System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving menstrual cycle information of a user; means for analyzing the received menstrual cycle information; means for applying a generative AI model to predict a menstrual cycle based on the analysis; means for generating health advice based on the predicted menstrual cycle; and means for transmitting the generated health advice to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional health approaches have the problem of not fully meeting the individual health needs of women according to their menstrual cycle and lacking specific advice tailored to the user's physical condition and lifestyle, making it difficult for users to optimally manage their own health. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: a system including means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, and means for sending the generated health advice to the user. This allows the user to receive personalized advice tailored to their health condition, enabling more accurate health management.

[0006] A "user" is an individual who utilizes the system to input their menstrual cycle data and receive health advice.

[0007] "Menstrual cycle data" is information about the user's menstruation, including the start date of the user's last menstruation and the length of the menstrual cycle.

[0008] "Means for receiving" refers to a function within the system for receiving menstrual cycle data provided by a user.

[0009] "Means for analyzing" refers to a function for processing received menstrual cycle data and extracting necessary information.

[0010] A "generative AI model" is a machine learning algorithm or artificial intelligence system used to predict a user's menstrual cycle.

[0011] "Prediction means" refers to the function that uses a generative AI model to estimate the start date of a user's next period and each phase.

[0012] "Health advice" is personalized advice on nutrition, exercise, and the like, provided based on the user's predicted menstrual cycle data.

[0013] "Means for generating" refers to a function for generating personalized health advice for a user based on the prediction results.

[0014] The "means for transmitting" refers to a function for sending the generated health advice to the user's terminal.

[0015] "System" means a collection of technical devices and software for performing a series of operations, including the above means. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on their specific femtech needs.

[0038] overview

[0039] The system receives and analyzes a user's menstrual cycle data, applies a generative AI model to predict menstrual cycles, and provides appropriate health advice to the user, allowing them to better manage their health.

[0040] Explanation of program processing

[0041] Server Processing

[0042] 1. Receiving User Information

[0043] The server receives data relating to the menstrual cycle (eg, the start date of the last period and the length of the cycle) from the user terminal.

[0044] For example, data can be received via an HTTP POST request in JSON format, such as:

[0045] json

[0046] {

[0047] "user_id": "12345",

[0048] "last_period_start_date": "2023-10-01",

[0049] "cycle_length": 28

[0050] }

[0051] 2. Data Analysis

[0052] The server analyzes the received data and extracts the data necessary for menstrual cycle prediction (e.g., the start date of the last menstrual period, the length of the cycle).

[0053] 3. Applying generative AI models

[0054] The server uses a generative AI model to predict the start date and phases of the user's next period.

[0055] For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the start date of your next period can be predicted as October 29, 2023.

[0056] 4. Health advice generation

[0057] Based on the prediction results of the generative AI model, the server applies health advice guidelines from the femtech field to generate individualized health advice for the user (e.g., recommendations for nutritional intake and exercise).

[0058] For example, you can generate advice like this:

[0059] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[0060] During menstruation: Stay hydrated.

[0061] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0062] 5. Submitting Advice

[0063] The server transmits the generated health advice to the user terminal.

[0064] For example, send the following JSON data as an HTTP response:

[0065] json

[0066] {

[0067] "advice": {

[0068] "nutrition": {

[0069] "pre_period": "Consume foods rich in iron and vitamin C.",

[0070] "during_period": "Stay hydrated."

[0071] },

[0072] "exercise": {

[0073] "pre_period": "Engage in light exercises or stretching.",

[0074] "during_period": "Practice yoga or walking for relaxation."

[0075] },

[0076] "predicted_next_period": "2023-10-29"

[0077] }

[0078] }

[0079] User terminal processing

[0080] 1. Data Entry

[0081] The user enters menstrual cycle data (eg, last menstrual period start date and cycle length) through the application screen.

[0082] 2. Data Transmission

[0083] The terminal sends the entered data to the server via an HTTP POST request.

[0084] 3. Receiving Advice

[0085] The device receives health advice sent as an HTTP response from the server.

[0086] 4. Displaying Advice

[0087] The device displays the received health advice on the application screen and guides the user to take appropriate action based on it.

[0088] Specific examples

[0089] Here is a concrete example of how Person A might use this system:

[0090] 1. Data entry: Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[0091] 2. Data transmission: The device transmits this information to the server.

[0092] 3. Server Processing:

[0093] The server receives and analyzes the data.

[0094] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[0095] Health advice is generated and sent back to the device.

[0096] 4. Receiving advice: The terminal receives advice from the server.

[0097] 5. Displaying advice: The device displays advice to Person A, who then manages his or her health based on that advice.

[0098] This system allows Ms. A to receive specific health advice based on her menstrual cycle, enabling her to optimally manage her health in her daily life.

[0099] The processing flow will be explained below.

[0100] Step 1:

[0101] The user opens the application and enters menstrual cycle data (last period start date and cycle length).

[0102] Step 2:

[0103] The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0104] json

[0105] {

[0106] "user_id": "12345",

[0107] "last_period_start_date": "2023-10-01",

[0108] "cycle_length": 28

[0109] }

[0110] Step 3:

[0111] The server receives the HTTP POST request and parses the JSON data, specifically extracting the last_period_start_date and cycle_length.

[0112] Step 4:

[0113] The server inputs the extracted data into the generative AI model to predict the start date of the user's next period. For example, if the input last_period_start_date is October 1, 2023, and the cycle_length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[0114] Step 5:

[0115] The server generates personalized health advice for each user based on the prediction results. Based on Femtech guidelines, the server creates personalized advice such as:

[0116] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[0117] During menstruation: Make sure you drink plenty of fluids.

[0118] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0119] Step 6:

[0120] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0121] json

[0122] {

[0123] "advice": {

[0124] "nutrition": {

[0125] "pre_period": "Consume foods rich in iron and vitamin C.",

[0126] "during_period": "Stay hydrated."

[0127] },

[0128] "exercise": {

[0129] "pre_period": "Engage in light exercises or stretching.",

[0130] "during_period": "Practice yoga or walking for relaxation."

[0131] },

[0132] "predicted_next_period": "2023-10-29"

[0133] }

[0134] }

[0135] Step 7:

[0136] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[0137] Step 8:

[0138] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[0139] Nutritional Recommendations

[0140] Exercise recommendations

[0141] Predicted start date of next period

[0142] Step 9:

[0143] The user checks the displayed health advice and puts it into practice in their daily life, for example, by eating iron-rich foods before menstruation.

[0144] Example 1

[0145] 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."

[0146] With conventional menstrual cycle management systems, it was difficult for users to receive specific advice on how to properly manage their health. Furthermore, menstrual cycle predictions were often inaccurate, making it difficult for users to trust the information and take action. As a result, users were unable to take appropriate measures at the appropriate time, which hindered their health management.

[0147] 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.

[0148] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for saving the data transmitted from the user's device and preparing input prompts for the analysis and generative AI model, means for applying health advice guidelines in the femtech field based on the prediction results, and means for returning the generated advice to the user's device. This enables the user to receive accurate menstrual cycle predictions and specific health advice based on them, enabling appropriate health management.

[0149] "User's menstrual cycle data" is a series of data related to the menstrual cycle, such as the start date of the last menstrual period and the length of the menstrual cycle, entered by the user.

[0150] A "generative AI model" is a machine learning model that predicts menstrual cycles based on past data.

[0151] An "input prompt" is a group of data that is input to the generative AI model to predict menstrual cycles.

[0152] The "Health Advice Guidelines in the Femtech Field" are guidelines for providing standard health advice in the technology field aimed at managing women's health.

[0153] "Health Advice" is personalized health guidance for a user, including nutrition and exercise recommendations, generated based on the predicted menstrual cycle.

[0154] A "user terminal" is a terminal device used by a user, and is a device for inputting menstrual cycle data and displaying health advice.

[0155] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on specific femtech needs. The system receives menstrual cycle data entered by the user, analyzes it, and then uses a generative AI model to predict the menstrual cycle and provide appropriate health advice to the user.

[0156] System configuration

[0157] The system mainly consists of the following hardware and software:

[0158] 1. Server

[0159] 2. User devices (smartphones, tablets, etc.)

[0160] 3. Generative AI Models (Machine Learning Models)

[0161] Server Features

[0162] The server has the following features:

[0163] 1. Receiving User Information

[0164] The server receives data related to the menstrual cycle (e.g., the start date of the last period and the length of the cycle) from the user terminal, often received as an HTTP POST request.

[0165] 2. Data Analysis

[0166] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction. The server obtains the "last menstrual period start date" and "cycle length" from the JSON format data and uses them in the next processing step.

[0167] 3. Applying generative AI models

[0168] The server uses the generative AI model to predict the start date and each phase of the user's next period. For example, the server inputs "Last period start date: 2023-10-01" and "Cycle length: 28 days" as input prompts to the generative AI model.

[0169] 4. Health advice generation

[0170] Based on the prediction results of the generative AI model, the server applies femtech health advice guidelines and generates personalized health advice for each user, including recommendations on nutrition and exercise.

[0171] 5. Submitting Advice

[0172] The server sends the generated health advice to the user device, typically as JSON data in an HTTP response.

[0173] User device functions

[0174] The user terminal has the following features:

[0175] 1. Data Entry

[0176] The user inputs menstrual cycle data through the application screen, specifically the start date of the last menstrual period and the length of the menstrual cycle.

[0177] 2. Data Transmission

[0178] The device sends the input data to the server via an HTTP POST request in JSON format, providing the server with the data to run the predictive model.

[0179] 3. Receiving Advice

[0180] The device receives health advice sent as an HTTP response from the server, such as the generated health advice and the start date of the next menstruation.

[0181] 4. Displaying Advice

[0182] The terminal displays the received health advice on the application screen, allowing the user to take appropriate action based on it.

[0183] Specific examples

[0184] Here is a concrete example of how Person A might use this system:

[0185] 1. Data Entry

[0186] Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[0187] 2. Data Transmission

[0188] The terminal sends this information to the server.

[0189] 3. Server Processing

[0190] The server receives and analyzes the data. For example, prompts such as "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" are input into the generative AI model.

[0191] 4. Generating predictions and advice

[0192] The generative AI model predicts the start date of the next period (October 29, 2023). Health advice is generated, such as "consume foods rich in iron and vitamin C" before menstruation and "stay hydrated" during menstruation.

[0193] 5. Receiving and displaying advice

[0194] The terminal receives advice from the server and displays it to Mr. A, who then manages his health based on it.

[0195] This system allows users to receive specific health advice based on their menstrual cycle, enabling them to optimally manage their health in their daily lives.

[0196] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0197] Specific processing flow of the program

[0198] Server Processing

[0199] Step 1: Receiving user information

[0200] The server receives data related to the menstrual cycle from the user terminal.

[0201] Input: HTTP POST request in JSON format (e.g., { "user_id": "12345", "last_period_start_date": "2023-10-01", "cycle_length": 28})

[0202] Processing: Temporarily storing data and preparing it for the next processing step.

[0203] Output: User data stored in internal data structures

[0204] Step 2: Analyze the data

[0205] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction.

[0206] Input: Saved user data

[0207] Processing: Obtain the "last period start date" and "cycle length" from the JSON data (e.g., last period start date: 2023-10-01, cycle length: 28).

[0208] Output: Analyzed data (last menstrual period start date, cycle length)

[0209] Step 3: Applying the generative AI model

[0210] The server uses a generative AI model to predict the start date and phases of the user's next period.

[0211] Input: Analyzed data (last menstrual period start date, cycle length)

[0212] Processing: The generative AI model is given the input prompts "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" to predict the menstrual cycle.

[0213] Output: Prediction result (e.g., next menstruation start date: 2023-10-29)

[0214] Step 4: Generate health advice

[0215] Based on the prediction results of the generative AI model, the server applies femtech guidelines to generate individual health advice for the user.

[0216] Input: Prediction result (start date of next period)

[0217] Treatment: Create advice based on guidelines regarding nutritional intake and exercise (e.g., before menstruation: take iron and vitamin C, during menstruation: make sure to stay hydrated).

[0218] Output: Generated health advice (e.g., {"nutrition": {"pre_period": "Consume foods rich in iron and vitamin C.", "during_period": "Stay hydrated."}, "exercise": {"pre_period": "Engage in light exercises or stretching.", "during_period": "Practice yoga or walking for relaxation."}, "predicted_next_period": "2023-10-29"})

[0219] Step 5: Submitting Advice

[0220] The server transmits the generated health advice to the user terminal.

[0221] Input: Generated health advice

[0222] Processing: Send JSON data to the user terminal as an HTTP response.

[0223] Output: Health advice sent to the user device

[0224] User terminal processing

[0225] Step 6: Data entry

[0226] The user inputs menstrual cycle data (last menstrual start date and cycle length) through the application screen.

[0227] Input: Last menstrual start date, cycle length (e.g., "Last menstrual start date: 2023-10-01", "Cycle length: 28 days")

[0228] Processing: The data entered by the user is temporarily saved in the terminal.

[0229] Output: Saved menstrual cycle data

[0230] Step 7: Send data

[0231] The terminal sends the entered data to the server via an HTTP POST request in JSON format.

[0232] Input: Saved menstrual cycle data

[0233] Operation: Generates an HTTP request and sends data to the specified server endpoint.

[0234] Output: Request sent to the server

[0235] Step 8: Receive advice

[0236] The device receives health advice sent as an HTTP response from the server.

[0237] Input: HTTP response from the server

[0238] Processing: Analyze the response content and extract the advice data.

[0239] Output: Extracted advice data

[0240] Step 9: View Advice

[0241] The device displays the received health advice on the application screen and guides the user to take appropriate action.

[0242] Input: Extracted advice data

[0243] Action: Update the UI to display the data on the application screen (e.g., "Recommended nutrients before menstruation: Iron and Vitamin C" and "Recommended behavior during menstruation: Stay hydrated").

[0244] Output: Advice displayed to the user

[0245] (Application example 1)

[0246] 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."

[0247] While systems that provide health advice based on a user's menstrual cycle already exist, they lack support that goes into the user's nutritional balance and diet. The present invention aims to provide more comprehensive support for users' health management by proposing and providing personalized food and drink menus so that users can easily eat meals that are appropriate for their menstrual cycle.

[0248] 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.

[0249] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for generating a personalized meal menu based on the predicted menstrual cycle, and means for providing the generated meal menu to the user. This makes it possible to promptly propose and provide to the user not only health advice but also nutritionally balanced meal menus suited to the user's menstrual cycle.

[0250] "User's menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last period and the length of the menstrual cycle.

[0251] The "generative AI model" is an artificial intelligence model that predicts the start date of a user's next period and each phase based on received menstrual cycle data.

[0252] "Health advice" is a recommendation regarding nutritional intake and exercise to help the user manage their health based on the predicted menstrual cycle.

[0253] A "personalized meal menu" is a food and drink menu that is individually suggested based on the user's menstrual cycle and takes into consideration the optimal nutritional balance.

[0254] The term "means" is a general concept that refers to devices and systems for realizing a specific function in this invention.

[0255] This invention is a system that receives a user's menstrual cycle data, predicts the start date of the next period using a generative AI model, and generates and provides health advice and personalized meal menus based on the prediction results. This system interacts with the user via a smartphone application and can easily provide health advice and meal menu suggestions to the user.

[0256] System Overview

[0257] Server-side processing

[0258] The server receives menstrual cycle data (e.g., the start date of the last period and the length of the cycle) sent from the user's device. The received data is analyzed and a generative AI model is used to predict the menstrual cycle. Health advice and a personalized meal plan are then generated based on the prediction results and sent to the user's device. The hardware used includes a high-performance server, and the software includes Python (server-side implementation using Flask), generative AI models (TensorFlow or PyTorch), and databases (MySQL or SQLite).

[0259] Terminal side processing

[0260] Users enter their menstrual cycle data through the smartphone application screen. This data is sent to the server via an HTTP POST request. Health advice and personalized meal menus sent from the server are received and displayed on the application screen. Users can also order delivery of the suggested menu items.

[0261] Processing flow

[0262] When a user enters the start date of their last period and the length of their cycle into the application, that data is sent to the server. The server receives and analyzes the data. It uses a generative AI model to predict the start date of the next period and generates health advice and a personalized meal plan based on the prediction. The generated data is then sent back to the user's device and displayed on the application screen.

[0263] Specific examples

[0264] For example, if a user enters "last period start date: October 1, 2023" and "cycle length: 28 days" into the application, the server receives this and uses the generative AI model to predict the next period start date (October 29, 2023). Based on the results, the following health advice is generated:

[0265] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[0266] During menstruation: Stay hydrated.

[0267] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0268] Additionally, personalized meal suggestions are also available:

[0269] Premenstrual: Spinach salad with citrus dressing, grilled chicken and quinoa.

[0270] During menstruation: Cucumber mint water, tomato and mozzarella salad.

[0271] Prompt Sentence Examples

[0272] "My last period started on October 1, 2023, and my cycle is 28 days. When is my next period? Also, what specific foods and nutrients should I be consuming throughout that period?"

[0273] In this way, the system of the present invention allows the user to receive personalized support for appropriate health management in accordance with their menstrual cycle.

[0274] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0275] Step 1:

[0276] The user inputs the "last menstrual start date" and "cycle length" through a smartphone application. This data is sent to the server as an HTTP POST request to the endpoint specified by the URI. The input data includes, for example, the user's ID, last menstrual start date, and menstrual cycle length.

[0277] Step 2:

[0278] The server analyzes the received HTTP POST request and extracts menstrual cycle data. The analyzed data is saved in the form of the menstrual start date and cycle length. The server inputs this data into a generative AI model, which processes and calculates the data to predict the menstrual cycle.

[0279] Step 3:

[0280] The server applies a generative AI model (using, for example, TensorFlow or PyTorch) to predict the start date and phases (premenstrual, menstrual, and postmenstrual) of the user's next period. The generative AI model makes a prediction based on the input data, and the output is the start date and phase information of the next period.

[0281] Step 4:

[0282] The server generates health advice based on the predicted menstrual cycle, aligned with standard health guidelines, including nutritional recommendations and exercise advice. The advice generated is specific and helpful for the user in managing their health.

[0283] Step 5:

[0284] The server then generates a personalized meal menu based on the predictions, which is designed to balance the nutritional intake of the user's menstrual cycle and includes specific dishes and ingredients recommended for each phase.

[0285] Step 6:

[0286] The server compiles the generated health advice and personalized meal menus and sends them to the user's device as an HTTP response. The output data includes health advice, the start date of the next menstrual period, and meal menus for each phase.

[0287] Step 7:

[0288] The user's device analyzes the received data and displays it on the application screen. The user can check the displayed information, such as the start date of their next period, health advice, and suggested meal menus. The user can also order the suggested menus for delivery.

[0289] Step 8:

[0290] If the user wishes to order food delivery, they confirm the selected menu items and complete the delivery order. The order is sent to the food delivery company via the smartphone app, and the meal is delivered to the user at the appropriate time.

[0291] Through the above processing steps, the present invention realizes a system that provides users with health management and dietary suggestions suited to their needs.

[0292] 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.

[0293] The present invention combines a system that predicts a user's menstrual cycle data and provides health advice based on specific femtech needs with an emotion engine that recognizes the user's emotions. This system provides more precise and personalized health care based not only on the user's health status but also on their emotional state.

[0294] overview

[0295] The system receives and analyzes the user's menstrual cycle data, then uses a generative AI model to predict the menstrual cycle. It also analyzes the user's emotional state using an emotion engine to generate and provide health advice to the user.

[0296] Explanation of program processing

[0297] Server Processing

[0298] 1. Receiving User Information

[0299] The server receives data related to the menstrual cycle (e.g., the start date of the last menstrual period and the length of the menstrual cycle) from the user terminal, as well as emotional information such as user input data, voice, and images.

[0300] For example, data can be received via an HTTP POST request in JSON format, such as:

[0301] json

[0302] {

[0303] "user_id": "12345",

[0304] "last_period_start_date": "2023-10-01",

[0305] "cycle_length": 28,

[0306] "emotion_data": {

[0307] "text": "I'm feeling stressed",

[0308] "voice": "audio_data",

[0309] "image": "image_data"

[0310] }

[0311] }

[0312] 2. Data Analysis

[0313] The server analyzes the received menstrual cycle data and extracts data necessary for menstrual cycle prediction (e.g., the start date of the last period, cycle length, etc.). It also analyzes the emotional data to identify the user's emotional state.

[0314] 3. Applying generative AI models

[0315] The server uses the generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[0316] 4. Applying the Emotion Engine

[0317] The server uses an emotion engine to analyze the user's emotional state from their input data, voice, and images. For example, if a user inputs "I'm feeling stressed," the server identifies the emotional state as "stress."

[0318] 5. Health advice generation

[0319] The server generates personalized health advice based on the prediction results of the generative AI model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, it creates advice such as:

[0320] Premenstrual period: Recommend consuming foods rich in iron and vitamin C. Also, if the emotional state is stressful, aromatherapy is recommended for relaxation.

[0321] During menstruation: Stay well hydrated and, if your emotional state is fatigue, get plenty of rest.

[0322] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0323] 6. Submitting Advice

[0324] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0325] json

[0326] {

[0327] "advice": {

[0328] "nutrition": {

[0329] "pre_period": "Consume foods rich in iron and vitamin C.",

[0330] "during_period": "Stay hydrated."

[0331] },

[0332] "exercise": {

[0333] "pre_period": "Engage in light exercises or stretching.",

[0334] "during_period": "Practice yoga or walking for relaxation."

[0335] },

[0336] "emotion": {

[0337] "stress": "Try aromatherapy to relax.",

[0338] "fatigue": "Make sure to get plenty of rest."

[0339] },

[0340] "predicted_next_period": "2023-10-29"

[0341] }

[0342] }

[0343] User terminal processing

[0344] 1. Data Entry

[0345] The user inputs menstrual cycle data (e.g., the start date of the last period and the length of the cycle) and emotional state (text, voice, image, etc.) through the application screen.

[0346] 2. Data Transmission

[0347] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request.

[0348] 3. Receiving Advice

[0349] The device receives health advice sent as an HTTP response from the server.

[0350] 4. Displaying Advice

[0351] The device displays the received health advice on the application screen and notifies the user so that they can take appropriate action based on it.

[0352] Specific examples

[0353] Here is a concrete example of how Person B might use this system:

[0354] 1. Data entry: Person B enters "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days" into the application, and also enters her emotional state in text, "I'm feeling stressed."

[0355] 2. Data transmission: The device transmits this information to the server.

[0356] 3. Server Processing:

[0357] The server receives and analyzes the data.

[0358] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[0359] The emotion engine identifies the emotion "stress."

[0360] Health advice is generated and sent back to the device.

[0361] 4. Receiving advice: The terminal receives advice from the server.

[0362] 5. Displaying Advice: The device displays advice to Person B, who can then manage his or her health based on the advice. For example, Person B may consume iron-rich foods and use aromatherapy to relieve stress.

[0363] This system allows Ms. B to receive not only specific health advice based on her menstrual cycle, but also advice tailored to her emotional state, enabling her to manage her health more effectively.

[0364] The processing flow will be explained below.

[0365] Step 1:

[0366] The user opens the application and enters menstrual cycle data (last period start date and cycle length) and emotional state (text, voice, image, etc.).

[0367] Step 2:

[0368] The device converts the input menstrual cycle data and emotion data into JSON format and sends it to the server as an HTTP POST request.

[0369] json

[0370] {

[0371] "user_id": "12345",

[0372] "last_period_start_date": "2023-10-01",

[0373] "cycle_length": 28,

[0374] "emotion_data": {

[0375] "text": "I'm feeling stressed",

[0376] "voice": "audio_data",

[0377] "image": "image_data"

[0378] }

[0379] }

[0380] Step 3:

[0381] The server receives the HTTP POST request and parses the JSON data to extract menstrual cycle data (last_period_start_date and cycle_length) and emotion data.

[0382] Step 4:

[0383] The server inputs the extracted menstrual cycle data into a generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the next period will be predicted to start on October 29, 2023.

[0384] Step 5:

[0385] The server uses an emotion engine to analyze the emotion data (text, voice, image) entered by the user and identify the user's emotional state. For example, if the text is "I'm feeling stressed," the server identifies the emotional state as "stress."

[0386] Step 6:

[0387] The server generates personalized health advice based on the prediction results of the AI ​​model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, the server generates advice such as:

[0388] For premenstrual nutrition, it is recommended to consume foods rich in iron and vitamin C.

[0389] When caring for yourself during your period, make sure you drink plenty of fluids.

[0390] If the user is feeling stressed, aromatherapy is recommended to help them relax.

[0391] As for exercise recommendations, light exercise and stretching are recommended before menstruation, and yoga or walking for relaxation during menstruation is recommended.

[0392] Step 7:

[0393] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0394] json

[0395] {

[0396] "advice": {

[0397] "nutrition": {

[0398] "pre_period": "Consume foods rich in iron and vitamin C.",

[0399] "during_period": "Stay hydrated."

[0400] },

[0401] "exercise": {

[0402] "pre_period": "Engage in light exercises or stretching.",

[0403] "during_period": "Practice yoga or walking for relaxation."

[0404] },

[0405] "emotion": {

[0406] "stress": "Try aromatherapy to relax."

[0407] },

[0408] "predicted_next_period": "2023-10-29"

[0409] }

[0410] }

[0411] Step 8:

[0412] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[0413] Step 9:

[0414] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[0415] Nutritional Recommendations

[0416] Exercise recommendations

[0417] Specific advice depending on your emotional state

[0418] Predicted start date of next period

[0419] Step 10:

[0420] The user checks the displayed health advice and puts it into practice in daily life. For example, if the user feels stressed, they can take action such as eating foods rich in iron and practicing aromatherapy.

[0421] Example 2

[0422] 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."

[0423] While current health management systems provide advice based on a user's menstrual cycle data, they lack health advice that takes into account the user's emotional state. This makes it difficult to comprehensively manage a user's overall health, and in particular, it is difficult to fully evaluate the impact of emotional stress and fatigue on health.

[0424] 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.

[0425] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for receiving the user's emotional data, means for analyzing the received emotional data, means for generating health advice based on the prediction results of the generative AI model and the analyzed emotional data, and means for transmitting the generated health advice to the user, thereby enabling more precise and personalized health care based on both the user's menstrual cycle and emotional state.

[0426] "Menstrual cycle data" is information about the user's menstruation, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[0427] The "means for receiving" is an interface for importing data from a user terminal into a server, and includes a function for receiving data using an HTTP request or other protocol.

[0428] "Means for analyzing" refers to a function that analyzes the data received by the server and performs processing to extract and understand the necessary information.

[0429] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to predict menstrual cycles, and makes highly accurate predictions based on past data.

[0430] "Emotional data" is information about the user's emotional state, and includes text, audio, and image data.

[0431] An "emotion engine" is a technology or system for analyzing emotion data and identifying a user's emotional state.

[0432] "Health advice" refers to specific recommendations or instructions regarding health management provided to the user based on the analysis results or prediction results.

[0433] The "transmission means" is an interface for returning the generated health advice to the user terminal, and includes a function for transmitting data using an HTTP response or other protocol.

[0434] This invention is a system that receives and analyzes a user's menstrual cycle data and emotional data, and provides menstrual cycle predictions and health advice using a generative AI model and emotional engine. This system operates on the basis of a server and a user terminal.

[0435] Server configuration and operation

[0436] 1. Receiving User Information

[0437] The server receives menstrual cycle data (last menstrual start date and cycle length) and emotional data (text, voice, and image) from the user's device. This allows data based on the user's situation to be collected in real time. For example, a user might enter "last menstrual start date: October 1, 2023," "cycle length: 28 days," and "I'm feeling stressed."

[0438] 2. Data Analysis

[0439] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing (NLP) engine, voice recognition software, and image recognition software, ensuring consistency and accuracy of the data.

[0440] 3. Applying generative AI models

[0441] The server applies a generative AI model based on menstrual cycle data to predict the start date of your next period. For example, if your last period started on October 1, 2023, and your cycle is 28 days long, the server predicts your next period will start on October 29, 2023. This generative AI model uses deep learning algorithms to make highly accurate predictions.

[0442] 4. Applying the Emotion Engine

[0443] The server analyzes the emotional data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[0444] 5. Health advice generation

[0445] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[0446] 6. Submitting Advice

[0447] The generated health advice is sent from the server to the user's device as an HTTP response. The advice is sent in JSON format and is displayed on the user's device after analysis.

[0448] Configuration and operation of user terminal

[0449] 1. Data Entry

[0450] Users input their menstrual cycle and emotional data through the application screen. The application provides an intuitive interface, allowing users to easily input data.

[0451] 2. Data Transmission

[0452] The user device converts the input data into JSON format and sends it to the server as an HTTP POST request. For security reasons, the communication is encrypted with SSL / TLS.

[0453] 3. Receiving and Displaying Advice

[0454] The user's device receives the advice sent from the server and displays it on the screen. It also has a notification function so that users can act quickly based on the advice. It also has a save function so that users can refer to past advice.

[0455] Specific examples

[0456] When a user uses this system, it works like this:

[0457] 1. The user enters the following information into the application: "Last period start date: October 1, 2023" and "Cycle length: 28 days" and then enters their emotional state in the text "I'm feeling stressed."

[0458] 2. The device sends this information to the server, which analyzes the data.

[0459] 3. The server uses a generative AI model to predict the start date of the next period and an emotion engine to identify the emotion "stress."

[0460] 4. The server generates personalized health advice and sends it back to the device.

[0461] 5. The device receives the advice and displays it to the user, who then manages their health based on the advice.

[0462] For example, a user may choose to eat iron-rich foods or try aromatherapy to relieve stress. The system allows users to receive specific health advice based on their menstrual cycle and emotional state, leading to more effective health management.

[0463] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0464] Step 1:

[0465] Data Entry

[0466] The user uses the application screen to input menstrual cycle data (last menstrual start date and cycle length) and emotion data (text, voice, image).

[0467] Input: Menstrual cycle data and emotion data entered by the user.

[0468] Output: Input data temporarily stored on the user's device.

[0469] Step 2:

[0470] Data transmission

[0471] The device converts the input data into JSON format and sends it to the server as an HTTP POST request. The communication is encrypted with SSL / TLS.

[0472] Input: Menstrual cycle data and emotion data entered by the user into the device.

[0473] Output: JSON formatted data sent to the server.

[0474] Step 3:

[0475] Receiving user information

[0476] The server receives the menstrual cycle data and emotion data transmitted from the user terminal.

[0477] Input: JSON formatted data.

[0478] Output: Menstrual cycle data and emotion data stored in the server's memory and database.

[0479] Step 4:

[0480] Data analysis

[0481] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing engine, voice recognition software, and image recognition software.

[0482] Input: Menstrual cycle data and emotion data stored on the server.

[0483] Output: Analyzed menstrual cycle information and emotional state.

[0484] Step 5:

[0485] Applying generative AI models

[0486] The server then applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period. For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the server will predict the start date of your next period as October 29, 2023. This process uses a deep learning algorithm.

[0487] Input: Parsed menstrual cycle information.

[0488] Output: Predicted start date of next period.

[0489] Step 6:

[0490] Applying the Emotion Engine

[0491] The server analyzes the emotion data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[0492] Input: Parsed emotion data.

[0493] Output: Identified emotional state.

[0494] Step 7:

[0495] Generating health advice

[0496] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[0497] Input: Predicted start date of next period and identified emotional state.

[0498] Output: The generated health advice.

[0499] Step 8:

[0500] Sending Advice

[0501] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0502] Input: Generated health advice.

[0503] Output: Health advice in JSON format sent to user device.

[0504] Step 9:

[0505] Receiving and viewing advice

[0506] The device receives health advice sent from the server and displays it on the application screen. A notification function is also provided so that users can act on the advice quickly. There is also a function to save past advice.

[0507] Input: Health advice sent from the server in JSON format.

[0508] Output: Health advice and notifications displayed on the application screen.

[0509] (Application example 2)

[0510] 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."

[0511] The challenge is to provide a system that can increase user satisfaction with food delivery services and assist with health management by providing health advice and food suggestions based on the user's menstrual cycle and emotional state. Currently, food suggestions are made without taking menstrual cycles or emotional states into consideration, so it is often not possible to suggest foods that are optimal for each individual user. Therefore, there is a need for a system that can provide precise, personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[0512] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0513] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model to predict the menstrual cycle based on the analysis results, means for applying an emotion engine to analyze the user's emotion data and identify the user's emotional state, means for generating health advice and food suggestions based on the predicted menstrual cycle and emotional state, and means for transmitting the generated health advice and food suggestions to the user, thereby enabling precise and personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[0514] "Menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[0515] A "generative AI model" is an artificial intelligence model that analyzes received menstrual cycle data and predicts the start date of the next period and other cycle data.

[0516] The "emotion engine" is an analytical engine that analyzes user input data, voice data, and image data to identify the user's emotional state.

[0517] "Health advice" is specific health management recommendations such as nutritional intake and exercise based on the user's menstrual cycle and emotional state.

[0518] "Food Suggestion" refers to recommending specific foods to improve a user's health based on their menstrual cycle and emotional state.

[0519] The "means for transmitting to the user" refers to a communication means for transmitting the generated health advice and food suggestions to the user's terminal.

[0520] The present invention provides a system for providing health advice and food recommendations based on a user's menstrual cycle and emotional state in a food delivery service. The system is implemented in the following steps.

[0521] The server first receives menstrual cycle data and emotional data from the user terminal, including the start date of the last period, the length of the period, and text, audio, and image data related to the user's emotional state.

[0522] The server then analyzes the received data: it analyzes menstrual cycle data and uses a generative AI model to predict the start date of the next period, and it analyzes emotional data using an emotion engine to identify the user's emotional state.

[0523] Based on the analysis results, the server generates health advice and food suggestions based on the user's menstrual cycle and emotional state. Specifically, it recommends that the user consume foods rich in iron and vitamin C before their period, and that they try aromatherapy to relax when they are stressed.

[0524] The generated health advice and food suggestions are sent from the server to the user's device. The user receives this information through the application and manages their health based on the displayed health advice and food suggestions. Specifically, the user can directly order the suggested foods within the application and have them delivered.

[0525] For example, if user B uses this system,

[0526] 1. If you enter "Last period start date: October 1, 2023" and "Cycle length: 28 days" and say "I'm feeling stressed," the server will predict the start date of your next period as October 29, 2023, and suggest aromatic teas and vitamin-rich fruits as foods to relieve stress.

[0527] 2. After checking the displayed advice, User B can immediately put it into action by ordering the suggested food through the application and having it delivered.

[0528] To illustrate, here are some example prompts:

[0529] "User: My last period started on October 1, 2023, and my cycle length is 28 days. I'm also feeling stressed. What is the start date of my next period and what foods do you recommend?"

[0530] This allows users to receive health advice and food suggestions that are best suited to their individual conditions, allowing them to effectively manage their health while increasing their satisfaction with the food delivery service.

[0531] The key technical components of this system are a generative AI model and an emotion engine, the latter of which analyzes the user's emotional data, and the former of which predicts the start date of the next period based on cycle data.

[0532] In certain embodiments, a Flask server acts as the central point for receiving and analyzing data from users, while the emotion engine and generative AI models are implemented using specialized software or libraries.

[0533] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0534] Step 1:

[0535] The user inputs menstrual cycle data and emotional data through the device. Specifically, the user inputs the "last menstrual period start date" and "cycle length" on the application screen, and inputs text, voice, or images related to their emotional state.

[0536] Input: User's menstrual cycle data (last menstrual start date, cycle length) and emotional data (text, voice, image)

[0537] Output: JSON formatted menstrual cycle data and emotion data

[0538] Step 2:

[0539] The device converts the input data into JSON format and sends it to the server. Specifically, the data entered by the user is sent to the server via an HTTP POST request.

[0540] Input: Menstrual cycle data and emotion data entered by the user into the device

[0541] Output: JSON data sent to the server

[0542] Step 3:

[0543] The server receives and analyzes the data sent by the user. Specifically, the server receives an HTTP request and parses and analyzes the data in JSON format.

[0544] Input: JSON data sent from the terminal

[0545] Output: Analyzed menstrual cycle data and emotion data

[0546] Step 4:

[0547] The server applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period.Specifically, the generative AI model inputs menstrual cycle data and estimates the start date of the next period.

[0548] Input: Analyzed menstrual cycle data (last menstrual start date, cycle length)

[0549] Output: Predicted start date of next period

[0550] Step 5:

[0551] The server analyzes the emotional data using an emotion engine to identify the user's emotional state. Specifically, it analyzes text, voice, and image data to identify the user's emotional state.

[0552] Input: Analyzed emotion data (text, audio, images)

[0553] Output: Identified emotional state

[0554] Step 6:

[0555] The server generates health advice and food suggestions based on the menstrual cycle prediction results and emotional state.Specifically, it generates nutrition advice, exercise advice, and appropriate food suggestions based on femtech guidelines and emotional data.

[0556] Input: Predicted next period start date, identified emotional state

[0557] Output: Health advice and food suggestions

[0558] Step 7:

[0559] The server converts the generated health advice and food suggestions into JSON format and sends it to the user's device as an HTTP response.

[0560] Input: Generated health advice and food suggestions

[0561] Output: JSON data sent to the user's device

[0562] Step 8:

[0563] The device analyzes the health advice and food suggestions received from the server and displays them to the user. Specifically, the device displays the received data on the application screen and notifies the user so that they can act accordingly.

[0564] Input: JSON data received from the server

[0565] Output: Health advice and food suggestions displayed on the application screen

[0566] Step 9:

[0567] The user orders the suggested food through the application and requests delivery. Specifically, the user selects the food within the application and places an order and requests delivery.

[0568] Input: Food selected by user

[0569] Output: Food ordered and delivery request

[0570] 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.

[0571] 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.

[0572] 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.

[0573] [Second embodiment]

[0574] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0575] 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.

[0576] 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).

[0577] 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.

[0578] 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.

[0579] 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).

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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."

[0586] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on their specific femtech needs.

[0587] overview

[0588] The system receives and analyzes a user's menstrual cycle data, applies a generative AI model to predict menstrual cycles, and provides appropriate health advice to the user, allowing them to better manage their health.

[0589] Explanation of program processing

[0590] Server Processing

[0591] 1. Receiving User Information

[0592] The server receives data relating to the menstrual cycle (eg, the start date of the last period and the length of the cycle) from the user terminal.

[0593] For example, data can be received via an HTTP POST request in JSON format, such as:

[0594] json

[0595] {

[0596] "user_id": "12345",

[0597] "last_period_start_date": "2023-10-01",

[0598] "cycle_length": 28

[0599] }

[0600] 2. Data Analysis

[0601] The server analyzes the received data and extracts the data necessary for menstrual cycle prediction (e.g., the start date of the last menstrual period, the length of the cycle).

[0602] 3. Applying generative AI models

[0603] The server uses a generative AI model to predict the start date and phases of the user's next period.

[0604] For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the start date of your next period can be predicted as October 29, 2023.

[0605] 4. Health advice generation

[0606] Based on the prediction results of the generative AI model, the server applies health advice guidelines from the femtech field to generate individualized health advice for the user (e.g., recommendations for nutritional intake and exercise).

[0607] For example, you can generate advice like this:

[0608] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[0609] During menstruation: Stay hydrated.

[0610] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0611] 5. Submitting Advice

[0612] The server transmits the generated health advice to the user terminal.

[0613] For example, send the following JSON data as an HTTP response:

[0614] json

[0615] {

[0616] "advice": {

[0617] "nutrition": {

[0618] "pre_period": "Consume foods rich in iron and vitamin C.",

[0619] "during_period": "Stay hydrated."

[0620] },

[0621] "exercise": {

[0622] "pre_period": "Engage in light exercises or stretching.",

[0623] "during_period": "Practice yoga or walking for relaxation."

[0624] },

[0625] "predicted_next_period": "2023-10-29"

[0626] }

[0627] }

[0628] User terminal processing

[0629] 1. Data Entry

[0630] The user enters menstrual cycle data (eg, last menstrual period start date and cycle length) through the application screen.

[0631] 2. Data Transmission

[0632] The terminal sends the entered data to the server via an HTTP POST request.

[0633] 3. Receiving Advice

[0634] The device receives health advice sent as an HTTP response from the server.

[0635] 4. Displaying Advice

[0636] The device displays the received health advice on the application screen and guides the user to take appropriate action based on it.

[0637] Specific examples

[0638] Here is a concrete example of how Person A might use this system:

[0639] 1. Data entry: Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[0640] 2. Data transmission: The device transmits this information to the server.

[0641] 3. Server Processing:

[0642] The server receives and analyzes the data.

[0643] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[0644] Health advice is generated and sent back to the device.

[0645] 4. Receiving advice: The terminal receives advice from the server.

[0646] 5. Displaying advice: The device displays advice to Person A, who then manages his or her health based on that advice.

[0647] This system allows Ms. A to receive specific health advice based on her menstrual cycle, enabling her to optimally manage her health in her daily life.

[0648] The processing flow will be explained below.

[0649] Step 1:

[0650] The user opens the application and enters menstrual cycle data (last period start date and cycle length).

[0651] Step 2:

[0652] The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0653] json

[0654] {

[0655] "user_id": "12345",

[0656] "last_period_start_date": "2023-10-01",

[0657] "cycle_length": 28

[0658] }

[0659] Step 3:

[0660] The server receives the HTTP POST request and parses the JSON data, specifically extracting the last_period_start_date and cycle_length.

[0661] Step 4:

[0662] The server inputs the extracted data into the generative AI model to predict the start date of the user's next period. For example, if the input last_period_start_date is October 1, 2023, and the cycle_length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[0663] Step 5:

[0664] The server generates personalized health advice for each user based on the prediction results. Based on Femtech guidelines, the server creates personalized advice such as:

[0665] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[0666] During menstruation: Make sure you drink plenty of fluids.

[0667] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0668] Step 6:

[0669] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0670] json

[0671] {

[0672] "advice": {

[0673] "nutrition": {

[0674] "pre_period": "Consume foods rich in iron and vitamin C.",

[0675] "during_period": "Stay hydrated."

[0676] },

[0677] "exercise": {

[0678] "pre_period": "Engage in light exercises or stretching.",

[0679] "during_period": "Practice yoga or walking for relaxation."

[0680] },

[0681] "predicted_next_period": "2023-10-29"

[0682] }

[0683] }

[0684] Step 7:

[0685] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[0686] Step 8:

[0687] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[0688] Nutritional Recommendations

[0689] Exercise recommendations

[0690] Predicted start date of next period

[0691] Step 9:

[0692] The user checks the displayed health advice and puts it into practice in their daily life, for example, by eating iron-rich foods before menstruation.

[0693] Example 1

[0694] 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."

[0695] With conventional menstrual cycle management systems, it was difficult for users to receive specific advice on how to properly manage their health. Furthermore, menstrual cycle predictions were often inaccurate, making it difficult for users to trust the information and take action. As a result, users were unable to take appropriate measures at the appropriate time, which hindered their health management.

[0696] 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.

[0697] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for saving the data transmitted from the user's device and preparing input prompts for the analysis and generative AI model, means for applying health advice guidelines in the femtech field based on the prediction results, and means for returning the generated advice to the user's device. This enables the user to receive accurate menstrual cycle predictions and specific health advice based on them, enabling appropriate health management.

[0698] "User's menstrual cycle data" is a series of data related to the menstrual cycle, such as the start date of the last menstrual period and the length of the menstrual cycle, entered by the user.

[0699] A "generative AI model" is a machine learning model that predicts menstrual cycles based on past data.

[0700] An "input prompt" is a group of data that is input to the generative AI model to predict menstrual cycles.

[0701] The "Health Advice Guidelines in the Femtech Field" are guidelines for providing standard health advice in the technology field aimed at managing women's health.

[0702] "Health Advice" is personalized health guidance for a user, including nutrition and exercise recommendations, generated based on the predicted menstrual cycle.

[0703] A "user terminal" is a terminal device used by a user, and is a device for inputting menstrual cycle data and displaying health advice.

[0704] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on specific femtech needs. The system receives menstrual cycle data entered by the user, analyzes it, and then uses a generative AI model to predict the menstrual cycle and provide appropriate health advice to the user.

[0705] System configuration

[0706] The system mainly consists of the following hardware and software:

[0707] 1. Server

[0708] 2. User devices (smartphones, tablets, etc.)

[0709] 3. Generative AI Models (Machine Learning Models)

[0710] Server Features

[0711] The server has the following features:

[0712] 1. Receiving User Information

[0713] The server receives data related to the menstrual cycle (e.g., the start date of the last period and the length of the cycle) from the user terminal, often received as an HTTP POST request.

[0714] 2. Data Analysis

[0715] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction. The server obtains the "last menstrual period start date" and "cycle length" from the JSON format data and uses them in the next processing step.

[0716] 3. Applying generative AI models

[0717] The server uses the generative AI model to predict the start date and each phase of the user's next period. For example, the server inputs "Last period start date: 2023-10-01" and "Cycle length: 28 days" as input prompts to the generative AI model.

[0718] 4. Health advice generation

[0719] Based on the prediction results of the generative AI model, the server applies femtech health advice guidelines and generates personalized health advice for each user, including recommendations on nutrition and exercise.

[0720] 5. Submitting Advice

[0721] The server sends the generated health advice to the user device, typically as JSON data in an HTTP response.

[0722] User device functions

[0723] The user terminal has the following features:

[0724] 1. Data Entry

[0725] The user inputs menstrual cycle data through the application screen, specifically the start date of the last menstrual period and the length of the menstrual cycle.

[0726] 2. Data Transmission

[0727] The device sends the input data to the server via an HTTP POST request in JSON format, providing the server with the data to run the predictive model.

[0728] 3. Receiving Advice

[0729] The device receives health advice sent as an HTTP response from the server, such as the generated health advice and the start date of the next menstruation.

[0730] 4. Displaying Advice

[0731] The terminal displays the received health advice on the application screen, allowing the user to take appropriate action based on it.

[0732] Specific examples

[0733] Here is a concrete example of how Person A might use this system:

[0734] 1. Data Entry

[0735] Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[0736] 2. Data Transmission

[0737] The terminal sends this information to the server.

[0738] 3. Server Processing

[0739] The server receives and analyzes the data. For example, prompts such as "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" are input into the generative AI model.

[0740] 4. Generating predictions and advice

[0741] The generative AI model predicts the start date of the next period (October 29, 2023). Health advice is generated, such as "consume foods rich in iron and vitamin C" before menstruation and "stay hydrated" during menstruation.

[0742] 5. Receiving and displaying advice

[0743] The terminal receives advice from the server and displays it to Mr. A, who then manages his health based on it.

[0744] This system allows users to receive specific health advice based on their menstrual cycle, enabling them to optimally manage their health in their daily lives.

[0745] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0746] Specific processing flow of the program

[0747] Server Processing

[0748] Step 1: Receiving user information

[0749] The server receives data related to the menstrual cycle from the user terminal.

[0750] Input: HTTP POST request in JSON format (e.g., { "user_id": "12345", "last_period_start_date": "2023-10-01", "cycle_length": 28})

[0751] Processing: Temporarily storing data and preparing it for the next processing step.

[0752] Output: User data stored in internal data structures

[0753] Step 2: Analyze the data

[0754] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction.

[0755] Input: Saved user data

[0756] Processing: Obtain the "last period start date" and "cycle length" from the JSON data (e.g., last period start date: 2023-10-01, cycle length: 28).

[0757] Output: Analyzed data (last menstrual period start date, cycle length)

[0758] Step 3: Applying the generative AI model

[0759] The server uses a generative AI model to predict the start date and phases of the user's next period.

[0760] Input: Analyzed data (last menstrual period start date, cycle length)

[0761] Processing: The generative AI model is given the input prompts "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" to predict the menstrual cycle.

[0762] Output: Prediction result (e.g., next menstruation start date: 2023-10-29)

[0763] Step 4: Generate health advice

[0764] Based on the prediction results of the generative AI model, the server applies femtech guidelines to generate individual health advice for the user.

[0765] Input: Prediction result (start date of next period)

[0766] Treatment: Create advice based on guidelines regarding nutritional intake and exercise (e.g., before menstruation: take iron and vitamin C, during menstruation: make sure to stay hydrated).

[0767] Output: Generated health advice (e.g., {"nutrition": {"pre_period": "Consume foods rich in iron and vitamin C.", "during_period": "Stay hydrated."}, "exercise": {"pre_period": "Engage in light exercises or stretching.", "during_period": "Practice yoga or walking for relaxation."}, "predicted_next_period": "2023-10-29"})

[0768] Step 5: Submitting Advice

[0769] The server transmits the generated health advice to the user terminal.

[0770] Input: Generated health advice

[0771] Processing: Send JSON data to the user terminal as an HTTP response.

[0772] Output: Health advice sent to the user device

[0773] User terminal processing

[0774] Step 6: Data entry

[0775] The user inputs menstrual cycle data (last menstrual start date and cycle length) through the application screen.

[0776] Input: Last menstrual start date, cycle length (e.g., "Last menstrual start date: 2023-10-01", "Cycle length: 28 days")

[0777] Processing: The data entered by the user is temporarily saved in the terminal.

[0778] Output: Saved menstrual cycle data

[0779] Step 7: Send data

[0780] The terminal sends the entered data to the server via an HTTP POST request in JSON format.

[0781] Input: Saved menstrual cycle data

[0782] Operation: Generates an HTTP request and sends data to the specified server endpoint.

[0783] Output: Request sent to the server

[0784] Step 8: Receive advice

[0785] The device receives health advice sent as an HTTP response from the server.

[0786] Input: HTTP response from the server

[0787] Processing: Analyze the response content and extract the advice data.

[0788] Output: Extracted advice data

[0789] Step 9: View Advice

[0790] The device displays the received health advice on the application screen and guides the user to take appropriate action.

[0791] Input: Extracted advice data

[0792] Action: Update the UI to display the data on the application screen (e.g., "Recommended nutrients before menstruation: Iron and Vitamin C" and "Recommended behavior during menstruation: Stay hydrated").

[0793] Output: Advice displayed to the user

[0794] (Application example 1)

[0795] 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."

[0796] While systems that provide health advice based on a user's menstrual cycle already exist, they lack support that goes into the user's nutritional balance and diet. The present invention aims to provide more comprehensive support for users' health management by proposing and providing personalized food and drink menus so that users can easily eat meals that are appropriate for their menstrual cycle.

[0797] 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.

[0798] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for generating a personalized meal menu based on the predicted menstrual cycle, and means for providing the generated meal menu to the user. This makes it possible to promptly propose and provide to the user not only health advice but also nutritionally balanced meal menus suited to the user's menstrual cycle.

[0799] "User's menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last period and the length of the menstrual cycle.

[0800] The "generative AI model" is an artificial intelligence model that predicts the start date of a user's next period and each phase based on received menstrual cycle data.

[0801] "Health advice" is a recommendation regarding nutritional intake and exercise to help the user manage their health based on the predicted menstrual cycle.

[0802] A "personalized meal menu" is a food and drink menu that is individually suggested based on the user's menstrual cycle and takes into consideration the optimal nutritional balance.

[0803] The term "means" is a general concept that refers to devices and systems for realizing a specific function in this invention.

[0804] This invention is a system that receives a user's menstrual cycle data, predicts the start date of the next period using a generative AI model, and generates and provides health advice and personalized meal menus based on the prediction results. This system interacts with the user via a smartphone application and can easily provide health advice and meal menu suggestions to the user.

[0805] System Overview

[0806] Server-side processing

[0807] The server receives menstrual cycle data (e.g., the start date of the last period and the length of the cycle) sent from the user's device. The received data is analyzed and a generative AI model is used to predict the menstrual cycle. Health advice and a personalized meal plan are then generated based on the prediction results and sent to the user's device. The hardware used includes a high-performance server, and the software includes Python (server-side implementation using Flask), generative AI models (TensorFlow or PyTorch), and databases (MySQL or SQLite).

[0808] Terminal side processing

[0809] Users enter their menstrual cycle data through the smartphone application screen. This data is sent to the server via an HTTP POST request. Health advice and personalized meal menus sent from the server are received and displayed on the application screen. Users can also order delivery of the suggested menu items.

[0810] Processing flow

[0811] When a user enters the start date of their last period and the length of their cycle into the application, that data is sent to the server. The server receives and analyzes the data. It uses a generative AI model to predict the start date of the next period and generates health advice and a personalized meal plan based on the prediction. The generated data is then sent back to the user's device and displayed on the application screen.

[0812] Specific examples

[0813] For example, if a user enters "last period start date: October 1, 2023" and "cycle length: 28 days" into the application, the server receives this and uses the generative AI model to predict the next period start date (October 29, 2023). Based on the results, the following health advice is generated:

[0814] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[0815] During menstruation: Stay hydrated.

[0816] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0817] Additionally, personalized meal suggestions are also available:

[0818] Premenstrual: Spinach salad with citrus dressing, grilled chicken and quinoa.

[0819] During menstruation: Cucumber mint water, tomato and mozzarella salad.

[0820] Prompt Sentence Examples

[0821] "My last period started on October 1, 2023, and my cycle is 28 days. When is my next period? Also, what specific foods and nutrients should I be consuming throughout that period?"

[0822] In this way, the system of the present invention allows the user to receive personalized support for appropriate health management in accordance with their menstrual cycle.

[0823] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0824] Step 1:

[0825] The user inputs the "last menstrual start date" and "cycle length" through a smartphone application. This data is sent to the server as an HTTP POST request to the endpoint specified by the URI. The input data includes, for example, the user's ID, last menstrual start date, and menstrual cycle length.

[0826] Step 2:

[0827] The server analyzes the received HTTP POST request and extracts menstrual cycle data. The analyzed data is saved in the form of the menstrual start date and cycle length. The server inputs this data into a generative AI model, which processes and calculates the data to predict the menstrual cycle.

[0828] Step 3:

[0829] The server applies a generative AI model (using, for example, TensorFlow or PyTorch) to predict the start date and phases (premenstrual, menstrual, and postmenstrual) of the user's next period. The generative AI model makes a prediction based on the input data, and the output is the start date and phase information of the next period.

[0830] Step 4:

[0831] The server generates health advice based on the predicted menstrual cycle, aligned with standard health guidelines, including nutritional recommendations and exercise advice. The advice generated is specific and helpful for the user in managing their health.

[0832] Step 5:

[0833] The server then generates a personalized meal menu based on the predictions, which is designed to balance the nutritional intake of the user's menstrual cycle and includes specific dishes and ingredients recommended for each phase.

[0834] Step 6:

[0835] The server compiles the generated health advice and personalized meal menus and sends them to the user's device as an HTTP response. The output data includes health advice, the start date of the next menstrual period, and meal menus for each phase.

[0836] Step 7:

[0837] The user's device analyzes the received data and displays it on the application screen. The user can check the displayed information, such as the start date of their next period, health advice, and suggested meal menus. The user can also order the suggested menus for delivery.

[0838] Step 8:

[0839] If the user wishes to order food delivery, they confirm the selected menu items and complete the delivery order. The order is sent to the food delivery company via the smartphone app, and the meal is delivered to the user at the appropriate time.

[0840] Through the above processing steps, the present invention realizes a system that provides users with health management and dietary suggestions suited to their needs.

[0841] 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.

[0842] The present invention combines a system that predicts a user's menstrual cycle data and provides health advice based on specific femtech needs with an emotion engine that recognizes the user's emotions. This system provides more precise and personalized health care based not only on the user's health status but also on their emotional state.

[0843] overview

[0844] The system receives and analyzes the user's menstrual cycle data, then uses a generative AI model to predict the menstrual cycle. It also analyzes the user's emotional state using an emotion engine to generate and provide health advice to the user.

[0845] Explanation of program processing

[0846] Server Processing

[0847] 1. Receiving User Information

[0848] The server receives data related to the menstrual cycle (e.g., the start date of the last menstrual period and the length of the menstrual cycle) from the user terminal, as well as emotional information such as user input data, voice, and images.

[0849] For example, data can be received via an HTTP POST request in JSON format, such as:

[0850] json

[0851] {

[0852] "user_id": "12345",

[0853] "last_period_start_date": "2023-10-01",

[0854] "cycle_length": 28,

[0855] "emotion_data": {

[0856] "text": "I'm feeling stressed",

[0857] "voice": "audio_data",

[0858] "image": "image_data"

[0859] }

[0860] }

[0861] 2. Data Analysis

[0862] The server analyzes the received menstrual cycle data and extracts data necessary for menstrual cycle prediction (e.g., the start date of the last period, cycle length, etc.). It also analyzes the emotional data to identify the user's emotional state.

[0863] 3. Applying generative AI models

[0864] The server uses the generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[0865] 4. Applying the Emotion Engine

[0866] The server uses an emotion engine to analyze the user's emotional state from their input data, voice, and images. For example, if a user inputs "I'm feeling stressed," the server identifies the emotional state as "stress."

[0867] 5. Health advice generation

[0868] The server generates personalized health advice based on the prediction results of the generative AI model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, it creates advice such as:

[0869] Premenstrual period: Recommend consuming foods rich in iron and vitamin C. Also, if the emotional state is stressful, aromatherapy is recommended for relaxation.

[0870] During menstruation: Stay well hydrated and, if your emotional state is fatigue, get plenty of rest.

[0871] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[0872] 6. Submitting Advice

[0873] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0874] json

[0875] {

[0876] "advice": {

[0877] "nutrition": {

[0878] "pre_period": "Consume foods rich in iron and vitamin C.",

[0879] "during_period": "Stay hydrated."

[0880] },

[0881] "exercise": {

[0882] "pre_period": "Engage in light exercises or stretching.",

[0883] "during_period": "Practice yoga or walking for relaxation."

[0884] },

[0885] "emotion": {

[0886] "stress": "Try aromatherapy to relax.",

[0887] "fatigue": "Make sure to get plenty of rest."

[0888] },

[0889] "predicted_next_period": "2023-10-29"

[0890] }

[0891] }

[0892] User terminal processing

[0893] 1. Data Entry

[0894] The user inputs menstrual cycle data (e.g., the start date of the last period and the length of the cycle) and emotional state (text, voice, image, etc.) through the application screen.

[0895] 2. Data Transmission

[0896] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request.

[0897] 3. Receiving Advice

[0898] The device receives health advice sent as an HTTP response from the server.

[0899] 4. Displaying Advice

[0900] The device displays the received health advice on the application screen and notifies the user so that they can take appropriate action based on it.

[0901] Specific examples

[0902] Here is a concrete example of how Person B might use this system:

[0903] 1. Data entry: Person B enters "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days" into the application, and also enters her emotional state in text, "I'm feeling stressed."

[0904] 2. Data transmission: The device transmits this information to the server.

[0905] 3. Server Processing:

[0906] The server receives and analyzes the data.

[0907] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[0908] The emotion engine identifies the emotion "stress."

[0909] Health advice is generated and sent back to the device.

[0910] 4. Receiving advice: The terminal receives advice from the server.

[0911] 5. Displaying Advice: The device displays advice to Person B, who can then manage his or her health based on the advice. For example, Person B may consume iron-rich foods and use aromatherapy to relieve stress.

[0912] This system allows Ms. B to receive not only specific health advice based on her menstrual cycle, but also advice tailored to her emotional state, enabling her to manage her health more effectively.

[0913] The processing flow will be explained below.

[0914] Step 1:

[0915] The user opens the application and enters menstrual cycle data (last period start date and cycle length) and emotional state (text, voice, image, etc.).

[0916] Step 2:

[0917] The device converts the input menstrual cycle data and emotion data into JSON format and sends it to the server as an HTTP POST request.

[0918] json

[0919] {

[0920] "user_id": "12345",

[0921] "last_period_start_date": "2023-10-01",

[0922] "cycle_length": 28,

[0923] "emotion_data": {

[0924] "text": "I'm feeling stressed",

[0925] "voice": "audio_data",

[0926] "image": "image_data"

[0927] }

[0928] }

[0929] Step 3:

[0930] The server receives the HTTP POST request and parses the JSON data to extract menstrual cycle data (last_period_start_date and cycle_length) and emotion data.

[0931] Step 4:

[0932] The server inputs the extracted menstrual cycle data into a generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the next period will be predicted to start on October 29, 2023.

[0933] Step 5:

[0934] The server uses an emotion engine to analyze the emotion data (text, voice, image) entered by the user and identify the user's emotional state. For example, if the text is "I'm feeling stressed," the server identifies the emotional state as "stress."

[0935] Step 6:

[0936] The server generates personalized health advice based on the prediction results of the AI ​​model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, the server generates advice such as:

[0937] For premenstrual nutrition, it is recommended to consume foods rich in iron and vitamin C.

[0938] When caring for yourself during your period, make sure you drink plenty of fluids.

[0939] If the user is feeling stressed, aromatherapy is recommended to help them relax.

[0940] As for exercise recommendations, light exercise and stretching are recommended before menstruation, and yoga or walking for relaxation during menstruation is recommended.

[0941] Step 7:

[0942] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[0943] json

[0944] {

[0945] "advice": {

[0946] "nutrition": {

[0947] "pre_period": "Consume foods rich in iron and vitamin C.",

[0948] "during_period": "Stay hydrated."

[0949] },

[0950] "exercise": {

[0951] "pre_period": "Engage in light exercises or stretching.",

[0952] "during_period": "Practice yoga or walking for relaxation."

[0953] },

[0954] "emotion": {

[0955] "stress": "Try aromatherapy to relax."

[0956] },

[0957] "predicted_next_period": "2023-10-29"

[0958] }

[0959] }

[0960] Step 8:

[0961] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[0962] Step 9:

[0963] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[0964] Nutritional Recommendations

[0965] Exercise recommendations

[0966] Specific advice depending on your emotional state

[0967] Predicted start date of next period

[0968] Step 10:

[0969] The user checks the displayed health advice and puts it into practice in daily life. For example, if the user feels stressed, they can take action such as eating foods rich in iron and practicing aromatherapy.

[0970] Example 2

[0971] 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."

[0972] While current health management systems provide advice based on a user's menstrual cycle data, they lack health advice that takes into account the user's emotional state. This makes it difficult to comprehensively manage a user's overall health, and in particular, it is difficult to fully evaluate the impact of emotional stress and fatigue on health.

[0973] 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.

[0974] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for receiving the user's emotional data, means for analyzing the received emotional data, means for generating health advice based on the prediction results of the generative AI model and the analyzed emotional data, and means for transmitting the generated health advice to the user, thereby enabling more precise and personalized health care based on both the user's menstrual cycle and emotional state.

[0975] "Menstrual cycle data" is information about the user's menstruation, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[0976] The "means for receiving" is an interface for importing data from a user terminal into a server, and includes a function for receiving data using an HTTP request or other protocol.

[0977] "Means for analyzing" refers to a function that analyzes the data received by the server and performs processing to extract and understand the necessary information.

[0978] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to predict menstrual cycles, and makes highly accurate predictions based on past data.

[0979] "Emotional data" is information about the user's emotional state, and includes text, audio, and image data.

[0980] An "emotion engine" is a technology or system for analyzing emotion data and identifying a user's emotional state.

[0981] "Health advice" refers to specific recommendations or instructions regarding health management provided to the user based on the analysis results or prediction results.

[0982] The "transmission means" is an interface for returning the generated health advice to the user terminal, and includes a function for transmitting data using an HTTP response or other protocol.

[0983] This invention is a system that receives and analyzes a user's menstrual cycle data and emotional data, and provides menstrual cycle predictions and health advice using a generative AI model and emotional engine. This system operates on the basis of a server and a user terminal.

[0984] Server configuration and operation

[0985] 1. Receiving User Information

[0986] The server receives menstrual cycle data (last menstrual start date and cycle length) and emotional data (text, voice, and image) from the user's device. This allows data based on the user's situation to be collected in real time. For example, a user might enter "last menstrual start date: October 1, 2023," "cycle length: 28 days," and "I'm feeling stressed."

[0987] 2. Data Analysis

[0988] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing (NLP) engine, voice recognition software, and image recognition software, ensuring consistency and accuracy of the data.

[0989] 3. Applying generative AI models

[0990] The server applies a generative AI model based on menstrual cycle data to predict the start date of your next period. For example, if your last period started on October 1, 2023, and your cycle is 28 days long, the server predicts your next period will start on October 29, 2023. This generative AI model uses deep learning algorithms to make highly accurate predictions.

[0991] 4. Applying the Emotion Engine

[0992] The server analyzes the emotional data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[0993] 5. Health advice generation

[0994] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[0995] 6. Submitting Advice

[0996] The generated health advice is sent from the server to the user's device as an HTTP response. The advice is sent in JSON format and is displayed on the user's device after analysis.

[0997] Configuration and operation of user terminal

[0998] 1. Data Entry

[0999] Users input their menstrual cycle and emotional data through the application screen. The application provides an intuitive interface, allowing users to easily input data.

[1000] 2. Data Transmission

[1001] The user device converts the input data into JSON format and sends it to the server as an HTTP POST request. For security reasons, the communication is encrypted with SSL / TLS.

[1002] 3. Receiving and Displaying Advice

[1003] The user's device receives the advice sent from the server and displays it on the screen. It also has a notification function so that users can act quickly based on the advice. It also has a save function so that users can refer to past advice.

[1004] Specific examples

[1005] When a user uses this system, it works like this:

[1006] 1. The user enters the following information into the application: "Last period start date: October 1, 2023" and "Cycle length: 28 days" and then enters their emotional state in the text "I'm feeling stressed."

[1007] 2. The device sends this information to the server, which analyzes the data.

[1008] 3. The server uses a generative AI model to predict the start date of the next period and an emotion engine to identify the emotion "stress."

[1009] 4. The server generates personalized health advice and sends it back to the device.

[1010] 5. The device receives the advice and displays it to the user, who then manages their health based on the advice.

[1011] For example, a user may choose to eat iron-rich foods or try aromatherapy to relieve stress. The system allows users to receive specific health advice based on their menstrual cycle and emotional state, leading to more effective health management.

[1012] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1013] Step 1:

[1014] Data Entry

[1015] The user uses the application screen to input menstrual cycle data (last menstrual start date and cycle length) and emotion data (text, voice, image).

[1016] Input: Menstrual cycle data and emotion data entered by the user.

[1017] Output: Input data temporarily stored on the user's device.

[1018] Step 2:

[1019] Data transmission

[1020] The device converts the input data into JSON format and sends it to the server as an HTTP POST request. The communication is encrypted with SSL / TLS.

[1021] Input: Menstrual cycle data and emotion data entered by the user into the device.

[1022] Output: JSON formatted data sent to the server.

[1023] Step 3:

[1024] Receiving user information

[1025] The server receives the menstrual cycle data and emotion data transmitted from the user terminal.

[1026] Input: JSON formatted data.

[1027] Output: Menstrual cycle data and emotion data stored in the server's memory and database.

[1028] Step 4:

[1029] Data analysis

[1030] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing engine, voice recognition software, and image recognition software.

[1031] Input: Menstrual cycle data and emotion data stored on the server.

[1032] Output: Analyzed menstrual cycle information and emotional state.

[1033] Step 5:

[1034] Applying generative AI models

[1035] The server then applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period. For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the server will predict the start date of your next period as October 29, 2023. This process uses a deep learning algorithm.

[1036] Input: Parsed menstrual cycle information.

[1037] Output: Predicted start date of next period.

[1038] Step 6:

[1039] Applying the Emotion Engine

[1040] The server analyzes the emotion data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[1041] Input: Parsed emotion data.

[1042] Output: Identified emotional state.

[1043] Step 7:

[1044] Generating health advice

[1045] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[1046] Input: Predicted start date of next period and identified emotional state.

[1047] Output: The generated health advice.

[1048] Step 8:

[1049] Sending Advice

[1050] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1051] Input: Generated health advice.

[1052] Output: Health advice in JSON format sent to user device.

[1053] Step 9:

[1054] Receiving and viewing advice

[1055] The device receives health advice sent from the server and displays it on the application screen. A notification function is also provided so that users can act on the advice quickly. There is also a function to save past advice.

[1056] Input: Health advice sent from the server in JSON format.

[1057] Output: Health advice and notifications displayed on the application screen.

[1058] (Application example 2)

[1059] 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."

[1060] The challenge is to provide a system that can increase user satisfaction with food delivery services and assist with health management by providing health advice and food suggestions based on the user's menstrual cycle and emotional state. Currently, food suggestions are made without taking menstrual cycles or emotional states into consideration, so it is often not possible to suggest foods that are optimal for each individual user. Therefore, there is a need for a system that can provide precise, personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[1061] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1062] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model to predict the menstrual cycle based on the analysis results, means for applying an emotion engine to analyze the user's emotion data and identify the user's emotional state, means for generating health advice and food suggestions based on the predicted menstrual cycle and emotional state, and means for transmitting the generated health advice and food suggestions to the user, thereby enabling precise and personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[1063] "Menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[1064] A "generative AI model" is an artificial intelligence model that analyzes received menstrual cycle data and predicts the start date of the next period and other cycle data.

[1065] The "emotion engine" is an analytical engine that analyzes user input data, voice data, and image data to identify the user's emotional state.

[1066] "Health advice" is specific health management recommendations such as nutritional intake and exercise based on the user's menstrual cycle and emotional state.

[1067] "Food Suggestion" refers to recommending specific foods to improve a user's health based on their menstrual cycle and emotional state.

[1068] The "means for transmitting to the user" refers to a communication means for transmitting the generated health advice and food suggestions to the user's terminal.

[1069] The present invention provides a system for providing health advice and food recommendations based on a user's menstrual cycle and emotional state in a food delivery service. The system is implemented in the following steps.

[1070] The server first receives menstrual cycle data and emotional data from the user terminal, including the start date of the last period, the length of the period, and text, audio, and image data related to the user's emotional state.

[1071] The server then analyzes the received data: it analyzes menstrual cycle data and uses a generative AI model to predict the start date of the next period, and it analyzes emotional data using an emotion engine to identify the user's emotional state.

[1072] Based on the analysis results, the server generates health advice and food suggestions based on the user's menstrual cycle and emotional state. Specifically, it recommends that the user consume foods rich in iron and vitamin C before their period, and that they try aromatherapy to relax when they are stressed.

[1073] The generated health advice and food suggestions are sent from the server to the user's device. The user receives this information through the application and manages their health based on the displayed health advice and food suggestions. Specifically, the user can directly order the suggested foods within the application and have them delivered.

[1074] For example, if user B uses this system,

[1075] 1. If you enter "Last period start date: October 1, 2023" and "Cycle length: 28 days" and say "I'm feeling stressed," the server will predict the start date of your next period as October 29, 2023, and suggest aromatic teas and vitamin-rich fruits as foods to relieve stress.

[1076] 2. After checking the displayed advice, User B can immediately put it into action by ordering the suggested food through the application and having it delivered.

[1077] To illustrate, here are some example prompts:

[1078] "User: My last period started on October 1, 2023, and my cycle length is 28 days. I'm also feeling stressed. What is the start date of my next period and what foods do you recommend?"

[1079] This allows users to receive health advice and food suggestions that are best suited to their individual conditions, allowing them to effectively manage their health while increasing their satisfaction with the food delivery service.

[1080] The key technical components of this system are a generative AI model and an emotion engine, the latter of which analyzes the user's emotional data, and the former of which predicts the start date of the next period based on cycle data.

[1081] In certain embodiments, a Flask server acts as the central point for receiving and analyzing data from users, while the emotion engine and generative AI models are implemented using specialized software or libraries.

[1082] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1083] Step 1:

[1084] The user inputs menstrual cycle data and emotional data through the device. Specifically, the user inputs the "last menstrual period start date" and "cycle length" on the application screen, and inputs text, voice, or images related to their emotional state.

[1085] Input: User's menstrual cycle data (last menstrual start date, cycle length) and emotional data (text, voice, image)

[1086] Output: JSON formatted menstrual cycle data and emotion data

[1087] Step 2:

[1088] The device converts the input data into JSON format and sends it to the server. Specifically, the data entered by the user is sent to the server via an HTTP POST request.

[1089] Input: Menstrual cycle data and emotion data entered by the user into the device

[1090] Output: JSON data sent to the server

[1091] Step 3:

[1092] The server receives and analyzes the data sent by the user. Specifically, the server receives an HTTP request and parses and analyzes the data in JSON format.

[1093] Input: JSON data sent from the terminal

[1094] Output: Analyzed menstrual cycle data and emotion data

[1095] Step 4:

[1096] The server applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period.Specifically, the generative AI model inputs menstrual cycle data and estimates the start date of the next period.

[1097] Input: Analyzed menstrual cycle data (last menstrual start date, cycle length)

[1098] Output: Predicted start date of next period

[1099] Step 5:

[1100] The server analyzes the emotional data using an emotion engine to identify the user's emotional state. Specifically, it analyzes text, voice, and image data to identify the user's emotional state.

[1101] Input: Analyzed emotion data (text, audio, images)

[1102] Output: Identified emotional state

[1103] Step 6:

[1104] The server generates health advice and food suggestions based on the menstrual cycle prediction results and emotional state.Specifically, it generates nutrition advice, exercise advice, and appropriate food suggestions based on femtech guidelines and emotional data.

[1105] Input: Predicted next period start date, identified emotional state

[1106] Output: Health advice and food suggestions

[1107] Step 7:

[1108] The server converts the generated health advice and food suggestions into JSON format and sends it to the user's device as an HTTP response.

[1109] Input: Generated health advice and food suggestions

[1110] Output: JSON data sent to the user's device

[1111] Step 8:

[1112] The device analyzes the health advice and food suggestions received from the server and displays them to the user. Specifically, the device displays the received data on the application screen and notifies the user so that they can act accordingly.

[1113] Input: JSON data received from the server

[1114] Output: Health advice and food suggestions displayed on the application screen

[1115] Step 9:

[1116] The user orders the suggested food through the application and requests delivery. Specifically, the user selects the food within the application and places an order and requests delivery.

[1117] Input: Food selected by user

[1118] Output: Food ordered and delivery request

[1119] 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.

[1120] 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.

[1121] 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.

[1122] [Third embodiment]

[1123] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1124] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1125] 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).

[1126] 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.

[1127] 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.

[1128] 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).

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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."

[1135] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on their specific femtech needs.

[1136] overview

[1137] The system receives and analyzes a user's menstrual cycle data, applies a generative AI model to predict menstrual cycles, and provides appropriate health advice to the user, allowing them to better manage their health.

[1138] Explanation of program processing

[1139] Server Processing

[1140] 1. Receiving User Information

[1141] The server receives data relating to the menstrual cycle (eg, the start date of the last period and the length of the cycle) from the user terminal.

[1142] For example, data can be received via an HTTP POST request in JSON format, such as:

[1143] json

[1144] {

[1145] "user_id": "12345",

[1146] "last_period_start_date": "2023-10-01",

[1147] "cycle_length": 28

[1148] }

[1149] 2. Data Analysis

[1150] The server analyzes the received data and extracts the data necessary for menstrual cycle prediction (e.g., the start date of the last menstrual period, the length of the cycle).

[1151] 3. Applying generative AI models

[1152] The server uses a generative AI model to predict the start date and phases of the user's next period.

[1153] For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the start date of your next period can be predicted as October 29, 2023.

[1154] 4. Health advice generation

[1155] Based on the prediction results of the generative AI model, the server applies health advice guidelines from the femtech field to generate individualized health advice for the user (e.g., recommendations for nutritional intake and exercise).

[1156] For example, you can generate advice like this:

[1157] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[1158] During menstruation: Stay hydrated.

[1159] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1160] 5. Submitting Advice

[1161] The server transmits the generated health advice to the user terminal.

[1162] For example, send the following JSON data as an HTTP response:

[1163] json

[1164] {

[1165] "advice": {

[1166] "nutrition": {

[1167] "pre_period": "Consume foods rich in iron and vitamin C.",

[1168] "during_period": "Stay hydrated."

[1169] },

[1170] "exercise": {

[1171] "pre_period": "Engage in light exercises or stretching.",

[1172] "during_period": "Practice yoga or walking for relaxation."

[1173] },

[1174] "predicted_next_period": "2023-10-29"

[1175] }

[1176] }

[1177] User terminal processing

[1178] 1. Data Entry

[1179] The user enters menstrual cycle data (eg, last menstrual period start date and cycle length) through the application screen.

[1180] 2. Data Transmission

[1181] The terminal sends the entered data to the server via an HTTP POST request.

[1182] 3. Receiving Advice

[1183] The device receives health advice sent as an HTTP response from the server.

[1184] 4. Displaying Advice

[1185] The device displays the received health advice on the application screen and guides the user to take appropriate action based on it.

[1186] Specific examples

[1187] Here is a concrete example of how Person A might use this system:

[1188] 1. Data entry: Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[1189] 2. Data transmission: The device transmits this information to the server.

[1190] 3. Server Processing:

[1191] The server receives and analyzes the data.

[1192] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[1193] Health advice is generated and sent back to the device.

[1194] 4. Receiving advice: The terminal receives advice from the server.

[1195] 5. Displaying advice: The device displays advice to Person A, who then manages his or her health based on that advice.

[1196] This system allows Ms. A to receive specific health advice based on her menstrual cycle, enabling her to optimally manage her health in her daily life.

[1197] The processing flow will be explained below.

[1198] Step 1:

[1199] The user opens the application and enters menstrual cycle data (last period start date and cycle length).

[1200] Step 2:

[1201] The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1202] json

[1203] {

[1204] "user_id": "12345",

[1205] "last_period_start_date": "2023-10-01",

[1206] "cycle_length": 28

[1207] }

[1208] Step 3:

[1209] The server receives the HTTP POST request and parses the JSON data, specifically extracting the last_period_start_date and cycle_length.

[1210] Step 4:

[1211] The server inputs the extracted data into the generative AI model to predict the start date of the user's next period. For example, if the input last_period_start_date is October 1, 2023, and the cycle_length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[1212] Step 5:

[1213] The server generates personalized health advice for each user based on the prediction results. Based on Femtech guidelines, the server creates personalized advice such as:

[1214] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[1215] During menstruation: Make sure you drink plenty of fluids.

[1216] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1217] Step 6:

[1218] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1219] json

[1220] {

[1221] "advice": {

[1222] "nutrition": {

[1223] "pre_period": "Consume foods rich in iron and vitamin C.",

[1224] "during_period": "Stay hydrated."

[1225] },

[1226] "exercise": {

[1227] "pre_period": "Engage in light exercises or stretching.",

[1228] "during_period": "Practice yoga or walking for relaxation."

[1229] },

[1230] "predicted_next_period": "2023-10-29"

[1231] }

[1232] }

[1233] Step 7:

[1234] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[1235] Step 8:

[1236] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[1237] Nutritional Recommendations

[1238] Exercise recommendations

[1239] Predicted start date of next period

[1240] Step 9:

[1241] The user checks the displayed health advice and puts it into practice in their daily life, for example, by eating iron-rich foods before menstruation.

[1242] Example 1

[1243] 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."

[1244] With conventional menstrual cycle management systems, it was difficult for users to receive specific advice on how to properly manage their health. Furthermore, menstrual cycle predictions were often inaccurate, making it difficult for users to trust the information and take action. As a result, users were unable to take appropriate measures at the appropriate time, which hindered their health management.

[1245] 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.

[1246] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for saving the data transmitted from the user's device and preparing input prompts for the analysis and generative AI model, means for applying health advice guidelines in the femtech field based on the prediction results, and means for returning the generated advice to the user's device. This enables the user to receive accurate menstrual cycle predictions and specific health advice based on them, enabling appropriate health management.

[1247] "User's menstrual cycle data" is a series of data related to the menstrual cycle, such as the start date of the last menstrual period and the length of the menstrual cycle, entered by the user.

[1248] A "generative AI model" is a machine learning model that predicts menstrual cycles based on past data.

[1249] An "input prompt" is a group of data that is input to the generative AI model to predict menstrual cycles.

[1250] The "Health Advice Guidelines in the Femtech Field" are guidelines for providing standard health advice in the technology field aimed at managing women's health.

[1251] "Health Advice" is personalized health guidance for a user, including nutrition and exercise recommendations, generated based on the predicted menstrual cycle.

[1252] A "user terminal" is a terminal device used by a user, and is a device for inputting menstrual cycle data and displaying health advice.

[1253] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on specific femtech needs. The system receives menstrual cycle data entered by the user, analyzes it, and then uses a generative AI model to predict the menstrual cycle and provide appropriate health advice to the user.

[1254] System configuration

[1255] The system mainly consists of the following hardware and software:

[1256] 1. Server

[1257] 2. User devices (smartphones, tablets, etc.)

[1258] 3. Generative AI Models (Machine Learning Models)

[1259] Server Features

[1260] The server has the following features:

[1261] 1. Receiving User Information

[1262] The server receives data related to the menstrual cycle (e.g., the start date of the last period and the length of the cycle) from the user terminal, often received as an HTTP POST request.

[1263] 2. Data Analysis

[1264] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction. The server obtains the "last menstrual period start date" and "cycle length" from the JSON format data and uses them in the next processing step.

[1265] 3. Applying generative AI models

[1266] The server uses the generative AI model to predict the start date and each phase of the user's next period. For example, the server inputs "Last period start date: 2023-10-01" and "Cycle length: 28 days" as input prompts to the generative AI model.

[1267] 4. Health advice generation

[1268] Based on the prediction results of the generative AI model, the server applies femtech health advice guidelines and generates personalized health advice for each user, including recommendations on nutrition and exercise.

[1269] 5. Submitting Advice

[1270] The server sends the generated health advice to the user device, typically as JSON data in an HTTP response.

[1271] User device functions

[1272] The user terminal has the following features:

[1273] 1. Data Entry

[1274] The user inputs menstrual cycle data through the application screen, specifically the start date of the last menstrual period and the length of the menstrual cycle.

[1275] 2. Data Transmission

[1276] The device sends the input data to the server via an HTTP POST request in JSON format, providing the server with the data to run the predictive model.

[1277] 3. Receiving Advice

[1278] The device receives health advice sent as an HTTP response from the server, such as the generated health advice and the start date of the next menstruation.

[1279] 4. Displaying Advice

[1280] The terminal displays the received health advice on the application screen, allowing the user to take appropriate action based on it.

[1281] Specific examples

[1282] Here is a concrete example of how Person A might use this system:

[1283] 1. Data Entry

[1284] Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[1285] 2. Data Transmission

[1286] The terminal sends this information to the server.

[1287] 3. Server Processing

[1288] The server receives and analyzes the data. For example, prompts such as "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" are input into the generative AI model.

[1289] 4. Generating predictions and advice

[1290] The generative AI model predicts the start date of the next period (October 29, 2023). Health advice is generated, such as "consume foods rich in iron and vitamin C" before menstruation and "stay hydrated" during menstruation.

[1291] 5. Receiving and displaying advice

[1292] The terminal receives advice from the server and displays it to Mr. A, who then manages his health based on it.

[1293] This system allows users to receive specific health advice based on their menstrual cycle, enabling them to optimally manage their health in their daily lives.

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

[1295] Specific processing flow of the program

[1296] Server Processing

[1297] Step 1: Receiving user information

[1298] The server receives data related to the menstrual cycle from the user terminal.

[1299] Input: HTTP POST request in JSON format (e.g., { "user_id": "12345", "last_period_start_date": "2023-10-01", "cycle_length": 28})

[1300] Processing: Temporarily storing data and preparing it for the next processing step.

[1301] Output: User data stored in internal data structures

[1302] Step 2: Analyze the data

[1303] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction.

[1304] Input: Saved user data

[1305] Processing: Obtain the "last period start date" and "cycle length" from the JSON data (e.g., last period start date: 2023-10-01, cycle length: 28).

[1306] Output: Analyzed data (last menstrual period start date, cycle length)

[1307] Step 3: Applying the generative AI model

[1308] The server uses a generative AI model to predict the start date and phases of the user's next period.

[1309] Input: Analyzed data (last menstrual period start date, cycle length)

[1310] Processing: The generative AI model is given the input prompts "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" to predict the menstrual cycle.

[1311] Output: Prediction result (e.g., next menstruation start date: 2023-10-29)

[1312] Step 4: Generate health advice

[1313] Based on the prediction results of the generative AI model, the server applies femtech guidelines to generate individual health advice for the user.

[1314] Input: Prediction result (start date of next period)

[1315] Treatment: Create advice based on guidelines regarding nutritional intake and exercise (e.g., before menstruation: take iron and vitamin C, during menstruation: make sure to stay hydrated).

[1316] Output: Generated health advice (e.g., {"nutrition": {"pre_period": "Consume foods rich in iron and vitamin C.", "during_period": "Stay hydrated."}, "exercise": {"pre_period": "Engage in light exercises or stretching.", "during_period": "Practice yoga or walking for relaxation."}, "predicted_next_period": "2023-10-29"})

[1317] Step 5: Submitting Advice

[1318] The server transmits the generated health advice to the user terminal.

[1319] Input: Generated health advice

[1320] Processing: Send JSON data to the user terminal as an HTTP response.

[1321] Output: Health advice sent to the user device

[1322] User terminal processing

[1323] Step 6: Data entry

[1324] The user inputs menstrual cycle data (last menstrual start date and cycle length) through the application screen.

[1325] Input: Last menstrual start date, cycle length (e.g., "Last menstrual start date: 2023-10-01", "Cycle length: 28 days")

[1326] Processing: The data entered by the user is temporarily saved in the terminal.

[1327] Output: Saved menstrual cycle data

[1328] Step 7: Send data

[1329] The terminal sends the entered data to the server via an HTTP POST request in JSON format.

[1330] Input: Saved menstrual cycle data

[1331] Operation: Generates an HTTP request and sends data to the specified server endpoint.

[1332] Output: Request sent to the server

[1333] Step 8: Receive advice

[1334] The device receives health advice sent as an HTTP response from the server.

[1335] Input: HTTP response from the server

[1336] Processing: Analyze the response content and extract the advice data.

[1337] Output: Extracted advice data

[1338] Step 9: View Advice

[1339] The device displays the received health advice on the application screen and guides the user to take appropriate action.

[1340] Input: Extracted advice data

[1341] Action: Update the UI to display the data on the application screen (e.g., "Recommended nutrients before menstruation: Iron and Vitamin C" and "Recommended behavior during menstruation: Stay hydrated").

[1342] Output: Advice displayed to the user

[1343] (Application example 1)

[1344] 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."

[1345] While systems that provide health advice based on a user's menstrual cycle already exist, they lack support that goes into the user's nutritional balance and diet. The present invention aims to provide more comprehensive support for users' health management by proposing and providing personalized food and drink menus so that users can easily eat meals that are appropriate for their menstrual cycle.

[1346] 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.

[1347] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for generating a personalized meal menu based on the predicted menstrual cycle, and means for providing the generated meal menu to the user. This makes it possible to promptly propose and provide to the user not only health advice but also nutritionally balanced meal menus suited to the user's menstrual cycle.

[1348] "User's menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last period and the length of the menstrual cycle.

[1349] The "generative AI model" is an artificial intelligence model that predicts the start date of a user's next period and each phase based on received menstrual cycle data.

[1350] "Health advice" is a recommendation regarding nutritional intake and exercise to help the user manage their health based on the predicted menstrual cycle.

[1351] A "personalized meal menu" is a food and drink menu that is individually suggested based on the user's menstrual cycle and takes into consideration the optimal nutritional balance.

[1352] The term "means" is a general concept that refers to devices and systems for realizing a specific function in this invention.

[1353] This invention is a system that receives a user's menstrual cycle data, predicts the start date of the next period using a generative AI model, and generates and provides health advice and personalized meal menus based on the prediction results. This system interacts with the user via a smartphone application and can easily provide health advice and meal menu suggestions to the user.

[1354] System Overview

[1355] Server-side processing

[1356] The server receives menstrual cycle data (e.g., the start date of the last period and the length of the cycle) sent from the user's device. The received data is analyzed and a generative AI model is used to predict the menstrual cycle. Health advice and a personalized meal plan are then generated based on the prediction results and sent to the user's device. The hardware used includes a high-performance server, and the software includes Python (server-side implementation using Flask), generative AI models (TensorFlow or PyTorch), and databases (MySQL or SQLite).

[1357] Terminal side processing

[1358] Users enter their menstrual cycle data through the smartphone application screen. This data is sent to the server via an HTTP POST request. Health advice and personalized meal menus sent from the server are received and displayed on the application screen. Users can also order delivery of the suggested menu items.

[1359] Processing flow

[1360] When a user enters the start date of their last period and the length of their cycle into the application, that data is sent to the server. The server receives and analyzes the data. It uses a generative AI model to predict the start date of the next period and generates health advice and a personalized meal plan based on the prediction. The generated data is then sent back to the user's device and displayed on the application screen.

[1361] Specific examples

[1362] For example, if a user enters "last period start date: October 1, 2023" and "cycle length: 28 days" into the application, the server receives this and uses the generative AI model to predict the next period start date (October 29, 2023). Based on the results, the following health advice is generated:

[1363] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[1364] During menstruation: Stay hydrated.

[1365] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1366] Additionally, personalized meal suggestions are also available:

[1367] Premenstrual: Spinach salad with citrus dressing, grilled chicken and quinoa.

[1368] During menstruation: Cucumber mint water, tomato and mozzarella salad.

[1369] Prompt Sentence Examples

[1370] "My last period started on October 1, 2023, and my cycle is 28 days. When is my next period? Also, what specific foods and nutrients should I be consuming throughout that period?"

[1371] In this way, the system of the present invention allows the user to receive personalized support for appropriate health management in accordance with their menstrual cycle.

[1372] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1373] Step 1:

[1374] The user inputs the "last menstrual start date" and "cycle length" through a smartphone application. This data is sent to the server as an HTTP POST request to the endpoint specified by the URI. The input data includes, for example, the user's ID, last menstrual start date, and menstrual cycle length.

[1375] Step 2:

[1376] The server analyzes the received HTTP POST request and extracts menstrual cycle data. The analyzed data is saved in the form of the menstrual start date and cycle length. The server inputs this data into a generative AI model, which processes and calculates the data to predict the menstrual cycle.

[1377] Step 3:

[1378] The server applies a generative AI model (using, for example, TensorFlow or PyTorch) to predict the start date and phases (premenstrual, menstrual, and postmenstrual) of the user's next period. The generative AI model makes a prediction based on the input data, and the output is the start date and phase information of the next period.

[1379] Step 4:

[1380] The server generates health advice based on the predicted menstrual cycle, aligned with standard health guidelines, including nutritional recommendations and exercise advice. The advice generated is specific and helpful for the user in managing their health.

[1381] Step 5:

[1382] The server then generates a personalized meal menu based on the predictions, which is designed to balance the nutritional intake of the user's menstrual cycle and includes specific dishes and ingredients recommended for each phase.

[1383] Step 6:

[1384] The server compiles the generated health advice and personalized meal menus and sends them to the user's device as an HTTP response. The output data includes health advice, the start date of the next menstrual period, and meal menus for each phase.

[1385] Step 7:

[1386] The user's device analyzes the received data and displays it on the application screen. The user can check the displayed information, such as the start date of their next period, health advice, and suggested meal menus. The user can also order the suggested menus for delivery.

[1387] Step 8:

[1388] If the user wishes to order food delivery, they confirm the selected menu items and complete the delivery order. The order is sent to the food delivery company via the smartphone app, and the meal is delivered to the user at the appropriate time.

[1389] Through the above processing steps, the present invention realizes a system that provides users with health management and dietary suggestions suited to their needs.

[1390] 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.

[1391] The present invention combines a system that predicts a user's menstrual cycle data and provides health advice based on specific femtech needs with an emotion engine that recognizes the user's emotions. This system provides more precise and personalized health care based not only on the user's health status but also on their emotional state.

[1392] overview

[1393] The system receives and analyzes the user's menstrual cycle data, then uses a generative AI model to predict the menstrual cycle. It also analyzes the user's emotional state using an emotion engine to generate and provide health advice to the user.

[1394] Explanation of program processing

[1395] Server Processing

[1396] 1. Receiving User Information

[1397] The server receives data related to the menstrual cycle (e.g., the start date of the last menstrual period and the length of the menstrual cycle) from the user terminal, as well as emotional information such as user input data, voice, and images.

[1398] For example, data can be received via an HTTP POST request in JSON format, such as:

[1399] json

[1400] {

[1401] "user_id": "12345",

[1402] "last_period_start_date": "2023-10-01",

[1403] "cycle_length": 28,

[1404] "emotion_data": {

[1405] "text": "I'm feeling stressed",

[1406] "voice": "audio_data",

[1407] "image": "image_data"

[1408] }

[1409] }

[1410] 2. Data Analysis

[1411] The server analyzes the received menstrual cycle data and extracts data necessary for menstrual cycle prediction (e.g., the start date of the last period, cycle length, etc.). It also analyzes the emotional data to identify the user's emotional state.

[1412] 3. Applying generative AI models

[1413] The server uses the generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[1414] 4. Applying the Emotion Engine

[1415] The server uses an emotion engine to analyze the user's emotional state from their input data, voice, and images. For example, if a user inputs "I'm feeling stressed," the server identifies the emotional state as "stress."

[1416] 5. Health advice generation

[1417] The server generates personalized health advice based on the prediction results of the generative AI model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, it creates advice such as:

[1418] Premenstrual period: Recommend consuming foods rich in iron and vitamin C. Also, if the emotional state is stressful, aromatherapy is recommended for relaxation.

[1419] During menstruation: Stay well hydrated and, if your emotional state is fatigue, get plenty of rest.

[1420] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1421] 6. Submitting Advice

[1422] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1423] json

[1424] {

[1425] "advice": {

[1426] "nutrition": {

[1427] "pre_period": "Consume foods rich in iron and vitamin C.",

[1428] "during_period": "Stay hydrated."

[1429] },

[1430] "exercise": {

[1431] "pre_period": "Engage in light exercises or stretching.",

[1432] "during_period": "Practice yoga or walking for relaxation."

[1433] },

[1434] "emotion": {

[1435] "stress": "Try aromatherapy to relax.",

[1436] "fatigue": "Make sure to get plenty of rest."

[1437] },

[1438] "predicted_next_period": "2023-10-29"

[1439] }

[1440] }

[1441] User terminal processing

[1442] 1. Data Entry

[1443] The user inputs menstrual cycle data (e.g., the start date of the last period and the length of the cycle) and emotional state (text, voice, image, etc.) through the application screen.

[1444] 2. Data Transmission

[1445] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request.

[1446] 3. Receiving Advice

[1447] The device receives health advice sent as an HTTP response from the server.

[1448] 4. Displaying Advice

[1449] The device displays the received health advice on the application screen and notifies the user so that they can take appropriate action based on it.

[1450] Specific examples

[1451] Here is a concrete example of how Person B might use this system:

[1452] 1. Data entry: Person B enters "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days" into the application, and also enters her emotional state in text, "I'm feeling stressed."

[1453] 2. Data transmission: The device transmits this information to the server.

[1454] 3. Server Processing:

[1455] The server receives and analyzes the data.

[1456] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[1457] The emotion engine identifies the emotion "stress."

[1458] Health advice is generated and sent back to the device.

[1459] 4. Receiving advice: The terminal receives advice from the server.

[1460] 5. Displaying Advice: The device displays advice to Person B, who can then manage his or her health based on the advice. For example, Person B may consume iron-rich foods and use aromatherapy to relieve stress.

[1461] This system allows Ms. B to receive not only specific health advice based on her menstrual cycle, but also advice tailored to her emotional state, enabling her to manage her health more effectively.

[1462] The processing flow will be explained below.

[1463] Step 1:

[1464] The user opens the application and enters menstrual cycle data (last period start date and cycle length) and emotional state (text, voice, image, etc.).

[1465] Step 2:

[1466] The device converts the input menstrual cycle data and emotion data into JSON format and sends it to the server as an HTTP POST request.

[1467] json

[1468] {

[1469] "user_id": "12345",

[1470] "last_period_start_date": "2023-10-01",

[1471] "cycle_length": 28,

[1472] "emotion_data": {

[1473] "text": "I'm feeling stressed",

[1474] "voice": "audio_data",

[1475] "image": "image_data"

[1476] }

[1477] }

[1478] Step 3:

[1479] The server receives the HTTP POST request and parses the JSON data to extract menstrual cycle data (last_period_start_date and cycle_length) and emotion data.

[1480] Step 4:

[1481] The server inputs the extracted menstrual cycle data into a generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the next period will be predicted to start on October 29, 2023.

[1482] Step 5:

[1483] The server uses an emotion engine to analyze the emotion data (text, voice, image) entered by the user and identify the user's emotional state. For example, if the text is "I'm feeling stressed," the server identifies the emotional state as "stress."

[1484] Step 6:

[1485] The server generates personalized health advice based on the prediction results of the AI ​​model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, the server generates advice such as:

[1486] For premenstrual nutrition, it is recommended to consume foods rich in iron and vitamin C.

[1487] When caring for yourself during your period, make sure you drink plenty of fluids.

[1488] If the user is feeling stressed, aromatherapy is recommended to help them relax.

[1489] As for exercise recommendations, light exercise and stretching are recommended before menstruation, and yoga or walking for relaxation during menstruation is recommended.

[1490] Step 7:

[1491] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1492] json

[1493] {

[1494] "advice": {

[1495] "nutrition": {

[1496] "pre_period": "Consume foods rich in iron and vitamin C.",

[1497] "during_period": "Stay hydrated."

[1498] },

[1499] "exercise": {

[1500] "pre_period": "Engage in light exercises or stretching.",

[1501] "during_period": "Practice yoga or walking for relaxation."

[1502] },

[1503] "emotion": {

[1504] "stress": "Try aromatherapy to relax."

[1505] },

[1506] "predicted_next_period": "2023-10-29"

[1507] }

[1508] }

[1509] Step 8:

[1510] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[1511] Step 9:

[1512] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[1513] Nutritional Recommendations

[1514] Exercise recommendations

[1515] Specific advice depending on your emotional state

[1516] Predicted start date of next period

[1517] Step 10:

[1518] The user checks the displayed health advice and puts it into practice in daily life. For example, if the user feels stressed, they can take action such as eating foods rich in iron and practicing aromatherapy.

[1519] Example 2

[1520] 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."

[1521] While current health management systems provide advice based on a user's menstrual cycle data, they lack health advice that takes into account the user's emotional state. This makes it difficult to comprehensively manage a user's overall health, and in particular, it is difficult to fully evaluate the impact of emotional stress and fatigue on health.

[1522] 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.

[1523] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for receiving the user's emotional data, means for analyzing the received emotional data, means for generating health advice based on the prediction results of the generative AI model and the analyzed emotional data, and means for transmitting the generated health advice to the user, thereby enabling more precise and personalized health care based on both the user's menstrual cycle and emotional state.

[1524] "Menstrual cycle data" is information about the user's menstruation, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[1525] The "means for receiving" is an interface for importing data from a user terminal into a server, and includes a function for receiving data using an HTTP request or other protocol.

[1526] "Means for analyzing" refers to a function that analyzes the data received by the server and performs processing to extract and understand the necessary information.

[1527] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to predict menstrual cycles, and makes highly accurate predictions based on past data.

[1528] "Emotional data" is information about the user's emotional state, and includes text, audio, and image data.

[1529] An "emotion engine" is a technology or system for analyzing emotion data and identifying a user's emotional state.

[1530] "Health advice" refers to specific recommendations or instructions regarding health management provided to the user based on the analysis results or prediction results.

[1531] The "transmission means" is an interface for returning the generated health advice to the user terminal, and includes a function for transmitting data using an HTTP response or other protocol.

[1532] This invention is a system that receives and analyzes a user's menstrual cycle data and emotional data, and provides menstrual cycle predictions and health advice using a generative AI model and emotional engine. This system operates on the basis of a server and a user terminal.

[1533] Server configuration and operation

[1534] 1. Receiving User Information

[1535] The server receives menstrual cycle data (last menstrual start date and cycle length) and emotional data (text, voice, and image) from the user's device. This allows data based on the user's situation to be collected in real time. For example, a user might enter "last menstrual start date: October 1, 2023," "cycle length: 28 days," and "I'm feeling stressed."

[1536] 2. Data Analysis

[1537] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing (NLP) engine, voice recognition software, and image recognition software, ensuring consistency and accuracy of the data.

[1538] 3. Applying generative AI models

[1539] The server applies a generative AI model based on menstrual cycle data to predict the start date of your next period. For example, if your last period started on October 1, 2023, and your cycle is 28 days long, the server predicts your next period will start on October 29, 2023. This generative AI model uses deep learning algorithms to make highly accurate predictions.

[1540] 4. Applying the Emotion Engine

[1541] The server analyzes the emotional data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[1542] 5. Health advice generation

[1543] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[1544] 6. Submitting Advice

[1545] The generated health advice is sent from the server to the user's device as an HTTP response. The advice is sent in JSON format and is displayed on the user's device after analysis.

[1546] Configuration and operation of user terminal

[1547] 1. Data Entry

[1548] Users input their menstrual cycle and emotional data through the application screen. The application provides an intuitive interface, allowing users to easily input data.

[1549] 2. Data Transmission

[1550] The user device converts the input data into JSON format and sends it to the server as an HTTP POST request. For security reasons, the communication is encrypted with SSL / TLS.

[1551] 3. Receiving and Displaying Advice

[1552] The user's device receives the advice sent from the server and displays it on the screen. It also has a notification function so that users can act quickly based on the advice. It also has a save function so that users can refer to past advice.

[1553] Specific examples

[1554] When a user uses this system, it works like this:

[1555] 1. The user enters the following information into the application: "Last period start date: October 1, 2023" and "Cycle length: 28 days" and then enters their emotional state in the text "I'm feeling stressed."

[1556] 2. The device sends this information to the server, which analyzes the data.

[1557] 3. The server uses a generative AI model to predict the start date of the next period and an emotion engine to identify the emotion "stress."

[1558] 4. The server generates personalized health advice and sends it back to the device.

[1559] 5. The device receives the advice and displays it to the user, who then manages their health based on the advice.

[1560] For example, a user may choose to eat iron-rich foods or try aromatherapy to relieve stress. The system allows users to receive specific health advice based on their menstrual cycle and emotional state, leading to more effective health management.

[1561] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1562] Step 1:

[1563] Data Entry

[1564] The user uses the application screen to input menstrual cycle data (last menstrual start date and cycle length) and emotion data (text, voice, image).

[1565] Input: Menstrual cycle data and emotion data entered by the user.

[1566] Output: Input data temporarily stored on the user's device.

[1567] Step 2:

[1568] Data transmission

[1569] The device converts the input data into JSON format and sends it to the server as an HTTP POST request. The communication is encrypted with SSL / TLS.

[1570] Input: Menstrual cycle data and emotion data entered by the user into the device.

[1571] Output: JSON formatted data sent to the server.

[1572] Step 3:

[1573] Receiving user information

[1574] The server receives the menstrual cycle data and emotion data transmitted from the user terminal.

[1575] Input: JSON formatted data.

[1576] Output: Menstrual cycle data and emotion data stored in the server's memory and database.

[1577] Step 4:

[1578] Data analysis

[1579] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing engine, voice recognition software, and image recognition software.

[1580] Input: Menstrual cycle data and emotion data stored on the server.

[1581] Output: Analyzed menstrual cycle information and emotional state.

[1582] Step 5:

[1583] Applying generative AI models

[1584] The server then applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period. For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the server will predict the start date of your next period as October 29, 2023. This process uses a deep learning algorithm.

[1585] Input: Parsed menstrual cycle information.

[1586] Output: Predicted start date of next period.

[1587] Step 6:

[1588] Applying the Emotion Engine

[1589] The server analyzes the emotion data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[1590] Input: Parsed emotion data.

[1591] Output: Identified emotional state.

[1592] Step 7:

[1593] Generating health advice

[1594] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[1595] Input: Predicted start date of next period and identified emotional state.

[1596] Output: The generated health advice.

[1597] Step 8:

[1598] Sending Advice

[1599] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1600] Input: Generated health advice.

[1601] Output: Health advice in JSON format sent to user device.

[1602] Step 9:

[1603] Receiving and viewing advice

[1604] The device receives health advice sent from the server and displays it on the application screen. A notification function is also provided so that users can act on the advice quickly. There is also a function to save past advice.

[1605] Input: Health advice sent from the server in JSON format.

[1606] Output: Health advice and notifications displayed on the application screen.

[1607] (Application example 2)

[1608] 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."

[1609] The challenge is to provide a system that can increase user satisfaction with food delivery services and assist with health management by providing health advice and food suggestions based on the user's menstrual cycle and emotional state. Currently, food suggestions are made without taking menstrual cycles or emotional states into consideration, so it is often not possible to suggest foods that are optimal for each individual user. Therefore, there is a need for a system that can provide precise, personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[1610] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1611] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model to predict the menstrual cycle based on the analysis results, means for applying an emotion engine to analyze the user's emotion data and identify the user's emotional state, means for generating health advice and food suggestions based on the predicted menstrual cycle and emotional state, and means for transmitting the generated health advice and food suggestions to the user, thereby enabling precise and personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[1612] "Menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[1613] A "generative AI model" is an artificial intelligence model that analyzes received menstrual cycle data and predicts the start date of the next period and other cycle data.

[1614] The "emotion engine" is an analytical engine that analyzes user input data, voice data, and image data to identify the user's emotional state.

[1615] "Health advice" is specific health management recommendations such as nutritional intake and exercise based on the user's menstrual cycle and emotional state.

[1616] "Food Suggestion" refers to recommending specific foods to improve a user's health based on their menstrual cycle and emotional state.

[1617] The "means for transmitting to the user" refers to a communication means for transmitting the generated health advice and food suggestions to the user's terminal.

[1618] The present invention provides a system for providing health advice and food recommendations based on a user's menstrual cycle and emotional state in a food delivery service. The system is implemented in the following steps.

[1619] The server first receives menstrual cycle data and emotional data from the user terminal, including the start date of the last period, the length of the period, and text, audio, and image data related to the user's emotional state.

[1620] The server then analyzes the received data: it analyzes menstrual cycle data and uses a generative AI model to predict the start date of the next period, and it analyzes emotional data using an emotion engine to identify the user's emotional state.

[1621] Based on the analysis results, the server generates health advice and food suggestions based on the user's menstrual cycle and emotional state. Specifically, it recommends that the user consume foods rich in iron and vitamin C before their period, and that they try aromatherapy to relax when they are stressed.

[1622] The generated health advice and food suggestions are sent from the server to the user's device. The user receives this information through the application and manages their health based on the displayed health advice and food suggestions. Specifically, the user can directly order the suggested foods within the application and have them delivered.

[1623] For example, if user B uses this system,

[1624] 1. If you enter "Last period start date: October 1, 2023" and "Cycle length: 28 days" and say "I'm feeling stressed," the server will predict the start date of your next period as October 29, 2023, and suggest aromatic teas and vitamin-rich fruits as foods to relieve stress.

[1625] 2. After checking the displayed advice, User B can immediately put it into action by ordering the suggested food through the application and having it delivered.

[1626] To illustrate, here are some example prompts:

[1627] "User: My last period started on October 1, 2023, and my cycle length is 28 days. I'm also feeling stressed. What is the start date of my next period and what foods do you recommend?"

[1628] This allows users to receive health advice and food suggestions that are best suited to their individual conditions, allowing them to effectively manage their health while increasing their satisfaction with the food delivery service.

[1629] The key technical components of this system are a generative AI model and an emotion engine, the latter of which analyzes the user's emotional data, and the former of which predicts the start date of the next period based on cycle data.

[1630] In certain embodiments, a Flask server acts as the central point for receiving and analyzing data from users, while the emotion engine and generative AI models are implemented using specialized software or libraries.

[1631] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1632] Step 1:

[1633] The user inputs menstrual cycle data and emotional data through the device. Specifically, the user inputs the "last menstrual period start date" and "cycle length" on the application screen, and inputs text, voice, or images related to their emotional state.

[1634] Input: User's menstrual cycle data (last menstrual start date, cycle length) and emotional data (text, voice, image)

[1635] Output: JSON formatted menstrual cycle data and emotion data

[1636] Step 2:

[1637] The device converts the input data into JSON format and sends it to the server. Specifically, the data entered by the user is sent to the server via an HTTP POST request.

[1638] Input: Menstrual cycle data and emotion data entered by the user into the device

[1639] Output: JSON data sent to the server

[1640] Step 3:

[1641] The server receives and analyzes the data sent by the user. Specifically, the server receives an HTTP request and parses and analyzes the data in JSON format.

[1642] Input: JSON data sent from the terminal

[1643] Output: Analyzed menstrual cycle data and emotion data

[1644] Step 4:

[1645] The server applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period.Specifically, the generative AI model inputs menstrual cycle data and estimates the start date of the next period.

[1646] Input: Analyzed menstrual cycle data (last menstrual start date, cycle length)

[1647] Output: Predicted start date of next period

[1648] Step 5:

[1649] The server analyzes the emotional data using an emotion engine to identify the user's emotional state. Specifically, it analyzes text, voice, and image data to identify the user's emotional state.

[1650] Input: Analyzed emotion data (text, audio, images)

[1651] Output: Identified emotional state

[1652] Step 6:

[1653] The server generates health advice and food suggestions based on the menstrual cycle prediction results and emotional state.Specifically, it generates nutrition advice, exercise advice, and appropriate food suggestions based on femtech guidelines and emotional data.

[1654] Input: Predicted next period start date, identified emotional state

[1655] Output: Health advice and food suggestions

[1656] Step 7:

[1657] The server converts the generated health advice and food suggestions into JSON format and sends it to the user's device as an HTTP response.

[1658] Input: Generated health advice and food suggestions

[1659] Output: JSON data sent to the user's device

[1660] Step 8:

[1661] The device analyzes the health advice and food suggestions received from the server and displays them to the user. Specifically, the device displays the received data on the application screen and notifies the user so that they can act accordingly.

[1662] Input: JSON data received from the server

[1663] Output: Health advice and food suggestions displayed on the application screen

[1664] Step 9:

[1665] The user orders the suggested food through the application and requests delivery. Specifically, the user selects the food within the application and places an order and requests delivery.

[1666] Input: Food selected by user

[1667] Output: Food ordered and delivery request

[1668] 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.

[1669] 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.

[1670] 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.

[1671] [Fourth embodiment]

[1672] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1673] 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.

[1674] 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).

[1675] 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.

[1676] 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.

[1677] 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).

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] 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.

[1684] 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."

[1685] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on their specific femtech needs.

[1686] overview

[1687] The system receives and analyzes a user's menstrual cycle data, applies a generative AI model to predict menstrual cycles, and provides appropriate health advice to the user, allowing them to better manage their health.

[1688] Explanation of program processing

[1689] Server Processing

[1690] 1. Receiving User Information

[1691] The server receives data relating to the menstrual cycle (eg, the start date of the last period and the length of the cycle) from the user terminal.

[1692] For example, data can be received via an HTTP POST request in JSON format, such as:

[1693] json

[1694] {

[1695] "user_id": "12345",

[1696] "last_period_start_date": "2023-10-01",

[1697] "cycle_length": 28

[1698] }

[1699] 2. Data Analysis

[1700] The server analyzes the received data and extracts the data necessary for menstrual cycle prediction (e.g., the start date of the last menstrual period, the length of the cycle).

[1701] 3. Applying generative AI models

[1702] The server uses a generative AI model to predict the start date and phases of the user's next period.

[1703] For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the start date of your next period can be predicted as October 29, 2023.

[1704] 4. Health advice generation

[1705] Based on the prediction results of the generative AI model, the server applies health advice guidelines from the femtech field to generate individualized health advice for the user (e.g., recommendations for nutritional intake and exercise).

[1706] For example, you can generate advice like this:

[1707] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[1708] During menstruation: Stay hydrated.

[1709] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1710] 5. Submitting Advice

[1711] The server transmits the generated health advice to the user terminal.

[1712] For example, send the following JSON data as an HTTP response:

[1713] json

[1714] {

[1715] "advice": {

[1716] "nutrition": {

[1717] "pre_period": "Consume foods rich in iron and vitamin C.",

[1718] "during_period": "Stay hydrated."

[1719] },

[1720] "exercise": {

[1721] "pre_period": "Engage in light exercises or stretching.",

[1722] "during_period": "Practice yoga or walking for relaxation."

[1723] },

[1724] "predicted_next_period": "2023-10-29"

[1725] }

[1726] }

[1727] User terminal processing

[1728] 1. Data Entry

[1729] The user enters menstrual cycle data (eg, last menstrual period start date and cycle length) through the application screen.

[1730] 2. Data Transmission

[1731] The terminal sends the entered data to the server via an HTTP POST request.

[1732] 3. Receiving Advice

[1733] The device receives health advice sent as an HTTP response from the server.

[1734] 4. Displaying Advice

[1735] The device displays the received health advice on the application screen and guides the user to take appropriate action based on it.

[1736] Specific examples

[1737] Here is a concrete example of how Person A might use this system:

[1738] 1. Data entry: Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[1739] 2. Data transmission: The device transmits this information to the server.

[1740] 3. Server Processing:

[1741] The server receives and analyzes the data.

[1742] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[1743] Health advice is generated and sent back to the device.

[1744] 4. Receiving advice: The terminal receives advice from the server.

[1745] 5. Displaying advice: The device displays advice to Person A, who then manages his or her health based on that advice.

[1746] This system allows Ms. A to receive specific health advice based on her menstrual cycle, enabling her to optimally manage her health in her daily life.

[1747] The processing flow will be explained below.

[1748] Step 1:

[1749] The user opens the application and enters menstrual cycle data (last period start date and cycle length).

[1750] Step 2:

[1751] The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1752] json

[1753] {

[1754] "user_id": "12345",

[1755] "last_period_start_date": "2023-10-01",

[1756] "cycle_length": 28

[1757] }

[1758] Step 3:

[1759] The server receives the HTTP POST request and parses the JSON data, specifically extracting the last_period_start_date and cycle_length.

[1760] Step 4:

[1761] The server inputs the extracted data into the generative AI model to predict the start date of the user's next period. For example, if the input last_period_start_date is October 1, 2023, and the cycle_length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[1762] Step 5:

[1763] The server generates personalized health advice for each user based on the prediction results. Based on Femtech guidelines, the server creates personalized advice such as:

[1764] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[1765] During menstruation: Make sure you drink plenty of fluids.

[1766] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1767] Step 6:

[1768] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1769] json

[1770] {

[1771] "advice": {

[1772] "nutrition": {

[1773] "pre_period": "Consume foods rich in iron and vitamin C.",

[1774] "during_period": "Stay hydrated."

[1775] },

[1776] "exercise": {

[1777] "pre_period": "Engage in light exercises or stretching.",

[1778] "during_period": "Practice yoga or walking for relaxation."

[1779] },

[1780] "predicted_next_period": "2023-10-29"

[1781] }

[1782] }

[1783] Step 7:

[1784] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[1785] Step 8:

[1786] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[1787] Nutritional Recommendations

[1788] Exercise recommendations

[1789] Predicted start date of next period

[1790] Step 9:

[1791] The user checks the displayed health advice and puts it into practice in their daily life, for example, by eating iron-rich foods before menstruation.

[1792] Example 1

[1793] 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."

[1794] With conventional menstrual cycle management systems, it was difficult for users to receive specific advice on how to properly manage their health. Furthermore, menstrual cycle predictions were often inaccurate, making it difficult for users to trust the information and take action. As a result, users were unable to take appropriate measures at the appropriate time, which hindered their health management.

[1795] 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.

[1796] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for saving the data transmitted from the user's device and preparing input prompts for the analysis and generative AI model, means for applying health advice guidelines in the femtech field based on the prediction results, and means for returning the generated advice to the user's device. This enables the user to receive accurate menstrual cycle predictions and specific health advice based on them, enabling appropriate health management.

[1797] "User's menstrual cycle data" is a series of data related to the menstrual cycle, such as the start date of the last menstrual period and the length of the menstrual cycle, entered by the user.

[1798] A "generative AI model" is a machine learning model that predicts menstrual cycles based on past data.

[1799] An "input prompt" is a group of data that is input to the generative AI model to predict menstrual cycles.

[1800] The "Health Advice Guidelines in the Femtech Field" are guidelines for providing standard health advice in the technology field aimed at managing women's health.

[1801] "Health Advice" is personalized health guidance for a user, including nutrition and exercise recommendations, generated based on the predicted menstrual cycle.

[1802] A "user terminal" is a terminal device used by a user, and is a device for inputting menstrual cycle data and displaying health advice.

[1803] The present invention relates to a system that predicts a user's menstrual cycle and provides health advice based on specific femtech needs. The system receives menstrual cycle data entered by the user, analyzes it, and then uses a generative AI model to predict the menstrual cycle and provide appropriate health advice to the user.

[1804] System configuration

[1805] The system mainly consists of the following hardware and software:

[1806] 1. Server

[1807] 2. User devices (smartphones, tablets, etc.)

[1808] 3. Generative AI Models (Machine Learning Models)

[1809] Server Features

[1810] The server has the following features:

[1811] 1. Receiving User Information

[1812] The server receives data related to the menstrual cycle (e.g., the start date of the last period and the length of the cycle) from the user terminal, often received as an HTTP POST request.

[1813] 2. Data Analysis

[1814] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction. The server obtains the "last menstrual period start date" and "cycle length" from the JSON format data and uses them in the next processing step.

[1815] 3. Applying generative AI models

[1816] The server uses the generative AI model to predict the start date and each phase of the user's next period. For example, the server inputs "Last period start date: 2023-10-01" and "Cycle length: 28 days" as input prompts to the generative AI model.

[1817] 4. Health advice generation

[1818] Based on the prediction results of the generative AI model, the server applies femtech health advice guidelines and generates personalized health advice for each user, including recommendations on nutrition and exercise.

[1819] 5. Submitting Advice

[1820] The server sends the generated health advice to the user device, typically as JSON data in an HTTP response.

[1821] User device functions

[1822] The user terminal has the following features:

[1823] 1. Data Entry

[1824] The user inputs menstrual cycle data through the application screen, specifically the start date of the last menstrual period and the length of the menstrual cycle.

[1825] 2. Data Transmission

[1826] The device sends the input data to the server via an HTTP POST request in JSON format, providing the server with the data to run the predictive model.

[1827] 3. Receiving Advice

[1828] The device receives health advice sent as an HTTP response from the server, such as the generated health advice and the start date of the next menstruation.

[1829] 4. Displaying Advice

[1830] The terminal displays the received health advice on the application screen, allowing the user to take appropriate action based on it.

[1831] Specific examples

[1832] Here is a concrete example of how Person A might use this system:

[1833] 1. Data Entry

[1834] Ms. A enters the following information into the application: "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days."

[1835] 2. Data Transmission

[1836] The terminal sends this information to the server.

[1837] 3. Server Processing

[1838] The server receives and analyzes the data. For example, prompts such as "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" are input into the generative AI model.

[1839] 4. Generating predictions and advice

[1840] The generative AI model predicts the start date of the next period (October 29, 2023). Health advice is generated, such as "consume foods rich in iron and vitamin C" before menstruation and "stay hydrated" during menstruation.

[1841] 5. Receiving and displaying advice

[1842] The terminal receives advice from the server and displays it to Mr. A, who then manages his health based on it.

[1843] This system allows users to receive specific health advice based on their menstrual cycle, enabling them to optimally manage their health in their daily lives.

[1844] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1845] Specific processing flow of the program

[1846] Server Processing

[1847] Step 1: Receiving user information

[1848] The server receives data related to the menstrual cycle from the user terminal.

[1849] Input: HTTP POST request in JSON format (e.g., { "user_id": "12345", "last_period_start_date": "2023-10-01", "cycle_length": 28})

[1850] Processing: Temporarily storing data and preparing it for the next processing step.

[1851] Output: User data stored in internal data structures

[1852] Step 2: Analyze the data

[1853] The server analyzes the received data and extracts the information necessary for menstrual cycle prediction.

[1854] Input: Saved user data

[1855] Processing: Obtain the "last period start date" and "cycle length" from the JSON data (e.g., last period start date: 2023-10-01, cycle length: 28).

[1856] Output: Analyzed data (last menstrual period start date, cycle length)

[1857] Step 3: Applying the generative AI model

[1858] The server uses a generative AI model to predict the start date and phases of the user's next period.

[1859] Input: Analyzed data (last menstrual period start date, cycle length)

[1860] Processing: The generative AI model is given the input prompts "Last menstrual period start date: 2023-10-01" and "Cycle length: 28 days" to predict the menstrual cycle.

[1861] Output: Prediction result (e.g., next menstruation start date: 2023-10-29)

[1862] Step 4: Generate health advice

[1863] Based on the prediction results of the generative AI model, the server applies femtech guidelines to generate individual health advice for the user.

[1864] Input: Prediction result (start date of next period)

[1865] Treatment: Create advice based on guidelines regarding nutritional intake and exercise (e.g., before menstruation: take iron and vitamin C, during menstruation: make sure to stay hydrated).

[1866] Output: Generated health advice (e.g., {"nutrition": {"pre_period": "Consume foods rich in iron and vitamin C.", "during_period": "Stay hydrated."}, "exercise": {"pre_period": "Engage in light exercises or stretching.", "during_period": "Practice yoga or walking for relaxation."}, "predicted_next_period": "2023-10-29"})

[1867] Step 5: Submitting Advice

[1868] The server transmits the generated health advice to the user terminal.

[1869] Input: Generated health advice

[1870] Processing: Send JSON data to the user terminal as an HTTP response.

[1871] Output: Health advice sent to the user device

[1872] User terminal processing

[1873] Step 6: Data entry

[1874] The user inputs menstrual cycle data (last menstrual start date and cycle length) through the application screen.

[1875] Input: Last menstrual start date, cycle length (e.g., "Last menstrual start date: 2023-10-01", "Cycle length: 28 days")

[1876] Processing: The data entered by the user is temporarily saved in the terminal.

[1877] Output: Saved menstrual cycle data

[1878] Step 7: Send data

[1879] The terminal sends the entered data to the server via an HTTP POST request in JSON format.

[1880] Input: Saved menstrual cycle data

[1881] Operation: Generates an HTTP request and sends data to the specified server endpoint.

[1882] Output: Request sent to the server

[1883] Step 8: Receive advice

[1884] The device receives health advice sent as an HTTP response from the server.

[1885] Input: HTTP response from the server

[1886] Processing: Analyze the response content and extract the advice data.

[1887] Output: Extracted advice data

[1888] Step 9: View Advice

[1889] The device displays the received health advice on the application screen and guides the user to take appropriate action.

[1890] Input: Extracted advice data

[1891] Action: Update the UI to display the data on the application screen (e.g., "Recommended nutrients before menstruation: Iron and Vitamin C" and "Recommended behavior during menstruation: Stay hydrated").

[1892] Output: Advice displayed to the user

[1893] (Application example 1)

[1894] 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."

[1895] While systems that provide health advice based on a user's menstrual cycle already exist, they lack support that goes into the user's nutritional balance and diet. The present invention aims to provide more comprehensive support for users' health management by proposing and providing personalized food and drink menus so that users can easily eat meals that are appropriate for their menstrual cycle.

[1896] 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.

[1897] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for generating health advice based on the predicted menstrual cycle, means for transmitting the generated health advice to the user, means for generating a personalized meal menu based on the predicted menstrual cycle, and means for providing the generated meal menu to the user. This makes it possible to promptly propose and provide to the user not only health advice but also nutritionally balanced meal menus suited to the user's menstrual cycle.

[1898] "User's menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last period and the length of the menstrual cycle.

[1899] The "generative AI model" is an artificial intelligence model that predicts the start date of a user's next period and each phase based on received menstrual cycle data.

[1900] "Health advice" is a recommendation regarding nutritional intake and exercise to help the user manage their health based on the predicted menstrual cycle.

[1901] A "personalized meal menu" is a food and drink menu that is individually suggested based on the user's menstrual cycle and takes into consideration the optimal nutritional balance.

[1902] The term "means" is a general concept that refers to devices and systems for realizing a specific function in this invention.

[1903] This invention is a system that receives a user's menstrual cycle data, predicts the start date of the next period using a generative AI model, and generates and provides health advice and personalized meal menus based on the prediction results. This system interacts with the user via a smartphone application and can easily provide health advice and meal menu suggestions to the user.

[1904] System Overview

[1905] Server-side processing

[1906] The server receives menstrual cycle data (e.g., the start date of the last period and the length of the cycle) sent from the user's device. The received data is analyzed and a generative AI model is used to predict the menstrual cycle. Health advice and a personalized meal plan are then generated based on the prediction results and sent to the user's device. The hardware used includes a high-performance server, and the software includes Python (server-side implementation using Flask), generative AI models (TensorFlow or PyTorch), and databases (MySQL or SQLite).

[1907] Terminal side processing

[1908] Users enter their menstrual cycle data through the smartphone application screen. This data is sent to the server via an HTTP POST request. Health advice and personalized meal menus sent from the server are received and displayed on the application screen. Users can also order delivery of the suggested menu items.

[1909] Processing flow

[1910] When a user enters the start date of their last period and the length of their cycle into the application, that data is sent to the server. The server receives and analyzes the data. It uses a generative AI model to predict the start date of the next period and generates health advice and a personalized meal plan based on the prediction. The generated data is then sent back to the user's device and displayed on the application screen.

[1911] Specific examples

[1912] For example, if a user enters "last period start date: October 1, 2023" and "cycle length: 28 days" into the application, the server receives this and uses the generative AI model to predict the next period start date (October 29, 2023). Based on the results, the following health advice is generated:

[1913] Premenstrual period: It is recommended to consume foods rich in iron and vitamin C.

[1914] During menstruation: Stay hydrated.

[1915] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1916] Additionally, personalized meal suggestions are also available:

[1917] Premenstrual: Spinach salad with citrus dressing, grilled chicken and quinoa.

[1918] During menstruation: Cucumber mint water, tomato and mozzarella salad.

[1919] Prompt Sentence Examples

[1920] "My last period started on October 1, 2023, and my cycle is 28 days. When is my next period? Also, what specific foods and nutrients should I be consuming throughout that period?"

[1921] In this way, the system of the present invention allows the user to receive personalized support for appropriate health management in accordance with their menstrual cycle.

[1922] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1923] Step 1:

[1924] The user inputs the "last menstrual start date" and "cycle length" through a smartphone application. This data is sent to the server as an HTTP POST request to the endpoint specified by the URI. The input data includes, for example, the user's ID, last menstrual start date, and menstrual cycle length.

[1925] Step 2:

[1926] The server analyzes the received HTTP POST request and extracts menstrual cycle data. The analyzed data is saved in the form of the menstrual start date and cycle length. The server inputs this data into a generative AI model, which processes and calculates the data to predict the menstrual cycle.

[1927] Step 3:

[1928] The server applies a generative AI model (using, for example, TensorFlow or PyTorch) to predict the start date and phases (premenstrual, menstrual, and postmenstrual) of the user's next period. The generative AI model makes a prediction based on the input data, and the output is the start date and phase information of the next period.

[1929] Step 4:

[1930] The server generates health advice based on the predicted menstrual cycle, aligned with standard health guidelines, including nutritional recommendations and exercise advice. The advice generated is specific and helpful for the user in managing their health.

[1931] Step 5:

[1932] The server then generates a personalized meal menu based on the predictions, which is designed to balance the nutritional intake of the user's menstrual cycle and includes specific dishes and ingredients recommended for each phase.

[1933] Step 6:

[1934] The server compiles the generated health advice and personalized meal menus and sends them to the user's device as an HTTP response. The output data includes health advice, the start date of the next menstrual period, and meal menus for each phase.

[1935] Step 7:

[1936] The user's device analyzes the received data and displays it on the application screen. The user can check the displayed information, such as the start date of their next period, health advice, and suggested meal menus. The user can also order the suggested menus for delivery.

[1937] Step 8:

[1938] If the user wishes to order food delivery, they confirm the selected menu items and complete the delivery order. The order is sent to the food delivery company via the smartphone app, and the meal is delivered to the user at the appropriate time.

[1939] Through the above processing steps, the present invention realizes a system that provides users with health management and dietary suggestions suited to their needs.

[1940] 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.

[1941] The present invention combines a system that predicts a user's menstrual cycle data and provides health advice based on specific femtech needs with an emotion engine that recognizes the user's emotions. This system provides more precise and personalized health care based not only on the user's health status but also on their emotional state.

[1942] overview

[1943] The system receives and analyzes the user's menstrual cycle data, then uses a generative AI model to predict the menstrual cycle. It also analyzes the user's emotional state using an emotion engine to generate and provide health advice to the user.

[1944] Explanation of program processing

[1945] Server Processing

[1946] 1. Receiving User Information

[1947] The server receives data related to the menstrual cycle (e.g., the start date of the last menstrual period and the length of the menstrual cycle) from the user terminal, as well as emotional information such as user input data, voice, and images.

[1948] For example, data can be received via an HTTP POST request in JSON format, such as:

[1949] json

[1950] {

[1951] "user_id": "12345",

[1952] "last_period_start_date": "2023-10-01",

[1953] "cycle_length": 28,

[1954] "emotion_data": {

[1955] "text": "I'm feeling stressed",

[1956] "voice": "audio_data",

[1957] "image": "image_data"

[1958] }

[1959] }

[1960] 2. Data Analysis

[1961] The server analyzes the received menstrual cycle data and extracts data necessary for menstrual cycle prediction (e.g., the start date of the last period, cycle length, etc.). It also analyzes the emotional data to identify the user's emotional state.

[1962] 3. Applying generative AI models

[1963] The server uses the generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the server predicts the start date of the next period to be October 29, 2023.

[1964] 4. Applying the Emotion Engine

[1965] The server uses an emotion engine to analyze the user's emotional state from their input data, voice, and images. For example, if a user inputs "I'm feeling stressed," the server identifies the emotional state as "stress."

[1966] 5. Health advice generation

[1967] The server generates personalized health advice based on the prediction results of the generative AI model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, it creates advice such as:

[1968] Premenstrual period: Recommend consuming foods rich in iron and vitamin C. Also, if the emotional state is stressful, aromatherapy is recommended for relaxation.

[1969] During menstruation: Stay well hydrated and, if your emotional state is fatigue, get plenty of rest.

[1970] Exercise: Light exercise and stretching are recommended before menstruation, and yoga or walking to relax during menstruation.

[1971] 6. Submitting Advice

[1972] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[1973] json

[1974] {

[1975] "advice": {

[1976] "nutrition": {

[1977] "pre_period": "Consume foods rich in iron and vitamin C.",

[1978] "during_period": "Stay hydrated."

[1979] },

[1980] "exercise": {

[1981] "pre_period": "Engage in light exercises or stretching.",

[1982] "during_period": "Practice yoga or walking for relaxation."

[1983] },

[1984] "emotion": {

[1985] "stress": "Try aromatherapy to relax.",

[1986] "fatigue": "Make sure to get plenty of rest."

[1987] },

[1988] "predicted_next_period": "2023-10-29"

[1989] }

[1990] }

[1991] User terminal processing

[1992] 1. Data Entry

[1993] The user inputs menstrual cycle data (e.g., the start date of the last period and the length of the cycle) and emotional state (text, voice, image, etc.) through the application screen.

[1994] 2. Data Transmission

[1995] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request.

[1996] 3. Receiving Advice

[1997] The device receives health advice sent as an HTTP response from the server.

[1998] 4. Displaying Advice

[1999] The device displays the received health advice on the application screen and notifies the user so that they can take appropriate action based on it.

[2000] Specific examples

[2001] Here is a concrete example of how Person B might use this system:

[2002] 1. Data entry: Person B enters "Last menstrual period start date: October 1, 2023" and "Cycle length: 28 days" into the application, and also enters her emotional state in text, "I'm feeling stressed."

[2003] 2. Data transmission: The device transmits this information to the server.

[2004] 3. Server Processing:

[2005] The server receives and analyzes the data.

[2006] A generative AI model is used to predict the start date of the next period (October 29, 2023).

[2007] The emotion engine identifies the emotion "stress."

[2008] Health advice is generated and sent back to the device.

[2009] 4. Receiving advice: The terminal receives advice from the server.

[2010] 5. Displaying Advice: The device displays advice to Person B, who can then manage his or her health based on the advice. For example, Person B may consume iron-rich foods and use aromatherapy to relieve stress.

[2011] This system allows Ms. B to receive not only specific health advice based on her menstrual cycle, but also advice tailored to her emotional state, enabling her to manage her health more effectively.

[2012] The processing flow will be explained below.

[2013] Step 1:

[2014] The user opens the application and enters menstrual cycle data (last period start date and cycle length) and emotional state (text, voice, image, etc.).

[2015] Step 2:

[2016] The device converts the input menstrual cycle data and emotion data into JSON format and sends it to the server as an HTTP POST request.

[2017] json

[2018] {

[2019] "user_id": "12345",

[2020] "last_period_start_date": "2023-10-01",

[2021] "cycle_length": 28,

[2022] "emotion_data": {

[2023] "text": "I'm feeling stressed",

[2024] "voice": "audio_data",

[2025] "image": "image_data"

[2026] }

[2027] }

[2028] Step 3:

[2029] The server receives the HTTP POST request and parses the JSON data to extract menstrual cycle data (last_period_start_date and cycle_length) and emotion data.

[2030] Step 4:

[2031] The server inputs the extracted menstrual cycle data into a generative AI model to predict the start date of the user's next period. For example, if the start date of the last period was October 1, 2023, and the cycle length is 28 days, the next period will be predicted to start on October 29, 2023.

[2032] Step 5:

[2033] The server uses an emotion engine to analyze the emotion data (text, voice, image) entered by the user and identify the user's emotional state. For example, if the text is "I'm feeling stressed," the server identifies the emotional state as "stress."

[2034] Step 6:

[2035] The server generates personalized health advice based on the prediction results of the AI ​​model and the analysis results of the emotion engine. Taking into account the femtech guidelines and the emotional state, the server generates advice such as:

[2036] For premenstrual nutrition, it is recommended to consume foods rich in iron and vitamin C.

[2037] When caring for yourself during your period, make sure you drink plenty of fluids.

[2038] If the user is feeling stressed, aromatherapy is recommended to help them relax.

[2039] As for exercise recommendations, light exercise and stretching are recommended before menstruation, and yoga or walking for relaxation during menstruation is recommended.

[2040] Step 7:

[2041] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[2042] json

[2043] {

[2044] "advice": {

[2045] "nutrition": {

[2046] "pre_period": "Consume foods rich in iron and vitamin C.",

[2047] "during_period": "Stay hydrated."

[2048] },

[2049] "exercise": {

[2050] "pre_period": "Engage in light exercises or stretching.",

[2051] "during_period": "Practice yoga or walking for relaxation."

[2052] },

[2053] "emotion": {

[2054] "stress": "Try aromatherapy to relax."

[2055] },

[2056] "predicted_next_period": "2023-10-29"

[2057] }

[2058] }

[2059] Step 8:

[2060] The device receives the HTTP response from the server and parses the JSON data to extract health advice.

[2061] Step 9:

[2062] The device will display the analyzed health advice on the application screen, allowing users to view the following information:

[2063] Nutritional Recommendations

[2064] Exercise recommendations

[2065] Specific advice depending on your emotional state

[2066] Predicted start date of next period

[2067] Step 10:

[2068] The user checks the displayed health advice and puts it into practice in daily life. For example, if the user feels stressed, they can take action such as eating foods rich in iron and practicing aromatherapy.

[2069] Example 2

[2070] 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."

[2071] While current health management systems provide advice based on a user's menstrual cycle data, they lack health advice that takes into account the user's emotional state. This makes it difficult to comprehensively manage a user's overall health, and in particular, it is difficult to fully evaluate the impact of emotional stress and fatigue on health.

[2072] 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.

[2073] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model that predicts the menstrual cycle based on the analysis results, means for receiving the user's emotional data, means for analyzing the received emotional data, means for generating health advice based on the prediction results of the generative AI model and the analyzed emotional data, and means for transmitting the generated health advice to the user, thereby enabling more precise and personalized health care based on both the user's menstrual cycle and emotional state.

[2074] "Menstrual cycle data" is information about the user's menstruation, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[2075] The "means for receiving" is an interface for importing data from a user terminal into a server, and includes a function for receiving data using an HTTP request or other protocol.

[2076] "Means for analyzing" refers to a function that analyzes the data received by the server and performs processing to extract and understand the necessary information.

[2077] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to predict menstrual cycles, and makes highly accurate predictions based on past data.

[2078] "Emotional data" is information about the user's emotional state, and includes text, audio, and image data.

[2079] An "emotion engine" is a technology or system for analyzing emotion data and identifying a user's emotional state.

[2080] "Health advice" refers to specific recommendations or instructions regarding health management provided to the user based on the analysis results or prediction results.

[2081] The "transmission means" is an interface for returning the generated health advice to the user terminal, and includes a function for transmitting data using an HTTP response or other protocol.

[2082] This invention is a system that receives and analyzes a user's menstrual cycle data and emotional data, and provides menstrual cycle predictions and health advice using a generative AI model and emotional engine. This system operates on the basis of a server and a user terminal.

[2083] Server configuration and operation

[2084] 1. Receiving User Information

[2085] The server receives menstrual cycle data (last menstrual start date and cycle length) and emotional data (text, voice, and image) from the user's device. This allows data based on the user's situation to be collected in real time. For example, a user might enter "last menstrual start date: October 1, 2023," "cycle length: 28 days," and "I'm feeling stressed."

[2086] 2. Data Analysis

[2087] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing (NLP) engine, voice recognition software, and image recognition software, ensuring consistency and accuracy of the data.

[2088] 3. Applying generative AI models

[2089] The server applies a generative AI model based on menstrual cycle data to predict the start date of your next period. For example, if your last period started on October 1, 2023, and your cycle is 28 days long, the server predicts your next period will start on October 29, 2023. This generative AI model uses deep learning algorithms to make highly accurate predictions.

[2090] 4. Applying the Emotion Engine

[2091] The server analyzes the emotional data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[2092] 5. Health advice generation

[2093] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[2094] 6. Submitting Advice

[2095] The generated health advice is sent from the server to the user's device as an HTTP response. The advice is sent in JSON format and is displayed on the user's device after analysis.

[2096] Configuration and operation of user terminal

[2097] 1. Data Entry

[2098] Users input their menstrual cycle and emotional data through the application screen. The application provides an intuitive interface, allowing users to easily input data.

[2099] 2. Data Transmission

[2100] The user device converts the input data into JSON format and sends it to the server as an HTTP POST request. For security reasons, the communication is encrypted with SSL / TLS.

[2101] 3. Receiving and Displaying Advice

[2102] The user's device receives the advice sent from the server and displays it on the screen. It also has a notification function so that users can act quickly based on the advice. It also has a save function so that users can refer to past advice.

[2103] Specific examples

[2104] When a user uses this system, it works like this:

[2105] 1. The user enters the following information into the application: "Last period start date: October 1, 2023" and "Cycle length: 28 days" and then enters their emotional state in the text "I'm feeling stressed."

[2106] 2. The device sends this information to the server, which analyzes the data.

[2107] 3. The server uses a generative AI model to predict the start date of the next period and an emotion engine to identify the emotion "stress."

[2108] 4. The server generates personalized health advice and sends it back to the device.

[2109] 5. The device receives the advice and displays it to the user, who then manages their health based on the advice.

[2110] For example, a user may choose to eat iron-rich foods or try aromatherapy to relieve stress. The system allows users to receive specific health advice based on their menstrual cycle and emotional state, leading to more effective health management.

[2111] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2112] Step 1:

[2113] Data Entry

[2114] The user uses the application screen to input menstrual cycle data (last menstrual start date and cycle length) and emotion data (text, voice, image).

[2115] Input: Menstrual cycle data and emotion data entered by the user.

[2116] Output: Input data temporarily stored on the user's device.

[2117] Step 2:

[2118] Data transmission

[2119] The device converts the input data into JSON format and sends it to the server as an HTTP POST request. The communication is encrypted with SSL / TLS.

[2120] Input: Menstrual cycle data and emotion data entered by the user into the device.

[2121] Output: JSON formatted data sent to the server.

[2122] Step 3:

[2123] Receiving user information

[2124] The server receives the menstrual cycle data and emotion data transmitted from the user terminal.

[2125] Input: JSON formatted data.

[2126] Output: Menstrual cycle data and emotion data stored in the server's memory and database.

[2127] Step 4:

[2128] Data analysis

[2129] The server analyzes the received data and extracts the necessary information (last period start date, cycle length, emotional state) using a natural language processing engine, voice recognition software, and image recognition software.

[2130] Input: Menstrual cycle data and emotion data stored on the server.

[2131] Output: Analyzed menstrual cycle information and emotional state.

[2132] Step 5:

[2133] Applying generative AI models

[2134] The server then applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period. For example, if the start date of your last period was October 1, 2023, and your cycle length is 28 days, the server will predict the start date of your next period as October 29, 2023. This process uses a deep learning algorithm.

[2135] Input: Parsed menstrual cycle information.

[2136] Output: Predicted start date of next period.

[2137] Step 6:

[2138] Applying the Emotion Engine

[2139] The server analyzes the emotion data and identifies the user's emotional state. For example, if the text data "I'm feeling stressed" is entered, the emotion engine will recognize the user's emotional state as "stressed." Similar analysis is performed on voice and image data.

[2140] Input: Parsed emotion data.

[2141] Output: Identified emotional state.

[2142] Step 7:

[2143] Generating health advice

[2144] The server generates health advice for the user based on the predictions of the generative AI model and the analysis results of the emotion engine. For example, if the predicted start date of the next menstrual period is approaching, the server may recommend that the user consume iron-rich foods, or recommend aromatherapy if stress is identified.

[2145] Input: Predicted start date of next period and identified emotional state.

[2146] Output: The generated health advice.

[2147] Step 8:

[2148] Sending Advice

[2149] The server converts the generated health advice into JSON format and sends it to the user's terminal as an HTTP response.

[2150] Input: Generated health advice.

[2151] Output: Health advice in JSON format sent to user device.

[2152] Step 9:

[2153] Receiving and viewing advice

[2154] The device receives health advice sent from the server and displays it on the application screen. A notification function is also provided so that users can act on the advice quickly. There is also a function to save past advice.

[2155] Input: Health advice sent from the server in JSON format.

[2156] Output: Health advice and notifications displayed on the application screen.

[2157] (Application example 2)

[2158] 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."

[2159] The challenge is to provide a system that can increase user satisfaction with food delivery services and assist with health management by providing health advice and food suggestions based on the user's menstrual cycle and emotional state. Currently, food suggestions are made without taking menstrual cycles or emotional states into consideration, so it is often not possible to suggest foods that are optimal for each individual user. Therefore, there is a need for a system that can provide precise, personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[2160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2161] In this invention, the server includes means for receiving a user's menstrual cycle data, means for analyzing the received data, means for applying a generative AI model to predict the menstrual cycle based on the analysis results, means for applying an emotion engine to analyze the user's emotion data and identify the user's emotional state, means for generating health advice and food suggestions based on the predicted menstrual cycle and emotional state, and means for transmitting the generated health advice and food suggestions to the user, thereby enabling precise and personalized health advice and food suggestions based on the user's menstrual cycle and emotional state.

[2162] "Menstrual cycle data" is information about the user's menstrual cycle, such as the start date of the user's last menstrual period and the length of the menstrual cycle.

[2163] A "generative AI model" is an artificial intelligence model that analyzes received menstrual cycle data and predicts the start date of the next period and other cycle data.

[2164] The "emotion engine" is an analytical engine that analyzes user input data, voice data, and image data to identify the user's emotional state.

[2165] "Health advice" is specific health management recommendations such as nutritional intake and exercise based on the user's menstrual cycle and emotional state.

[2166] "Food Suggestion" refers to recommending specific foods to improve a user's health based on their menstrual cycle and emotional state.

[2167] The "means for transmitting to the user" refers to a communication means for transmitting the generated health advice and food suggestions to the user's terminal.

[2168] The present invention provides a system for providing health advice and food recommendations based on a user's menstrual cycle and emotional state in a food delivery service. The system is implemented in the following steps.

[2169] The server first receives menstrual cycle data and emotional data from the user terminal, including the start date of the last period, the length of the period, and text, audio, and image data related to the user's emotional state.

[2170] The server then analyzes the received data: it analyzes menstrual cycle data and uses a generative AI model to predict the start date of the next period, and it analyzes emotional data using an emotion engine to identify the user's emotional state.

[2171] Based on the analysis results, the server generates health advice and food suggestions based on the user's menstrual cycle and emotional state. Specifically, it recommends that the user consume foods rich in iron and vitamin C before their period, and that they try aromatherapy to relax when they are stressed.

[2172] The generated health advice and food suggestions are sent from the server to the user's device. The user receives this information through the application and manages their health based on the displayed health advice and food suggestions. Specifically, the user can directly order the suggested foods within the application and have them delivered.

[2173] For example, if user B uses this system,

[2174] 1. If you enter "Last period start date: October 1, 2023" and "Cycle length: 28 days" and say "I'm feeling stressed," the server will predict the start date of your next period as October 29, 2023, and suggest aromatic teas and vitamin-rich fruits as foods to relieve stress.

[2175] 2. After checking the displayed advice, User B can immediately put it into action by ordering the suggested food through the application and having it delivered.

[2176] To illustrate, here are some example prompts:

[2177] "User: My last period started on October 1, 2023, and my cycle length is 28 days. I'm also feeling stressed. What is the start date of my next period and what foods do you recommend?"

[2178] This allows users to receive health advice and food suggestions that are best suited to their individual conditions, allowing them to effectively manage their health while increasing their satisfaction with the food delivery service.

[2179] The key technical components of this system are a generative AI model and an emotion engine, the latter of which analyzes the user's emotional data, and the former of which predicts the start date of the next period based on cycle data.

[2180] In certain embodiments, a Flask server acts as the central point for receiving and analyzing data from users, while the emotion engine and generative AI models are implemented using specialized software or libraries.

[2181] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2182] Step 1:

[2183] The user inputs menstrual cycle data and emotional data through the device. Specifically, the user inputs the "last menstrual period start date" and "cycle length" on the application screen, and inputs text, voice, or images related to their emotional state.

[2184] Input: User's menstrual cycle data (last menstrual start date, cycle length) and emotional data (text, voice, image)

[2185] Output: JSON formatted menstrual cycle data and emotion data

[2186] Step 2:

[2187] The device converts the input data into JSON format and sends it to the server. Specifically, the data entered by the user is sent to the server via an HTTP POST request.

[2188] Input: Menstrual cycle data and emotion data entered by the user into the device

[2189] Output: JSON data sent to the server

[2190] Step 3:

[2191] The server receives and analyzes the data sent by the user. Specifically, the server receives an HTTP request and parses and analyzes the data in JSON format.

[2192] Input: JSON data sent from the terminal

[2193] Output: Analyzed menstrual cycle data and emotion data

[2194] Step 4:

[2195] The server applies a generative AI model based on the analyzed menstrual cycle data to predict the start date of the next period.Specifically, the generative AI model inputs menstrual cycle data and estimates the start date of the next period.

[2196] Input: Analyzed menstrual cycle data (last menstrual start date, cycle length)

[2197] Output: Predicted start date of next period

[2198] Step 5:

[2199] The server analyzes the emotional data using an emotion engine to identify the user's emotional state. Specifically, it analyzes text, voice, and image data to identify the user's emotional state.

[2200] Input: Analyzed emotion data (text, audio, images)

[2201] Output: Identified emotional state

[2202] Step 6:

[2203] The server generates health advice and food suggestions based on the menstrual cycle prediction results and emotional state.Specifically, it generates nutrition advice, exercise advice, and appropriate food suggestions based on femtech guidelines and emotional data.

[2204] Input: Predicted next period start date, identified emotional state

[2205] Output: Health advice and food suggestions

[2206] Step 7:

[2207] The server converts the generated health advice and food suggestions into JSON format and sends it to the user's device as an HTTP response.

[2208] Input: Generated health advice and food suggestions

[2209] Output: JSON data sent to the user's device

[2210] Step 8:

[2211] The device analyzes the health advice and food suggestions received from the server and displays them to the user. Specifically, the device displays the received data on the application screen and notifies the user so that they can act accordingly.

[2212] Input: JSON data received from the server

[2213] Output: Health advice and food suggestions displayed on the application screen

[2214] Step 9:

[2215] The user orders the suggested food through the application and requests delivery. Specifically, the user selects the food within the application and places an order and requests delivery.

[2216] Input: Food selected by user

[2217] Output: Food ordered and delivery request

[2218] 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.

[2219] 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.

[2220] 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.

[2221] 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.

[2222] 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.

[2223] 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.

[2224] 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).

[2225] 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.

[2226] 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."

[2227] 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.

[2228] 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).

[2229] 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.

[2230] 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.

[2231] 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.

[2232] 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.

[2233] 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.

[2234] 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.

[2235] 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.

[2236] 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.

[2237] 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.

[2238] 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.

[2239] The following is further disclosed regarding the above embodiment.

[2240] (Claim 1)

[2241] means for receiving menstrual cycle data of a user;

[2242] means for analyzing the received data;

[2243] A means of applying a generative AI model to predict menstrual cycles based on the analysis results; and

[2244] means for generating health advice based on the predicted menstrual cycle;

[2245] The system includes means for transmitting the generated health advice to a user.

[2246] (Claim 2)

[2247] 10. The system of claim 1, wherein the user's menstrual cycle data includes the start date of the last period and the length of the menstrual cycle.

[2248] (Claim 3)

[2249] 10. The system of claim 1, wherein the health advice includes nutritional recommendations and exercise advice.

[2250] "Example 1"

[2251] (Claim 1)

[2252] means for receiving menstrual cycle data of a user;

[2253] means for analyzing the received data;

[2254] A means of applying a generative AI model to predict menstrual cycles based on the analysis results; and

[2255] means for generating health advice based on the predicted menstrual cycle;

[2256] means for transmitting the generated health advice to a user;

[2257] a means for storing data transmitted from a user's device and preparing input prompts for analysis and generative AI models;

[2258] A means of applying health advice guidelines in the femtech field based on the prediction results;

[2259] The system includes means for transmitting the generated advice back to the user terminal.

[2260] (Claim 2)

[2261] 10. The system of claim 1, wherein the user's menstrual cycle data includes the start date of the last period and the length of the menstrual cycle.

[2262] (Claim 3)

[2263] 10. The system of claim 1, wherein the health advice includes nutritional recommendations and exercise advice.

[2264] "Application Example 1"

[2265] (Claim 1)

[2266] means for receiving menstrual cycle data of a user;

[2267] means for analyzing the received data;

[2268] A means of applying a generative AI model to predict menstrual cycles based on the analysis results; and

[2269] means for generating health advice based on the predicted menstrual cycle;

[2270] means for transmitting the generated health advice to a user;

[2271] means for generating a personalized meal menu based on the predicted menstrual cycle;

[2272] The system includes a means for providing the generated meal menu to a user.

[2273] (Claim 2)

[2274] 10. The system of claim 1, wherein the user's menstrual cycle data includes the start date of the last period and the length of the menstrual cycle.

[2275] (Claim 3)

[2276] 10. The system of claim 1, wherein the health advice includes nutritional recommendations and exercise advice.

[2277] "Example 2: Combining Emotion Engines"

[2278] (Claim 1)

[2279] means for receiving menstrual cycle data of a user;

[2280] means for analyzing the received data;

[2281] A means of applying a generative AI model to predict menstrual cycles based on the analysis results; and

[2282] means for receiving user emotion data;

[2283] means for analyzing the received emotion data;

[2284] A means for generating health advice based on the prediction results of the generative AI model and the analyzed emotion data; and

[2285] The system includes means for transmitting the generated health advice to a user.

[2286] (Claim 2)

[2287] 10. The system of claim 1, wherein the user's menstrual cycle data includes the start date of the last period and the length of the menstrual cycle.

[2288] (Claim 3)

[2289] 10. The system of claim 1, wherein the health advice includes nutritional recommendations, exercise recommendations, and relaxation recommendations based on emotional state.

[2290] "Application example 2 when combining emotion engines"

[2291] (Claim 1)

[2292] means for receiving menstrual cycle data of a user;

[2293] means for analyzing the received data;

[2294] A means of applying a generative AI model to predict menstrual cycles based on the analysis results; and

[2295] means for applying an emotion engine to analyze the user's emotion data and identify an emotional state;

[2296] means for generating health advice and food suggestions based on the predicted menstrual cycle and emotional state;

[2297] The system includes means for transmitting the generated health advice and food suggestions to a user.

[2298] (Claim 2)

[2299] 10. The system of claim 1, wherein the user's menstrual cycle data includes the start date of the last period and the length of the menstrual cycle.

[2300] (Claim 3)

[2301] 10. The system of claim 1, wherein the health advice includes nutritional recommendations and exercise advice. [Explanation of symbols]

[2302] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving menstrual cycle data of a user; means for analyzing the received data; A means of applying a generative AI model to predict menstrual cycles based on the analysis results; and means for generating health advice based on the predicted menstrual cycle; The system includes means for transmitting the generated health advice to a user.

2. The system of claim 1 , wherein the user's menstrual cycle data includes the start date of the last period and the length of the menstrual cycle.

3. The system of claim 1 , wherein the health advice includes nutritional recommendations and exercise advice.

Images