

[0290] The emotion engine uses cameras, microphones, biometric sensors, etc. to analyze the user's facial expressions, tone of voice, heart rate, etc. to identify their emotional state.

[0291] For example, while a user is using a smartphone app, the camera captures their facial expressions, and based on that, the emotion engine recognizes emotions such as "joy," "anger," and "sadness."

[0292] 3. Data Analysis

[0293] The server analyzes the lifestyle data and emotion data sent from the device.

[0294] The analysis uses artificial intelligence algorithms to extract insights and trends from user data.

[0295] For example, it analyzes a user's eating history and emotional data to assess the impact that a particular meal has on the user's emotions.

[0296] 4. Proposal Generation

[0297] The server generates personalized offers based on the analysis results.

[0298] Suggestions include exercise plans, dietary advice, and help with hobbies to help you manage your health, and the app also adjusts the suggestions based on your emotional state.

[0299] For example, it generates specific suggestions such as, "Since you ate pizza yesterday, we recommend that you choose a salad today to get more vegetables."

[0300] 5. Notification of Proposal

[0301] The terminal notifies the user of the proposal received from the server.

[0302] Notifications are delivered via audio, allowing users to actually interact with the device.

[0303] For example, the device may say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[0304] 6. User Feedback

[0305] Users provide feedback on the suggestions.

[0306] The feedback is sent to the server through the device.

[0307] For example, a user might provide feedback such as, "The salad is good, but can you recommend a dressing?"

[0308] 7. Proposal Modifications

[0309] The server then refines the suggestions based on user feedback and sentiment data.

[0310] The revised suggestions will be notified to the user again via the device.

[0311] For example, the server may modify the content to say, "We recommend olive oil and lemon dressing for your salad," and the terminal will notify you of this.

[0312] As a specific example, consider the following case.

[0313] Specific examples

[0314] Meal suggestion examples

[0315] 1. Data Collection

[0316] When a user logs into a smartphone app saying, "I had pizza for dinner last night," the device's facial recognition camera detects that the user is smiling, and the emotion engine then uses that information to identify the user.

[0317] 2. Data Analysis

[0318] The server analyzes this data and evaluates the pizza's nutritional content (calories, fat, carbohydrates, etc.), taking into account the user's happy emotions after eating the pizza.

[0319] 3. Proposal generation

[0320] The server generates a suggestion: "You seemed happy eating pizza yesterday, so today I suggest you eat more vegetables for a healthy balance."

[0321] 4. Proposal Notice

[0322] The device will announce in a voice message, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific dressing suggestions?"

[0323] 5. User Feedback

[0324] The user responds, "Please also tell me what dressing you would recommend to go with the salad," and the device sends this feedback to the server.

[0325] 6. Proposal modification

[0326] The server amends the suggestion to "The salad would benefit from a little olive oil and lemon dressing" and sends it to the terminal again.

[0327] Through this system, users will receive healthy suggestions that take their emotional data into account, allowing them to make choices that better suit their lifestyle.

[0328] The processing flow will be explained below.

[0329] Step 1:

[0330] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[0331] Step 2:

[0332] The device uses a camera, microphone, and biometric sensors to analyze the user's facial expressions, tone of voice, and heart rate using an emotion engine, for example, to detect if the user is smiling after eating pizza.

[0333] Step 3:

[0334] The device sends the collected lifestyle data and emotional data to a server, which then uploads the log data and emotional data to the server via the Internet.

[0335] Step 4:

[0336] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and analyze the user's emotional state. It also refers to past data to evaluate the relationship between the user's nutritional balance and their emotions.

[0337] Step 5:

[0338] The server generates recommendations based on the analysis results, such as "You seemed happy after eating pizza yesterday, so I recommend you eat more vegetables today to achieve a healthy balance."

[0339] Step 6:

[0340] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[0341] Step 7:

[0342] The device will notify the user of the received suggestions via voice. The device will say, "Since you had pizza yesterday, I recommend you have a salad today. Would you like some specific suggestions on dressings?" The user can listen to the suggestions via voice.

[0343] Step 8:

[0344] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[0345] Step 9:

[0346] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[0347] Step 10:

[0348] The server then modifies the suggestion based on the user's feedback and sentiment data, resending it to "You might want to use a little olive oil and lemon dressing on your salad" and sending it back to the device.

[0349] Step 11:

[0350] The device then notifies the user again with the revised suggestion, saying, "We recommend olive oil and lemon dressing on your salad." The user accepts and implements this suggestion.

[0351] Through these steps, the audio glasses system can provide users with continuously optimized health advice to improve the quality of their daily lives, and by combining it with an emotion engine, it can make suggestions based on the user's emotional state, providing more personalized support.

[0352] Example 2

[0353] 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."

[0354] Many modern personalized health management and lifestyle recommendation systems collect and use user lifestyle data to make recommendations. However, these systems do not take into account the user's emotional data, and recommendations may not match the user's emotional state. As a result, there are problems with low user acceptance and satisfaction. Furthermore, conventional systems are unable to properly reflect user feedback, limiting the accuracy and effectiveness of recommendations. To solve these issues, a system is needed that collects and analyzes not only the user's lifestyle data but also their emotional data, and generates and modifies recommendations based on that data.

[0355] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user life data and emotional data, means for analyzing the collected life data and emotional data, means for generating personalized proposals based on the analysis results, means for notifying the user of the generated proposals, and means for modifying the proposals based on the user's feedback and emotional data. This makes it possible to provide personalized proposals that match the user's emotional state, thereby improving user satisfaction and proposal acceptance. Furthermore, by reflecting user feedback, the accuracy and effectiveness of the proposals can be further improved.

[0356] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[0357] "Emotional data" is information used to analyze a user's facial expressions, tone of voice, heart rate, etc., to identify emotional states such as joy, anger, and sadness.

[0358] "Means of collection" refers to the methods of obtaining data using devices such as smartphones, smartwatches, and fitness trackers.

[0359] "Means of analysis" refers to the use of artificial intelligence algorithms to analyze collected data and extract insights and trends.

[0360] "Means for generating recommendations" refers to a method for generating personalized health management and lifestyle recommendations based on the analysis results.

[0361] The "notification method" is the method for notifying the user of the generated suggestions, such as by voice or text message.

[0362] "Means to modify suggestions" refers to ways to improve existing suggestions based on user feedback and additional sentiment data.

[0363] The present invention is a set of systems that collect and analyze users' life data and emotional data, generate and notify personalized suggestions, and modify these suggestions based on users' feedback and emotional data. The system further incorporates an emotional engine to provide more appropriate and personalized suggestions to users.

[0364] In order to implement this system, the following specific means are used.

[0365] 1. Collection of lifestyle and emotional data

[0366] The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data on users' daily activities, dietary habits, exercise history, and hobbies. Furthermore, the device utilizes an emotion engine to analyze the user's facial expressions, tone of voice, heart rate, and other data using cameras, microphones, and biometric sensors to identify their emotional state.

[0367] For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," the data is sent from the device to the server. At the same time, the camera captures the user's face, and the emotion engine detects "happiness."

[0368] 2. Data Analysis

[0369] The server analyzes the lifestyle and emotional data sent from the device, using artificial intelligence algorithms to extract insights and trends from the user's data.

[0370] For example, the server receives the log "I had pizza for dinner last night" and the "pleasure" data from the emotion engine, and analyzes these data using a human artificial intelligence algorithm to evaluate the impact that a particular meal has on the user's emotions.

[0371] 3. Proposal Generation

[0372] The server generates personalized recommendations based on the analysis, including exercise plans and dietary advice to help manage your health, tailored based on your emotional state.

[0373] For example, the server generates a suggestion such as, "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, the suggestion includes a detailed suggestion such as, "I recommend a salad today."

[0374] 4. Notification of Proposal

[0375] The device notifies the user of the suggestions it receives from the server, and the notification is done via voice, allowing the user to actually interact with the device.

[0376] For example, the device might say to the user, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific suggestions for dressing?"

[0377] 5. User Feedback

[0378] The user provides feedback on the suggestions, which is sent to the server via the device.

[0379] For example, the user might respond, "The salad is good, but could you recommend a dressing?" and the device would send this feedback to the server.

[0380] 6. Proposal Modifications

[0381] The server then modifies the suggestions based on the user's feedback and emotional data, and the modified suggestions are then sent back to the user via their device.

[0382] For example, the server might revise the suggestion to, "You might want to use a little olive oil and lemon dressing on the salad," and the device would reiterate this aloud.

[0383] Through this system, users can receive healthy suggestions that take into account their emotional data and make choices that better suit their lifestyle.

[0384] Examples of prompt statements

[0385] "You logged that you had pizza for dinner yesterday. What suggestions would you generate and how would you notify me? Also, explain how you would refine the suggestions based on user feedback."

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1: Collecting lifestyle and emotional data

[0388] Description: The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data about a user's daily activities, eating habits, exercise history, and hobbies.

[0389] Input: Data about the user's daily activities, eating habits, exercise history, and hobbies.

[0390] Data Processing: Collected data is aggregated from each device in a centralized format.

[0391] Output: Centralized lifestyle data.

[0392] Specific operation: For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," that data is sent from the device to the server. The device then uses an emotion engine and a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[0393] Step 2: Sending data

[0394] Description: The device sends the collected life data and emotion data to the server.

[0395] Input: Centralized life and emotion data.

[0396] Data processing: None in particular.

[0397] Output: The data sent to the server.

[0398] Specific operation: The device sends the log "I had pizza for dinner yesterday" and the emotion data "joy" to the server.

[0399] Step 3: Analyze the data

[0400] Description: The server analyzes the life data and emotion data sent from the device.

[0401] Input: Life data and emotion data.

[0402] Data processing: Using artificial intelligence algorithms to extract insights and trends from data.

[0403] Output: Analysis results.

[0404] Specific operation: The server uses the log of "I had pizza for dinner yesterday" and the emotion data of "happiness" to evaluate the impact of the user's eating habits on their emotions.

[0405] Step 4: Generate proposals

[0406] Description: The server generates personalized offers based on the analysis results.

[0407] Input: Analysis results.

[0408] Data processing: Based on the analysis results, health management and lifestyle suggestions are created.

[0409] Output: Individual proposals.

[0410] Specific behavior: The server generates a suggestion such as "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, it includes a detailed suggestion such as "I recommend a salad today."

[0411] Step 5: Proposal Notification

[0412] Description: The device notifies the user of the offers received from the server.

[0413] Input: A suggestion from the server.

[0414] Data processing: None in particular.

[0415] Output: Notification to the user.

[0416] Specific behavior: The device will notify the user by voice, "You had pizza yesterday, so I recommend you have a salad today. Would you like some specific dressing suggestions?"

[0417] Step 6: User feedback

[0418] Description: The user provides feedback on the suggestions and sends it to the server via the device.

[0419] Input: User feedback.

[0420] Data processing: None in particular.

[0421] Output: Feedback sent to the server.

[0422] Specific behavior: The user responds, "The salad is good, but could you recommend a dressing?" and the device sends this feedback to the server.

[0423] Step 7: Modify the proposal

[0424] Description: The server modifies the suggestions based on user feedback and sentiment data.

[0425] Input: Feedback and emotion data.

[0426] Data processing: Analyze feedback and sentiment data and update suggestions.

[0427] Output: The revised proposal.

[0428] Specific behavior: The server modifies the suggestion to "You might want to use a little olive oil and lemon dressing on the salad" and notifies the user again via the device.

[0429] Through this series of processing steps, users receive healthy suggestions that take emotional data into account, allowing them to make choices that better suit their lifestyle.

[0430] (Application example 2)

[0431] 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."

[0432] Modern consumers have diverse preferences and emotional states, and there is a demand for personalized shopping experiences based on these. However, conventional systems have had difficulty effectively utilizing users' lifestyle and emotional data to make appropriate product recommendations in real time. Furthermore, there was no established method for efficiently collecting and analyzing feedback to improve the accuracy of recommendations. The present invention aims to solve these issues and provide a system that provides users with optimal product recommendations.

[0433] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on the user's purchase history. This enables real-time, personalized product proposals that take into account the user's preferences and emotional state.

[0434] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[0435] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, tone of voice, heart rate, etc.

[0436] "Analytics" refers to the methods used to assess user behavior, preferences, and emotional states based on collected data to extract insights and trends.

[0437] "Proposal generation means" refers to a method for creating personalized proposals for a user based on the analysis results.

[0438] "Notification means" refers to the method for communicating generated suggestions to the user.

[0439] "Feedback channels" are ways to gather responses and opinions from users and use them to refine your proposals.

[0440] "Purchase history" refers to a record of products and services a user has purchased in the past.

[0441] "Product suggestions" refer to products and services recommended to users based on their lifestyle data, emotional data, and purchasing history.

[0442] The present invention provides a system that collects user lifestyle data and emotion data, analyzes the data, generates and notifies personalized suggestions, and modifies the suggestions based on user feedback. The system is configured as follows.

[0443] The server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on purchase history.

[0444] Hardware and software used

[0445] Hardware:

[0446] Cameras (e.g., cameras built into smart glasses or smartphones)

[0447] Microphones (e.g., microphones built into smart glasses or smartphones)

[0448] software:

[0449] OpenCV: A framework for real-time processing of camera images

[0450] SpeechRecognition: A library for analyzing speech

[0451] Requests: Library for data communication with the server

[0452] EmotionRecognizer: Emotion recognition engine

[0453] Data processing and calculation

[0454] The device (e.g., smart glasses or smartphone) captures the user's facial expressions and voice in real time. It uses a camera to acquire the user's facial expression data, processes the images using OpenCV, and then analyzes the emotion data using EmotionRecognizer.

[0455] The microphone is used to capture the user's voice data, and the speech is converted into text using the SpeechRecognition library. This data is then combined and sent to the server using the Requests library. The server receives the data, analyzes it, and generates personalized product suggestions for the user. The suggestions are then sent back to the device and notified to the user.

[0456] Specific examples

[0457] For example, imagine a user is shopping in a physical store. Smart glasses capture the user's facial expression data and detect whether the user is enjoying themselves. If the user also says, "I've been feeling tired lately," the system collects this as text data. This data is sent to a server and analyzed along with the user's purchase history. As a result, personalized products such as "tea with a relaxing effect" are suggested.

[0458] Prompt Sentence Examples

[0459] Create a recommendation for a brick-and-mortar shopping assistant that collects emotional data from users' facial expressions and voice, and analyzes it along with their purchasing history. Generate optimal product recommendations for users based on the following data:

[0460] A list of items recently purchased by the user

[0461] User facial expression data

[0462] User voice data

[0463] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0464] Step 1:

[0465] The user wears smart glasses or a smartphone, and the device captures their facial expressions and voice. The device acquires the user's facial expression data through the camera and processes the image data using OpenCV. It also acquires voice data using the microphone and converts the voice into text data using the SpeechRecognition library. The input is the user's facial expression and voice, and the output is processed facial expression data and text data.

[0466] Step 2:

[0467] The device converts the acquired facial expression data into emotional data using EmotionRecognizer. Specifically, it recognizes emotions such as "happiness," "anger," and "sadness" from the user's facial expressions in real time and stores them as digital data. The input is processed facial expression data, and the output is emotional data.

[0468] Step 3:

[0469] The device integrates emotion data and speech-to-text data and sends it to the server using the Requests library. The data sent includes the user's emotion data, speech-to-text data, and purchase history. In this case, the input is emotion data and speech-to-text data, and the output is a request containing these data.

[0470] Step 4:

[0471] The server analyzes the received data and generates product suggestions suitable for the user. It uses an AI algorithm to evaluate the user's lifestyle and emotional data to generate personalized product suggestions. The input is emotional data, voice and text data, and purchase history, and the output is product suggestions.

[0472] Step 5:

[0473] The server sends the generated product suggestions to the terminal. At this time, the information notified to the user includes details of the suggested products and the reasons for them. The input is the product suggestions, and the output is a notification to the user.

[0474] Step 6:

[0475] The user provides feedback on the received product suggestions. The terminal transmits the user's feedback to the server again. At this time, the input is the user's feedback and the output is a request to the server.

[0476] Step 7:

[0477] The server analyzes the user's feedback and modifies the proposal if necessary. The modified proposal is then notified to the user again. The input is the user's feedback and the output is the modified proposal.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] [Second embodiment]

[0482] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0483] 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.

[0484] 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).

[0485] 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.

[0486] 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.

[0487] 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).

[0488] 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. 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.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] 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.

[0493] 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."

[0494] The present invention is a system that collects and analyzes a user's lifestyle data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. The system includes programs for executing the processes of collection, analysis, suggestion, notification, and feedback.

[0495] 1. Collection of lifestyle data

[0496] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0497] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[0498] For example, if a user logs the contents of their meal on a smartphone app, the data is automatically sent from the device to the server.

[0499] 2. Data Analysis

[0500] The server analyzes the life data sent from the device.

[0501] This analysis uses artificial intelligence to extract insights and trends from user data.

[0502] For example, it analyzes a user's dietary history to determine whether their nutritional balance is unbalanced.

[0503] 3. Proposal Generation

[0504] The server generates personalized offers based on the analysis results.

[0505] Suggestions include exercise plans and dietary advice to help manage your health, as well as support on how to enjoy hobbies.

[0506] For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to get more vegetables."

[0507] 4. Notification of Proposal

[0508] The terminal notifies the user of the proposal received from the server.

[0509] Notifications are delivered via audio, allowing users to actually interact with the device.

[0510] For example, the device might say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[0511] 5. User Feedback

[0512] Users provide feedback on the suggestions.

[0513] The feedback is sent to the server through the device.

[0514] For example, a user might provide feedback like, "The salad sounds good, but can you recommend a dressing?"

[0515] 6. Proposal Modifications

[0516] The server then modifies the suggestions based on user feedback.

[0517] The revised suggestions will be notified to the user again via the device.

[0518] For example, the server reproduces the content "We recommend olive oil and lemon dressing for your salad," and the terminal notifies this.

[0519] As a specific example, consider the following case.

[0520] Specific examples

[0521] Meal suggestion examples

[0522] 1. Data Collection

[0523] A user logs into a smartphone app, "I had pizza for dinner last night."

[0524] 2. Data Analysis

[0525] The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.).

[0526] 3. Proposal generation

[0527] The server generates a suggestion like, "Since you had pizza yesterday, we recommend you choose a salad today to get more vegetables."

[0528] 4. Proposal Notice

[0529] The device will announce in a voice message, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[0530] 5. User Feedback

[0531] The user replies, "Salad sounds good, but can you recommend a dressing?"

[0532] 6. Proposal modification

[0533] The server corrects the suggestion to "I recommend olive oil and lemon dressing for the salad" and notifies again.

[0534] This allows users to easily make balanced dietary choices, and by repeating this cycle, the accuracy of the suggestions will improve, allowing for more useful advice to be provided to users.

[0535] The processing flow will be explained below.

[0536] Step 1:

[0537] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[0538] Step 2:

[0539] The device sends the collected lifestyle data to a server, and the device uploads log data to the server via the Internet. This data includes meal contents, meal times, and meal amounts.

[0540] Step 3:

[0541] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and also references past data to evaluate the user's nutritional intake balance.

[0542] Step 4:

[0543] The server generates a suggestion based on the analysis results, such as "Since you ate pizza yesterday, we recommend you choose a salad today to get more vegetables."

[0544] Step 5:

[0545] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[0546] Step 6:

[0547] The device will notify the user of the received suggestion by voice. The device will notify, "Since you had pizza yesterday, I recommend you eat a salad today. What do you think?" The user can listen to the suggestion by voice.

[0548] Step 7:

[0549] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[0550] Step 8:

[0551] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[0552] Step 9:

[0553] The server modifies the suggestion based on the user's feedback. The server regenerates the suggestion, "I recommend olive oil and lemon dressing for your salad," and sends it to the device.

[0554] Step 10:

[0555] The device will then re-promote the revised suggestion to the user, saying, "We recommend olive oil and lemon dressing on your salad."

[0556] Through these steps, the Audio Glasses system provides users with continuously optimized health advice to improve the quality of their daily lives.

[0557] Example 1

[0558] 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."

[0559] In today's busy lifestyles, supporting users in managing their health and improving their lifestyles requires suggestions tailored to their individual circumstances. However, conventional systems do not adequately analyze the data collected from users, resulting in insufficient individualization of suggestions and insufficient reflection of feedback. This makes it difficult to provide effective support for users in managing their health and improving their lifestyles, and reduces the accuracy and usefulness of suggestions.

[0560] 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.

[0561] In this invention, the server includes a means for collecting user lifestyle data, a means for storing the collected lifestyle data in a database, a means for analyzing the lifestyle data using an artificial intelligence model to extract insights, and a means for personalizing suggestions based on the user's preferences and behavioral data, thereby enabling highly accurate personalized suggestions to be provided to the user and for suggestions to be revised based on feedback.

[0562] "User" refers to an individual who uses this system.

[0563] "Lifestyle Data" refers to data including information about a user's daily activities, eating habits, exercise history, and hobbies.

[0564] "Means of collection" refers to the devices and applications used to collect users' lifestyle data.

[0565] "Means of storage" refers to the means for storing collected lifestyle data in a database or the like.

[0566] "Means of analysis" refers to artificial intelligence and data processing technologies used to analyze collected lifestyle data and extract insights and trends.

[0567] "Means for generating suggestions" refers to means for creating suggestions suitable for the user based on the analysis results.

[0568] "Means for notifying suggestions" refers to means for notifying a user of generated suggestions.

[0569] "Means for modifying suggestions based on feedback" refers to means for analyzing user feedback and modifying suggestions based on the results of that analysis.

[0570] "Database" refers to a system for storing and managing collected lifestyle data.

[0571] "Artificial intelligence model" refers to the machine learning models and algorithms used to analyze life data, extract insights, and generate recommendations.

[0572] "Means of extracting insights" refers to techniques for finding important information and trends from analyzed data.

[0573] "Personalization" refers to customizing recommendations based on a user's specific preferences and behavior.

[0574] The present invention is a system that collects and analyzes users' life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. Specific embodiments are described below.

[0575] 1. Collection of lifestyle data

[0576] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies. Data collection is done through devices such as smartphone apps, smartwatches, and fitness trackers. For example, when a user enters their meal history into a smartphone app, the data is automatically sent from the device to a server.

[0577] 2. Data storage

[0578] The server stores the lifestyle data sent from the device in a database for later analysis. For example, the server stores a user's exercise history for one week in a database.

[0579] 3. Data Analysis

[0580] The server analyzes the stored lifestyle data. This analysis uses artificial intelligence (generative AI models) to extract insights and trends from the data. For example, it can determine whether a user's nutritional balance is unbalanced based on their dietary history.

[0581] 4. Proposal Generation

[0582] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[0583] 5. Notification of Proposal

[0584] The device notifies the user of the suggestions received from the server. The notification is done through voice, so the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[0585] 6. User Feedback

[0586] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[0587] 7. Proposal Modifications

[0588] The server then modifies the suggestions based on the user's feedback. The modified suggestions are then sent to the user via the device. For example, the server might regenerate a suggestion such as "We recommend olive oil and lemon dressing for your salad," and the device would then notify the user.

[0589] Specific examples

[0590] For example, suppose a user logs into a smartphone app that they "ate pizza for dinner yesterday." The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.). As a result, the server generates a suggestion such as, "Since you ate pizza yesterday, I recommend you choose a salad today to get more vegetables." The device then notifies the user by voice, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?" The user responds, "Salads sound good, but could you also recommend a dressing?" Based on this feedback, the server modifies the suggestion to, "I recommend olive oil and lemon dressing for the salad," and notifies them again.

[0591] Prompt Sentence Examples

[0592] "Please explain how to build a system that collects and analyzes lifestyle data and generates optimal health management suggestions for users."

[0593] "Please give us a concrete example of a system that collects and analyzes food logs and provides personalized meal suggestions."

[0594] This invention allows users to easily choose a balanced diet and adopt healthy lifestyle habits. Furthermore, by repeating this cycle, the accuracy of the suggestions will improve, making it possible to provide more useful advice to users.

[0595] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0596] Step 1: Collecting lifestyle data

[0597] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0598] Input: Data recorded by users via smartphone apps, smartwatches, and fitness trackers.

[0599] What it does: The phone receives data from these devices via Bluetooth or Wi-Fi and stores it in a formatted form on its internal memory.

[0600] Output: The collected user lifestyle data is temporarily stored on the device.

[0601] Step 2: Send the data log

[0602] The terminal transmits the collected data to the server in real time.

[0603] Input: Life data stored on the device.

[0604] How it works: The device sends life data to the server at regular intervals or when the data is updated. Data transfer is encrypted and protected using the HTTPS protocol.

[0605] Output: The collected data is transferred to the server.

[0606] Step 3: Save your data

[0607] The server stores the received data in a database.

[0608] Input: Life data sent from the device.

[0609] Specific operation: The server stores the received data using a database management system (e.g., MySQL or PostgreSQL). The data integrity is checked and invalid data is removed.

[0610] Output: Life data is accurately stored in the database.

[0611] Step 4: Preprocessing the data

[0612] The server cleans the collected data and converts it into a format suitable for analysis.

[0613] Input: Life data stored in a database.

[0614] What it does: The server imputes missing values ​​from the data, removes noise, and normalizes the data, for example, correcting anomalous numerical data and encoding categorical data.

[0615] Output: A preprocessed and clean dataset.

[0616] Step 5: Analyze the data

[0617] The server uses the pre-processed data to analyze it using a generative AI model.

[0618] Input: Preprocessed lifestyle dataset.

[0619] Specific operation: The server inputs data into a machine learning model (e.g., a deep learning model) and performs analysis, thereby extracting trends in the user's behavioral patterns and health status.

[0620] Output: The insights and trends extracted as a result of the analysis.

[0621] Step 6: Generate proposals

[0622] The server generates personalized offers based on the analysis results.

[0623] Input: Insights and trends based on analytical results.

[0624] Specific operation: The server uses a proposal generation algorithm to create specific proposals that will help the user manage their health and improve their lifestyle. For example, a proposal might be generated such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[0625] Output: The individual suggestions generated.

[0626] Step 7: Prepare your proposal

[0627] The server formats the proposals to be sent to the user and converts them into a format that can be sent to the terminal.

[0628] Input: Generated suggestions.

[0629] Specific operation: The proposal content is converted into natural language that is easy for the user to understand, and speech synthesis data is also prepared if necessary.

[0630] Output: Formatted proposal data.

[0631] Step 8: Sending notifications

[0632] The device notifies the user of the received proposal.

[0633] Input: Formatted proposal data.

[0634] What it does: The device notifies the user of the suggestion using voice or text message, for example, "You had pizza yesterday, so I suggest you have a salad today."

[0635] Output: The suggestion that was notified to the user.

[0636] Step 9: Accepting feedback

[0637] Users provide feedback on the suggestions.

[0638] Input: User response based on suggestions.

[0639] What happens: The user provides feedback via voice or text, such as a request like, "The salad is great, but can you recommend a dressing?"

[0640] Output: User feedback data.

[0641] Step 10: Submit your feedback

[0642] The device sends the feedback from the user to the server.

[0643] Input: User feedback data.

[0644] Specific operation: The terminal sends feedback data to the server using the HTTPS protocol.

[0645] Output: Feedback data sent to the server.

[0646] Step 11: Analyze feedback

[0647] The server analyzes the received feedback to help refine the proposal.

[0648] Input: User feedback data.

[0649] Specific operation: The server uses natural language processing technology to analyze the content of the feedback and extract the user's requests and comments.

[0650] Output: Insights for revision based on feedback.

[0651] Step 12: Modifying the proposal

[0652] The server then modifies the suggestions based on user feedback.

[0653] Input: Insights based on feedback.

[0654] What happens: The server reapplies the suggestion generation algorithm to create a new suggestion that reflects the user's requests and comments, e.g., "I recommend olive oil and lemon dressing for salads."

[0655] Output: The revised proposal.

[0656] Step 13: Send a reminder

[0657] The device will notify the user again with the revised suggestions.

[0658] Input: Revised proposal.

[0659] What happens: The device notifies the user using voice or text message with the revised suggestion, for example, reminding them, "We recommend olive oil and lemon dressing on your salad."

[0660] Output: The suggestion that was snoozed to the user.

[0661] (Application example 1)

[0662] 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."

[0663] In modern society, health management tailored to individual lifestyles and eating habits is considered important, but there is a problem in that generic health suggestions cannot meet the different needs of each user. In particular, the lack of specific suggestions for dietary habits makes it difficult for individual users to maintain appropriate eating habits. In addition, the lack of advice on specific seasonings and ingredient selection for meals makes it difficult for users to eat a diet that suits their own health condition.

[0664] 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.

[0665] In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual suggestions based on the analysis results, means for notifying the user of the generated suggestions, means for modifying the suggestions based on the user's feedback, means for generating and notifying specific meal suggestions based on the lifestyle data, and means for analyzing the feedback content selected by the user based on the suggestions and suggesting seasonings suitable for the meal menu. This enables users to receive optimal health management and specific meal suggestions tailored to their individual lifestyles and eating habits.

[0666] "User lifestyle data" refers to information related to a user's daily activities, eating habits, exercise history, hobbies, etc.

[0667] "Means of collection" refers to devices and methods for obtaining and recording users' lifestyle data.

[0668] "Means for analysis" refers to systems and methods for processing collected lifestyle data and extracting useful information and trends.

[0669] "Means for generating recommendations" refers to a process or device that generates personalized advice or recommendations based on the results of the analysis.

[0670] "Means for notifying suggestions" refers to the functions and devices used to communicate the generated suggestions to users.

[0671] "Means for revising suggestions" refers to a method or system for revising existing suggestions based on user feedback.

[0672] "Specific meal suggestions" refers to advice recommending specific ingredients and menus based on the user's lifestyle data.

[0673] The "means for suggesting seasonings" refers to a function or method for providing seasonings and seasoning methods suitable for the proposed meal menu.

[0674] The present invention is a system that collects and analyzes users' lifestyle data, and generates, notifies, and modifies personalized suggestions based on that data. Specifically, the system is comprised of the following processes:

[0675] 1. System Programming

[0676] The system has the following main program flow:

[0677] Collection of lifestyle data

[0678] Devices (such as smartphones, smartwatches, and fitness trackers) collect data about users' daily activities, eating habits, exercise history, and hobbies. For example, a user logs in a smartphone app that they "ate pizza for dinner last night." This data is then sent from the device to a server.

[0679] Data analysis

[0680] The server receives and analyzes the lifestyle data sent from the device. This analysis uses a generative AI model to extract insights and trends from the user's lifestyle data. For example, it can evaluate the nutritional content (calories, fat, carbohydrates, etc.) of a pizza to determine whether it is nutritionally unbalanced.

[0681] Proposal Generation

[0682] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, a suggestion might be, "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[0683] Proposal Notification

[0684] The device notifies the user of the suggestions received from the server. The notification is done through voice, and the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[0685] User Feedback

[0686] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[0687] Proposal amendments

[0688] The server then modifies the suggestions based on the user's feedback, and the modified suggestions are then sent to the user via the device. For example, the server might regenerate the suggestion, "We recommend olive oil and lemon dressing for your salad," and the device would notify the user.

[0689] 2. Hardware and Software Used

[0690] This system uses the following hardware and software:

[0691] Smartphone: A device for inputting user data (such as meal contents).

[0692] Server: Analyzes data, generates suggestions, and manages feedback.

[0693] Generative AI models: Used to analyze data and generate recommendations.

[0694] For example: Machine learning libraries such as TensorFlow, Keras, etc.

[0695] 3. Examples and prompts

[0696] If a user inputs "I had pizza for dinner last night," the system will proceed as follows: The server will analyze the nutritional information (calories, fat, carbohydrates, etc.) of the pizza and generate a suggestion, for example using the following prompt:

[0697] Example prompt sentence:

[0698] The user ate pizza yesterday. It was high in calories, so we recommend a meal with lots of vegetables today.

[0699] The system provides users with specific and personalized suggestions for living a healthy life, enabling them to receive optimal health management tailored to their individual lifestyles and eating habits.

[0700] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0701] Step 1:

[0702] The user enters meal information into the app.

[0703] Input: The user enters meal details (e.g., "I had pizza for dinner last night") into a smartphone app.

[0704] Processing: The smartphone app sends the entered meal information to the server.

[0705] Output: The server receives the meal data and stores it in a database.

[0706] Step 2:

[0707] The server analyzes lifestyle data.

[0708] Input: The server retrieves the user's lifestyle data from the database.

[0709] Processing: The server analyzes the acquired data using a generative AI model. Specifically, it evaluates nutritional components (calories, fat, carbohydrates, etc.) and determines the user's nutritional balance.

[0710] Output: A report is generated based on the analysis results, which contains details of the user's nutritional balance.

[0711] Step 3:

[0712] The server generates personalized offers.

[0713] Input: Analysis results (report)

[0714] Processing: The server uses the generative AI model based on the analysis results to create personalized meal recommendations, such as "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[0715] Output: The generated proposal is added to the notification queue.

[0716] Step 4:

[0717] The device will notify the user of the suggestion.

[0718] Input: Notification queue proposal data

[0719] Processing: The smartphone app will notify the user of the suggestion by voice, for example, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[0720] Output: The user receives the suggestions aloud.

[0721] Step 5:

[0722] Users provide feedback.

[0723] Input: User feedback on the suggestion (e.g., "The salad sounds good, but could you recommend a dressing?")

[0724] Processing: The user enters feedback via the smartphone app and sends it to the server.

[0725] Output: The feedback data is received by the server and added to the feedback queue.

[0726] Step 6:

[0727] The server modifies the proposal based on the feedback.

[0728] Input: Feedback data

[0729] Processing: The server analyzes the feedback data and uses a generative AI model to refine the suggestions, for example, creating a new suggestion such as "I recommend olive oil and lemon dressing for your salad."

[0730] Output: The revised proposal is added back to the notification queue.

[0731] Step 7:

[0732] The device will notify the user again with the revised suggestion.

[0733] Input: Proposed correction data

[0734] Action: The smartphone app will re-announce the suggested revision to the user, for example, "We recommend olive oil and lemon dressing for your salad."

[0735] Output: The user receives the revised suggestion aloud.

[0736] 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.

[0737] The present invention is a system that collects and analyzes users' daily life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. This system also combines an emotion engine that recognizes users' emotions to provide more appropriate and personalized suggestions to users.

[0738] 1. Collection of lifestyle data

[0739] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0740] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[0741] For example, if a user logs the contents of their meal in a smartphone app, the data is sent from the device to a server.

[0742] 2. Collecting Emotional Data

[0743] The device utilizes an emotion engine to collect user emotion data.

[0744] The emotion engine uses cameras, microphones, biometric sensors, etc. to analyze the user's facial expressions, tone of voice, heart rate, etc. to identify their emotional state.

[0745] For example, while a user is using a smartphone app, the camera captures their facial expressions, and based on that, the emotion engine recognizes emotions such as "joy," "anger," and "sadness."

[0746] 3. Data Analysis

[0747] The server analyzes the lifestyle data and emotion data sent from the device.

[0748] The analysis uses artificial intelligence algorithms to extract insights and trends from user data.

[0749] For example, it analyzes a user's eating history and emotional data to assess the impact that a particular meal has on the user's emotions.

[0750] 4. Proposal Generation

[0751] The server generates personalized offers based on the analysis results.

[0752] Suggestions include exercise plans, dietary advice, and help with hobbies to help you manage your health, and the app also adjusts the suggestions based on your emotional state.

[0753] For example, it generates specific suggestions such as, "Since you ate pizza yesterday, we recommend that you choose a salad today to get more vegetables."

[0754] 5. Notification of Proposal

[0755] The terminal notifies the user of the proposal received from the server.

[0756] Notifications are delivered via audio, allowing users to actually interact with the device.

[0757] For example, the device may say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[0758] 6. User Feedback

[0759] Users provide feedback on the suggestions.

[0760] The feedback is sent to the server through the device.

[0761] For example, a user might provide feedback such as, "The salad is good, but can you recommend a dressing?"

[0762] 7. Proposal Modifications

[0763] The server then refines the suggestions based on user feedback and sentiment data.

[0764] The revised suggestions will be notified to the user again via the device.

[0765] For example, the server may modify the content to say, "We recommend olive oil and lemon dressing for your salad," and the terminal will notify you of this.

[0766] As a specific example, consider the following case.

[0767] Specific examples

[0768] Meal suggestion examples

[0769] 1. Data Collection

[0770] When a user logs into a smartphone app saying, "I had pizza for dinner last night," the device's facial recognition camera detects that the user is smiling, and the emotion engine then uses that information to identify the user.

[0771] 2. Data Analysis

[0772] The server analyzes this data and evaluates the pizza's nutritional content (calories, fat, carbohydrates, etc.), taking into account the user's happy emotions after eating the pizza.

[0773] 3. Proposal generation

[0774] The server generates a suggestion: "You seemed happy eating pizza yesterday, so today I suggest you eat more vegetables for a healthy balance."

[0775] 4. Proposal Notice

[0776] The device will announce in a voice message, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific dressing suggestions?"

[0777] 5. User Feedback

[0778] The user responds, "Please also tell me what dressing you would recommend to go with the salad," and the device sends this feedback to the server.

[0779] 6. Proposal modification

[0780] The server amends the suggestion to "The salad would benefit from a little olive oil and lemon dressing" and sends it to the terminal again.

[0781] Through this system, users will receive healthy suggestions that take their emotional data into account, allowing them to make choices that better suit their lifestyle.

[0782] The processing flow will be explained below.

[0783] Step 1:

[0784] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[0785] Step 2:

[0786] The device uses a camera, microphone, and biometric sensors to analyze the user's facial expressions, tone of voice, and heart rate using an emotion engine, for example, to detect if the user is smiling after eating pizza.

[0787] Step 3:

[0788] The device sends the collected lifestyle data and emotional data to a server, which then uploads the log data and emotional data to the server via the Internet.

[0789] Step 4:

[0790] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and analyze the user's emotional state. It also refers to past data to evaluate the relationship between the user's nutritional balance and their emotions.

[0791] Step 5:

[0792] The server generates recommendations based on the analysis results, such as "You seemed happy after eating pizza yesterday, so I recommend you eat more vegetables today to achieve a healthy balance."

[0793] Step 6:

[0794] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[0795] Step 7:

[0796] The device will notify the user of the received suggestions via voice. The device will say, "Since you had pizza yesterday, I recommend you have a salad today. Would you like some specific suggestions on dressings?" The user can listen to the suggestions via voice.

[0797] Step 8:

[0798] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[0799] Step 9:

[0800] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[0801] Step 10:

[0802] The server then modifies the suggestion based on the user's feedback and sentiment data, resending it to "You might want to use a little olive oil and lemon dressing on your salad" and sending it back to the device.

[0803] Step 11:

[0804] The device then notifies the user again with the revised suggestion, saying, "We recommend olive oil and lemon dressing on your salad." The user accepts and implements this suggestion.

[0805] Through these steps, the audio glasses system can provide users with continuously optimized health advice to improve the quality of their daily lives, and by combining it with an emotion engine, it can make suggestions based on the user's emotional state, providing more personalized support.

[0806] Example 2

[0807] 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."

[0808] Many modern personalized health management and lifestyle recommendation systems collect and use user lifestyle data to make recommendations. However, these systems do not take into account the user's emotional data, and recommendations may not match the user's emotional state. As a result, there are problems with low user acceptance and satisfaction. Furthermore, conventional systems are unable to properly reflect user feedback, limiting the accuracy and effectiveness of recommendations. To solve these issues, a system is needed that collects and analyzes not only the user's lifestyle data but also their emotional data, and generates and modifies recommendations based on that data.

[0809] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user life data and emotional data, means for analyzing the collected life data and emotional data, means for generating personalized proposals based on the analysis results, means for notifying the user of the generated proposals, and means for modifying the proposals based on the user's feedback and emotional data. This makes it possible to provide personalized proposals that match the user's emotional state, thereby improving user satisfaction and proposal acceptance. Furthermore, by reflecting user feedback, the accuracy and effectiveness of the proposals can be further improved.

[0810] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[0811] "Emotional data" is information used to analyze a user's facial expressions, tone of voice, heart rate, etc., to identify emotional states such as joy, anger, and sadness.

[0812] "Means of collection" refers to the methods of obtaining data using devices such as smartphones, smartwatches, and fitness trackers.

[0813] "Means of analysis" refers to the use of artificial intelligence algorithms to analyze collected data and extract insights and trends.

[0814] "Means for generating recommendations" refers to a method for generating personalized health management and lifestyle recommendations based on the analysis results.

[0815] The "notification method" is the method for notifying the user of the generated suggestions, such as by voice or text message.

[0816] "Means to modify suggestions" refers to ways to improve existing suggestions based on user feedback and additional sentiment data.

[0817] The present invention is a set of systems that collect and analyze users' life data and emotional data, generate and notify personalized suggestions, and modify these suggestions based on users' feedback and emotional data. The system further incorporates an emotional engine to provide more appropriate and personalized suggestions to users.

[0818] In order to implement this system, the following specific means are used.

[0819] 1. Collection of lifestyle and emotional data

[0820] The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data on users' daily activities, dietary habits, exercise history, and hobbies. Furthermore, the device utilizes an emotion engine to analyze the user's facial expressions, tone of voice, heart rate, and other data using cameras, microphones, and biometric sensors to identify their emotional state.

[0821] For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," the data is sent from the device to the server. At the same time, the camera captures the user's face, and the emotion engine detects "happiness."

[0822] 2. Data Analysis

[0823] The server analyzes the lifestyle and emotional data sent from the device, using artificial intelligence algorithms to extract insights and trends from the user's data.

[0824] For example, the server receives the log "I had pizza for dinner last night" and the "pleasure" data from the emotion engine, and analyzes these data using a human artificial intelligence algorithm to evaluate the impact that a particular meal has on the user's emotions.

[0825] 3. Proposal Generation

[0826] The server generates personalized recommendations based on the analysis, including exercise plans and dietary advice to help manage your health, tailored based on your emotional state.

[0827] For example, the server generates a suggestion such as, "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, the suggestion includes a detailed suggestion such as, "I recommend a salad today."

[0828] 4. Notification of Proposal

[0829] The device notifies the user of the suggestions it receives from the server, and the notification is done via voice, allowing the user to actually interact with the device.

[0830] For example, the device might say to the user, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific suggestions for dressing?"

[0831] 5. User Feedback

[0832] The user provides feedback on the suggestions, which is sent to the server via the device.

[0833] For example, the user might respond, "The salad is good, but could you recommend a dressing?" and the device would send this feedback to the server.

[0834] 6. Proposal Modifications

[0835] The server then modifies the suggestions based on the user's feedback and emotional data, and the modified suggestions are then sent back to the user via their device.

[0836] For example, the server might revise the suggestion to, "You might want to use a little olive oil and lemon dressing on the salad," and the device would reiterate this aloud.

[0837] Through this system, users can receive healthy suggestions that take into account their emotional data and make choices that better suit their lifestyle.

[0838] Examples of prompt statements

[0839] "You logged that you had pizza for dinner yesterday. What suggestions would you generate and how would you notify me? Also, explain how you would refine the suggestions based on user feedback."

[0840] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0841] Step 1: Collecting lifestyle and emotional data

[0842] Description: The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data about a user's daily activities, eating habits, exercise history, and hobbies.

[0843] Input: Data about the user's daily activities, eating habits, exercise history, and hobbies.

[0844] Data Processing: Collected data is aggregated from each device in a centralized format.

[0845] Output: Centralized lifestyle data.

[0846] Specific operation: For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," that data is sent from the device to the server. The device then uses an emotion engine and a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[0847] Step 2: Sending data

[0848] Description: The device sends the collected life data and emotion data to the server.

[0849] Input: Centralized life and emotion data.

[0850] Data processing: None in particular.

[0851] Output: The data sent to the server.

[0852] Specific operation: The device sends the log "I had pizza for dinner yesterday" and the emotion data "joy" to the server.

[0853] Step 3: Analyze the data

[0854] Description: The server analyzes the life data and emotion data sent from the device.

[0855] Input: Life data and emotion data.

[0856] Data processing: Using artificial intelligence algorithms to extract insights and trends from data.

[0857] Output: Analysis results.

[0858] Specific operation: The server uses the log of "I had pizza for dinner yesterday" and the emotion data of "happiness" to evaluate the impact of the user's eating habits on their emotions.

[0859] Step 4: Generate proposals

[0860] Description: The server generates personalized offers based on the analysis results.

[0861] Input: Analysis results.

[0862] Data processing: Based on the analysis results, health management and lifestyle suggestions are created.

[0863] Output: Individual proposals.

[0864] Specific behavior: The server generates a suggestion such as "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, it includes a detailed suggestion such as "I recommend a salad today."

[0865] Step 5: Proposal Notification

[0866] Description: The device notifies the user of the offers received from the server.

[0867] Input: A suggestion from the server.

[0868] Data processing: None in particular.

[0869] Output: Notification to the user.

[0870] Specific behavior: The device will notify the user by voice, "You had pizza yesterday, so I recommend you have a salad today. Would you like some specific dressing suggestions?"

[0871] Step 6: User feedback

[0872] Description: The user provides feedback on the suggestions and sends it to the server via the device.

[0873] Input: User feedback.

[0874] Data processing: None in particular.

[0875] Output: Feedback sent to the server.

[0876] Specific behavior: The user responds, "The salad is good, but could you recommend a dressing?" and the device sends this feedback to the server.

[0877] Step 7: Modify the proposal

[0878] Description: The server modifies the suggestions based on user feedback and sentiment data.

[0879] Input: Feedback and emotion data.

[0880] Data processing: Analyze feedback and sentiment data and update suggestions.

[0881] Output: The revised proposal.

[0882] Specific behavior: The server modifies the suggestion to "You might want to use a little olive oil and lemon dressing on the salad" and notifies the user again via the device.

[0883] Through this series of processing steps, users receive healthy suggestions that take emotional data into account, allowing them to make choices that better suit their lifestyle.

[0884] (Application example 2)

[0885] 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."

[0886] Modern consumers have diverse preferences and emotional states, and there is a demand for personalized shopping experiences based on these. However, conventional systems have had difficulty effectively utilizing users' lifestyle and emotional data to make appropriate product recommendations in real time. Furthermore, there was no established method for efficiently collecting and analyzing feedback to improve the accuracy of recommendations. The present invention aims to solve these issues and provide a system that provides users with optimal product recommendations.

[0887] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on the user's purchase history. This enables real-time, personalized product proposals that take into account the user's preferences and emotional state.

[0888] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[0889] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, tone of voice, heart rate, etc.

[0890] "Analytics" refers to the methods used to assess user behavior, preferences, and emotional states based on collected data to extract insights and trends.

[0891] "Proposal generation means" refers to a method for creating personalized proposals for a user based on the analysis results.

[0892] "Notification means" refers to the method for communicating generated suggestions to the user.

[0893] "Feedback channels" are ways to gather responses and opinions from users and use them to refine your proposals.

[0894] "Purchase history" refers to a record of products and services a user has purchased in the past.

[0895] "Product suggestions" refer to products and services recommended to users based on their lifestyle data, emotional data, and purchasing history.

[0896] The present invention provides a system that collects user lifestyle data and emotion data, analyzes the data, generates and notifies personalized suggestions, and modifies the suggestions based on user feedback. The system is configured as follows.

[0897] The server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on purchase history.

[0898] Hardware and software used

[0899] Hardware:

[0900] Cameras (e.g., cameras built into smart glasses or smartphones)

[0901] Microphones (e.g., microphones built into smart glasses or smartphones)

[0902] software:

[0903] OpenCV: A framework for real-time processing of camera images

[0904] SpeechRecognition: A library for analyzing speech

[0905] Requests: Library for data communication with the server

[0906] EmotionRecognizer: Emotion recognition engine

[0907] Data processing and calculation

[0908] The device (e.g., smart glasses or smartphone) captures the user's facial expressions and voice in real time. It uses a camera to acquire the user's facial expression data, processes the images using OpenCV, and then analyzes the emotion data using EmotionRecognizer.

[0909] The microphone is used to capture the user's voice data, and the speech is converted into text using the SpeechRecognition library. This data is then combined and sent to the server using the Requests library. The server receives the data, analyzes it, and generates personalized product suggestions for the user. The suggestions are then sent back to the device and notified to the user.

[0910] Specific examples

[0911] For example, imagine a user is shopping in a physical store. Smart glasses capture the user's facial expression data and detect whether the user is enjoying themselves. If the user also says, "I've been feeling tired lately," the system collects this as text data. This data is sent to a server and analyzed along with the user's purchase history. As a result, personalized products such as "tea with a relaxing effect" are suggested.

[0912] Prompt Sentence Examples

[0913] Create a recommendation for a brick-and-mortar shopping assistant that collects emotional data from users' facial expressions and voice, and analyzes it along with their purchasing history. Generate optimal product recommendations for users based on the following data:

[0914] A list of items recently purchased by the user

[0915] User facial expression data

[0916] User voice data

[0917] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0918] Step 1:

[0919] The user wears smart glasses or a smartphone, and the device captures their facial expressions and voice. The device acquires the user's facial expression data through the camera and processes the image data using OpenCV. It also acquires voice data using the microphone and converts the voice into text data using the SpeechRecognition library. The input is the user's facial expression and voice, and the output is processed facial expression data and text data.

[0920] Step 2:

[0921] The device converts the acquired facial expression data into emotional data using EmotionRecognizer. Specifically, it recognizes emotions such as "happiness," "anger," and "sadness" from the user's facial expressions in real time and stores them as digital data. The input is processed facial expression data, and the output is emotional data.

[0922] Step 3:

[0923] The device integrates emotion data and speech-to-text data and sends it to the server using the Requests library. The data sent includes the user's emotion data, speech-to-text data, and purchase history. In this case, the input is emotion data and speech-to-text data, and the output is a request containing these data.

[0924] Step 4:

[0925] The server analyzes the received data and generates product suggestions suitable for the user. It uses an AI algorithm to evaluate the user's lifestyle and emotional data to generate personalized product suggestions. The input is emotional data, voice and text data, and purchase history, and the output is product suggestions.

[0926] Step 5:

[0927] The server sends the generated product suggestions to the terminal. At this time, the information notified to the user includes details of the suggested products and the reasons for them. The input is the product suggestions, and the output is a notification to the user.

[0928] Step 6:

[0929] The user provides feedback on the received product suggestions. The terminal transmits the user's feedback to the server again. At this time, the input is the user's feedback and the output is a request to the server.

[0930] Step 7:

[0931] The server analyzes the user's feedback and modifies the proposal if necessary. The modified proposal is then notified to the user again. The input is the user's feedback and the output is the modified proposal.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] [Third embodiment]

[0936] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0937] 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.

[0938] 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).

[0939] 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.

[0940] 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.

[0941] 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).

[0942] 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. 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.

[0943] 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.

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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."

[0948] The present invention is a system that collects and analyzes a user's lifestyle data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. The system includes programs for executing the processes of collection, analysis, suggestion, notification, and feedback.

[0949] 1. Collection of lifestyle data

[0950] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[0951] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[0952] For example, if a user logs the contents of their meal on a smartphone app, the data is automatically sent from the device to the server.

[0953] 2. Data Analysis

[0954] The server analyzes the life data sent from the device.

[0955] This analysis uses artificial intelligence to extract insights and trends from user data.

[0956] For example, it analyzes a user's dietary history to determine whether their nutritional balance is unbalanced.

[0957] 3. Proposal Generation

[0958] The server generates personalized offers based on the analysis results.

[0959] Suggestions include exercise plans and dietary advice to help manage your health, as well as support on how to enjoy hobbies.

[0960] For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to get more vegetables."

[0961] 4. Notification of Proposal

[0962] The terminal notifies the user of the proposal received from the server.

[0963] Notifications are delivered via audio, allowing users to actually interact with the device.

[0964] For example, the device might say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[0965] 5. User Feedback

[0966] Users provide feedback on the suggestions.

[0967] The feedback is sent to the server through the device.

[0968] For example, a user might provide feedback like, "The salad sounds good, but can you recommend a dressing?"

[0969] 6. Proposal Modifications

[0970] The server then modifies the suggestions based on user feedback.

[0971] The revised suggestions will be notified to the user again via the device.

[0972] For example, the server reproduces the content "We recommend olive oil and lemon dressing for your salad," and the terminal notifies this.

[0973] As a specific example, consider the following case.

[0974] Specific examples

[0975] Meal suggestion examples

[0976] 1. Data Collection

[0977] A user logs into a smartphone app, "I had pizza for dinner last night."

[0978] 2. Data Analysis

[0979] The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.).

[0980] 3. Proposal generation

[0981] The server generates a suggestion like, "Since you had pizza yesterday, we recommend you choose a salad today to get more vegetables."

[0982] 4. Proposal Notice

[0983] The device will announce in a voice message, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[0984] 5. User Feedback

[0985] The user replies, "Salad sounds good, but can you recommend a dressing?"

[0986] 6. Proposal modification

[0987] The server corrects the suggestion to "I recommend olive oil and lemon dressing for the salad" and notifies again.

[0988] This allows users to easily make balanced dietary choices, and by repeating this cycle, the accuracy of the suggestions will improve, allowing for more useful advice to be provided to users.

[0989] The processing flow will be explained below.

[0990] Step 1:

[0991] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[0992] Step 2:

[0993] The device sends the collected lifestyle data to a server, and the device uploads log data to the server via the Internet. This data includes meal contents, meal times, and meal amounts.

[0994] Step 3:

[0995] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and also references past data to evaluate the user's nutritional intake balance.

[0996] Step 4:

[0997] The server generates a suggestion based on the analysis results, such as "Since you ate pizza yesterday, we recommend you choose a salad today to get more vegetables."

[0998] Step 5:

[0999] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[1000] Step 6:

[1001] The device will notify the user of the received suggestion by voice. The device will notify, "Since you had pizza yesterday, I recommend you eat a salad today. What do you think?" The user can listen to the suggestion by voice.

[1002] Step 7:

[1003] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[1004] Step 8:

[1005] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[1006] Step 9:

[1007] The server modifies the suggestion based on the user's feedback. The server regenerates the suggestion, "I recommend olive oil and lemon dressing for your salad," and sends it to the device.

[1008] Step 10:

[1009] The device will then re-promote the revised suggestion to the user, saying, "We recommend olive oil and lemon dressing on your salad."

[1010] Through these steps, the Audio Glasses system provides users with continuously optimized health advice to improve the quality of their daily lives.

[1011] Example 1

[1012] 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."

[1013] In today's busy lifestyles, supporting users in managing their health and improving their lifestyles requires suggestions tailored to their individual circumstances. However, conventional systems do not adequately analyze the data collected from users, resulting in insufficient individualization of suggestions and insufficient reflection of feedback. This makes it difficult to provide effective support for users in managing their health and improving their lifestyles, and reduces the accuracy and usefulness of suggestions.

[1014] 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.

[1015] In this invention, the server includes a means for collecting user lifestyle data, a means for storing the collected lifestyle data in a database, a means for analyzing the lifestyle data using an artificial intelligence model to extract insights, and a means for personalizing suggestions based on the user's preferences and behavioral data, thereby enabling highly accurate personalized suggestions to be provided to the user and for suggestions to be revised based on feedback.

[1016] "User" refers to an individual who uses this system.

[1017] "Lifestyle Data" refers to data including information about a user's daily activities, eating habits, exercise history, and hobbies.

[1018] "Means of collection" refers to the devices and applications used to collect users' lifestyle data.

[1019] "Means of storage" refers to the means for storing collected lifestyle data in a database or the like.

[1020] "Means of analysis" refers to artificial intelligence and data processing technologies used to analyze collected lifestyle data and extract insights and trends.

[1021] "Means for generating suggestions" refers to means for creating suggestions suitable for the user based on the analysis results.

[1022] "Means for notifying suggestions" refers to means for notifying a user of generated suggestions.

[1023] "Means for modifying suggestions based on feedback" refers to means for analyzing user feedback and modifying suggestions based on the results of that analysis.

[1024] "Database" refers to a system for storing and managing collected lifestyle data.

[1025] "Artificial intelligence model" refers to the machine learning models and algorithms used to analyze life data, extract insights, and generate recommendations.

[1026] "Means of extracting insights" refers to techniques for finding important information and trends from analyzed data.

[1027] "Personalization" refers to customizing recommendations based on a user's specific preferences and behavior.

[1028] The present invention is a system that collects and analyzes users' life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. Specific embodiments are described below.

[1029] 1. Collection of lifestyle data

[1030] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies. Data collection is done through devices such as smartphone apps, smartwatches, and fitness trackers. For example, when a user enters their meal history into a smartphone app, the data is automatically sent from the device to a server.

[1031] 2. Data storage

[1032] The server stores the lifestyle data sent from the device in a database for later analysis. For example, the server stores a user's exercise history for one week in a database.

[1033] 3. Data Analysis

[1034] The server analyzes the stored lifestyle data. This analysis uses artificial intelligence (generative AI models) to extract insights and trends from the data. For example, it can determine whether a user's nutritional balance is unbalanced based on their dietary history.

[1035] 4. Proposal Generation

[1036] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[1037] 5. Notification of Proposal

[1038] The device notifies the user of the suggestions received from the server. The notification is done through voice, so the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[1039] 6. User Feedback

[1040] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[1041] 7. Proposal Modifications

[1042] The server then modifies the suggestions based on the user's feedback. The modified suggestions are then sent to the user via the device. For example, the server might regenerate a suggestion such as "We recommend olive oil and lemon dressing for your salad," and the device would then notify the user.

[1043] Specific examples

[1044] For example, suppose a user logs into a smartphone app that they "ate pizza for dinner yesterday." The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.). As a result, the server generates a suggestion such as, "Since you ate pizza yesterday, I recommend you choose a salad today to get more vegetables." The device then notifies the user by voice, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?" The user responds, "Salads sound good, but could you also recommend a dressing?" Based on this feedback, the server modifies the suggestion to, "I recommend olive oil and lemon dressing for the salad," and notifies them again.

[1045] Prompt Sentence Examples

[1046] "Please explain how to build a system that collects and analyzes lifestyle data and generates optimal health management suggestions for users."

[1047] "Please give us a concrete example of a system that collects and analyzes food logs and provides personalized meal suggestions."

[1048] This invention allows users to easily choose a balanced diet and adopt healthy lifestyle habits. Furthermore, by repeating this cycle, the accuracy of the suggestions will improve, making it possible to provide more useful advice to users.

[1049] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1050] Step 1: Collecting lifestyle data

[1051] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1052] Input: Data recorded by users via smartphone apps, smartwatches, and fitness trackers.

[1053] What it does: The phone receives data from these devices via Bluetooth or Wi-Fi and stores it in a formatted form on its internal memory.

[1054] Output: The collected user lifestyle data is temporarily stored on the device.

[1055] Step 2: Send the data log

[1056] The terminal transmits the collected data to the server in real time.

[1057] Input: Life data stored on the device.

[1058] How it works: The device sends life data to the server at regular intervals or when the data is updated. Data transfer is encrypted and protected using the HTTPS protocol.

[1059] Output: The collected data is transferred to the server.

[1060] Step 3: Save your data

[1061] The server stores the received data in a database.

[1062] Input: Life data sent from the device.

[1063] Specific operation: The server stores the received data using a database management system (e.g., MySQL or PostgreSQL). The data integrity is checked and invalid data is removed.

[1064] Output: Life data is accurately stored in the database.

[1065] Step 4: Preprocessing the data

[1066] The server cleans the collected data and converts it into a format suitable for analysis.

[1067] Input: Life data stored in a database.

[1068] What it does: The server imputes missing values ​​from the data, removes noise, and normalizes the data, for example, correcting anomalous numerical data and encoding categorical data.

[1069] Output: A preprocessed and clean dataset.

[1070] Step 5: Analyze the data

[1071] The server uses the pre-processed data to analyze it using a generative AI model.

[1072] Input: Preprocessed lifestyle dataset.

[1073] Specific operation: The server inputs data into a machine learning model (e.g., a deep learning model) and performs analysis, thereby extracting trends in the user's behavioral patterns and health status.

[1074] Output: The insights and trends extracted as a result of the analysis.

[1075] Step 6: Generate proposals

[1076] The server generates personalized offers based on the analysis results.

[1077] Input: Insights and trends based on analytical results.

[1078] Specific operation: The server uses a proposal generation algorithm to create specific proposals that will help the user manage their health and improve their lifestyle. For example, a proposal might be generated such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[1079] Output: The individual suggestions generated.

[1080] Step 7: Prepare your proposal

[1081] The server formats the proposals to be sent to the user and converts them into a format that can be sent to the terminal.

[1082] Input: Generated suggestions.

[1083] Specific operation: The proposal content is converted into natural language that is easy for the user to understand, and speech synthesis data is also prepared if necessary.

[1084] Output: Formatted proposal data.

[1085] Step 8: Sending notifications

[1086] The device notifies the user of the received proposal.

[1087] Input: Formatted proposal data.

[1088] What it does: The device notifies the user of the suggestion using voice or text message, for example, "You had pizza yesterday, so I suggest you have a salad today."

[1089] Output: The suggestion that was notified to the user.

[1090] Step 9: Accepting feedback

[1091] Users provide feedback on the suggestions.

[1092] Input: User response based on suggestions.

[1093] What happens: The user provides feedback via voice or text, such as a request like, "The salad is great, but can you recommend a dressing?"

[1094] Output: User feedback data.

[1095] Step 10: Submit your feedback

[1096] The device sends the feedback from the user to the server.

[1097] Input: User feedback data.

[1098] Specific operation: The terminal sends feedback data to the server using the HTTPS protocol.

[1099] Output: Feedback data sent to the server.

[1100] Step 11: Analyze feedback

[1101] The server analyzes the received feedback to help refine the proposal.

[1102] Input: User feedback data.

[1103] Specific operation: The server uses natural language processing technology to analyze the content of the feedback and extract the user's requests and comments.

[1104] Output: Insights for revision based on feedback.

[1105] Step 12: Modifying the proposal

[1106] The server then modifies the suggestions based on user feedback.

[1107] Input: Insights based on feedback.

[1108] What happens: The server reapplies the suggestion generation algorithm to create a new suggestion that reflects the user's requests and comments, e.g., "I recommend olive oil and lemon dressing for salads."

[1109] Output: The revised proposal.

[1110] Step 13: Send a reminder

[1111] The device will notify the user again with the revised suggestions.

[1112] Input: Revised proposal.

[1113] What happens: The device notifies the user using voice or text message with the revised suggestion, for example, reminding them, "We recommend olive oil and lemon dressing on your salad."

[1114] Output: The suggestion that was snoozed to the user.

[1115] (Application example 1)

[1116] 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."

[1117] In modern society, health management tailored to individual lifestyles and eating habits is considered important, but there is a problem in that generic health suggestions cannot meet the different needs of each user. In particular, the lack of specific suggestions for dietary habits makes it difficult for individual users to maintain appropriate eating habits. In addition, the lack of advice on specific seasonings and ingredient selection for meals makes it difficult for users to eat a diet that suits their own health condition.

[1118] 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.

[1119] In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual suggestions based on the analysis results, means for notifying the user of the generated suggestions, means for modifying the suggestions based on the user's feedback, means for generating and notifying specific meal suggestions based on the lifestyle data, and means for analyzing the feedback content selected by the user based on the suggestions and suggesting seasonings suitable for the meal menu. This enables users to receive optimal health management and specific meal suggestions tailored to their individual lifestyles and eating habits.

[1120] "User lifestyle data" refers to information related to a user's daily activities, eating habits, exercise history, hobbies, etc.

[1121] "Means of collection" refers to devices and methods for obtaining and recording users' lifestyle data.

[1122] "Means for analysis" refers to systems and methods for processing collected lifestyle data and extracting useful information and trends.

[1123] "Means for generating recommendations" refers to a process or device that generates personalized advice or recommendations based on the results of the analysis.

[1124] "Means for notifying suggestions" refers to the functions and devices used to communicate the generated suggestions to users.

[1125] "Means for revising suggestions" refers to a method or system for revising existing suggestions based on user feedback.

[1126] "Specific meal suggestions" refers to advice recommending specific ingredients and menus based on the user's lifestyle data.

[1127] The "means for suggesting seasonings" refers to a function or method for providing seasonings and seasoning methods suitable for the proposed meal menu.

[1128] The present invention is a system that collects and analyzes users' lifestyle data, and generates, notifies, and modifies personalized suggestions based on that data. Specifically, the system is comprised of the following processes:

[1129] 1. System Programming

[1130] The system has the following main program flow:

[1131] Collection of lifestyle data

[1132] Devices (such as smartphones, smartwatches, and fitness trackers) collect data about users' daily activities, eating habits, exercise history, and hobbies. For example, a user logs in a smartphone app that they "ate pizza for dinner last night." This data is then sent from the device to a server.

[1133] Data analysis

[1134] The server receives and analyzes the lifestyle data sent from the device. This analysis uses a generative AI model to extract insights and trends from the user's lifestyle data. For example, it can evaluate the nutritional content (calories, fat, carbohydrates, etc.) of a pizza to determine whether it is nutritionally unbalanced.

[1135] Proposal Generation

[1136] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, a suggestion might be, "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[1137] Proposal Notification

[1138] The device notifies the user of the suggestions received from the server. The notification is done through voice, and the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[1139] User Feedback

[1140] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[1141] Proposal amendments

[1142] The server then modifies the suggestions based on the user's feedback, and the modified suggestions are then sent to the user via the device. For example, the server might regenerate the suggestion, "We recommend olive oil and lemon dressing for your salad," and the device would notify the user.

[1143] 2. Hardware and Software Used

[1144] This system uses the following hardware and software:

[1145] Smartphone: A device for inputting user data (such as meal contents).

[1146] Server: Analyzes data, generates suggestions, and manages feedback.

[1147] Generative AI models: Used to analyze data and generate recommendations.

[1148] For example: Machine learning libraries such as TensorFlow, Keras, etc.

[1149] 3. Examples and prompts

[1150] If a user inputs "I had pizza for dinner last night," the system will proceed as follows: The server will analyze the nutritional information (calories, fat, carbohydrates, etc.) of the pizza and generate a suggestion, for example using the following prompt:

[1151] Example prompt sentence:

[1152] The user ate pizza yesterday. It was high in calories, so we recommend a meal with lots of vegetables today.

[1153] The system provides users with specific and personalized suggestions for living a healthy life, enabling them to receive optimal health management tailored to their individual lifestyles and eating habits.

[1154] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1155] Step 1:

[1156] The user enters meal information into the app.

[1157] Input: The user enters meal details (e.g., "I had pizza for dinner last night") into a smartphone app.

[1158] Processing: The smartphone app sends the entered meal information to the server.

[1159] Output: The server receives the meal data and stores it in a database.

[1160] Step 2:

[1161] The server analyzes lifestyle data.

[1162] Input: The server retrieves the user's lifestyle data from the database.

[1163] Processing: The server analyzes the acquired data using a generative AI model. Specifically, it evaluates nutritional components (calories, fat, carbohydrates, etc.) and determines the user's nutritional balance.

[1164] Output: A report is generated based on the analysis results, which contains details of the user's nutritional balance.

[1165] Step 3:

[1166] The server generates personalized offers.

[1167] Input: Analysis results (report)

[1168] Processing: The server uses the generative AI model based on the analysis results to create personalized meal recommendations, such as "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[1169] Output: The generated proposal is added to the notification queue.

[1170] Step 4:

[1171] The device will notify the user of the suggestion.

[1172] Input: Notification queue proposal data

[1173] Processing: The smartphone app will notify the user of the suggestion by voice, for example, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[1174] Output: The user receives the suggestions aloud.

[1175] Step 5:

[1176] Users provide feedback.

[1177] Input: User feedback on the suggestion (e.g., "The salad sounds good, but could you recommend a dressing?")

[1178] Processing: The user enters feedback via the smartphone app and sends it to the server.

[1179] Output: The feedback data is received by the server and added to the feedback queue.

[1180] Step 6:

[1181] The server modifies the proposal based on the feedback.

[1182] Input: Feedback data

[1183] Processing: The server analyzes the feedback data and uses a generative AI model to refine the suggestions, for example, creating a new suggestion such as "I recommend olive oil and lemon dressing for your salad."

[1184] Output: The revised proposal is added back to the notification queue.

[1185] Step 7:

[1186] The device will notify the user again with the revised suggestion.

[1187] Input: Proposed correction data

[1188] Action: The smartphone app will re-announce the suggested revision to the user, for example, "We recommend olive oil and lemon dressing for your salad."

[1189] Output: The user receives the revised suggestion aloud.

[1190] 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.

[1191] The present invention is a system that collects and analyzes users' daily life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. This system also combines an emotion engine that recognizes users' emotions to provide more appropriate and personalized suggestions to users.

[1192] 1. Collection of lifestyle data

[1193] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1194] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[1195] For example, if a user logs the contents of their meal in a smartphone app, the data is sent from the device to a server.

[1196] 2. Collecting Emotional Data

[1197] The device utilizes an emotion engine to collect user emotion data.

[1198] The emotion engine uses cameras, microphones, biometric sensors, etc. to analyze the user's facial expressions, tone of voice, heart rate, etc. to identify their emotional state.

[1199] For example, while a user is using a smartphone app, the camera captures their facial expressions, and based on that, the emotion engine recognizes emotions such as "joy," "anger," and "sadness."

[1200] 3. Data Analysis

[1201] The server analyzes the lifestyle data and emotion data sent from the device.

[1202] The analysis uses artificial intelligence algorithms to extract insights and trends from user data.

[1203] For example, it analyzes a user's eating history and emotional data to assess the impact that a particular meal has on the user's emotions.

[1204] 4. Proposal Generation

[1205] The server generates personalized offers based on the analysis results.

[1206] Suggestions include exercise plans, dietary advice, and help with hobbies to help you manage your health, and the app also adjusts the suggestions based on your emotional state.

[1207] For example, it generates specific suggestions such as, "Since you ate pizza yesterday, we recommend that you choose a salad today to get more vegetables."

[1208] 5. Notification of Proposal

[1209] The terminal notifies the user of the proposal received from the server.

[1210] Notifications are delivered via audio, allowing users to actually interact with the device.

[1211] For example, the device may say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[1212] 6. User Feedback

[1213] Users provide feedback on the suggestions.

[1214] The feedback is sent to the server through the device.

[1215] For example, a user might provide feedback such as, "The salad is good, but can you recommend a dressing?"

[1216] 7. Proposal Modifications

[1217] The server then refines the suggestions based on user feedback and sentiment data.

[1218] The revised suggestions will be notified to the user again via the device.

[1219] For example, the server may modify the content to say, "We recommend olive oil and lemon dressing for your salad," and the terminal will notify you of this.

[1220] As a specific example, consider the following case.

[1221] Specific examples

[1222] Meal suggestion examples

[1223] 1. Data Collection

[1224] When a user logs into a smartphone app saying, "I had pizza for dinner last night," the device's facial recognition camera detects that the user is smiling, and the emotion engine then uses that information to identify the user.

[1225] 2. Data Analysis

[1226] The server analyzes this data and evaluates the pizza's nutritional content (calories, fat, carbohydrates, etc.), taking into account the user's happy emotions after eating the pizza.

[1227] 3. Proposal generation

[1228] The server generates a suggestion: "You seemed happy eating pizza yesterday, so today I suggest you eat more vegetables for a healthy balance."

[1229] 4. Proposal Notice

[1230] The device will announce in a voice message, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific dressing suggestions?"

[1231] 5. User Feedback

[1232] The user responds, "Please also tell me what dressing you would recommend to go with the salad," and the device sends this feedback to the server.

[1233] 6. Proposal modification

[1234] The server amends the suggestion to "The salad would benefit from a little olive oil and lemon dressing" and sends it to the terminal again.

[1235] Through this system, users will receive healthy suggestions that take their emotional data into account, allowing them to make choices that better suit their lifestyle.

[1236] The processing flow will be explained below.

[1237] Step 1:

[1238] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[1239] Step 2:

[1240] The device uses a camera, microphone, and biometric sensors to analyze the user's facial expressions, tone of voice, and heart rate using an emotion engine, for example, to detect if the user is smiling after eating pizza.

[1241] Step 3:

[1242] The device sends the collected lifestyle data and emotional data to a server, which then uploads the log data and emotional data to the server via the Internet.

[1243] Step 4:

[1244] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and analyze the user's emotional state. It also refers to past data to evaluate the relationship between the user's nutritional balance and their emotions.

[1245] Step 5:

[1246] The server generates recommendations based on the analysis results, such as "You seemed happy after eating pizza yesterday, so I recommend you eat more vegetables today to achieve a healthy balance."

[1247] Step 6:

[1248] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[1249] Step 7:

[1250] The device will notify the user of the received suggestions via voice. The device will say, "Since you had pizza yesterday, I recommend you have a salad today. Would you like some specific suggestions on dressings?" The user can listen to the suggestions via voice.

[1251] Step 8:

[1252] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[1253] Step 9:

[1254] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[1255] Step 10:

[1256] The server then modifies the suggestion based on the user's feedback and sentiment data, resending it to "You might want to use a little olive oil and lemon dressing on your salad" and sending it back to the device.

[1257] Step 11:

[1258] The device then notifies the user again with the revised suggestion, saying, "We recommend olive oil and lemon dressing on your salad." The user accepts and implements this suggestion.

[1259] Through these steps, the audio glasses system can provide users with continuously optimized health advice to improve the quality of their daily lives, and by combining it with an emotion engine, it can make suggestions based on the user's emotional state, providing more personalized support.

[1260] Example 2

[1261] 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."

[1262] Many modern personalized health management and lifestyle recommendation systems collect and use user lifestyle data to make recommendations. However, these systems do not take into account the user's emotional data, and recommendations may not match the user's emotional state. As a result, there are problems with low user acceptance and satisfaction. Furthermore, conventional systems are unable to properly reflect user feedback, limiting the accuracy and effectiveness of recommendations. To solve these issues, a system is needed that collects and analyzes not only the user's lifestyle data but also their emotional data, and generates and modifies recommendations based on that data.

[1263] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user life data and emotional data, means for analyzing the collected life data and emotional data, means for generating personalized proposals based on the analysis results, means for notifying the user of the generated proposals, and means for modifying the proposals based on the user's feedback and emotional data. This makes it possible to provide personalized proposals that match the user's emotional state, thereby improving user satisfaction and proposal acceptance. Furthermore, by reflecting user feedback, the accuracy and effectiveness of the proposals can be further improved.

[1264] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[1265] "Emotional data" is information used to analyze a user's facial expressions, tone of voice, heart rate, etc., to identify emotional states such as joy, anger, and sadness.

[1266] "Means of collection" refers to the methods of obtaining data using devices such as smartphones, smartwatches, and fitness trackers.

[1267] "Means of analysis" refers to the use of artificial intelligence algorithms to analyze collected data and extract insights and trends.

[1268] "Means for generating recommendations" refers to a method for generating personalized health management and lifestyle recommendations based on the analysis results.

[1269] The "notification method" is the method for notifying the user of the generated suggestions, such as by voice or text message.

[1270] "Means to modify suggestions" refers to ways to improve existing suggestions based on user feedback and additional sentiment data.

[1271] The present invention is a set of systems that collect and analyze users' life data and emotional data, generate and notify personalized suggestions, and modify these suggestions based on users' feedback and emotional data. The system further incorporates an emotional engine to provide more appropriate and personalized suggestions to users.

[1272] In order to implement this system, the following specific means are used.

[1273] 1. Collection of lifestyle and emotional data

[1274] The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data on users' daily activities, dietary habits, exercise history, and hobbies. Furthermore, the device utilizes an emotion engine to analyze the user's facial expressions, tone of voice, heart rate, and other data using cameras, microphones, and biometric sensors to identify their emotional state.

[1275] For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," the data is sent from the device to the server. At the same time, the camera captures the user's face, and the emotion engine detects "happiness."

[1276] 2. Data Analysis

[1277] The server analyzes the lifestyle and emotional data sent from the device, using artificial intelligence algorithms to extract insights and trends from the user's data.

[1278] For example, the server receives the log "I had pizza for dinner last night" and the "pleasure" data from the emotion engine, and analyzes these data using a human artificial intelligence algorithm to evaluate the impact that a particular meal has on the user's emotions.

[1279] 3. Proposal Generation

[1280] The server generates personalized recommendations based on the analysis, including exercise plans and dietary advice to help manage your health, tailored based on your emotional state.

[1281] For example, the server generates a suggestion such as, "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, the suggestion includes a detailed suggestion such as, "I recommend a salad today."

[1282] 4. Notification of Proposal

[1283] The device notifies the user of the suggestions it receives from the server, and the notification is done via voice, allowing the user to actually interact with the device.

[1284] For example, the device might say to the user, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific suggestions for dressing?"

[1285] 5. User Feedback

[1286] The user provides feedback on the suggestions, which is sent to the server via the device.

[1287] For example, the user might respond, "The salad is good, but could you recommend a dressing?" and the device would send this feedback to the server.

[1288] 6. Proposal Modifications

[1289] The server then modifies the suggestions based on the user's feedback and emotional data, and the modified suggestions are then sent back to the user via their device.

[1290] For example, the server might revise the suggestion to, "You might want to use a little olive oil and lemon dressing on the salad," and the device would reiterate this aloud.

[1291] Through this system, users can receive healthy suggestions that take into account their emotional data and make choices that better suit their lifestyle.

[1292] Examples of prompt statements

[1293] "You logged that you had pizza for dinner yesterday. What suggestions would you generate and how would you notify me? Also, explain how you would refine the suggestions based on user feedback."

[1294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1295] Step 1: Collecting lifestyle and emotional data

[1296] Description: The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data about a user's daily activities, eating habits, exercise history, and hobbies.

[1297] Input: Data about the user's daily activities, eating habits, exercise history, and hobbies.

[1298] Data Processing: Collected data is aggregated from each device in a centralized format.

[1299] Output: Centralized lifestyle data.

[1300] Specific operation: For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," that data is sent from the device to the server. The device then uses an emotion engine and a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[1301] Step 2: Sending data

[1302] Description: The device sends the collected life data and emotion data to the server.

[1303] Input: Centralized life and emotion data.

[1304] Data processing: None in particular.

[1305] Output: The data sent to the server.

[1306] Specific operation: The device sends the log "I had pizza for dinner yesterday" and the emotion data "joy" to the server.

[1307] Step 3: Analyze the data

[1308] Description: The server analyzes the life data and emotion data sent from the device.

[1309] Input: Life data and emotion data.

[1310] Data processing: Using artificial intelligence algorithms to extract insights and trends from data.

[1311] Output: Analysis results.

[1312] Specific operation: The server uses the log of "I had pizza for dinner yesterday" and the emotion data of "happiness" to evaluate the impact of the user's eating habits on their emotions.

[1313] Step 4: Generate proposals

[1314] Description: The server generates personalized offers based on the analysis results.

[1315] Input: Analysis results.

[1316] Data processing: Based on the analysis results, health management and lifestyle suggestions are created.

[1317] Output: Individual proposals.

[1318] Specific behavior: The server generates a suggestion such as "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, it includes a detailed suggestion such as "I recommend a salad today."

[1319] Step 5: Proposal Notification

[1320] Description: The device notifies the user of the offers received from the server.

[1321] Input: A suggestion from the server.

[1322] Data processing: None in particular.

[1323] Output: Notification to the user.

[1324] Specific behavior: The device will notify the user by voice, "You had pizza yesterday, so I recommend you have a salad today. Would you like some specific dressing suggestions?"

[1325] Step 6: User feedback

[1326] Description: The user provides feedback on the suggestions and sends it to the server via the device.

[1327] Input: User feedback.

[1328] Data processing: None in particular.

[1329] Output: Feedback sent to the server.

[1330] Specific behavior: The user responds, "The salad is good, but could you recommend a dressing?" and the device sends this feedback to the server.

[1331] Step 7: Modify the proposal

[1332] Description: The server modifies the suggestions based on user feedback and sentiment data.

[1333] Input: Feedback and emotion data.

[1334] Data processing: Analyze feedback and sentiment data and update suggestions.

[1335] Output: The revised proposal.

[1336] Specific behavior: The server modifies the suggestion to "You might want to use a little olive oil and lemon dressing on the salad" and notifies the user again via the device.

[1337] Through this series of processing steps, users receive healthy suggestions that take emotional data into account, allowing them to make choices that better suit their lifestyle.

[1338] (Application example 2)

[1339] 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."

[1340] Modern consumers have diverse preferences and emotional states, and there is a demand for personalized shopping experiences based on these. However, conventional systems have had difficulty effectively utilizing users' lifestyle and emotional data to make appropriate product recommendations in real time. Furthermore, there was no established method for efficiently collecting and analyzing feedback to improve the accuracy of recommendations. The present invention aims to solve these issues and provide a system that provides users with optimal product recommendations.

[1341] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on the user's purchase history. This enables real-time, personalized product proposals that take into account the user's preferences and emotional state.

[1342] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[1343] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, tone of voice, heart rate, etc.

[1344] "Analytics" refers to the methods used to assess user behavior, preferences, and emotional states based on collected data to extract insights and trends.

[1345] "Proposal generation means" refers to a method for creating personalized proposals for a user based on the analysis results.

[1346] "Notification means" refers to the method for communicating generated suggestions to the user.

[1347] "Feedback channels" are ways to gather responses and opinions from users and use them to refine your proposals.

[1348] "Purchase history" refers to a record of products and services a user has purchased in the past.

[1349] "Product suggestions" refer to products and services recommended to users based on their lifestyle data, emotional data, and purchasing history.

[1350] The present invention provides a system that collects user lifestyle data and emotion data, analyzes the data, generates and notifies personalized suggestions, and modifies the suggestions based on user feedback. The system is configured as follows.

[1351] The server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on purchase history.

[1352] Hardware and software used

[1353] Hardware:

[1354] Cameras (e.g., cameras built into smart glasses or smartphones)

[1355] Microphones (e.g., microphones built into smart glasses or smartphones)

[1356] software:

[1357] OpenCV: A framework for real-time processing of camera images

[1358] SpeechRecognition: A library for analyzing speech

[1359] Requests: Library for data communication with the server

[1360] EmotionRecognizer: Emotion recognition engine

[1361] Data processing and calculation

[1362] The device (e.g., smart glasses or smartphone) captures the user's facial expressions and voice in real time. It uses a camera to acquire the user's facial expression data, processes the images using OpenCV, and then analyzes the emotion data using EmotionRecognizer.

[1363] The microphone is used to capture the user's voice data, and the speech is converted into text using the SpeechRecognition library. This data is then combined and sent to the server using the Requests library. The server receives the data, analyzes it, and generates personalized product suggestions for the user. The suggestions are then sent back to the device and notified to the user.

[1364] Specific examples

[1365] For example, imagine a user is shopping in a physical store. Smart glasses capture the user's facial expression data and detect whether the user is enjoying themselves. If the user also says, "I've been feeling tired lately," the system collects this as text data. This data is sent to a server and analyzed along with the user's purchase history. As a result, personalized products such as "tea with a relaxing effect" are suggested.

[1366] Prompt Sentence Examples

[1367] Create a recommendation for a brick-and-mortar shopping assistant that collects emotional data from users' facial expressions and voice, and analyzes it along with their purchasing history. Generate optimal product recommendations for users based on the following data:

[1368] A list of items recently purchased by the user

[1369] User facial expression data

[1370] User voice data

[1371] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1372] Step 1:

[1373] The user wears smart glasses or a smartphone, and the device captures their facial expressions and voice. The device acquires the user's facial expression data through the camera and processes the image data using OpenCV. It also acquires voice data using the microphone and converts the voice into text data using the SpeechRecognition library. The input is the user's facial expression and voice, and the output is processed facial expression data and text data.

[1374] Step 2:

[1375] The device converts the acquired facial expression data into emotional data using EmotionRecognizer. Specifically, it recognizes emotions such as "happiness," "anger," and "sadness" from the user's facial expressions in real time and stores them as digital data. The input is processed facial expression data, and the output is emotional data.

[1376] Step 3:

[1377] The device integrates emotion data and speech-to-text data and sends it to the server using the Requests library. The data sent includes the user's emotion data, speech-to-text data, and purchase history. In this case, the input is emotion data and speech-to-text data, and the output is a request containing these data.

[1378] Step 4:

[1379] The server analyzes the received data and generates product suggestions suitable for the user. It uses an AI algorithm to evaluate the user's lifestyle and emotional data to generate personalized product suggestions. The input is emotional data, voice and text data, and purchase history, and the output is product suggestions.

[1380] Step 5:

[1381] The server sends the generated product suggestions to the terminal. At this time, the information notified to the user includes details of the suggested products and the reasons for them. The input is the product suggestions, and the output is a notification to the user.

[1382] Step 6:

[1383] The user provides feedback on the received product suggestions. The terminal transmits the user's feedback to the server again. At this time, the input is the user's feedback and the output is a request to the server.

[1384] Step 7:

[1385] The server analyzes the user's feedback and modifies the proposal if necessary. The modified proposal is then notified to the user again. The input is the user's feedback and the output is the modified proposal.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] [Fourth embodiment]

[1390] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1391] 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.

[1392] 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).

[1393] 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.

[1394] 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.

[1395] 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).

[1396] 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. 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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."

[1403] The present invention is a system that collects and analyzes a user's lifestyle data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. The system includes programs for executing the processes of collection, analysis, suggestion, notification, and feedback.

[1404] 1. Collection of lifestyle data

[1405] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1406] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[1407] For example, if a user logs the contents of their meal on a smartphone app, the data is automatically sent from the device to the server.

[1408] 2. Data Analysis

[1409] The server analyzes the life data sent from the device.

[1410] This analysis uses artificial intelligence to extract insights and trends from user data.

[1411] For example, it analyzes a user's dietary history to determine whether their nutritional balance is unbalanced.

[1412] 3. Proposal Generation

[1413] The server generates personalized offers based on the analysis results.

[1414] Suggestions include exercise plans and dietary advice to help manage your health, as well as support on how to enjoy hobbies.

[1415] For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to get more vegetables."

[1416] 4. Notification of Proposal

[1417] The terminal notifies the user of the proposal received from the server.

[1418] Notifications are delivered via audio, allowing users to actually interact with the device.

[1419] For example, the device might say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[1420] 5. User Feedback

[1421] Users provide feedback on the suggestions.

[1422] The feedback is sent to the server through the device.

[1423] For example, a user might provide feedback like, "The salad sounds good, but can you recommend a dressing?"

[1424] 6. Proposal Modifications

[1425] The server then modifies the suggestions based on user feedback.

[1426] The revised suggestions will be notified to the user again via the device.

[1427] For example, the server reproduces the content "We recommend olive oil and lemon dressing for your salad," and the terminal notifies this.

[1428] As a specific example, consider the following case.

[1429] Specific examples

[1430] Meal suggestion examples

[1431] 1. Data Collection

[1432] A user logs into a smartphone app, "I had pizza for dinner last night."

[1433] 2. Data Analysis

[1434] The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.).

[1435] 3. Proposal generation

[1436] The server generates a suggestion like, "Since you had pizza yesterday, we recommend you choose a salad today to get more vegetables."

[1437] 4. Proposal Notice

[1438] The device will announce in a voice message, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[1439] 5. User Feedback

[1440] The user replies, "Salad sounds good, but can you recommend a dressing?"

[1441] 6. Proposal modification

[1442] The server corrects the suggestion to "I recommend olive oil and lemon dressing for the salad" and notifies again.

[1443] This allows users to easily make balanced dietary choices, and by repeating this cycle, the accuracy of the suggestions will improve, allowing for more useful advice to be provided to users.

[1444] The processing flow will be explained below.

[1445] Step 1:

[1446] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[1447] Step 2:

[1448] The device sends the collected lifestyle data to a server, and the device uploads log data to the server via the Internet. This data includes meal contents, meal times, and meal amounts.

[1449] Step 3:

[1450] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and also references past data to evaluate the user's nutritional intake balance.

[1451] Step 4:

[1452] The server generates a suggestion based on the analysis results, such as "Since you ate pizza yesterday, we recommend you choose a salad today to get more vegetables."

[1453] Step 5:

[1454] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[1455] Step 6:

[1456] The device will notify the user of the received suggestion by voice. The device will notify, "Since you had pizza yesterday, I recommend you eat a salad today. What do you think?" The user can listen to the suggestion by voice.

[1457] Step 7:

[1458] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[1459] Step 8:

[1460] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[1461] Step 9:

[1462] The server modifies the suggestion based on the user's feedback. The server regenerates the suggestion, "I recommend olive oil and lemon dressing for your salad," and sends it to the device.

[1463] Step 10:

[1464] The device will then re-promote the revised suggestion to the user, saying, "We recommend olive oil and lemon dressing on your salad."

[1465] Through these steps, the Audio Glasses system provides users with continuously optimized health advice to improve the quality of their daily lives.

[1466] Example 1

[1467] 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."

[1468] In today's busy lifestyles, supporting users in managing their health and improving their lifestyles requires suggestions tailored to their individual circumstances. However, conventional systems do not adequately analyze the data collected from users, resulting in insufficient individualization of suggestions and insufficient reflection of feedback. This makes it difficult to provide effective support for users in managing their health and improving their lifestyles, and reduces the accuracy and usefulness of suggestions.

[1469] 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.

[1470] In this invention, the server includes a means for collecting user lifestyle data, a means for storing the collected lifestyle data in a database, a means for analyzing the lifestyle data using an artificial intelligence model to extract insights, and a means for personalizing suggestions based on the user's preferences and behavioral data, thereby enabling highly accurate personalized suggestions to be provided to the user and for suggestions to be revised based on feedback.

[1471] "User" refers to an individual who uses this system.

[1472] "Lifestyle Data" refers to data including information about a user's daily activities, eating habits, exercise history, and hobbies.

[1473] "Means of collection" refers to the devices and applications used to collect users' lifestyle data.

[1474] "Means of storage" refers to the means for storing collected lifestyle data in a database or the like.

[1475] "Means of analysis" refers to artificial intelligence and data processing technologies used to analyze collected lifestyle data and extract insights and trends.

[1476] "Means for generating suggestions" refers to means for creating suggestions suitable for the user based on the analysis results.

[1477] "Means for notifying suggestions" refers to means for notifying a user of generated suggestions.

[1478] "Means for modifying suggestions based on feedback" refers to means for analyzing user feedback and modifying suggestions based on the results of that analysis.

[1479] "Database" refers to a system for storing and managing collected lifestyle data.

[1480] "Artificial intelligence model" refers to the machine learning models and algorithms used to analyze life data, extract insights, and generate recommendations.

[1481] "Means of extracting insights" refers to techniques for finding important information and trends from analyzed data.

[1482] "Personalization" refers to customizing recommendations based on a user's specific preferences and behavior.

[1483] The present invention is a system that collects and analyzes users' life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. Specific embodiments are described below.

[1484] 1. Collection of lifestyle data

[1485] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies. Data collection is done through devices such as smartphone apps, smartwatches, and fitness trackers. For example, when a user enters their meal history into a smartphone app, the data is automatically sent from the device to a server.

[1486] 2. Data storage

[1487] The server stores the lifestyle data sent from the device in a database for later analysis. For example, the server stores a user's exercise history for one week in a database.

[1488] 3. Data Analysis

[1489] The server analyzes the stored lifestyle data. This analysis uses artificial intelligence (generative AI models) to extract insights and trends from the data. For example, it can determine whether a user's nutritional balance is unbalanced based on their dietary history.

[1490] 4. Proposal Generation

[1491] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, it generates a specific suggestion such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[1492] 5. Notification of Proposal

[1493] The device notifies the user of the suggestions received from the server. The notification is done through voice, so the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[1494] 6. User Feedback

[1495] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[1496] 7. Proposal Modifications

[1497] The server then modifies the suggestions based on the user's feedback. The modified suggestions are then sent to the user via the device. For example, the server might regenerate a suggestion such as "We recommend olive oil and lemon dressing for your salad," and the device would then notify the user.

[1498] Specific examples

[1499] For example, suppose a user logs into a smartphone app that they "ate pizza for dinner yesterday." The server analyzes this data and evaluates the nutritional content of the pizza (calories, fat, carbohydrates, etc.). As a result, the server generates a suggestion such as, "Since you ate pizza yesterday, I recommend you choose a salad today to get more vegetables." The device then notifies the user by voice, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?" The user responds, "Salads sound good, but could you also recommend a dressing?" Based on this feedback, the server modifies the suggestion to, "I recommend olive oil and lemon dressing for the salad," and notifies them again.

[1500] Prompt Sentence Examples

[1501] "Please explain how to build a system that collects and analyzes lifestyle data and generates optimal health management suggestions for users."

[1502] "Please give us a concrete example of a system that collects and analyzes food logs and provides personalized meal suggestions."

[1503] This invention allows users to easily choose a balanced diet and adopt healthy lifestyle habits. Furthermore, by repeating this cycle, the accuracy of the suggestions will improve, making it possible to provide more useful advice to users.

[1504] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1505] Step 1: Collecting lifestyle data

[1506] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1507] Input: Data recorded by users via smartphone apps, smartwatches, and fitness trackers.

[1508] What it does: The phone receives data from these devices via Bluetooth or Wi-Fi and stores it in a formatted form on its internal memory.

[1509] Output: The collected user lifestyle data is temporarily stored on the device.

[1510] Step 2: Send the data log

[1511] The terminal transmits the collected data to the server in real time.

[1512] Input: Life data stored on the device.

[1513] How it works: The device sends life data to the server at regular intervals or when the data is updated. Data transfer is encrypted and protected using the HTTPS protocol.

[1514] Output: The collected data is transferred to the server.

[1515] Step 3: Save your data

[1516] The server stores the received data in a database.

[1517] Input: Life data sent from the device.

[1518] Specific operation: The server stores the received data using a database management system (e.g., MySQL or PostgreSQL). The data integrity is checked and invalid data is removed.

[1519] Output: Life data is accurately stored in the database.

[1520] Step 4: Preprocessing the data

[1521] The server cleans the collected data and converts it into a format suitable for analysis.

[1522] Input: Life data stored in a database.

[1523] What it does: The server imputes missing values ​​from the data, removes noise, and normalizes the data, for example, correcting anomalous numerical data and encoding categorical data.

[1524] Output: A preprocessed and clean dataset.

[1525] Step 5: Analyze the data

[1526] The server uses the pre-processed data to analyze it using a generative AI model.

[1527] Input: Preprocessed lifestyle dataset.

[1528] Specific operation: The server inputs data into a machine learning model (e.g., a deep learning model) and performs analysis, thereby extracting trends in the user's behavioral patterns and health status.

[1529] Output: The insights and trends extracted as a result of the analysis.

[1530] Step 6: Generate proposals

[1531] The server generates personalized offers based on the analysis results.

[1532] Input: Insights and trends based on analytical results.

[1533] Specific operation: The server uses a proposal generation algorithm to create specific proposals that will help the user manage their health and improve their lifestyle. For example, a proposal might be generated such as, "Since you ate pizza yesterday, I recommend a salad today to increase your intake of vegetables."

[1534] Output: The individual suggestions generated.

[1535] Step 7: Prepare your proposal

[1536] The server formats the proposals to be sent to the user and converts them into a format that can be sent to the terminal.

[1537] Input: Generated suggestions.

[1538] Specific operation: The proposal content is converted into natural language that is easy for the user to understand, and speech synthesis data is also prepared if necessary.

[1539] Output: Formatted proposal data.

[1540] Step 8: Sending notifications

[1541] The device notifies the user of the received proposal.

[1542] Input: Formatted proposal data.

[1543] What it does: The device notifies the user of the suggestion using voice or text message, for example, "You had pizza yesterday, so I suggest you have a salad today."

[1544] Output: The suggestion that was notified to the user.

[1545] Step 9: Accepting feedback

[1546] Users provide feedback on the suggestions.

[1547] Input: User response based on suggestions.

[1548] What happens: The user provides feedback via voice or text, such as a request like, "The salad is great, but can you recommend a dressing?"

[1549] Output: User feedback data.

[1550] Step 10: Submit your feedback

[1551] The device sends the feedback from the user to the server.

[1552] Input: User feedback data.

[1553] Specific operation: The terminal sends feedback data to the server using the HTTPS protocol.

[1554] Output: Feedback data sent to the server.

[1555] Step 11: Analyze feedback

[1556] The server analyzes the received feedback to help refine the proposal.

[1557] Input: User feedback data.

[1558] Specific operation: The server uses natural language processing technology to analyze the content of the feedback and extract the user's requests and comments.

[1559] Output: Insights for revision based on feedback.

[1560] Step 12: Modifying the proposal

[1561] The server then modifies the suggestions based on user feedback.

[1562] Input: Insights based on feedback.

[1563] What happens: The server reapplies the suggestion generation algorithm to create a new suggestion that reflects the user's requests and comments, e.g., "I recommend olive oil and lemon dressing for salads."

[1564] Output: The revised proposal.

[1565] Step 13: Send a reminder

[1566] The device will notify the user again with the revised suggestions.

[1567] Input: Revised proposal.

[1568] What happens: The device notifies the user using voice or text message with the revised suggestion, for example, reminding them, "We recommend olive oil and lemon dressing on your salad."

[1569] Output: The suggestion that was snoozed to the user.

[1570] (Application example 1)

[1571] 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."

[1572] In modern society, health management tailored to individual lifestyles and eating habits is considered important, but there is a problem in that generic health suggestions cannot meet the different needs of each user. In particular, the lack of specific suggestions for dietary habits makes it difficult for individual users to maintain appropriate eating habits. In addition, the lack of advice on specific seasonings and ingredient selection for meals makes it difficult for users to eat a diet that suits their own health condition.

[1573] 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.

[1574] In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual suggestions based on the analysis results, means for notifying the user of the generated suggestions, means for modifying the suggestions based on the user's feedback, means for generating and notifying specific meal suggestions based on the lifestyle data, and means for analyzing the feedback content selected by the user based on the suggestions and suggesting seasonings suitable for the meal menu. This enables users to receive optimal health management and specific meal suggestions tailored to their individual lifestyles and eating habits.

[1575] "User lifestyle data" refers to information related to a user's daily activities, eating habits, exercise history, hobbies, etc.

[1576] "Means of collection" refers to devices and methods for obtaining and recording users' lifestyle data.

[1577] "Means for analysis" refers to systems and methods for processing collected lifestyle data and extracting useful information and trends.

[1578] "Means for generating recommendations" refers to a process or device that generates personalized advice or recommendations based on the results of the analysis.

[1579] "Means for notifying suggestions" refers to the functions and devices used to communicate the generated suggestions to users.

[1580] "Means for revising suggestions" refers to a method or system for revising existing suggestions based on user feedback.

[1581] "Specific meal suggestions" refers to advice recommending specific ingredients and menus based on the user's lifestyle data.

[1582] The "means for suggesting seasonings" refers to a function or method for providing seasonings and seasoning methods suitable for the proposed meal menu.

[1583] The present invention is a system that collects and analyzes users' lifestyle data, and generates, notifies, and modifies personalized suggestions based on that data. Specifically, the system is comprised of the following processes:

[1584] 1. System Programming

[1585] The system has the following main program flow:

[1586] Collection of lifestyle data

[1587] Devices (such as smartphones, smartwatches, and fitness trackers) collect data about users' daily activities, eating habits, exercise history, and hobbies. For example, a user logs in a smartphone app that they "ate pizza for dinner last night." This data is then sent from the device to a server.

[1588] Data analysis

[1589] The server receives and analyzes the lifestyle data sent from the device. This analysis uses a generative AI model to extract insights and trends from the user's lifestyle data. For example, it can evaluate the nutritional content (calories, fat, carbohydrates, etc.) of a pizza to determine whether it is nutritionally unbalanced.

[1590] Proposal Generation

[1591] The server generates personalized suggestions based on the analysis results. These suggestions include exercise plans and dietary advice to help with health management, and support for hobbies. For example, a suggestion might be, "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[1592] Proposal Notification

[1593] The device notifies the user of the suggestions received from the server. The notification is done through voice, and the user can actually interact with the device. For example, the device might say, "Since you ate pizza yesterday, I recommend you eat a salad today. What do you think?"

[1594] User Feedback

[1595] The user provides feedback on the suggestions, which is sent to the server via the device. For example, the user might say, "The salad sounds good, but could you recommend a dressing?"

[1596] Proposal amendments

[1597] The server then modifies the suggestions based on the user's feedback, and the modified suggestions are then sent to the user via the device. For example, the server might regenerate the suggestion, "We recommend olive oil and lemon dressing for your salad," and the device would notify the user.

[1598] 2. Hardware and Software Used

[1599] This system uses the following hardware and software:

[1600] Smartphone: A device for inputting user data (such as meal contents).

[1601] Server: Analyzes data, generates suggestions, and manages feedback.

[1602] Generative AI models: Used to analyze data and generate recommendations.

[1603] For example: Machine learning libraries such as TensorFlow, Keras, etc.

[1604] 3. Examples and prompts

[1605] If a user inputs "I had pizza for dinner last night," the system will proceed as follows: The server will analyze the nutritional information (calories, fat, carbohydrates, etc.) of the pizza and generate a suggestion, for example using the following prompt:

[1606] Example prompt sentence:

[1607] The user ate pizza yesterday. It was high in calories, so we recommend a meal with lots of vegetables today.

[1608] The system provides users with specific and personalized suggestions for living a healthy life, enabling them to receive optimal health management tailored to their individual lifestyles and eating habits.

[1609] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1610] Step 1:

[1611] The user enters meal information into the app.

[1612] Input: The user enters meal details (e.g., "I had pizza for dinner last night") into a smartphone app.

[1613] Processing: The smartphone app sends the entered meal information to the server.

[1614] Output: The server receives the meal data and stores it in a database.

[1615] Step 2:

[1616] The server analyzes lifestyle data.

[1617] Input: The server retrieves the user's lifestyle data from the database.

[1618] Processing: The server analyzes the acquired data using a generative AI model. Specifically, it evaluates nutritional components (calories, fat, carbohydrates, etc.) and determines the user's nutritional balance.

[1619] Output: A report is generated based on the analysis results, which contains details of the user's nutritional balance.

[1620] Step 3:

[1621] The server generates personalized offers.

[1622] Input: Analysis results (report)

[1623] Processing: The server uses the generative AI model based on the analysis results to create personalized meal recommendations, such as "Since you ate pizza yesterday, we recommend choosing a salad today to get more vegetables."

[1624] Output: The generated proposal is added to the notification queue.

[1625] Step 4:

[1626] The device will notify the user of the suggestion.

[1627] Input: Notification queue proposal data

[1628] Processing: The smartphone app will notify the user of the suggestion by voice, for example, "You had pizza yesterday, so I recommend you have a salad today. What do you think?"

[1629] Output: The user receives the suggestions aloud.

[1630] Step 5:

[1631] Users provide feedback.

[1632] Input: User feedback on the suggestion (e.g., "The salad sounds good, but could you recommend a dressing?")

[1633] Processing: The user enters feedback via the smartphone app and sends it to the server.

[1634] Output: The feedback data is received by the server and added to the feedback queue.

[1635] Step 6:

[1636] The server modifies the proposal based on the feedback.

[1637] Input: Feedback data

[1638] Processing: The server analyzes the feedback data and uses a generative AI model to refine the suggestions, for example, creating a new suggestion such as "I recommend olive oil and lemon dressing for your salad."

[1639] Output: The revised proposal is added back to the notification queue.

[1640] Step 7:

[1641] The device will notify the user again with the revised suggestion.

[1642] Input: Proposed correction data

[1643] Action: The smartphone app will re-announce the suggested revision to the user, for example, "We recommend olive oil and lemon dressing for your salad."

[1644] Output: The user receives the revised suggestion aloud.

[1645] 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.

[1646] The present invention is a system that collects and analyzes users' daily life data, generates and notifies personalized suggestions, and modifies these suggestions based on feedback. This system also combines an emotion engine that recognizes users' emotions to provide more appropriate and personalized suggestions to users.

[1647] 1. Collection of lifestyle data

[1648] The device collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1649] Data collection is done using devices such as smartphone apps, smartwatches and fitness trackers.

[1650] For example, if a user logs the contents of their meal in a smartphone app, the data is sent from the device to a server.

[1651] 2. Collecting Emotional Data

[1652] The device utilizes an emotion engine to collect user emotion data.

[1653] The emotion engine uses cameras, microphones, biometric sensors, etc. to analyze the user's facial expressions, tone of voice, heart rate, etc. to identify their emotional state.

[1654] For example, while a user is using a smartphone app, the camera captures their facial expressions, and based on that, the emotion engine recognizes emotions such as "joy," "anger," and "sadness."

[1655] 3. Data Analysis

[1656] The server analyzes the lifestyle data and emotion data sent from the device.

[1657] The analysis uses artificial intelligence algorithms to extract insights and trends from user data.

[1658] For example, it analyzes a user's eating history and emotional data to assess the impact that a particular meal has on the user's emotions.

[1659] 4. Proposal Generation

[1660] The server generates personalized offers based on the analysis results.

[1661] Suggestions include exercise plans, dietary advice, and help with hobbies to help you manage your health, and the app also adjusts the suggestions based on your emotional state.

[1662] For example, it generates specific suggestions such as, "Since you ate pizza yesterday, we recommend that you choose a salad today to get more vegetables."

[1663] 5. Notification of Proposal

[1664] The terminal notifies the user of the proposal received from the server.

[1665] Notifications are delivered via audio, allowing users to actually interact with the device.

[1666] For example, the device may say, "You had pizza yesterday, so I recommend you eat a salad today. What do you think?"

[1667] 6. User Feedback

[1668] Users provide feedback on the suggestions.

[1669] The feedback is sent to the server through the device.

[1670] For example, a user might provide feedback such as, "The salad is good, but can you recommend a dressing?"

[1671] 7. Proposal Modifications

[1672] The server then refines the suggestions based on user feedback and sentiment data.

[1673] The revised suggestions will be notified to the user again via the device.

[1674] For example, the server may modify the content to say, "We recommend olive oil and lemon dressing for your salad," and the terminal will notify you of this.

[1675] As a specific example, consider the following case.

[1676] Specific examples

[1677] Meal suggestion examples

[1678] 1. Data Collection

[1679] When a user logs into a smartphone app saying, "I had pizza for dinner last night," the device's facial recognition camera detects that the user is smiling, and the emotion engine then uses that information to identify the user.

[1680] 2. Data Analysis

[1681] The server analyzes this data and evaluates the pizza's nutritional content (calories, fat, carbohydrates, etc.), taking into account the user's happy emotions after eating the pizza.

[1682] 3. Proposal generation

[1683] The server generates a suggestion: "You seemed happy eating pizza yesterday, so today I suggest you eat more vegetables for a healthy balance."

[1684] 4. Proposal Notice

[1685] The device will announce in a voice message, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific dressing suggestions?"

[1686] 5. User Feedback

[1687] The user responds, "Please also tell me what dressing you would recommend to go with the salad," and the device sends this feedback to the server.

[1688] 6. Proposal modification

[1689] The server amends the suggestion to "The salad would benefit from a little olive oil and lemon dressing" and sends it to the terminal again.

[1690] Through this system, users will receive healthy suggestions that take their emotional data into account, allowing them to make choices that better suit their lifestyle.

[1691] The processing flow will be explained below.

[1692] Step 1:

[1693] The device collects data about the user's daily life. For example, the user records in a smartphone app, "I had pizza for dinner yesterday." This information is automatically recorded by the device and sent to the server.

[1694] Step 2:

[1695] The device uses a camera, microphone, and biometric sensors to analyze the user's facial expressions, tone of voice, and heart rate using an emotion engine, for example, to detect if the user is smiling after eating pizza.

[1696] Step 3:

[1697] The device sends the collected lifestyle data and emotional data to a server, which then uploads the log data and emotional data to the server via the Internet.

[1698] Step 4:

[1699] The server analyzes the received data and uses an artificial intelligence algorithm to evaluate the nutritional content of the pizza (calories, fat, carbohydrates, etc.) and analyze the user's emotional state. It also refers to past data to evaluate the relationship between the user's nutritional balance and their emotions.

[1700] Step 5:

[1701] The server generates recommendations based on the analysis results, such as "You seemed happy after eating pizza yesterday, so I recommend you eat more vegetables today to achieve a healthy balance."

[1702] Step 6:

[1703] The server sends the generated proposal to the terminal, which then receives it via the Internet.

[1704] Step 7:

[1705] The device will notify the user of the received suggestions via voice. The device will say, "Since you had pizza yesterday, I recommend you have a salad today. Would you like some specific suggestions on dressings?" The user can listen to the suggestions via voice.

[1706] Step 8:

[1707] The user provides feedback on the suggestion, for example, "The salad sounds good, but what dressing would you recommend?" This feedback is sent to the server via the device.

[1708] Step 9:

[1709] The device sends the user's feedback to the server, which receives it and uses it to refine the proposal in the next step.

[1710] Step 10:

[1711] The server then modifies the suggestion based on the user's feedback and sentiment data, resending it to "You might want to use a little olive oil and lemon dressing on your salad" and sending it back to the device.

[1712] Step 11:

[1713] The device then notifies the user again with the revised suggestion, saying, "We recommend olive oil and lemon dressing on your salad." The user accepts and implements this suggestion.

[1714] Through these steps, the audio glasses system can provide users with continuously optimized health advice to improve the quality of their daily lives, and by combining it with an emotion engine, it can make suggestions based on the user's emotional state, providing more personalized support.

[1715] Example 2

[1716] 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."

[1717] Many modern personalized health management and lifestyle recommendation systems collect and use user lifestyle data to make recommendations. However, these systems do not take into account the user's emotional data, and recommendations may not match the user's emotional state. As a result, there are problems with low user acceptance and satisfaction. Furthermore, conventional systems are unable to properly reflect user feedback, limiting the accuracy and effectiveness of recommendations. To solve these issues, a system is needed that collects and analyzes not only the user's lifestyle data but also their emotional data, and generates and modifies recommendations based on that data.

[1718] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user life data and emotional data, means for analyzing the collected life data and emotional data, means for generating personalized proposals based on the analysis results, means for notifying the user of the generated proposals, and means for modifying the proposals based on the user's feedback and emotional data. This makes it possible to provide personalized proposals that match the user's emotional state, thereby improving user satisfaction and proposal acceptance. Furthermore, by reflecting user feedback, the accuracy and effectiveness of the proposals can be further improved.

[1719] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[1720] "Emotional data" is information used to analyze a user's facial expressions, tone of voice, heart rate, etc., to identify emotional states such as joy, anger, and sadness.

[1721] "Means of collection" refers to the methods of obtaining data using devices such as smartphones, smartwatches, and fitness trackers.

[1722] "Means of analysis" refers to the use of artificial intelligence algorithms to analyze collected data and extract insights and trends.

[1723] "Means for generating recommendations" refers to a method for generating personalized health management and lifestyle recommendations based on the analysis results.

[1724] The "notification method" is the method for notifying the user of the generated suggestions, such as by voice or text message.

[1725] "Means to modify suggestions" refers to ways to improve existing suggestions based on user feedback and additional sentiment data.

[1726] The present invention is a set of systems that collect and analyze users' life data and emotional data, generate and notify personalized suggestions, and modify these suggestions based on users' feedback and emotional data. The system further incorporates an emotional engine to provide more appropriate and personalized suggestions to users.

[1727] In order to implement this system, the following specific means are used.

[1728] 1. Collection of lifestyle and emotional data

[1729] The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data on users' daily activities, dietary habits, exercise history, and hobbies. Furthermore, the device utilizes an emotion engine to analyze the user's facial expressions, tone of voice, heart rate, and other data using cameras, microphones, and biometric sensors to identify their emotional state.

[1730] For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," the data is sent from the device to the server. At the same time, the camera captures the user's face, and the emotion engine detects "happiness."

[1731] 2. Data Analysis

[1732] The server analyzes the lifestyle and emotional data sent from the device, using artificial intelligence algorithms to extract insights and trends from the user's data.

[1733] For example, the server receives the log "I had pizza for dinner last night" and the "pleasure" data from the emotion engine, and analyzes these data using a human artificial intelligence algorithm to evaluate the impact that a particular meal has on the user's emotions.

[1734] 3. Proposal Generation

[1735] The server generates personalized recommendations based on the analysis, including exercise plans and dietary advice to help manage your health, tailored based on your emotional state.

[1736] For example, the server generates a suggestion such as, "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, the suggestion includes a detailed suggestion such as, "I recommend a salad today."

[1737] 4. Notification of Proposal

[1738] The device notifies the user of the suggestions it receives from the server, and the notification is done via voice, allowing the user to actually interact with the device.

[1739] For example, the device might say to the user, "Since you had pizza yesterday, we recommend you have a salad today. Would you like some specific suggestions for dressing?"

[1740] 5. User Feedback

[1741] The user provides feedback on the suggestions, which is sent to the server via the device.

[1742] For example, the user might respond, "The salad is good, but could you recommend a dressing?" and the device would send this feedback to the server.

[1743] 6. Proposal Modifications

[1744] The server then modifies the suggestions based on the user's feedback and emotional data, and the modified suggestions are then sent back to the user via their device.

[1745] For example, the server might revise the suggestion to, "You might want to use a little olive oil and lemon dressing on the salad," and the device would reiterate this aloud.

[1746] Through this system, users can receive healthy suggestions that take into account their emotional data and make choices that better suit their lifestyle.

[1747] Examples of prompt statements

[1748] "You logged that you had pizza for dinner yesterday. What suggestions would you generate and how would you notify me? Also, explain how you would refine the suggestions based on user feedback."

[1749] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1750] Step 1: Collecting lifestyle and emotional data

[1751] Description: The device uses devices such as smartphones, smartwatches, and fitness trackers to collect data about a user's daily activities, eating habits, exercise history, and hobbies.

[1752] Input: Data about the user's daily activities, eating habits, exercise history, and hobbies.

[1753] Data Processing: Collected data is aggregated from each device in a centralized format.

[1754] Output: Centralized lifestyle data.

[1755] Specific operation: For example, when a user logs in a smartphone app that they "ate pizza for dinner last night," that data is sent from the device to the server. The device then uses an emotion engine and a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[1756] Step 2: Sending data

[1757] Description: The device sends the collected life data and emotion data to the server.

[1758] Input: Centralized life and emotion data.

[1759] Data processing: None in particular.

[1760] Output: The data sent to the server.

[1761] Specific operation: The device sends the log "I had pizza for dinner yesterday" and the emotion data "joy" to the server.

[1762] Step 3: Analyze the data

[1763] Description: The server analyzes the life data and emotion data sent from the device.

[1764] Input: Life data and emotion data.

[1765] Data processing: Using artificial intelligence algorithms to extract insights and trends from data.

[1766] Output: Analysis results.

[1767] Specific operation: The server uses the log of "I had pizza for dinner yesterday" and the emotion data of "happiness" to evaluate the impact of the user's eating habits on their emotions.

[1768] Step 4: Generate proposals

[1769] Description: The server generates personalized offers based on the analysis results.

[1770] Input: Analysis results.

[1771] Data processing: Based on the analysis results, health management and lifestyle suggestions are created.

[1772] Output: Individual proposals.

[1773] Specific behavior: The server generates a suggestion such as "Since you ate pizza yesterday, you should eat more vegetables today." Specifically, it includes a detailed suggestion such as "I recommend a salad today."

[1774] Step 5: Proposal Notification

[1775] Description: The device notifies the user of the offers received from the server.

[1776] Input: A suggestion from the server.

[1777] Data processing: None in particular.

[1778] Output: Notification to the user.

[1779] Specific behavior: The device will notify the user by voice, "You had pizza yesterday, so I recommend you have a salad today. Would you like some specific dressing suggestions?"

[1780] Step 6: User feedback

[1781] Description: The user provides feedback on the suggestions and sends it to the server via the device.

[1782] Input: User feedback.

[1783] Data processing: None in particular.

[1784] Output: Feedback sent to the server.

[1785] Specific behavior: The user responds, "The salad is good, but could you recommend a dressing?" and the device sends this feedback to the server.

[1786] Step 7: Modify the proposal

[1787] Description: The server modifies the suggestions based on user feedback and sentiment data.

[1788] Input: Feedback and emotion data.

[1789] Data processing: Analyze feedback and sentiment data and update suggestions.

[1790] Output: The revised proposal.

[1791] Specific behavior: The server modifies the suggestion to "You might want to use a little olive oil and lemon dressing on the salad" and notifies the user again via the device.

[1792] Through this series of processing steps, users receive healthy suggestions that take emotional data into account, allowing them to make choices that better suit their lifestyle.

[1793] (Application example 2)

[1794] 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."

[1795] Modern consumers have diverse preferences and emotional states, and there is a demand for personalized shopping experiences based on these. However, conventional systems have had difficulty effectively utilizing users' lifestyle and emotional data to make appropriate product recommendations in real time. Furthermore, there was no established method for efficiently collecting and analyzing feedback to improve the accuracy of recommendations. The present invention aims to solve these issues and provide a system that provides users with optimal product recommendations.

[1796] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on the user's purchase history. This enables real-time, personalized product proposals that take into account the user's preferences and emotional state.

[1797] "User lifestyle data" refers to information about the user's daily activities, eating habits, exercise history, hobbies, etc.

[1798] "Emotional data" refers to information about a user's emotional state obtained from facial expressions, tone of voice, heart rate, etc.

[1799] "Analytics" refers to the methods used to assess user behavior, preferences, and emotional states based on collected data to extract insights and trends.

[1800] "Proposal generation means" refers to a method for creating personalized proposals for a user based on the analysis results.

[1801] "Notification means" refers to the method for communicating generated suggestions to the user.

[1802] "Feedback channels" are ways to gather responses and opinions from users and use them to refine your proposals.

[1803] "Purchase history" refers to a record of products and services a user has purchased in the past.

[1804] "Product suggestions" refer to products and services recommended to users based on their lifestyle data, emotional data, and purchasing history.

[1805] The present invention provides a system that collects user lifestyle data and emotion data, analyzes the data, generates and notifies personalized suggestions, and modifies the suggestions based on user feedback. The system is configured as follows.

[1806] The server includes means for collecting user lifestyle data, means for analyzing the collected lifestyle data, means for generating individual proposals based on the analysis results, means for notifying the user of the generated proposals, means for modifying the proposals based on user feedback, means for collecting user emotion data, means for analyzing the collected emotion data, and means for generating and notifying product proposals based on purchase history.

[1807] Hardware and software used

[1808] Hardware:

[1809] Cameras (e.g., cameras built into smart glasses or smartphones)

[1810] Microphones (e.g., microphones built into smart glasses or smartphones)

[1811] software:

[1812] OpenCV: A framework for real-time processing of camera images

[1813] SpeechRecognition: A library for analyzing speech

[1814] Requests: Library for data communication with the server

[1815] EmotionRecognizer: Emotion recognition engine

[1816] Data processing and calculation

[1817] The device (e.g., smart glasses or smartphone) captures the user's facial expressions and voice in real time. It uses a camera to acquire the user's facial expression data, processes the images using OpenCV, and then analyzes the emotion data using EmotionRecognizer.

[1818] The microphone is used to capture the user's voice data, and the speech is converted into text using the SpeechRecognition library. This data is then combined and sent to the server using the Requests library. The server receives the data, analyzes it, and generates personalized product suggestions for the user. The suggestions are then sent back to the device and notified to the user.

[1819] Specific examples

[1820] For example, imagine a user is shopping in a physical store. Smart glasses capture the user's facial expression data and detect whether the user is enjoying themselves. If the user also says, "I've been feeling tired lately," the system collects this as text data. This data is sent to a server and analyzed along with the user's purchase history. As a result, personalized products such as "tea with a relaxing effect" are suggested.

[1821] Prompt Sentence Examples

[1822] Create a recommendation for a brick-and-mortar shopping assistant that collects emotional data from users' facial expressions and voice, and analyzes it along with their purchasing history. Generate optimal product recommendations for users based on the following data:

[1823] A list of items recently purchased by the user

[1824] User facial expression data

[1825] User voice data

[1826] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1827] Step 1:

[1828] The user wears smart glasses or a smartphone, and the device captures their facial expressions and voice. The device acquires the user's facial expression data through the camera and processes the image data using OpenCV. It also acquires voice data using the microphone and converts the voice into text data using the SpeechRecognition library. The input is the user's facial expression and voice, and the output is processed facial expression data and text data.

[1829] Step 2:

[1830] The device converts the acquired facial expression data into emotional data using EmotionRecognizer. Specifically, it recognizes emotions such as "happiness," "anger," and "sadness" from the user's facial expressions in real time and stores them as digital data. The input is processed facial expression data, and the output is emotional data.

[1831] Step 3:

[1832] The device integrates emotion data and speech-to-text data and sends it to the server using the Requests library. The data sent includes the user's emotion data, speech-to-text data, and purchase history. In this case, the input is emotion data and speech-to-text data, and the output is a request containing these data.

[1833] Step 4:

[1834] The server analyzes the received data and generates product suggestions suitable for the user. It uses an AI algorithm to evaluate the user's lifestyle and emotional data to generate personalized product suggestions. The input is emotional data, voice and text data, and purchase history, and the output is product suggestions.

[1835] Step 5:

[1836] The server sends the generated product suggestions to the terminal. At this time, the information notified to the user includes details of the suggested products and the reasons for them. The input is the product suggestions, and the output is a notification to the user.

[1837] Step 6:

[1838] The user provides feedback on the received product suggestions. The terminal transmits the user's feedback to the server again. At this time, the input is the user's feedback and the output is a request to the server.

[1839] Step 7:

[1840] The server analyzes the user's feedback and modifies the proposal if necessary. The modified proposal is then notified to the user again. The input is the user's feedback and the output is the modified proposal.

[1841] 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.

[1842] 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.

[1843] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1844] 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.

[1845] 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.

[1846] 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.

[1847] 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).

[1848] 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.

[1849] 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."

[1850] 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.

[1851] 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).

[1852] 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.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] 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.

[1859] 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.

[1860] 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.

[1861] 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.

[1862] The following is further disclosed regarding the above embodiment.

[1863] (Claim 1)

[1864] Means of collecting user life data;

[1865] A means of analyzing the collected lifestyle data,

[1866] means for generating personalized recommendations based on the analysis results;

[1867] a means for notifying the user of the generated suggestions;

[1868] The system includes a means for revising the suggestions based on user feedback.

[1869] (Claim 2)

[1870] 10. The system of claim 1, wherein the system collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1871] (Claim 3)

[1872] 10. The system of claim 1, further comprising means for analyzing user feedback and regenerating suggestions.

[1873] (Claim 4)

[1874] 10. The system of claim 1, wherein the collected data is analyzed using artificial intelligence.

[1875] (Claim 5)

[1876] 10. The system of claim 1, further comprising means for audibly announcing the generated suggestions to the user.

[1877] (Claim 6)

[1878] The system of claim 1 , wherein the system generates suggestions including exercise plans, dietary advice, and hobby suggestions.

[1879] (Claim 7)

[1880] 10. The system of claim 1, further comprising means for transmitting the feedback to a server via the Internet.

[1881] (Claim 8)

[1882] 10. The system of claim 1, further comprising means for making restaurant reservations based on the analysis results.

[1883] (Claim 9)

[1884] 10. The system of claim 1, further comprising means for tracking the implementation of the suggestions and providing feedback accordingly.

[1885] "Example 1"

[1886] (Claim 1)

[1887] Means of collecting user life data;

[1888] A means of analyzing the collected lifestyle data,

[1889] means for generating personalized recommendations based on the analysis results;

[1890] a means for notifying the user of the generated suggestions;

[1891] a means of revising the proposals based on user feedback;

[1892] A means for storing the collected life data in a database;

[1893] A means for analyzing life data using the artificial intelligence model and extracting insights;

[1894] means for personalizing said suggestions based on user preferences and behavioral data;

[1895] A system including:

[1896] (Claim 2)

[1897] 10. The system of claim 1, wherein the system collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1898] (Claim 3)

[1899] 10. The system of claim 1, further comprising means for analyzing user feedback and regenerating suggestions.

[1900] "Application Example 1"

[1901] (Claim 1)

[1902] Means of collecting user life data;

[1903] A means of analyzing the collected lifestyle data,

[1904] means for generating personalized recommendations based on the analysis results;

[1905] a means for notifying the user of the generated suggestions;

[1906] a means of revising the proposals based on user feedback;

[1907] A system including a means for generating and notifying specific meal suggestions based on lifestyle data.

[1908] (Claim 2)

[1909] 10. The system of claim 1, wherein the system collects data about the user's daily activities, eating habits, exercise history, and hobbies.

[1910] (Claim 3)

[1911] 10. The system of claim 1, further comprising means for analyzing user feedback and regenerating suggestions.

[1912] (Claim 4)

[1913] The system according to claim 1, further comprising means for analyzing the feedback content selected by the user based on the suggestions and suggesting seasonings suitable for the meal menu.

[1914] "Example 2: Combining Emotion Engines"

[1915] (Claim 1)

[1916] A means for collecting user life data and emotional data;

[1917] A means for analyzing the collected life data and emotion data;

[1918] means for generating personalized recommendations based on the analysis results;

[1919] a means for notifying the user of the generated suggestions;

[1920] The system includes a means for revising the suggestions based on user feedback and sentiment data.

[1921] (Claim 2)

[1922] 10. The system of claim 1, wherein the system collects data about the user's daily activities, eating habits, exercise history, hobbies, and emotional state.

[1923] (Claim 3)

[1924] 10. The system of claim 1, further comprising means for analyzing user feedback and sentiment data and regenerating suggestions.

[1925] "Application example 2 when combining emotion engines"

[1926] (Claim 1)

[1927] Means of collecting user life data;

[1928] A means of analyzing the collected lifestyle data,

[1929] means for generating personalized recommendations based on the analysis results;

[1930] a means for notifying the user of the generated suggestions;

[1931] a means of revising the proposals based on user feedback;

[1932] a means for collecting user emotional data;

[1933] a means for analyzing the collected emotion data;

[1934] A system including a means for generating and notifying product suggestions based on purchase history.

[1935] (Claim 2)

[1936] 10. The system of claim 1, wherein the system collects data on the user's daily activities, eating habits, exercise history, hobbies, and purchasing history.

[1937] (Claim 3)

[1938] 10. The system of claim 1, further comprising means for analyzing and regenerating suggestions based on the collected data and sentiment data. [Explanation of symbols]

[1939] 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 of collecting user life data; A means of analyzing the collected lifestyle data, means for generating personalized recommendations based on the analysis results; a means for notifying the user of the generated suggestions; The system includes a means for revising the suggestions based on user feedback.

2. The system of claim 1 , wherein the system collects data about the user's daily activities, eating habits, exercise history, and hobbies.

3. 10. The system of claim 1, further comprising means for analyzing user feedback and regenerating suggestions.

4. The system of claim 1 , wherein the analysis of the collected data uses artificial intelligence.

5. The system of claim 1 further comprising means for audibly announcing the generated suggestions to the user.

6. The system of claim 1 generates suggestions including exercise plans, dietary advice, and hobby suggestions.

7. 10. The system of claim 1, further comprising means for transmitting the feedback to a server via the Internet.

8. 2. The system of claim 1, further comprising means for making restaurant reservations based on the analysis results.

9. 10. The system of claim 1, further comprising means for tracking the implementation of the suggestions and providing feedback accordingly.

Images