System

Abstract

A system is provided.SOLUTION: A system comprising: data collection means; data analysis means for analyzing data acquired by the data collection means; notification means for transmitting a notification to a user based on an analysis result analyzed by the data analysis means; and feedback means for tracking a quality of sleep of the user and providing feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While many working adults in modern society desire to ensure sufficient sleep, they face problems such as difficulty falling asleep and poor sleep quality. These problems can lead to chronic fatigue and health problems, significantly reducing work efficiency and quality of life. The present invention aims to improve this situation by providing a system that supports users in going to bed at the optimal time. [Means for solving the problem]

[0005] The present invention provides a system including a data collection means, a data analysis means for analyzing data acquired by the data collection means, a notification means for sending a notification to a user based on the analysis results obtained by the data analysis means, and a feedback means for tracking the user's sleep quality and providing feedback (see claim 1). Specifically, the data collection means is a means for collecting the user's body temperature, air temperature, tone of voice, food intake information, and sleep time (see claim 2). The data analysis means is a means for calculating the user's sleepiness index using the data (see claim 3). The notification means is a means for calculating the timing at which the user is most likely to fall asleep and generating a notification based on the calculation (see claim 4), and the feedback means is a means for providing the user with specific feedback for improving the quality of their sleep based on the user's sleep data (see claim 5).

[0006] "Data collection means" refers to a device or method for collecting a user's body temperature, air temperature, tone of voice, dietary intake information, sleep time, etc.

[0007] "Data analysis means" refers to a device or method for analyzing data acquired by the data collection means and extracting specific patterns or trends.

[0008] The "notification means" refers to a device or method for notifying the user of the optimal timing to go to bed based on the results of the analysis by the data analysis means.

[0009] "Feedback means" refers to a device or method that tracks a user's sleep quality and provides improvement measures or advice based on that data.

[0010] The "drowsiness index" refers to a numerical value or index that indicates the user's level of drowsiness, calculated by the data analysis means.

[0011] "Tracking" refers to the process of continuously collecting data over a period of time and tracking changes. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0020] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, and a feedback means. This allows a user to know the optimal timing for going to bed and obtain improvements for living a healthy life. The system of the present invention is implemented as follows using a mobile terminal and a server.

[0034] 1. Data Collection Methods

[0035] Users input data about their daily lives (e.g., what they eat, how much they sleep, etc.) through an app on their mobile device. This data is acquired by an input means serving as a data collection means.

[0036] The device automatically collects the user's body temperature, ambient temperature, and voice tone using built-in sensors, and also uses wearable devices such as smartwatches to collect the number of times the user turns over in bed and their heart rate.

[0037] 2. Data analysis methods

[0038] The server receives the data sent from the device and stores it in a database, enabling centralized management of data.

[0039] The server performs preprocessing based on the stored data, correcting missing data and removing outliers.

[0040] The server analyzes the accumulated data and uses a machine learning algorithm to calculate the user's sleepiness index in real time, which is calculated by comprehensively analyzing body temperature, air temperature, tone of voice, dietary information, etc.

[0041] 3. Means of notification

[0042] The server calculates the best time for the user to fall asleep based on the sleepiness index, taking into account the ideal wake-up time set by the user.

[0043] The server identifies the optimal time to go to bed, generates a notification message based on that information, and sends it to the device.

[0044] The device displays the received notification message to the user and sends an alert saying "It's almost time to go to bed" at the appropriate time.

[0045] 4. Feedback methods

[0046] The server analyzes the user's past sleep and behavioral data and generates specific feedback to improve sleep quality.

[0047] The device displays this feedback message to the user and suggests improvements, such as advice on how long to avoid caffeine, how to set the temperature in your bedroom, or how to relax before bed.

[0048] Specific examples

[0049] Provide specific examples based on the flow of a day.

[0050] morning:

[0051] The user enters information about breakfast into the app, and the device collects that information.

[0052] noon:

[0053] The device automatically measures the ambient temperature and the user's body temperature, and the user inputs into the app that they had coffee for lunch.

[0054] evening:

[0055] The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[0056] night:

[0057] The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[0058] Before bed:

[0059] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[0060] next morning:

[0061] The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get better sleep if you lower the room temperature a little late at night."

[0062] This allows users to objectively understand their lifestyle and sleep patterns, and learn optimal sleep timing and ways to improve them.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user launches the app on their mobile device and enters data such as food intake and sleep time for that day, which starts the initial data collection.

[0066] Step 2:

[0067] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, ambient temperature, tone of voice, and the number of times they turn over in their sleep.

[0068] Step 3:

[0069] The data collected by the device is sent to the server in real time, and a timestamp is added to the data to clarify the time when each data point occurred.

[0070] Step 4:

[0071] The server stores the received data in a database, where it checks the data for consistency and detects and corrects outliers and missing data.

[0072] Step 5:

[0073] The server preprocesses the stored data, where it is standardized and converted into a format suitable for analysis.

[0074] Step 6:

[0075] The server runs a machine learning algorithm to calculate the user's sleepiness index, using a model that takes variables such as body temperature, air temperature, tone of voice, and food intake information as inputs and outputs a sleepiness level.

[0076] Step 7:

[0077] The server uses the calculated sleepiness index to predict the best time for the user to fall asleep, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[0078] Step 8:

[0079] The server generates a notification message according to the optimal bedtime and transmits it to the terminal, the message including the specific bedtime.

[0080] Step 9:

[0081] After the device receives the notification message, it displays a notification to the user at a specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[0082] Step 10:

[0083] The user then goes to bed and the device again collects nighttime sleep data, including the number of times the user turns over in their sleep and any changes in their environment.

[0084] Step 11:

[0085] The server receives the night's sleep data and assesses the quality of your sleep, including the percentage of deep sleep and the number of times you woke up.

[0086] Step 12:

[0087] The server compares the current data with the previous day's data and generates feedback messages to improve sleep quality, such as specific advice on adjusting the bedroom temperature or timing your caffeine intake.

[0088] Step 13:

[0089] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[0090] Through this series of steps, users can improve their lifestyle and sleep patterns and discover the optimal time to go to bed.

[0091] Example 1

[0092] 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."

[0093] In modern society, busy lifestyles, stress, and irregular life rhythms are causing many people to have poor sleep quality. This can lead to poor daytime performance and potentially health problems. Existing technologies have difficulty comprehensively analyzing individual lifestyle data and proposing effective sleep improvement measures. Therefore, there is a need for a system that can collect and analyze users' daily life data in detail to suggest optimal bedtimes and specific improvement measures.

[0094] 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.

[0095] In this invention, the server includes: a data collection means for the user to input lifestyle data such as dietary content and sleep duration; a data collection means for automatically collecting data such as body temperature, air temperature, tone of voice, number of turns in sleep, and heart rate from the device sensors and the wearable device; a data analysis means for receiving the data acquired by the data collection means and storing it in a database; a data analysis means for preprocessing the data to supplement missing data and remove outliers; a data analysis means for analyzing the data using a machine learning algorithm to calculate the user's sleepiness index; a data analysis means for calculating the user's optimal bedtime timing based on the analysis results; a notification means for generating a notification message and sending it to the user's device; and a feedback means for analyzing the user's past sleep data and behavioral data and providing specific feedback. This allows the user to objectively understand their lifestyle and sleep patterns and learn the optimal sleep timing and specific improvement measures.

[0096] "Data collection means" refers to a means for inputting daily life data such as the user's diet and sleep time, and a means for automatically collecting body temperature, air temperature, tone of voice, number of times the user turns over in bed, heart rate, etc. from the device's sensors or wearable devices.

[0097] The "data analysis means" refers to a means for receiving data acquired by the data collection means and storing it in a database, a means for supplementing missing data and removing outliers as preprocessing, and a means for analyzing data using a machine learning algorithm to calculate the user's sleepiness index and the optimal timing for going to bed.

[0098] The "notification means" is a means for generating a notification message based on the optimal bedtime timing calculated by the data analysis means and transmitting the message to the user's device.

[0099] The "feedback means" is a means for analyzing the user's past sleep data and behavioral data and providing a feedback message including specific measures for improvement.

[0100] A "user" is an individual who inputs lifestyle data such as dietary habits and sleep duration, and receives notifications and feedback.

[0101] A "device" is hardware, such as a mobile terminal or wearable device (e.g., a smartwatch), that collects data from a user and receives notifications.

[0102] A "sensor" is a component built into a device or wearable device that automatically collects data such as body temperature, air temperature, tone of voice, number of times you turn over in your sleep, and heart rate.

[0103] A "wearable device" is an electronic device that can be worn by a user, such as a smartwatch, and is used to measure body temperature, heart rate, exercise volume, etc.

[0104] The "sleepiness index" is an index that indicates how sleepy the user feels, analyzed based on body temperature, air temperature, tone of voice, dietary information, sleep time, etc.

[0105] A "machine learning algorithm" is a computational method that learns from accumulated data and analyzes patterns and trends to make predictions and classify new data.

[0106] The present invention relates to a system equipped with data collection means, data analysis means, notification means, and feedback means, with the aim of enabling users to learn the optimal timing for going to bed and improve their daily habits to lead a healthier life.

[0107] Data collection methods

[0108] Users provide their daily life data by entering it into a mobile app, including the specific meals and times they ate for breakfast, lunch, and dinner, as well as the total amount of sleep they received that day.

[0109] The device uses various built-in sensors and wearable devices such as smartwatches to automatically collect data such as body temperature, air temperature, tone of voice, number of times the user turns over in bed, and heart rate. For example, the smartwatch detects the user's heart rate and number of times the user turns over in bed, the temperature sensor measures the room temperature, and the microphone records the tone of voice.

[0110] Data Analysis Methods

[0111] The server receives the data sent from the device and stores it in a database, allowing for centralized management of user data.

[0112] The server performs preprocessing on the stored data, such as checking data from a heart rate sensor, removing unnaturally high or low values ​​as outliers, and filling in missing meal data with the average value.

[0113] The server applies a machine learning algorithm to the preprocessed data to calculate the user's sleepiness index in real time. This index is calculated based on data such as body temperature, air temperature, tone of voice, food intake, and sleep duration, allowing the user to understand their current level of sleepiness.

[0114] Notification means

[0115] The server then calculates the optimal time for the user to go to bed based on the calculated sleepiness index. This time is calculated taking into account the user's set wake-up time. For example, 10:30 PM may be calculated as the optimal time to go to bed.

[0116] The server stores the optimal timing for going to bed, generates a notification message based on the optimal timing, and transmits the notification message to the terminal.

[0117] The device will display the received notification message to the user and send an alert at the appropriate time saying, "It's almost time to go to bed." For example, a pop-up notification will appear at 9:30 PM and an alarm will sound to encourage the user to go to bed.

[0118] Feedback Methods

[0119] The server analyzes the user's past sleep and behavioral data and generates a feedback message with specific recommendations for improvement.

[0120] The device will display this feedback message to the user and offer suggestions to improve the quality of their sleep, such as "You may get better sleep if you lower the temperature a little late at night," along with a morning alert.

[0121] Specific examples

[0122] Below is a concrete example based on the flow of a day.

[0123] Morning: The user enters information about their breakfast into the app and the device collects it.

[0124] Lunch: The device automatically measures the ambient temperature and the user's body temperature, and the app records that the user had coffee for lunch.

[0125] Evening: The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[0126] Night: The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening and the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[0127] Before bedtime: The server notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[0128] The next morning: The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get a better night's sleep if you lower the room temperature a little late at night."

[0129] Prompt Sentence Examples

[0130] By inputting the following prompt sentence into the generative AI model, a detailed program for the above system can be generated.

[0131] Your goal is to create a program for a system that collects and analyzes daily life data and notifies users of the optimal time to go to bed. This system uses mobile devices and a server to collect, analyze, notify, and provide feedback on data. The following conditions must be met:

[0132] 1. Allow users to enter their meal and sleep schedules into a mobile app.

[0133] 2. The device automatically collects data such as temperature, body temperature, and tone of voice.

[0134] 3. The server analyzes the collected data and calculates the optimal time to go to bed.

[0135] 4. The server generates a notification message and sends it to the terminal.

[0136] 5. The device will display a notification to the user informing them of the best time to go to bed.

[0137] 6. The server generates feedback from past data and suggests improvement measures to the user.

[0138] This allows users to objectively understand their lifestyle habits and sleep patterns, and learn the optimal sleep timing and specific improvement measures.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] A user inputs data about their daily life into an app on their mobile device. The input data includes the contents of meals, the times when they ate, and the amount of sleep they received. This data is saved on the device and later sent to a server. Specifically, the user accesses a specific screen in the app and inputs information such as the contents and times of meals using text boxes and pull-down menus.

[0142] Step 2:

[0143] The device collects data from built-in sensors and wearable devices such as a smartwatch. Specifically, a temperature sensor measures body temperature, a microphone records voice tone, and a smartwatch collects the number of times the user turns over in bed and their heart rate. This data is collected in real time, processed initially, and then stored in the device. For example, the temperature sensor periodically collects body temperature, and the smartwatch records the user's heart rate and the number of times the user turns over in bed.

[0144] Step 3:

[0145] The device sends the collected data to the server. Input data includes body temperature, air temperature, tone of voice, number of times the device turns over in bed, heart rate, etc. The transmission process is carried out over the Internet, and the data is encrypted before being sent. Specifically, the device periodically sends data in packet form to the server.

[0146] Step 4:

[0147] The server stores the received data in a database. This data is later used for analysis. The input data is body temperature, air temperature, tone of voice, number of times the patient turns over in bed, and heart rate, and the data is stored in the corresponding tables in the database. Specifically, the server analyzes the received data, breaks it down into each field, and inserts it into the database.

[0148] Step 5:

[0149] The server preprocesses the stored data. Preprocessing includes filling in missing data and removing outliers. For example, it detects and removes outliers in body temperature data, and fills in missing dietary data with the average value. The input data is the collected body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the clean data after preprocessing.

[0150] Step 6:

[0151] The server uses the preprocessed data to perform analysis using a machine learning algorithm. The input data are preprocessed body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the user's sleepiness index. Specifically, the data is input into a tested machine learning model and the sleepiness index is calculated in real time.

[0152] Step 7:

[0153] The server calculates the optimal time to go to bed for the user based on the sleepiness index. The input data is the sleepiness index and the user's ideal wake-up time, and the output data is the optimal time to go to bed. For example, if a user wants to wake up at 7:00 AM, the server calculates that the optimal time to go to bed is 10:30 PM.

[0154] Step 8:

[0155] The server generates a notification message about the optimal time to go to bed and sends it to the device. The input data is the optimal time to go to bed, and the output data is the notification message. Specifically, it generates a message such as "It's almost time to go to bed" and sends it to the device.

[0156] Step 9:

[0157] The device displays the received notification message to the user and sends an alert at the appropriate time. The input data is the notification message, and the output data is a visual and audible alert. Specifically, a pop-up notification is displayed at 9:30 PM and an alarm sounds to encourage the user to go to bed.

[0158] Step 10:

[0159] The server analyzes the user's past sleep and behavioral data and generates a feedback message containing specific recommendations for improvement. The input data is past data, and the output data is the feedback message. For example, specific advice such as "You may be able to get better sleep if you lower the room temperature late at night" is generated based on the previous week's data.

[0160] Step 11:

[0161] The device displays a feedback message to the user and suggests improvements. The input data is the feedback message, and the output data is a visual suggestion. Specifically, the feedback message is displayed along with the morning alarm, and the suggestion is notified to the user.

[0162] (Application example 1)

[0163] 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."

[0164] Conventional health management systems could suggest optimal bedtimes based on a user's daily life and sleep data, but no system existed that could also manage and link dietary information. In particular, it was difficult to link with food delivery services and suggest meals that took into account the user's health status. As a result, users were unable to receive comprehensive advice on appropriate dietary information and bedtimes, making comprehensive health management difficult.

[0165] 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.

[0166] In this invention, the server includes a data collection means, a data analysis means, a notification means, a feedback means, and a meal suggestion means, which makes it possible to suggest the optimal time to go to bed based on the user's daily life data and sleep data, and to suggest the optimal meal for the user in cooperation with a food delivery service.

[0167] A "data collection means" is a device or process that acquires data related to a user's lifestyle, including, for example, body temperature, air temperature, tone of voice, dietary information, sleep duration, and the like.

[0168] The "data analysis means" is a device or process that analyzes the data acquired by the data collection means and calculates the user's health condition and sleepiness index.

[0169] The "notification means" is a device or process that sends a notification to the user based on the analysis results obtained by the data analysis means.

[0170] The "feedback means" is a device or process that performs analysis based on the user's behavioral data and sleep data and provides the user with feedback such as health improvement measures.

[0171] The "meal suggestion means" is a device or process that suggests meals that are optimal for the user's health condition based on the analysis results obtained by the data analysis means and data linked to the food delivery service.

[0172] The term "system" refers to the entire configuration that operates by combining the aforementioned data collection means, data analysis means, notification means, feedback means, and meal suggestion means.

[0173] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and a diet suggestion means, which allows a user to receive suggestions for optimal bedtime and healthy eating habits.

[0174] Hardware and software used:

[0175] 1. Smartphone: A device for data entry and notifications.

[0176] 2. Server: Stores and analyzes data.

[0177] 3. Wearable devices (e.g., smart watches): measure body temperature and heart rate.

[0178] 4. Food delivery apps: Get and order meals.

[0179] Data collection methods:

[0180] Users enter their daily diet and sleep duration through a smartphone app, and also use a smartwatch to collect data such as body temperature, heart rate, and the number of times they turn over in bed.

[0181] Data analysis methods:

[0182] The server receives data sent from smartphones and smartwatches and stores it in a database. It then preprocesses the data, correcting missing data and removing outliers. The server then uses machine learning algorithms to analyze the data and determine the user's sleepiness index and health condition.

[0183] Notification method:

[0184] Based on the analysis results, the server generates notifications suggesting optimal bedtimes and meals for the user and sends them to their smartphone. Users can receive alerts such as "It's almost time to go to bed" and messages such as "Here's today's healthy menu."

[0185] Feedback methods:

[0186] The server generates feedback based on the user's past data and suggests health improvement measures. The smartphone notifies the user of this feedback and provides advice such as "avoiding eating late at night will improve the quality of your sleep."

[0187] Meal suggestion methods:

[0188] The data analysis method works with food delivery services to suggest optimal meal plans based on the user's health status. For example, the server will make specific meal suggestions such as "We recommend a menu with lots of vegetables for lunch" based on the results of its analysis, and will also display a link to order from the delivery service.

[0189] Examples:

[0190] morning:

[0191] Users enter information about their breakfast into the app, and the smartwatch measures their body temperature and heart rate.

[0192] noon:

[0193] The smartwatch measures the ambient temperature and the user's body temperature, and the user enters their lunch information into the app.

[0194] evening:

[0195] Temperature and body temperature are measured again, and activity levels and tone of voice are also collected.

[0196] night:

[0197] The server analyzes this data, calculates a sleepiness index, suggests healthy menu items, and displays an ordering link in conjunction with a delivery service.

[0198] Before bed:

[0199] A notification appears on your smartphone saying, "It's almost time for bed."

[0200] next morning:

[0201] Providing server-generated feedback, such as advice like "Next time, dim the lights in your bedroom to help you sleep better."

[0202] Example prompts to input to a generative AI model:

[0203] I would like to develop a system that suggests optimal bedtime and healthy meals to users based on their diet, body temperature, heart rate, number of times they turn over in bed, and lifestyle habits. I would like to incorporate this into a food delivery app and have it provide a function that notifies users of health advice in real time. Please tell me the specific content of the notification message and the data analysis method.

[0204] This allows users to conveniently enjoy meals while maintaining a healthy lifestyle.

[0205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0206] Step 1:

[0207] Users use a smartphone app to input their daily diet and sleep schedules. The input data is stored in the smartphone, allowing data on the user's lifestyle to be collected.

[0208] Step 2:

[0209] A wearable device (such as a smartwatch) worn by the user measures biological data such as body temperature, heart rate, and the number of times the user turns over in bed in real time. The measured data is automatically sent to a smartphone, and biological data is collected in this way.

[0210] Step 3:

[0211] The collected data is sent from the smartphone to a server, which receives the data and stores it in a database, enabling centralized management of the data.

[0212] Step 4:

[0213] The server preprocesses the data stored in the database, correcting missing data and removing outliers, and converting it into a format suitable for applying machine learning algorithms. The processed data is then used for analysis.

[0214] Step 5:

[0215] The server uses a machine learning algorithm to calculate the user's sleepiness index in real time from pre-processed data. Input data includes body temperature, air temperature, tone of voice, and food intake information, and the sleepiness index is obtained as output.

[0216] Step 6:

[0217] Based on the analysis results, the server evaluates the user's health condition and sleepiness index, and calculates the optimal time to go to bed. The server also takes into account the ideal wake-up time set by the user. The calculated bedtime is then sent as a notification message.

[0218] Step 7:

[0219] The server uses a meal suggestion algorithm to suggest healthy meals to the user. Based on the results of data analysis and the meal data from the food delivery service, the server selects the optimal meal menu for the user and generates a suggestion message.

[0220] Step 8:

[0221] The server then sends the generated notification message and meal suggestion message to the smartphone, which then displays the received message to the user and sends alerts such as "It's almost time to go to bed" or "Here's today's healthy menu."

[0222] Step 9:

[0223] The server generates feedback based on the user's past data. It analyzes the user's sleep and behavioral data and creates feedback messages that suggest health improvement measures. For example, it includes specific advice such as "Avoiding eating late at night will improve the quality of your sleep."

[0224] Step 10:

[0225] The server then sends the generated feedback message to the smartphone, which then displays it to the user, allowing the user to see specific improvements to their health status and lifestyle habits.

[0226] 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.

[0227] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and an emotion engine. This allows a user to know the optimal time to go to bed and obtain improvement measures that take into account their mental state. The system of the present invention is implemented as follows, using a mobile terminal, an emotion engine, and a server.

[0228] 1. Data Collection Methods

[0229] The user launches the app on their mobile device and inputs data about their daily life (e.g., what they eat, how much sleep they get, etc.), which starts the initial data collection.

[0230] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[0231] The device has a built-in emotion engine that analyzes the user's voice in real time and recognizes emotions from the voice data. This emotion data can be used as an indicator of stress levels and anxiety states.

[0232] 2. Data analysis methods

[0233] The server receives the data sent from the device and stores it in a database, including body temperature, air temperature, tone of voice, feeding information, sleep duration, and emotional data.

[0234] The server preprocesses the stored data, correcting missing data and detecting and removing outliers.

[0235] The server runs a machine learning algorithm to calculate the user's drowsiness index, taking into account emotion data obtained from the emotion engine to improve accuracy.

[0236] 3. Means of notification

[0237] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[0238] The server generates a notification message according to the optimal bedtime and sends it to the terminal, the notification message including the specific bedtime.

[0239] After receiving the notification message, the device displays a notification to the user at the specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[0240] 4. Feedback methods

[0241] The server analyzes the user's past sleep and emotional data and generates specific feedback to improve sleep quality.

[0242] The device displays this feedback message to the user and suggests improvements, such as "meditate before bed to reduce stress," "adjust the temperature in your bedroom," or "time your caffeine intake."

[0243] Specific examples

[0244] Provide specific examples based on the flow of a day.

[0245] morning:

[0246] Users input information about their breakfast into the app, which the device collects. The emotion engine also analyzes the tone of voice obtained from everyday conversations and records emotional data.

[0247] noon:

[0248] The device automatically measures the ambient temperature and the user's body temperature, and the emotion engine determines the stress level from the voice during conversation. The user inputs into the app that they had coffee for lunch.

[0249] evening:

[0250] The device again measures the ambient temperature and the user's body temperature, as well as collecting information such as movement volume and tone of voice. The emotion engine also continues to collect data, recording stress levels and anxiety states.

[0251] night:

[0252] The server receives and analyzes this data. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in drowsiness after drinking coffee to calculate a drowsiness index. Emotional data can also be taken into account to obtain a more accurate drowsiness index.

[0253] Before bed:

[0254] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index and emotional data. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's almost time to go to bed."

[0255] next morning:

[0256] The server compares past and current data and generates feedback messages to improve sleep quality, which the device displays to the user along with a morning alert as "points to improve next time." For example, it provides advice such as "Try meditating to reduce stress" or "You may be able to get better sleep if you lower the room temperature a little late at night."

[0257] Through this series of actions, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[0258] The processing flow will be explained below.

[0259] Step 1:

[0260] The user launches the app on their mobile device and enters data such as the day's food intake and sleep time. The app has a form where users can enter details of the food they ate, the time they ate it, and the amount of sleep they got the previous night.

[0261] Step 2:

[0262] The device uses built-in sensors or connected wearable devices (e.g., smartwatches) to automatically collect data on the user's body temperature, ambient temperature, tone of voice, and the number of times the user turns over in bed. For example, a body temperature sensor measures and records the user's body temperature every hour.

[0263] Step 3:

[0264] The device collects the user's voice in real time, and the emotion engine analyzes the voice data to estimate the user's current emotional state (e.g., stress level, anxiety) by analyzing the voice frequency, volume, intonation, etc.

[0265] Step 4:

[0266] The device sends the collected data (body temperature, air temperature, tone of voice, emotional data, number of turns in sleep) to a server in real time, and the data is time-stamped for easy later analysis.

[0267] Step 5:

[0268] The server receives the data sent from the device and stores it in a database, where it checks the data to ensure consistency and accuracy (e.g., detecting outliers).

[0269] Step 6:

[0270] The server preprocesses the stored data, correcting missing data, removing outliers, normalizing the data, and converting it into a format suitable for analysis.

[0271] Step 7:

[0272] The server uses a machine learning algorithm to calculate the user's drowsiness index, which involves the following process:

[0273] An energy consumption model is constructed from the user's body temperature, air temperature, and food intake information.

[0274] Identify stress and fatigue levels based on tone of voice and emotional data.

[0275] These variables are analyzed comprehensively to calculate a sleepiness index.

[0276] Step 8:

[0277] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the user's ideal wake-up time.

[0278] Step 9:

[0279] The server generates a notification message according to the optimal bedtime and sends it to the terminal, which includes a specific time that is convenient for the user to fall asleep (e.g., 9:30 PM).

[0280] Step 10:

[0281] After the device receives the notification message, it will display a notification to the user at the specified time saying "It's almost time to go to bed," along with an appropriate sound or vibration to help the user acknowledge the notification.

[0282] Step 11:

[0283] The user goes to bed, and the device continues to collect sleep data (such as the number of times the user turns over in their sleep) throughout the night, thereby monitoring changes in body temperature and the ambient temperature during the night.

[0284] Step 12:

[0285] The server receives the nightly sleep data and evaluates the quality of sleep by analyzing the percentage of deep sleep and the number of times you woke up, among other factors, to quantify the quality of sleep.

[0286] Step 13:

[0287] The server compares the current data with the previous day's data and generates specific feedback messages to improve the quality of sleep, including lifestyle improvements (e.g., "Meditate before bed to reduce stress" or "Adjust the temperature in your bedroom").

[0288] Step 14:

[0289] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[0290] Through this series of steps, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[0291] Example 2

[0292] 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."

[0293] In modern society, many people suffer from insufficient sleep or poor quality sleep. This is considered a problem as it reduces health and quality of life. However, there are only a limited number of systems that provide specific measures and timing for improving sleep quality. There is a need for a system that takes into account the user's emotional state and suggests optimal improvement measures.

[0294] 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.

[0295] In this invention, the server includes a data collection means, a data analysis means, a notification means, an emotion analysis means, and a feedback means, which allows the server to collect and analyze the user's lifestyle data and emotion data, and provide feedback to individually optimize bedtime and improve the quality of sleep.

[0296] "Data collection means" refers to means for collecting data about the user's daily life (body temperature, air temperature, tone of voice, dietary information, sleep time, emotional data, etc.).

[0297] The "data analysis means" is a means for analyzing the data acquired by the data collection means and calculating the user's drowsiness index and other indices.

[0298] The "notification means" is a means for notifying the user of the optimal timing for going to bed and other important information based on the results of the analysis by the data analysis means.

[0299] "Emotion analysis means" refers to a means for recognizing and analyzing the user's emotions from collected voice data.

[0300] The "feedback means" is a means for tracking the user's sleep quality and providing specific improvement measures based on the analysis results.

[0301] The "drowsiness index" is an index that quantifies the user's state of drowsiness, and is calculated by the data analysis means.

[0302] The present invention provides a system that collects and analyzes a user's lifestyle and emotional data to provide optimal bedtime timing and measures to improve sleep quality. The system includes a data collection means, a data analysis means, a notification means, an emotional analysis means, and a feedback means.

[0303] System configuration and operation

[0304] Data collection methods

[0305] The user launches the app on their mobile device and manually enters data about their daily life, such as what they eat and how much sleep they get.

[0306] The device uses built-in sensors and connected wearable devices to automatically collect data such as the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[0307] The device uses emotion analysis to analyze the user's tone of voice in real time, extracting and recording emotional data, such as determining stress levels or anxiety levels from the tone of voice.

[0308] Data Analysis Methods

[0309] The server receives data sent from the device (body temperature, air temperature, tone of voice, feeding information, sleep time, emotional data) and stores it in a database.

[0310] The server preprocesses the received data, complements missing values, and detects and removes outliers.

[0311] The server runs a pre-configured machine learning algorithm to calculate the user's drowsiness index, which also takes into account emotional data to improve accuracy.

[0312] Notification means

[0313] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the ideal wake-up time.

[0314] The server generates a notification message and sends it to the terminal. For example, it generates a message saying, "It's a good idea to go to bed at 9:30 PM."

[0315] The terminal displays a notification message at the specified time, alerting the user that "it's almost time to go to bed."

[0316] Feedback Methods

[0317] The server analyzes the user's past sleep data and emotional data to determine any fluctuations.

[0318] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[0319] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[0320] Examples and prompts

[0321] Specific examples

[0322] morning:

[0323] The user inputs their breakfast (e.g., bread and coffee) into the app, the device measures their body temperature, and the emotion engine analyzes and records the emotions from their voice.

[0324] noon:

[0325] The device measures the ambient temperature and the user's body temperature. The user also inputs information about the lunch they had (salad and soup) into the app. The emotion engine analyzes the tone of voice during conversation and evaluates the stress level.

[0326] evening:

[0327] The device again measures the ambient temperature and the user's body temperature, as well as collects information such as activity level and tone of voice, and analyzes emotional data to record stress levels and anxiety states.

[0328] night:

[0329] The server receives and analyzes this data and calculates the user's sleepiness index, taking into account the timing of when body temperature starts to drop in the evening and fluctuations in sleepiness after consuming caffeine.

[0330] Before bed:

[0331] The server calculates the optimal time to go to bed based on the calculated sleepiness index and emotional data, and at 9:30 p.m. the device displays a notification saying, "It's almost time to go to bed."

[0332] next morning:

[0333] The server compares past and current data and generates specific feedback messages, which the device presents to the user along with morning alerts, offering advice such as "Try meditating" or "You might get better sleep if you lower the temperature in your room."

[0334] Prompt Sentence Examples

[0335] "Using your sleep data from the past three days, what is the best time for me to go to bed tonight? Also, please suggest specific improvements I can make to improve the quality of my sleep."

[0336] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0337] Step 1:

[0338] Manual data entry

[0339] Users launch the app on their mobile device and manually enter data about their daily life, such as what they ate, how much sleep they had, etc. Specifically, they record what they had for breakfast, lunch, and dinner, whether they exercised, and when they went to bed.

[0340] Input: User's lifestyle data such as diet, sleep time, and exercise information

[0341] Output: User's daily life data recorded in the mobile device app

[0342] Step 2:

[0343] Automatic collection of sensor data

[0344] The device uses built-in sensors and connected wearable devices to automatically collect the user's body temperature, air temperature, tone of voice, and number of times they turn over in bed.

[0345] For example, a temperature sensor built into the terminal measures the user's body temperature, and a wearable device records the number of times the user turns over in their sleep.

[0346] Input: Body temperature, temperature, tone of voice, number of times turning over in bed, data from connected wearable devices

[0347] Output: Collected vital and environmental data

[0348] Step 3:

[0349] Real-time analysis of sentiment data

[0350] The device uses emotion analysis means to analyze the tone of the user's voice in real time, and extracts and records emotion data.

[0351] For example, analyzing a user's speech to determine stress levels and anxiety states.

[0352] Input: User's voice tone (audio data)

[0353] Output: Analyzed emotional data (stress level, anxiety state, etc.)

[0354] Step 4:

[0355] Data transmission and storage

[0356] The device sends the data collected in steps 1 to 3 to the server.

[0357] The server stores the received data in a database, including body temperature, air temperature, tone of voice, food intake information, sleep duration, and emotional data.

[0358] Input: Collected and analyzed lifestyle data and emotional data

[0359] Output: User data stored in the server database

[0360] Step 5:

[0361] Data Preprocessing

[0362] The server performs preprocessing on the data it receives, complementing missing data and detecting and removing outliers to improve data quality.

[0363] Input: Saved user data (raw)

[0364] Output: Preprocessed and clean data

[0365] Step 6:

[0366] Calculating the sleepiness index

[0367] The server uses the pre-processed data to run a machine learning algorithm to calculate the user's drowsiness index, which includes emotional data, resulting in a more accurate drowsiness index.

[0368] Input: Preprocessed life data and emotion data

[0369] Output: Calculated sleepiness index

[0370] Step 7:

[0371] Predicting optimal bedtime

[0372] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the ideal wake-up time.

[0373] Input: Sleepiness index, emotional data, ideal wake-up time

[0374] Output: Optimal bedtime

[0375] Step 8:

[0376] Generate and send notification messages

[0377] The server generates a notification message based on the optimal bedtime and sends it to the device. For example, it generates a specific message such as "It's best to go to bed at 9:30 pm."

[0378] The terminal displays the received notification message to the user.

[0379] Input: Optimal Bedtime

[0380] Output: A notification message to the user

[0381] Step 9:

[0382] Analyzing past data and generating feedback

[0383] The server analyzes past sleep data and emotional data to determine any fluctuations.

[0384] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[0385] Input: Past sleep data, emotional data

[0386] Output: A specific feedback message

[0387] Step 10:

[0388] View Feedback

[0389] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[0390] Input: Specific feedback message

[0391] Output: Provide feedback to the user

[0392] (Application example 2)

[0393] 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."

[0394] Conventional lifestyle data collection systems lack the functionality to comprehensively support a user's health management and financial management. Furthermore, they have difficulty providing specific feedback that takes into account the user's emotional state and stress level, resulting in insufficient support for lifestyle improvement. To address these issues, the present invention provides a system that comprehensively analyzes a user's lifestyle data and expenditure data and provides health management feedback and financial management feedback.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a data analysis means for analyzing the data acquired by the data collection means, a notification means for sending a notification to the user based on the analysis results obtained by the data analysis means, and a feedback means for providing health management feedback based on the user's lifestyle data and expenditure data. This makes it possible to comprehensively analyze the user's health condition and expenditure pattern and provide specific and optimal feedback.

[0396] The "data collection means" is a means for collecting various data from the user and the surrounding environment using sensors and input devices.

[0397] The "data analysis means" is a means for processing and analyzing the collected data and calculating indicators and patterns related to the user's condition and lifestyle habits.

[0398] The "notification means" is a means for providing advice and information on appropriate lifestyle habits to the user by notifying the user based on the analysis results.

[0399] The "feedback means" is a means for providing appropriate feedback to the user based on the analysis results and supporting the improvement of lifestyle habits.

[0400] "Lifestyle data" refers to information about the user's daily life, including body temperature, air temperature, tone of voice, dietary intake information, sleep time, amount of exercise, heart rate, stress level, and the like.

[0401] "Expense Data" is information about a user's financial transactions, including purchase history and expense details.

[0402] The "health index" is a numerical representation of the user's health condition based on collected lifestyle data, and is an index that is useful for improving lifestyle habits.

[0403] "Spending patterns" are an analysis of a user's financial behavior trends based on collected spending data, and are useful information for improving financial management.

[0404] The present invention relates to a system that collects and analyzes a user's lifestyle data and expenditure data, and provides health management feedback and financial management feedback based on the collected data. The specific configuration and processing method of the system are described below.

[0405] System Configuration

[0406] 1. Data collection methods:

[0407] Hardware: Smartphones, wearable devices (e.g., Apple Watch, Fitbit, etc.)

[0408] Software: Smartphone app (iOS, Android), wearable device linkage app

[0409] Function: Collects data on the user's daily life (body temperature, temperature, tone of voice, dietary intake, sleep time, exercise, heart rate, stress level, etc.) and expenditure data. Users enter their lifestyle data through a smartphone app, and the wearable device collects biometric data in real time.

[0410] 2. Data analysis methods:

[0411] Hardware: Cloud server (e.g. AWS, GCP)

[0412] Software: Databases (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., TensorFlow, Keras), natural language processing libraries (e.g., NLTK, spaCy)

[0413] Function: Cleanses collected data (removes outliers and fills in missing data) and uses machine learning algorithms to analyze users' health indicators and spending patterns.

[0414] 3. Means of notification:

[0415] Hardware: Smartphone

[0416] Software: Smartphone app with notification function

[0417] Function: Based on the results of data analysis, the app provides users with lifestyle advice and information at the appropriate time. It pushes notifications such as "Choose healthy snacks when shopping in the evening" at specific times.

[0418] 4. Feedback methods:

[0419] Hardware: Smartphone, cloud server

[0420] Software: Smartphone app, analysis software on cloud server

[0421] Function: Based on the analysis results, the app provides appropriate feedback to users, such as specific advice such as "Spend more on healthy foods next time you go shopping."

[0422] A concrete example of the processing flow

[0423] In the morning, the user enters their food intake information into a smartphone app, and the wearable device records their heart rate and body temperature in real time. In the afternoon, the wearable device measures their stress level and exercise volume, and in the evening, the data is sent to a cloud server. The cloud server analyzes the data and calculates the user's health index and spending patterns. Based on the analysis results, a notification is pushed to the smartphone before the evening shopping trip, urging the user to "pick a healthy snack." The next morning, feedback is provided based on past data.

[0424] Prompt Sentence Examples

[0425] "It uses the user's dietary and spending data to generate feedback to optimize the balance between health and finances."

[0426] With the above system configuration and processing method, the present invention can comprehensively analyze a user's health condition and expenditure patterns and provide specific and optimal feedback.

[0427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0428] Step 1:

[0429] Users launch a smartphone app and input their dietary intake, exercise, and expenditure information. This input data is collected through a data collection tool. Wearable devices also collect real-time biometric information (body temperature, heart rate, stress level, etc.) and send it to the smartphone.

[0430] Input: Eating information, exercise information, expenditure information, body temperature, heart rate, stress level

[0431] Output: Collected life and biometric data

[0432] Step 2:

[0433] The terminal sends the data received from the wearable device to a cloud server, which then receives the data. The data is stored in a database and preprocessed, such as removing outliers and correcting missing data.

[0434] Input: Collected lifestyle and biometric data

[0435] Output: Cleansed data

[0436] Step 3:

[0437] The server uses the cleansed data to run machine learning algorithms to calculate the user's health index and spending patterns. The analysis is performed using machine learning libraries (e.g., TensorFlow, Keras).

[0438] Input: Cleansed data

[0439] Output: Health index, expenditure patterns

[0440] Step 4:

[0441] The server generates optimal feedback messages for each user based on the analysis results, and inputs prompts into a generative AI model (e.g., GPT-3) to generate specific advice and feedback.

[0442] Input: Health Index, Expenditure Pattern

[0443] Output: Feedback message (example prompt: "Generate feedback based on the user's dietary and expenditure data to optimize their health and financial balance.")

[0444] Step 5:

[0445] A notification message is created to notify the user of the feedback message generated by the server at a specific timing, and is sent to the smartphone terminal.

[0446] Input: Feedback message

[0447] Output: Notification message

[0448] Step 6:

[0449] The smartphone device will present the received notification message to the user as a push notification. For example, a notification such as "Choose healthy snacks when shopping in the evening" will be displayed at a specific time.

[0450] Input: Notification message

[0451] Output: Display a notification to the user

[0452] Step 7:

[0453] The next morning, the server compares and analyzes past data, generates new feedback based on the user's condition, and sends it to the smartphone. The user receives the feedback as "points for improvement next time" along with the morning alert.

[0454] Input: Historical and current data

[0455] Output: New feedback message

[0456] 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.

[0457] 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.

[0458] 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.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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."

[0472] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, and a feedback means. This allows a user to know the optimal timing for going to bed and obtain improvements for living a healthy life. The system of the present invention is implemented as follows using a mobile terminal and a server.

[0473] 1. Data Collection Methods

[0474] Users input data about their daily lives (e.g., what they eat, how much they sleep, etc.) through an app on their mobile device. This data is acquired by an input means serving as a data collection means.

[0475] The device automatically collects the user's body temperature, ambient temperature, and voice tone using built-in sensors, and also uses wearable devices such as smartwatches to collect the number of times the user turns over in bed and their heart rate.

[0476] 2. Data analysis methods

[0477] The server receives the data sent from the device and stores it in a database, enabling centralized management of data.

[0478] The server performs preprocessing based on the stored data, correcting missing data and removing outliers.

[0479] The server analyzes the accumulated data and uses a machine learning algorithm to calculate the user's sleepiness index in real time, which is calculated by comprehensively analyzing body temperature, air temperature, tone of voice, dietary information, etc.

[0480] 3. Means of notification

[0481] The server calculates the best time for the user to fall asleep based on the sleepiness index, taking into account the ideal wake-up time set by the user.

[0482] The server identifies the optimal time to go to bed, generates a notification message based on that information, and sends it to the device.

[0483] The device displays the received notification message to the user and sends an alert saying "It's almost time to go to bed" at the appropriate time.

[0484] 4. Feedback methods

[0485] The server analyzes the user's past sleep and behavioral data and generates specific feedback to improve sleep quality.

[0486] The device displays this feedback message to the user and suggests improvements, such as advice on how long to avoid caffeine, how to set the temperature in your bedroom, or how to relax before bed.

[0487] Specific examples

[0488] Provide specific examples based on the flow of a day.

[0489] morning:

[0490] The user enters information about breakfast into the app, and the device collects that information.

[0491] noon:

[0492] The device automatically measures the ambient temperature and the user's body temperature, and the user inputs into the app that they had coffee for lunch.

[0493] evening:

[0494] The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[0495] night:

[0496] The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[0497] Before bed:

[0498] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[0499] next morning:

[0500] The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get better sleep if you lower the room temperature a little late at night."

[0501] This allows users to objectively understand their lifestyle and sleep patterns, and learn optimal sleep timing and ways to improve them.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The user launches the app on their mobile device and enters data such as food intake and sleep time for that day, which starts the initial data collection.

[0505] Step 2:

[0506] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, ambient temperature, tone of voice, and the number of times they turn over in their sleep.

[0507] Step 3:

[0508] The data collected by the device is sent to the server in real time, and a timestamp is added to the data to clarify the time when each data point occurred.

[0509] Step 4:

[0510] The server stores the received data in a database, where it checks the data for consistency and detects and corrects outliers and missing data.

[0511] Step 5:

[0512] The server preprocesses the stored data, where it is standardized and converted into a format suitable for analysis.

[0513] Step 6:

[0514] The server runs a machine learning algorithm to calculate the user's sleepiness index, using a model that takes variables such as body temperature, air temperature, tone of voice, and food intake information as inputs and outputs a sleepiness level.

[0515] Step 7:

[0516] The server uses the calculated sleepiness index to predict the best time for the user to fall asleep, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[0517] Step 8:

[0518] The server generates a notification message according to the optimal bedtime and transmits it to the terminal, the message including the specific bedtime.

[0519] Step 9:

[0520] After the device receives the notification message, it displays a notification to the user at a specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[0521] Step 10:

[0522] The user then goes to bed and the device again collects nighttime sleep data, including the number of times the user turns over in their sleep and any changes in their environment.

[0523] Step 11:

[0524] The server receives the night's sleep data and assesses the quality of your sleep, including the percentage of deep sleep and the number of times you woke up.

[0525] Step 12:

[0526] The server compares the current data with the previous day's data and generates feedback messages to improve sleep quality, such as specific advice on adjusting the bedroom temperature or timing your caffeine intake.

[0527] Step 13:

[0528] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[0529] Through this series of steps, users can improve their lifestyle and sleep patterns and discover the optimal time to go to bed.

[0530] Example 1

[0531] 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."

[0532] In modern society, busy lifestyles, stress, and irregular life rhythms are causing many people to have poor sleep quality. This can lead to poor daytime performance and potentially health problems. Existing technologies have difficulty comprehensively analyzing individual lifestyle data and proposing effective sleep improvement measures. Therefore, there is a need for a system that can collect and analyze users' daily life data in detail to suggest optimal bedtimes and specific improvement measures.

[0533] 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.

[0534] In this invention, the server includes: a data collection means for the user to input lifestyle data such as dietary content and sleep duration; a data collection means for automatically collecting data such as body temperature, air temperature, tone of voice, number of turns in sleep, and heart rate from the device sensors and the wearable device; a data analysis means for receiving the data acquired by the data collection means and storing it in a database; a data analysis means for preprocessing the data to supplement missing data and remove outliers; a data analysis means for analyzing the data using a machine learning algorithm to calculate the user's sleepiness index; a data analysis means for calculating the user's optimal bedtime timing based on the analysis results; a notification means for generating a notification message and sending it to the user's device; and a feedback means for analyzing the user's past sleep data and behavioral data and providing specific feedback. This allows the user to objectively understand their lifestyle and sleep patterns and learn the optimal sleep timing and specific improvement measures.

[0535] "Data collection means" refers to a means for inputting daily life data such as the user's diet and sleep time, and a means for automatically collecting body temperature, air temperature, tone of voice, number of times the user turns over in bed, heart rate, etc. from the device's sensors or wearable devices.

[0536] The "data analysis means" refers to a means for receiving data acquired by the data collection means and storing it in a database, a means for supplementing missing data and removing outliers as preprocessing, and a means for analyzing data using a machine learning algorithm to calculate the user's sleepiness index and the optimal timing for going to bed.

[0537] The "notification means" is a means for generating a notification message based on the optimal bedtime timing calculated by the data analysis means and transmitting the message to the user's device.

[0538] The "feedback means" is a means for analyzing the user's past sleep data and behavioral data and providing a feedback message including specific measures for improvement.

[0539] A "user" is an individual who inputs lifestyle data such as dietary habits and sleep duration, and receives notifications and feedback.

[0540] A "device" is hardware, such as a mobile terminal or wearable device (e.g., a smartwatch), that collects data from a user and receives notifications.

[0541] A "sensor" is a component built into a device or wearable device that automatically collects data such as body temperature, air temperature, tone of voice, number of times you turn over in your sleep, and heart rate.

[0542] A "wearable device" is an electronic device that can be worn by a user, such as a smartwatch, and is used to measure body temperature, heart rate, exercise volume, etc.

[0543] The "sleepiness index" is an index that indicates how sleepy the user feels, analyzed based on body temperature, air temperature, tone of voice, dietary information, sleep time, etc.

[0544] A "machine learning algorithm" is a computational method that learns from accumulated data and analyzes patterns and trends to make predictions and classify new data.

[0545] The present invention relates to a system equipped with data collection means, data analysis means, notification means, and feedback means, with the aim of enabling users to learn the optimal timing for going to bed and improve their daily habits to lead a healthier life.

[0546] Data collection methods

[0547] Users provide their daily life data by entering it into a mobile app, including the specific meals and times they ate for breakfast, lunch, and dinner, as well as the total amount of sleep they received that day.

[0548] The device uses various built-in sensors and wearable devices such as smartwatches to automatically collect data such as body temperature, air temperature, tone of voice, number of times the user turns over in bed, and heart rate. For example, the smartwatch detects the user's heart rate and number of times the user turns over in bed, the temperature sensor measures the room temperature, and the microphone records the tone of voice.

[0549] Data Analysis Methods

[0550] The server receives the data sent from the device and stores it in a database, allowing for centralized management of user data.

[0551] The server performs preprocessing on the stored data, such as checking data from a heart rate sensor, removing unnaturally high or low values ​​as outliers, and filling in missing meal data with the average value.

[0552] The server applies a machine learning algorithm to the preprocessed data to calculate the user's sleepiness index in real time. This index is calculated based on data such as body temperature, air temperature, tone of voice, food intake, and sleep duration, allowing the user to understand their current level of sleepiness.

[0553] Notification means

[0554] The server then calculates the optimal time for the user to go to bed based on the calculated sleepiness index. This time is calculated taking into account the user's set wake-up time. For example, 10:30 PM may be calculated as the optimal time to go to bed.

[0555] The server stores the optimal timing for going to bed, generates a notification message based on the optimal timing, and transmits the notification message to the terminal.

[0556] The device will display the received notification message to the user and send an alert at the appropriate time saying, "It's almost time to go to bed." For example, a pop-up notification will appear at 9:30 PM and an alarm will sound to encourage the user to go to bed.

[0557] Feedback Methods

[0558] The server analyzes the user's past sleep and behavioral data and generates a feedback message with specific recommendations for improvement.

[0559] The device will display this feedback message to the user and offer suggestions to improve the quality of their sleep, such as "You may get better sleep if you lower the temperature a little late at night," along with a morning alert.

[0560] Specific examples

[0561] Below is a concrete example based on the flow of a day.

[0562] Morning: The user enters information about their breakfast into the app and the device collects it.

[0563] Lunch: The device automatically measures the ambient temperature and the user's body temperature, and the app records that the user had coffee for lunch.

[0564] Evening: The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[0565] Night: The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening and the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[0566] Before bedtime: The server notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[0567] The next morning: The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get a better night's sleep if you lower the room temperature a little late at night."

[0568] Prompt Sentence Examples

[0569] By inputting the following prompt sentence into the generative AI model, a detailed program for the above system can be generated.

[0570] Your goal is to create a program for a system that collects and analyzes daily life data and notifies users of the optimal time to go to bed. This system uses mobile devices and a server to collect, analyze, notify, and provide feedback on data. The following conditions must be met:

[0571] 1. Allow users to enter their meal and sleep schedules into a mobile app.

[0572] 2. The device automatically collects data such as temperature, body temperature, and tone of voice.

[0573] 3. The server analyzes the collected data and calculates the optimal time to go to bed.

[0574] 4. The server generates a notification message and sends it to the terminal.

[0575] 5. The device will display a notification to the user informing them of the best time to go to bed.

[0576] 6. The server generates feedback from past data and suggests improvement measures to the user.

[0577] This allows users to objectively understand their lifestyle habits and sleep patterns, and learn the optimal sleep timing and specific improvement measures.

[0578] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0579] Step 1:

[0580] A user inputs data about their daily life into an app on their mobile device. The input data includes the contents of meals, the times when they ate, and the amount of sleep they received. This data is saved on the device and later sent to a server. Specifically, the user accesses a specific screen in the app and inputs information such as the contents and times of meals using text boxes and pull-down menus.

[0581] Step 2:

[0582] The device collects data from built-in sensors and wearable devices such as a smartwatch. Specifically, a temperature sensor measures body temperature, a microphone records voice tone, and a smartwatch collects the number of times the user turns over in bed and their heart rate. This data is collected in real time, processed initially, and then stored in the device. For example, the temperature sensor periodically collects body temperature, and the smartwatch records the user's heart rate and the number of times the user turns over in bed.

[0583] Step 3:

[0584] The device sends the collected data to the server. Input data includes body temperature, air temperature, tone of voice, number of times the device turns over in bed, heart rate, etc. The transmission process is carried out over the Internet, and the data is encrypted before being sent. Specifically, the device periodically sends data in packet form to the server.

[0585] Step 4:

[0586] The server stores the received data in a database. This data is later used for analysis. The input data is body temperature, air temperature, tone of voice, number of times the patient turns over in bed, and heart rate, and the data is stored in the corresponding tables in the database. Specifically, the server analyzes the received data, breaks it down into each field, and inserts it into the database.

[0587] Step 5:

[0588] The server preprocesses the stored data. Preprocessing includes filling in missing data and removing outliers. For example, it detects and removes outliers in body temperature data, and fills in missing dietary data with the average value. The input data is the collected body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the clean data after preprocessing.

[0589] Step 6:

[0590] The server uses the preprocessed data to perform analysis using a machine learning algorithm. The input data are preprocessed body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the user's sleepiness index. Specifically, the data is input into a tested machine learning model and the sleepiness index is calculated in real time.

[0591] Step 7:

[0592] The server calculates the optimal time to go to bed for the user based on the sleepiness index. The input data is the sleepiness index and the user's ideal wake-up time, and the output data is the optimal time to go to bed. For example, if a user wants to wake up at 7:00 AM, the server calculates that the optimal time to go to bed is 10:30 PM.

[0593] Step 8:

[0594] The server generates a notification message about the optimal time to go to bed and sends it to the device. The input data is the optimal time to go to bed, and the output data is the notification message. Specifically, it generates a message such as "It's almost time to go to bed" and sends it to the device.

[0595] Step 9:

[0596] The device displays the received notification message to the user and sends an alert at the appropriate time. The input data is the notification message, and the output data is a visual and audible alert. Specifically, a pop-up notification is displayed at 9:30 PM and an alarm sounds to encourage the user to go to bed.

[0597] Step 10:

[0598] The server analyzes the user's past sleep and behavioral data and generates a feedback message containing specific recommendations for improvement. The input data is past data, and the output data is the feedback message. For example, specific advice such as "You may be able to get better sleep if you lower the room temperature late at night" is generated based on the previous week's data.

[0599] Step 11:

[0600] The device displays a feedback message to the user and suggests improvements. The input data is the feedback message, and the output data is a visual suggestion. Specifically, the feedback message is displayed along with the morning alarm, and the suggestion is notified to the user.

[0601] (Application example 1)

[0602] 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."

[0603] Conventional health management systems could suggest optimal bedtimes based on a user's daily life and sleep data, but no system existed that could also manage and link dietary information. In particular, it was difficult to link with food delivery services and suggest meals that took into account the user's health status. As a result, users were unable to receive comprehensive advice on appropriate dietary information and bedtimes, making comprehensive health management difficult.

[0604] 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.

[0605] In this invention, the server includes a data collection means, a data analysis means, a notification means, a feedback means, and a meal suggestion means, which makes it possible to suggest the optimal time to go to bed based on the user's daily life data and sleep data, and to suggest the optimal meal for the user in cooperation with a food delivery service.

[0606] A "data collection means" is a device or process that acquires data related to a user's lifestyle, including, for example, body temperature, air temperature, tone of voice, dietary information, sleep duration, and the like.

[0607] The "data analysis means" is a device or process that analyzes the data acquired by the data collection means and calculates the user's health condition and sleepiness index.

[0608] The "notification means" is a device or process that sends a notification to the user based on the analysis results obtained by the data analysis means.

[0609] The "feedback means" is a device or process that performs analysis based on the user's behavioral data and sleep data and provides the user with feedback such as health improvement measures.

[0610] The "meal suggestion means" is a device or process that suggests meals that are optimal for the user's health condition based on the analysis results obtained by the data analysis means and data linked to the food delivery service.

[0611] The term "system" refers to the entire configuration that operates by combining the aforementioned data collection means, data analysis means, notification means, feedback means, and meal suggestion means.

[0612] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and a diet suggestion means, which allows a user to receive suggestions for optimal bedtime and healthy eating habits.

[0613] Hardware and software used:

[0614] 1. Smartphone: A device for data entry and notifications.

[0615] 2. Server: Stores and analyzes data.

[0616] 3. Wearable devices (e.g., smart watches): measure body temperature and heart rate.

[0617] 4. Food delivery apps: Get and order meals.

[0618] Data collection methods:

[0619] Users enter their daily diet and sleep duration through a smartphone app, and also use a smartwatch to collect data such as body temperature, heart rate, and the number of times they turn over in bed.

[0620] Data analysis methods:

[0621] The server receives data sent from smartphones and smartwatches and stores it in a database. It then preprocesses the data, correcting missing data and removing outliers. The server then uses machine learning algorithms to analyze the data and determine the user's sleepiness index and health condition.

[0622] Notification method:

[0623] Based on the analysis results, the server generates notifications suggesting optimal bedtimes and meals for the user and sends them to their smartphone. Users can receive alerts such as "It's almost time to go to bed" and messages such as "Here's today's healthy menu."

[0624] Feedback methods:

[0625] The server generates feedback based on the user's past data and suggests health improvement measures. The smartphone notifies the user of this feedback and provides advice such as "avoiding eating late at night will improve the quality of your sleep."

[0626] Meal suggestion methods:

[0627] The data analysis method works with food delivery services to suggest optimal meal plans based on the user's health status. For example, the server will make specific meal suggestions such as "We recommend a menu with lots of vegetables for lunch" based on the results of its analysis, and will also display a link to order from the delivery service.

[0628] Examples:

[0629] morning:

[0630] Users enter information about their breakfast into the app, and the smartwatch measures their body temperature and heart rate.

[0631] noon:

[0632] The smartwatch measures the ambient temperature and the user's body temperature, and the user enters their lunch information into the app.

[0633] evening:

[0634] Temperature and body temperature are measured again, and activity levels and tone of voice are also collected.

[0635] night:

[0636] The server analyzes this data, calculates a sleepiness index, suggests healthy menu items, and displays an ordering link in conjunction with a delivery service.

[0637] Before bed:

[0638] A notification appears on your smartphone saying, "It's almost time for bed."

[0639] next morning:

[0640] Providing server-generated feedback, such as advice like "Next time, dim the lights in your bedroom to help you sleep better."

[0641] Example prompts to input to a generative AI model:

[0642] I would like to develop a system that suggests optimal bedtime and healthy meals to users based on their diet, body temperature, heart rate, number of times they turn over in bed, and lifestyle habits. I would like to incorporate this into a food delivery app and have it provide a function that notifies users of health advice in real time. Please tell me the specific content of the notification message and the data analysis method.

[0643] This allows users to conveniently enjoy meals while maintaining a healthy lifestyle.

[0644] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0645] Step 1:

[0646] Users use a smartphone app to input their daily diet and sleep schedules. The input data is stored in the smartphone, allowing data on the user's lifestyle to be collected.

[0647] Step 2:

[0648] A wearable device (such as a smartwatch) worn by the user measures biological data such as body temperature, heart rate, and the number of times the user turns over in bed in real time. The measured data is automatically sent to a smartphone, and biological data is collected in this way.

[0649] Step 3:

[0650] The collected data is sent from the smartphone to a server, which receives the data and stores it in a database, enabling centralized management of the data.

[0651] Step 4:

[0652] The server preprocesses the data stored in the database, correcting missing data and removing outliers, and converting it into a format suitable for applying machine learning algorithms. The processed data is then used for analysis.

[0653] Step 5:

[0654] The server uses a machine learning algorithm to calculate the user's sleepiness index in real time from pre-processed data. Input data includes body temperature, air temperature, tone of voice, and food intake information, and the sleepiness index is obtained as output.

[0655] Step 6:

[0656] Based on the analysis results, the server evaluates the user's health condition and sleepiness index, and calculates the optimal time to go to bed. The server also takes into account the ideal wake-up time set by the user. The calculated bedtime is then sent as a notification message.

[0657] Step 7:

[0658] The server uses a meal suggestion algorithm to suggest healthy meals to the user. Based on the results of data analysis and the meal data from the food delivery service, the server selects the optimal meal menu for the user and generates a suggestion message.

[0659] Step 8:

[0660] The server then sends the generated notification message and meal suggestion message to the smartphone, which then displays the received message to the user and sends alerts such as "It's almost time to go to bed" or "Here's today's healthy menu."

[0661] Step 9:

[0662] The server generates feedback based on the user's past data. It analyzes the user's sleep and behavioral data and creates feedback messages that suggest health improvement measures. For example, it includes specific advice such as "Avoiding eating late at night will improve the quality of your sleep."

[0663] Step 10:

[0664] The server then sends the generated feedback message to the smartphone, which then displays it to the user, allowing the user to see specific improvements to their health status and lifestyle habits.

[0665] 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.

[0666] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and an emotion engine. This allows a user to know the optimal time to go to bed and obtain improvement measures that take into account their mental state. The system of the present invention is implemented as follows, using a mobile terminal, an emotion engine, and a server.

[0667] 1. Data Collection Methods

[0668] The user launches the app on their mobile device and inputs data about their daily life (e.g., what they eat, how much sleep they get, etc.), which starts the initial data collection.

[0669] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[0670] The device has a built-in emotion engine that analyzes the user's voice in real time and recognizes emotions from the voice data. This emotion data can be used as an indicator of stress levels and anxiety states.

[0671] 2. Data analysis methods

[0672] The server receives the data sent from the device and stores it in a database, including body temperature, air temperature, tone of voice, feeding information, sleep duration, and emotional data.

[0673] The server preprocesses the stored data, correcting missing data and detecting and removing outliers.

[0674] The server runs a machine learning algorithm to calculate the user's drowsiness index, taking into account emotion data obtained from the emotion engine to improve accuracy.

[0675] 3. Means of notification

[0676] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[0677] The server generates a notification message according to the optimal bedtime and sends it to the terminal, the notification message including the specific bedtime.

[0678] After receiving the notification message, the device displays a notification to the user at the specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[0679] 4. Feedback methods

[0680] The server analyzes the user's past sleep and emotional data and generates specific feedback to improve sleep quality.

[0681] The device displays this feedback message to the user and suggests improvements, such as "meditate before bed to reduce stress," "adjust the temperature in your bedroom," or "time your caffeine intake."

[0682] Specific examples

[0683] Provide specific examples based on the flow of a day.

[0684] morning:

[0685] Users input information about their breakfast into the app, which the device collects. The emotion engine also analyzes the tone of voice obtained from everyday conversations and records emotional data.

[0686] noon:

[0687] The device automatically measures the ambient temperature and the user's body temperature, and the emotion engine determines the stress level from the voice during conversation. The user inputs into the app that they had coffee for lunch.

[0688] evening:

[0689] The device again measures the ambient temperature and the user's body temperature, as well as collecting information such as movement volume and tone of voice. The emotion engine also continues to collect data, recording stress levels and anxiety states.

[0690] night:

[0691] The server receives and analyzes this data. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in drowsiness after drinking coffee to calculate a drowsiness index. Emotional data can also be taken into account to obtain a more accurate drowsiness index.

[0692] Before bed:

[0693] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index and emotional data. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's almost time to go to bed."

[0694] next morning:

[0695] The server compares past and current data and generates feedback messages to improve sleep quality, which the device displays to the user along with a morning alert as "points to improve next time." For example, it provides advice such as "Try meditating to reduce stress" or "You may be able to get better sleep if you lower the room temperature a little late at night."

[0696] Through this series of actions, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The user launches the app on their mobile device and enters data such as the day's food intake and sleep time. The app has a form where users can enter details of the food they ate, the time they ate it, and the amount of sleep they got the previous night.

[0700] Step 2:

[0701] The device uses built-in sensors or connected wearable devices (e.g., smartwatches) to automatically collect data on the user's body temperature, ambient temperature, tone of voice, and the number of times the user turns over in bed. For example, a body temperature sensor measures and records the user's body temperature every hour.

[0702] Step 3:

[0703] The device collects the user's voice in real time, and the emotion engine analyzes the voice data to estimate the user's current emotional state (e.g., stress level, anxiety) by analyzing the voice frequency, volume, intonation, etc.

[0704] Step 4:

[0705] The device sends the collected data (body temperature, air temperature, tone of voice, emotional data, number of turns in sleep) to a server in real time, and the data is time-stamped for easy later analysis.

[0706] Step 5:

[0707] The server receives the data sent from the device and stores it in a database, where it checks the data to ensure consistency and accuracy (e.g., detecting outliers).

[0708] Step 6:

[0709] The server preprocesses the stored data, correcting missing data, removing outliers, normalizing the data, and converting it into a format suitable for analysis.

[0710] Step 7:

[0711] The server uses a machine learning algorithm to calculate the user's drowsiness index, which involves the following process:

[0712] An energy consumption model is constructed from the user's body temperature, air temperature, and food intake information.

[0713] Identify stress and fatigue levels based on tone of voice and emotional data.

[0714] These variables are analyzed comprehensively to calculate a sleepiness index.

[0715] Step 8:

[0716] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the user's ideal wake-up time.

[0717] Step 9:

[0718] The server generates a notification message according to the optimal bedtime and sends it to the terminal, which includes a specific time that is convenient for the user to fall asleep (e.g., 9:30 PM).

[0719] Step 10:

[0720] After the device receives the notification message, it will display a notification to the user at the specified time saying "It's almost time to go to bed," along with an appropriate sound or vibration to help the user acknowledge the notification.

[0721] Step 11:

[0722] The user goes to bed, and the device continues to collect sleep data (such as the number of times the user turns over in their sleep) throughout the night, thereby monitoring changes in body temperature and the ambient temperature during the night.

[0723] Step 12:

[0724] The server receives the nightly sleep data and evaluates the quality of sleep by analyzing the percentage of deep sleep and the number of times you woke up, among other factors, to quantify the quality of sleep.

[0725] Step 13:

[0726] The server compares the current data with the previous day's data and generates specific feedback messages to improve the quality of sleep, including lifestyle improvements (e.g., "Meditate before bed to reduce stress" or "Adjust the temperature in your bedroom").

[0727] Step 14:

[0728] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[0729] Through this series of steps, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[0730] Example 2

[0731] 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."

[0732] In modern society, many people suffer from insufficient sleep or poor quality sleep. This is considered a problem as it reduces health and quality of life. However, there are only a limited number of systems that provide specific measures and timing for improving sleep quality. There is a need for a system that takes into account the user's emotional state and suggests optimal improvement measures.

[0733] 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.

[0734] In this invention, the server includes a data collection means, a data analysis means, a notification means, an emotion analysis means, and a feedback means, which allows the server to collect and analyze the user's lifestyle data and emotion data, and provide feedback to individually optimize bedtime and improve the quality of sleep.

[0735] "Data collection means" refers to means for collecting data about the user's daily life (body temperature, air temperature, tone of voice, dietary information, sleep time, emotional data, etc.).

[0736] The "data analysis means" is a means for analyzing the data acquired by the data collection means and calculating the user's drowsiness index and other indices.

[0737] The "notification means" is a means for notifying the user of the optimal timing for going to bed and other important information based on the results of the analysis by the data analysis means.

[0738] "Emotion analysis means" refers to a means for recognizing and analyzing the user's emotions from collected voice data.

[0739] The "feedback means" is a means for tracking the user's sleep quality and providing specific improvement measures based on the analysis results.

[0740] The "drowsiness index" is an index that quantifies the user's state of drowsiness, and is calculated by the data analysis means.

[0741] The present invention provides a system that collects and analyzes a user's lifestyle and emotional data to provide optimal bedtime timing and measures to improve sleep quality. The system includes a data collection means, a data analysis means, a notification means, an emotional analysis means, and a feedback means.

[0742] System configuration and operation

[0743] Data collection methods

[0744] The user launches the app on their mobile device and manually enters data about their daily life, such as what they eat and how much sleep they get.

[0745] The device uses built-in sensors and connected wearable devices to automatically collect data such as the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[0746] The device uses emotion analysis to analyze the user's tone of voice in real time, extracting and recording emotional data, such as determining stress levels or anxiety levels from the tone of voice.

[0747] Data Analysis Methods

[0748] The server receives data sent from the device (body temperature, air temperature, tone of voice, feeding information, sleep time, emotional data) and stores it in a database.

[0749] The server preprocesses the received data, complements missing values, and detects and removes outliers.

[0750] The server runs a pre-configured machine learning algorithm to calculate the user's drowsiness index, which also takes into account emotional data to improve accuracy.

[0751] Notification means

[0752] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the ideal wake-up time.

[0753] The server generates a notification message and sends it to the terminal. For example, it generates a message saying, "It's a good idea to go to bed at 9:30 PM."

[0754] The terminal displays a notification message at the specified time, alerting the user that "it's almost time to go to bed."

[0755] Feedback Methods

[0756] The server analyzes the user's past sleep data and emotional data to determine any fluctuations.

[0757] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[0758] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[0759] Examples and prompts

[0760] Specific examples

[0761] morning:

[0762] The user inputs their breakfast (e.g., bread and coffee) into the app, the device measures their body temperature, and the emotion engine analyzes and records the emotions from their voice.

[0763] noon:

[0764] The device measures the ambient temperature and the user's body temperature. The user also inputs information about the lunch they had (salad and soup) into the app. The emotion engine analyzes the tone of voice during conversation and evaluates the stress level.

[0765] evening:

[0766] The device again measures the ambient temperature and the user's body temperature, as well as collects information such as activity level and tone of voice, and analyzes emotional data to record stress levels and anxiety states.

[0767] night:

[0768] The server receives and analyzes this data and calculates the user's sleepiness index, taking into account the timing of when body temperature starts to drop in the evening and fluctuations in sleepiness after consuming caffeine.

[0769] Before bed:

[0770] The server calculates the optimal time to go to bed based on the calculated sleepiness index and emotional data, and at 9:30 p.m. the device displays a notification saying, "It's almost time to go to bed."

[0771] next morning:

[0772] The server compares past and current data and generates specific feedback messages, which the device presents to the user along with morning alerts, offering advice such as "Try meditating" or "You might get better sleep if you lower the temperature in your room."

[0773] Prompt Sentence Examples

[0774] "Using your sleep data from the past three days, what is the best time for me to go to bed tonight? Also, please suggest specific improvements I can make to improve the quality of my sleep."

[0775] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0776] Step 1:

[0777] Manual data entry

[0778] Users launch the app on their mobile device and manually enter data about their daily life, such as what they ate, how much sleep they had, etc. Specifically, they record what they had for breakfast, lunch, and dinner, whether they exercised, and when they went to bed.

[0779] Input: User's lifestyle data such as diet, sleep time, and exercise information

[0780] Output: User's daily life data recorded in the mobile device app

[0781] Step 2:

[0782] Automatic collection of sensor data

[0783] The device uses built-in sensors and connected wearable devices to automatically collect the user's body temperature, air temperature, tone of voice, and number of times they turn over in bed.

[0784] For example, a temperature sensor built into the terminal measures the user's body temperature, and a wearable device records the number of times the user turns over in their sleep.

[0785] Input: Body temperature, temperature, tone of voice, number of times turning over in bed, data from connected wearable devices

[0786] Output: Collected vital and environmental data

[0787] Step 3:

[0788] Real-time analysis of sentiment data

[0789] The device uses emotion analysis means to analyze the tone of the user's voice in real time, and extracts and records emotion data.

[0790] For example, analyzing a user's speech to determine stress levels and anxiety states.

[0791] Input: User's voice tone (audio data)

[0792] Output: Analyzed emotional data (stress level, anxiety state, etc.)

[0793] Step 4:

[0794] Data transmission and storage

[0795] The device sends the data collected in steps 1 to 3 to the server.

[0796] The server stores the received data in a database, including body temperature, air temperature, tone of voice, food intake information, sleep duration, and emotional data.

[0797] Input: Collected and analyzed lifestyle data and emotional data

[0798] Output: User data stored in the server database

[0799] Step 5:

[0800] Data Preprocessing

[0801] The server performs preprocessing on the data it receives, complementing missing data and detecting and removing outliers to improve data quality.

[0802] Input: Saved user data (raw)

[0803] Output: Preprocessed and clean data

[0804] Step 6:

[0805] Calculating the sleepiness index

[0806] The server uses the pre-processed data to run a machine learning algorithm to calculate the user's drowsiness index, which includes emotional data, resulting in a more accurate drowsiness index.

[0807] Input: Preprocessed life data and emotion data

[0808] Output: Calculated sleepiness index

[0809] Step 7:

[0810] Predicting optimal bedtime

[0811] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the ideal wake-up time.

[0812] Input: Sleepiness index, emotional data, ideal wake-up time

[0813] Output: Optimal bedtime

[0814] Step 8:

[0815] Generate and send notification messages

[0816] The server generates a notification message based on the optimal bedtime and sends it to the device. For example, it generates a specific message such as "It's best to go to bed at 9:30 pm."

[0817] The terminal displays the received notification message to the user.

[0818] Input: Optimal Bedtime

[0819] Output: A notification message to the user

[0820] Step 9:

[0821] Analyzing past data and generating feedback

[0822] The server analyzes past sleep data and emotional data to determine any fluctuations.

[0823] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[0824] Input: Past sleep data, emotional data

[0825] Output: A specific feedback message

[0826] Step 10:

[0827] View Feedback

[0828] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[0829] Input: Specific feedback message

[0830] Output: Provide feedback to the user

[0831] (Application example 2)

[0832] 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."

[0833] Conventional lifestyle data collection systems lack the functionality to comprehensively support a user's health management and financial management. Furthermore, they have difficulty providing specific feedback that takes into account the user's emotional state and stress level, resulting in insufficient support for lifestyle improvement. To address these issues, the present invention provides a system that comprehensively analyzes a user's lifestyle data and expenditure data and provides health management feedback and financial management feedback.

[0834] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a data analysis means for analyzing the data acquired by the data collection means, a notification means for sending a notification to the user based on the analysis results obtained by the data analysis means, and a feedback means for providing health management feedback based on the user's lifestyle data and expenditure data. This makes it possible to comprehensively analyze the user's health condition and expenditure pattern and provide specific and optimal feedback.

[0835] The "data collection means" is a means for collecting various data from the user and the surrounding environment using sensors and input devices.

[0836] The "data analysis means" is a means for processing and analyzing the collected data and calculating indicators and patterns related to the user's condition and lifestyle habits.

[0837] The "notification means" is a means for providing advice and information on appropriate lifestyle habits to the user by notifying the user based on the analysis results.

[0838] The "feedback means" is a means for providing appropriate feedback to the user based on the analysis results and supporting the improvement of lifestyle habits.

[0839] "Lifestyle data" refers to information about the user's daily life, including body temperature, air temperature, tone of voice, dietary intake information, sleep time, amount of exercise, heart rate, stress level, and the like.

[0840] "Expense Data" is information about a user's financial transactions, including purchase history and expense details.

[0841] The "health index" is a numerical representation of the user's health condition based on collected lifestyle data, and is an index that is useful for improving lifestyle habits.

[0842] "Spending patterns" are an analysis of a user's financial behavior trends based on collected spending data, and are useful information for improving financial management.

[0843] The present invention relates to a system that collects and analyzes a user's lifestyle data and expenditure data, and provides health management feedback and financial management feedback based on the collected data. The specific configuration and processing method of the system are described below.

[0844] System Configuration

[0845] 1. Data collection methods:

[0846] Hardware: Smartphones, wearable devices (e.g., Apple Watch, Fitbit, etc.)

[0847] Software: Smartphone app (iOS, Android), wearable device linkage app

[0848] Function: Collects data on the user's daily life (body temperature, temperature, tone of voice, dietary intake, sleep time, exercise, heart rate, stress level, etc.) and expenditure data. Users enter their lifestyle data through a smartphone app, and the wearable device collects biometric data in real time.

[0849] 2. Data analysis methods:

[0850] Hardware: Cloud server (e.g. AWS, GCP)

[0851] Software: Databases (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., TensorFlow, Keras), natural language processing libraries (e.g., NLTK, spaCy)

[0852] Function: Cleanses collected data (removes outliers and fills in missing data) and uses machine learning algorithms to analyze users' health indicators and spending patterns.

[0853] 3. Means of notification:

[0854] Hardware: Smartphone

[0855] Software: Smartphone app with notification function

[0856] Function: Based on the results of data analysis, the app provides users with lifestyle advice and information at the appropriate time. It pushes notifications such as "Choose healthy snacks when shopping in the evening" at specific times.

[0857] 4. Feedback methods:

[0858] Hardware: Smartphone, cloud server

[0859] Software: Smartphone app, analysis software on cloud server

[0860] Function: Based on the analysis results, the app provides appropriate feedback to users, such as specific advice such as "Spend more on healthy foods next time you go shopping."

[0861] A concrete example of the processing flow

[0862] In the morning, the user enters their food intake information into a smartphone app, and the wearable device records their heart rate and body temperature in real time. In the afternoon, the wearable device measures their stress level and exercise volume, and in the evening, the data is sent to a cloud server. The cloud server analyzes the data and calculates the user's health index and spending patterns. Based on the analysis results, a notification is pushed to the smartphone before the evening shopping trip, urging the user to "pick a healthy snack." The next morning, feedback is provided based on past data.

[0863] Prompt Sentence Examples

[0864] "It uses the user's dietary and spending data to generate feedback to optimize the balance between health and finances."

[0865] With the above system configuration and processing method, the present invention can comprehensively analyze a user's health condition and expenditure patterns and provide specific and optimal feedback.

[0866] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0867] Step 1:

[0868] Users launch a smartphone app and input their dietary intake, exercise, and expenditure information. This input data is collected through a data collection tool. Wearable devices also collect real-time biometric information (body temperature, heart rate, stress level, etc.) and send it to the smartphone.

[0869] Input: Eating information, exercise information, expenditure information, body temperature, heart rate, stress level

[0870] Output: Collected life and biometric data

[0871] Step 2:

[0872] The terminal sends the data received from the wearable device to a cloud server, which then receives the data. The data is stored in a database and preprocessed, such as removing outliers and correcting missing data.

[0873] Input: Collected lifestyle and biometric data

[0874] Output: Cleansed data

[0875] Step 3:

[0876] The server uses the cleansed data to run machine learning algorithms to calculate the user's health index and spending patterns. The analysis is performed using machine learning libraries (e.g., TensorFlow, Keras).

[0877] Input: Cleansed data

[0878] Output: Health index, expenditure patterns

[0879] Step 4:

[0880] The server generates optimal feedback messages for each user based on the analysis results, and inputs prompts into a generative AI model (e.g., GPT-3) to generate specific advice and feedback.

[0881] Input: Health Index, Expenditure Pattern

[0882] Output: Feedback message (example prompt: "Generate feedback based on the user's dietary and expenditure data to optimize their health and financial balance.")

[0883] Step 5:

[0884] A notification message is created to notify the user of the feedback message generated by the server at a specific timing, and is sent to the smartphone terminal.

[0885] Input: Feedback message

[0886] Output: Notification message

[0887] Step 6:

[0888] The smartphone device will present the received notification message to the user as a push notification. For example, a notification such as "Choose healthy snacks when shopping in the evening" will be displayed at a specific time.

[0889] Input: Notification message

[0890] Output: Display a notification to the user

[0891] Step 7:

[0892] The next morning, the server compares and analyzes past data, generates new feedback based on the user's condition, and sends it to the smartphone. The user receives the feedback as "points for improvement next time" along with the morning alert.

[0893] Input: Historical and current data

[0894] Output: New feedback message

[0895] 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.

[0896] 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.

[0897] 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.

[0898] [Third embodiment]

[0899] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0900] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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).

[0905] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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."

[0911] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, and a feedback means. This allows a user to know the optimal timing for going to bed and obtain improvements for living a healthy life. The system of the present invention is implemented as follows using a mobile terminal and a server.

[0912] 1. Data Collection Methods

[0913] Users input data about their daily lives (e.g., what they eat, how much they sleep, etc.) through an app on their mobile device. This data is acquired by an input means serving as a data collection means.

[0914] The device automatically collects the user's body temperature, ambient temperature, and voice tone using built-in sensors, and also uses wearable devices such as smartwatches to collect the number of times the user turns over in bed and their heart rate.

[0915] 2. Data analysis methods

[0916] The server receives the data sent from the device and stores it in a database, enabling centralized management of data.

[0917] The server performs preprocessing based on the stored data, correcting missing data and removing outliers.

[0918] The server analyzes the accumulated data and uses a machine learning algorithm to calculate the user's sleepiness index in real time, which is calculated by comprehensively analyzing body temperature, air temperature, tone of voice, dietary information, etc.

[0919] 3. Means of notification

[0920] The server calculates the best time for the user to fall asleep based on the sleepiness index, taking into account the ideal wake-up time set by the user.

[0921] The server identifies the optimal time to go to bed, generates a notification message based on that information, and sends it to the device.

[0922] The device displays the received notification message to the user and sends an alert saying "It's almost time to go to bed" at the appropriate time.

[0923] 4. Feedback methods

[0924] The server analyzes the user's past sleep and behavioral data and generates specific feedback to improve sleep quality.

[0925] The device displays this feedback message to the user and suggests improvements, such as advice on how long to avoid caffeine, how to set the temperature in your bedroom, or how to relax before bed.

[0926] Specific examples

[0927] Provide specific examples based on the flow of a day.

[0928] morning:

[0929] The user enters information about breakfast into the app, and the device collects that information.

[0930] noon:

[0931] The device automatically measures the ambient temperature and the user's body temperature, and the user inputs into the app that they had coffee for lunch.

[0932] evening:

[0933] The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[0934] night:

[0935] The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[0936] Before bed:

[0937] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[0938] next morning:

[0939] The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get better sleep if you lower the room temperature a little late at night."

[0940] This allows users to objectively understand their lifestyle and sleep patterns, and learn optimal sleep timing and ways to improve them.

[0941] The processing flow will be explained below.

[0942] Step 1:

[0943] The user launches the app on their mobile device and enters data such as food intake and sleep time for that day, which starts the initial data collection.

[0944] Step 2:

[0945] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, ambient temperature, tone of voice, and the number of times they turn over in their sleep.

[0946] Step 3:

[0947] The data collected by the device is sent to the server in real time, and a timestamp is added to the data to clarify the time when each data point occurred.

[0948] Step 4:

[0949] The server stores the received data in a database, where it checks the data for consistency and detects and corrects outliers and missing data.

[0950] Step 5:

[0951] The server preprocesses the stored data, where it is standardized and converted into a format suitable for analysis.

[0952] Step 6:

[0953] The server runs a machine learning algorithm to calculate the user's sleepiness index, using a model that takes variables such as body temperature, air temperature, tone of voice, and food intake information as inputs and outputs a sleepiness level.

[0954] Step 7:

[0955] The server uses the calculated sleepiness index to predict the best time for the user to fall asleep, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[0956] Step 8:

[0957] The server generates a notification message according to the optimal bedtime and transmits it to the terminal, the message including the specific bedtime.

[0958] Step 9:

[0959] After the device receives the notification message, it displays a notification to the user at a specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[0960] Step 10:

[0961] The user then goes to bed and the device again collects nighttime sleep data, including the number of times the user turns over in their sleep and any changes in their environment.

[0962] Step 11:

[0963] The server receives the night's sleep data and assesses the quality of your sleep, including the percentage of deep sleep and the number of times you woke up.

[0964] Step 12:

[0965] The server compares the current data with the previous day's data and generates feedback messages to improve sleep quality, such as specific advice on adjusting the bedroom temperature or timing your caffeine intake.

[0966] Step 13:

[0967] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[0968] Through this series of steps, users can improve their lifestyle and sleep patterns and discover the optimal time to go to bed.

[0969] Example 1

[0970] 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."

[0971] In modern society, busy lifestyles, stress, and irregular life rhythms are causing many people to have poor sleep quality. This can lead to poor daytime performance and potentially health problems. Existing technologies have difficulty comprehensively analyzing individual lifestyle data and proposing effective sleep improvement measures. Therefore, there is a need for a system that can collect and analyze users' daily life data in detail to suggest optimal bedtimes and specific improvement measures.

[0972] 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.

[0973] In this invention, the server includes: a data collection means for the user to input lifestyle data such as dietary content and sleep duration; a data collection means for automatically collecting data such as body temperature, air temperature, tone of voice, number of turns in sleep, and heart rate from the device sensors and the wearable device; a data analysis means for receiving the data acquired by the data collection means and storing it in a database; a data analysis means for preprocessing the data to supplement missing data and remove outliers; a data analysis means for analyzing the data using a machine learning algorithm to calculate the user's sleepiness index; a data analysis means for calculating the user's optimal bedtime timing based on the analysis results; a notification means for generating a notification message and sending it to the user's device; and a feedback means for analyzing the user's past sleep data and behavioral data and providing specific feedback. This allows the user to objectively understand their lifestyle and sleep patterns and learn the optimal sleep timing and specific improvement measures.

[0974] "Data collection means" refers to a means for inputting daily life data such as the user's diet and sleep time, and a means for automatically collecting body temperature, air temperature, tone of voice, number of times the user turns over in bed, heart rate, etc. from the device's sensors or wearable devices.

[0975] The "data analysis means" refers to a means for receiving data acquired by the data collection means and storing it in a database, a means for supplementing missing data and removing outliers as preprocessing, and a means for analyzing data using a machine learning algorithm to calculate the user's sleepiness index and the optimal timing for going to bed.

[0976] The "notification means" is a means for generating a notification message based on the optimal bedtime timing calculated by the data analysis means and transmitting the message to the user's device.

[0977] The "feedback means" is a means for analyzing the user's past sleep data and behavioral data and providing a feedback message including specific measures for improvement.

[0978] A "user" is an individual who inputs lifestyle data such as dietary habits and sleep duration, and receives notifications and feedback.

[0979] A "device" is hardware, such as a mobile terminal or wearable device (e.g., a smartwatch), that collects data from a user and receives notifications.

[0980] A "sensor" is a component built into a device or wearable device that automatically collects data such as body temperature, air temperature, tone of voice, number of times you turn over in your sleep, and heart rate.

[0981] A "wearable device" is an electronic device that can be worn by a user, such as a smartwatch, and is used to measure body temperature, heart rate, exercise volume, etc.

[0982] The "sleepiness index" is an index that indicates how sleepy the user feels, analyzed based on body temperature, air temperature, tone of voice, dietary information, sleep time, etc.

[0983] A "machine learning algorithm" is a computational method that learns from accumulated data and analyzes patterns and trends to make predictions and classify new data.

[0984] The present invention relates to a system equipped with data collection means, data analysis means, notification means, and feedback means, with the aim of enabling users to learn the optimal timing for going to bed and improve their daily habits to lead a healthier life.

[0985] Data collection methods

[0986] Users provide their daily life data by entering it into a mobile app, including the specific meals and times they ate for breakfast, lunch, and dinner, as well as the total amount of sleep they received that day.

[0987] The device uses various built-in sensors and wearable devices such as smartwatches to automatically collect data such as body temperature, air temperature, tone of voice, number of times the user turns over in bed, and heart rate. For example, the smartwatch detects the user's heart rate and number of times the user turns over in bed, the temperature sensor measures the room temperature, and the microphone records the tone of voice.

[0988] Data Analysis Methods

[0989] The server receives the data sent from the device and stores it in a database, allowing for centralized management of user data.

[0990] The server performs preprocessing on the stored data, such as checking data from a heart rate sensor, removing unnaturally high or low values ​​as outliers, and filling in missing meal data with the average value.

[0991] The server applies a machine learning algorithm to the preprocessed data to calculate the user's sleepiness index in real time. This index is calculated based on data such as body temperature, air temperature, tone of voice, food intake, and sleep duration, allowing the user to understand their current level of sleepiness.

[0992] Notification means

[0993] The server then calculates the optimal time for the user to go to bed based on the calculated sleepiness index. This time is calculated taking into account the user's set wake-up time. For example, 10:30 PM may be calculated as the optimal time to go to bed.

[0994] The server stores the optimal timing for going to bed, generates a notification message based on the optimal timing, and transmits the notification message to the terminal.

[0995] The device will display the received notification message to the user and send an alert at the appropriate time saying, "It's almost time to go to bed." For example, a pop-up notification will appear at 9:30 PM and an alarm will sound to encourage the user to go to bed.

[0996] Feedback Methods

[0997] The server analyzes the user's past sleep and behavioral data and generates a feedback message with specific recommendations for improvement.

[0998] The device will display this feedback message to the user and offer suggestions to improve the quality of their sleep, such as "You may get better sleep if you lower the temperature a little late at night," along with a morning alert.

[0999] Specific examples

[1000] Below is a concrete example based on the flow of a day.

[1001] Morning: The user enters information about their breakfast into the app and the device collects it.

[1002] Lunch: The device automatically measures the ambient temperature and the user's body temperature, and the app records that the user had coffee for lunch.

[1003] Evening: The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[1004] Night: The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening and the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[1005] Before bedtime: The server notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[1006] The next morning: The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get a better night's sleep if you lower the room temperature a little late at night."

[1007] Prompt Sentence Examples

[1008] By inputting the following prompt sentence into the generative AI model, a detailed program for the above system can be generated.

[1009] Your goal is to create a program for a system that collects and analyzes daily life data and notifies users of the optimal time to go to bed. This system uses mobile devices and a server to collect, analyze, notify, and provide feedback on data. The following conditions must be met:

[1010] 1. Allow users to enter their meal and sleep schedules into a mobile app.

[1011] 2. The device automatically collects data such as temperature, body temperature, and tone of voice.

[1012] 3. The server analyzes the collected data and calculates the optimal time to go to bed.

[1013] 4. The server generates a notification message and sends it to the terminal.

[1014] 5. The device will display a notification to the user informing them of the best time to go to bed.

[1015] 6. The server generates feedback from past data and suggests improvement measures to the user.

[1016] This allows users to objectively understand their lifestyle habits and sleep patterns, and learn the optimal sleep timing and specific improvement measures.

[1017] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1018] Step 1:

[1019] A user inputs data about their daily life into an app on their mobile device. The input data includes the contents of meals, the times when they ate, and the amount of sleep they received. This data is saved on the device and later sent to a server. Specifically, the user accesses a specific screen in the app and inputs information such as the contents and times of meals using text boxes and pull-down menus.

[1020] Step 2:

[1021] The device collects data from built-in sensors and wearable devices such as a smartwatch. Specifically, a temperature sensor measures body temperature, a microphone records voice tone, and a smartwatch collects the number of times the user turns over in bed and their heart rate. This data is collected in real time, processed initially, and then stored in the device. For example, the temperature sensor periodically collects body temperature, and the smartwatch records the user's heart rate and the number of times the user turns over in bed.

[1022] Step 3:

[1023] The device sends the collected data to the server. Input data includes body temperature, air temperature, tone of voice, number of times the device turns over in bed, heart rate, etc. The transmission process is carried out over the Internet, and the data is encrypted before being sent. Specifically, the device periodically sends data in packet form to the server.

[1024] Step 4:

[1025] The server stores the received data in a database. This data is later used for analysis. The input data is body temperature, air temperature, tone of voice, number of times the patient turns over in bed, and heart rate, and the data is stored in the corresponding tables in the database. Specifically, the server analyzes the received data, breaks it down into each field, and inserts it into the database.

[1026] Step 5:

[1027] The server preprocesses the stored data. Preprocessing includes filling in missing data and removing outliers. For example, it detects and removes outliers in body temperature data, and fills in missing dietary data with the average value. The input data is the collected body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the clean data after preprocessing.

[1028] Step 6:

[1029] The server uses the preprocessed data to perform analysis using a machine learning algorithm. The input data are preprocessed body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the user's sleepiness index. Specifically, the data is input into a tested machine learning model and the sleepiness index is calculated in real time.

[1030] Step 7:

[1031] The server calculates the optimal time to go to bed for the user based on the sleepiness index. The input data is the sleepiness index and the user's ideal wake-up time, and the output data is the optimal time to go to bed. For example, if a user wants to wake up at 7:00 AM, the server calculates that the optimal time to go to bed is 10:30 PM.

[1032] Step 8:

[1033] The server generates a notification message about the optimal time to go to bed and sends it to the device. The input data is the optimal time to go to bed, and the output data is the notification message. Specifically, it generates a message such as "It's almost time to go to bed" and sends it to the device.

[1034] Step 9:

[1035] The device displays the received notification message to the user and sends an alert at the appropriate time. The input data is the notification message, and the output data is a visual and audible alert. Specifically, a pop-up notification is displayed at 9:30 PM and an alarm sounds to encourage the user to go to bed.

[1036] Step 10:

[1037] The server analyzes the user's past sleep and behavioral data and generates a feedback message containing specific recommendations for improvement. The input data is past data, and the output data is the feedback message. For example, specific advice such as "You may be able to get better sleep if you lower the room temperature late at night" is generated based on the previous week's data.

[1038] Step 11:

[1039] The device displays a feedback message to the user and suggests improvements. The input data is the feedback message, and the output data is a visual suggestion. Specifically, the feedback message is displayed along with the morning alarm, and the suggestion is notified to the user.

[1040] (Application example 1)

[1041] 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."

[1042] Conventional health management systems could suggest optimal bedtimes based on a user's daily life and sleep data, but no system existed that could also manage and link dietary information. In particular, it was difficult to link with food delivery services and suggest meals that took into account the user's health status. As a result, users were unable to receive comprehensive advice on appropriate dietary information and bedtimes, making comprehensive health management difficult.

[1043] 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.

[1044] In this invention, the server includes a data collection means, a data analysis means, a notification means, a feedback means, and a meal suggestion means, which makes it possible to suggest the optimal time to go to bed based on the user's daily life data and sleep data, and to suggest the optimal meal for the user in cooperation with a food delivery service.

[1045] A "data collection means" is a device or process that acquires data related to a user's lifestyle, including, for example, body temperature, air temperature, tone of voice, dietary information, sleep duration, and the like.

[1046] The "data analysis means" is a device or process that analyzes the data acquired by the data collection means and calculates the user's health condition and sleepiness index.

[1047] The "notification means" is a device or process that sends a notification to the user based on the analysis results obtained by the data analysis means.

[1048] The "feedback means" is a device or process that performs analysis based on the user's behavioral data and sleep data and provides the user with feedback such as health improvement measures.

[1049] The "meal suggestion means" is a device or process that suggests meals that are optimal for the user's health condition based on the analysis results obtained by the data analysis means and data linked to the food delivery service.

[1050] The term "system" refers to the entire configuration that operates by combining the aforementioned data collection means, data analysis means, notification means, feedback means, and meal suggestion means.

[1051] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and a diet suggestion means, which allows a user to receive suggestions for optimal bedtime and healthy eating habits.

[1052] Hardware and software used:

[1053] 1. Smartphone: A device for data entry and notifications.

[1054] 2. Server: Stores and analyzes data.

[1055] 3. Wearable devices (e.g., smart watches): measure body temperature and heart rate.

[1056] 4. Food delivery apps: Get and order meals.

[1057] Data collection methods:

[1058] Users enter their daily diet and sleep duration through a smartphone app, and also use a smartwatch to collect data such as body temperature, heart rate, and the number of times they turn over in bed.

[1059] Data analysis methods:

[1060] The server receives data sent from smartphones and smartwatches and stores it in a database. It then preprocesses the data, correcting missing data and removing outliers. The server then uses machine learning algorithms to analyze the data and determine the user's sleepiness index and health condition.

[1061] Notification method:

[1062] Based on the analysis results, the server generates notifications suggesting optimal bedtimes and meals for the user and sends them to their smartphone. Users can receive alerts such as "It's almost time to go to bed" and messages such as "Here's today's healthy menu."

[1063] Feedback methods:

[1064] The server generates feedback based on the user's past data and suggests health improvement measures. The smartphone notifies the user of this feedback and provides advice such as "avoiding eating late at night will improve the quality of your sleep."

[1065] Meal suggestion methods:

[1066] The data analysis method works with food delivery services to suggest optimal meal plans based on the user's health status. For example, the server will make specific meal suggestions such as "We recommend a menu with lots of vegetables for lunch" based on the results of its analysis, and will also display a link to order from the delivery service.

[1067] Examples:

[1068] morning:

[1069] Users enter information about their breakfast into the app, and the smartwatch measures their body temperature and heart rate.

[1070] noon:

[1071] The smartwatch measures the ambient temperature and the user's body temperature, and the user enters their lunch information into the app.

[1072] evening:

[1073] Temperature and body temperature are measured again, and activity levels and tone of voice are also collected.

[1074] night:

[1075] The server analyzes this data, calculates a sleepiness index, suggests healthy menu items, and displays an ordering link in conjunction with a delivery service.

[1076] Before bed:

[1077] A notification appears on your smartphone saying, "It's almost time for bed."

[1078] next morning:

[1079] Providing server-generated feedback, such as advice like "Next time, dim the lights in your bedroom to help you sleep better."

[1080] Example prompts to input to a generative AI model:

[1081] I would like to develop a system that suggests optimal bedtime and healthy meals to users based on their diet, body temperature, heart rate, number of times they turn over in bed, and lifestyle habits. I would like to incorporate this into a food delivery app and have it provide a function that notifies users of health advice in real time. Please tell me the specific content of the notification message and the data analysis method.

[1082] This allows users to conveniently enjoy meals while maintaining a healthy lifestyle.

[1083] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1084] Step 1:

[1085] Users use a smartphone app to input their daily diet and sleep schedules. The input data is stored in the smartphone, allowing data on the user's lifestyle to be collected.

[1086] Step 2:

[1087] A wearable device (such as a smartwatch) worn by the user measures biological data such as body temperature, heart rate, and the number of times the user turns over in bed in real time. The measured data is automatically sent to a smartphone, and biological data is collected in this way.

[1088] Step 3:

[1089] The collected data is sent from the smartphone to a server, which receives the data and stores it in a database, enabling centralized management of the data.

[1090] Step 4:

[1091] The server preprocesses the data stored in the database, correcting missing data and removing outliers, and converting it into a format suitable for applying machine learning algorithms. The processed data is then used for analysis.

[1092] Step 5:

[1093] The server uses a machine learning algorithm to calculate the user's sleepiness index in real time from pre-processed data. Input data includes body temperature, air temperature, tone of voice, and food intake information, and the sleepiness index is obtained as output.

[1094] Step 6:

[1095] Based on the analysis results, the server evaluates the user's health condition and sleepiness index, and calculates the optimal time to go to bed. The server also takes into account the ideal wake-up time set by the user. The calculated bedtime is then sent as a notification message.

[1096] Step 7:

[1097] The server uses a meal suggestion algorithm to suggest healthy meals to the user. Based on the results of data analysis and the meal data from the food delivery service, the server selects the optimal meal menu for the user and generates a suggestion message.

[1098] Step 8:

[1099] The server then sends the generated notification message and meal suggestion message to the smartphone, which then displays the received message to the user and sends alerts such as "It's almost time to go to bed" or "Here's today's healthy menu."

[1100] Step 9:

[1101] The server generates feedback based on the user's past data. It analyzes the user's sleep and behavioral data and creates feedback messages that suggest health improvement measures. For example, it includes specific advice such as "Avoiding eating late at night will improve the quality of your sleep."

[1102] Step 10:

[1103] The server then sends the generated feedback message to the smartphone, which then displays it to the user, allowing the user to see specific improvements to their health status and lifestyle habits.

[1104] 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.

[1105] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and an emotion engine. This allows a user to know the optimal time to go to bed and obtain improvement measures that take into account their mental state. The system of the present invention is implemented as follows, using a mobile terminal, an emotion engine, and a server.

[1106] 1. Data Collection Methods

[1107] The user launches the app on their mobile device and inputs data about their daily life (e.g., what they eat, how much sleep they get, etc.), which starts the initial data collection.

[1108] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[1109] The device has a built-in emotion engine that analyzes the user's voice in real time and recognizes emotions from the voice data. This emotion data can be used as an indicator of stress levels and anxiety states.

[1110] 2. Data analysis methods

[1111] The server receives the data sent from the device and stores it in a database, including body temperature, air temperature, tone of voice, feeding information, sleep duration, and emotional data.

[1112] The server preprocesses the stored data, correcting missing data and detecting and removing outliers.

[1113] The server runs a machine learning algorithm to calculate the user's drowsiness index, taking into account emotion data obtained from the emotion engine to improve accuracy.

[1114] 3. Means of notification

[1115] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[1116] The server generates a notification message according to the optimal bedtime and sends it to the terminal, the notification message including the specific bedtime.

[1117] After receiving the notification message, the device displays a notification to the user at the specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[1118] 4. Feedback methods

[1119] The server analyzes the user's past sleep and emotional data and generates specific feedback to improve sleep quality.

[1120] The device displays this feedback message to the user and suggests improvements, such as "meditate before bed to reduce stress," "adjust the temperature in your bedroom," or "time your caffeine intake."

[1121] Specific examples

[1122] Provide specific examples based on the flow of a day.

[1123] morning:

[1124] Users input information about their breakfast into the app, which the device collects. The emotion engine also analyzes the tone of voice obtained from everyday conversations and records emotional data.

[1125] noon:

[1126] The device automatically measures the ambient temperature and the user's body temperature, and the emotion engine determines the stress level from the voice during conversation. The user inputs into the app that they had coffee for lunch.

[1127] evening:

[1128] The device again measures the ambient temperature and the user's body temperature, as well as collecting information such as movement volume and tone of voice. The emotion engine also continues to collect data, recording stress levels and anxiety states.

[1129] night:

[1130] The server receives and analyzes this data. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in drowsiness after drinking coffee to calculate a drowsiness index. Emotional data can also be taken into account to obtain a more accurate drowsiness index.

[1131] Before bed:

[1132] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index and emotional data. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's almost time to go to bed."

[1133] next morning:

[1134] The server compares past and current data and generates feedback messages to improve sleep quality, which the device displays to the user along with a morning alert as "points to improve next time." For example, it provides advice such as "Try meditating to reduce stress" or "You may be able to get better sleep if you lower the room temperature a little late at night."

[1135] Through this series of actions, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] The user launches the app on their mobile device and enters data such as the day's food intake and sleep time. The app has a form where users can enter details of the food they ate, the time they ate it, and the amount of sleep they got the previous night.

[1139] Step 2:

[1140] The device uses built-in sensors or connected wearable devices (e.g., smartwatches) to automatically collect data on the user's body temperature, ambient temperature, tone of voice, and the number of times the user turns over in bed. For example, a body temperature sensor measures and records the user's body temperature every hour.

[1141] Step 3:

[1142] The device collects the user's voice in real time, and the emotion engine analyzes the voice data to estimate the user's current emotional state (e.g., stress level, anxiety) by analyzing the voice frequency, volume, intonation, etc.

[1143] Step 4:

[1144] The device sends the collected data (body temperature, air temperature, tone of voice, emotional data, number of turns in sleep) to a server in real time, and the data is time-stamped for easy later analysis.

[1145] Step 5:

[1146] The server receives the data sent from the device and stores it in a database, where it checks the data to ensure consistency and accuracy (e.g., detecting outliers).

[1147] Step 6:

[1148] The server preprocesses the stored data, correcting missing data, removing outliers, normalizing the data, and converting it into a format suitable for analysis.

[1149] Step 7:

[1150] The server uses a machine learning algorithm to calculate the user's drowsiness index, which involves the following process:

[1151] An energy consumption model is constructed from the user's body temperature, air temperature, and food intake information.

[1152] Identify stress and fatigue levels based on tone of voice and emotional data.

[1153] These variables are analyzed comprehensively to calculate a sleepiness index.

[1154] Step 8:

[1155] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the user's ideal wake-up time.

[1156] Step 9:

[1157] The server generates a notification message according to the optimal bedtime and sends it to the terminal, which includes a specific time that is convenient for the user to fall asleep (e.g., 9:30 PM).

[1158] Step 10:

[1159] After the device receives the notification message, it will display a notification to the user at the specified time saying "It's almost time to go to bed," along with an appropriate sound or vibration to help the user acknowledge the notification.

[1160] Step 11:

[1161] The user goes to bed, and the device continues to collect sleep data (such as the number of times the user turns over in their sleep) throughout the night, thereby monitoring changes in body temperature and the ambient temperature during the night.

[1162] Step 12:

[1163] The server receives the nightly sleep data and evaluates the quality of sleep by analyzing the percentage of deep sleep and the number of times you woke up, among other factors, to quantify the quality of sleep.

[1164] Step 13:

[1165] The server compares the current data with the previous day's data and generates specific feedback messages to improve the quality of sleep, including lifestyle improvements (e.g., "Meditate before bed to reduce stress" or "Adjust the temperature in your bedroom").

[1166] Step 14:

[1167] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[1168] Through this series of steps, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[1169] Example 2

[1170] 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."

[1171] In modern society, many people suffer from insufficient sleep or poor quality sleep. This is considered a problem as it reduces health and quality of life. However, there are only a limited number of systems that provide specific measures and timing for improving sleep quality. There is a need for a system that takes into account the user's emotional state and suggests optimal improvement measures.

[1172] 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.

[1173] In this invention, the server includes a data collection means, a data analysis means, a notification means, an emotion analysis means, and a feedback means, which allows the server to collect and analyze the user's lifestyle data and emotion data, and provide feedback to individually optimize bedtime and improve the quality of sleep.

[1174] "Data collection means" refers to means for collecting data about the user's daily life (body temperature, air temperature, tone of voice, dietary information, sleep time, emotional data, etc.).

[1175] The "data analysis means" is a means for analyzing the data acquired by the data collection means and calculating the user's drowsiness index and other indices.

[1176] The "notification means" is a means for notifying the user of the optimal timing for going to bed and other important information based on the results of the analysis by the data analysis means.

[1177] "Emotion analysis means" refers to a means for recognizing and analyzing the user's emotions from collected voice data.

[1178] The "feedback means" is a means for tracking the user's sleep quality and providing specific improvement measures based on the analysis results.

[1179] The "drowsiness index" is an index that quantifies the user's state of drowsiness, and is calculated by the data analysis means.

[1180] The present invention provides a system that collects and analyzes a user's lifestyle and emotional data to provide optimal bedtime timing and measures to improve sleep quality. The system includes a data collection means, a data analysis means, a notification means, an emotional analysis means, and a feedback means.

[1181] System configuration and operation

[1182] Data collection methods

[1183] The user launches the app on their mobile device and manually enters data about their daily life, such as what they eat and how much sleep they get.

[1184] The device uses built-in sensors and connected wearable devices to automatically collect data such as the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[1185] The device uses emotion analysis to analyze the user's tone of voice in real time, extracting and recording emotional data, such as determining stress levels or anxiety levels from the tone of voice.

[1186] Data Analysis Methods

[1187] The server receives data sent from the device (body temperature, air temperature, tone of voice, feeding information, sleep time, emotional data) and stores it in a database.

[1188] The server preprocesses the received data, complements missing values, and detects and removes outliers.

[1189] The server runs a pre-configured machine learning algorithm to calculate the user's drowsiness index, which also takes into account emotional data to improve accuracy.

[1190] Notification means

[1191] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the ideal wake-up time.

[1192] The server generates a notification message and sends it to the terminal. For example, it generates a message saying, "It's a good idea to go to bed at 9:30 PM."

[1193] The terminal displays a notification message at the specified time, alerting the user that "it's almost time to go to bed."

[1194] Feedback Methods

[1195] The server analyzes the user's past sleep data and emotional data to determine any fluctuations.

[1196] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[1197] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[1198] Examples and prompts

[1199] Specific examples

[1200] morning:

[1201] The user inputs their breakfast (e.g., bread and coffee) into the app, the device measures their body temperature, and the emotion engine analyzes and records the emotions from their voice.

[1202] noon:

[1203] The device measures the ambient temperature and the user's body temperature. The user also inputs information about the lunch they had (salad and soup) into the app. The emotion engine analyzes the tone of voice during conversation and evaluates the stress level.

[1204] evening:

[1205] The device again measures the ambient temperature and the user's body temperature, as well as collects information such as activity level and tone of voice, and analyzes emotional data to record stress levels and anxiety states.

[1206] night:

[1207] The server receives and analyzes this data and calculates the user's sleepiness index, taking into account the timing of when body temperature starts to drop in the evening and fluctuations in sleepiness after consuming caffeine.

[1208] Before bed:

[1209] The server calculates the optimal time to go to bed based on the calculated sleepiness index and emotional data, and at 9:30 p.m. the device displays a notification saying, "It's almost time to go to bed."

[1210] next morning:

[1211] The server compares past and current data and generates specific feedback messages, which the device presents to the user along with morning alerts, offering advice such as "Try meditating" or "You might get better sleep if you lower the temperature in your room."

[1212] Prompt Sentence Examples

[1213] "Using your sleep data from the past three days, what is the best time for me to go to bed tonight? Also, please suggest specific improvements I can make to improve the quality of my sleep."

[1214] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1215] Step 1:

[1216] Manual data entry

[1217] Users launch the app on their mobile device and manually enter data about their daily life, such as what they ate, how much sleep they had, etc. Specifically, they record what they had for breakfast, lunch, and dinner, whether they exercised, and when they went to bed.

[1218] Input: User's lifestyle data such as diet, sleep time, and exercise information

[1219] Output: User's daily life data recorded in the mobile device app

[1220] Step 2:

[1221] Automatic collection of sensor data

[1222] The device uses built-in sensors and connected wearable devices to automatically collect the user's body temperature, air temperature, tone of voice, and number of times they turn over in bed.

[1223] For example, a temperature sensor built into the terminal measures the user's body temperature, and a wearable device records the number of times the user turns over in their sleep.

[1224] Input: Body temperature, temperature, tone of voice, number of times turning over in bed, data from connected wearable devices

[1225] Output: Collected vital and environmental data

[1226] Step 3:

[1227] Real-time analysis of sentiment data

[1228] The device uses emotion analysis means to analyze the tone of the user's voice in real time, and extracts and records emotion data.

[1229] For example, analyzing a user's speech to determine stress levels and anxiety states.

[1230] Input: User's voice tone (audio data)

[1231] Output: Analyzed emotional data (stress level, anxiety state, etc.)

[1232] Step 4:

[1233] Data transmission and storage

[1234] The device sends the data collected in steps 1 to 3 to the server.

[1235] The server stores the received data in a database, including body temperature, air temperature, tone of voice, food intake information, sleep duration, and emotional data.

[1236] Input: Collected and analyzed lifestyle data and emotional data

[1237] Output: User data stored in the server database

[1238] Step 5:

[1239] Data Preprocessing

[1240] The server performs preprocessing on the data it receives, complementing missing data and detecting and removing outliers to improve data quality.

[1241] Input: Saved user data (raw)

[1242] Output: Preprocessed and clean data

[1243] Step 6:

[1244] Calculating the sleepiness index

[1245] The server uses the pre-processed data to run a machine learning algorithm to calculate the user's drowsiness index, which includes emotional data, resulting in a more accurate drowsiness index.

[1246] Input: Preprocessed life data and emotion data

[1247] Output: Calculated sleepiness index

[1248] Step 7:

[1249] Predicting optimal bedtime

[1250] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the ideal wake-up time.

[1251] Input: Sleepiness index, emotional data, ideal wake-up time

[1252] Output: Optimal bedtime

[1253] Step 8:

[1254] Generate and send notification messages

[1255] The server generates a notification message based on the optimal bedtime and sends it to the device. For example, it generates a specific message such as "It's best to go to bed at 9:30 pm."

[1256] The terminal displays the received notification message to the user.

[1257] Input: Optimal Bedtime

[1258] Output: A notification message to the user

[1259] Step 9:

[1260] Analyzing past data and generating feedback

[1261] The server analyzes past sleep data and emotional data to determine any fluctuations.

[1262] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[1263] Input: Past sleep data, emotional data

[1264] Output: A specific feedback message

[1265] Step 10:

[1266] View Feedback

[1267] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[1268] Input: Specific feedback message

[1269] Output: Provide feedback to the user

[1270] (Application example 2)

[1271] 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."

[1272] Conventional lifestyle data collection systems lack the functionality to comprehensively support a user's health management and financial management. Furthermore, they have difficulty providing specific feedback that takes into account the user's emotional state and stress level, resulting in insufficient support for lifestyle improvement. To address these issues, the present invention provides a system that comprehensively analyzes a user's lifestyle data and expenditure data and provides health management feedback and financial management feedback.

[1273] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a data analysis means for analyzing the data acquired by the data collection means, a notification means for sending a notification to the user based on the analysis results obtained by the data analysis means, and a feedback means for providing health management feedback based on the user's lifestyle data and expenditure data. This makes it possible to comprehensively analyze the user's health condition and expenditure pattern and provide specific and optimal feedback.

[1274] The "data collection means" is a means for collecting various data from the user and the surrounding environment using sensors and input devices.

[1275] The "data analysis means" is a means for processing and analyzing the collected data and calculating indicators and patterns related to the user's condition and lifestyle habits.

[1276] The "notification means" is a means for providing advice and information on appropriate lifestyle habits to the user by notifying the user based on the analysis results.

[1277] The "feedback means" is a means for providing appropriate feedback to the user based on the analysis results and supporting the improvement of lifestyle habits.

[1278] "Lifestyle data" refers to information about the user's daily life, including body temperature, air temperature, tone of voice, dietary intake information, sleep time, amount of exercise, heart rate, stress level, and the like.

[1279] "Expense Data" is information about a user's financial transactions, including purchase history and expense details.

[1280] The "health index" is a numerical representation of the user's health condition based on collected lifestyle data, and is an index that is useful for improving lifestyle habits.

[1281] "Spending patterns" are an analysis of a user's financial behavior trends based on collected spending data, and are useful information for improving financial management.

[1282] The present invention relates to a system that collects and analyzes a user's lifestyle data and expenditure data, and provides health management feedback and financial management feedback based on the collected data. The specific configuration and processing method of the system are described below.

[1283] System Configuration

[1284] 1. Data collection methods:

[1285] Hardware: Smartphones, wearable devices (e.g., Apple Watch, Fitbit, etc.)

[1286] Software: Smartphone app (iOS, Android), wearable device linkage app

[1287] Function: Collects data on the user's daily life (body temperature, temperature, tone of voice, dietary intake, sleep time, exercise, heart rate, stress level, etc.) and expenditure data. Users enter their lifestyle data through a smartphone app, and the wearable device collects biometric data in real time.

[1288] 2. Data analysis methods:

[1289] Hardware: Cloud server (e.g. AWS, GCP)

[1290] Software: Databases (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., TensorFlow, Keras), natural language processing libraries (e.g., NLTK, spaCy)

[1291] Function: Cleanses collected data (removes outliers and fills in missing data) and uses machine learning algorithms to analyze users' health indicators and spending patterns.

[1292] 3. Means of notification:

[1293] Hardware: Smartphone

[1294] Software: Smartphone app with notification function

[1295] Function: Based on the results of data analysis, the app provides users with lifestyle advice and information at the appropriate time. It pushes notifications such as "Choose healthy snacks when shopping in the evening" at specific times.

[1296] 4. Feedback methods:

[1297] Hardware: Smartphone, cloud server

[1298] Software: Smartphone app, analysis software on cloud server

[1299] Function: Based on the analysis results, the app provides appropriate feedback to users, such as specific advice such as "Spend more on healthy foods next time you go shopping."

[1300] A concrete example of the processing flow

[1301] In the morning, the user enters their food intake information into a smartphone app, and the wearable device records their heart rate and body temperature in real time. In the afternoon, the wearable device measures their stress level and exercise volume, and in the evening, the data is sent to a cloud server. The cloud server analyzes the data and calculates the user's health index and spending patterns. Based on the analysis results, a notification is pushed to the smartphone before the evening shopping trip, urging the user to "pick a healthy snack." The next morning, feedback is provided based on past data.

[1302] Prompt Sentence Examples

[1303] "It uses the user's dietary and spending data to generate feedback to optimize the balance between health and finances."

[1304] With the above system configuration and processing method, the present invention can comprehensively analyze a user's health condition and expenditure patterns and provide specific and optimal feedback.

[1305] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1306] Step 1:

[1307] Users launch a smartphone app and input their dietary intake, exercise, and expenditure information. This input data is collected through a data collection tool. Wearable devices also collect real-time biometric information (body temperature, heart rate, stress level, etc.) and send it to the smartphone.

[1308] Input: Eating information, exercise information, expenditure information, body temperature, heart rate, stress level

[1309] Output: Collected life and biometric data

[1310] Step 2:

[1311] The terminal sends the data received from the wearable device to a cloud server, which then receives the data. The data is stored in a database and preprocessed, such as removing outliers and correcting missing data.

[1312] Input: Collected lifestyle and biometric data

[1313] Output: Cleansed data

[1314] Step 3:

[1315] The server uses the cleansed data to run machine learning algorithms to calculate the user's health index and spending patterns. The analysis is performed using machine learning libraries (e.g., TensorFlow, Keras).

[1316] Input: Cleansed data

[1317] Output: Health index, expenditure patterns

[1318] Step 4:

[1319] The server generates optimal feedback messages for each user based on the analysis results, and inputs prompts into a generative AI model (e.g., GPT-3) to generate specific advice and feedback.

[1320] Input: Health Index, Expenditure Pattern

[1321] Output: Feedback message (example prompt: "Generate feedback based on the user's dietary and expenditure data to optimize their health and financial balance.")

[1322] Step 5:

[1323] A notification message is created to notify the user of the feedback message generated by the server at a specific timing, and is sent to the smartphone terminal.

[1324] Input: Feedback message

[1325] Output: Notification message

[1326] Step 6:

[1327] The smartphone device will present the received notification message to the user as a push notification. For example, a notification such as "Choose healthy snacks when shopping in the evening" will be displayed at a specific time.

[1328] Input: Notification message

[1329] Output: Display a notification to the user

[1330] Step 7:

[1331] The next morning, the server compares and analyzes past data, generates new feedback based on the user's condition, and sends it to the smartphone. The user receives the feedback as "points for improvement next time" along with the morning alert.

[1332] Input: Historical and current data

[1333] Output: New feedback message

[1334] 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.

[1335] 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.

[1336] 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.

[1337] [Fourth embodiment]

[1338] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1339] 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.

[1340] 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).

[1341] 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.

[1342] 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.

[1343] 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).

[1344] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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."

[1351] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, and a feedback means. This allows a user to know the optimal timing for going to bed and obtain improvements for living a healthy life. The system of the present invention is implemented as follows using a mobile terminal and a server.

[1352] 1. Data Collection Methods

[1353] Users input data about their daily lives (e.g., what they eat, how much they sleep, etc.) through an app on their mobile device. This data is acquired by an input means serving as a data collection means.

[1354] The device automatically collects the user's body temperature, ambient temperature, and voice tone using built-in sensors, and also uses wearable devices such as smartwatches to collect the number of times the user turns over in bed and their heart rate.

[1355] 2. Data analysis methods

[1356] The server receives the data sent from the device and stores it in a database, enabling centralized management of data.

[1357] The server performs preprocessing based on the stored data, correcting missing data and removing outliers.

[1358] The server analyzes the accumulated data and uses a machine learning algorithm to calculate the user's sleepiness index in real time, which is calculated by comprehensively analyzing body temperature, air temperature, tone of voice, dietary information, etc.

[1359] 3. Means of notification

[1360] The server calculates the best time for the user to fall asleep based on the sleepiness index, taking into account the ideal wake-up time set by the user.

[1361] The server identifies the optimal time to go to bed, generates a notification message based on that information, and sends it to the device.

[1362] The device displays the received notification message to the user and sends an alert saying "It's almost time to go to bed" at the appropriate time.

[1363] 4. Feedback methods

[1364] The server analyzes the user's past sleep and behavioral data and generates specific feedback to improve sleep quality.

[1365] The device displays this feedback message to the user and suggests improvements, such as advice on how long to avoid caffeine, how to set the temperature in your bedroom, or how to relax before bed.

[1366] Specific examples

[1367] Provide specific examples based on the flow of a day.

[1368] morning:

[1369] The user enters information about breakfast into the app, and the device collects that information.

[1370] noon:

[1371] The device automatically measures the ambient temperature and the user's body temperature, and the user inputs into the app that they had coffee for lunch.

[1372] evening:

[1373] The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[1374] night:

[1375] The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[1376] Before bed:

[1377] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[1378] next morning:

[1379] The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get better sleep if you lower the room temperature a little late at night."

[1380] This allows users to objectively understand their lifestyle and sleep patterns, and learn optimal sleep timing and ways to improve them.

[1381] The processing flow will be explained below.

[1382] Step 1:

[1383] The user launches the app on their mobile device and enters data such as food intake and sleep time for that day, which starts the initial data collection.

[1384] Step 2:

[1385] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, ambient temperature, tone of voice, and the number of times they turn over in their sleep.

[1386] Step 3:

[1387] The data collected by the device is sent to the server in real time, and a timestamp is added to the data to clarify the time when each data point occurred.

[1388] Step 4:

[1389] The server stores the received data in a database, where it checks the data for consistency and detects and corrects outliers and missing data.

[1390] Step 5:

[1391] The server preprocesses the stored data, where it is standardized and converted into a format suitable for analysis.

[1392] Step 6:

[1393] The server runs a machine learning algorithm to calculate the user's sleepiness index, using a model that takes variables such as body temperature, air temperature, tone of voice, and food intake information as inputs and outputs a sleepiness level.

[1394] Step 7:

[1395] The server uses the calculated sleepiness index to predict the best time for the user to fall asleep, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[1396] Step 8:

[1397] The server generates a notification message according to the optimal bedtime and transmits it to the terminal, the message including the specific bedtime.

[1398] Step 9:

[1399] After the device receives the notification message, it displays a notification to the user at a specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[1400] Step 10:

[1401] The user then goes to bed and the device again collects nighttime sleep data, including the number of times the user turns over in their sleep and any changes in their environment.

[1402] Step 11:

[1403] The server receives the night's sleep data and assesses the quality of your sleep, including the percentage of deep sleep and the number of times you woke up.

[1404] Step 12:

[1405] The server compares the current data with the previous day's data and generates feedback messages to improve sleep quality, such as specific advice on adjusting the bedroom temperature or timing your caffeine intake.

[1406] Step 13:

[1407] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[1408] Through this series of steps, users can improve their lifestyle and sleep patterns and discover the optimal time to go to bed.

[1409] Example 1

[1410] 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."

[1411] In modern society, busy lifestyles, stress, and irregular life rhythms are causing many people to have poor sleep quality. This can lead to poor daytime performance and potentially health problems. Existing technologies have difficulty comprehensively analyzing individual lifestyle data and proposing effective sleep improvement measures. Therefore, there is a need for a system that can collect and analyze users' daily life data in detail to suggest optimal bedtimes and specific improvement measures.

[1412] 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.

[1413] In this invention, the server includes: a data collection means for the user to input lifestyle data such as dietary content and sleep duration; a data collection means for automatically collecting data such as body temperature, air temperature, tone of voice, number of turns in sleep, and heart rate from the device sensors and the wearable device; a data analysis means for receiving the data acquired by the data collection means and storing it in a database; a data analysis means for preprocessing the data to supplement missing data and remove outliers; a data analysis means for analyzing the data using a machine learning algorithm to calculate the user's sleepiness index; a data analysis means for calculating the user's optimal bedtime timing based on the analysis results; a notification means for generating a notification message and sending it to the user's device; and a feedback means for analyzing the user's past sleep data and behavioral data and providing specific feedback. This allows the user to objectively understand their lifestyle and sleep patterns and learn the optimal sleep timing and specific improvement measures.

[1414] "Data collection means" refers to a means for inputting daily life data such as the user's diet and sleep time, and a means for automatically collecting body temperature, air temperature, tone of voice, number of times the user turns over in bed, heart rate, etc. from the device's sensors or wearable devices.

[1415] The "data analysis means" refers to a means for receiving data acquired by the data collection means and storing it in a database, a means for supplementing missing data and removing outliers as preprocessing, and a means for analyzing data using a machine learning algorithm to calculate the user's sleepiness index and the optimal timing for going to bed.

[1416] The "notification means" is a means for generating a notification message based on the optimal bedtime timing calculated by the data analysis means and transmitting the message to the user's device.

[1417] The "feedback means" is a means for analyzing the user's past sleep data and behavioral data and providing a feedback message including specific measures for improvement.

[1418] A "user" is an individual who inputs lifestyle data such as dietary habits and sleep duration, and receives notifications and feedback.

[1419] A "device" is hardware, such as a mobile terminal or wearable device (e.g., a smartwatch), that collects data from a user and receives notifications.

[1420] A "sensor" is a component built into a device or wearable device that automatically collects data such as body temperature, air temperature, tone of voice, number of times you turn over in your sleep, and heart rate.

[1421] A "wearable device" is an electronic device that can be worn by a user, such as a smartwatch, and is used to measure body temperature, heart rate, exercise volume, etc.

[1422] The "sleepiness index" is an index that indicates how sleepy the user feels, analyzed based on body temperature, air temperature, tone of voice, dietary information, sleep time, etc.

[1423] A "machine learning algorithm" is a computational method that learns from accumulated data and analyzes patterns and trends to make predictions and classify new data.

[1424] The present invention relates to a system equipped with data collection means, data analysis means, notification means, and feedback means, with the aim of enabling users to learn the optimal timing for going to bed and improve their daily habits to lead a healthier life.

[1425] Data collection methods

[1426] Users provide their daily life data by entering it into a mobile app, including the specific meals and times they ate for breakfast, lunch, and dinner, as well as the total amount of sleep they received that day.

[1427] The device uses various built-in sensors and wearable devices such as smartwatches to automatically collect data such as body temperature, air temperature, tone of voice, number of times the user turns over in bed, and heart rate. For example, the smartwatch detects the user's heart rate and number of times the user turns over in bed, the temperature sensor measures the room temperature, and the microphone records the tone of voice.

[1428] Data Analysis Methods

[1429] The server receives the data sent from the device and stores it in a database, allowing for centralized management of user data.

[1430] The server performs preprocessing on the stored data, such as checking data from a heart rate sensor, removing unnaturally high or low values ​​as outliers, and filling in missing meal data with the average value.

[1431] The server applies a machine learning algorithm to the preprocessed data to calculate the user's sleepiness index in real time. This index is calculated based on data such as body temperature, air temperature, tone of voice, food intake, and sleep duration, allowing the user to understand their current level of sleepiness.

[1432] Notification means

[1433] The server then calculates the optimal time for the user to go to bed based on the calculated sleepiness index. This time is calculated taking into account the user's set wake-up time. For example, 10:30 PM may be calculated as the optimal time to go to bed.

[1434] The server stores the optimal timing for going to bed, generates a notification message based on the optimal timing, and transmits the notification message to the terminal.

[1435] The device will display the received notification message to the user and send an alert at the appropriate time saying, "It's almost time to go to bed." For example, a pop-up notification will appear at 9:30 PM and an alarm will sound to encourage the user to go to bed.

[1436] Feedback Methods

[1437] The server analyzes the user's past sleep and behavioral data and generates a feedback message with specific recommendations for improvement.

[1438] The device will display this feedback message to the user and offer suggestions to improve the quality of their sleep, such as "You may get better sleep if you lower the temperature a little late at night," along with a morning alert.

[1439] Specific examples

[1440] Below is a concrete example based on the flow of a day.

[1441] Morning: The user enters information about their breakfast into the app and the device collects it.

[1442] Lunch: The device automatically measures the ambient temperature and the user's body temperature, and the app records that the user had coffee for lunch.

[1443] Evening: The device again measures the ambient temperature and the user's body temperature, and also collects information such as activity level and voice tone.

[1444] Night: The server receives this data and analyzes it. For example, it analyzes the time when the user's body temperature starts to drop in the evening and the change in sleepiness after drinking coffee, and calculates a sleepiness index.

[1445] Before bedtime: The server notifies the user of the optimal time to go to bed based on the calculated sleepiness index. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's time to go to bed."

[1446] The next morning: The server generates feedback based on past data, and the device displays it to the user along with a morning alert as "points for improvement next time." For example, it provides advice such as, "You may be able to get a better night's sleep if you lower the room temperature a little late at night."

[1447] Prompt Sentence Examples

[1448] By inputting the following prompt sentence into the generative AI model, a detailed program for the above system can be generated.

[1449] Your goal is to create a program for a system that collects and analyzes daily life data and notifies users of the optimal time to go to bed. This system uses mobile devices and a server to collect, analyze, notify, and provide feedback on data. The following conditions must be met:

[1450] 1. Allow users to enter their meal and sleep schedules into a mobile app.

[1451] 2. The device automatically collects data such as temperature, body temperature, and tone of voice.

[1452] 3. The server analyzes the collected data and calculates the optimal time to go to bed.

[1453] 4. The server generates a notification message and sends it to the terminal.

[1454] 5. The device will display a notification to the user informing them of the best time to go to bed.

[1455] 6. The server generates feedback from past data and suggests improvement measures to the user.

[1456] This allows users to objectively understand their lifestyle habits and sleep patterns, and learn the optimal sleep timing and specific improvement measures.

[1457] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1458] Step 1:

[1459] A user inputs data about their daily life into an app on their mobile device. The input data includes the contents of meals, the times when they ate, and the amount of sleep they received. This data is saved on the device and later sent to a server. Specifically, the user accesses a specific screen in the app and inputs information such as the contents and times of meals using text boxes and pull-down menus.

[1460] Step 2:

[1461] The device collects data from built-in sensors and wearable devices such as a smartwatch. Specifically, a temperature sensor measures body temperature, a microphone records voice tone, and a smartwatch collects the number of times the user turns over in bed and their heart rate. This data is collected in real time, processed initially, and then stored in the device. For example, the temperature sensor periodically collects body temperature, and the smartwatch records the user's heart rate and the number of times the user turns over in bed.

[1462] Step 3:

[1463] The device sends the collected data to the server. Input data includes body temperature, air temperature, tone of voice, number of times the device turns over in bed, heart rate, etc. The transmission process is carried out over the Internet, and the data is encrypted before being sent. Specifically, the device periodically sends data in packet form to the server.

[1464] Step 4:

[1465] The server stores the received data in a database. This data is later used for analysis. The input data is body temperature, air temperature, tone of voice, number of times the patient turns over in bed, and heart rate, and the data is stored in the corresponding tables in the database. Specifically, the server analyzes the received data, breaks it down into each field, and inserts it into the database.

[1466] Step 5:

[1467] The server preprocesses the stored data. Preprocessing includes filling in missing data and removing outliers. For example, it detects and removes outliers in body temperature data, and fills in missing dietary data with the average value. The input data is the collected body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the clean data after preprocessing.

[1468] Step 6:

[1469] The server uses the preprocessed data to perform analysis using a machine learning algorithm. The input data are preprocessed body temperature, air temperature, tone of voice, number of turns in bed, and heart rate, and the output data is the user's sleepiness index. Specifically, the data is input into a tested machine learning model and the sleepiness index is calculated in real time.

[1470] Step 7:

[1471] The server calculates the optimal time to go to bed for the user based on the sleepiness index. The input data is the sleepiness index and the user's ideal wake-up time, and the output data is the optimal time to go to bed. For example, if a user wants to wake up at 7:00 AM, the server calculates that the optimal time to go to bed is 10:30 PM.

[1472] Step 8:

[1473] The server generates a notification message about the optimal time to go to bed and sends it to the device. The input data is the optimal time to go to bed, and the output data is the notification message. Specifically, it generates a message such as "It's almost time to go to bed" and sends it to the device.

[1474] Step 9:

[1475] The device displays the received notification message to the user and sends an alert at the appropriate time. The input data is the notification message, and the output data is a visual and audible alert. Specifically, a pop-up notification is displayed at 9:30 PM and an alarm sounds to encourage the user to go to bed.

[1476] Step 10:

[1477] The server analyzes the user's past sleep and behavioral data and generates a feedback message containing specific recommendations for improvement. The input data is past data, and the output data is the feedback message. For example, specific advice such as "You may be able to get better sleep if you lower the room temperature late at night" is generated based on the previous week's data.

[1478] Step 11:

[1479] The device displays a feedback message to the user and suggests improvements. The input data is the feedback message, and the output data is a visual suggestion. Specifically, the feedback message is displayed along with the morning alarm, and the suggestion is notified to the user.

[1480] (Application example 1)

[1481] 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."

[1482] Conventional health management systems could suggest optimal bedtimes based on a user's daily life and sleep data, but no system existed that could also manage and link dietary information. In particular, it was difficult to link with food delivery services and suggest meals that took into account the user's health status. As a result, users were unable to receive comprehensive advice on appropriate dietary information and bedtimes, making comprehensive health management difficult.

[1483] 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.

[1484] In this invention, the server includes a data collection means, a data analysis means, a notification means, a feedback means, and a meal suggestion means, which makes it possible to suggest the optimal time to go to bed based on the user's daily life data and sleep data, and to suggest the optimal meal for the user in cooperation with a food delivery service.

[1485] A "data collection means" is a device or process that acquires data related to a user's lifestyle, including, for example, body temperature, air temperature, tone of voice, dietary information, sleep duration, and the like.

[1486] The "data analysis means" is a device or process that analyzes the data acquired by the data collection means and calculates the user's health condition and sleepiness index.

[1487] The "notification means" is a device or process that sends a notification to the user based on the analysis results obtained by the data analysis means.

[1488] The "feedback means" is a device or process that performs analysis based on the user's behavioral data and sleep data and provides the user with feedback such as health improvement measures.

[1489] The "meal suggestion means" is a device or process that suggests meals that are optimal for the user's health condition based on the analysis results obtained by the data analysis means and data linked to the food delivery service.

[1490] The term "system" refers to the entire configuration that operates by combining the aforementioned data collection means, data analysis means, notification means, feedback means, and meal suggestion means.

[1491] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and a diet suggestion means, which allows a user to receive suggestions for optimal bedtime and healthy eating habits.

[1492] Hardware and software used:

[1493] 1. Smartphone: A device for data entry and notifications.

[1494] 2. Server: Stores and analyzes data.

[1495] 3. Wearable devices (e.g., smart watches): measure body temperature and heart rate.

[1496] 4. Food delivery apps: Get and order meals.

[1497] Data collection methods:

[1498] Users enter their daily diet and sleep duration through a smartphone app, and also use a smartwatch to collect data such as body temperature, heart rate, and the number of times they turn over in bed.

[1499] Data analysis methods:

[1500] The server receives data sent from smartphones and smartwatches and stores it in a database. It then preprocesses the data, correcting missing data and removing outliers. The server then uses machine learning algorithms to analyze the data and determine the user's sleepiness index and health condition.

[1501] Notification method:

[1502] Based on the analysis results, the server generates notifications suggesting optimal bedtimes and meals for the user and sends them to their smartphone. Users can receive alerts such as "It's almost time to go to bed" and messages such as "Here's today's healthy menu."

[1503] Feedback methods:

[1504] The server generates feedback based on the user's past data and suggests health improvement measures. The smartphone notifies the user of this feedback and provides advice such as "avoiding eating late at night will improve the quality of your sleep."

[1505] Meal suggestion methods:

[1506] The data analysis method works with food delivery services to suggest optimal meal plans based on the user's health status. For example, the server will make specific meal suggestions such as "We recommend a menu with lots of vegetables for lunch" based on the results of its analysis, and will also display a link to order from the delivery service.

[1507] Examples:

[1508] morning:

[1509] Users enter information about their breakfast into the app, and the smartwatch measures their body temperature and heart rate.

[1510] noon:

[1511] The smartwatch measures the ambient temperature and the user's body temperature, and the user enters their lunch information into the app.

[1512] evening:

[1513] Temperature and body temperature are measured again, and activity levels and tone of voice are also collected.

[1514] night:

[1515] The server analyzes this data, calculates a sleepiness index, suggests healthy menu items, and displays an ordering link in conjunction with a delivery service.

[1516] Before bed:

[1517] A notification appears on your smartphone saying, "It's almost time for bed."

[1518] next morning:

[1519] Providing server-generated feedback, such as advice like "Next time, dim the lights in your bedroom to help you sleep better."

[1520] Example prompts to input to a generative AI model:

[1521] I would like to develop a system that suggests optimal bedtime and healthy meals to users based on their diet, body temperature, heart rate, number of times they turn over in bed, and lifestyle habits. I would like to incorporate this into a food delivery app and have it provide a function that notifies users of health advice in real time. Please tell me the specific content of the notification message and the data analysis method.

[1522] This allows users to conveniently enjoy meals while maintaining a healthy lifestyle.

[1523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1524] Step 1:

[1525] Users use a smartphone app to input their daily diet and sleep schedules. The input data is stored in the smartphone, allowing data on the user's lifestyle to be collected.

[1526] Step 2:

[1527] A wearable device (such as a smartwatch) worn by the user measures biological data such as body temperature, heart rate, and the number of times the user turns over in bed in real time. The measured data is automatically sent to a smartphone, and biological data is collected in this way.

[1528] Step 3:

[1529] The collected data is sent from the smartphone to a server, which receives the data and stores it in a database, enabling centralized management of the data.

[1530] Step 4:

[1531] The server preprocesses the data stored in the database, correcting missing data and removing outliers, and converting it into a format suitable for applying machine learning algorithms. The processed data is then used for analysis.

[1532] Step 5:

[1533] The server uses a machine learning algorithm to calculate the user's sleepiness index in real time from pre-processed data. Input data includes body temperature, air temperature, tone of voice, and food intake information, and the sleepiness index is obtained as output.

[1534] Step 6:

[1535] Based on the analysis results, the server evaluates the user's health condition and sleepiness index, and calculates the optimal time to go to bed. The server also takes into account the ideal wake-up time set by the user. The calculated bedtime is then sent as a notification message.

[1536] Step 7:

[1537] The server uses a meal suggestion algorithm to suggest healthy meals to the user. Based on the results of data analysis and the meal data from the food delivery service, the server selects the optimal meal menu for the user and generates a suggestion message.

[1538] Step 8:

[1539] The server then sends the generated notification message and meal suggestion message to the smartphone, which then displays the received message to the user and sends alerts such as "It's almost time to go to bed" or "Here's today's healthy menu."

[1540] Step 9:

[1541] The server generates feedback based on the user's past data. It analyzes the user's sleep and behavioral data and creates feedback messages that suggest health improvement measures. For example, it includes specific advice such as "Avoiding eating late at night will improve the quality of your sleep."

[1542] Step 10:

[1543] The server then sends the generated feedback message to the smartphone, which then displays it to the user, allowing the user to see specific improvements to their health status and lifestyle habits.

[1544] 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.

[1545] The present invention relates to a system that includes a data collection means, a data analysis means, a notification means, a feedback means, and an emotion engine. This allows a user to know the optimal time to go to bed and obtain improvement measures that take into account their mental state. The system of the present invention is implemented as follows, using a mobile terminal, an emotion engine, and a server.

[1546] 1. Data Collection Methods

[1547] The user launches the app on their mobile device and inputs data about their daily life (e.g., what they eat, how much sleep they get, etc.), which starts the initial data collection.

[1548] The device automatically collects data using built-in sensors and connected wearable devices, specifically recording the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[1549] The device has a built-in emotion engine that analyzes the user's voice in real time and recognizes emotions from the voice data. This emotion data can be used as an indicator of stress levels and anxiety states.

[1550] 2. Data analysis methods

[1551] The server receives the data sent from the device and stores it in a database, including body temperature, air temperature, tone of voice, feeding information, sleep duration, and emotional data.

[1552] The server preprocesses the stored data, correcting missing data and detecting and removing outliers.

[1553] The server runs a machine learning algorithm to calculate the user's drowsiness index, taking into account emotion data obtained from the emotion engine to improve accuracy.

[1554] 3. Means of notification

[1555] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the user's ideal wake-up time.

[1556] The server generates a notification message according to the optimal bedtime and sends it to the terminal, the notification message including the specific bedtime.

[1557] After receiving the notification message, the device displays a notification to the user at the specified time (e.g., 9:30 p.m.) saying, "It's almost time to go to bed."

[1558] 4. Feedback methods

[1559] The server analyzes the user's past sleep and emotional data and generates specific feedback to improve sleep quality.

[1560] The device displays this feedback message to the user and suggests improvements, such as "meditate before bed to reduce stress," "adjust the temperature in your bedroom," or "time your caffeine intake."

[1561] Specific examples

[1562] Provide specific examples based on the flow of a day.

[1563] morning:

[1564] Users input information about their breakfast into the app, which the device collects. The emotion engine also analyzes the tone of voice obtained from everyday conversations and records emotional data.

[1565] noon:

[1566] The device automatically measures the ambient temperature and the user's body temperature, and the emotion engine determines the stress level from the voice during conversation. The user inputs into the app that they had coffee for lunch.

[1567] evening:

[1568] The device again measures the ambient temperature and the user's body temperature, as well as collecting information such as movement volume and tone of voice. The emotion engine also continues to collect data, recording stress levels and anxiety states.

[1569] night:

[1570] The server receives and analyzes this data. For example, it analyzes the time when the user's body temperature starts to drop in the evening or the change in drowsiness after drinking coffee to calculate a drowsiness index. Emotional data can also be taken into account to obtain a more accurate drowsiness index.

[1571] Before bed:

[1572] The server then notifies the user of the optimal time to go to bed based on the calculated sleepiness index and emotional data. For example, at 9:30 p.m., the device displays a notification to the user saying, "It's almost time to go to bed."

[1573] next morning:

[1574] The server compares past and current data and generates feedback messages to improve sleep quality, which the device displays to the user along with a morning alert as "points to improve next time." For example, it provides advice such as "Try meditating to reduce stress" or "You may be able to get better sleep if you lower the room temperature a little late at night."

[1575] Through this series of actions, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[1576] The processing flow will be explained below.

[1577] Step 1:

[1578] The user launches the app on their mobile device and enters data such as the day's food intake and sleep time. The app has a form where users can enter details of the food they ate, the time they ate it, and the amount of sleep they got the previous night.

[1579] Step 2:

[1580] The device uses built-in sensors or connected wearable devices (e.g., smartwatches) to automatically collect data on the user's body temperature, ambient temperature, tone of voice, and the number of times the user turns over in bed. For example, a body temperature sensor measures and records the user's body temperature every hour.

[1581] Step 3:

[1582] The device collects the user's voice in real time, and the emotion engine analyzes the voice data to estimate the user's current emotional state (e.g., stress level, anxiety) by analyzing the voice frequency, volume, intonation, etc.

[1583] Step 4:

[1584] The device sends the collected data (body temperature, air temperature, tone of voice, emotional data, number of turns in sleep) to a server in real time, and the data is time-stamped for easy later analysis.

[1585] Step 5:

[1586] The server receives the data sent from the device and stores it in a database, where it checks the data to ensure consistency and accuracy (e.g., detecting outliers).

[1587] Step 6:

[1588] The server preprocesses the stored data, correcting missing data, removing outliers, normalizing the data, and converting it into a format suitable for analysis.

[1589] Step 7:

[1590] The server uses a machine learning algorithm to calculate the user's drowsiness index, which involves the following process:

[1591] An energy consumption model is constructed from the user's body temperature, air temperature, and food intake information.

[1592] Identify stress and fatigue levels based on tone of voice and emotional data.

[1593] These variables are analyzed comprehensively to calculate a sleepiness index.

[1594] Step 8:

[1595] The server predicts the best time for the user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the user's ideal wake-up time.

[1596] Step 9:

[1597] The server generates a notification message according to the optimal bedtime and sends it to the terminal, which includes a specific time that is convenient for the user to fall asleep (e.g., 9:30 PM).

[1598] Step 10:

[1599] After the device receives the notification message, it will display a notification to the user at the specified time saying "It's almost time to go to bed," along with an appropriate sound or vibration to help the user acknowledge the notification.

[1600] Step 11:

[1601] The user goes to bed, and the device continues to collect sleep data (such as the number of times the user turns over in their sleep) throughout the night, thereby monitoring changes in body temperature and the ambient temperature during the night.

[1602] Step 12:

[1603] The server receives the nightly sleep data and evaluates the quality of sleep by analyzing the percentage of deep sleep and the number of times you woke up, among other factors, to quantify the quality of sleep.

[1604] Step 13:

[1605] The server compares the current data with the previous day's data and generates specific feedback messages to improve the quality of sleep, including lifestyle improvements (e.g., "Meditate before bed to reduce stress" or "Adjust the temperature in your bedroom").

[1606] Step 14:

[1607] The device receives the feedback message and displays it to the user, who can then adjust their lifestyle to improve their sleep next time.

[1608] Through this series of steps, users can improve their lifestyle and sleep patterns and learn about the best time to go to bed and improvement measures that take into account their mental state.

[1609] Example 2

[1610] 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."

[1611] In modern society, many people suffer from insufficient sleep or poor quality sleep. This is considered a problem as it reduces health and quality of life. However, there are only a limited number of systems that provide specific measures and timing for improving sleep quality. There is a need for a system that takes into account the user's emotional state and suggests optimal improvement measures.

[1612] 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.

[1613] In this invention, the server includes a data collection means, a data analysis means, a notification means, an emotion analysis means, and a feedback means, which allows the server to collect and analyze the user's lifestyle data and emotion data, and provide feedback to individually optimize bedtime and improve the quality of sleep.

[1614] "Data collection means" refers to means for collecting data about the user's daily life (body temperature, air temperature, tone of voice, dietary information, sleep time, emotional data, etc.).

[1615] The "data analysis means" is a means for analyzing the data acquired by the data collection means and calculating the user's drowsiness index and other indices.

[1616] The "notification means" is a means for notifying the user of the optimal timing for going to bed and other important information based on the results of the analysis by the data analysis means.

[1617] "Emotion analysis means" refers to a means for recognizing and analyzing the user's emotions from collected voice data.

[1618] The "feedback means" is a means for tracking the user's sleep quality and providing specific improvement measures based on the analysis results.

[1619] The "drowsiness index" is an index that quantifies the user's state of drowsiness, and is calculated by the data analysis means.

[1620] The present invention provides a system that collects and analyzes a user's lifestyle and emotional data to provide optimal bedtime timing and measures to improve sleep quality. The system includes a data collection means, a data analysis means, a notification means, an emotional analysis means, and a feedback means.

[1621] System configuration and operation

[1622] Data collection methods

[1623] The user launches the app on their mobile device and manually enters data about their daily life, such as what they eat and how much sleep they get.

[1624] The device uses built-in sensors and connected wearable devices to automatically collect data such as the user's body temperature, air temperature, tone of voice, and the number of times they turn over in their sleep.

[1625] The device uses emotion analysis to analyze the user's tone of voice in real time, extracting and recording emotional data, such as determining stress levels or anxiety levels from the tone of voice.

[1626] Data Analysis Methods

[1627] The server receives data sent from the device (body temperature, air temperature, tone of voice, feeding information, sleep time, emotional data) and stores it in a database.

[1628] The server preprocesses the received data, complements missing values, and detects and removes outliers.

[1629] The server runs a pre-configured machine learning algorithm to calculate the user's drowsiness index, which also takes into account emotional data to improve accuracy.

[1630] Notification means

[1631] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal bedtime, taking into account the ideal wake-up time.

[1632] The server generates a notification message and sends it to the terminal. For example, it generates a message saying, "It's a good idea to go to bed at 9:30 PM."

[1633] The terminal displays a notification message at the specified time, alerting the user that "it's almost time to go to bed."

[1634] Feedback Methods

[1635] The server analyzes the user's past sleep data and emotional data to determine any fluctuations.

[1636] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[1637] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[1638] Examples and prompts

[1639] Specific examples

[1640] morning:

[1641] The user inputs their breakfast (e.g., bread and coffee) into the app, the device measures their body temperature, and the emotion engine analyzes and records the emotions from their voice.

[1642] noon:

[1643] The device measures the ambient temperature and the user's body temperature. The user also inputs information about the lunch they had (salad and soup) into the app. The emotion engine analyzes the tone of voice during conversation and evaluates the stress level.

[1644] evening:

[1645] The device again measures the ambient temperature and the user's body temperature, as well as collects information such as activity level and tone of voice, and analyzes emotional data to record stress levels and anxiety states.

[1646] night:

[1647] The server receives and analyzes this data and calculates the user's sleepiness index, taking into account the timing of when body temperature starts to drop in the evening and fluctuations in sleepiness after consuming caffeine.

[1648] Before bed:

[1649] The server calculates the optimal time to go to bed based on the calculated sleepiness index and emotional data, and at 9:30 p.m. the device displays a notification saying, "It's almost time to go to bed."

[1650] next morning:

[1651] The server compares past and current data and generates specific feedback messages, which the device presents to the user along with morning alerts, offering advice such as "Try meditating" or "You might get better sleep if you lower the temperature in your room."

[1652] Prompt Sentence Examples

[1653] "Using your sleep data from the past three days, what is the best time for me to go to bed tonight? Also, please suggest specific improvements I can make to improve the quality of my sleep."

[1654] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1655] Step 1:

[1656] Manual data entry

[1657] Users launch the app on their mobile device and manually enter data about their daily life, such as what they ate, how much sleep they had, etc. Specifically, they record what they had for breakfast, lunch, and dinner, whether they exercised, and when they went to bed.

[1658] Input: User's lifestyle data such as diet, sleep time, and exercise information

[1659] Output: User's daily life data recorded in the mobile device app

[1660] Step 2:

[1661] Automatic collection of sensor data

[1662] The device uses built-in sensors and connected wearable devices to automatically collect the user's body temperature, air temperature, tone of voice, and number of times they turn over in bed.

[1663] For example, a temperature sensor built into the terminal measures the user's body temperature, and a wearable device records the number of times the user turns over in their sleep.

[1664] Input: Body temperature, temperature, tone of voice, number of times turning over in bed, data from connected wearable devices

[1665] Output: Collected vital and environmental data

[1666] Step 3:

[1667] Real-time analysis of sentiment data

[1668] The device uses emotion analysis means to analyze the tone of the user's voice in real time, and extracts and records emotion data.

[1669] For example, analyzing a user's speech to determine stress levels and anxiety states.

[1670] Input: User's voice tone (audio data)

[1671] Output: Analyzed emotional data (stress level, anxiety state, etc.)

[1672] Step 4:

[1673] Data transmission and storage

[1674] The device sends the data collected in steps 1 to 3 to the server.

[1675] The server stores the received data in a database, including body temperature, air temperature, tone of voice, food intake information, sleep duration, and emotional data.

[1676] Input: Collected and analyzed lifestyle data and emotional data

[1677] Output: User data stored in the server database

[1678] Step 5:

[1679] Data Preprocessing

[1680] The server performs preprocessing on the data it receives, complementing missing data and detecting and removing outliers to improve data quality.

[1681] Input: Saved user data (raw)

[1682] Output: Preprocessed and clean data

[1683] Step 6:

[1684] Calculating the sleepiness index

[1685] The server uses the pre-processed data to run a machine learning algorithm to calculate the user's drowsiness index, which includes emotional data, resulting in a more accurate drowsiness index.

[1686] Input: Preprocessed life data and emotion data

[1687] Output: Calculated sleepiness index

[1688] Step 7:

[1689] Predicting optimal bedtime

[1690] The server predicts the best time for a user to fall asleep based on the calculated sleepiness index and emotional data, and calculates the optimal time to go to bed, taking into account the ideal wake-up time.

[1691] Input: Sleepiness index, emotional data, ideal wake-up time

[1692] Output: Optimal bedtime

[1693] Step 8:

[1694] Generate and send notification messages

[1695] The server generates a notification message based on the optimal bedtime and sends it to the device. For example, it generates a specific message such as "It's best to go to bed at 9:30 pm."

[1696] The terminal displays the received notification message to the user.

[1697] Input: Optimal Bedtime

[1698] Output: A notification message to the user

[1699] Step 9:

[1700] Analyzing past data and generating feedback

[1701] The server analyzes past sleep data and emotional data to determine any fluctuations.

[1702] Based on the analysis results, the server generates specific feedback to improve the user's sleep quality, including suggestions such as "Meditating before bed is a good way to reduce stress."

[1703] Input: Past sleep data, emotional data

[1704] Output: A specific feedback message

[1705] Step 10:

[1706] View Feedback

[1707] The device displays the generated feedback message to the user and suggests improvements. For example, along with a morning alert, the device provides advice such as "You might get better sleep if you lower the room temperature a little late at night" as a "point to improve next time."

[1708] Input: Specific feedback message

[1709] Output: Provide feedback to the user

[1710] (Application example 2)

[1711] 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."

[1712] Conventional lifestyle data collection systems lack the functionality to comprehensively support a user's health management and financial management. Furthermore, they have difficulty providing specific feedback that takes into account the user's emotional state and stress level, resulting in insufficient support for lifestyle improvement. To address these issues, the present invention provides a system that comprehensively analyzes a user's lifestyle data and expenditure data and provides health management feedback and financial management feedback.

[1713] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a data analysis means for analyzing the data acquired by the data collection means, a notification means for sending a notification to the user based on the analysis results obtained by the data analysis means, and a feedback means for providing health management feedback based on the user's lifestyle data and expenditure data. This makes it possible to comprehensively analyze the user's health condition and expenditure pattern and provide specific and optimal feedback.

[1714] The "data collection means" is a means for collecting various data from the user and the surrounding environment using sensors and input devices.

[1715] The "data analysis means" is a means for processing and analyzing the collected data and calculating indicators and patterns related to the user's condition and lifestyle habits.

[1716] The "notification means" is a means for providing advice and information on appropriate lifestyle habits to the user by notifying the user based on the analysis results.

[1717] The "feedback means" is a means for providing appropriate feedback to the user based on the analysis results and supporting the improvement of lifestyle habits.

[1718] "Lifestyle data" refers to information about the user's daily life, including body temperature, air temperature, tone of voice, dietary intake information, sleep time, amount of exercise, heart rate, stress level, and the like.

[1719] "Expense Data" is information about a user's financial transactions, including purchase history and expense details.

[1720] The "health index" is a numerical representation of the user's health condition based on collected lifestyle data, and is an index that is useful for improving lifestyle habits.

[1721] "Spending patterns" are an analysis of a user's financial behavior trends based on collected spending data, and are useful information for improving financial management.

[1722] The present invention relates to a system that collects and analyzes a user's lifestyle data and expenditure data, and provides health management feedback and financial management feedback based on the collected data. The specific configuration and processing method of the system are described below.

[1723] System Configuration

[1724] 1. Data collection methods:

[1725] Hardware: Smartphones, wearable devices (e.g., Apple Watch, Fitbit, etc.)

[1726] Software: Smartphone app (iOS, Android), wearable device linkage app

[1727] Function: Collects data on the user's daily life (body temperature, temperature, tone of voice, dietary intake, sleep time, exercise, heart rate, stress level, etc.) and expenditure data. Users enter their lifestyle data through a smartphone app, and the wearable device collects biometric data in real time.

[1728] 2. Data analysis methods:

[1729] Hardware: Cloud server (e.g. AWS, GCP)

[1730] Software: Databases (e.g., MySQL, PostgreSQL), machine learning libraries (e.g., TensorFlow, Keras), natural language processing libraries (e.g., NLTK, spaCy)

[1731] Function: Cleanses collected data (removes outliers and fills in missing data) and uses machine learning algorithms to analyze users' health indicators and spending patterns.

[1732] 3. Means of notification:

[1733] Hardware: Smartphone

[1734] Software: Smartphone app with notification function

[1735] Function: Based on the results of data analysis, the app provides users with lifestyle advice and information at the appropriate time. It pushes notifications such as "Choose healthy snacks when shopping in the evening" at specific times.

[1736] 4. Feedback methods:

[1737] Hardware: Smartphone, cloud server

[1738] Software: Smartphone app, analysis software on cloud server

[1739] Function: Based on the analysis results, the app provides appropriate feedback to users, such as specific advice such as "Spend more on healthy foods next time you go shopping."

[1740] A concrete example of the processing flow

[1741] In the morning, the user enters their food intake information into a smartphone app, and the wearable device records their heart rate and body temperature in real time. In the afternoon, the wearable device measures their stress level and exercise volume, and in the evening, the data is sent to a cloud server. The cloud server analyzes the data and calculates the user's health index and spending patterns. Based on the analysis results, a notification is pushed to the smartphone before the evening shopping trip, urging the user to "pick a healthy snack." The next morning, feedback is provided based on past data.

[1742] Prompt Sentence Examples

[1743] "It uses the user's dietary and spending data to generate feedback to optimize the balance between health and finances."

[1744] With the above system configuration and processing method, the present invention can comprehensively analyze a user's health condition and expenditure patterns and provide specific and optimal feedback.

[1745] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1746] Step 1:

[1747] Users launch a smartphone app and input their dietary intake, exercise, and expenditure information. This input data is collected through a data collection tool. Wearable devices also collect real-time biometric information (body temperature, heart rate, stress level, etc.) and send it to the smartphone.

[1748] Input: Eating information, exercise information, expenditure information, body temperature, heart rate, stress level

[1749] Output: Collected life and biometric data

[1750] Step 2:

[1751] The terminal sends the data received from the wearable device to a cloud server, which then receives the data. The data is stored in a database and preprocessed, such as removing outliers and correcting missing data.

[1752] Input: Collected lifestyle and biometric data

[1753] Output: Cleansed data

[1754] Step 3:

[1755] The server uses the cleansed data to run machine learning algorithms to calculate the user's health index and spending patterns. The analysis is performed using machine learning libraries (e.g., TensorFlow, Keras).

[1756] Input: Cleansed data

[1757] Output: Health index, expenditure patterns

[1758] Step 4:

[1759] The server generates optimal feedback messages for each user based on the analysis results, and inputs prompts into a generative AI model (e.g., GPT-3) to generate specific advice and feedback.

[1760] Input: Health Index, Expenditure Pattern

[1761] Output: Feedback message (example prompt: "Generate feedback based on the user's dietary and expenditure data to optimize their health and financial balance.")

[1762] Step 5:

[1763] A notification message is created to notify the user of the feedback message generated by the server at a specific timing, and is sent to the smartphone terminal.

[1764] Input: Feedback message

[1765] Output: Notification message

[1766] Step 6:

[1767] The smartphone device will present the received notification message to the user as a push notification. For example, a notification such as "Choose healthy snacks when shopping in the evening" will be displayed at a specific time.

[1768] Input: Notification message

[1769] Output: Display a notification to the user

[1770] Step 7:

[1771] The next morning, the server compares and analyzes past data, generates new feedback based on the user's condition, and sends it to the smartphone. The user receives the feedback as "points for improvement next time" along with the morning alert.

[1772] Input: Historical and current data

[1773] Output: New feedback message

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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).

[1781] 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.

[1782] 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."

[1783] 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.

[1784] 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).

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] The following is further disclosed regarding the above embodiment.

[1796] (Claim 1)

[1797] data collection means;

[1798] data analysis means for analyzing the data acquired by the data collection means;

[1799] a notification means for transmitting a notification to a user based on the analysis result obtained by the data analysis means;

[1800] The system comprises a feedback means for tracking the user's sleep quality and providing feedback.

[1801] (Claim 2)

[1802] 2. The system according to claim 1, wherein the data collection means is means for collecting the user's body temperature, air temperature, tone of voice, food intake information, and sleep time.

[1803] (Claim 3)

[1804] 2. The system according to claim 1, wherein the data analysis means is means for calculating a drowsiness index of the user using the data.

[1805] (Claim 4)

[1806] 2. The system according to claim 1, wherein the notification means calculates the timing at which the user is most likely to fall asleep and generates a notification based on the calculated timing.

[1807] (Claim 5)

[1808] 2. The system according to claim 1, wherein the feedback means is means for providing the user with specific feedback for improving sleep quality based on the user's sleep data.

[1809] "Example 1"

[1810] (Claim 1)

[1811] A data collection means for a user to input lifestyle data such as dietary content and sleep time;

[1812] A data collection means for automatically collecting data such as body temperature, temperature, tone of voice, number of times the user turns over in bed, and heart rate from the device's sensors and wearable device;

[1813] a data analysis means for receiving the data acquired by the data collection means and storing the data in a database;

[1814] a data analysis means for preprocessing the data, complementing missing data, and removing outliers;

[1815] a data analysis means for analyzing the data using a machine learning algorithm and calculating a drowsiness index of the user;

[1816] A data analysis means for calculating the optimal timing for a user to go to bed based on the analysis results;

[1817] notification means for generating and transmitting a notification message to a user's device;

[1818] The system includes a feedback means for analyzing a user's past sleep and behavioral data and providing specific feedback.

[1819] (Claim 2)

[1820] The system according to claim 1, wherein the user inputs meal contents and sleep time into an app on a mobile device.

[1821] (Claim 3)

[1822] The system of claim 1, wherein the device automatically collects body temperature, air temperature, tone of voice, number of times turning over in bed, and heart rate from built-in sensors, a smartwatch, etc.

[1823] "Application Example 1"

[1824] (Claim 1)

[1825] data collection means;

[1826] data analysis means for analyzing the data acquired by the data collection means;

[1827] a notification means for transmitting a notification to a user based on the analysis result obtained by the data analysis means;

[1828] feedback means for tracking and providing feedback on the user's sleep quality;

[1829] A meal suggestion tool that works in conjunction with food delivery services to suggest the best meal for users

[1830] A system including:

[1831] (Claim 2)

[1832] The system according to claim 1, wherein the data collection means is a means for collecting the user's body temperature, air temperature, tone of voice, eating information, and sleep time, and a means for obtaining meal contents through a food delivery app.

[1833] (Claim 3)

[1834] 2. The system according to claim 1, wherein the data analysis means is means for calculating a sleepiness index of the user using the data and for making dietary suggestions taking into consideration the health condition of the user.

[1835] "Example 2: Combining Emotion Engines"

[1836] (Claim 1)

[1837] data collection means;

[1838] data analysis means for analyzing the data acquired by the data collection means;

[1839] a notification means for transmitting a notification to a user based on the analysis result obtained by the data analysis means;

[1840] emotion analysis means for recognizing emotions from the voice data collected by the data collection means;

[1841] The system includes a feedback means for tracking the user's sleep quality and providing feedback.

[1842] (Claim 2)

[1843] 2. The system according to claim 1, wherein the data collection means is means for collecting the user's body temperature, air temperature, tone of voice, food intake information, sleep time and emotional data.

[1844] (Claim 3)

[1845] 2. The system according to claim 1, wherein the data analysis means is means for calculating a drowsiness index of the user using the data.

[1846] "Application example 2 when combining emotion engines"

[1847] (Claim 1)

[1848] data collection means;

[1849] data analysis means for analyzing the data acquired by the data collection means;

[1850] a notification means for transmitting a notification to a user based on the analysis result obtained by the data analysis means;

[1851] The system comprises a feedback means for providing health management feedback based on lifestyle and expenditure data of the user.

[1852] (Claim 2)

[1853] 2. The system according to claim 1, wherein the data collection means is means for collecting the user's body temperature, air temperature, tone of voice, food intake information, sleep time, amount of exercise, heart rate, stress level and expenditure data.

[1854] (Claim 3)

[1855] 2. The system of claim 1, wherein the data analysis means is means for calculating a user's health index and spending patterns using the data. [Explanation of symbols]

[1856] 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. data collection means; data analysis means for analyzing the data acquired by the data collection means; a notification means for transmitting a notification to a user based on the analysis result obtained by the data analysis means; The system comprises a feedback means for tracking the user's sleep quality and providing feedback.

2. 2. The system according to claim 1, wherein the data collection means is means for collecting the user's body temperature, air temperature, tone of voice, food intake information, and sleep time.

3. 2. The system according to claim 1, wherein the data analysis means is means for calculating a sleepiness index of the user using the data.

4. 2. The system according to claim 1, wherein the notification means calculates the timing when the user is most likely to fall asleep and generates a notification based on the calculated timing.

5. The system according to claim 1 , wherein the feedback means is means for providing the user with specific feedback for improving sleep quality based on the user's sleep data.

Images