System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting daily activity information by a user; means for transmitting the input activity information to a server; means for analyzing the activity information received by the server; means for generating advice using a generation AI based on the analysis result; means for transmitting the generated advice to a user device; and means for displaying the advice received by the device to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, the senior population has increased, creating a demand for personalized support tailored to each individual's health condition and lifestyle. Current systems are unable to adequately address the diverse needs of seniors, and general health advice and lifestyle improvement suggestions are often applied to many individuals. Therefore, there is a need for a means to provide specific, individualized advice to improve the quality of life of each senior and appropriately manage their health. [Means for solving the problem]

[0005] The present invention provides a system including a means for a user to input daily activity data, a means for transmitting the data to a server, a means for the server to analyze the received data, a means for generating personalized advice based on the analysis results using a generation AI, a means for transmitting the generated advice to the user's terminal, and a means for displaying the advice received by the terminal to the user. Furthermore, the system includes a means for accumulating the analysis results over the long term, monitoring trends, and a means for evaluating the user's health condition and lifestyle patterns, thereby enabling comprehensive health management for seniors and improving their quality of life.

[0006] A "user" is a person who uses the system to input daily activity data and receive personalized advice.

[0007] "Activity data" refers to data including the amount of food, exercise, work, time spent on hobbies, sleep, and other activities that a user engages in in their daily life.

[0008] The term "means" refers to a method or device for realizing a specific function in a system.

[0009] The "server" is a computer that analyzes data received from the user's device, generates advice using a generation AI, and sends it to the user's device.

[0010] "Generative AI" is artificial intelligence that analyzes incoming data and generates individual advice based on the results.

[0011] The "terminal" is a device on which the user inputs daily activity data and displays advice received from the server. For example, this applies to a smartphone or tablet.

[0012] "Advice" refers to instructions or suggestions for individual lifestyle improvements and health management that are created by the server using generative AI based on the analysis results and presented to the user.

[0013] "Analysis" refers to the process by which the server processes the received activity data and evaluates the user's lifestyle patterns and health status.

[0014] "Trends" refers to long-term trends and changes in a user's lifestyle patterns and health status derived from data collected over a long period of time. [Brief explanation of the drawings]

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

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

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

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

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

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

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

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

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

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

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0036] The system of this invention allows users to input their daily activity data, which is then analyzed by a server that uses AI to generate and provide personalized advice.

[0037] 1. User data entry

[0038] The user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button. The entered data is saved in real time and sent to the server when the Send button is pressed.

[0039] 2. Sending data from the device to the server

[0040] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, a notification of data transmission completion is displayed to the user.

[0041] 3. Data reception and analysis by the server

[0042] The server receives the activity data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on the timing and content of meals, the frequency of exercise, sleep patterns, etc.

[0043] 4. Generating Advice

[0044] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server may generate specific advice such as "Add 30 minutes of walking every day." This advice is then converted back into an appropriate format and a request is generated to send it to the device.

[0045] 5. Sending and displaying advice to the device

[0046] The advice data generated by the server is sent to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0047] Specific examples

[0048] Let's say a user enters one week's worth of lifestyle data into an app and sends it to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0049] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] A user launches an application on their smartphone or tablet.

[0053] Step 2:

[0054] The terminal confirms the user's login and displays the diary entry screen.

[0055] Step 3:

[0056] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[0057] Step 4:

[0058] The device saves the entered data in real time and enables the "Send" button once the entry is complete.

[0059] Step 5:

[0060] The user presses the "Send" button.

[0061] Step 6:

[0062] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[0063] Step 7:

[0064] The device sends a request to the server over the Internet.

[0065] Step 8:

[0066] The server receives the activity data sent from the terminal.

[0067] Step 9:

[0068] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[0069] Step 10:

[0070] The server runs analytical algorithms to assess the user's health and lifestyle patterns.

[0071] Step 11:

[0072] The server uses a generative AI model based on the analysis results to generate individual advice.

[0073] Step 12:

[0074] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[0075] Step 13:

[0076] The server sends a request via the Internet to send advice data to the terminal.

[0077] Step 14:

[0078] The terminal receives the advice data transmitted from the server.

[0079] Step 15:

[0080] The terminal generates a notification or screen display for the user of the decoded advice.

[0081] Step 16:

[0082] The user checks the advice displayed on the device and implements it to improve their lifestyle habits.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] In conventional health management systems, users' daily activity data is typically recorded manually, and health managers analyze it and provide advice. However, this method suffers from problems such as inconvenient data entry, delayed analysis, and generalized advice. In particular, it is difficult to provide personalized advice tailored to each user's specific needs, making it difficult to maintain user motivation. Furthermore, there is a lack of means to monitor long-term health trends.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes: a means for a user to input daily activity data; a means for saving the input activity data in real time on the terminal, converting it into an appropriate format, and transmitting it to the server; a means for receiving, decoding, and analyzing the activity data transmitted from the terminal; a means for generating personalized advice using a generative AI model based on the analysis results; and a means for transmitting the generated advice to the user's terminal and notifying or displaying the received advice to the user. This allows the user to easily input daily activity data, quickly and accurately analyze the data, and provide personalized advice. It also makes it possible to accumulate analysis results over the long term and monitor the user's health trends.

[0088] "User" refers to the individual using the system or on whose behalf they enter data and receive advice.

[0089] "Activity data" refers to information about the user's daily activities, such as diet, exercise, work, hobbies, and sleep.

[0090] "Device" refers to a smartphone, tablet, or other portable electronic device used by a user to enter activity data.

[0091] "Server" refers to a remote computer system that receives and analyzes activity data sent from a user's terminal, and generates and sends advice.

[0092] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a lightweight data exchange format.

[0093] "Generative AI model" refers to a machine learning model that uses artificial intelligence technology to generate personalized advice based on user activity data.

[0094] "Analysis algorithm" refers to a series of calculation procedures used to analyze a user's activity data and evaluate their health status and lifestyle patterns.

[0095] "Advice" refers to specific suggestions or recommendations that the server outputs based on the user's activity data using a generative AI model.

[0096] "Notification" refers to the method used by the device to inform the user of advice or other important information.

[0097] "Long-term storage" refers to storing user activity data and analysis results for a certain period of time or longer and making them continuously available.

[0098] "Health trends" refers to changes and trends in health status and lifestyle patterns that can be seen from long-term accumulated user activity data and analysis results.

[0099] The system of this invention works by having users input their daily activity data, which is then analyzed by a server and used to generate and provide personalized advice using a generative AI model.

[0100] First, the user installs a dedicated application on a device such as a smartphone or tablet. This application can be downloaded from the Apple App Store or the GOOGLE PLAY (registered trademark) Store. When the application is launched, a diary-style input screen is displayed. On this screen, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button, and this data is saved in real time and sent to the server in JSON format.

[0101] Next, the device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the device displays a notification to the user that the data has been transmitted.

[0102] The server receives the activity data sent from the device and decodes it according to JSON format. The decoded data is broken down into individual items and passed to the server's analysis module. The server's analysis module runs an algorithm to analyze the received data and evaluate the user's health status and lifestyle patterns. This analysis is based on, for example, the timing and content of meals, the frequency of exercise, and sleep patterns. The analysis module uses algorithms implemented in Python.

[0103] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking every day." This generated advice is then converted back into an appropriate format (such as JSON) and a request is generated to send to the device.

[0104] Finally, the advice data generated by the server is sent back to the device via the Internet, where it is decoded and a notification or screen display is generated for the user, allowing the user to receive personalized advice at the appropriate time.

[0105] As a concrete example, consider the case where a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generative AI model generates advice such as "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0106] An example of a prompt sentence to be input into the generative AI model is, "After analyzing the user's exercise data, we found that the average exercise time per week is 30 minutes short. Please generate specific advice."

[0107] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] The user installs a dedicated application on their smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. Once this is complete, the user presses the "Submit" button. The input is the activity data entered by the user. The output is that the data is saved in real time.

[0111] Step 2:

[0112] The device converts the entered activity data into JSON format. Specifically, a module in the application compiles the data from the user's input fields into a JSON object, which prepares the format for data transmission. The input is the user's activity data. The output is the data converted into JSON format.

[0113] Step 3:

[0114] The terminal generates a request to send data converted to JSON format to the server. The request uses the HTTP protocol and the data is sent to the server over the Internet. As input, there is data in JSON format. As output, an HTTP request is generated and sent to the server.

[0115] Step 4:

[0116] The server receives the HTTP request sent from the device and extracts the included JSON data. A module in the server decodes the JSON data and breaks it down into individual items (meal details, exercise time, work time, etc.). The input is the HTTP request received by the server. The output is the decoded data for each item.

[0117] Step 5:

[0118] The server runs algorithms to analyze the decoded data. The analysis module evaluates the user's health status and lifestyle patterns. For example, algorithms implemented in Python analyze the timing and content of meals, exercise frequency, and sleep patterns. The input is the decoded data for each item. The output is the analysis results.

[0119] Step 6:

[0120] Based on the analysis results, the server uses a generative AI model to generate individual advice. Specifically, the analysis data is input to the generative AI model as a prompt sentence, and the optimal advice is output. The inputs are the analysis results and the prompt sentence. The output is the generated advice.

[0121] Step 7:

[0122] The generated advice is converted back to JSON format and a request is generated to send to the device. The server converts the advice content into the appropriate format and creates an HTTP request. The input is the generated advice. The output is an HTTP request to send to the device.

[0123] Step 8:

[0124] The terminal receives the HTTP request received from the server and decodes the included advice data, thereby generating a notification for the user. The input is the HTTP request received from the server, and the output is the decoded advice data.

[0125] Step 9:

[0126] The device provides the decoded advice content to the user as a notification or a screen display. For example, a push notification function is used to notify the user of specific advice. The input is the decoded advice data. The output is the advice to be notified to the user.

[0127] (Application example 1)

[0128] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0129] In modern society, people face the challenge of understanding their own health status and lifestyle patterns and receiving appropriate advice in their busy daily lives. In particular, providing personalized health advice and exercise plans in physical stores places a heavy burden on staff and is inefficient. Furthermore, there is a lack of ways for users to instantly receive specific, personalized advice based on their own activity data.

[0130] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0131] In this invention, the server includes: a means for a user to input daily activity data; a means for transmitting the input activity data to the server; a means for analyzing the activity data received by the server; a means for generating advice using a generation AI based on the analysis results; a means for transmitting the generated advice to the user's terminal; a means for displaying the advice received by the terminal to the user; and a means for providing health and exercise advice based on the user's activity data at a physical store. This allows users to instantly receive personalized advice based on the analysis results from the server simply by inputting specific data about their daily lives. This also reduces the burden on staff at physical stores and allows for efficient provision of health advice.

[0132] A "user" is an individual who utilizes the system to input their daily activity data and receive personalized advice.

[0133] "Activity data" refers to information about the user's daily life, such as diet, exercise, work, hobbies, and sleep.

[0134] The "server" is a central processing unit that receives and analyzes activity data sent by the user, generates advice using a generation AI, and sends it back to the user.

[0135] "Analysis" refers to the process by which the server evaluates the activity data it receives to reveal the user's health status and lifestyle patterns.

[0136] "Generative AI" refers to an algorithm or system that uses artificial intelligence technology to automatically generate personalized advice based on analysis results.

[0137] "Advice" refers to specific instructions or recommendations provided by the server using generated AI based on the user's activity data.

[0138] A "terminal" is a device (e.g., a smartphone, tablet, etc.) that allows a user to input activity data and receive and display advice sent from the server.

[0139] A "brick and mortar" is a physical location, such as a fitness club or health food store, where users can visit in person to receive health and exercise advice.

[0140] The system of this invention allows users to input their daily activity data, and the server analyzes the data and uses AI to provide personalized advice. Specifically, it works as follows.

[0141] First, the user uses a device such as a smartphone or tablet to input their daily activity data, including what they eat, how much time they spend exercising, working, enjoying their hobbies, and sleeping. Once the data is complete, they press the "send" button. This input data is saved in real time and sent to the server when the send button is pressed.

[0142] The server receives the activity data sent by the user. This data is sent in JSON format, and the server decodes it and breaks it down into individual components. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on patterns such as diet, exercise, and sleep.

[0143] Based on the analysis results, the server uses the generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking each day." This generated advice is then converted back into an appropriate format and sent to the user's device. The advice received by the device is decoded and displayed as a notification or screen display for the user.

[0144] This system is also designed to be used in physical stores, such as fitness clubs and health food stores, where staff can provide personalized health and exercise advice based on the data entered by the user. This allows users to receive specific advice based on their own health status and lifestyle patterns, thereby improving their quality of life.

[0145] The hardware used includes smartphones and tablets, which require an internet connection to send and receive data, and the software used includes Python and the Requests library, which facilitates data transmission, reception, analysis, and display.

[0146] As a concrete example, let's say a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0147] Example prompt sentence:

[0148] "Generate health advice based on user activity data in the following format:

[0149] Diet: Increase your intake of ○○

[0150] Exercise: Add XX minutes of exercise XX times per week

[0151] Rest: Recommended sleep time is x hours

[0152] User data: {'food': 'Salad, Fish', 'exercise': 'Running 30 mins', 'work': '8 hours', 'hobby': 'Reading 1 hour', 'sleep': '7 hours'}

[0153] This system allows users to easily receive personalized health advice by simply entering data about their daily lives, enabling them to effectively manage their health.

[0154] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0155] Step 1:

[0156] The user inputs daily activity data.

[0157] Specific operation: The user launches the dedicated app on their smartphone or tablet and enters the details of their meals, exercise time, work time, hobby time, and sleep time into a diary-style input screen. Once the input is complete, they press the "Send" button.

[0158] Input: Daily activity data (meals, exercise, work, hobbies, sleep)

[0159] Output: Activity data converted to JSON format

[0160] Step 2:

[0161] The terminal transmits the input activity data to the server.

[0162] Specific operation: The device converts the input data into JSON format and sends it to the server via the Internet. When the transmission is complete, the device displays a notification to the user that the data has been sent.

[0163] Input: Activity data in JSON format

[0164] Output: Data transmission request, transmission completion notification

[0165] Step 3:

[0166] The server receives the transmitted activity data.

[0167] Specific operation: The server receives the data sent from the device. The received data is decoded from JSON format and broken down into each item (food, exercise, work, hobbies, sleep).

[0168] Input: Data transmission request from the terminal

[0169] Output: Decoded activity data

[0170] Step 4:

[0171] The server analyzes the received data.

[0172] How it works: The server runs an analysis algorithm to assess the user's health and lifestyle based on their activity data, including what they eat, how often they exercise, and their sleep patterns.

[0173] Input: Decoded activity data

[0174] Output: Analysis results (evaluation of health status and lifestyle patterns)

[0175] Step 5:

[0176] The server generates advice using a generative AI based on the analysis results.

[0177] Specific operation: The server inputs the analysis results into the generative AI model and generates personalized health advice. For example, the generative AI may generate specific advice such as "Add 30 minutes of walking every day."

[0178] Input: Analysis results

[0179] Output: Generated advice

[0180] Step 6:

[0181] The server transmits the generated advice to the user's terminal.

[0182] Specific operation: The server converts the generated advice back into JSON format and sends it to the user's device.

[0183] Input: Generated advice

[0184] Output: Advice data in JSON format, data submission request

[0185] Step 7:

[0186] The terminal displays the received advice to the user.

[0187] Specific actions: The device decodes the received advice data and presents the advice to the user as a notification or on-screen display. The user can then confirm the advice and take specific action.

[0188] Input: Advice data in JSON format

[0189] Output: User notification or displayed advice

[0190] Step 8:

[0191] In physical stores, staff will provide support based on users' activity data.

[0192] Specific operation: When a user visits a physical store, staff will refer to the user's activity data through the system and suggest appropriate training plans and health foods.

[0193] Input: User activity data and analysis results

[0194] Output: Specific support and advice from store staff

[0195] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0196] The system of this invention allows users to input their daily activity data, which is then analyzed by a server, which then uses a generation AI and emotion engine to generate and provide personalized advice.

[0197] 1. User data entry

[0198] Users install a dedicated application on their smartphone, tablet, or other device. When the application is launched, a diary-style input screen appears. Here, users enter the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once input is complete, they press the "Send" button. The input data is saved in real time and sent to the server when the "Send" button is pressed. The emotion engine also uses the input data, behavioral history, and even voice and facial expression recognition technology to infer and record the user's emotions.

[0199] 2. Sending data from the device to the server

[0200] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. When the transmission is complete, a notification of the completion of data transmission is displayed to the user.

[0201] 3. Data reception and analysis by the server

[0202] The server receives the activity and emotion data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health status, lifestyle patterns, and even emotional tendencies.

[0203] 4. Generating Advice

[0204] Based on the analysis results, the server uses a generative AI model to generate individualized advice. Taking the user's emotional state into account also results in more appropriate and personalized advice. For example, if a user is not getting enough exercise and has recently experienced increased stress, the server may generate specific advice such as, "Try adding 30 minutes of walking each day. Also, try to set aside time to relax." This generated advice is then converted back into an appropriate format and a request is generated to send it to the device.

[0205] 5. Sending and displaying advice to the device

[0206] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0207] Specific examples

[0208] Suppose a user enters one week's lifestyle and emotional data into the app and sends the data to the server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generation AI generates comprehensive advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review it and adjust their lifestyle.

[0209] In this way, users can receive specific daily advice based on their health status, lifestyle patterns, and emotional tendencies, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is possible.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] A user launches an application on their smartphone or tablet.

[0213] Step 2:

[0214] The terminal confirms the user's login and displays the diary entry screen.

[0215] Step 3:

[0216] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[0217] Step 4:

[0218] The emotion engine uses voice and facial expression recognition technology to infer the user's current emotions, along with emotion analysis based on the user's input and behavioral history.

[0219] Step 5:

[0220] The device stores activity and emotion data in real time and enables the "Send" button once input is complete.

[0221] Step 6:

[0222] The user presses the "Send" button.

[0223] Step 7:

[0224] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[0225] Step 8:

[0226] The device sends a request to the server over the Internet.

[0227] Step 9:

[0228] The server receives the activity data and emotion data transmitted from the terminal.

[0229] Step 10:

[0230] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[0231] Step 11:

[0232] The server runs analytical algorithms to assess the user's health, lifestyle patterns, and emotional tendencies.

[0233] Step 12:

[0234] The server uses a generative AI model based on the analysis results to generate personalized advice, taking into account the user's emotional state.

[0235] Step 13:

[0236] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[0237] Step 14:

[0238] The server sends a request via the Internet to send advice data to the terminal.

[0239] Step 15:

[0240] The terminal receives the advice data transmitted from the server.

[0241] Step 16:

[0242] The terminal decodes the received advice and generates a notification or screen display for the user.

[0243] Step 17:

[0244] The user checks the advice displayed on the device and follows it to improve their lifestyle habits.

[0245] Example 2

[0246] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0247] In modern society, there is a demand for continuous evaluation of individuals' health status and lifestyle patterns and provision of appropriate feedback. However, conventional systems have difficulty providing personalized advice that takes into account the user's emotional state, and they also lack the ability to monitor trends based on long-term data analysis, resulting in problems that prevent sufficient improvement in the user's quality of life.

[0248] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0249] In this invention, the server includes: means for a user to input daily activity data; means for converting the input activity data and emotional data into an appropriate format and transmitting the converted data to the server; means for the server to analyze the received activity data and emotional data and evaluate the user's health condition, lifestyle patterns, and emotional tendencies; means for generating advice using a generation AI based on the analysis results and emotional data; means for converting the generated advice into an appropriate format and transmitting the advice to the user's device; and means for the device to notify or display the received advice to the user. This enables the provision of personalized advice to each user that takes into account their emotional state, and enables long-term trend monitoring of health conditions and lifestyle patterns.

[0250] "Activity data" refers to information such as dietary content, exercise time, work time, hobby time, and sleep time that is recorded in the user's daily life.

[0251] "Emotional data" refers to data that represents the user's emotional state, and includes information inferred or recorded from voice and facial expression recognition technology and behavioral history.

[0252] "Dedicated application" refers to software that users install on their smartphones or tablets to input activity data and emotional data.

[0253] "Server" refers to a computer system that receives and analyzes activity data and emotion data sent from a device, and generates and sends advice to the user using a generative AI model.

[0254] "Analysis algorithm" refers to the method or calculation procedure used by the server to analyze the activity data and emotional data received and evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[0255] "Generative AI model" refers to the artificial intelligence model used by the server to generate personalized advice for users based on the analysis results.

[0256] A "prompt sentence" is a sentence input into a generative AI model, and refers to an instruction sentence that guides the content of the advice generated based on the analysis results.

[0257] "Terminal" refers to an electronic device, such as a smartphone or tablet, used by a user to input data and display generated advice.

[0258] The "JSON format" is a lightweight data exchange format for expressing data structures, and is used when sending and receiving data between a terminal and a server.

[0259] "Notification" refers to the display of a message to convey important information, such as advice, generated by the system to the user.

[0260] The system of this invention works by having users input their daily activity data and emotional data, which is then analyzed by a server, which then uses a generative AI model and emotional engine to generate and provide personalized advice.

[0261] First, the user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. After completing the input, the user presses the "Send" button. The emotion engine then uses the input data, behavioral history, and voice and facial expression recognition technology to infer and record the user's emotions.

[0262] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the user is notified that the data has been transmitted.

[0263] The server receives the activity and emotion data sent from the device, decodes it according to a specific format, breaks it down into individual items, and runs a specified analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[0264] Based on the analysis results, the server uses a generative AI model to generate individualized advice. This process also takes into account the user's emotional data, resulting in more personalized advice. For example, if a user is not getting enough exercise and is experiencing increased stress, the generative AI model might generate advice such as, "Add 30 minutes of walking each day. Also, try to set aside time to relax." This advice is then converted back into an appropriate format (e.g., JSON format) and a request is generated to send it to the device.

[0265] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0266] Specific examples

[0267] Suppose a user enters one week's lifestyle and emotional data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generative AI model generates advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review the advice and adjust their lifestyle.

[0268] Prompt Sentence Examples

[0269] An example of an input prompt for the generative AI model would be, "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice."

[0270] The system provides personalized advice to each user that takes into account their emotional state and enables long-term trend monitoring of health and lifestyle patterns.

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

[0272] Step 1:

[0273] The user installs a dedicated application on a device such as a smartphone or tablet. When the app is launched, a diary-style input screen appears. The user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. This data constitutes "input." After completing the input, the user presses the "send" button. The emotion engine uses the input data, behavioral history, voice, and facial expressions to infer and record the user's emotions. This operation generates activity data and emotion data, which constitutes "output."

[0274] Step 2:

[0275] The device converts the activity and emotion data entered by the user into an appropriate format (e.g., JSON format). During this conversion process, the data is organized and formatted so that it can be interpreted by the server. This is part of data processing. The converted data becomes the "input," and then a data transmission request is sent to the server via the internet. This request becomes the "output." Once transmission is complete, a notification that the data has been sent is displayed to the user.

[0276] Step 3:

[0277] The server receives activity data and emotion data sent from the device. The received data becomes the "input." When the server receives this data, it first decodes it in JSON format and breaks it down into individual items. The decoded data becomes the "output." Next, it runs an analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies. The results of this analysis also become the "output."

[0278] Step 4:

[0279] Based on the analysis results, the server uses a generative AI model to generate individualized advice. The analysis results and emotional data become the "input." The server inputs a prompt (e.g., "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice.") into the generative AI model. This prompt becomes the "output." The generative AI model generates individualized advice based on this prompt. The generated advice becomes the "output." This advice is again converted into an appropriate format (e.g., JSON format), and a request is generated to send to the device.

[0280] Step 5:

[0281] The server sends the generated advice data to the terminal via the Internet. This advice data becomes the "input." The terminal decodes the received advice data and generates a notification or screen display for the user. The decoded advice becomes the "output." The user can receive individual advice at the appropriate time. This notification or display serves as a concrete guide for the user to take action.

[0282] (Application example 2)

[0283] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0284] While conventional systems can provide personalized advice based on a user's activity and emotional data, they have the problem of not directly linking this advice to purchasing activities and behavior in physical stores. Furthermore, users have difficulty selecting products and services that reflect their own health status and lifestyle patterns. This results in problems such as insufficient achievement of behavioral change and improvement of the user's quality of life.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0286] In this invention, the server includes means for a user to input daily activity data, means for transmitting the input activity data to the server, means for analyzing the activity data received by the server, means for generating advice using a generation AI based on the analysis results, means for transmitting the generated advice to the user's terminal, means for displaying the advice received by the terminal to the user, and means for advising the user on what to purchase and what to do in the store based on the user's activity data and emotion data. This enables the user to be effectively guided in their actions and purchases in a physical store based on their own activity data and emotion data.

[0287] "User" refers to an individual who uses this system to input activity data and emotion data and receives advice from the server.

[0288] "Activity data" refers to information about a user's daily diet, exercise, work, hobbies, and sleep.

[0289] "Emotional data" is data that indicates the user's emotional state and is estimated and recorded using voice and facial expression recognition technology.

[0290] A "dedicated application" refers to software that users install on their devices, such as smartphones, to input activity data and emotional data and communicate with the server.

[0291] "Server" refers to a computer system that receives activity data and emotion data sent by users, analyzes them, and generates and provides advice using generative AI.

[0292] "Generative AI" refers to an artificial intelligence model that analyzes and generates personalized advice based on the data it receives.

[0293] "Terminal" refers to a device (e.g., a smartphone or tablet) on which a user installs a dedicated application and receives and displays advice from a server.

[0294] "Means of advising on purchases and actions" refers to a function that suggests recommended products and actions in physical stores based on the user's activity data and emotional data.

[0295] "In-store navigation" refers to a feature that helps users find the right products and services in a physical store.

[0296] In the system for implementing this invention, a user inputs activity data and emotion data, which is then analyzed by a server, and individualized advice is generated and provided using a generation AI and emotion engine. This will be explained in detail below.

[0297] System Configuration

[0298] This system consists of a user device (such as a smartphone) and a server. Users install a dedicated application on their device and input their daily activity and emotion data. The server receives the data sent by the user, analyzes it, and generates appropriate advice.

[0299] Data entry and submission

[0300] Users enter information about their daily diet, exercise, work, hobbies, and sleep through a dedicated application. Emotional data is also inferred and recorded using voice and facial expression recognition technology (e.g., technology using a smartphone's camera and microphone). This data is converted into JSON format and sent to the server.

[0301] Data analysis and advice generation

[0302] The server receives the transmitted data and runs an analysis algorithm. The analysis algorithm evaluates the user's health condition and lifestyle patterns. It then uses a generative AI model to generate personalized advice. The generative AI model generates optimal advice based on the user's activity data and emotional data. For example, if a lack of exercise and emotional stress are detected, the generated advice would be, "Add 30 minutes of walking every day. Also, try to make time to relax."

[0303] Sending and viewing advice

[0304] The generated advice is sent from the server to the user's device, where it is decoded and presented to the user via notification or on-screen display, allowing the user to receive the most appropriate advice at the right time.

[0305] Application in physical stores

[0306] Furthermore, this system can also be applied to navigating purchases and activities in physical stores. When a user brings the dedicated application with them and visits a physical store, the in-store navigation function is activated. Based on the user's activity and emotional data, the system navigates to recommended ingredients, exercise equipment, relaxation products, and more within the store. It also guides users to special activities (free classes and demonstrations) in specific sections of the store (health foods, fitness, relaxation). This allows users to make more effective purchases in physical stores.

[0307] Examples of prompt statements

[0308] A specific example of a prompt is as follows:

[0309] "Based on the user's recent data, generate advice like this:

[0310] Today's exercise time: 30 minutes

[0311] Today's meal: Bread, salad

[0312] Today's work hours: 8 hours

[0313] Hobby time today: 2 hours

[0314] Sleep time today: 7 hours

[0315] Today's emotion: happy

[0316] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[0317] In this way, users can receive specific advice based on their health status and emotions in a physical store, improving their quality of life.

[0318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0319] Step 1:

[0320] Users install the dedicated application on their smartphones and launch it. Using a diary-style input screen, users enter data on their daily activities (food, exercise, work, hobbies, sleep) and emotional data. The entered data is temporarily stored on the device.

[0321] Input: User activity data and emotion data

[0322] Output: Input data stored in the device

[0323] Step 2:

[0324] When the user presses the "Send" button, the device converts the input activity and emotion data into JSON format and generates an HTTP request, which is then sent to the server via the Internet.

[0325] Input: Input data stored in the device

[0326] Output: JSON formatted data sent to the server

[0327] Step 3:

[0328] The server receives and decodes the JSON-formatted data sent from the device. The received data is then stored in a database. Data analysis algorithms are then run to analyze the data to evaluate the user's health status and lifestyle patterns.

[0329] Input: JSON format data sent to the server

[0330] Output: Analyzed data on the user's health status and lifestyle patterns

[0331] Step 4:

[0332] The server generates individual advice using a generative AI model based on the analysis results. A prompt sentence is generated based on the analyzed data and input to the generative AI model. The generative AI model generates optimal advice, converts it into JSON format, and saves it.

[0333] Input: Analyzed data on the user's health status and lifestyle patterns, and prompts for the generative AI model

[0334] Output: Generated individual advice

[0335] Step 5:

[0336] The server sends the generated advice to the user's device. The advice data is sent in JSON format, and the device receives it.

[0337] Input: JSON format data of the generated individual advice

[0338] Output: Advice data sent to the terminal

[0339] Step 6:

[0340] The device decodes the received advice data and displays it to the user. The user can view the advice provided through the application. If necessary, the navigation function in the physical store is activated, and the user can receive advice on what to buy and what to do in the store.

[0341] Input: Advice data sent to the terminal

[0342] Output: The individual advice displayed to the user

[0343] As an example of how this works, the following prompt sentence is input to the generative AI model:

[0344] "Based on the user's recent data, generate advice like this:

[0345] Today's exercise time: 30 minutes

[0346] Today's meal: Bread, salad

[0347] Today's work hours: 8 hours

[0348] Hobby time today: 2 hours

[0349] Sleep time today: 7 hours

[0350] Today's emotion: happy

[0351] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[0352] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0353] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0354] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0355] [Second embodiment]

[0356] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0357] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0358] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0359] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0360] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0361] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0362] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0363] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0364] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0365] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0366] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0367] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0368] The system of this invention allows users to input their daily activity data, which is then analyzed by a server that uses AI to generate and provide personalized advice.

[0369] 1. User data entry

[0370] The user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button. The entered data is saved in real time and sent to the server when the Send button is pressed.

[0371] 2. Sending data from the device to the server

[0372] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, a notification of data transmission completion is displayed to the user.

[0373] 3. Data reception and analysis by the server

[0374] The server receives the activity data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on the timing and content of meals, the frequency of exercise, sleep patterns, etc.

[0375] 4. Generating Advice

[0376] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server may generate specific advice such as "Add 30 minutes of walking every day." This advice is then converted back into an appropriate format and a request is generated to send it to the device.

[0377] 5. Sending and displaying advice to the device

[0378] The advice data generated by the server is sent to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0379] Specific examples

[0380] Let's say a user enters one week's worth of lifestyle data into an app and sends it to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0381] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[0382] The processing flow will be explained below.

[0383] Step 1:

[0384] A user launches an application on their smartphone or tablet.

[0385] Step 2:

[0386] The terminal confirms the user's login and displays the diary entry screen.

[0387] Step 3:

[0388] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[0389] Step 4:

[0390] The device saves the entered data in real time and enables the "Send" button once the entry is complete.

[0391] Step 5:

[0392] The user presses the "Send" button.

[0393] Step 6:

[0394] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[0395] Step 7:

[0396] The device sends a request to the server over the Internet.

[0397] Step 8:

[0398] The server receives the activity data sent from the terminal.

[0399] Step 9:

[0400] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[0401] Step 10:

[0402] The server runs analytical algorithms to assess the user's health and lifestyle patterns.

[0403] Step 11:

[0404] The server uses a generative AI model based on the analysis results to generate individual advice.

[0405] Step 12:

[0406] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[0407] Step 13:

[0408] The server sends a request via the Internet to send advice data to the terminal.

[0409] Step 14:

[0410] The terminal receives the advice data transmitted from the server.

[0411] Step 15:

[0412] The terminal generates a notification or screen display for the user of the decoded advice.

[0413] Step 16:

[0414] The user checks the advice displayed on the device and implements it to improve their lifestyle habits.

[0415] Example 1

[0416] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0417] In conventional health management systems, users' daily activity data is typically recorded manually, and health managers analyze it and provide advice. However, this method suffers from problems such as inconvenient data entry, delayed analysis, and generalized advice. In particular, it is difficult to provide personalized advice tailored to each user's specific needs, making it difficult to maintain user motivation. Furthermore, there is a lack of means to monitor long-term health trends.

[0418] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0419] In this invention, the server includes: a means for a user to input daily activity data; a means for saving the input activity data in real time on the terminal, converting it into an appropriate format, and transmitting it to the server; a means for receiving, decoding, and analyzing the activity data transmitted from the terminal; a means for generating personalized advice using a generative AI model based on the analysis results; and a means for transmitting the generated advice to the user's terminal and notifying or displaying the received advice to the user. This allows the user to easily input daily activity data, quickly and accurately analyze the data, and provide personalized advice. It also makes it possible to accumulate analysis results over the long term and monitor the user's health trends.

[0420] "User" refers to the individual using the system or on whose behalf they enter data and receive advice.

[0421] "Activity data" refers to information about the user's daily activities, such as diet, exercise, work, hobbies, and sleep.

[0422] "Device" refers to a smartphone, tablet, or other portable electronic device used by a user to enter activity data.

[0423] "Server" refers to a remote computer system that receives and analyzes activity data sent from a user's terminal, and generates and sends advice.

[0424] "JSON format" stands for JavaScript Object Notation and refers to a lightweight data exchange format.

[0425] "Generative AI model" refers to a machine learning model that uses artificial intelligence technology to generate personalized advice based on user activity data.

[0426] "Analysis algorithm" refers to a series of calculation procedures used to analyze a user's activity data and evaluate their health status and lifestyle patterns.

[0427] "Advice" refers to specific suggestions or recommendations that the server outputs based on the user's activity data using a generative AI model.

[0428] "Notification" refers to the method used by the device to inform the user of advice or other important information.

[0429] "Long-term storage" refers to storing user activity data and analysis results for a certain period of time or longer and making them continuously available.

[0430] "Health trends" refers to changes and trends in health status and lifestyle patterns that can be seen from long-term accumulated user activity data and analysis results.

[0431] The system of this invention works by having users input their daily activity data, which is then analyzed by a server and used to generate and provide personalized advice using a generative AI model.

[0432] First, the user installs a dedicated application on a device such as a smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen is displayed. On this screen, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button, and this data is saved in real time and sent to the server in JSON format.

[0433] Next, the device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the device displays a notification to the user that the data has been transmitted.

[0434] The server receives the activity data sent from the device and decodes it according to JSON format. The decoded data is broken down into individual items and passed to the server's analysis module. The server's analysis module runs an algorithm to analyze the received data and evaluate the user's health status and lifestyle patterns. This analysis is based on, for example, the timing and content of meals, the frequency of exercise, and sleep patterns. The analysis module uses algorithms implemented in Python.

[0435] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking every day." This generated advice is then converted back into an appropriate format (such as JSON) and a request is generated to send to the device.

[0436] Finally, the advice data generated by the server is sent back to the device via the Internet, where it is decoded and a notification or screen display is generated for the user, allowing the user to receive personalized advice at the appropriate time.

[0437] As a concrete example, consider the case where a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generative AI model generates advice such as "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0438] An example of a prompt sentence to be input into the generative AI model is, "After analyzing the user's exercise data, we found that the average exercise time per week is 30 minutes short. Please generate specific advice."

[0439] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[0440] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0441] Step 1:

[0442] The user installs a dedicated application on their smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. Once this is complete, the user presses the "Submit" button. The input is the activity data entered by the user. The output is the data saved in real time.

[0443] Step 2:

[0444] The device converts the entered activity data into JSON format. Specifically, a module in the application compiles the data from the user's input fields into a JSON object, which prepares the format for data transmission. The input is the user's activity data. The output is the data converted into JSON format.

[0445] Step 3:

[0446] The terminal generates a request to send data converted to JSON format to the server. The request uses the HTTP protocol and the data is sent to the server over the Internet. As input, there is data in JSON format. As output, an HTTP request is generated and sent to the server.

[0447] Step 4:

[0448] The server receives the HTTP request sent from the device and extracts the included JSON data. A module in the server decodes the JSON data and breaks it down into individual items (meal details, exercise time, work time, etc.). The input is the HTTP request received by the server. The output is the decoded data for each item.

[0449] Step 5:

[0450] The server runs algorithms to analyze the decoded data. The analysis module evaluates the user's health status and lifestyle patterns. For example, algorithms implemented in Python analyze the timing and content of meals, exercise frequency, and sleep patterns. The input is the decoded data for each item. The output is the analysis results.

[0451] Step 6:

[0452] Based on the analysis results, the server uses a generative AI model to generate individual advice. Specifically, the analysis data is input to the generative AI model as a prompt sentence, and the optimal advice is output. The inputs are the analysis results and the prompt sentence. The output is the generated advice.

[0453] Step 7:

[0454] The generated advice is converted back to JSON format and a request is generated to send to the device. The server converts the advice content into the appropriate format and creates an HTTP request. The input is the generated advice. The output is an HTTP request to send to the device.

[0455] Step 8:

[0456] The terminal receives the HTTP request received from the server and decodes the included advice data, thereby generating a notification for the user. The input is the HTTP request received from the server, and the output is the decoded advice data.

[0457] Step 9:

[0458] The device provides the decoded advice content to the user as a notification or a screen display. For example, a push notification function is used to notify the user of specific advice. The input is the decoded advice data. The output is the advice to be notified to the user.

[0459] (Application example 1)

[0460] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0461] In modern society, people face the challenge of understanding their own health status and lifestyle patterns and receiving appropriate advice in their busy daily lives. In particular, providing personalized health advice and exercise plans in physical stores places a heavy burden on staff and is inefficient. Furthermore, there is a lack of ways for users to instantly receive specific, personalized advice based on their own activity data.

[0462] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0463] In this invention, the server includes: a means for a user to input daily activity data; a means for transmitting the input activity data to the server; a means for analyzing the activity data received by the server; a means for generating advice using a generation AI based on the analysis results; a means for transmitting the generated advice to the user's terminal; a means for displaying the advice received by the terminal to the user; and a means for providing health and exercise advice based on the user's activity data at a physical store. This allows users to instantly receive personalized advice based on the analysis results from the server simply by inputting specific data about their daily lives. This also reduces the burden on staff at physical stores and allows for efficient provision of health advice.

[0464] A "user" is an individual who utilizes the system to input their daily activity data and receive personalized advice.

[0465] "Activity data" refers to information about the user's daily life, such as diet, exercise, work, hobbies, and sleep.

[0466] The "server" is a central processing unit that receives and analyzes activity data sent by the user, generates advice using a generation AI, and sends it back to the user.

[0467] "Analysis" refers to the process by which the server evaluates the activity data it receives to reveal the user's health status and lifestyle patterns.

[0468] "Generative AI" refers to an algorithm or system that uses artificial intelligence technology to automatically generate personalized advice based on analysis results.

[0469] "Advice" refers to specific instructions or recommendations provided by the server using generated AI based on the user's activity data.

[0470] A "terminal" is a device (e.g., a smartphone, tablet, etc.) that allows a user to input activity data and receive and display advice sent from the server.

[0471] A "brick and mortar" is a physical location, such as a fitness club or health food store, where users can visit in person to receive health and exercise advice.

[0472] The system of this invention allows users to input their daily activity data, and the server analyzes the data and uses AI to provide personalized advice. Specifically, it works as follows.

[0473] First, the user uses a device such as a smartphone or tablet to input their daily activity data, including what they eat, how much time they spend exercising, working, enjoying their hobbies, and sleeping. Once the data is complete, they press the "send" button. This input data is saved in real time and sent to the server when the send button is pressed.

[0474] The server receives the activity data sent by the user. This data is sent in JSON format, and the server decodes it and breaks it down into individual components. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on patterns such as diet, exercise, and sleep.

[0475] Based on the analysis results, the server uses the generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking each day." This generated advice is then converted back into an appropriate format and sent to the user's device. The advice received by the device is decoded and displayed as a notification or screen display for the user.

[0476] This system is also designed to be used in physical stores, such as fitness clubs and health food stores, where staff can provide personalized health and exercise advice based on the data entered by the user. This allows users to receive specific advice based on their own health status and lifestyle patterns, thereby improving their quality of life.

[0477] The hardware used includes smartphones and tablets, which require an internet connection to send and receive data, and the software used includes Python and the Requests library, which facilitates data transmission, reception, analysis, and display.

[0478] As a concrete example, let's say a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0479] Example prompt sentence:

[0480] "Generate health advice based on user activity data in the following format:

[0481] Diet: Increase your intake of ○○

[0482] Exercise: Add XX minutes of exercise XX times per week

[0483] Rest: Recommended sleep time is x hours

[0484] User data: {'food': 'Salad, Fish', 'exercise': 'Running 30 mins', 'work': '8 hours', 'hobby': 'Reading 1 hour', 'sleep': '7 hours'}

[0485] This system allows users to easily receive personalized health advice by simply entering data about their daily lives, enabling them to effectively manage their health.

[0486] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0487] Step 1:

[0488] The user inputs daily activity data.

[0489] Specific operation: The user launches the dedicated app on their smartphone or tablet and enters the details of their meals, exercise time, work time, hobby time, and sleep time into a diary-style input screen. Once the input is complete, they press the "Send" button.

[0490] Input: Daily activity data (meals, exercise, work, hobbies, sleep)

[0491] Output: Activity data converted to JSON format

[0492] Step 2:

[0493] The terminal transmits the input activity data to the server.

[0494] Specific operation: The device converts the input data into JSON format and sends it to the server via the Internet. When the transmission is complete, the device displays a notification to the user that the data has been sent.

[0495] Input: Activity data in JSON format

[0496] Output: Data transmission request, transmission completion notification

[0497] Step 3:

[0498] The server receives the transmitted activity data.

[0499] Specific operation: The server receives the data sent from the device. The received data is decoded from JSON format and broken down into each item (food, exercise, work, hobbies, sleep).

[0500] Input: Data transmission request from the terminal

[0501] Output: Decoded activity data

[0502] Step 4:

[0503] The server analyzes the received data.

[0504] How it works: The server runs an analysis algorithm to assess the user's health and lifestyle based on their activity data, including what they eat, how often they exercise, and their sleep patterns.

[0505] Input: Decoded activity data

[0506] Output: Analysis results (evaluation of health status and lifestyle patterns)

[0507] Step 5:

[0508] The server generates advice using a generative AI based on the analysis results.

[0509] Specific operation: The server inputs the analysis results into the generative AI model and generates personalized health advice. For example, the generative AI may generate specific advice such as "Add 30 minutes of walking every day."

[0510] Input: Analysis results

[0511] Output: Generated advice

[0512] Step 6:

[0513] The server transmits the generated advice to the user's terminal.

[0514] Specific operation: The server converts the generated advice back into JSON format and sends it to the user's device.

[0515] Input: Generated advice

[0516] Output: Advice data in JSON format, data submission request

[0517] Step 7:

[0518] The terminal displays the received advice to the user.

[0519] Specific actions: The device decodes the received advice data and presents the advice to the user as a notification or on-screen display. The user can then confirm the advice and take specific action.

[0520] Input: Advice data in JSON format

[0521] Output: User notification or displayed advice

[0522] Step 8:

[0523] In physical stores, staff will provide support based on users' activity data.

[0524] Specific operation: When a user visits a physical store, staff will refer to the user's activity data through the system and suggest appropriate training plans and health foods.

[0525] Input: User activity data and analysis results

[0526] Output: Specific support and advice from store staff

[0527] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0528] The system of this invention allows users to input their daily activity data, which is then analyzed by a server, which then uses a generation AI and emotion engine to generate and provide personalized advice.

[0529] 1. User data entry

[0530] Users install a dedicated application on their smartphone, tablet, or other device. When the application is launched, a diary-style input screen appears. Here, users enter the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once input is complete, they press the "Send" button. The input data is saved in real time and sent to the server when the "Send" button is pressed. The emotion engine also uses the input data, behavioral history, and even voice and facial expression recognition technology to infer and record the user's emotions.

[0531] 2. Sending data from the device to the server

[0532] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. When the transmission is complete, a notification of the completion of data transmission is displayed to the user.

[0533] 3. Data reception and analysis by the server

[0534] The server receives the activity and emotion data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health status, lifestyle patterns, and even emotional tendencies.

[0535] 4. Generating Advice

[0536] Based on the analysis results, the server uses a generative AI model to generate individualized advice. Taking the user's emotional state into account also results in more appropriate and personalized advice. For example, if a user is not getting enough exercise and has recently experienced increased stress, the server may generate specific advice such as, "Try adding 30 minutes of walking each day. Also, try to set aside time to relax." This generated advice is then converted back into an appropriate format and a request is generated to send it to the device.

[0537] 5. Sending and displaying advice to the device

[0538] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0539] Specific examples

[0540] Suppose a user enters one week's lifestyle and emotional data into the app and sends the data to the server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generation AI generates comprehensive advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review it and adjust their lifestyle.

[0541] In this way, users can receive specific daily advice based on their health status, lifestyle patterns, and emotional tendencies, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is possible.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] A user launches an application on their smartphone or tablet.

[0545] Step 2:

[0546] The terminal confirms the user's login and displays the diary entry screen.

[0547] Step 3:

[0548] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[0549] Step 4:

[0550] The emotion engine uses voice and facial expression recognition technology to infer the user's current emotions, along with emotion analysis based on the user's input and behavioral history.

[0551] Step 5:

[0552] The device stores activity and emotion data in real time and enables the "Send" button once input is complete.

[0553] Step 6:

[0554] The user presses the "Send" button.

[0555] Step 7:

[0556] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[0557] Step 8:

[0558] The device sends a request to the server over the Internet.

[0559] Step 9:

[0560] The server receives the activity data and emotion data transmitted from the terminal.

[0561] Step 10:

[0562] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[0563] Step 11:

[0564] The server runs analytical algorithms to assess the user's health, lifestyle patterns, and emotional tendencies.

[0565] Step 12:

[0566] The server uses a generative AI model based on the analysis results to generate personalized advice, taking into account the user's emotional state.

[0567] Step 13:

[0568] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[0569] Step 14:

[0570] The server sends a request via the Internet to send advice data to the terminal.

[0571] Step 15:

[0572] The terminal receives the advice data transmitted from the server.

[0573] Step 16:

[0574] The terminal decodes the received advice and generates a notification or screen display for the user.

[0575] Step 17:

[0576] The user checks the advice displayed on the device and follows it to improve their lifestyle habits.

[0577] Example 2

[0578] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0579] In modern society, there is a demand for continuous evaluation of individuals' health status and lifestyle patterns and provision of appropriate feedback. However, conventional systems have difficulty providing personalized advice that takes into account the user's emotional state, and they also lack the ability to monitor trends based on long-term data analysis, resulting in problems that prevent sufficient improvement in the user's quality of life.

[0580] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0581] In this invention, the server includes: means for a user to input daily activity data; means for converting the input activity data and emotional data into an appropriate format and transmitting the converted data to the server; means for the server to analyze the received activity data and emotional data and evaluate the user's health condition, lifestyle patterns, and emotional tendencies; means for generating advice using a generation AI based on the analysis results and emotional data; means for converting the generated advice into an appropriate format and transmitting the advice to the user's device; and means for the device to notify or display the received advice to the user. This enables the provision of personalized advice to each user that takes into account their emotional state, and enables long-term trend monitoring of health conditions and lifestyle patterns.

[0582] "Activity data" refers to information such as dietary content, exercise time, work time, hobby time, and sleep time that is recorded in the user's daily life.

[0583] "Emotional data" refers to data that represents the user's emotional state, and includes information inferred or recorded from voice and facial expression recognition technology and behavioral history.

[0584] "Dedicated application" refers to software that users install on their smartphones or tablets to input activity data and emotional data.

[0585] "Server" refers to a computer system that receives and analyzes activity data and emotion data sent from a device, and generates and sends advice to the user using a generative AI model.

[0586] "Analysis algorithm" refers to the method or calculation procedure used by the server to analyze the activity data and emotional data received and evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[0587] "Generative AI model" refers to the artificial intelligence model used by the server to generate personalized advice for users based on the analysis results.

[0588] A "prompt sentence" is a sentence input into a generative AI model, and refers to an instruction sentence that guides the content of the advice generated based on the analysis results.

[0589] "Terminal" refers to an electronic device, such as a smartphone or tablet, used by a user to input data and display generated advice.

[0590] The "JSON format" is a lightweight data exchange format for expressing data structures, and is used when sending and receiving data between a terminal and a server.

[0591] "Notification" refers to the display of a message to convey important information, such as advice, generated by the system to the user.

[0592] The system of this invention works by having users input their daily activity data and emotional data, which is then analyzed by a server, which then uses a generative AI model and emotional engine to generate and provide personalized advice.

[0593] First, the user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. After completing the input, the user presses the "Send" button. The emotion engine then uses the input data, behavioral history, and voice and facial expression recognition technology to infer and record the user's emotions.

[0594] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the user is notified that the data has been transmitted.

[0595] The server receives the activity and emotion data sent from the device, decodes it according to a specific format, breaks it down into individual items, and runs a specified analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[0596] Based on the analysis results, the server uses a generative AI model to generate individualized advice. This process also takes into account the user's emotional data, resulting in more personalized advice. For example, if a user is not getting enough exercise and is experiencing increased stress, the generative AI model might generate advice such as, "Add 30 minutes of walking each day. Also, try to set aside time to relax." This advice is then converted back into an appropriate format (e.g., JSON format) and a request is generated to send it to the device.

[0597] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0598] Specific examples

[0599] Suppose a user enters one week's lifestyle and emotional data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generative AI model generates advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review the advice and adjust their lifestyle.

[0600] Prompt Sentence Examples

[0601] An example of an input prompt for the generative AI model would be, "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice."

[0602] The system provides personalized advice to each user that takes into account their emotional state and enables long-term trend monitoring of health and lifestyle patterns.

[0603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The user installs a dedicated application on a device such as a smartphone or tablet. When the app is launched, a diary-style input screen appears. The user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. This data constitutes "input." After completing the input, the user presses the "send" button. The emotion engine uses the input data, behavioral history, voice, and facial expressions to infer and record the user's emotions. This operation generates activity data and emotion data, which constitutes "output."

[0606] Step 2:

[0607] The device converts the activity and emotion data entered by the user into an appropriate format (e.g., JSON format). During this conversion process, the data is organized and formatted so that it can be interpreted by the server. This is part of data processing. The converted data becomes the "input," and then a data transmission request is sent to the server via the internet. This request becomes the "output." Once transmission is complete, a notification that the data has been sent is displayed to the user.

[0608] Step 3:

[0609] The server receives activity data and emotion data sent from the device. The received data becomes the "input." When the server receives this data, it first decodes it in JSON format and breaks it down into individual items. The decoded data becomes the "output." Next, it runs an analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies. The results of this analysis also become the "output."

[0610] Step 4:

[0611] Based on the analysis results, the server uses a generative AI model to generate individualized advice. The analysis results and emotional data become the "input." The server inputs a prompt (e.g., "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice.") into the generative AI model. This prompt becomes the "output." The generative AI model generates individualized advice based on this prompt. The generated advice becomes the "output." This advice is again converted into an appropriate format (e.g., JSON format), and a request is generated to send to the device.

[0612] Step 5:

[0613] The server sends the generated advice data to the terminal via the Internet. This advice data becomes the "input." The terminal decodes the received advice data and generates a notification or screen display for the user. The decoded advice becomes the "output." The user can receive individual advice at the appropriate time. This notification or display serves as a concrete guide for the user to take action.

[0614] (Application example 2)

[0615] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0616] While conventional systems can provide personalized advice based on a user's activity and emotional data, they have the problem of not directly linking this advice to purchasing activities and behavior in physical stores. Furthermore, users have difficulty selecting products and services that reflect their own health status and lifestyle patterns. This results in problems such as insufficient achievement of behavioral change and improvement of the user's quality of life.

[0617] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0618] In this invention, the server includes means for a user to input daily activity data, means for transmitting the input activity data to the server, means for analyzing the activity data received by the server, means for generating advice using a generation AI based on the analysis results, means for transmitting the generated advice to the user's terminal, means for displaying the advice received by the terminal to the user, and means for advising the user on what to purchase and what to do in the store based on the user's activity data and emotion data. This enables the user to be effectively guided in their actions and purchases in a physical store based on their own activity data and emotion data.

[0619] "User" refers to an individual who uses this system to input activity data and emotion data and receives advice from the server.

[0620] "Activity data" refers to information about a user's daily diet, exercise, work, hobbies, and sleep.

[0621] "Emotional data" is data that indicates the user's emotional state and is estimated and recorded using voice and facial expression recognition technology.

[0622] A "dedicated application" refers to software that users install on their devices, such as smartphones, to input activity data and emotional data and communicate with the server.

[0623] "Server" refers to a computer system that receives activity data and emotion data sent by users, analyzes them, and generates and provides advice using generative AI.

[0624] "Generative AI" refers to an artificial intelligence model that analyzes and generates personalized advice based on the data it receives.

[0625] "Terminal" refers to a device (e.g., a smartphone or tablet) on which a user installs a dedicated application and receives and displays advice from a server.

[0626] "Means of advising on purchases and actions" refers to a function that suggests recommended products and actions in physical stores based on the user's activity data and emotional data.

[0627] "In-store navigation" refers to a feature that helps users find the right products and services in a physical store.

[0628] In the system for implementing this invention, a user inputs activity data and emotion data, which is then analyzed by a server, and individualized advice is generated and provided using a generation AI and emotion engine. This will be explained in detail below.

[0629] System Configuration

[0630] This system consists of a user device (such as a smartphone) and a server. Users install a dedicated application on their device and input their daily activity and emotion data. The server receives the data sent by the user, analyzes it, and generates appropriate advice.

[0631] Data entry and submission

[0632] Users enter information about their daily diet, exercise, work, hobbies, and sleep through a dedicated application. Emotional data is also inferred and recorded using voice and facial expression recognition technology (e.g., technology using a smartphone's camera and microphone). This data is converted into JSON format and sent to the server.

[0633] Data analysis and advice generation

[0634] The server receives the transmitted data and runs an analysis algorithm. The analysis algorithm evaluates the user's health condition and lifestyle patterns. It then uses a generative AI model to generate personalized advice. The generative AI model generates optimal advice based on the user's activity data and emotional data. For example, if a lack of exercise and emotional stress are detected, the generated advice would be, "Add 30 minutes of walking every day. Also, try to make time to relax."

[0635] Sending and viewing advice

[0636] The generated advice is sent from the server to the user's device, where it is decoded and presented to the user via notification or on-screen display, allowing the user to receive the most appropriate advice at the right time.

[0637] Application in physical stores

[0638] Furthermore, this system can also be applied to navigating purchases and activities in physical stores. When a user brings the dedicated application with them and visits a physical store, the in-store navigation function is activated. Based on the user's activity and emotional data, the system navigates to recommended ingredients, exercise equipment, relaxation products, and more within the store. It also guides users to special activities (free classes and demonstrations) in specific sections of the store (health foods, fitness, relaxation). This allows users to make more effective purchases in physical stores.

[0639] Examples of prompt statements

[0640] A specific example of a prompt is as follows:

[0641] "Based on the user's recent data, generate advice like this:

[0642] Today's exercise time: 30 minutes

[0643] Today's meal: Bread, salad

[0644] Today's work hours: 8 hours

[0645] Hobby time today: 2 hours

[0646] Sleep time today: 7 hours

[0647] Today's emotion: happy

[0648] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[0649] In this way, users can receive specific advice based on their health status and emotions in a physical store, improving their quality of life.

[0650] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0651] Step 1:

[0652] Users install the dedicated application on their smartphones and launch it. Using a diary-style input screen, users enter data on their daily activities (food, exercise, work, hobbies, sleep) and emotional data. The entered data is temporarily stored on the device.

[0653] Input: User activity data and emotion data

[0654] Output: Input data stored in the device

[0655] Step 2:

[0656] When the user presses the "Send" button, the device converts the input activity and emotion data into JSON format and generates an HTTP request, which is then sent to the server via the Internet.

[0657] Input: Input data stored in the device

[0658] Output: JSON formatted data sent to the server

[0659] Step 3:

[0660] The server receives and decodes the JSON-formatted data sent from the device. The received data is then stored in a database. Data analysis algorithms are then run to analyze the data to evaluate the user's health status and lifestyle patterns.

[0661] Input: JSON format data sent to the server

[0662] Output: Analyzed data on the user's health status and lifestyle patterns

[0663] Step 4:

[0664] The server generates individual advice using a generative AI model based on the analysis results. A prompt sentence is generated based on the analyzed data and input to the generative AI model. The generative AI model generates optimal advice, converts it into JSON format, and saves it.

[0665] Input: Analyzed data on the user's health status and lifestyle patterns, and prompts for the generative AI model

[0666] Output: Generated individual advice

[0667] Step 5:

[0668] The server sends the generated advice to the user's device. The advice data is sent in JSON format, and the device receives it.

[0669] Input: JSON format data of the generated individual advice

[0670] Output: Advice data sent to the terminal

[0671] Step 6:

[0672] The device decodes the received advice data and displays it to the user. The user can view the advice provided through the application. If necessary, the navigation function in the physical store is activated, and the user can receive advice on what to buy and what to do in the store.

[0673] Input: Advice data sent to the terminal

[0674] Output: The individual advice displayed to the user

[0675] As an example of how this works, the following prompt sentence is input to the generative AI model:

[0676] "Based on the user's recent data, generate advice like this:

[0677] Today's exercise time: 30 minutes

[0678] Today's meal: Bread, salad

[0679] Today's work hours: 8 hours

[0680] Hobby time today: 2 hours

[0681] Sleep time today: 7 hours

[0682] Today's emotion: happy

[0683] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[0684] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0685] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0686] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0687] [Third embodiment]

[0688] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0689] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0690] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0691] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0692] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0693] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0694] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0695] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0696] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0697] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0698] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0699] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0700] The system of this invention allows users to input their daily activity data, which is then analyzed by a server that uses AI to generate and provide personalized advice.

[0701] 1. User data entry

[0702] The user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button. The entered data is saved in real time and sent to the server when the Send button is pressed.

[0703] 2. Sending data from the device to the server

[0704] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, a notification of data transmission completion is displayed to the user.

[0705] 3. Data reception and analysis by the server

[0706] The server receives the activity data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on the timing and content of meals, the frequency of exercise, sleep patterns, etc.

[0707] 4. Generating Advice

[0708] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server may generate specific advice such as "Add 30 minutes of walking every day." This advice is then converted back into an appropriate format and a request is generated to send it to the device.

[0709] 5. Sending and displaying advice to the device

[0710] The advice data generated by the server is sent to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0711] Specific examples

[0712] Let's say a user enters one week's worth of lifestyle data into an app and sends it to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0713] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[0714] The processing flow will be explained below.

[0715] Step 1:

[0716] A user launches an application on their smartphone or tablet.

[0717] Step 2:

[0718] The terminal confirms the user's login and displays the diary entry screen.

[0719] Step 3:

[0720] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[0721] Step 4:

[0722] The device saves the entered data in real time and enables the "Send" button once the entry is complete.

[0723] Step 5:

[0724] The user presses the "Send" button.

[0725] Step 6:

[0726] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[0727] Step 7:

[0728] The device sends a request to the server over the Internet.

[0729] Step 8:

[0730] The server receives the activity data sent from the terminal.

[0731] Step 9:

[0732] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[0733] Step 10:

[0734] The server runs analytical algorithms to assess the user's health and lifestyle patterns.

[0735] Step 11:

[0736] The server uses a generative AI model based on the analysis results to generate individual advice.

[0737] Step 12:

[0738] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[0739] Step 13:

[0740] The server sends a request via the Internet to send advice data to the terminal.

[0741] Step 14:

[0742] The terminal receives the advice data transmitted from the server.

[0743] Step 15:

[0744] The terminal generates a notification or screen display for the user of the decoded advice.

[0745] Step 16:

[0746] The user checks the advice displayed on the device and implements it to improve their lifestyle habits.

[0747] Example 1

[0748] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0749] In conventional health management systems, users' daily activity data is typically recorded manually, and health managers analyze it and provide advice. However, this method suffers from problems such as inconvenient data entry, delayed analysis, and generalized advice. In particular, it is difficult to provide personalized advice tailored to each user's specific needs, making it difficult to maintain user motivation. Furthermore, there is a lack of means to monitor long-term health trends.

[0750] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0751] In this invention, the server includes: a means for a user to input daily activity data; a means for saving the input activity data in real time on the terminal, converting it into an appropriate format, and transmitting it to the server; a means for receiving, decoding, and analyzing the activity data transmitted from the terminal; a means for generating personalized advice using a generative AI model based on the analysis results; and a means for transmitting the generated advice to the user's terminal and notifying or displaying the received advice to the user. This allows the user to easily input daily activity data, quickly and accurately analyze the data, and provide personalized advice. It also makes it possible to accumulate analysis results over the long term and monitor the user's health trends.

[0752] "User" refers to the individual using the system or on whose behalf they enter data and receive advice.

[0753] "Activity data" refers to information about the user's daily activities, such as diet, exercise, work, hobbies, and sleep.

[0754] "Device" refers to a smartphone, tablet, or other portable electronic device used by a user to enter activity data.

[0755] "Server" refers to a remote computer system that receives and analyzes activity data sent from a user's terminal, and generates and sends advice.

[0756] "JSON format" stands for JavaScript Object Notation and refers to a lightweight data exchange format.

[0757] "Generative AI model" refers to a machine learning model that uses artificial intelligence technology to generate personalized advice based on user activity data.

[0758] "Analysis algorithm" refers to a series of calculation procedures used to analyze a user's activity data and evaluate their health status and lifestyle patterns.

[0759] "Advice" refers to specific suggestions or recommendations that the server outputs based on the user's activity data using a generative AI model.

[0760] "Notification" refers to the method used by the device to inform the user of advice or other important information.

[0761] "Long-term storage" refers to storing user activity data and analysis results for a certain period of time or longer and making them continuously available.

[0762] "Health trends" refers to changes and trends in health status and lifestyle patterns that can be seen from long-term accumulated user activity data and analysis results.

[0763] The system of this invention works by having users input their daily activity data, which is then analyzed by a server and used to generate and provide personalized advice using a generative AI model.

[0764] First, the user installs a dedicated application on a device such as a smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen is displayed. On this screen, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button, and this data is saved in real time and sent to the server in JSON format.

[0765] Next, the device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the device displays a notification to the user that the data has been transmitted.

[0766] The server receives the activity data sent from the device and decodes it according to JSON format. The decoded data is broken down into individual items and passed to the server's analysis module. The server's analysis module runs an algorithm to analyze the received data and evaluate the user's health status and lifestyle patterns. This analysis is based on, for example, the timing and content of meals, the frequency of exercise, and sleep patterns. The analysis module uses algorithms implemented in Python.

[0767] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking every day." This generated advice is then converted back into an appropriate format (such as JSON) and a request is generated to send to the device.

[0768] Finally, the advice data generated by the server is sent back to the device via the Internet, where it is decoded and a notification or screen display is generated for the user, allowing the user to receive personalized advice at the appropriate time.

[0769] As a concrete example, consider the case where a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generative AI model generates advice such as "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0770] An example of a prompt sentence to be input into the generative AI model is, "After analyzing the user's exercise data, we found that the average exercise time per week is 30 minutes short. Please generate specific advice."

[0771] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[0772] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0773] Step 1:

[0774] The user installs a dedicated application on their smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. Once this is complete, the user presses the "Submit" button. The input is the activity data entered by the user. The output is the data saved in real time.

[0775] Step 2:

[0776] The device converts the entered activity data into JSON format. Specifically, a module in the application compiles the data from the user's input fields into a JSON object, which prepares the format for data transmission. The input is the user's activity data. The output is the data converted into JSON format.

[0777] Step 3:

[0778] The terminal generates a request to send data converted to JSON format to the server. The request uses the HTTP protocol and the data is sent to the server over the Internet. As input, there is data in JSON format. As output, an HTTP request is generated and sent to the server.

[0779] Step 4:

[0780] The server receives the HTTP request sent from the device and extracts the included JSON data. A module in the server decodes the JSON data and breaks it down into individual items (meal details, exercise time, work time, etc.). The input is the HTTP request received by the server. The output is the decoded data for each item.

[0781] Step 5:

[0782] The server runs algorithms to analyze the decoded data. The analysis module evaluates the user's health status and lifestyle patterns. For example, algorithms implemented in Python analyze the timing and content of meals, exercise frequency, and sleep patterns. The input is the decoded data for each item. The output is the analysis results.

[0783] Step 6:

[0784] Based on the analysis results, the server uses a generative AI model to generate individual advice. Specifically, the analysis data is input to the generative AI model as a prompt sentence, and the optimal advice is output. The inputs are the analysis results and the prompt sentence. The output is the generated advice.

[0785] Step 7:

[0786] The generated advice is converted back to JSON format and a request is generated to send to the device. The server converts the advice content into the appropriate format and creates an HTTP request. The input is the generated advice. The output is an HTTP request to send to the device.

[0787] Step 8:

[0788] The terminal receives the HTTP request received from the server and decodes the included advice data, thereby generating a notification for the user. The input is the HTTP request received from the server, and the output is the decoded advice data.

[0789] Step 9:

[0790] The device provides the decoded advice content to the user as a notification or a screen display. For example, a push notification function is used to notify the user of specific advice. The input is the decoded advice data. The output is the advice to be notified to the user.

[0791] (Application example 1)

[0792] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0793] In modern society, people face the challenge of understanding their own health status and lifestyle patterns and receiving appropriate advice in their busy daily lives. In particular, providing personalized health advice and exercise plans in physical stores places a heavy burden on staff and is inefficient. Furthermore, there is a lack of ways for users to instantly receive specific, personalized advice based on their own activity data.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0795] In this invention, the server includes: a means for a user to input daily activity data; a means for transmitting the input activity data to the server; a means for analyzing the activity data received by the server; a means for generating advice using a generation AI based on the analysis results; a means for transmitting the generated advice to the user's terminal; a means for displaying the advice received by the terminal to the user; and a means for providing health and exercise advice based on the user's activity data at a physical store. This allows users to instantly receive personalized advice based on the analysis results from the server simply by inputting specific data about their daily lives. This also reduces the burden on staff at physical stores and allows for efficient provision of health advice.

[0796] A "user" is an individual who utilizes the system to input their daily activity data and receive personalized advice.

[0797] "Activity data" refers to information about the user's daily life, such as diet, exercise, work, hobbies, and sleep.

[0798] The "server" is a central processing unit that receives and analyzes activity data sent by the user, generates advice using a generation AI, and sends it back to the user.

[0799] "Analysis" refers to the process by which the server evaluates the activity data it receives to reveal the user's health status and lifestyle patterns.

[0800] "Generative AI" refers to an algorithm or system that uses artificial intelligence technology to automatically generate personalized advice based on analysis results.

[0801] "Advice" refers to specific instructions or recommendations provided by the server using generated AI based on the user's activity data.

[0802] A "terminal" is a device (e.g., a smartphone, tablet, etc.) that allows a user to input activity data and receive and display advice sent from the server.

[0803] A "brick and mortar" is a physical location, such as a fitness club or health food store, where users can visit in person to receive health and exercise advice.

[0804] The system of this invention allows users to input their daily activity data, and the server analyzes the data and uses AI to provide personalized advice. Specifically, it works as follows.

[0805] First, the user uses a device such as a smartphone or tablet to input their daily activity data, including what they eat, how much time they spend exercising, working, enjoying their hobbies, and sleeping. Once the data is complete, they press the "send" button. This input data is saved in real time and sent to the server when the send button is pressed.

[0806] The server receives the activity data sent by the user. This data is sent in JSON format, and the server decodes it and breaks it down into individual components. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on patterns such as diet, exercise, and sleep.

[0807] Based on the analysis results, the server uses the generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking each day." This generated advice is then converted back into an appropriate format and sent to the user's device. The advice received by the device is decoded and displayed as a notification or screen display for the user.

[0808] This system is also designed to be used in physical stores, such as fitness clubs and health food stores, where staff can provide personalized health and exercise advice based on the data entered by the user. This allows users to receive specific advice based on their own health status and lifestyle patterns, thereby improving their quality of life.

[0809] The hardware used includes smartphones and tablets, which require an internet connection to send and receive data, and the software used includes Python and the Requests library, which facilitates data transmission, reception, analysis, and display.

[0810] As a concrete example, let's say a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[0811] Example prompt sentence:

[0812] "Generate health advice based on user activity data in the following format:

[0813] Diet: Increase your intake of ○○

[0814] Exercise: Add XX minutes of exercise XX times per week

[0815] Rest: Recommended sleep time is x hours

[0816] User data: {'food': 'Salad, Fish', 'exercise': 'Running 30 mins', 'work': '8 hours', 'hobby': 'Reading 1 hour', 'sleep': '7 hours'}

[0817] This system allows users to easily receive personalized health advice by simply entering data about their daily lives, enabling them to effectively manage their health.

[0818] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0819] Step 1:

[0820] The user inputs daily activity data.

[0821] Specific operation: The user launches the dedicated app on their smartphone or tablet and enters the details of their meals, exercise time, work time, hobby time, and sleep time into a diary-style input screen. Once the input is complete, they press the "Send" button.

[0822] Input: Daily activity data (meals, exercise, work, hobbies, sleep)

[0823] Output: Activity data converted to JSON format

[0824] Step 2:

[0825] The terminal transmits the input activity data to the server.

[0826] Specific operation: The device converts the input data into JSON format and sends it to the server via the Internet. When the transmission is complete, the device displays a notification to the user that the data has been sent.

[0827] Input: Activity data in JSON format

[0828] Output: Data transmission request, transmission completion notification

[0829] Step 3:

[0830] The server receives the transmitted activity data.

[0831] Specific operation: The server receives the data sent from the device. The received data is decoded from JSON format and broken down into each item (food, exercise, work, hobbies, sleep).

[0832] Input: Data transmission request from the terminal

[0833] Output: Decoded activity data

[0834] Step 4:

[0835] The server analyzes the received data.

[0836] How it works: The server runs an analysis algorithm to assess the user's health and lifestyle based on their activity data, including what they eat, how often they exercise, and their sleep patterns.

[0837] Input: Decoded activity data

[0838] Output: Analysis results (evaluation of health status and lifestyle patterns)

[0839] Step 5:

[0840] The server generates advice using a generative AI based on the analysis results.

[0841] Specific operation: The server inputs the analysis results into the generative AI model and generates personalized health advice. For example, the generative AI may generate specific advice such as "Add 30 minutes of walking every day."

[0842] Input: Analysis results

[0843] Output: Generated advice

[0844] Step 6:

[0845] The server transmits the generated advice to the user's terminal.

[0846] Specific operation: The server converts the generated advice back into JSON format and sends it to the user's device.

[0847] Input: Generated advice

[0848] Output: Advice data in JSON format, data submission request

[0849] Step 7:

[0850] The terminal displays the received advice to the user.

[0851] Specific actions: The device decodes the received advice data and presents the advice to the user as a notification or on-screen display. The user can then confirm the advice and take specific action.

[0852] Input: Advice data in JSON format

[0853] Output: User notification or displayed advice

[0854] Step 8:

[0855] In physical stores, staff will provide support based on users' activity data.

[0856] Specific operation: When a user visits a physical store, staff will refer to the user's activity data through the system and suggest appropriate training plans and health foods.

[0857] Input: User activity data and analysis results

[0858] Output: Specific support and advice from store staff

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

[0860] The system of this invention allows users to input their daily activity data, which is then analyzed by a server, which then uses a generation AI and emotion engine to generate and provide personalized advice.

[0861] 1. User data entry

[0862] Users install a dedicated application on their smartphone, tablet, or other device. When the application is launched, a diary-style input screen appears. Here, users enter the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once input is complete, they press the "Send" button. The input data is saved in real time and sent to the server when the "Send" button is pressed. The emotion engine also uses the input data, behavioral history, and even voice and facial expression recognition technology to infer and record the user's emotions.

[0863] 2. Sending data from the device to the server

[0864] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. When the transmission is complete, a notification of the completion of data transmission is displayed to the user.

[0865] 3. Data reception and analysis by the server

[0866] The server receives the activity and emotion data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health status, lifestyle patterns, and even emotional tendencies.

[0867] 4. Generating Advice

[0868] Based on the analysis results, the server uses a generative AI model to generate individualized advice. Taking the user's emotional state into account also results in more appropriate and personalized advice. For example, if a user is not getting enough exercise and has recently experienced increased stress, the server may generate specific advice such as, "Try adding 30 minutes of walking each day. Also, try to set aside time to relax." This generated advice is then converted back into an appropriate format and a request is generated to send it to the device.

[0869] 5. Sending and displaying advice to the device

[0870] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0871] Specific examples

[0872] Suppose a user enters one week's lifestyle and emotional data into the app and sends the data to the server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generation AI generates comprehensive advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review it and adjust their lifestyle.

[0873] In this way, users can receive specific daily advice based on their health status, lifestyle patterns, and emotional tendencies, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is possible.

[0874] The processing flow will be explained below.

[0875] Step 1:

[0876] A user launches an application on their smartphone or tablet.

[0877] Step 2:

[0878] The terminal confirms the user's login and displays the diary entry screen.

[0879] Step 3:

[0880] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[0881] Step 4:

[0882] The emotion engine uses voice and facial expression recognition technology to infer the user's current emotions, along with emotion analysis based on the user's input and behavioral history.

[0883] Step 5:

[0884] The device stores activity and emotion data in real time and enables the "Send" button once input is complete.

[0885] Step 6:

[0886] The user presses the "Send" button.

[0887] Step 7:

[0888] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[0889] Step 8:

[0890] The device sends a request to the server over the Internet.

[0891] Step 9:

[0892] The server receives the activity data and emotion data transmitted from the terminal.

[0893] Step 10:

[0894] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[0895] Step 11:

[0896] The server runs analytical algorithms to assess the user's health, lifestyle patterns, and emotional tendencies.

[0897] Step 12:

[0898] The server uses a generative AI model based on the analysis results to generate personalized advice, taking into account the user's emotional state.

[0899] Step 13:

[0900] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[0901] Step 14:

[0902] The server sends a request via the Internet to send advice data to the terminal.

[0903] Step 15:

[0904] The terminal receives the advice data transmitted from the server.

[0905] Step 16:

[0906] The terminal decodes the received advice and generates a notification or screen display for the user.

[0907] Step 17:

[0908] The user checks the advice displayed on the device and follows it to improve their lifestyle habits.

[0909] Example 2

[0910] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0911] In modern society, there is a demand for continuous evaluation of individuals' health status and lifestyle patterns and provision of appropriate feedback. However, conventional systems have difficulty providing personalized advice that takes into account the user's emotional state, and they also lack the ability to monitor trends based on long-term data analysis, resulting in problems that prevent sufficient improvement in the user's quality of life.

[0912] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0913] In this invention, the server includes: means for a user to input daily activity data; means for converting the input activity data and emotional data into an appropriate format and transmitting the converted data to the server; means for the server to analyze the received activity data and emotional data and evaluate the user's health condition, lifestyle patterns, and emotional tendencies; means for generating advice using a generation AI based on the analysis results and emotional data; means for converting the generated advice into an appropriate format and transmitting the advice to the user's device; and means for the device to notify or display the received advice to the user. This enables the provision of personalized advice to each user that takes into account their emotional state, and enables long-term trend monitoring of health conditions and lifestyle patterns.

[0914] "Activity data" refers to information such as dietary content, exercise time, work time, hobby time, and sleep time that is recorded in the user's daily life.

[0915] "Emotional data" refers to data that represents the user's emotional state, and includes information inferred or recorded from voice and facial expression recognition technology and behavioral history.

[0916] "Dedicated application" refers to software that users install on their smartphones or tablets to input activity data and emotional data.

[0917] "Server" refers to a computer system that receives and analyzes activity data and emotion data sent from a device, and generates and sends advice to the user using a generative AI model.

[0918] "Analysis algorithm" refers to the method or calculation procedure used by the server to analyze the activity data and emotional data received and evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[0919] "Generative AI model" refers to the artificial intelligence model used by the server to generate personalized advice for users based on the analysis results.

[0920] A "prompt sentence" is a sentence input into a generative AI model, and refers to an instruction sentence that guides the content of the advice generated based on the analysis results.

[0921] "Terminal" refers to an electronic device, such as a smartphone or tablet, used by a user to input data and display generated advice.

[0922] The "JSON format" is a lightweight data exchange format for expressing data structures, and is used when sending and receiving data between a terminal and a server.

[0923] "Notification" refers to the display of a message to convey important information, such as advice, generated by the system to the user.

[0924] The system of this invention works by having users input their daily activity data and emotional data, which is then analyzed by a server, which then uses a generative AI model and emotional engine to generate and provide personalized advice.

[0925] First, the user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. After completing the input, the user presses the "Send" button. The emotion engine then uses the input data, behavioral history, and voice and facial expression recognition technology to infer and record the user's emotions.

[0926] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the user is notified that the data has been transmitted.

[0927] The server receives the activity and emotion data sent from the device, decodes it according to a specific format, breaks it down into individual items, and runs a specified analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[0928] Based on the analysis results, the server uses a generative AI model to generate individualized advice. This process also takes into account the user's emotional data, resulting in more personalized advice. For example, if a user is not getting enough exercise and is experiencing increased stress, the generative AI model might generate advice such as, "Add 30 minutes of walking each day. Also, try to set aside time to relax." This advice is then converted back into an appropriate format (e.g., JSON format) and a request is generated to send it to the device.

[0929] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[0930] Specific examples

[0931] Suppose a user enters one week's lifestyle and emotional data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generative AI model generates advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review the advice and adjust their lifestyle.

[0932] Prompt Sentence Examples

[0933] An example of an input prompt for the generative AI model would be, "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice."

[0934] The system provides personalized advice to each user that takes into account their emotional state and enables long-term trend monitoring of health and lifestyle patterns.

[0935] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0936] Step 1:

[0937] The user installs a dedicated application on a device such as a smartphone or tablet. When the app is launched, a diary-style input screen appears. The user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. This data constitutes "input." After completing the input, the user presses the "send" button. The emotion engine uses the input data, behavioral history, voice, and facial expressions to infer and record the user's emotions. This operation generates activity data and emotion data, which constitutes "output."

[0938] Step 2:

[0939] The device converts the activity and emotion data entered by the user into an appropriate format (e.g., JSON format). During this conversion process, the data is organized and formatted so that it can be interpreted by the server. This is part of data processing. The converted data becomes the "input," and then a data transmission request is sent to the server via the internet. This request becomes the "output." Once transmission is complete, a notification that the data has been sent is displayed to the user.

[0940] Step 3:

[0941] The server receives activity data and emotion data sent from the device. The received data becomes the "input." When the server receives this data, it first decodes it in JSON format and breaks it down into individual items. The decoded data becomes the "output." Next, it runs an analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies. The results of this analysis also become the "output."

[0942] Step 4:

[0943] Based on the analysis results, the server uses a generative AI model to generate individualized advice. The analysis results and emotional data become the "input." The server inputs a prompt (e.g., "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice.") into the generative AI model. This prompt becomes the "output." The generative AI model generates individualized advice based on this prompt. The generated advice becomes the "output." This advice is again converted into an appropriate format (e.g., JSON format), and a request is generated to send to the device.

[0944] Step 5:

[0945] The server sends the generated advice data to the terminal via the Internet. This advice data becomes the "input." The terminal decodes the received advice data and generates a notification or screen display for the user. The decoded advice becomes the "output." The user can receive individual advice at the appropriate time. This notification or display serves as a concrete guide for the user to take action.

[0946] (Application example 2)

[0947] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0948] While conventional systems can provide personalized advice based on a user's activity and emotional data, they have the problem of not directly linking this advice to purchasing activities and behavior in physical stores. Furthermore, users have difficulty selecting products and services that reflect their own health status and lifestyle patterns. This results in problems such as insufficient achievement of behavioral change and improvement of the user's quality of life.

[0949] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0950] In this invention, the server includes means for a user to input daily activity data, means for transmitting the input activity data to the server, means for analyzing the activity data received by the server, means for generating advice using a generation AI based on the analysis results, means for transmitting the generated advice to the user's terminal, means for displaying the advice received by the terminal to the user, and means for advising the user on what to purchase and what to do in the store based on the user's activity data and emotion data. This enables the user to be effectively guided in their actions and purchases in a physical store based on their own activity data and emotion data.

[0951] "User" refers to an individual who uses this system to input activity data and emotion data and receives advice from the server.

[0952] "Activity data" refers to information about a user's daily diet, exercise, work, hobbies, and sleep.

[0953] "Emotional data" is data that indicates the user's emotional state and is estimated and recorded using voice and facial expression recognition technology.

[0954] A "dedicated application" refers to software that users install on their devices, such as smartphones, to input activity data and emotional data and communicate with the server.

[0955] "Server" refers to a computer system that receives activity data and emotion data sent by users, analyzes them, and generates and provides advice using generative AI.

[0956] "Generative AI" refers to an artificial intelligence model that analyzes and generates personalized advice based on the data it receives.

[0957] "Terminal" refers to a device (e.g., a smartphone or tablet) on which a user installs a dedicated application and receives and displays advice from a server.

[0958] "Means of advising on purchases and actions" refers to a function that suggests recommended products and actions in physical stores based on the user's activity data and emotional data.

[0959] "In-store navigation" refers to a feature that helps users find the right products and services in a physical store.

[0960] In the system for implementing this invention, a user inputs activity data and emotion data, which is then analyzed by a server, and individualized advice is generated and provided using a generation AI and emotion engine. This will be explained in detail below.

[0961] System Configuration

[0962] This system consists of a user device (such as a smartphone) and a server. Users install a dedicated application on their device and input their daily activity and emotion data. The server receives the data sent by the user, analyzes it, and generates appropriate advice.

[0963] Data entry and submission

[0964] Users enter information about their daily diet, exercise, work, hobbies, and sleep through a dedicated application. Emotional data is also inferred and recorded using voice and facial expression recognition technology (e.g., technology using a smartphone's camera and microphone). This data is converted into JSON format and sent to the server.

[0965] Data analysis and advice generation

[0966] The server receives the transmitted data and runs an analysis algorithm. The analysis algorithm evaluates the user's health condition and lifestyle patterns. It then uses a generative AI model to generate personalized advice. The generative AI model generates optimal advice based on the user's activity data and emotional data. For example, if a lack of exercise and emotional stress are detected, the generated advice would be, "Add 30 minutes of walking every day. Also, try to make time to relax."

[0967] Sending and viewing advice

[0968] The generated advice is sent from the server to the user's device, where it is decoded and presented to the user via notification or on-screen display, allowing the user to receive the most appropriate advice at the right time.

[0969] Application in physical stores

[0970] Furthermore, this system can also be applied to navigating purchases and activities in physical stores. When a user brings the dedicated application with them and visits a physical store, the in-store navigation function is activated. Based on the user's activity and emotional data, the system navigates to recommended ingredients, exercise equipment, relaxation products, and more within the store. It also guides users to special activities (free classes and demonstrations) in specific sections of the store (health foods, fitness, relaxation). This allows users to make more effective purchases in physical stores.

[0971] Examples of prompt statements

[0972] A specific example of a prompt is as follows:

[0973] "Based on the user's recent data, generate advice like this:

[0974] Today's exercise time: 30 minutes

[0975] Today's meal: Bread, salad

[0976] Today's work hours: 8 hours

[0977] Hobby time today: 2 hours

[0978] Sleep time today: 7 hours

[0979] Today's emotion: happy

[0980] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[0981] In this way, users can receive specific advice based on their health status and emotions in a physical store, improving their quality of life.

[0982] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0983] Step 1:

[0984] Users install the dedicated application on their smartphones and launch it. Using a diary-style input screen, users enter data on their daily activities (food, exercise, work, hobbies, sleep) and emotional data. The entered data is temporarily stored on the device.

[0985] Input: User activity data and emotion data

[0986] Output: Input data stored in the device

[0987] Step 2:

[0988] When the user presses the "Send" button, the device converts the input activity and emotion data into JSON format and generates an HTTP request, which is then sent to the server via the Internet.

[0989] Input: Input data stored in the device

[0990] Output: JSON formatted data sent to the server

[0991] Step 3:

[0992] The server receives and decodes the JSON-formatted data sent from the device. The received data is then stored in a database. Data analysis algorithms are then run to analyze the data to evaluate the user's health status and lifestyle patterns.

[0993] Input: JSON format data sent to the server

[0994] Output: Analyzed data on the user's health status and lifestyle patterns

[0995] Step 4:

[0996] The server generates individual advice using a generative AI model based on the analysis results. A prompt sentence is generated based on the analyzed data and input to the generative AI model. The generative AI model generates optimal advice, converts it into JSON format, and saves it.

[0997] Input: Analyzed data on the user's health status and lifestyle patterns, and prompts for the generative AI model

[0998] Output: Generated individual advice

[0999] Step 5:

[1000] The server sends the generated advice to the user's device. The advice data is sent in JSON format, and the device receives it.

[1001] Input: JSON format data of the generated individual advice

[1002] Output: Advice data sent to the terminal

[1003] Step 6:

[1004] The device decodes the received advice data and displays it to the user. The user can view the advice provided through the application. If necessary, the navigation function in the physical store is activated, and the user can receive advice on what to buy and what to do in the store.

[1005] Input: Advice data sent to the terminal

[1006] Output: The individual advice displayed to the user

[1007] As an example of how this works, the following prompt sentence is input to the generative AI model:

[1008] "Based on the user's recent data, generate advice like this:

[1009] Today's exercise time: 30 minutes

[1010] Today's meal: Bread, salad

[1011] Today's work hours: 8 hours

[1012] Hobby time today: 2 hours

[1013] Sleep time today: 7 hours

[1014] Today's emotion: happy

[1015] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[1016] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1017] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1018] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1019] [Fourth embodiment]

[1020] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1021] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1023] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1024] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1025] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1027] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1028] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1029] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1031] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1033] The system of this invention allows users to input their daily activity data, which is then analyzed by a server that uses AI to generate and provide personalized advice.

[1034] 1. User data entry

[1035] The user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button. The entered data is saved in real time and sent to the server when the Send button is pressed.

[1036] 2. Sending data from the device to the server

[1037] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, a notification of data transmission completion is displayed to the user.

[1038] 3. Data reception and analysis by the server

[1039] The server receives the activity data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on the timing and content of meals, the frequency of exercise, sleep patterns, etc.

[1040] 4. Generating Advice

[1041] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server may generate specific advice such as "Add 30 minutes of walking every day." This advice is then converted back into an appropriate format and a request is generated to send it to the device.

[1042] 5. Sending and displaying advice to the device

[1043] The advice data generated by the server is sent to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[1044] Specific examples

[1045] Let's say a user enters one week's worth of lifestyle data into an app and sends it to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[1046] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[1047] The processing flow will be explained below.

[1048] Step 1:

[1049] A user launches an application on their smartphone or tablet.

[1050] Step 2:

[1051] The terminal confirms the user's login and displays the diary entry screen.

[1052] Step 3:

[1053] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[1054] Step 4:

[1055] The device saves the entered data in real time and enables the "Send" button once the entry is complete.

[1056] Step 5:

[1057] The user presses the "Send" button.

[1058] Step 6:

[1059] The device converts the input activity data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[1060] Step 7:

[1061] The device sends a request to the server over the Internet.

[1062] Step 8:

[1063] The server receives the activity data sent from the terminal.

[1064] Step 9:

[1065] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[1066] Step 10:

[1067] The server runs analytical algorithms to assess the user's health and lifestyle patterns.

[1068] Step 11:

[1069] The server uses a generative AI model based on the analysis results to generate individual advice.

[1070] Step 12:

[1071] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[1072] Step 13:

[1073] The server sends a request via the Internet to send advice data to the terminal.

[1074] Step 14:

[1075] The terminal receives the advice data transmitted from the server.

[1076] Step 15:

[1077] The terminal generates a notification or screen display for the user of the decoded advice.

[1078] Step 16:

[1079] The user checks the advice displayed on the device and implements it to improve their lifestyle habits.

[1080] Example 1

[1081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1082] In conventional health management systems, users' daily activity data is typically recorded manually, and health managers analyze it and provide advice. However, this method suffers from problems such as inconvenient data entry, delayed analysis, and generalized advice. In particular, it is difficult to provide personalized advice tailored to each user's specific needs, making it difficult to maintain user motivation. Furthermore, there is a lack of means to monitor long-term health trends.

[1083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1084] In this invention, the server includes: a means for a user to input daily activity data; a means for saving the input activity data in real time on the terminal, converting it into an appropriate format, and transmitting it to the server; a means for receiving, decoding, and analyzing the activity data transmitted from the terminal; a means for generating personalized advice using a generative AI model based on the analysis results; and a means for transmitting the generated advice to the user's terminal and notifying or displaying the received advice to the user. This allows the user to easily input daily activity data, quickly and accurately analyze the data, and provide personalized advice. It also makes it possible to accumulate analysis results over the long term and monitor the user's health trends.

[1085] "User" refers to the individual using the system or on whose behalf they enter data and receive advice.

[1086] "Activity data" refers to information about the user's daily activities, such as diet, exercise, work, hobbies, and sleep.

[1087] "Device" refers to a smartphone, tablet, or other portable electronic device used by a user to enter activity data.

[1088] "Server" refers to a remote computer system that receives and analyzes activity data sent from a user's terminal, and generates and sends advice.

[1089] "JSON format" stands for JavaScript Object Notation and refers to a lightweight data exchange format.

[1090] "Generative AI model" refers to a machine learning model that uses artificial intelligence technology to generate personalized advice based on user activity data.

[1091] "Analysis algorithm" refers to a series of calculation procedures used to analyze a user's activity data and evaluate their health status and lifestyle patterns.

[1092] "Advice" refers to specific suggestions or recommendations that the server outputs based on the user's activity data using a generative AI model.

[1093] "Notification" refers to the method used by the device to inform the user of advice or other important information.

[1094] "Long-term storage" refers to storing user activity data and analysis results for a certain period of time or longer and making them continuously available.

[1095] "Health trends" refers to changes and trends in health status and lifestyle patterns that can be seen from long-term accumulated user activity data and analysis results.

[1096] The system of this invention works by having users input their daily activity data, which is then analyzed by a server and used to generate and provide personalized advice using a generative AI model.

[1097] First, the user installs a dedicated application on a device such as a smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen is displayed. On this screen, the user enters the day's meal contents, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once the input is complete, the user presses the "Send" button, and this data is saved in real time and sent to the server in JSON format.

[1098] Next, the device converts the input activity data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the device displays a notification to the user that the data has been transmitted.

[1099] The server receives the activity data sent from the device and decodes it according to JSON format. The decoded data is broken down into individual items and passed to the server's analysis module. The server's analysis module runs an algorithm to analyze the received data and evaluate the user's health status and lifestyle patterns. This analysis is based on, for example, the timing and content of meals, the frequency of exercise, and sleep patterns. The analysis module uses algorithms implemented in Python.

[1100] Based on the analysis results, the server uses a generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking every day." This generated advice is then converted back into an appropriate format (such as JSON) and a request is generated to send to the device.

[1101] Finally, the advice data generated by the server is sent back to the device via the Internet, where it is decoded and a notification or screen display is generated for the user, allowing the user to receive personalized advice at the appropriate time.

[1102] As a concrete example, consider the case where a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generative AI model generates advice such as "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[1103] An example of a prompt sentence to be input into the generative AI model is, "After analyzing the user's exercise data, we found that the average exercise time per week is 30 minutes short. Please generate specific advice."

[1104] In this way, users can receive specific advice based on their health status and lifestyle patterns on a daily basis, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is also possible.

[1105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1106] Step 1:

[1107] The user installs a dedicated application on their smartphone or tablet. This application can be downloaded from the Apple App Store or Google Play Store. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. Once this is complete, the user presses the "Submit" button. The input is the activity data entered by the user. The output is the data saved in real time.

[1108] Step 2:

[1109] The device converts the entered activity data into JSON format. Specifically, a module in the application compiles the data from the user's input fields into a JSON object, which prepares the format for data transmission. The input is the user's activity data. The output is the data converted into JSON format.

[1110] Step 3:

[1111] The terminal generates a request to send data converted to JSON format to the server. The request uses the HTTP protocol and the data is sent to the server over the Internet. As input, there is data in JSON format. As output, an HTTP request is generated and sent to the server.

[1112] Step 4:

[1113] The server receives the HTTP request sent from the device and extracts the included JSON data. A module in the server decodes the JSON data and breaks it down into individual items (meal details, exercise time, work time, etc.). The input is the HTTP request received by the server. The output is the decoded data for each item.

[1114] Step 5:

[1115] The server runs algorithms to analyze the decoded data. The analysis module evaluates the user's health status and lifestyle patterns. For example, algorithms implemented in Python analyze the timing and content of meals, exercise frequency, and sleep patterns. The input is the decoded data for each item. The output is the analysis results.

[1116] Step 6:

[1117] Based on the analysis results, the server uses a generative AI model to generate individual advice. Specifically, the analysis data is input to the generative AI model as a prompt sentence, and the optimal advice is output. The inputs are the analysis results and the prompt sentence. The output is the generated advice.

[1118] Step 7:

[1119] The generated advice is converted back to JSON format and a request is generated to send to the device. The server converts the advice content into the appropriate format and creates an HTTP request. The input is the generated advice. The output is an HTTP request to send to the device.

[1120] Step 8:

[1121] The terminal receives the HTTP request received from the server and decodes the included advice data, thereby generating a notification for the user. The input is the HTTP request received from the server, and the output is the decoded advice data.

[1122] Step 9:

[1123] The device provides the decoded advice content to the user as a notification or a screen display. For example, a push notification function is used to notify the user of specific advice. The input is the decoded advice data. The output is the advice to be notified to the user.

[1124] (Application example 1)

[1125] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1126] In modern society, people face the challenge of understanding their own health status and lifestyle patterns and receiving appropriate advice in their busy daily lives. In particular, providing personalized health advice and exercise plans in physical stores places a heavy burden on staff and is inefficient. Furthermore, there is a lack of ways for users to instantly receive specific, personalized advice based on their own activity data.

[1127] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1128] In this invention, the server includes: a means for a user to input daily activity data; a means for transmitting the input activity data to the server; a means for analyzing the activity data received by the server; a means for generating advice using a generation AI based on the analysis results; a means for transmitting the generated advice to the user's terminal; a means for displaying the advice received by the terminal to the user; and a means for providing health and exercise advice based on the user's activity data at a physical store. This allows users to instantly receive personalized advice based on the analysis results from the server simply by inputting specific data about their daily lives. This also reduces the burden on staff at physical stores and allows for efficient provision of health advice.

[1129] A "user" is an individual who utilizes the system to input their daily activity data and receive personalized advice.

[1130] "Activity data" refers to information about the user's daily life, such as diet, exercise, work, hobbies, and sleep.

[1131] The "server" is a central processing unit that receives and analyzes activity data sent by the user, generates advice using a generation AI, and sends it back to the user.

[1132] "Analysis" refers to the process by which the server evaluates the activity data it receives to reveal the user's health status and lifestyle patterns.

[1133] "Generative AI" refers to an algorithm or system that uses artificial intelligence technology to automatically generate personalized advice based on analysis results.

[1134] "Advice" refers to specific instructions or recommendations provided by the server using generated AI based on the user's activity data.

[1135] A "terminal" is a device (e.g., a smartphone, tablet, etc.) that allows a user to input activity data and receive and display advice sent from the server.

[1136] A "brick and mortar" is a physical location, such as a fitness club or health food store, where users can visit in person to receive health and exercise advice.

[1137] The system of this invention allows users to input their daily activity data, and the server analyzes the data and uses AI to provide personalized advice. Specifically, it works as follows.

[1138] First, the user uses a device such as a smartphone or tablet to input their daily activity data, including what they eat, how much time they spend exercising, working, enjoying their hobbies, and sleeping. Once the data is complete, they press the "send" button. This input data is saved in real time and sent to the server when the send button is pressed.

[1139] The server receives the activity data sent by the user. This data is sent in JSON format, and the server decodes it and breaks it down into individual components. The server then runs an algorithm to analyze the received data and evaluate the user's health and lifestyle patterns. This analysis is based on patterns such as diet, exercise, and sleep.

[1140] Based on the analysis results, the server uses the generative AI model to generate personalized advice. For example, if the user is not getting enough exercise, the server generates specific advice such as "Add 30 minutes of walking each day." This generated advice is then converted back into an appropriate format and sent to the user's device. The advice received by the device is decoded and displayed as a notification or screen display for the user.

[1141] This system is also designed to be used in physical stores, such as fitness clubs and health food stores, where staff can provide personalized health and exercise advice based on the data entered by the user. This allows users to receive specific advice based on their own health status and lifestyle patterns, thereby improving their quality of life.

[1142] The hardware used includes smartphones and tablets, which require an internet connection to send and receive data, and the software used includes Python and the Requests library, which facilitates data transmission, reception, analysis, and display.

[1143] As a concrete example, let's say a user enters one week's worth of lifestyle data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient. Based on this, the generation AI generates advice such as, "You're not getting enough exercise. It would be a good idea to add 30 minutes of walking every day." This advice is sent to the device, which notifies the user. The user can check this and make an effort to add more walking time starting the next day.

[1144] Example prompt sentence:

[1145] "Generate health advice based on user activity data in the following format:

[1146] Diet: Increase your intake of ○○

[1147] Exercise: Add XX minutes of exercise XX times per week

[1148] Rest: Recommended sleep time is x hours

[1149] User data: {'food': 'Salad, Fish', 'exercise': 'Running 30 mins', 'work': '8 hours', 'hobby': 'Reading 1 hour', 'sleep': '7 hours'}

[1150] This system allows users to easily receive personalized health advice by simply entering data about their daily lives, enabling them to effectively manage their health.

[1151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1152] Step 1:

[1153] The user inputs daily activity data.

[1154] Specific operation: The user launches the dedicated app on their smartphone or tablet and enters the details of their meals, exercise time, work time, hobby time, and sleep time into a diary-style input screen. Once the input is complete, they press the "Send" button.

[1155] Input: Daily activity data (meals, exercise, work, hobbies, sleep)

[1156] Output: Activity data converted to JSON format

[1157] Step 2:

[1158] The terminal transmits the input activity data to the server.

[1159] Specific operation: The device converts the input data into JSON format and sends it to the server via the Internet. When the transmission is complete, the device displays a notification to the user that the data has been sent.

[1160] Input: Activity data in JSON format

[1161] Output: Data transmission request, transmission completion notification

[1162] Step 3:

[1163] The server receives the transmitted activity data.

[1164] Specific operation: The server receives the data sent from the device. The received data is decoded from JSON format and broken down into each item (food, exercise, work, hobbies, sleep).

[1165] Input: Data transmission request from the terminal

[1166] Output: Decoded activity data

[1167] Step 4:

[1168] The server analyzes the received data.

[1169] How it works: The server runs an analysis algorithm to assess the user's health and lifestyle based on their activity data, including what they eat, how often they exercise, and their sleep patterns.

[1170] Input: Decoded activity data

[1171] Output: Analysis results (evaluation of health status and lifestyle patterns)

[1172] Step 5:

[1173] The server generates advice using a generative AI based on the analysis results.

[1174] Specific operation: The server inputs the analysis results into the generative AI model and generates personalized health advice. For example, the generative AI may generate specific advice such as "Add 30 minutes of walking every day."

[1175] Input: Analysis results

[1176] Output: Generated advice

[1177] Step 6:

[1178] The server transmits the generated advice to the user's terminal.

[1179] Specific operation: The server converts the generated advice back into JSON format and sends it to the user's device.

[1180] Input: Generated advice

[1181] Output: Advice data in JSON format, data submission request

[1182] Step 7:

[1183] The terminal displays the received advice to the user.

[1184] Specific actions: The device decodes the received advice data and presents the advice to the user as a notification or on-screen display. The user can then confirm the advice and take specific action.

[1185] Input: Advice data in JSON format

[1186] Output: User notification or displayed advice

[1187] Step 8:

[1188] In physical stores, staff will provide support based on users' activity data.

[1189] Specific operation: When a user visits a physical store, staff will refer to the user's activity data through the system and suggest appropriate training plans and health foods.

[1190] Input: User activity data and analysis results

[1191] Output: Specific support and advice from store staff

[1192] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1193] The system of this invention allows users to input their daily activity data, which is then analyzed by a server, which then uses a generation AI and emotion engine to generate and provide personalized advice.

[1194] 1. User data entry

[1195] Users install a dedicated application on their smartphone, tablet, or other device. When the application is launched, a diary-style input screen appears. Here, users enter the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. Once input is complete, they press the "Send" button. The input data is saved in real time and sent to the server when the "Send" button is pressed. The emotion engine also uses the input data, behavioral history, and even voice and facial expression recognition technology to infer and record the user's emotions.

[1196] 2. Sending data from the device to the server

[1197] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. When the transmission is complete, a notification of the completion of data transmission is displayed to the user.

[1198] 3. Data reception and analysis by the server

[1199] The server receives the activity and emotion data sent from the device. The received data is decoded according to a specific format (e.g., JSON format) and broken down into individual items. The server then runs an algorithm to analyze the received data and evaluate the user's health status, lifestyle patterns, and even emotional tendencies.

[1200] 4. Generating Advice

[1201] Based on the analysis results, the server uses a generative AI model to generate individualized advice. Taking the user's emotional state into account also results in more appropriate and personalized advice. For example, if a user is not getting enough exercise and has recently experienced increased stress, the server may generate specific advice such as, "Try adding 30 minutes of walking each day. Also, try to set aside time to relax." This generated advice is then converted back into an appropriate format and a request is generated to send it to the device.

[1202] 5. Sending and displaying advice to the device

[1203] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[1204] Specific examples

[1205] Suppose a user enters one week's lifestyle and emotional data into the app and sends the data to the server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generation AI generates comprehensive advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review it and adjust their lifestyle.

[1206] In this way, users can receive specific daily advice based on their health status, lifestyle patterns, and emotional tendencies, improving their quality of life. Furthermore, by monitoring users' long-term health trends from accumulated data, further health management support is possible.

[1207] The processing flow will be explained below.

[1208] Step 1:

[1209] A user launches an application on their smartphone or tablet.

[1210] Step 2:

[1211] The terminal confirms the user's login and displays the diary entry screen.

[1212] Step 3:

[1213] The user inputs the day's meal contents, exercise time, work time, hobby time, and sleep time into the input fields.

[1214] Step 4:

[1215] The emotion engine uses voice and facial expression recognition technology to infer the user's current emotions, along with emotion analysis based on the user's input and behavioral history.

[1216] Step 5:

[1217] The device stores activity and emotion data in real time and enables the "Send" button once input is complete.

[1218] Step 6:

[1219] The user presses the "Send" button.

[1220] Step 7:

[1221] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a request to send to the server.

[1222] Step 8:

[1223] The device sends a request to the server over the Internet.

[1224] Step 9:

[1225] The server receives the activity data and emotion data transmitted from the terminal.

[1226] Step 10:

[1227] The server checks the format of the received data, decodes it if necessary, and breaks it down into individual items.

[1228] Step 11:

[1229] The server runs analytical algorithms to assess the user's health, lifestyle patterns, and emotional tendencies.

[1230] Step 12:

[1231] The server uses a generative AI model based on the analysis results to generate personalized advice, taking into account the user's emotional state.

[1232] Step 13:

[1233] The server converts the generated advice into an appropriate format and generates a request to send to the terminal.

[1234] Step 14:

[1235] The server sends a request via the Internet to send advice data to the terminal.

[1236] Step 15:

[1237] The terminal receives the advice data transmitted from the server.

[1238] Step 16:

[1239] The terminal decodes the received advice and generates a notification or screen display for the user.

[1240] Step 17:

[1241] The user checks the advice displayed on the device and follows it to improve their lifestyle habits.

[1242] Example 2

[1243] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1244] In modern society, there is a demand for continuous evaluation of individuals' health status and lifestyle patterns and provision of appropriate feedback. However, conventional systems have difficulty providing personalized advice that takes into account the user's emotional state, and they also lack the ability to monitor trends based on long-term data analysis, resulting in problems that prevent sufficient improvement in the user's quality of life.

[1245] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1246] In this invention, the server includes: means for a user to input daily activity data; means for converting the input activity data and emotional data into an appropriate format and transmitting the converted data to the server; means for the server to analyze the received activity data and emotional data and evaluate the user's health condition, lifestyle patterns, and emotional tendencies; means for generating advice using a generation AI based on the analysis results and emotional data; means for converting the generated advice into an appropriate format and transmitting the advice to the user's device; and means for the device to notify or display the received advice to the user. This enables the provision of personalized advice to each user that takes into account their emotional state, and enables long-term trend monitoring of health conditions and lifestyle patterns.

[1247] "Activity data" refers to information such as dietary content, exercise time, work time, hobby time, and sleep time that is recorded in the user's daily life.

[1248] "Emotional data" refers to data that represents the user's emotional state, and includes information inferred or recorded from voice and facial expression recognition technology and behavioral history.

[1249] "Dedicated application" refers to software that users install on their smartphones or tablets to input activity data and emotional data.

[1250] "Server" refers to a computer system that receives and analyzes activity data and emotion data sent from a device, and generates and sends advice to the user using a generative AI model.

[1251] "Analysis algorithm" refers to the method or calculation procedure used by the server to analyze the activity data and emotional data received and evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[1252] "Generative AI model" refers to the artificial intelligence model used by the server to generate personalized advice for users based on the analysis results.

[1253] A "prompt sentence" is a sentence input into a generative AI model, and refers to an instruction sentence that guides the content of the advice generated based on the analysis results.

[1254] "Terminal" refers to an electronic device, such as a smartphone or tablet, used by a user to input data and display generated advice.

[1255] The "JSON format" is a lightweight data exchange format for expressing data structures, and is used when sending and receiving data between a terminal and a server.

[1256] "Notification" refers to the display of a message to convey important information, such as advice, generated by the system to the user.

[1257] The system of this invention works by having users input their daily activity data and emotional data, which is then analyzed by a server, which then uses a generative AI model and emotional engine to generate and provide personalized advice.

[1258] First, the user installs a dedicated application on a device such as a smartphone or tablet. When the application is launched, a diary-style input screen appears. Here, the user enters the day's diet, exercise time, work time, hobby time, and sleep time into the appropriate input fields. After completing the input, the user presses the "Send" button. The emotion engine then uses the input data, behavioral history, and voice and facial expression recognition technology to infer and record the user's emotions.

[1259] The device converts the input activity data and emotion data into an appropriate format (e.g., JSON format) and generates a data transmission request to the server. This request is sent to the server via the Internet. Once the transmission is complete, the user is notified that the data has been transmitted.

[1260] The server receives the activity and emotion data sent from the device, decodes it according to a specific format, breaks it down into individual items, and runs a specified analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies.

[1261] Based on the analysis results, the server uses a generative AI model to generate individualized advice. This process also takes into account the user's emotional data, resulting in more personalized advice. For example, if a user is not getting enough exercise and is experiencing increased stress, the generative AI model might generate advice such as, "Add 30 minutes of walking each day. Also, try to set aside time to relax." This advice is then converted back into an appropriate format (e.g., JSON format) and a request is generated to send it to the device.

[1262] The server sends the generated advice data to the device via the Internet. The device decodes the received advice and generates a notification or screen display for the user, allowing the user to receive personalized advice at the appropriate time.

[1263] Specific examples

[1264] Suppose a user enters one week's lifestyle and emotional data into an app and sends the data to a server. The server analyzes the received data and detects that the average amount of exercise time per week is insufficient, and also recognizes from the user's emotional data that their stress level is rising. Based on this, the generative AI model generates advice such as, "You're not getting enough exercise. Try adding 30 minutes of walking every day. Also, try spending more time on your hobbies to relax." This advice is sent to the device, which then notifies the user. The user can review the advice and adjust their lifestyle.

[1265] Prompt Sentence Examples

[1266] An example of an input prompt for the generative AI model would be, "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice."

[1267] The system provides personalized advice to each user that takes into account their emotional state and enables long-term trend monitoring of health and lifestyle patterns.

[1268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1269] Step 1:

[1270] The user installs a dedicated application on a device such as a smartphone or tablet. When the app is launched, a diary-style input screen appears. The user enters the day's diet, exercise time, work time, hobby time, and sleep time into the input fields. This data constitutes "input." After completing the input, the user presses the "send" button. The emotion engine uses the input data, behavioral history, voice, and facial expressions to infer and record the user's emotions. This operation generates activity data and emotion data, which constitutes "output."

[1271] Step 2:

[1272] The device converts the activity and emotion data entered by the user into an appropriate format (e.g., JSON format). During this conversion process, the data is organized and formatted so that it can be interpreted by the server. This is part of data processing. The converted data becomes the "input," and then a data transmission request is sent to the server via the internet. This request becomes the "output." Once transmission is complete, a notification that the data has been sent is displayed to the user.

[1273] Step 3:

[1274] The server receives activity data and emotion data sent from the device. The received data becomes the "input." When the server receives this data, it first decodes it in JSON format and breaks it down into individual items. The decoded data becomes the "output." Next, it runs an analysis algorithm to evaluate the user's health condition, lifestyle patterns, and emotional tendencies. The results of this analysis also become the "output."

[1275] Step 4:

[1276] Based on the analysis results, the server uses a generative AI model to generate individualized advice. The analysis results and emotional data become the "input." The server inputs a prompt (e.g., "The user has submitted data showing their exercise record and stress level for the past week. Please analyze this and provide appropriate health advice.") into the generative AI model. This prompt becomes the "output." The generative AI model generates individualized advice based on this prompt. The generated advice becomes the "output." This advice is again converted into an appropriate format (e.g., JSON format), and a request is generated to send to the device.

[1277] Step 5:

[1278] The server sends the generated advice data to the terminal via the Internet. This advice data becomes the "input." The terminal decodes the received advice data and generates a notification or screen display for the user. The decoded advice becomes the "output." The user can receive individual advice at the appropriate time. This notification or display serves as a concrete guide for the user to take action.

[1279] (Application example 2)

[1280] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1281] While conventional systems can provide personalized advice based on a user's activity and emotional data, they have the problem of not directly linking this advice to purchasing activities and behavior in physical stores. Furthermore, users have difficulty selecting products and services that reflect their own health status and lifestyle patterns. This results in problems such as insufficient achievement of behavioral change and improvement of the user's quality of life.

[1282] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1283] In this invention, the server includes means for a user to input daily activity data, means for transmitting the input activity data to the server, means for analyzing the activity data received by the server, means for generating advice using a generation AI based on the analysis results, means for transmitting the generated advice to the user's terminal, means for displaying the advice received by the terminal to the user, and means for advising the user on what to purchase and what to do in the store based on the user's activity data and emotion data. This enables the user to be effectively guided in their actions and purchases in a physical store based on their own activity data and emotion data.

[1284] "User" refers to an individual who uses this system to input activity data and emotion data and receives advice from the server.

[1285] "Activity data" refers to information about a user's daily diet, exercise, work, hobbies, and sleep.

[1286] "Emotional data" is data that indicates the user's emotional state and is estimated and recorded using voice and facial expression recognition technology.

[1287] A "dedicated application" refers to software that users install on their devices, such as smartphones, to input activity data and emotional data and communicate with the server.

[1288] "Server" refers to a computer system that receives activity data and emotion data sent by users, analyzes them, and generates and provides advice using generative AI.

[1289] "Generative AI" refers to an artificial intelligence model that analyzes and generates personalized advice based on the data it receives.

[1290] "Terminal" refers to a device (e.g., a smartphone or tablet) on which a user installs a dedicated application and receives and displays advice from a server.

[1291] "Means of advising on purchases and actions" refers to a function that suggests recommended products and actions in physical stores based on the user's activity data and emotional data.

[1292] "In-store navigation" refers to a feature that helps users find the right products and services in a physical store.

[1293] In the system for implementing this invention, a user inputs activity data and emotion data, which is then analyzed by a server, and individualized advice is generated and provided using a generation AI and emotion engine. This will be explained in detail below.

[1294] System Configuration

[1295] This system consists of a user device (such as a smartphone) and a server. Users install a dedicated application on their device and input their daily activity and emotion data. The server receives the data sent by the user, analyzes it, and generates appropriate advice.

[1296] Data entry and submission

[1297] Users enter information about their daily diet, exercise, work, hobbies, and sleep through a dedicated application. Emotional data is also inferred and recorded using voice and facial expression recognition technology (e.g., technology using a smartphone's camera and microphone). This data is converted into JSON format and sent to the server.

[1298] Data analysis and advice generation

[1299] The server receives the transmitted data and runs an analysis algorithm. The analysis algorithm evaluates the user's health condition and lifestyle patterns. It then uses a generative AI model to generate personalized advice. The generative AI model generates optimal advice based on the user's activity data and emotional data. For example, if a lack of exercise and emotional stress are detected, the generated advice would be, "Add 30 minutes of walking every day. Also, try to make time to relax."

[1300] Sending and viewing advice

[1301] The generated advice is sent from the server to the user's device, where it is decoded and presented to the user via notification or on-screen display, allowing the user to receive the most appropriate advice at the right time.

[1302] Application in physical stores

[1303] Furthermore, this system can also be applied to navigating purchases and activities in physical stores. When a user brings the dedicated application with them and visits a physical store, the in-store navigation function is activated. Based on the user's activity and emotional data, the system navigates to recommended ingredients, exercise equipment, relaxation products, and more within the store. It also guides users to special activities (free classes and demonstrations) in specific sections of the store (health foods, fitness, relaxation). This allows users to make more effective purchases in physical stores.

[1304] Examples of prompt statements

[1305] A specific example of a prompt is as follows:

[1306] "Based on the user's recent data, generate advice like this:

[1307] Today's exercise time: 30 minutes

[1308] Today's meal: Bread, salad

[1309] Today's work hours: 8 hours

[1310] Hobby time today: 2 hours

[1311] Sleep time today: 7 hours

[1312] Today's emotion: happy

[1313] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[1314] In this way, users can receive specific advice based on their health status and emotions in a physical store, improving their quality of life.

[1315] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1316] Step 1:

[1317] Users install the dedicated application on their smartphones and launch it. Using a diary-style input screen, users enter data on their daily activities (food, exercise, work, hobbies, sleep) and emotional data. The entered data is temporarily stored on the device.

[1318] Input: User activity data and emotion data

[1319] Output: Input data stored in the device

[1320] Step 2:

[1321] When the user presses the "Send" button, the device converts the input activity and emotion data into JSON format and generates an HTTP request, which is then sent to the server via the Internet.

[1322] Input: Input data stored in the device

[1323] Output: JSON formatted data sent to the server

[1324] Step 3:

[1325] The server receives and decodes the JSON-formatted data sent from the device. The received data is then stored in a database. Data analysis algorithms are then run to analyze the data to evaluate the user's health status and lifestyle patterns.

[1326] Input: JSON format data sent to the server

[1327] Output: Analyzed data on the user's health status and lifestyle patterns

[1328] Step 4:

[1329] The server generates individual advice using a generative AI model based on the analysis results. A prompt sentence is generated based on the analyzed data and input to the generative AI model. The generative AI model generates optimal advice, converts it into JSON format, and saves it.

[1330] Input: Analyzed data on the user's health status and lifestyle patterns, and prompts for the generative AI model

[1331] Output: Generated individual advice

[1332] Step 5:

[1333] The server sends the generated advice to the user's device. The advice data is sent in JSON format, and the device receives it.

[1334] Input: JSON format data of the generated individual advice

[1335] Output: Advice data sent to the terminal

[1336] Step 6:

[1337] The device decodes the received advice data and displays it to the user. The user can view the advice provided through the application. If necessary, the navigation function in the physical store is activated, and the user can receive advice on what to buy and what to do in the store.

[1338] Input: Advice data sent to the terminal

[1339] Output: The individual advice displayed to the user

[1340] As an example of how this works, the following prompt sentence is input to the generative AI model:

[1341] "Based on the user's recent data, generate advice like this:

[1342] Today's exercise time: 30 minutes

[1343] Today's meal: Bread, salad

[1344] Today's work hours: 8 hours

[1345] Hobby time today: 2 hours

[1346] Sleep time today: 7 hours

[1347] Today's emotion: happy

[1348] The generated advice should be useful in the health food, fitness and relaxation sections of the store where the user visits."

[1349] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1350] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1351] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1352] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1353] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1354] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1355] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1356] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1357] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1358] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1359] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1360] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1361] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1362] 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.

[1363] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1364] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1365] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1366] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1367] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1368] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1369] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1370] The following is further disclosed regarding the above embodiment.

[1371] (Claim 1)

[1372] a means for a user to input daily activity data;

[1373] means for transmitting the input activity data to a server;

[1374] means for analyzing the activity data received by the server;

[1375] A means for generating advice using AI based on the analysis results;

[1376] means for transmitting the generated advice to a user terminal;

[1377] means for displaying the advice received by the terminal to the user;

[1378] A system including:

[1379] (Claim 2)

[1380] 10. The system of claim 1, further comprising means for accumulating analytical results over time and monitoring trends.

[1381] (Claim 3)

[1382] 2. The system according to claim 1, further comprising means for evaluating the health condition and lifestyle patterns of the user based on the analysis results.

[1383] "Example 1"

[1384] (Claim 1)

[1385] a means for a user to input daily activity data;

[1386] A means for saving the inputted activity data in real time on the terminal, converting it into an appropriate format, and transmitting it to a server;

[1387] means for receiving, decoding, and analyzing activity data transmitted from the terminal;

[1388] a means for generating personalized advice using a generative AI model based on the analysis results;

[1389] means for transmitting the generated advice to a user's terminal and notifying or displaying the advice received by the terminal to the user;

[1390] A system including:

[1391] (Claim 2)

[1392] 10. The system of claim 1, further comprising means for accumulating analytical results over time and monitoring trends.

[1393] (Claim 3)

[1394] 2. The system according to claim 1, further comprising means for evaluating the health condition and lifestyle patterns of the user based on the analysis results.

[1395] "Application Example 1"

[1396] Claims that combine new parts

[1397] (Claim 1)

[1398] a means for a user to input daily activity data;

[1399] means for transmitting the input activity data to a server;

[1400] means for analyzing the activity data received by the server;

[1401] A means for generating advice using AI based on the analysis results;

[1402] means for transmitting the generated advice to a user terminal;

[1403] means for displaying the advice received by the terminal to the user;

[1404] A means to provide health and exercise advice based on user activity data in physical stores;

[1405] A system including:

[1406] (Claim 2)

[1407] 10. The system of claim 1, further comprising means for accumulating analytical results over time and monitoring trends.

[1408] (Claim 3)

[1409] 2. The system according to claim 1, further comprising means for evaluating the health condition and lifestyle patterns of the user based on the analysis results.

[1410] "Example 2: Combining Emotion Engines"

[1411] (Claim 1)

[1412] a means for a user to input daily activity data;

[1413] means for converting the input activity data and emotion data into an appropriate format and transmitting the converted data to a server;

[1414] A means for analyzing the activity data and emotion data received by the server and evaluating the user's health condition, lifestyle pattern, and emotion tendency;

[1415] A means for generating advice using generative AI based on the analysis results and emotion data;

[1416] means for converting the generated advice into an appropriate format and transmitting the advice to a user's terminal;

[1417] means for notifying or displaying the advice received by the terminal to the user;

[1418] A system including:

[1419] (Claim 2)

[1420] 10. The system of claim 1, further comprising means for accumulating analytical results over time and monitoring trends.

[1421] (Claim 3)

[1422] 2. The system according to claim 1, further comprising means for evaluating the health condition and lifestyle patterns of the user based on the analysis results.

[1423] "Application example 2 when combining emotion engines"

[1424] (Claim 1)

[1425] a means for a user to input daily activity data;

[1426] means for transmitting the input activity data to a server;

[1427] means for analyzing the activity data received by the server;

[1428] A means for generating advice using AI based on the analysis results;

[1429] means for transmitting the generated advice to a user terminal;

[1430] means for displaying the advice received by the terminal to the user;

[1431] A means for providing in-store purchase and behavior advice based on user activity data and emotion data;

[1432] A system including:

[1433] (Claim 2)

[1434] 10. The system of claim 1, further comprising means for accumulating analytical results over time and monitoring trends.

[1435] (Claim 3)

[1436] 2. The system according to claim 1, further comprising means for evaluating the health condition and lifestyle patterns of the user based on the analysis results. [Explanation of symbols]

[1437] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input daily activity data; means for transmitting the input activity data to a server; means for analyzing the activity data received by the server; A means for generating advice using AI based on the analysis results; means for transmitting the generated advice to a user terminal; means for displaying the advice received by the terminal to the user; A system including:

2. 10. The system of claim 1, further comprising means for accumulating analytical results over time and monitoring trends.

3. The system according to claim 1 , further comprising means for evaluating the health condition and lifestyle patterns of the user based on the analysis results.

Images