system

Abstract

We provide the system. [Solution] A means of receiving health data entered by the user, A means for transmitting received health data to a generative artificial intelligence for analysis, A means of receiving feedback analyzed by a generative artificial intelligence, A means of sending received feedback to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Health data such as weight, body fat percentage, and blood pressure measured by many users in their daily lives, as well as monthly mobile usage data, are merely numbers as they are, and it is difficult for users to interpret them and utilize them for health management and optimization of usage situations. Therefore, a mechanism for converting user data into useful information and providing appropriate feedback is required. In particular, when steps for identifying outliers and confirming data accuracy are lacking, it may hinder users' health management and efficient mobile usage.

Means for Solving the Problems

[0005] The present invention provides a system including means for receiving health data entered by a user, means for transmitting the received health data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. The system further includes means for receiving mobile usage data entered by a user, means for transmitting the received mobile usage data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. In addition, by including means for checking the accuracy and consistency of the received health data and mobile usage data, sending notifications prompting re-entry if abnormal values ​​exist, means for transmitting normal data to a generative artificial intelligence for analysis, and means for transmitting feedback analyzed by the generative artificial intelligence to the user, the system provides optimal feedback to the user and supports health management and efficient mobile usage.

[0006] A "user" refers to an individual who uses the system to input health data or mobile usage data and receives feedback.

[0007] "Health data" refers to numerical information that indicates a user's health status, such as weight, body fat percentage, and blood pressure.

[0008] "Mobile usage data" refers to information such as the amount of data a user uses on a monthly basis and their usage patterns for their mobile devices.

[0009] "Generative artificial intelligence for analysis" refers to an artificial intelligence system that analyzes data provided by users and generates useful feedback.

[0010] "Feedback" refers to useful information and advice provided to users based on the results analyzed by generative artificial intelligence.

[0011] "Means of receiving" refers to components that have the functionality to receive data and feedback from external sources.

[0012] "Means of transmission" refers to components that have the functionality to send data or feedback to external parties.

[0013] "Means of checking consistency" refers to components that have the functionality to verify the integrity and accuracy of received data and notify the user if there are any problems.

[0014] An "outlier" refers to a value that exceeds the normal range or is inconsistent. When such an outlier exists, it is determined that the user needs to be prompted to re-enter the information. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The system consists of a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, receiving feedback from the generative artificial intelligence, and transmitting it back to the user.

[0037] System configuration and operation

[0038] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. This data entered by the user into the application is first stored by the device. Then, the device sends this data to the server.

[0039] Next, the server receives this data. The server checks the accuracy and consistency of the received data. If an anomaly is detected, a notification is sent to the user prompting them to re-enter the data. If accurate data is obtained, that data is sent to a generative artificial intelligence for analysis.

[0040] Generative artificial intelligence (AI) compares past data and general health information to generate useful feedback for the user. For example, if it is determined that a user's weight is increasing or their blood pressure is high, the AI ​​will generate feedback such as recommendations for improving their diet or exercising.

[0041] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[0042] Specific example

[0043] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the data is sent to a generative artificial intelligence.

[0044] The generative AI compares the user's data from the past month and confirms that their weight has increased and their blood pressure is elevated. Based on this, the generative AI generates the following feedback: "User, your weight has increased in the past month. Your blood pressure is also elevated. Please try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[0045] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[0046] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence (AI). The AI ​​analyzes the data usage and usage patterns and generates appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0047] Thus, the present invention provides a system that appropriately analyzes users' health data and mobile usage data and provides useful feedback to improve users' quality of life.

[0048] The following describes the processing flow.

[0049] ❶ Utilization of PHR at HELPO

[0050] Processing flow: Utilizing PHR in HELPO

[0051] Step 1:

[0052] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[0053] The device stores the entered data within the app and converts it into a format for sending to the server.

[0054] Step 2:

[0055] The server receives health data sent from the user's terminal.

[0056] The server verifies the data to ensure it is accurate and consistent.

[0057] Step 3:

[0058] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0059] The server verifies that the data transmission was successful.

[0060] Step 4:

[0061] Generative artificial intelligence analyzes the received health data.

[0062] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[0063] Step 5:

[0064] Generative artificial intelligence generates useful feedback based on the analysis results.

[0065] The feedback includes specific health management advice and warnings.

[0066] Step 6:

[0067] The generative artificial intelligence generates feedback which is then sent to the server.

[0068] The server prepares to send feedback to the user.

[0069] Step 7:

[0070] The server sends the generated feedback to the user's device.

[0071] Users receive notifications on their smartphones, open the app, and check the feedback.

[0072] Step 8:

[0073] Users review the feedback and modify their health management behaviors.

[0074] For example, reviewing your diet and adding exercise are recommended.

[0075] ❷ Utilization in mobile usage patterns

[0076] Processing flow: Utilization based on mobile usage

[0077] Step 1:

[0078] The user opens the app on their smartphone to check their monthly usage details.

[0079] The terminal collects usage details data and converts it into a format for transmission to the server.

[0080] Step 2:

[0081] The server receives monthly usage data sent from the user's terminal.

[0082] The server verifies the data to ensure its consistency.

[0083] Step 3:

[0084] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0085] The server verifies that the data transmission was successful.

[0086] Step 4:

[0087] The generative artificial intelligence analyzes the usage data it receives.

[0088] Generative artificial intelligence compares current usage with past data to identify increases or decreases in usage and unusual usage patterns.

[0089] Step 5:

[0090] Generative artificial intelligence generates useful feedback based on the analysis results.

[0091] The feedback includes specific advice and warnings regarding data usage and usage patterns.

[0092] Step 6:

[0093] The generative artificial intelligence generates feedback which is then sent to the server.

[0094] The server prepares to send feedback to the user.

[0095] Step 7:

[0096] The server sends the generated feedback to the user's device.

[0097] Users receive notifications on their smartphones, open the app, and check the feedback.

[0098] Step 8:

[0099] Users review the feedback and adjust their mobile usage accordingly.

[0100] For example, take measures such as actively using Wi-Fi to reduce data usage.

[0101] The above outlines the specific processing flow within this system.

[0102] (Example 1)

[0103] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0104] In today's living environment, it is crucial to efficiently and appropriately understand individual health conditions and provide feedback based on that understanding. However, manually recording and analyzing data is time-consuming and prone to inaccuracies. Similarly, managing mobile usage data is not easy for users themselves. Therefore, there is a need for a system that allows users to easily input health and mobile usage data, and that appropriately analyzes this data to provide feedback.

[0105] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0106] In this invention, the server includes means for receiving health data entered by the user, means for temporarily storing the received health data in a computer system, means for transmitting the stored data to a central control unit, means for verifying the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if an abnormal value is detected, means for transmitting normal data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This enables the user to easily and accurately manage their health data and mobile usage data and to quickly receive appropriate feedback based on that data.

[0107] A "user" is an individual who uses the system to input health data and mobile usage data.

[0108] "Health data" refers to information that indicates an individual's health status, such as weight, body fat percentage, and blood pressure.

[0109] "Mobile usage data" refers to information that shows how a user's mobile device is being used, such as application usage time and data usage.

[0110] An "electronic computer system" is a computer system used for processing data, such as storing, transmitting, and analyzing it.

[0111] A "central control unit" is a device that manages received data and controls its transmission to the artificial intelligence used for analysis.

[0112] "Generative artificial intelligence" is a type of artificial intelligence that analyzes received data and generates feedback for the user.

[0113] "Feedback" refers to advice and instructions for the user that a generative artificial intelligence generates based on its analysis results.

[0114] "Means of verifying accuracy and consistency" refer to methods for verifying that received data is appropriate and does not contradict past data.

[0115] An "outlier" is a data value that deviates from the normal range, indicating an input error or an abnormal condition.

[0116] A "notification prompting re-entry" is a message that asks the user to re-enter data when an abnormal value is detected.

[0117] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The present invention is a system that includes a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, and providing feedback of the analysis results to the user.

[0118] System configuration and operation

[0119] 1. User data entry

[0120] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[0121] 2. Data storage and transmission

[0122] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[0123] 3. Receiving and confirming data

[0124] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[0125] 4. Data transmission to generative artificial intelligence

[0126] If the data is found to be normal, the server sends it to a generative artificial intelligence system for analysis (specifically, GPT-4®).

[0127] 5. Data Analysis and Feedback Generation

[0128] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user. This feedback is then sent back to the server as the result of the generative AI's analysis.

[0129] 6. Submit feedback

[0130] The server sends feedback received from the generative artificial intelligence to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[0131] Specific example

[0132] Consider a scenario where a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency and accuracy. Once consistency is confirmed, the data is sent to a generative artificial intelligence (GPT-4). The generative AI compares this data to the data from the past month and confirms that the user's weight has increased and their blood pressure is elevated. Based on this, the generative AI generates feedback such as: "User, your weight has increased over the past month. Your blood pressure is also elevated. Try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[0133] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[0134] Example of a prompt

[0135] Analyze the user's input data and provide feedback. The user's weight is 70kg, body fat percentage is 22%, and blood pressure is 130 / 85. Compare this to data from the past month and generate appropriate health advice.

[0136] This system allows users to easily and accurately manage their health and mobile usage data and receive timely, relevant feedback based on that data. The seamless integration of the entire system enhances the user experience and contributes to improved health management and mobile usage.

[0137] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0138] Step 1: Enter user data

[0139] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[0140] Specific actions:

[0141] The user opens the app and enters data such as weight (70kg), body fat percentage (22%), and blood pressure (130 / 85).

[0142] input:

[0143] Health data or mobile usage data.

[0144] output:

[0145] Data stored in the device's local storage.

[0146] Step 2: Save and send data from your device.

[0147] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[0148] Specific actions:

[0149] The user clicks the "Send" button.

[0150] The device writes data to local storage.

[0151] The device sends data to the server using an HTTP request.

[0152] input:

[0153] Health data or mobile usage data stored in local storage.

[0154] output:

[0155] Data sent to the server.

[0156] Step 3: Server data reception and verification

[0157] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[0158] Specific actions:

[0159] The server receives an HTTP request.

[0160] The server checks the accuracy and consistency of the data. For example, it checks whether outliers such as a weight of 500kg are detected.

[0161] If an abnormal value is detected, the server will send a notification to the user prompting them to re-enter the information.

[0162] input:

[0163] Data sent from the device.

[0164] output:

[0165] Notifications indicating that re-entry is required, or confirmed valid data.

[0166] Step 4: Sending data to the generative artificial intelligence

[0167] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[0168] Specific actions:

[0169] The server organizes the verified data and sends it as a POST request to the generative AI's API endpoint.

[0170] The request will include health data. For example: "Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85".

[0171] input:

[0172] Verified and valid data.

[0173] output:

[0174] Data sent to a generative artificial intelligence system.

[0175] Step 5: Data Analysis and Feedback Generation

[0176] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user.

[0177] Specific actions:

[0178] GPT-4 will perform data analysis and compare it with data from the past month.

[0179] Based on the analysis results, feedback is generated for the user. Example: "User, your weight has increased in the past month. Your blood pressure is also on the high side. Please try to eat a balanced diet and get moderate exercise."

[0180] input:

[0181] Health data or mobile usage data transmitted from the server.

[0182] output:

[0183] Analyzed data and generated feedback.

[0184] Step 6: Send feedback back to the server

[0185] The generative artificial intelligence sends the generated feedback back to the server. The server receives it and proceeds to the next processing step.

[0186] Specific actions:

[0187] The GPT-4 sends the generated feedback back to the server.

[0188] The server receives the data and saves it to the database.

[0189] input:

[0190] Feedback from generative artificial intelligence.

[0191] output:

[0192] Feedback information stored on the server.

[0193] Step 7: Submitting Feedback

[0194] The server sends the received feedback to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[0195] Specific actions:

[0196] The server sends feedback to the user's smartphone using a notification or HTTP request.

[0197] The user clicks the notification to check the feedback.

[0198] input:

[0199] Feedback information stored on the server.

[0200] output:

[0201] Feedback displayed on the user's device.

[0202] (Application Example 1)

[0203] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0204] Managing employee health and optimizing robot operating efficiency are major challenges in modern factories. Unclear employee health status can negatively impact work safety and efficiency. Furthermore, the inability to understand appropriate robot operating patterns can easily lead to reduced utilization and inefficient operation. Moreover, manually managing this data is labor-intensive and time-consuming, making automation essential.

[0205] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0206] In this invention, the server includes means for receiving health data and operational data entered by the user, means for transmitting the received health data and operational data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user and the robot. This enables the optimization of employee health management and robot operational efficiency.

[0207] "Health data" refers to information about biometric indicators such as weight, body fat percentage, and blood pressure that users input.

[0208] "Operational data" refers to information about the operating status and performance of robots and machines used in factories and other work sites.

[0209] "Generative artificial intelligence for analysis" refers to a system that includes advanced algorithms and models for analyzing received data and generating appropriate feedback for the user or machine.

[0210] "Feedback" refers to advice and recommendations provided by generative artificial intelligence as a result of analyzing health data and operational data.

[0211] A "user" is an individual or administrator who uses this system to input health data and operational data.

[0212] A "robot" is a mechanical device that automatically performs specific tasks in factories and other workplaces.

[0213] "Means of receiving data" refers to the mechanisms and methods for receiving data from users and various devices and incorporating it into the system.

[0214] "Means of transmission" refers to the mechanisms and methods for sending collected data and analysis results to appropriate destinations (generative artificial intelligence, users, robots, etc.).

[0215] This invention provides a system that optimizes employee health management and robot operation management within a factory. The system collects health and operation data entered by the user, analyzes the data using generative artificial intelligence, and provides feedback.

[0216] The server receives health and operational data entered by users. This includes data entered from users' smartphones and tablets. Health data includes weight, body fat percentage, and blood pressure, while operational data includes the operating status and performance data of robots and machines.

[0217] The received data is checked for consistency and accuracy on the server. If an anomaly is detected, the server sends a notification to the user prompting them to re-enter the data. If normal data is obtained, it is sent to the generative artificial intelligence.

[0218] Generative artificial intelligence analyzes received health and operational data to generate appropriate feedback. For example, if an employee's weight is increasing or their blood pressure is high, the generative AI will recommend a balanced diet and moderate exercise. For robot operational data, advice is provided to improve operational efficiency.

[0219] The generated feedback is sent via a server to the user's smartphone or tablet, as well as to the monitoring robot. Based on this feedback, users and factory managers can take action to improve health management and operational efficiency.

[0220] The hardware used includes smartphones, tablets, and robots. The software used includes Python, the requests library, and a generative artificial intelligence server.

[0221] As a concrete example, factory employees input their daily weight, body fat percentage, and blood pressure into their smartphones, and this data is sent to a server. After consistency and accuracy are verified, generative artificial intelligence analyzes the data and generates feedback. For example, feedback such as, "User, your weight has increased in the past month. Your blood pressure is also on the high side. Try to eat a balanced diet and get moderate exercise," is generated and sent to the user.

[0222] Additionally, robot operation data is transmitted, analyzed by generative artificial intelligence, and feedback is provided such as, "To improve the efficiency of operating time, it is recommended to review the timing of operations."

[0223] Example of a prompt:

[0224] "Analyze the user's health data (weight, body fat percentage, blood pressure) from the past month and generate feedback for health management."

[0225] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0226] Step 1:

[0227] Users input health and operational data using smartphones or tablets. Health data includes weight, body fat percentage, and blood pressure. Operational data includes the operating status and performance data of robots and machinery. This input is transmitted directly to the server by the user's device.

[0228] Input: Health data and work data entered by the user.

[0229] Output: Input data sent to the server

[0230] Step 2:

[0231] The server checks the accuracy and consistency of the data it receives. Specifically, it verifies that there are no outliers and that the data is free of missing values ​​or formatting errors. If outliers or missing values ​​are detected, the server sends a notification to the user's terminal prompting them to re-enter the data.

[0232] Input: Health data and operational data submitted by the user.

[0233] Output: Successful data or notification prompting re-entry.

[0234] Step 3:

[0235] The server transmits data that has been verified for accuracy and consistency to the generative artificial intelligence. At this time, current and past health data and operational data are also transmitted to enable appropriate analysis by comparing them with past data.

[0236] Input: Accurate health and operational data submitted by the user.

[0237] Output: Data sent to the generative artificial intelligence.

[0238] Step 4:

[0239] Generative artificial intelligence analyzes received data and generates feedback. Based on health data, for example, it generates health management advice based on fluctuations in weight and blood pressure. Based on operational data, it generates recommendations for efficient robot operation patterns and maintenance.

[0240] Input: Health data and operational data received by the generative artificial intelligence.

[0241] Output: Generated feedback

[0242] Step 5:

[0243] The server sends the generated feedback to the user's terminal and the robot. The user receives health management advice and warnings, while the robot receives instructions for improving its operating patterns and performing maintenance.

[0244] Input: Feedback generated by a generative artificial intelligence system.

[0245] Output: Feedback sent to the user's terminal and the robot.

[0246] Step 6:

[0247] Users and factory managers use their devices to review feedback and take necessary actions. Specifically, users may improve their diet or revise their exercise plans based on health management advice. Factory managers may adjust robot operating patterns and maintenance plans.

[0248] Input: Feedback received by user and factory administrator terminals.

[0249] Output: Actions taken by users and factory administrators

[0250] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0251] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[0252] System configuration and operation

[0253] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. The data entered by the user is stored on the device and sent to the server.

[0254] Next, the server receives this data. The server checks the accuracy and consistency of the data and sends a notification prompting re-entry if any anomalies are found. If accurate data is obtained, it is sent to a generative artificial intelligence for analysis.

[0255] Furthermore, the emotion engine incorporated into the system of the present invention recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and the content of the input data, and generates emotion data. This emotion data is also transmitted to the generative artificial intelligence system.

[0256] Generative artificial intelligence analyzes received health data, mobile usage data, and emotional data. By comparing historical data with general health indicators and emotional information, it generates optimal feedback for the user. For example, if a user's weight is increasing and the emotional engine detects that their stress levels are high, the generative AI can generate feedback recommending stress reduction strategies and dietary changes.

[0257] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[0258] Specific example

[0259] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the emotion engine analyzes the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to the generative artificial intelligence.

[0260] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[0261] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[0262] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0263] Thus, the present invention provides a system that appropriately analyzes users' health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[0264] The following describes the processing flow.

[0265] ❶ Utilizing PHR in HELPO (with emotion engine)

[0266] Processing flow: Utilizing PHR in HELPO

[0267] Step 1:

[0268] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[0269] The device stores the entered data within the app and converts it into a format for sending to the server.

[0270] Step 2:

[0271] The server receives the health data sent from the user terminal.

[0272] The server performs verification to confirm the accuracy and consistency of the data.

[0273] Step 3:

[0274] After the server checks the accuracy and consistency, it sends the verified data to the generative artificial intelligence for analysis.

[0275] The server confirms that the data transmission has been successfully performed.

[0276] Step 4:

[0277] The user activates the camera in the app, and the emotion engine analyzes the user's expression and voice to generate emotion data.

[0278] The terminal sends the generated emotion data to the server.

[0279] Step 5:

[0280] The server receives the emotion data sent from the user terminal.

[0281] The server checks the accuracy and consistency of the emotion data in the same way as the health data.

[0282] Step 6:

[0283] After the server confirms the accuracy and consistency, it sends the emotion data to the generative artificial intelligence for analysis.

[0284] The server confirms that the data transmission has been successfully performed.

[0285] Step 7:

[0286] The generative artificial intelligence analyzes the received health data and emotion data.

[0287] The generative artificial intelligence compares with past data and general health indicators to identify specific trends and outliers.

[0288] Step 8:

[0289] Generate feedback based on the health data, emotion data, and mobile usage data received by the generative artificial intelligence.

[0290] The feedback includes specific advice and warnings regarding health management.

[0291] Step 9:

[0292] The feedback generated by the generative artificial intelligence is returned to the server.

[0293] The server receives the feedback and prepares to send it to the user.

[0294] Step 10:

[0295] The server sends the generated feedback to the user's terminal.

[0296] The user receives a notification from the smartphone, opens the app, and checks the feedback.

[0297] Step 11:

[0298] The user checks the feedback content and modifies their health management actions and emotion management.

[0299] For example, it is recommended to review the diet, add exercise, and take stress reduction measures.

[0300] ❷ Utilization in mobile usage (with emotion engine)

[0301] Process flow: Utilization in mobile usage

[0302] Step 1:

[0303] The user opens the app to check the monthly usage details from the smartphone app.

[0304] The terminal collects the usage detail data and converts it into a format for transmission to the server.

[0305] Step 2:

[0306] The server receives the monthly usage data sent from the user terminal.

[0307] The server performs verification to check the accuracy and consistency of the data.

[0308] Step 3:

[0309] After the server checks the accuracy and consistency, it sends the verified usage data to the generation system artificial intelligence for analysis.

[0310] The server confirms that the data transmission has been successfully performed.

[0311] Step 4:

[0312] The user activates the camera within the app, and the emotion engine analyzes the user's expression and voice to generate emotion data.

[0313] The terminal sends the generated emotion data to the server.

[0314] Step 5:

[0315] The server receives the emotion data sent from the user terminal.

[0316] The server checks the accuracy and consistency of the emotion data, similar to the health data.

[0317] Step 6:

[0318] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[0319] The server verifies that the data transmission was successful.

[0320] Step 7:

[0321] The generative artificial intelligence analyzes the received usage data and sentiment data.

[0322] Generative artificial intelligence compares current data with past data to identify increases or decreases in communication usage, abnormal usage patterns, and emotional states.

[0323] Step 8:

[0324] The generative artificial intelligence generates feedback based on the received usage data and sentiment data.

[0325] The feedback includes specific advice and warnings regarding optimizing communication usage.

[0326] Step 9:

[0327] The feedback generated by the generative artificial intelligence is returned to the server.

[0328] The server receives the feedback and prepares to send it to the user.

[0329] Step 10:

[0330] The server sends the generated feedback to the user's device.

[0331] Users receive notifications on their smartphones, open the app, and check the feedback.

[0332] Step 11:

[0333] Users review feedback and make adjustments to their mobile usage and sentiment management.

[0334] For example, it is recommended to use Wi-Fi to reduce data usage and to take measures to reduce stress.

[0335] The above outlines the specific processing flow within this system.

[0336] (Example 2)

[0337] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0338] Traditional systems could analyze user health data and mobile usage data individually, but struggled to integrate this data and provide feedback that considered the user's emotional state. Furthermore, the lack of automated means to verify data consistency and accuracy meant that detecting anomalies and prompting re-entry was often done manually, placing a significant burden on users. This made optimal health management and lifestyle improvements difficult.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes means for receiving health data entered by the user, means for storing the received health data and transmitting it to the server, means for checking the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if abnormal values ​​exist, means for transmitting normal health data to a generative artificial intelligence for analysis, means for generating emotional data with an emotion engine for analyzing the user's emotions, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This makes it possible to comprehensively analyze health data, mobile usage data, and user emotional data, and provide optimal feedback to the user in real time.

[0341] "Health data" refers to information about a user's physical health, such as weight, body fat percentage, and blood pressure.

[0342] A "server" is a computer system that receives, stores, processes, and transmits data.

[0343] A "terminal" refers to a device used by a user to input data and communicate with a server, such as a smartphone or tablet.

[0344] "Generative artificial intelligence" refers to algorithms and systems that analyze input data and generate feedback.

[0345] An "emotion engine" is a system that analyzes a user's emotional state from their voice, facial expressions, and input data, and generates emotional data.

[0346] "Consistency" is a characteristic that indicates that the received data is consistent and unambiguous.

[0347] A "notification prompting re-entry" is a message that requests the user to re-enter data if there are discrepancies in the accuracy or consistency of the data.

[0348] "Means for sending data to a generative artificial intelligence for analysis" refers to a mechanism for sending data that has been verified for accuracy and consistency to a generative artificial intelligence for analysis.

[0349] "Feedback" refers to advice and information provided to users based on the results of analysis by generative artificial intelligence.

[0350] "Mobile usage data" refers to information about how users are using their mobile devices and their usage patterns.

[0351] "Means of sending notifications" refers to a mechanism that sends a message to the user prompting them to re-enter information when an abnormal value is detected.

[0352] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[0353] Hardware and software configuration

[0354] Users input daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using devices such as smartphones and tablets. The device temporarily stores this data and sends it to a server via the internet. The server automatically checks the accuracy and consistency of the received data and sends a notification to the user prompting them to re-enter the data if any abnormal values ​​are found. The generative artificial intelligence used for analysis on the server specifically employs AI models such as TENSORFLOW® and OpenAI®'s GPT-3® for analysis.

[0355] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and input data, and generates emotion data. Software such as FaceAPI and Affectiva can be used for emotion analysis. This emotion data is also sent to the generative artificial intelligence.

[0356] Generative artificial intelligence integrates and analyzes received health data, mobile usage data, and emotional data. Based on historical data, general health indicators, and emotional information, it can generate optimal feedback for the user. The generated feedback is returned to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and adjusts their health management behaviors accordingly.

[0357] Specific example

[0358] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and verifies its consistency. The consistent data is then analyzed by an emotion engine to determine the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to a generative artificial intelligence system.

[0359] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[0360] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[0361] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0362] Examples of prompt messages include, "Generate optimal health advice based on the user's health data," and "Analyze this data and create feedback that provides the user with stress reduction advice." In this way, the present invention realizes a system that appropriately analyzes the user's health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

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

[0364] Step 1:

[0365] Users input health data (weight, body fat percentage, blood pressure, etc.) using their smartphones or tablets.

[0366] Input: Health data entered by the user (e.g., weight 70kg, body fat percentage 22%, blood pressure 130 / 85)

[0367] Output: Health data temporarily stored by the device

[0368] Step 2:

[0369] The device sends the health data it has saved to the server.

[0370] Input: Health data stored on the device

[0371] Output: Health data sent to the server

[0372] Step 3:

[0373] The server checks the accuracy and consistency of the health data it receives.

[0374] Input: Health data received by the server

[0375] Output: Data with confirmed accuracy and consistency; notifications prompting re-entry if outliers are found.

[0376] Step 4:

[0377] The server sends normal health data to a generative artificial intelligence system for analysis.

[0378] Input: Health data verified for accuracy and consistency.

[0379] Output: Data sent to the generative artificial intelligence for analysis.

[0380] Step 5:

[0381] The emotion engine analyzes the user's voice, facial expressions, and input data to generate emotion data.

[0382] Input: User's voice and facial expression data, entered health data

[0383] Output: Generated sentiment data

[0384] Step 6:

[0385] The server sends emotional data to a generative artificial intelligence system for analysis.

[0386] Input: Generated emotion data

[0387] Output: Emotional data sent to a generative artificial intelligence for analysis.

[0388] Step 7:

[0389] Generative artificial intelligence analyzes health data, mobile usage data, and emotional data to generate appropriate feedback.

[0390] Input: Submitted health data, mobile usage data, emotional data

[0391] Output: Generated feedback

[0392] Step 8:

[0393] The server sends the generated feedback to the user's device.

[0394] Input: Generated feedback

[0395] Output: Feedback sent to the user's device

[0396] Step 9:

[0397] Users can view feedback through their devices and adjust their actions based on that feedback.

[0398] Input: Feedback sent to the device

[0399] Output: Review of user feedback and modification of actions

[0400] Through these steps, the system can comprehensively analyze the user's health data and mobile usage data, and provide appropriate feedback that also takes into account the user's emotional state.

[0401] (Application Example 2)

[0402] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0403] In modern society, managing users' health is a crucial issue, and many people find it difficult to maintain proper health management amidst their busy lives. Furthermore, stress and emotional fluctuations significantly impact health, creating a need for methods that provide comprehensive feedback, including emotional responses, to individual users. Additionally, there is a desire for integration with food delivery services that utilize health and emotional data to provide optimal meal suggestions that users can immediately implement.

[0404] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving health data entered by the user, means for transmitting the received health data to a generative artificial intelligence for analysis, means for emotion recognition for generating emotion data from the user's voice and facial expressions, means for transmitting the generated emotion data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, means for transmitting the received feedback to the user, means for analyzing the health data and emotion data to make meal suggestions, and means for ordering the suggested meal menu in cooperation with a food delivery service. This makes it possible to provide comprehensive feedback based on health data and emotion data, and to suggest and implement the optimal meal according to the user's unique health condition.

[0405] "Health data" refers to biometric information such as weight, body fat percentage, and blood pressure entered by the user.

[0406] "Generative artificial intelligence" is an artificial intelligence technology that analyzes data received from users and generates feedback.

[0407] An "emotion recognition method" is a system that generates emotion data by analyzing the user's voice and facial expressions.

[0408] "Emotional data" refers to information that indicates a user's emotional state, generated by an emotion recognition system.

[0409] "Feedback" refers to advice and instructions that generative artificial intelligence provides to the user based on its analysis results.

[0410] The "means of providing meal suggestions" refer to a system that suggests appropriate meal menus based on the user's health data and emotional data.

[0411] A "food delivery service" is an external delivery service that delivers suggested meal menus to users.

[0412] A "notification prompting re-entry" is a message that requests the user to re-enter accurate data when an abnormal value is detected.

[0413] This invention is a system for analyzing a user's health and emotional data and providing feedback and meal suggestions. The system consists of means for receiving health data entered by the user, means for emotion recognition, generative artificial intelligence, means for sending feedback, means for providing meal suggestions, and means for placing orders in cooperation with a food delivery service.

[0414] System configuration and operation

[0415] 1. Input and reception of health data

[0416] Users input health data such as weight, body fat percentage, and blood pressure using their own devices (e.g., smartphones). The devices then send this data to the server.

[0417] 2. Emotion recognition

[0418] The server analyzes the user's voice and facial expressions using emotion recognition tools (e.g., EmotionEngine) and generates emotion data. This emotion data is also sent to the server.

[0419] 3. Data Analysis

[0420] The server sends the received health and emotional data to a generative artificial intelligence (e.g., HealthAIModel) for analysis. The generative AI then generates feedback based on the received data.

[0421] 4. Providing feedback

[0422] The generated feedback is sent to the user's device by the server. The user can review the feedback and revise their health management methods.

[0423] 5. Meal suggestions and food delivery

[0424] Generative artificial intelligence provides optimal meal suggestions based on health and emotional data. The suggested meal menus are linked to food delivery services via a server, allowing users to order directly.

[0425] Hardware and software

[0426] Hardware: Smartphones, servers

[0427] Software: EmotionEngine (emotion recognition method), HealthAIModel (generative artificial intelligence)

[0428] Specific example

[0429] For example, consider a user who inputs a weight of 70 kg, a body fat percentage of 22%, and a blood pressure of 130 / 85. This data is sent to the server, where a high-stress state is detected by emotion recognition. Based on this data, a generative artificial intelligence generates the following feedback and meal suggestions:

[0430] "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Focus on a balanced diet, moderate exercise, and incorporate relaxation into your routine. We suggest the following meal plan, which includes balanced meals and relaxing elements."

[0431] Example of a prompt

[0432] The user's health data is as follows:

[0433] Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85

[0434] The emotional data indicates a high stress level.

[0435] Please suggest the optimal meal plan for the user.

[0436] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0437] Step 1:

[0438] Users input health data (e.g., weight, body fat percentage, blood pressure) using a smartphone or other device. The entered data is sent from the device to the server. At this time, the system also checks the integrity and format of the input data.

[0439] Step 2:

[0440] The server checks the accuracy and consistency of the received health data before sending it to the generative artificial intelligence for analysis. If the data is inconsistent or contains abnormal values, a notification prompting re-entry is sent to the user's device. If the data is normal, the server proceeds to the next step.

[0441] Step 3:

[0442] Using emotion recognition tools (e.g., EmotionEngine), the server generates emotion data from the user's voice and facial expressions. This emotion data is also sent to a generative artificial intelligence. Input data includes the user's voice files and real-time video feeds.

[0443] Step 4:

[0444] The server sends normal health data and generated emotional data to a generative artificial intelligence (e.g., HealthAIModel). The generative AI analyzes the user's health and emotional state based on this data and generates comprehensive feedback. Specifically, judgments are made based on comparisons with past data and general health indicators.

[0445] Step 5:

[0446] The generated feedback is sent back to the server, which then sends it to the user's device. The user can then view the feedback through their device. This feedback includes an assessment of their health status and specific advice for improvement.

[0447] Step 6:

[0448] Furthermore, the generative artificial intelligence suggests meal menus tailored to the user based on health and emotional data. This information is provided to the user via a server. The suggested menus are optimized for each user's individual health and emotional state.

[0449] Step 7:

[0450] If a user reviews the suggested meal menu and wishes to place a delivery order, the server connects with a food delivery service. This connection allows users to easily order the suggested meal menu. In this case, the order data is sent to the food delivery service via an API.

[0451] Step 8:

[0452] The delivery service prepares meals based on the suggested menu and delivers them to the user. Through this entire process, users not only receive feedback for health management but also take concrete actions (ordering meals) based on that feedback.

[0453] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0454] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0455] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0456] [Second Embodiment]

[0457] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0458] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0459] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0460] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0461] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0462] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0463] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0464] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0465] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0466] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0467] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0468] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0469] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The system consists of a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, receiving feedback from the generative artificial intelligence, and transmitting it back to the user.

[0470] System configuration and operation

[0471] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. This data entered by the user into the application is first stored by the device. Then, the device sends this data to the server.

[0472] Next, the server receives this data. The server checks the accuracy and consistency of the received data. If an anomaly is detected, a notification is sent to the user prompting them to re-enter the data. If accurate data is obtained, that data is sent to a generative artificial intelligence for analysis.

[0473] Generative artificial intelligence (AI) compares past data and general health information to generate useful feedback for the user. For example, if it is determined that a user's weight is increasing or their blood pressure is high, the AI ​​will generate feedback such as recommendations for improving their diet or exercising.

[0474] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[0475] Specific example

[0476] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the data is sent to a generative artificial intelligence.

[0477] The generative AI compares the user's data from the past month and confirms that their weight has increased and their blood pressure is elevated. Based on this, the generative AI generates the following feedback: "User, your weight has increased in the past month. Your blood pressure is also elevated. Please try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[0478] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[0479] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence (AI). The AI ​​analyzes the data usage and usage patterns and generates appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0480] Thus, the present invention provides a system that appropriately analyzes users' health data and mobile usage data and provides useful feedback to improve users' quality of life.

[0481] The following describes the processing flow.

[0482] ❶ Utilization of PHR at HELPO

[0483] Processing flow: Utilizing PHR in HELPO

[0484] Step 1:

[0485] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[0486] The device stores the entered data within the app and converts it into a format for sending to the server.

[0487] Step 2:

[0488] The server receives health data sent from the user's terminal.

[0489] The server verifies the data to ensure it is accurate and consistent.

[0490] Step 3:

[0491] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0492] The server verifies that the data transmission was successful.

[0493] Step 4:

[0494] Generative artificial intelligence analyzes the received health data.

[0495] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[0496] Step 5:

[0497] Generative artificial intelligence generates useful feedback based on the analysis results.

[0498] The feedback includes specific health management advice and warnings.

[0499] Step 6:

[0500] The generative artificial intelligence generates feedback which is then sent to the server.

[0501] The server prepares to send feedback to the user.

[0502] Step 7:

[0503] The server sends the generated feedback to the user's device.

[0504] Users receive notifications on their smartphones, open the app, and check the feedback.

[0505] Step 8:

[0506] Users review the feedback and modify their health management behaviors.

[0507] For example, reviewing your diet and adding exercise are recommended.

[0508] ❷ Utilization in mobile usage patterns

[0509] Processing flow: Utilization based on mobile usage

[0510] Step 1:

[0511] The user opens the app on their smartphone to check their monthly usage details.

[0512] The terminal collects usage details data and converts it into a format for transmission to the server.

[0513] Step 2:

[0514] The server receives monthly usage data sent from the user's terminal.

[0515] The server verifies the data to ensure its consistency.

[0516] Step 3:

[0517] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0518] The server verifies that the data transmission was successful.

[0519] Step 4:

[0520] The generative artificial intelligence analyzes the usage data it receives.

[0521] Generative artificial intelligence compares current usage with past data to identify increases or decreases in usage and unusual usage patterns.

[0522] Step 5:

[0523] Generative artificial intelligence generates useful feedback based on the analysis results.

[0524] The feedback includes specific advice and warnings regarding data usage and usage patterns.

[0525] Step 6:

[0526] The generative artificial intelligence generates feedback which is then sent to the server.

[0527] The server prepares to send feedback to the user.

[0528] Step 7:

[0529] The server sends the generated feedback to the user's device.

[0530] Users receive notifications on their smartphones, open the app, and check the feedback.

[0531] Step 8:

[0532] Users review the feedback and adjust their mobile usage accordingly.

[0533] For example, take measures such as actively using Wi-Fi to reduce data usage.

[0534] The above outlines the specific processing flow within this system.

[0535] (Example 1)

[0536] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0537] In today's living environment, it is crucial to efficiently and appropriately understand individual health conditions and provide feedback based on that understanding. However, manually recording and analyzing data is time-consuming and prone to inaccuracies. Similarly, managing mobile usage data is not easy for users themselves. Therefore, there is a need for a system that allows users to easily input health and mobile usage data, and that appropriately analyzes this data to provide feedback.

[0538] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0539] In this invention, the server includes means for receiving health data entered by the user, means for temporarily storing the received health data in a computer system, means for transmitting the stored data to a central control unit, means for verifying the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if an abnormal value is detected, means for transmitting normal data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This enables the user to easily and accurately manage their health data and mobile usage data and to quickly receive appropriate feedback based on that data.

[0540] A "user" is an individual who uses the system to input health data and mobile usage data.

[0541] "Health data" refers to information that indicates an individual's health status, such as weight, body fat percentage, and blood pressure.

[0542] "Mobile usage data" refers to information that shows how a user's mobile device is being used, such as application usage time and data usage.

[0543] An "electronic computer system" is a computer system used for processing data, such as storing, transmitting, and analyzing it.

[0544] A "central control unit" is a device that manages received data and controls its transmission to the artificial intelligence used for analysis.

[0545] "Generative artificial intelligence" is a type of artificial intelligence that analyzes received data and generates feedback for the user.

[0546] "Feedback" refers to advice and instructions for the user that a generative artificial intelligence generates based on its analysis results.

[0547] "Means of verifying accuracy and consistency" refer to methods for verifying that received data is appropriate and does not contradict past data.

[0548] An "outlier" is a data value that deviates from the normal range, indicating an input error or an abnormal condition.

[0549] A "notification prompting re-entry" is a message that asks the user to re-enter data when an abnormal value is detected.

[0550] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The present invention is a system that includes a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, and providing feedback of the analysis results to the user.

[0551] System configuration and operation

[0552] 1. User data entry

[0553] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[0554] 2. Data storage and transmission

[0555] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[0556] 3. Receiving and confirming data

[0557] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[0558] 4. Data transmission to generative artificial intelligence

[0559] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[0560] 5. Data Analysis and Feedback Generation

[0561] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user. This feedback is then sent back to the server as the result of the generative AI's analysis.

[0562] 6. Submit feedback

[0563] The server sends feedback received from the generative artificial intelligence to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[0564] Specific example

[0565] Consider a scenario where a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency and accuracy. Once consistency is confirmed, the data is sent to a generative artificial intelligence (GPT-4). The generative AI compares this data to the data from the past month and confirms that the user's weight has increased and their blood pressure is elevated. Based on this, the generative AI generates feedback such as: "User, your weight has increased over the past month. Your blood pressure is also elevated. Try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[0566] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[0567] Example of a prompt

[0568] Analyze the user's input data and provide feedback. The user's weight is 70kg, body fat percentage is 22%, and blood pressure is 130 / 85. Compare this to data from the past month and generate appropriate health advice.

[0569] This system allows users to easily and accurately manage their health and mobile usage data and receive timely, relevant feedback based on that data. The seamless integration of the entire system enhances the user experience and contributes to improved health management and mobile usage.

[0570] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0571] Step 1: Enter user data

[0572] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[0573] Specific actions:

[0574] The user opens the app and enters data such as weight (70kg), body fat percentage (22%), and blood pressure (130 / 85).

[0575] input:

[0576] Health data or mobile usage data.

[0577] output:

[0578] Data stored in the device's local storage.

[0579] Step 2: Save and send data from your device.

[0580] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[0581] Specific actions:

[0582] The user clicks the "Send" button.

[0583] The device writes data to local storage.

[0584] The device sends data to the server using an HTTP request.

[0585] input:

[0586] Health data or mobile usage data stored in local storage.

[0587] output:

[0588] Data sent to the server.

[0589] Step 3: Server data reception and verification

[0590] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[0591] Specific actions:

[0592] The server receives an HTTP request.

[0593] The server checks the accuracy and consistency of the data. For example, it checks whether outliers such as a weight of 500kg are detected.

[0594] If an abnormal value is detected, the server will send a notification to the user prompting them to re-enter the information.

[0595] input:

[0596] Data sent from the device.

[0597] output:

[0598] Notifications indicating that re-entry is required, or confirmed valid data.

[0599] Step 4: Sending data to the generative artificial intelligence

[0600] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[0601] Specific actions:

[0602] The server organizes the verified data and sends it as a POST request to the generative AI's API endpoint.

[0603] The request will include health data. For example: "Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85".

[0604] input:

[0605] Verified and valid data.

[0606] output:

[0607] Data sent to a generative artificial intelligence system.

[0608] Step 5: Data Analysis and Feedback Generation

[0609] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user.

[0610] Specific actions:

[0611] GPT-4 will perform data analysis and compare it with data from the past month.

[0612] Based on the analysis results, feedback is generated for the user. Example: "User, your weight has increased in the past month. Your blood pressure is also on the high side. Please try to eat a balanced diet and get moderate exercise."

[0613] input:

[0614] Health data or mobile usage data transmitted from the server.

[0615] output:

[0616] Analyzed data and generated feedback.

[0617] Step 6: Send feedback back to the server

[0618] The generative artificial intelligence sends the generated feedback back to the server. The server receives it and proceeds to the next processing step.

[0619] Specific actions:

[0620] The GPT-4 sends the generated feedback back to the server.

[0621] The server receives the data and saves it to the database.

[0622] input:

[0623] Feedback from generative artificial intelligence.

[0624] output:

[0625] Feedback information stored on the server.

[0626] Step 7: Submitting Feedback

[0627] The server sends the received feedback to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[0628] Specific actions:

[0629] The server sends feedback to the user's smartphone using a notification or HTTP request.

[0630] The user clicks the notification to check the feedback.

[0631] input:

[0632] Feedback information stored on the server.

[0633] output:

[0634] Feedback displayed on the user's device.

[0635] (Application Example 1)

[0636] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0637] Managing employee health and optimizing robot operating efficiency are major challenges in modern factories. Unclear employee health status can negatively impact work safety and efficiency. Furthermore, the inability to understand appropriate robot operating patterns can easily lead to reduced utilization and inefficient operation. Moreover, manually managing this data is labor-intensive and time-consuming, making automation essential.

[0638] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0639] In this invention, the server includes means for receiving health data and operational data entered by the user, means for transmitting the received health data and operational data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user and the robot. This enables the optimization of employee health management and robot operational efficiency.

[0640] "Health data" refers to information about biometric indicators such as weight, body fat percentage, and blood pressure that users input.

[0641] "Operational data" refers to information about the operating status and performance of robots and machines used in factories and other work sites.

[0642] "Generative artificial intelligence for analysis" refers to a system that includes advanced algorithms and models for analyzing received data and generating appropriate feedback for the user or machine.

[0643] "Feedback" refers to advice and recommendations provided by generative artificial intelligence as a result of analyzing health data and operational data.

[0644] A "user" is an individual or administrator who uses this system to input health data and operational data.

[0645] A "robot" is a mechanical device that automatically performs specific tasks in factories and other workplaces.

[0646] "Means of receiving data" refers to the mechanisms and methods for receiving data from users and various devices and incorporating it into the system.

[0647] "Means of transmission" refers to the mechanisms and methods for sending collected data and analysis results to appropriate destinations (generative artificial intelligence, users, robots, etc.).

[0648] This invention provides a system that optimizes employee health management and robot operation management within a factory. The system collects health and operation data entered by the user, analyzes the data using generative artificial intelligence, and provides feedback.

[0649] The server receives health and operational data entered by users. This includes data entered from users' smartphones and tablets. Health data includes weight, body fat percentage, and blood pressure, while operational data includes the operating status and performance data of robots and machines.

[0650] The received data is checked for consistency and accuracy on the server. If an anomaly is detected, the server sends a notification to the user prompting them to re-enter the data. If normal data is obtained, it is sent to the generative artificial intelligence.

[0651] Generative artificial intelligence analyzes received health and operational data to generate appropriate feedback. For example, if an employee's weight is increasing or their blood pressure is high, the generative AI will recommend a balanced diet and moderate exercise. For robot operational data, advice is provided to improve operational efficiency.

[0652] The generated feedback is sent via a server to the user's smartphone or tablet, as well as to the monitoring robot. Based on this feedback, users and factory managers can take action to improve health management and operational efficiency.

[0653] The hardware used includes smartphones, tablets, and robots. The software used includes Python, the requests library, and a generative artificial intelligence server.

[0654] As a concrete example, factory employees input their daily weight, body fat percentage, and blood pressure into their smartphones, and this data is sent to a server. After consistency and accuracy are verified, generative artificial intelligence analyzes the data and generates feedback. For example, feedback such as, "User, your weight has increased in the past month. Your blood pressure is also on the high side. Try to eat a balanced diet and get moderate exercise," is generated and sent to the user.

[0655] Additionally, robot operation data is transmitted, analyzed by generative artificial intelligence, and feedback is provided such as, "To improve the efficiency of operating time, it is recommended to review the timing of operations."

[0656] Example of a prompt:

[0657] "Analyze the user's health data (weight, body fat percentage, blood pressure) from the past month and generate feedback for health management."

[0658] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0659] Step 1:

[0660] Users input health and operational data using smartphones or tablets. Health data includes weight, body fat percentage, and blood pressure. Operational data includes the operating status and performance data of robots and machinery. This input is transmitted directly to the server by the user's device.

[0661] Input: Health data and work data entered by the user.

[0662] Output: Input data sent to the server

[0663] Step 2:

[0664] The server checks the accuracy and consistency of the data it receives. Specifically, it verifies that there are no outliers and that the data is free of missing values ​​or formatting errors. If outliers or missing values ​​are detected, the server sends a notification to the user's terminal prompting them to re-enter the data.

[0665] Input: Health data and operational data submitted by the user.

[0666] Output: Successful data or notification prompting re-entry.

[0667] Step 3:

[0668] The server transmits data that has been verified for accuracy and consistency to the generative artificial intelligence. At this time, current and past health data and operational data are also transmitted to enable appropriate analysis by comparing them with past data.

[0669] Input: Accurate health and operational data submitted by the user.

[0670] Output: Data sent to the generative artificial intelligence.

[0671] Step 4:

[0672] Generative artificial intelligence analyzes received data and generates feedback. Based on health data, for example, it generates health management advice based on fluctuations in weight and blood pressure. Based on operational data, it generates recommendations for efficient robot operation patterns and maintenance.

[0673] Input: Health data and operational data received by the generative artificial intelligence.

[0674] Output: Generated feedback

[0675] Step 5:

[0676] The server sends the generated feedback to the user's terminal and the robot. The user receives health management advice and warnings, while the robot receives instructions for improving its operating patterns and performing maintenance.

[0677] Input: Feedback generated by a generative artificial intelligence system.

[0678] Output: Feedback sent to the user's terminal and the robot.

[0679] Step 6:

[0680] Users and factory managers use their devices to review feedback and take necessary actions. Specifically, users may improve their diet or revise their exercise plans based on health management advice. Factory managers may adjust robot operating patterns and maintenance plans.

[0681] Input: Feedback received by user and factory administrator terminals.

[0682] Output: Actions taken by users and factory administrators

[0683] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0684] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[0685] System configuration and operation

[0686] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. The data entered by the user is stored on the device and sent to the server.

[0687] Next, the server receives this data. The server checks the accuracy and consistency of the data and sends a notification prompting re-entry if any anomalies are found. If accurate data is obtained, it is sent to a generative artificial intelligence for analysis.

[0688] Furthermore, the emotion engine incorporated into the system of the present invention recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and the content of the input data, and generates emotion data. This emotion data is also transmitted to the generative artificial intelligence system.

[0689] Generative artificial intelligence analyzes received health data, mobile usage data, and emotional data. By comparing historical data with general health indicators and emotional information, it generates optimal feedback for the user. For example, if a user's weight is increasing and the emotional engine detects that their stress levels are high, the generative AI can generate feedback recommending stress reduction strategies and dietary changes.

[0690] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[0691] Specific example

[0692] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the emotion engine analyzes the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to the generative artificial intelligence.

[0693] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[0694] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[0695] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0696] Thus, the present invention provides a system that appropriately analyzes users' health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[0697] The following describes the processing flow.

[0698] ❶ Utilizing PHR in HELPO (with emotion engine)

[0699] Processing flow: Utilizing PHR in HELPO

[0700] Step 1:

[0701] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[0702] The device stores the entered data within the app and converts it into a format for sending to the server.

[0703] Step 2:

[0704] The server receives health data sent from the user's terminal.

[0705] The server performs validation to ensure the accuracy and consistency of the data.

[0706] Step 3:

[0707] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0708] The server verifies that the data transmission was successful.

[0709] Step 4:

[0710] The user activates the in-app camera, and the emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0711] The device sends the generated emotion data to the server.

[0712] Step 5:

[0713] The server receives emotion data sent from the user's terminal.

[0714] The server verifies the accuracy and consistency of emotional data, as well as health data.

[0715] Step 6:

[0716] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[0717] The server verifies that the data transmission was successful.

[0718] Step 7:

[0719] Generative artificial intelligence analyzes the received health and emotional data.

[0720] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[0721] Step 8:

[0722] Generative artificial intelligence generates feedback based on received health data, emotional data, and mobile usage data.

[0723] The feedback includes specific advice and warnings regarding health management.

[0724] Step 9:

[0725] The feedback generated by the generative artificial intelligence is returned to the server.

[0726] The server receives the feedback and prepares to send it to the user.

[0727] Step 10:

[0728] The server sends the generated feedback to the user's device.

[0729] Users receive notifications on their smartphones, open the app, and check the feedback.

[0730] Step 11:

[0731] Users review the feedback and modify their health management behaviors and emotional management.

[0732] For example, it is recommended to review your diet, add exercise, and implement stress reduction measures.

[0733] ❷ Application in mobile usage (with emotion engine)

[0734] Processing flow: Utilization based on mobile usage

[0735] Step 1:

[0736] The user opens the app on their smartphone to check their monthly usage details.

[0737] The terminal collects usage details data and converts it into a format for transmission to the server.

[0738] Step 2:

[0739] The server receives monthly usage data sent from the user's terminal.

[0740] The server performs validation to ensure the accuracy and consistency of the data.

[0741] Step 3:

[0742] After the server checks for accuracy and consistency, it sends the verified usage data to a generative artificial intelligence system for analysis.

[0743] The server verifies that the data transmission was successful.

[0744] Step 4:

[0745] The user activates the in-app camera, and the emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0746] The device sends the generated emotion data to the server.

[0747] Step 5:

[0748] The server receives emotion data sent from the user's terminal.

[0749] The server verifies the accuracy and consistency of emotional data, as well as health data.

[0750] Step 6:

[0751] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[0752] The server verifies that the data transmission was successful.

[0753] Step 7:

[0754] The generative artificial intelligence analyzes the received usage data and sentiment data.

[0755] Generative artificial intelligence compares current data with past data to identify increases or decreases in communication usage, abnormal usage patterns, and emotional states.

[0756] Step 8:

[0757] The generative artificial intelligence generates feedback based on the received usage data and sentiment data.

[0758] The feedback includes specific advice and warnings regarding optimizing communication usage.

[0759] Step 9:

[0760] The feedback generated by the generative artificial intelligence is returned to the server.

[0761] The server receives the feedback and prepares to send it to the user.

[0762] Step 10:

[0763] The server sends the generated feedback to the user's device.

[0764] Users receive notifications on their smartphones, open the app, and check the feedback.

[0765] Step 11:

[0766] Users review feedback and make adjustments to their mobile usage and sentiment management.

[0767] For example, it is recommended to use Wi-Fi to reduce data usage and to take measures to reduce stress.

[0768] The above outlines the specific processing flow within this system.

[0769] (Example 2)

[0770] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0771] Traditional systems could analyze user health data and mobile usage data individually, but struggled to integrate this data and provide feedback that considered the user's emotional state. Furthermore, the lack of automated means to verify data consistency and accuracy meant that detecting anomalies and prompting re-entry was often done manually, placing a significant burden on users. This made optimal health management and lifestyle improvements difficult.

[0772] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0773] In this invention, the server includes means for receiving health data entered by the user, means for storing the received health data and transmitting it to the server, means for checking the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if abnormal values ​​exist, means for transmitting normal health data to a generative artificial intelligence for analysis, means for generating emotional data with an emotion engine for analyzing the user's emotions, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This makes it possible to comprehensively analyze health data, mobile usage data, and user emotional data, and provide optimal feedback to the user in real time.

[0774] "Health data" refers to information about a user's physical health, such as weight, body fat percentage, and blood pressure.

[0775] A "server" is a computer system that receives, stores, processes, and transmits data.

[0776] A "terminal" refers to a device used by a user to input data and communicate with a server, such as a smartphone or tablet.

[0777] "Generative artificial intelligence" refers to algorithms and systems that analyze input data and generate feedback.

[0778] An "emotion engine" is a system that analyzes a user's emotional state from their voice, facial expressions, and input data, and generates emotional data.

[0779] "Consistency" is a characteristic that indicates that the received data is consistent and unambiguous.

[0780] A "notification prompting re-entry" is a message that requests the user to re-enter data if there are discrepancies in the accuracy or consistency of the data.

[0781] "Means for sending data to a generative artificial intelligence for analysis" refers to a mechanism for sending data that has been verified for accuracy and consistency to a generative artificial intelligence for analysis.

[0782] "Feedback" refers to advice and information provided to users based on the results of analysis by generative artificial intelligence.

[0783] "Mobile usage data" refers to information about how users are using their mobile devices and their usage patterns.

[0784] "Means of sending notifications" refers to a mechanism that sends a message to the user prompting them to re-enter information when an abnormal value is detected.

[0785] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[0786] Hardware and software configuration

[0787] Users input daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using devices such as smartphones and tablets. The device temporarily stores this data and sends it to a server via the internet. The server automatically checks the accuracy and consistency of the received data and sends a notification to the user prompting them to re-enter the data if any abnormal values ​​are found. Generative artificial intelligence on the server performs the analysis using AI models such as TensorFlow and OpenAI's GPT-3.

[0788] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and input data, and generates emotion data. Software such as FaceAPI and Affectiva can be used for emotion analysis. This emotion data is also sent to the generative artificial intelligence.

[0789] Generative artificial intelligence integrates and analyzes received health data, mobile usage data, and emotional data. Based on historical data, general health indicators, and emotional information, it can generate optimal feedback for the user. The generated feedback is returned to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and adjusts their health management behaviors accordingly.

[0790] Specific example

[0791] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and verifies its consistency. The consistent data is then analyzed by an emotion engine to determine the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to a generative artificial intelligence system.

[0792] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[0793] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[0794] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0795] Examples of prompt messages include, "Generate optimal health advice based on the user's health data," and "Analyze this data and create feedback that provides the user with stress reduction advice." In this way, the present invention realizes a system that appropriately analyzes the user's health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[0796] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0797] Step 1:

[0798] Users input health data (weight, body fat percentage, blood pressure, etc.) using their smartphones or tablets.

[0799] Input: Health data entered by the user (e.g., weight 70kg, body fat percentage 22%, blood pressure 130 / 85)

[0800] Output: Health data temporarily stored by the device

[0801] Step 2:

[0802] The device sends the health data it has saved to the server.

[0803] Input: Health data stored on the device

[0804] Output: Health data sent to the server

[0805] Step 3:

[0806] The server checks the accuracy and consistency of the health data it receives.

[0807] Input: Health data received by the server

[0808] Output: Data with confirmed accuracy and consistency; notifications prompting re-entry if outliers are found.

[0809] Step 4:

[0810] The server sends normal health data to a generative artificial intelligence system for analysis.

[0811] Input: Health data verified for accuracy and consistency.

[0812] Output: Data sent to the generative artificial intelligence for analysis.

[0813] Step 5:

[0814] The emotion engine analyzes the user's voice, facial expressions, and input data to generate emotion data.

[0815] Input: User's voice and facial expression data, entered health data

[0816] Output: Generated sentiment data

[0817] Step 6:

[0818] The server sends emotional data to a generative artificial intelligence system for analysis.

[0819] Input: Generated emotion data

[0820] Output: Emotional data sent to a generative artificial intelligence for analysis.

[0821] Step 7:

[0822] Generative artificial intelligence analyzes health data, mobile usage data, and emotional data to generate appropriate feedback.

[0823] Input: Submitted health data, mobile usage data, emotional data

[0824] Output: Generated feedback

[0825] Step 8:

[0826] The server sends the generated feedback to the user's device.

[0827] Input: Generated feedback

[0828] Output: Feedback sent to the user's device

[0829] Step 9:

[0830] Users can view feedback through their devices and adjust their actions based on that feedback.

[0831] Input: Feedback sent to the device

[0832] Output: Review of user feedback and modification of actions

[0833] Through these steps, the system can comprehensively analyze the user's health data and mobile usage data, and provide appropriate feedback that also takes into account the user's emotional state.

[0834] (Application Example 2)

[0835] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0836] In modern society, managing users' health is a crucial issue, and many people find it difficult to maintain proper health management amidst their busy lives. Furthermore, stress and emotional fluctuations significantly impact health, creating a need for methods that provide comprehensive feedback, including emotional responses, to individual users. Additionally, there is a desire for integration with food delivery services that utilize health and emotional data to provide optimal meal suggestions that users can immediately implement.

[0837] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving health data entered by the user, means for transmitting the received health data to a generative artificial intelligence for analysis, means for emotion recognition for generating emotion data from the user's voice and facial expressions, means for transmitting the generated emotion data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, means for transmitting the received feedback to the user, means for analyzing the health data and emotion data to make meal suggestions, and means for ordering the suggested meal menu in cooperation with a food delivery service. This makes it possible to provide comprehensive feedback based on health data and emotion data, and to suggest and implement the optimal meal according to the user's unique health condition.

[0838] "Health data" refers to biometric information such as weight, body fat percentage, and blood pressure entered by the user.

[0839] "Generative artificial intelligence" is an artificial intelligence technology that analyzes data received from users and generates feedback.

[0840] An "emotion recognition method" is a system that analyzes the user's voice and facial expressions to generate emotion data.

[0841] "Emotional data" refers to information generated by emotion recognition tools that indicates the user's emotional state.

[0842] "Feedback" refers to advice and instructions that generative artificial intelligence provides to the user based on its analysis results.

[0843] The "means of providing meal suggestions" refer to a system that suggests appropriate meal menus based on the user's health data and emotional data.

[0844] A "food delivery service" is an external delivery service that delivers suggested meal menus to users.

[0845] A "notification prompting re-entry" is a message that requests the user to re-enter accurate data when an abnormal value is detected.

[0846] This invention is a system for analyzing a user's health and emotional data and providing feedback and meal suggestions. The system consists of means for receiving health data entered by the user, means for emotion recognition, generative artificial intelligence, means for sending feedback, means for providing meal suggestions, and means for placing orders in cooperation with a food delivery service.

[0847] System configuration and operation

[0848] 1. Input and reception of health data

[0849] Users input health data such as weight, body fat percentage, and blood pressure using their own devices (e.g., smartphones). The devices then send this data to the server.

[0850] 2. Emotion recognition

[0851] The server analyzes the user's voice and facial expressions using emotion recognition tools (e.g., EmotionEngine) and generates emotion data. This emotion data is also sent to the server.

[0852] 3. Data Analysis

[0853] The server sends the received health and emotional data to a generative artificial intelligence (e.g., HealthAIModel) for analysis. The generative AI then generates feedback based on the received data.

[0854] 4. Providing feedback

[0855] The generated feedback is sent to the user's device by the server. The user can review the feedback and revise their health management methods.

[0856] 5. Meal suggestions and food delivery

[0857] Generative artificial intelligence provides optimal meal suggestions based on health and emotional data. The suggested meal menus are linked to food delivery services via a server, allowing users to order directly.

[0858] Hardware and software

[0859] Hardware: Smartphones, servers

[0860] Software: EmotionEngine (emotion recognition method), HealthAIModel (generative artificial intelligence)

[0861] Specific example

[0862] For example, consider a user who inputs a weight of 70 kg, a body fat percentage of 22%, and a blood pressure of 130 / 85. This data is sent to the server, where a high-stress state is detected by emotion recognition. Based on this data, a generative artificial intelligence generates the following feedback and meal suggestions:

[0863] "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Focus on a balanced diet, moderate exercise, and incorporate relaxation into your routine. We suggest the following meal plan, which includes balanced meals and relaxing elements."

[0864] Example of a prompt

[0865] The user's health data is as follows:

[0866] Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85

[0867] The emotional data indicates a high stress level.

[0868] Please suggest the optimal meal plan for the user.

[0869] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0870] Step 1:

[0871] Users input health data (e.g., weight, body fat percentage, blood pressure) using a smartphone or other device. The entered data is sent from the device to the server. At this time, the system also checks the integrity and format of the input data.

[0872] Step 2:

[0873] The server checks the accuracy and consistency of the received health data before sending it to the generative artificial intelligence for analysis. If the data is inconsistent or contains abnormal values, a notification prompting the user to re-enter the data is sent to their device. If the data is normal, the server proceeds to the next step.

[0874] Step 3:

[0875] Using emotion recognition tools (e.g., EmotionEngine), the server generates emotion data from the user's voice and facial expressions. This emotion data is also sent to a generative artificial intelligence. Input data includes the user's voice files and real-time video feeds.

[0876] Step 4:

[0877] The server sends normal health data and generated emotional data to a generative artificial intelligence (e.g., HealthAIModel). The generative AI analyzes the user's health and emotional state based on this data and generates comprehensive feedback. Specifically, judgments are made based on comparisons with past data and general health indicators.

[0878] Step 5:

[0879] The generated feedback is sent back to the server, which then sends it to the user's device. The user can then view the feedback through their device. This feedback includes an assessment of their health status and specific advice for improvement.

[0880] Step 6:

[0881] Furthermore, the generative artificial intelligence suggests meal menus tailored to the user based on health and emotional data. This information is provided to the user via a server. The suggested menus are optimized for each user's individual health and emotional state.

[0882] Step 7:

[0883] If a user reviews the suggested meal menu and wishes to place a delivery order, the server connects with a food delivery service. This connection allows users to easily order the suggested meal menu. In this case, the order data is sent to the food delivery service via an API.

[0884] Step 8:

[0885] The delivery service prepares meals based on the suggested menu and delivers them to the user. Through this entire process, users not only receive feedback for health management but also take concrete actions (ordering meals) based on that feedback.

[0886] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0887] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0888] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0889] [Third Embodiment]

[0890] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0891] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0892] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0893] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0894] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0895] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0896] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0897] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0898] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0899] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0900] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0901] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0902] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The system consists of a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, receiving feedback from the generative artificial intelligence, and transmitting it back to the user.

[0903] System configuration and operation

[0904] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. This data entered by the user into the application is first stored by the device. Then, the device sends this data to the server.

[0905] Next, the server receives this data. The server checks the accuracy and consistency of the received data. If an anomaly is detected, a notification is sent to the user prompting them to re-enter the data. If accurate data is obtained, that data is sent to a generative artificial intelligence for analysis.

[0906] Generative artificial intelligence (AI) compares past data and general health information to generate useful feedback for the user. For example, if it is determined that a user's weight is increasing or their blood pressure is high, the AI ​​will generate feedback such as recommendations for improving their diet or exercising.

[0907] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[0908] Specific example

[0909] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the data is sent to a generative artificial intelligence.

[0910] The generative AI compares the user's data from the past month and confirms that their weight has increased and their blood pressure is elevated. Based on this, the generative AI generates the following feedback: "User, your weight has increased in the past month. Your blood pressure is also elevated. Please try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[0911] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[0912] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence (AI). The AI ​​analyzes the data usage and usage patterns and generates appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[0913] Thus, the present invention provides a system that appropriately analyzes users' health data and mobile usage data and provides useful feedback to improve users' quality of life.

[0914] The following describes the processing flow.

[0915] ❶ Utilization of PHR at HELPO

[0916] Processing flow: Utilizing PHR in HELPO

[0917] Step 1:

[0918] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[0919] The device stores the entered data within the app and converts it into a format for sending to the server.

[0920] Step 2:

[0921] The server receives health data sent from the user's terminal.

[0922] The server verifies the data to ensure it is accurate and consistent.

[0923] Step 3:

[0924] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0925] The server verifies that the data transmission was successful.

[0926] Step 4:

[0927] Generative artificial intelligence analyzes the received health data.

[0928] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[0929] Step 5:

[0930] Generative artificial intelligence generates useful feedback based on the analysis results.

[0931] The feedback includes specific health management advice and warnings.

[0932] Step 6:

[0933] The generative artificial intelligence generates feedback which is then sent to the server.

[0934] The server prepares to send feedback to the user.

[0935] Step 7:

[0936] The server sends the generated feedback to the user's device.

[0937] Users receive notifications on their smartphones, open the app, and check the feedback.

[0938] Step 8:

[0939] Users review the feedback and modify their health management behaviors.

[0940] For example, reviewing your diet and adding exercise are recommended.

[0941] ❷ Utilization in mobile usage patterns

[0942] Processing flow: Utilization based on mobile usage

[0943] Step 1:

[0944] The user opens the app on their smartphone to check their monthly usage details.

[0945] The terminal collects usage details data and converts it into a format for transmission to the server.

[0946] Step 2:

[0947] The server receives monthly usage data sent from the user's terminal.

[0948] The server verifies the data to ensure its consistency.

[0949] Step 3:

[0950] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[0951] The server verifies that the data transmission was successful.

[0952] Step 4:

[0953] The generative artificial intelligence analyzes the usage data it receives.

[0954] Generative artificial intelligence compares current usage with past data to identify increases or decreases in usage and unusual usage patterns.

[0955] Step 5:

[0956] Generative artificial intelligence generates useful feedback based on the analysis results.

[0957] The feedback includes specific advice and warnings regarding data usage and usage patterns.

[0958] Step 6:

[0959] The generative artificial intelligence generates feedback which is then sent to the server.

[0960] The server prepares to send feedback to the user.

[0961] Step 7:

[0962] The server sends the generated feedback to the user's device.

[0963] Users receive notifications on their smartphones, open the app, and check the feedback.

[0964] Step 8:

[0965] Users review the feedback and adjust their mobile usage accordingly.

[0966] For example, take measures such as actively using Wi-Fi to reduce data usage.

[0967] The above outlines the specific processing flow within this system.

[0968] (Example 1)

[0969] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0970] In today's living environment, it is crucial to efficiently and appropriately understand individual health conditions and provide feedback based on that understanding. However, manually recording and analyzing data is time-consuming and prone to inaccuracies. Similarly, managing mobile usage data is not easy for users themselves. Therefore, there is a need for a system that allows users to easily input health and mobile usage data, and that appropriately analyzes this data to provide feedback.

[0971] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0972] In this invention, the server includes means for receiving health data entered by the user, means for temporarily storing the received health data in a computer system, means for transmitting the stored data to a central control unit, means for verifying the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if an abnormal value is detected, means for transmitting normal data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This enables the user to easily and accurately manage their health data and mobile usage data and to quickly receive appropriate feedback based on that data.

[0973] A "user" is an individual who uses the system to input health data and mobile usage data.

[0974] "Health data" refers to information that indicates an individual's health status, such as weight, body fat percentage, and blood pressure.

[0975] "Mobile usage data" refers to information that shows how a user's mobile device is being used, such as application usage time and data usage.

[0976] An "electronic computer system" is a computer system used for processing data, such as storing, transmitting, and analyzing it.

[0977] A "central control unit" is a device that manages received data and controls its transmission to the artificial intelligence used for analysis.

[0978] "Generative artificial intelligence" is a type of artificial intelligence that analyzes received data and generates feedback for the user.

[0979] "Feedback" refers to advice and instructions for the user that a generative artificial intelligence generates based on its analysis results.

[0980] "Means of verifying accuracy and consistency" refer to methods for verifying that received data is appropriate and does not contradict past data.

[0981] An "outlier" is a data value that deviates from the normal range, indicating an input error or an abnormal condition.

[0982] A "notification prompting re-entry" is a message that asks the user to re-enter data when an abnormal value is detected.

[0983] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The present invention is a system that includes a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, and providing feedback of the analysis results to the user.

[0984] System configuration and operation

[0985] 1. User data entry

[0986] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[0987] 2. Data storage and transmission

[0988] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[0989] 3. Receiving and confirming data

[0990] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[0991] 4. Data transmission to generative artificial intelligence

[0992] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[0993] 5. Data Analysis and Feedback Generation

[0994] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user. This feedback is then sent back to the server as the result of the generative AI's analysis.

[0995] 6. Submit feedback

[0996] The server sends feedback received from the generative artificial intelligence to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[0997] Specific example

[0998] Consider a scenario where a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency and accuracy. Once consistency is confirmed, the data is sent to a generative artificial intelligence (GPT-4). The generative AI compares this data to the data from the past month and confirms that the user's weight has increased and their blood pressure is elevated. Based on this, the generative AI generates feedback such as: "User, your weight has increased over the past month. Your blood pressure is also elevated. Try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[0999] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[1000] Example of a prompt

[1001] Analyze the user's input data and provide feedback. The user's weight is 70kg, body fat percentage is 22%, and blood pressure is 130 / 85. Compare this to data from the past month and generate appropriate health advice.

[1002] This system allows users to easily and accurately manage their health and mobile usage data and receive timely, relevant feedback based on that data. The seamless integration of the entire system enhances the user experience and contributes to improved health management and mobile usage.

[1003] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1004] Step 1: Enter user data

[1005] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[1006] Specific actions:

[1007] The user opens the app and enters data such as weight (70kg), body fat percentage (22%), and blood pressure (130 / 85).

[1008] input:

[1009] Health data or mobile usage data.

[1010] output:

[1011] Data stored in the device's local storage.

[1012] Step 2: Save and send data from your device.

[1013] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[1014] Specific actions:

[1015] The user clicks the "Send" button.

[1016] The device writes data to local storage.

[1017] The device sends data to the server using an HTTP request.

[1018] input:

[1019] Health data or mobile usage data stored in local storage.

[1020] output:

[1021] Data sent to the server.

[1022] Step 3: Server data reception and verification

[1023] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[1024] Specific actions:

[1025] The server receives an HTTP request.

[1026] The server checks the accuracy and consistency of the data. For example, it checks whether outliers such as a weight of 500kg are detected.

[1027] If an abnormal value is detected, the server will send a notification to the user prompting them to re-enter the information.

[1028] input:

[1029] Data sent from the device.

[1030] output:

[1031] Notifications indicating that re-entry is required, or confirmed valid data.

[1032] Step 4: Sending data to the generative artificial intelligence

[1033] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[1034] Specific actions:

[1035] The server organizes the verified data and sends it as a POST request to the generative AI's API endpoint.

[1036] The request will include health data. For example: "Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85".

[1037] input:

[1038] Verified and valid data.

[1039] output:

[1040] Data sent to a generative artificial intelligence system.

[1041] Step 5: Data Analysis and Feedback Generation

[1042] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user.

[1043] Specific actions:

[1044] GPT-4 will perform data analysis and compare it with data from the past month.

[1045] Based on the analysis results, feedback is generated for the user. Example: "User, your weight has increased in the past month. Your blood pressure is also on the high side. Please try to eat a balanced diet and get moderate exercise."

[1046] input:

[1047] Health data or mobile usage data transmitted from the server.

[1048] output:

[1049] Analyzed data and generated feedback.

[1050] Step 6: Send feedback back to the server

[1051] The generative artificial intelligence sends the generated feedback back to the server. The server receives it and proceeds to the next processing step.

[1052] Specific actions:

[1053] The GPT-4 sends the generated feedback back to the server.

[1054] The server receives the data and saves it to the database.

[1055] input:

[1056] Feedback from generative artificial intelligence.

[1057] output:

[1058] Feedback information stored on the server.

[1059] Step 7: Submitting Feedback

[1060] The server sends the received feedback to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[1061] Specific actions:

[1062] The server sends feedback to the user's smartphone using a notification or HTTP request.

[1063] The user clicks the notification to check the feedback.

[1064] input:

[1065] Feedback information stored on the server.

[1066] output:

[1067] Feedback displayed on the user's device.

[1068] (Application Example 1)

[1069] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1070] Managing employee health and optimizing robot operating efficiency are major challenges in modern factories. Unclear employee health status can negatively impact work safety and efficiency. Furthermore, the inability to understand appropriate robot operating patterns can easily lead to reduced utilization and inefficient operation. Moreover, manually managing this data is labor-intensive and time-consuming, making automation essential.

[1071] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1072] In this invention, the server includes means for receiving health data and operational data entered by the user, means for transmitting the received health data and operational data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user and the robot. This enables the optimization of employee health management and robot operational efficiency.

[1073] "Health data" refers to information about biometric indicators such as weight, body fat percentage, and blood pressure that users input.

[1074] "Operational data" refers to information about the operating status and performance of robots and machines used in factories and other work sites.

[1075] "Generative artificial intelligence for analysis" refers to a system that includes advanced algorithms and models for analyzing received data and generating appropriate feedback for the user or machine.

[1076] "Feedback" refers to advice and recommendations provided by generative artificial intelligence as a result of analyzing health data and operational data.

[1077] A "user" is an individual or administrator who uses this system to input health data and operational data.

[1078] A "robot" is a mechanical device that automatically performs specific tasks in factories and other workplaces.

[1079] "Means of receiving data" refers to the mechanisms and methods for receiving data from users and various devices and incorporating it into the system.

[1080] "Means of transmission" refers to the mechanisms and methods for sending collected data and analysis results to appropriate destinations (generative artificial intelligence, users, robots, etc.).

[1081] This invention provides a system that optimizes employee health management and robot operation management within a factory. The system collects health and operation data entered by the user, analyzes the data using generative artificial intelligence, and provides feedback.

[1082] The server receives health and operational data entered by users. This includes data entered from users' smartphones and tablets. Health data includes weight, body fat percentage, and blood pressure, while operational data includes the operating status and performance data of robots and machines.

[1083] The received data is checked for consistency and accuracy on the server. If an anomaly is detected, the server sends a notification to the user prompting them to re-enter the data. If normal data is obtained, it is sent to the generative artificial intelligence.

[1084] Generative artificial intelligence analyzes received health and operational data to generate appropriate feedback. For example, if an employee's weight is increasing or their blood pressure is high, the generative AI will recommend a balanced diet and moderate exercise. For robot operational data, advice is provided to improve operational efficiency.

[1085] The generated feedback is sent via a server to the user's smartphone or tablet, as well as to the monitoring robot. Based on this feedback, users and factory managers can take action to improve health management and operational efficiency.

[1086] The hardware used includes smartphones, tablets, and robots. The software used includes Python, the requests library, and a generative artificial intelligence server.

[1087] As a concrete example, factory employees input their daily weight, body fat percentage, and blood pressure into their smartphones, and this data is sent to a server. After consistency and accuracy are verified, generative artificial intelligence analyzes the data and generates feedback. For example, feedback such as, "User, your weight has increased in the past month. Your blood pressure is also on the high side. Try to eat a balanced diet and get moderate exercise," is generated and sent to the user.

[1088] Additionally, robot operation data is transmitted, analyzed by generative artificial intelligence, and feedback is provided such as, "To improve the efficiency of operating time, it is recommended to review the timing of operations."

[1089] Example of a prompt:

[1090] "Analyze the user's health data (weight, body fat percentage, blood pressure) from the past month and generate feedback for health management."

[1091] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1092] Step 1:

[1093] Users input health and operational data using smartphones or tablets. Health data includes weight, body fat percentage, and blood pressure. Operational data includes the operating status and performance data of robots and machinery. This input is transmitted directly to the server by the user's device.

[1094] Input: Health data and work data entered by the user.

[1095] Output: Input data sent to the server

[1096] Step 2:

[1097] The server checks the accuracy and consistency of the data it receives. Specifically, it verifies that there are no outliers and that the data is free of missing values ​​or formatting errors. If outliers or missing values ​​are detected, the server sends a notification to the user's terminal prompting them to re-enter the data.

[1098] Input: Health data and operational data submitted by the user.

[1099] Output: Successful data or notification prompting re-entry.

[1100] Step 3:

[1101] The server transmits data that has been verified for accuracy and consistency to the generative artificial intelligence. At this time, current and past health data and operational data are also transmitted to enable appropriate analysis by comparing them with past data.

[1102] Input: Accurate health and operational data submitted by the user.

[1103] Output: Data sent to the generative artificial intelligence.

[1104] Step 4:

[1105] Generative artificial intelligence analyzes received data and generates feedback. Based on health data, for example, it generates health management advice based on fluctuations in weight and blood pressure. Based on operational data, it generates recommendations for efficient robot operation patterns and maintenance.

[1106] Input: Health data and operational data received by the generative artificial intelligence.

[1107] Output: Generated feedback

[1108] Step 5:

[1109] The server sends the generated feedback to the user's terminal and the robot. The user receives health management advice and warnings, while the robot receives instructions for improving its operating patterns and performing maintenance.

[1110] Input: Feedback generated by a generative artificial intelligence system.

[1111] Output: Feedback sent to the user's terminal and the robot.

[1112] Step 6:

[1113] Users and factory managers use their devices to review feedback and take necessary actions. Specifically, users may improve their diet or revise their exercise plans based on health management advice. Factory managers may adjust robot operating patterns and maintenance plans.

[1114] Input: Feedback received by user and factory administrator terminals.

[1115] Output: Actions taken by users and factory administrators

[1116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1117] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[1118] System configuration and operation

[1119] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. The data entered by the user is stored on the device and sent to the server.

[1120] Next, the server receives this data. The server checks the accuracy and consistency of the data and sends a notification prompting re-entry if any anomalies are found. If accurate data is obtained, it is sent to a generative artificial intelligence for analysis.

[1121] Furthermore, the emotion engine incorporated into the system of the present invention recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and the content of the input data, and generates emotion data. This emotion data is also transmitted to the generative artificial intelligence system.

[1122] Generative artificial intelligence analyzes received health data, mobile usage data, and emotional data. By comparing historical data with general health indicators and emotional information, it generates optimal feedback for the user. For example, if a user's weight is increasing and the emotional engine detects that their stress levels are high, the generative AI can generate feedback recommending stress reduction strategies and dietary changes.

[1123] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[1124] Specific example

[1125] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the emotion engine analyzes the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to the generative artificial intelligence.

[1126] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[1127] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[1128] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[1129] Thus, the present invention provides a system that appropriately analyzes users' health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[1130] The following describes the processing flow.

[1131] ❶ Utilizing PHR in HELPO (with emotion engine)

[1132] Processing flow: Utilizing PHR in HELPO

[1133] Step 1:

[1134] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[1135] The device stores the entered data within the app and converts it into a format for sending to the server.

[1136] Step 2:

[1137] The server receives health data sent from the user's terminal.

[1138] The server performs validation to ensure the accuracy and consistency of the data.

[1139] Step 3:

[1140] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[1141] The server verifies that the data transmission was successful.

[1142] Step 4:

[1143] The user activates the in-app camera, and the emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1144] The device sends the generated emotion data to the server.

[1145] Step 5:

[1146] The server receives emotion data sent from the user's terminal.

[1147] The server verifies the accuracy and consistency of emotional data, as well as health data.

[1148] Step 6:

[1149] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[1150] The server verifies that the data transmission was successful.

[1151] Step 7:

[1152] Generative artificial intelligence analyzes the received health and emotional data.

[1153] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[1154] Step 8:

[1155] Generative artificial intelligence generates feedback based on received health data, emotional data, and mobile usage data.

[1156] The feedback includes specific advice and warnings regarding health management.

[1157] Step 9:

[1158] The feedback generated by the generative artificial intelligence is returned to the server.

[1159] The server receives the feedback and prepares to send it to the user.

[1160] Step 10:

[1161] The server sends the generated feedback to the user's device.

[1162] Users receive notifications on their smartphones, open the app, and check the feedback.

[1163] Step 11:

[1164] Users review the feedback and modify their health management behaviors and emotional management.

[1165] For example, it is recommended to review your diet, add exercise, and implement stress reduction measures.

[1166] ❷ Application in mobile usage (with emotion engine)

[1167] Processing flow: Utilization based on mobile usage

[1168] Step 1:

[1169] The user opens the app on their smartphone to check their monthly usage details.

[1170] The terminal collects usage details data and converts it into a format for transmission to the server.

[1171] Step 2:

[1172] The server receives monthly usage data sent from the user's terminal.

[1173] The server performs validation to ensure the accuracy and consistency of the data.

[1174] Step 3:

[1175] After the server checks for accuracy and consistency, it sends the verified usage data to a generative artificial intelligence system for analysis.

[1176] The server verifies that the data transmission was successful.

[1177] Step 4:

[1178] The user activates the in-app camera, and the emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1179] The device sends the generated emotion data to the server.

[1180] Step 5:

[1181] The server receives emotion data sent from the user's terminal.

[1182] The server verifies the accuracy and consistency of emotional data, as well as health data.

[1183] Step 6:

[1184] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[1185] The server verifies that the data transmission was successful.

[1186] Step 7:

[1187] The generative artificial intelligence analyzes the received usage data and sentiment data.

[1188] Generative artificial intelligence compares current data with past data to identify increases or decreases in communication usage, abnormal usage patterns, and emotional states.

[1189] Step 8:

[1190] The generative artificial intelligence generates feedback based on the received usage data and sentiment data.

[1191] The feedback includes specific advice and warnings regarding optimizing communication usage.

[1192] Step 9:

[1193] The feedback generated by the generative artificial intelligence is returned to the server.

[1194] The server receives the feedback and prepares to send it to the user.

[1195] Step 10:

[1196] The server sends the generated feedback to the user's device.

[1197] Users receive notifications on their smartphones, open the app, and check the feedback.

[1198] Step 11:

[1199] Users review feedback and make adjustments to their mobile usage and sentiment management.

[1200] For example, it is recommended to use Wi-Fi to reduce data usage and to take measures to reduce stress.

[1201] The above outlines the specific processing flow within this system.

[1202] (Example 2)

[1203] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1204] Traditional systems could analyze user health data and mobile usage data individually, but struggled to integrate this data and provide feedback that considered the user's emotional state. Furthermore, the lack of automated means to verify data consistency and accuracy meant that detecting anomalies and prompting re-entry was often done manually, placing a significant burden on users. This made optimal health management and lifestyle improvements difficult.

[1205] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1206] In this invention, the server includes means for receiving health data entered by the user, means for storing the received health data and transmitting it to the server, means for checking the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if abnormal values ​​exist, means for transmitting normal health data to a generative artificial intelligence for analysis, means for generating emotional data with an emotion engine for analyzing the user's emotions, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This makes it possible to comprehensively analyze health data, mobile usage data, and user emotional data, and provide optimal feedback to the user in real time.

[1207] "Health data" refers to information about a user's physical health, such as weight, body fat percentage, and blood pressure.

[1208] A "server" is a computer system that receives, stores, processes, and transmits data.

[1209] A "terminal" refers to a device used by a user to input data and communicate with a server, such as a smartphone or tablet.

[1210] "Generative artificial intelligence" refers to algorithms and systems that analyze input data and generate feedback.

[1211] An "emotion engine" is a system that analyzes a user's emotional state from their voice, facial expressions, and input data, and generates emotional data.

[1212] "Consistency" is a characteristic that indicates that the received data is consistent and unambiguous.

[1213] A "notification prompting re-entry" is a message that requests the user to re-enter data if there are discrepancies in the accuracy or consistency of the data.

[1214] "Means for sending data to a generative artificial intelligence for analysis" refers to a mechanism for sending data that has been verified for accuracy and consistency to a generative artificial intelligence for analysis.

[1215] "Feedback" refers to advice and information provided to users based on the results of analysis by generative artificial intelligence.

[1216] "Mobile usage data" refers to information about how users are using their mobile devices and their usage patterns.

[1217] "Means of sending notifications" refers to a mechanism that sends a message to the user prompting them to re-enter information when an abnormal value is detected.

[1218] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[1219] Hardware and software configuration

[1220] Users input daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using devices such as smartphones and tablets. The device temporarily stores this data and sends it to a server via the internet. The server automatically checks the accuracy and consistency of the received data and sends a notification to the user prompting them to re-enter the data if any abnormal values ​​are found. Generative artificial intelligence on the server performs the analysis using AI models such as TensorFlow and OpenAI's GPT-3.

[1221] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and input data, and generates emotion data. Software such as FaceAPI and Affectiva can be used for emotion analysis. This emotion data is also sent to the generative artificial intelligence.

[1222] Generative artificial intelligence integrates and analyzes received health data, mobile usage data, and emotional data. Based on historical data, general health indicators, and emotional information, it can generate optimal feedback for the user. The generated feedback is returned to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and adjusts their health management behaviors accordingly.

[1223] Specific example

[1224] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and verifies its consistency. The consistent data is then analyzed by an emotion engine to determine the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to a generative artificial intelligence system.

[1225] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[1226] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[1227] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[1228] Examples of prompt messages include, "Generate optimal health advice based on the user's health data," and "Analyze this data and create feedback that provides the user with stress reduction advice." In this way, the present invention realizes a system that appropriately analyzes the user's health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[1229] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1230] Step 1:

[1231] Users input health data (weight, body fat percentage, blood pressure, etc.) using their smartphones or tablets.

[1232] Input: Health data entered by the user (e.g., weight 70kg, body fat percentage 22%, blood pressure 130 / 85)

[1233] Output: Health data temporarily stored by the device

[1234] Step 2:

[1235] The device sends the health data it has saved to the server.

[1236] Input: Health data stored on the device

[1237] Output: Health data sent to the server

[1238] Step 3:

[1239] The server checks the accuracy and consistency of the health data it receives.

[1240] Input: Health data received by the server

[1241] Output: Data with confirmed accuracy and consistency; notifications prompting re-entry if outliers are found.

[1242] Step 4:

[1243] The server sends normal health data to a generative artificial intelligence system for analysis.

[1244] Input: Health data verified for accuracy and consistency.

[1245] Output: Data sent to the generative artificial intelligence for analysis.

[1246] Step 5:

[1247] The emotion engine analyzes the user's voice, facial expressions, and input data to generate emotion data.

[1248] Input: User's voice and facial expression data, entered health data

[1249] Output: Generated sentiment data

[1250] Step 6:

[1251] The server sends emotional data to a generative artificial intelligence system for analysis.

[1252] Input: Generated emotion data

[1253] Output: Emotional data sent to a generative artificial intelligence for analysis.

[1254] Step 7:

[1255] Generative artificial intelligence analyzes health data, mobile usage data, and emotional data to generate appropriate feedback.

[1256] Input: Submitted health data, mobile usage data, emotional data

[1257] Output: Generated feedback

[1258] Step 8:

[1259] The server sends the generated feedback to the user's device.

[1260] Input: Generated feedback

[1261] Output: Feedback sent to the user's device

[1262] Step 9:

[1263] Users can view feedback through their devices and adjust their actions based on that feedback.

[1264] Input: Feedback sent to the device

[1265] Output: Review of user feedback and modification of actions

[1266] Through these steps, the system can comprehensively analyze the user's health data and mobile usage data, and provide appropriate feedback that also takes into account the user's emotional state.

[1267] (Application Example 2)

[1268] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1269] In modern society, managing users' health is a crucial issue, and many people find it difficult to maintain proper health management amidst their busy lives. Furthermore, stress and emotional fluctuations significantly impact health, creating a need for methods that provide comprehensive feedback, including emotional responses, to individual users. Additionally, there is a desire for integration with food delivery services that utilize health and emotional data to provide optimal meal suggestions that users can immediately implement.

[1270] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving health data entered by the user, means for transmitting the received health data to a generative artificial intelligence for analysis, means for emotion recognition for generating emotion data from the user's voice and facial expressions, means for transmitting the generated emotion data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, means for transmitting the received feedback to the user, means for analyzing the health data and emotion data to make meal suggestions, and means for ordering the suggested meal menu in cooperation with a food delivery service. This makes it possible to provide comprehensive feedback based on health data and emotion data, and to suggest and implement the optimal meal according to the user's unique health condition.

[1271] "Health data" refers to biometric information such as weight, body fat percentage, and blood pressure entered by the user.

[1272] "Generative artificial intelligence" is an artificial intelligence technology that analyzes data received from users and generates feedback.

[1273] An "emotion recognition method" is a system that analyzes the user's voice and facial expressions to generate emotion data.

[1274] "Emotional data" refers to information generated by emotion recognition tools that indicates the user's emotional state.

[1275] "Feedback" refers to advice and instructions that generative artificial intelligence provides to the user based on its analysis results.

[1276] The "means of providing meal suggestions" refer to a system that suggests appropriate meal menus based on the user's health data and emotional data.

[1277] A "food delivery service" is an external delivery service that delivers suggested meal menus to users.

[1278] A "notification prompting re-entry" is a message that requests the user to re-enter accurate data when an abnormal value is detected.

[1279] This invention is a system for analyzing a user's health and emotional data and providing feedback and meal suggestions. The system consists of means for receiving health data entered by the user, means for emotion recognition, generative artificial intelligence, means for sending feedback, means for providing meal suggestions, and means for placing orders in cooperation with a food delivery service.

[1280] System configuration and operation

[1281] 1. Input and reception of health data

[1282] Users input health data such as weight, body fat percentage, and blood pressure using their own devices (e.g., smartphones). The devices then send this data to the server.

[1283] 2. Emotion recognition

[1284] The server analyzes the user's voice and facial expressions using emotion recognition tools (e.g., EmotionEngine) and generates emotion data. This emotion data is also sent to the server.

[1285] 3. Data Analysis

[1286] The server sends the received health and emotional data to a generative artificial intelligence (e.g., HealthAIModel) for analysis. The generative AI then generates feedback based on the received data.

[1287] 4. Providing feedback

[1288] The generated feedback is sent to the user's device by the server. The user can review the feedback and revise their health management methods.

[1289] 5. Meal suggestions and food delivery

[1290] Generative artificial intelligence provides optimal meal suggestions based on health and emotional data. The suggested meal menus are linked to food delivery services via a server, allowing users to order directly.

[1291] Hardware and software

[1292] Hardware: Smartphones, servers

[1293] Software: EmotionEngine (emotion recognition method), HealthAIModel (generative artificial intelligence)

[1294] Specific example

[1295] For example, consider a user who inputs a weight of 70 kg, a body fat percentage of 22%, and a blood pressure of 130 / 85. This data is sent to the server, where a high-stress state is detected by emotion recognition. Based on this data, a generative artificial intelligence generates the following feedback and meal suggestions:

[1296] "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Focus on a balanced diet, moderate exercise, and incorporate relaxation into your routine. We suggest the following meal plan, which includes balanced meals and relaxing elements."

[1297] Example of a prompt

[1298] The user's health data is as follows:

[1299] Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85

[1300] The emotional data indicates a high stress level.

[1301] Please suggest the optimal meal plan for the user.

[1302] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1303] Step 1:

[1304] Users input health data (e.g., weight, body fat percentage, blood pressure) using a smartphone or other device. The entered data is sent from the device to the server. At this time, the system also checks the integrity and format of the input data.

[1305] Step 2:

[1306] The server checks the accuracy and consistency of the received health data before sending it to the generative artificial intelligence for analysis. If the data is inconsistent or contains abnormal values, a notification prompting re-entry is sent to the user's device. If the data is normal, the server proceeds to the next step.

[1307] Step 3:

[1308] Using emotion recognition tools (e.g., EmotionEngine), the server generates emotion data from the user's voice and facial expressions. This emotion data is also sent to a generative artificial intelligence. Input data includes the user's voice files and real-time video feeds.

[1309] Step 4:

[1310] The server sends normal health data and generated emotional data to a generative artificial intelligence (e.g., HealthAIModel). The generative AI analyzes the user's health and emotional state based on this data and generates comprehensive feedback. Specifically, judgments are made based on comparisons with past data and general health indicators.

[1311] Step 5:

[1312] The generated feedback is sent back to the server, which then sends it to the user's device. The user can then view the feedback through their device. This feedback includes an assessment of their health status and specific advice for improvement.

[1313] Step 6:

[1314] Furthermore, the generative artificial intelligence suggests meal menus tailored to the user based on health and emotional data. This information is provided to the user via a server. The suggested menus are optimized for each user's individual health and emotional state.

[1315] Step 7:

[1316] If a user reviews the suggested meal menu and wishes to place a delivery order, the server connects with a food delivery service. This connection allows users to easily order the suggested meal menu. In this case, the order data is sent to the food delivery service via an API.

[1317] Step 8:

[1318] The delivery service prepares meals based on the suggested menu and delivers them to the user. Through this entire process, users not only receive feedback for health management but also take concrete actions (ordering meals) based on that feedback.

[1319] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1320] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1321] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1322] [Fourth Embodiment]

[1323] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1324] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1325] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1326] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1327] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1328] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1329] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1330] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1331] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1332] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1333] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1334] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1335] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1336] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The system consists of a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, receiving feedback from the generative artificial intelligence, and transmitting it back to the user.

[1337] System configuration and operation

[1338] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. This data entered by the user into the application is first stored by the device. Then, the device sends this data to the server.

[1339] Next, the server receives this data. The server checks the accuracy and consistency of the received data. If an anomaly is detected, a notification is sent to the user prompting them to re-enter the data. If accurate data is obtained, that data is sent to a generative artificial intelligence for analysis.

[1340] Generative artificial intelligence (AI) compares past data and general health information to generate useful feedback for the user. For example, if it is determined that a user's weight is increasing or their blood pressure is high, the AI ​​will generate feedback such as recommendations for improving their diet or exercising.

[1341] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[1342] Specific example

[1343] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the data is sent to a generative artificial intelligence.

[1344] The generative AI compares the user's data from the past month and confirms that their weight has increased and their blood pressure is elevated. Based on this, the generative AI generates the following feedback: "User, your weight has increased in the past month. Your blood pressure is also elevated. Please try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[1345] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[1346] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence (AI). The AI ​​analyzes the data usage and usage patterns and generates appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[1347] Thus, the present invention provides a system that appropriately analyzes users' health data and mobile usage data and provides useful feedback to improve users' quality of life.

[1348] The following describes the processing flow.

[1349] ❶ Utilization of PHR at HELPO

[1350] Processing flow: Utilizing PHR in HELPO

[1351] Step 1:

[1352] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[1353] The device stores the entered data within the app and converts it into a format for sending to the server.

[1354] Step 2:

[1355] The server receives health data sent from the user's terminal.

[1356] The server verifies the data to ensure it is accurate and consistent.

[1357] Step 3:

[1358] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[1359] The server verifies that the data transmission was successful.

[1360] Step 4:

[1361] Generative artificial intelligence analyzes the received health data.

[1362] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[1363] Step 5:

[1364] Generative artificial intelligence generates useful feedback based on the analysis results.

[1365] The feedback includes specific health management advice and warnings.

[1366] Step 6:

[1367] The generative artificial intelligence generates feedback which is then sent to the server.

[1368] The server prepares to send feedback to the user.

[1369] Step 7:

[1370] The server sends the generated feedback to the user's device.

[1371] Users receive notifications on their smartphones, open the app, and check the feedback.

[1372] Step 8:

[1373] Users review the feedback and modify their health management behaviors.

[1374] For example, reviewing your diet and adding exercise are recommended.

[1375] ❷ Utilization in mobile usage patterns

[1376] Processing flow: Utilization based on mobile usage

[1377] Step 1:

[1378] The user opens the app on their smartphone to check their monthly usage details.

[1379] The terminal collects usage details data and converts it into a format for transmission to the server.

[1380] Step 2:

[1381] The server receives monthly usage data sent from the user's terminal.

[1382] The server verifies the data to ensure its consistency.

[1383] Step 3:

[1384] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[1385] The server verifies that the data transmission was successful.

[1386] Step 4:

[1387] The generative artificial intelligence analyzes the usage data it receives.

[1388] Generative artificial intelligence compares current usage with past data to identify increases or decreases in usage and unusual usage patterns.

[1389] Step 5:

[1390] Generative artificial intelligence generates useful feedback based on the analysis results.

[1391] The feedback includes specific advice and warnings regarding data usage and usage patterns.

[1392] Step 6:

[1393] The generative artificial intelligence generates feedback which is then sent to the server.

[1394] The server prepares to send feedback to the user.

[1395] Step 7:

[1396] The server sends the generated feedback to the user's device.

[1397] Users receive notifications on their smartphones, open the app, and check the feedback.

[1398] Step 8:

[1399] Users review the feedback and adjust their mobile usage accordingly.

[1400] For example, take measures such as actively using Wi-Fi to reduce data usage.

[1401] The above outlines the specific processing flow within this system.

[1402] (Example 1)

[1403] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1404] In today's living environment, it is crucial to efficiently and appropriately understand individual health conditions and provide feedback based on that understanding. However, manually recording and analyzing data is time-consuming and prone to inaccuracies. Similarly, managing mobile usage data is not easy for users themselves. Therefore, there is a need for a system that allows users to easily input health and mobile usage data, and that appropriately analyzes this data to provide feedback.

[1405] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1406] In this invention, the server includes means for receiving health data entered by the user, means for temporarily storing the received health data in a computer system, means for transmitting the stored data to a central control unit, means for verifying the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if an abnormal value is detected, means for transmitting normal data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This enables the user to easily and accurately manage their health data and mobile usage data and to quickly receive appropriate feedback based on that data.

[1407] A "user" is an individual who uses the system to input health data and mobile usage data.

[1408] "Health data" refers to information that indicates an individual's health status, such as weight, body fat percentage, and blood pressure.

[1409] "Mobile usage data" refers to information that shows how a user's mobile device is being used, such as application usage time and data usage.

[1410] An "electronic computer system" is a computer system used for processing data, such as storing, transmitting, and analyzing it.

[1411] A "central control unit" is a device that manages received data and controls its transmission to the artificial intelligence used for analysis.

[1412] "Generative artificial intelligence" is a type of artificial intelligence that analyzes received data and generates feedback for the user.

[1413] "Feedback" refers to advice and instructions for the user that a generative artificial intelligence generates based on its analysis results.

[1414] "Means of verifying accuracy and consistency" refer to methods for verifying that received data is appropriate and does not contradict past data.

[1415] An "outlier" is a data value that deviates from the normal range, indicating an input error or an abnormal condition.

[1416] A "notification prompting re-entry" is a message that asks the user to re-enter data when an abnormal value is detected.

[1417] This invention relates to a system that analyzes user-inputted health data and mobile usage data and provides feedback. The present invention is a system that includes a series of processes: receiving data input by the user, transmitting it to a generative artificial intelligence for analysis, and providing feedback of the analysis results to the user.

[1418] System configuration and operation

[1419] 1. User data entry

[1420] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[1421] 2. Data storage and transmission

[1422] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[1423] 3. Receiving and confirming data

[1424] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[1425] 4. Data transmission to generative artificial intelligence

[1426] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[1427] 5. Data Analysis and Feedback Generation

[1428] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user. This feedback is then sent back to the server as the result of the generative AI's analysis.

[1429] 6. Submit feedback

[1430] The server sends feedback received from the generative artificial intelligence to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[1431] Specific example

[1432] Consider a scenario where a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency and accuracy. Once consistency is confirmed, the data is sent to a generative artificial intelligence (GPT-4). The generative AI compares this data to the data from the past month and confirms that the user's weight has increased and their blood pressure is elevated. Based on this, the generative AI generates feedback such as: "User, your weight has increased over the past month. Your blood pressure is also elevated. Try to eat a balanced diet and get moderate exercise. Consult a doctor if necessary."

[1433] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback and reconsider their health management practices.

[1434] Example of a prompt

[1435] Analyze the user's input data and provide feedback. The user's weight is 70kg, body fat percentage is 22%, and blood pressure is 130 / 85. Compare this to data from the past month and generate appropriate health advice.

[1436] This system allows users to easily and accurately manage their health and mobile usage data and receive timely, relevant feedback based on that data. The seamless integration of the entire system enhances the user experience and contributes to improved health management and mobile usage.

[1437] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1438] Step 1: Enter user data

[1439] Users use their smartphones or other devices to input health data (e.g., weight, body fat percentage, blood pressure, etc.) and mobile usage data (e.g., app usage time, data usage, etc.) into a dedicated application.

[1440] Specific actions:

[1441] The user opens the app and enters data such as weight (70kg), body fat percentage (22%), and blood pressure (130 / 85).

[1442] input:

[1443] Health data or mobile usage data.

[1444] output:

[1445] Data stored in the device's local storage.

[1446] Step 2: Save and send data from your device.

[1447] The terminal temporarily stores the entered data in its internal computer system. The stored data is then transmitted from the terminal to the central control unit (server).

[1448] Specific actions:

[1449] The user clicks the "Send" button.

[1450] The device writes data to local storage.

[1451] The device sends data to the server using an HTTP request.

[1452] input:

[1453] Health data or mobile usage data stored in local storage.

[1454] output:

[1455] Data sent to the server.

[1456] Step 3: Server data reception and verification

[1457] The server receives data sent from the terminal. It verifies the accuracy and consistency of the received data, and if any abnormal values ​​are detected, it sends a notification to the user prompting them to re-enter the data.

[1458] Specific actions:

[1459] The server receives an HTTP request.

[1460] The server checks the accuracy and consistency of the data. For example, it checks whether outliers such as a weight of 500kg are detected.

[1461] If an abnormal value is detected, the server will send a notification to the user prompting them to re-enter the information.

[1462] input:

[1463] Data sent from the device.

[1464] output:

[1465] Notifications indicating that re-entry is required, or confirmed valid data.

[1466] Step 4: Sending data to the generative artificial intelligence

[1467] If the data is found to be normal, the server sends it to a generative artificial intelligence (specifically GPT-4) for analysis.

[1468] Specific actions:

[1469] The server organizes the verified data and sends it as a POST request to the generative AI's API endpoint.

[1470] The request will include health data. For example: "Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85".

[1471] input:

[1472] Verified and valid data.

[1473] output:

[1474] Data sent to a generative artificial intelligence system.

[1475] Step 5: Data Analysis and Feedback Generation

[1476] Generative artificial intelligence analyzes the received data and compares it with past data and general health information to generate appropriate feedback for the user.

[1477] Specific actions:

[1478] GPT-4 will perform data analysis and compare it with data from the past month.

[1479] Based on the analysis results, feedback is generated for the user. Example: "User, your weight has increased in the past month. Your blood pressure is also on the high side. Please try to eat a balanced diet and get moderate exercise."

[1480] input:

[1481] Health data or mobile usage data transmitted from the server.

[1482] output:

[1483] Analyzed data and generated feedback.

[1484] Step 6: Send feedback back to the server

[1485] The generative artificial intelligence sends the generated feedback back to the server. The server receives it and proceeds to the next processing step.

[1486] Specific actions:

[1487] The GPT-4 sends the generated feedback back to the server.

[1488] The server receives the data and saves it to the database.

[1489] input:

[1490] Feedback from generative artificial intelligence.

[1491] output:

[1492] Feedback information stored on the server.

[1493] Step 7: Submitting Feedback

[1494] The server sends the received feedback to the user's device. Users can then review the feedback through their device and use it to improve their health management and mobile usage.

[1495] Specific actions:

[1496] The server sends feedback to the user's smartphone using a notification or HTTP request.

[1497] The user clicks the notification to check the feedback.

[1498] input:

[1499] Feedback information stored on the server.

[1500] output:

[1501] Feedback displayed on the user's device.

[1502] (Application Example 1)

[1503] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1504] Managing employee health and optimizing robot operating efficiency are major challenges in modern factories. Unclear employee health status can negatively impact work safety and efficiency. Furthermore, the inability to understand appropriate robot operating patterns can easily lead to reduced utilization and inefficient operation. Moreover, manually managing this data is labor-intensive and time-consuming, making automation essential.

[1505] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1506] In this invention, the server includes means for receiving health data and operational data entered by the user, means for transmitting the received health data and operational data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user and the robot. This enables the optimization of employee health management and robot operational efficiency.

[1507] "Health data" refers to information about biometric indicators such as weight, body fat percentage, and blood pressure that users input.

[1508] "Operational data" refers to information about the operating status and performance of robots and machines used in factories and other work sites.

[1509] "Generative artificial intelligence for analysis" refers to a system that includes advanced algorithms and models for analyzing received data and generating appropriate feedback for the user or machine.

[1510] "Feedback" refers to advice and recommendations provided by generative artificial intelligence as a result of analyzing health data and operational data.

[1511] A "user" is an individual or administrator who uses this system to input health data and operational data.

[1512] A "robot" is a mechanical device that automatically performs specific tasks in factories and other workplaces.

[1513] "Means of receiving data" refers to the mechanisms and methods for receiving data from users and various devices and incorporating it into the system.

[1514] "Means of transmission" refers to the mechanisms and methods for sending collected data and analysis results to appropriate destinations (generative artificial intelligence, users, robots, etc.).

[1515] This invention provides a system that optimizes employee health management and robot operation management within a factory. The system collects health and operation data entered by the user, analyzes the data using generative artificial intelligence, and provides feedback.

[1516] The server receives health and operational data entered by users. This includes data entered from users' smartphones and tablets. Health data includes weight, body fat percentage, and blood pressure, while operational data includes the operating status and performance data of robots and machines.

[1517] The received data is checked for consistency and accuracy on the server. If an anomaly is detected, the server sends a notification to the user prompting them to re-enter the data. If normal data is obtained, it is sent to the generative artificial intelligence.

[1518] Generative artificial intelligence analyzes received health and operational data to generate appropriate feedback. For example, if an employee's weight is increasing or their blood pressure is high, the generative AI will recommend a balanced diet and moderate exercise. For robot operational data, advice is provided to improve operational efficiency.

[1519] The generated feedback is sent via a server to the user's smartphone or tablet, as well as to the monitoring robot. Based on this feedback, users and factory managers can take action to improve health management and operational efficiency.

[1520] The hardware used includes smartphones, tablets, and robots. The software used includes Python, the requests library, and a generative artificial intelligence server.

[1521] As a concrete example, factory employees input their daily weight, body fat percentage, and blood pressure into their smartphones, and this data is sent to a server. After consistency and accuracy are verified, generative artificial intelligence analyzes the data and generates feedback. For example, feedback such as, "User, your weight has increased in the past month. Your blood pressure is also on the high side. Try to eat a balanced diet and get moderate exercise," is generated and sent to the user.

[1522] Additionally, robot operation data is transmitted, analyzed by generative artificial intelligence, and feedback is provided such as, "To improve the efficiency of operating time, it is recommended to review the timing of operations."

[1523] Example of a prompt:

[1524] "Analyze the user's health data (weight, body fat percentage, blood pressure) from the past month and generate feedback for health management."

[1525] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1526] Step 1:

[1527] Users input health and operational data using smartphones or tablets. Health data includes weight, body fat percentage, and blood pressure. Operational data includes the operating status and performance data of robots and machinery. This input is transmitted directly to the server by the user's device.

[1528] Input: Health data and work data entered by the user.

[1529] Output: Input data sent to the server

[1530] Step 2:

[1531] The server checks the accuracy and consistency of the data it receives. Specifically, it verifies that there are no outliers and that the data is free of missing values ​​or formatting errors. If outliers or missing values ​​are detected, the server sends a notification to the user's terminal prompting them to re-enter the data.

[1532] Input: Health data and operational data submitted by the user.

[1533] Output: Successful data or notification prompting re-entry.

[1534] Step 3:

[1535] The server transmits data that has been verified for accuracy and consistency to the generative artificial intelligence. At this time, current and past health data and operational data are also transmitted to enable appropriate analysis by comparing them with past data.

[1536] Input: Accurate health and operational data submitted by the user.

[1537] Output: Data sent to the generative artificial intelligence.

[1538] Step 4:

[1539] Generative artificial intelligence analyzes received data and generates feedback. Based on health data, for example, it generates health management advice based on fluctuations in weight and blood pressure. Based on operational data, it generates recommendations for efficient robot operation patterns and maintenance.

[1540] Input: Health data and operational data received by the generative artificial intelligence.

[1541] Output: Generated feedback

[1542] Step 5:

[1543] The server sends the generated feedback to the user's terminal and the robot. The user receives health management advice and warnings, while the robot receives instructions for improving its operating patterns and performing maintenance.

[1544] Input: Feedback generated by a generative artificial intelligence system.

[1545] Output: Feedback sent to the user's terminal and the robot.

[1546] Step 6:

[1547] Users and factory managers use their devices to review feedback and take necessary actions. Specifically, users may improve their diet or revise their exercise plans based on health management advice. Factory managers may adjust robot operating patterns and maintenance plans.

[1548] Input: Feedback received by user and factory administrator terminals.

[1549] Output: Actions taken by users and factory administrators

[1550] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1551] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[1552] System configuration and operation

[1553] First, let's consider a scenario where a user enters daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using a smartphone or other device. The data entered by the user is stored on the device and sent to the server.

[1554] Next, the server receives this data. The server checks the accuracy and consistency of the data and sends a notification prompting re-entry if any anomalies are found. If accurate data is obtained, it is sent to a generative artificial intelligence for analysis.

[1555] Furthermore, the emotion engine incorporated into the system of the present invention recognizes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and the content of the input data, and generates emotion data. This emotion data is also transmitted to the generative artificial intelligence system.

[1556] Generative artificial intelligence analyzes received health data, mobile usage data, and emotional data. By comparing historical data with general health indicators and emotional information, it generates optimal feedback for the user. For example, if a user's weight is increasing and the emotional engine detects that their stress levels are high, the generative AI can generate feedback recommending stress reduction strategies and dietary changes.

[1557] The generated feedback is sent back to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and modifies their health management behaviors based on it.

[1558] Specific example

[1559] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and checks for consistency. Once consistency is confirmed, the emotion engine analyzes the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to the generative artificial intelligence.

[1560] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[1561] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[1562] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[1563] Thus, the present invention provides a system that appropriately analyzes users' health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[1564] The following describes the processing flow.

[1565] ❶ Utilizing PHR in HELPO (with emotion engine)

[1566] Processing flow: Utilizing PHR in HELPO

[1567] Step 1:

[1568] Users input health data (weight, body fat percentage, blood pressure, etc.) via a smartphone app.

[1569] The device stores the entered data within the app and converts it into a format for sending to the server.

[1570] Step 2:

[1571] The server receives health data sent from the user's terminal.

[1572] The server performs validation to ensure the accuracy and consistency of the data.

[1573] Step 3:

[1574] After the server checks for accuracy and consistency, it sends the verified data to a generative artificial intelligence system for analysis.

[1575] The server verifies that the data transmission was successful.

[1576] Step 4:

[1577] The user activates the in-app camera, and the emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1578] The device sends the generated emotion data to the server.

[1579] Step 5:

[1580] The server receives emotion data sent from the user's terminal.

[1581] The server verifies the accuracy and consistency of emotional data, as well as health data.

[1582] Step 6:

[1583] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[1584] The server verifies that the data transmission was successful.

[1585] Step 7:

[1586] Generative artificial intelligence analyzes the received health and emotional data.

[1587] Generative artificial intelligence compares historical data with general health indicators to identify specific trends and anomalies.

[1588] Step 8:

[1589] Generative artificial intelligence generates feedback based on received health data, emotional data, and mobile usage data.

[1590] The feedback includes specific advice and warnings regarding health management.

[1591] Step 9:

[1592] The feedback generated by the generative artificial intelligence is returned to the server.

[1593] The server receives the feedback and prepares to send it to the user.

[1594] Step 10:

[1595] The server sends the generated feedback to the user's device.

[1596] Users receive notifications on their smartphones, open the app, and check the feedback.

[1597] Step 11:

[1598] Users review the feedback and modify their health management behaviors and emotional management.

[1599] For example, it is recommended to review your diet, add exercise, and implement stress reduction measures.

[1600] ❷ Application in mobile usage (with emotion engine)

[1601] Processing flow: Utilization based on mobile usage

[1602] Step 1:

[1603] The user opens the app on their smartphone to check their monthly usage details.

[1604] The terminal collects usage details data and converts it into a format for transmission to the server.

[1605] Step 2:

[1606] The server receives monthly usage data sent from the user's terminal.

[1607] The server performs validation to ensure the accuracy and consistency of the data.

[1608] Step 3:

[1609] After the server checks for accuracy and consistency, it sends the verified usage data to a generative artificial intelligence system for analysis.

[1610] The server verifies that the data transmission was successful.

[1611] Step 4:

[1612] The user activates the in-app camera, and the emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1613] The device sends the generated emotion data to the server.

[1614] Step 5:

[1615] The server receives emotion data sent from the user's terminal.

[1616] The server verifies the accuracy and consistency of emotional data, as well as health data.

[1617] Step 6:

[1618] After the server verifies accuracy and consistency, it sends the emotional data to a generative artificial intelligence system for analysis.

[1619] The server verifies that the data transmission was successful.

[1620] Step 7:

[1621] The generative artificial intelligence analyzes the received usage data and sentiment data.

[1622] Generative artificial intelligence compares current data with past data to identify increases or decreases in communication usage, abnormal usage patterns, and emotional states.

[1623] Step 8:

[1624] The generative artificial intelligence generates feedback based on the received usage data and sentiment data.

[1625] The feedback includes specific advice and warnings regarding optimizing communication usage.

[1626] Step 9:

[1627] The feedback generated by the generative artificial intelligence is returned to the server.

[1628] The server receives the feedback and prepares to send it to the user.

[1629] Step 10:

[1630] The server sends the generated feedback to the user's device.

[1631] Users receive notifications on their smartphones, open the app, and check the feedback.

[1632] Step 11:

[1633] Users review feedback and make adjustments to their mobile usage and sentiment management.

[1634] For example, it is recommended to use Wi-Fi to reduce data usage and to take measures to reduce stress.

[1635] The above outlines the specific processing flow within this system.

[1636] (Example 2)

[1637] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1638] Traditional systems could analyze user health data and mobile usage data individually, but struggled to integrate this data and provide feedback that considered the user's emotional state. Furthermore, the lack of automated means to verify data consistency and accuracy meant that detecting anomalies and prompting re-entry was often done manually, placing a significant burden on users. This made optimal health management and lifestyle improvements difficult.

[1639] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1640] In this invention, the server includes means for receiving health data entered by the user, means for storing the received health data and transmitting it to the server, means for checking the accuracy and consistency of the received health data, means for sending a notification prompting re-entry if abnormal values ​​exist, means for transmitting normal health data to a generative artificial intelligence for analysis, means for generating emotional data with an emotion engine for analyzing the user's emotions, means for receiving feedback analyzed by the generative artificial intelligence, and means for transmitting the received feedback to the user. This makes it possible to comprehensively analyze health data, mobile usage data, and user emotional data, and provide optimal feedback to the user in real time.

[1641] "Health data" refers to information about a user's physical health, such as weight, body fat percentage, and blood pressure.

[1642] A "server" is a computer system that receives, stores, processes, and transmits data.

[1643] A "terminal" refers to a device used by a user to input data and communicate with a server, such as a smartphone or tablet.

[1644] "Generative artificial intelligence" refers to algorithms and systems that analyze input data and generate feedback.

[1645] An "emotion engine" is a system that analyzes a user's emotional state from their voice, facial expressions, and input data, and generates emotional data.

[1646] "Consistency" is a characteristic that indicates that the received data is consistent and unambiguous.

[1647] A "notification prompting re-entry" is a message that requests the user to re-enter data if there are discrepancies in the accuracy or consistency of the data.

[1648] "Means for sending data to a generative artificial intelligence for analysis" refers to a mechanism for sending data that has been verified for accuracy and consistency to a generative artificial intelligence for analysis.

[1649] "Feedback" refers to advice and information provided to users based on the results of analysis by generative artificial intelligence.

[1650] "Mobile usage data" refers to information about how users are using their mobile devices and their usage patterns.

[1651] "Means of sending notifications" refers to a mechanism that sends a message to the user prompting them to re-enter information when an abnormal value is detected.

[1652] This invention relates to a system that analyzes user-inputted health data and mobile usage data, and further combines this with an emotion engine that recognizes the user's emotions to provide feedback. The system consists of a series of processes: receiving health data and mobile usage data, analyzing it in conjunction with a generative artificial intelligence and emotion engine for analysis, and providing feedback to the user.

[1653] Hardware and software configuration

[1654] Users input daily health data (e.g., weight, body fat percentage, blood pressure, etc.) using devices such as smartphones and tablets. The device temporarily stores this data and sends it to a server via the internet. The server automatically checks the accuracy and consistency of the received data and sends a notification to the user prompting them to re-enter the data if any abnormal values ​​are found. Generative artificial intelligence on the server performs the analysis using AI models such as TensorFlow and OpenAI's GPT-3.

[1655] Furthermore, this system is equipped with an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's emotions from their voice, facial expressions, and input data, and generates emotion data. Software such as FaceAPI and Affectiva can be used for emotion analysis. This emotion data is also sent to the generative artificial intelligence.

[1656] Generative artificial intelligence integrates and analyzes received health data, mobile usage data, and emotional data. Based on historical data, general health indicators, and emotional information, it can generate optimal feedback for the user. The generated feedback is returned to the server, which then sends it to the user's device. The user reviews the feedback via their smartphone or other device and adjusts their health management behaviors accordingly.

[1657] Specific example

[1658] For example, suppose a user records their weight (70kg), body fat percentage (22%), and blood pressure (130 / 85) on their smartphone this morning. The device sends this data to a server. The server receives the data and verifies its consistency. The consistent data is then analyzed by an emotion engine to determine the user's emotions. If the emotion engine detects that the user is experiencing high stress levels based on their voice and facial expressions, that emotional data is also sent to a generative artificial intelligence system.

[1659] The generative AI compares the user's data from the past month and identifies that their weight has increased, their blood pressure is elevated, and their stress levels are higher. Based on this, the generative AI generates the following feedback: "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Try to eat a balanced diet, get moderate exercise, and make time for relaxation. Consult a doctor if necessary."

[1660] This feedback is sent back to the server, which then sends it to the user's smartphone. The user opens the app to review the feedback, reconsiders their health management methods, and takes steps to reduce stress.

[1661] Furthermore, data regarding mobile usage is processed similarly. When a user opens the app on their smartphone to check their monthly usage details, the usage data is sent to the server. The server receives the data and passes it to a generative artificial intelligence and an emotion engine. The generative AI and emotion engine analyze data usage, usage patterns, and emotional states, and generate appropriate advice for the user. This advice is then communicated to the user via the server, providing them with specific guidance to improve their usage.

[1662] Examples of prompt messages include, "Generate optimal health advice based on the user's health data," and "Analyze this data and create feedback that provides the user with stress reduction advice." In this way, the present invention realizes a system that appropriately analyzes the user's health data, mobile usage data, and emotional data, and provides useful feedback to improve the user's quality of life.

[1663] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1664] Step 1:

[1665] Users input health data (weight, body fat percentage, blood pressure, etc.) using their smartphones or tablets.

[1666] Input: Health data entered by the user (e.g., weight 70kg, body fat percentage 22%, blood pressure 130 / 85)

[1667] Output: Health data temporarily stored by the device

[1668] Step 2:

[1669] The device sends the health data it has saved to the server.

[1670] Input: Health data stored on the device

[1671] Output: Health data sent to the server

[1672] Step 3:

[1673] The server checks the accuracy and consistency of the health data it receives.

[1674] Input: Health data received by the server

[1675] Output: Data with confirmed accuracy and consistency; notifications prompting re-entry if outliers are found.

[1676] Step 4:

[1677] The server sends normal health data to a generative artificial intelligence system for analysis.

[1678] Input: Health data verified for accuracy and consistency.

[1679] Output: Data sent to the generative artificial intelligence for analysis.

[1680] Step 5:

[1681] The emotion engine analyzes the user's voice, facial expressions, and input data to generate emotion data.

[1682] Input: User's voice and facial expression data, entered health data

[1683] Output: Generated sentiment data

[1684] Step 6:

[1685] The server sends emotional data to a generative artificial intelligence system for analysis.

[1686] Input: Generated emotion data

[1687] Output: Emotional data sent to a generative artificial intelligence for analysis.

[1688] Step 7:

[1689] Generative artificial intelligence analyzes health data, mobile usage data, and emotional data to generate appropriate feedback.

[1690] Input: Submitted health data, mobile usage data, emotional data

[1691] Output: Generated feedback

[1692] Step 8:

[1693] The server sends the generated feedback to the user's device.

[1694] Input: Generated feedback

[1695] Output: Feedback sent to the user's device

[1696] Step 9:

[1697] Users can view feedback through their devices and adjust their actions based on that feedback.

[1698] Input: Feedback sent to the device

[1699] Output: Review of user feedback and modification of actions

[1700] Through these steps, the system can comprehensively analyze the user's health data and mobile usage data, and provide appropriate feedback that also takes into account the user's emotional state.

[1701] (Application Example 2)

[1702] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1703] In modern society, managing users' health is a crucial issue, and many people find it difficult to maintain proper health management amidst their busy lives. Furthermore, stress and emotional fluctuations significantly impact health, creating a need for methods that provide comprehensive feedback, including emotional responses, to individual users. Additionally, there is a desire for integration with food delivery services that utilize health and emotional data to provide optimal meal suggestions that users can immediately implement.

[1704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving health data entered by the user, means for transmitting the received health data to a generative artificial intelligence for analysis, means for emotion recognition for generating emotion data from the user's voice and facial expressions, means for transmitting the generated emotion data to a generative artificial intelligence for analysis, means for receiving feedback analyzed by the generative artificial intelligence, means for transmitting the received feedback to the user, means for analyzing the health data and emotion data to make meal suggestions, and means for ordering the suggested meal menu in cooperation with a food delivery service. This makes it possible to provide comprehensive feedback based on health data and emotion data, and to suggest and implement the optimal meal according to the user's unique health condition.

[1705] "Health data" refers to biometric information such as weight, body fat percentage, and blood pressure entered by the user.

[1706] "Generative artificial intelligence" is an artificial intelligence technology that analyzes data received from users and generates feedback.

[1707] An "emotion recognition method" is a system that analyzes the user's voice and facial expressions to generate emotion data.

[1708] "Emotional data" refers to information generated by emotion recognition tools that indicates the user's emotional state.

[1709] "Feedback" refers to advice and instructions that generative artificial intelligence provides to the user based on its analysis results.

[1710] The "means of providing meal suggestions" refer to a system that suggests appropriate meal menus based on the user's health data and emotional data.

[1711] A "food delivery service" is an external delivery service that delivers suggested meal menus to users.

[1712] A "notification prompting re-entry" is a message that requests the user to re-enter accurate data when an abnormal value is detected.

[1713] This invention is a system for analyzing a user's health and emotional data and providing feedback and meal suggestions. The system consists of means for receiving health data entered by the user, means for emotion recognition, generative artificial intelligence, means for sending feedback, means for providing meal suggestions, and means for placing orders in cooperation with a food delivery service.

[1714] System configuration and operation

[1715] 1. Input and reception of health data

[1716] Users input health data such as weight, body fat percentage, and blood pressure using their own devices (e.g., smartphones). The devices then send this data to the server.

[1717] 2. Emotion recognition

[1718] The server analyzes the user's voice and facial expressions using emotion recognition tools (e.g., EmotionEngine) and generates emotion data. This emotion data is also sent to the server.

[1719] 3. Data Analysis

[1720] The server sends the received health and emotional data to a generative artificial intelligence (e.g., HealthAIModel) for analysis. The generative AI then generates feedback based on the received data.

[1721] 4. Providing feedback

[1722] The generated feedback is sent to the user's device by the server. The user can review the feedback and revise their health management methods.

[1723] 5. Meal suggestions and food delivery

[1724] Generative artificial intelligence provides optimal meal suggestions based on health and emotional data. The suggested meal menus are linked to food delivery services via a server, allowing users to order directly.

[1725] Hardware and software

[1726] Hardware: Smartphones, servers

[1727] Software: EmotionEngine (emotion recognition method), HealthAIModel (generative artificial intelligence)

[1728] Specific example

[1729] For example, consider a user who inputs a weight of 70 kg, a body fat percentage of 22%, and a blood pressure of 130 / 85. This data is sent to the server, where a high-stress state is detected by emotion recognition. Based on this data, a generative artificial intelligence generates the following feedback and meal suggestions:

[1730] "User, your weight has increased over the past month. Your blood pressure is also elevated, and you appear to be experiencing increased stress. Focus on a balanced diet, moderate exercise, and incorporate relaxation into your routine. We suggest the following meal plan, which includes balanced meals and relaxing elements."

[1731] Example of a prompt

[1732] The user's health data is as follows:

[1733] Weight: 70kg, Body fat percentage: 22%, Blood pressure: 130 / 85

[1734] The emotional data indicates a high stress level.

[1735] Please suggest the optimal meal plan for the user.

[1736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1737] Step 1:

[1738] Users input health data (e.g., weight, body fat percentage, blood pressure) using a smartphone or other device. The entered data is sent from the device to the server. At this time, the system also checks the integrity and format of the input data.

[1739] Step 2:

[1740] The server checks the accuracy and consistency of the received health data before sending it to the generative artificial intelligence for analysis. If the data is inconsistent or contains abnormal values, a notification prompting re-entry is sent to the user's device. If the data is normal, the server proceeds to the next step.

[1741] Step 3:

[1742] Using emotion recognition tools (e.g., EmotionEngine), the server generates emotion data from the user's voice and facial expressions. This emotion data is also sent to a generative artificial intelligence. Input data includes the user's voice files and real-time video feeds.

[1743] Step 4:

[1744] The server sends normal health data and generated emotional data to a generative artificial intelligence (e.g., HealthAIModel). The generative AI analyzes the user's health and emotional state based on this data and generates comprehensive feedback. Specifically, judgments are made based on comparisons with past data and general health indicators.

[1745] Step 5:

[1746] The generated feedback is sent back to the server, which then sends it to the user's device. The user can then view the feedback through their device. This feedback includes an assessment of their health status and specific advice for improvement.

[1747] Step 6:

[1748] Furthermore, the generative artificial intelligence suggests meal menus tailored to the user based on health and emotional data. This information is provided to the user via a server. The suggested menus are optimized for each user's individual health and emotional state.

[1749] Step 7:

[1750] If a user reviews the suggested meal menu and wishes to place a delivery order, the server connects with a food delivery service. This connection allows users to easily order the suggested meal menu. In this case, the order data is sent to the food delivery service via an API.

[1751] Step 8:

[1752] The delivery service prepares meals based on the suggested menu and delivers them to the user. Through this entire process, users not only receive feedback for health management but also take concrete actions (ordering meals) based on that feedback.

[1753] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1754] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1755] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1756] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1757] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1758] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1759] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1760] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1761] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1762] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1763] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1764] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1765] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1766] 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.

[1767] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1768] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1769] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1770] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1771] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1772] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1773] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1774] The following is further disclosed regarding the embodiments described above.

[1775] (Claim 1)

[1776] A means of receiving health data entered by the user,

[1777] A means for transmitting received health data to a generative artificial intelligence for analysis,

[1778] A means of receiving feedback analyzed by a generative artificial intelligence,

[1779] A means of sending received feedback to the user,

[1780] A system that includes this.

[1781] (Claim 2)

[1782] A means of receiving mobile usage data entered by the user,

[1783] A means for transmitting received mobile usage data to a generative artificial intelligence for analysis,

[1784] A means of receiving feedback analyzed by a generative artificial intelligence,

[1785] A means of sending received feedback to the user,

[1786] The system according to claim 1, including the following:

[1787] (Claim 3)

[1788] Means for checking the accuracy and consistency of received health data and mobile usage data,

[1789] A means of sending a notification prompting re-entry if an abnormal value exists,

[1790] A means for transmitting normal data to a generative artificial intelligence for analysis,

[1791] A means of sending feedback analyzed by a generative artificial intelligence to the user,

[1792] The system according to claim 1, including the following:

[1793] "Example 1"

[1794] (Claim 1)

[1795] A means of receiving health data entered by the user,

[1796] A means of temporarily storing received health data in a computer system,

[1797] Means for transmitting stored data to a central control unit,

[1798] Means for verifying the accuracy and consistency of received health data,

[1799] A means of sending a notification prompting re-entry when an abnormal value is detected,

[1800] A means for transmitting normal data to a generative artificial intelligence for analysis,

[1801] A means of receiving feedback analyzed by a generative artificial intelligence,

[1802] A means of sending received feedback to the user,

[1803] A system that includes this.

[1804] (Claim 2)

[1805] A means of receiving mobile usage data entered by the user,

[1806] A means of temporarily storing received mobile usage data in a computer system,

[1807] Means for transmitting stored data to a central control unit,

[1808] A means for transmitting received mobile usage data to a generative artificial intelligence for analysis,

[1809] A means of receiving feedback analyzed by a generative artificial intelligence,

[1810] A means of sending received feedback to the user,

[1811] The system according to claim 1, including the following:

[1812] (Claim 3)

[1813] Means for checking the accuracy and consistency of received health data and mobile usage data,

[1814] A means of sending a notification prompting re-entry if an abnormal value exists,

[1815] A means for transmitting normal data to a generative artificial intelligence for analysis,

[1816] A means of sending feedback analyzed by a generative artificial intelligence to the user,

[1817] The system according to claim 1, including the following:

[1818] "Application Example 1"

[1819] (Claim 1)

[1820] A means for receiving health data and operational data entered by the user,

[1821] A means for transmitting received health data and operational data to a generative artificial intelligence for analysis,

[1822] A means of receiving feedback analyzed by a generative artificial intelligence,

[1823] A means for transmitting received feedback to the user and the robot,

[1824] A system that includes this.

[1825] (Claim 2)

[1826] A means of receiving mobile usage data entered by the user,

[1827] A means for transmitting received mobile usage data to a generative artificial intelligence for analysis,

[1828] A means of receiving feedback analyzed by a generative artificial intelligence,

[1829] A means of sending received feedback to the user,

[1830] The system according to claim 1, including the following:

[1831] (Claim 3)

[1832] A means to check the accuracy and consistency of received health data, mobile usage data, and operational data,

[1833] A means of sending a notification prompting re-entry if an abnormal value exists,

[1834] A means for transmitting normal data to a generative artificial intelligence for analysis,

[1835] A means for sending feedback analyzed by a generative artificial intelligence to the user and the robot,

[1836] The system according to claim 1, including the following:

[1837] "Example 2 of combining an emotion engine"

[1838] (Claim 1)

[1839] A means of receiving health data entered by the user,

[1840] A means of storing received health data and sending it to a server,

[1841] Means for checking the accuracy and consistency of received health data,

[1842] A means of sending a notification prompting re-entry if an abnormal value exists,

[1843] A means of transmitting normal health data to a generative artificial intelligence for analysis,

[1844] It includes an emotion engine that analyzes user emotions and means for generating emotion data,

[1845] A means of receiving feedback analyzed by a generative artificial intelligence,

[1846] A means of sending received feedback to the user,

[1847] A system that includes this.

[1848] (Claim 2)

[1849] A means of receiving mobile usage data entered by the user,

[1850] A means for transmitting received mobile usage data to a generative artificial intelligence for analysis,

[1851] A means of receiving feedback analyzed by a generative artificial intelligence,

[1852] A means of sending received feedback to the user,

[1853] The system according to claim 1, including the following:

[1854] (Claim 3)

[1855] A means for a generative artificial intelligence to analyze received health data, mobile usage data, and emotional data, and generate appropriate feedback.

[1856] A means of sending feedback analyzed by a generative artificial intelligence to the user,

[1857] The system according to claim 1, including the following:

[1858] "Application example 2 when combining with an emotional engine"

[1859] (Claim 1)

[1860] A means of receiving health data entered by the user,

[1861] A means for transmitting received health data to a generative artificial intelligence for analysis,

[1862] An emotion recognition method that generates emotion data from the user's voice and facial expressions,

[1863] A means for transmitting the generated emotional data to a generative artificial intelligence for analysis,

[1864] A means of receiving feedback analyzed by a generative artificial intelligence,

[1865] A means of sending received feedback to the user,

[1866] A method for providing dietary suggestions by analyzing health data and emotional data,

[1867] One method is to order the suggested meal menu in conjunction with a food delivery service.

[1868] A system that includes this.

[1869] (Claim 2)

[1870] A means of receiving mobile usage data entered by the user,

[1871] A means for transmitting received mobile usage data to a generative artificial intelligence for analysis,

[1872] A means of receiving feedback analyzed by a generative artificial intelligence,

[1873] A means of sending received feedback to the user,

[1874] The system according to claim 1, including the following:

[1875] (Claim 3)

[1876] Means for checking the accuracy and consistency of received health data and mobile usage data,

[1877] A means of sending a notification prompting re-entry if an abnormal value exists,

[1878] A means for transmitting normal data to a generative artificial intelligence for analysis,

[1879] A means of sending feedback analyzed by a generative artificial intelligence to the user,

[1880] The system according to claim 1, including the following: [Explanation of Symbols]

[1881] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving health data entered by the user, A means for transmitting received health data to a generative artificial intelligence for analysis, A means of receiving feedback analyzed by a generative artificial intelligence, A means of sending received feedback to the user, A system that includes this.

2. A means of receiving mobile usage data entered by the user, A means for transmitting received mobile usage data to a generative artificial intelligence for analysis, A means of receiving feedback analyzed by a generative artificial intelligence, A means of sending received feedback to the user, The system according to claim 1, including the following:

3. Means for checking the accuracy and consistency of received health data and mobile usage data, A means of sending a notification prompting re-entry if an abnormal value exists, A means for transmitting normal data to a generative artificial intelligence for analysis, A means of sending feedback analyzed by a generative artificial intelligence to the user, The system according to claim 1, including the following:

Images