system

Abstract

Provide a system. The method includes: receiving a health-related message from a user; means for analyzing the message to identify a health problem of the user; a means for obtaining data related to the identified health problem from other applications; A means of analyzing the acquired data to identify the causes of health problems; a means for generating improvement recommendations based on the identified factors; a means for notifying the user of the generated improvement suggestions; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, many people suffer from mild ill health and fatigue, and there is a need for a convenient way to consult about these issues. However, current systems have issues such as making it difficult to obtain appropriate measures when people are feeling unwell but not severe enough to go to the hospital. There is also a need for health management applications to link with each other to provide more accurate and effective health advice. [Means for solving the problem]

[0005] The present invention provides a system that receives health-related messages from users, analyzes the messages using a natural language processing engine, and identifies the user's health problems. The system acquires data related to the identified health problems from health management applications, exercise management applications, and medication management applications, analyzes the data, and identifies the causes of the health problems. Furthermore, the system generates improvement proposals based on the identified causes and notifies the user of the improvement proposals, allowing the user to easily take measures.

[0006] "User" refers to an individual who uses this system and provides health-related information.

[0007] "Health-related messages" refer to comments or questions about health or well-being that users enter into the system.

[0008] A "natural language processing engine" refers to technology that analyzes text written in human language and automatically understands the meaning contained within it.

[0009] "Health Issues" refers to any ill health or health concerns that a User is experiencing.

[0010] "Means of obtaining data from other applications" refers to the processes and techniques used to gather the required information from external health management applications, exercise management applications, and medication management applications.

[0011] "Analysis" refers to the process of examining acquired data in detail and detecting patterns and factors contained within it.

[0012] "Contributing Factor" refers to any cause that may cause or aggravate a User's health problem.

[0013] "Means for generating improvement recommendations" refers to the process of creating specific advice or suggestions to improve the user's health status based on the identified factors.

[0014] "Means of notification" refers to the methods and techniques used to communicate generated improvement proposals to users.

[0015] "Dietary Data" refers to information about a user's daily diet recorded in the health management application.

[0016] "Exercise Data" means information about a User's exercise history and fitness activities recorded in the Exercise Management Application.

[0017] "Medication Data" refers to information about medications currently taken by a User, as well as their usage and side effects, recorded in the medication management application. [Brief explanation of the drawings]

[0018] [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 illustrating 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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a diet management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. The following describes an embodiment of this system.

[0040] System Overview

[0041] The system consists of the following main components:

[0042] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[0043] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[0044] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[0045] Program processing

[0046] Receiving and Parsing User Input

[0047] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[0048] Terminal: Sends received messages to the server.

[0049] Server: Uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[0050] Data linkage and acquisition

[0051] Server: After a health problem is identified, the server, with the user's consent, connects with relevant applications (diet management app, exercise management app, medication management app) and obtains the necessary data via API.

[0052] Terminal: Display the acquired data to the user and ask them to correct any errors.

[0053] Factor analysis and generation of improvement proposals

[0054] Server: Analyzes the acquired data (dietary history, exercise history, medication history) and clarifies the causes of identified health problems (e.g., fatigue).

[0055] Server: Generates specific improvement proposals based on the results of the factor analysis. For example, if a lack of vitamin B is the cause, the server generates advice such as "We suggest that you consume foods rich in vitamin B."

[0056] Notifying users and getting feedback

[0057] Server: Sends the generated improvement suggestions to the user.

[0058] On the device: Show the user suggested improvements and accept additional inquiries and feedback as needed.

[0059] Specific examples

[0060] Example 1: Dietary nutrient deficiency

[0061] 1. Terminal: The user types, "I feel tired."

[0062] 2. Server: Identify "fatigue" using a natural language processing engine.

[0063] 3. Server: Acquires food history data from the food management app.

[0064] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[0065] 5. Server: Generates an improvement suggestion: "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B (e.g., fish, chicken, beans)."

[0066] 6. Terminal: Display the suggestions to the user.

[0067] Example 2: Fatigue due to excessive exercise

[0068] 1. Device: The user types, "I've been feeling really tired lately."

[0069] 2. Server: Identify "fatigue" using a natural language processing engine.

[0070] 3. Server: Obtains exercise history data from the running app.

[0071] 4. Server: Analyzes the data and identifies hyperactivity.

[0072] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[0073] 6. Terminal: Display the suggestions to the user.

[0074] Through this system, users can receive prompt and appropriate treatment for even mild illnesses that do not require a visit to the hospital, and by linking and analyzing data, they can receive more accurate and personalized health advice.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[0078] Step 2:

[0079] Terminal: Sends the entered message to the server.

[0080] Step 3:

[0081] Server: Passes the received message to a natural language processing engine for analysis. Specifically, it analyzes the context and identifies the user's health problem (in this case, "fatigue").

[0082] Step 4:

[0083] Server: Based on the identified health issue, it sends API requests to relevant applications (diet management app, exercise management app, medicine record book) to obtain the user's latest data.

[0084] Step 5:

[0085] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[0086] Step 6:

[0087] Server: Analyzes the acquired data and identifies the causes of health problems. Specifically, it analyzes the following data individually:

[0088] Dietary data: Identify nutrient deficiencies and excesses.

[0089] Exercise data: Identify over- or under-exercise.

[0090] Drug data: Identify potential health issues caused by medication side effects.

[0091] Step 7:

[0092] Server: Generates improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest eating foods rich in vitamin B" is generated.

[0093] Step 8:

[0094] Server: Sends the generated improvement suggestions to the user.

[0095] Step 9:

[0096] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[0097] Step 10:

[0098] Users: Review the proposal and provide additional inquiries or feedback as needed.

[0099] Example 1

[0100] 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."

[0101] In today's modern living environment, it is important to detect minor health problems early and take appropriate measures. However, conventional methods require users to operate health management applications individually, and collect and analyze data, which is time-consuming. In addition, integrating and analyzing data from each application is technically difficult, and some factors may be overlooked. This makes it difficult for users to quickly receive appropriate health advice.

[0102] 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.

[0103] In this invention, the server includes means for receiving health-related messages from a user, means for analyzing the messages to identify a health problem of the user, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating an improvement plan based on the identified cause, means for notifying the user of the generated improvement plan, means for displaying the acquired data to the user to encourage correction, and means for receiving user feedback based on the generated improvement plan. This eliminates the need for users to operate individual applications, and enables the centralized collection and analysis of health data to quickly receive appropriate advice.

[0104] "Health-related messages" are text data in which users write about their health status and physical condition.

[0105] A "health issue" is a specific health problem or symptom that a user is experiencing.

[0106] An "application" is a software program that users use on their smartphones or tablets to manage their health and record data.

[0107] "Data" refers to records of health information about the user, including dietary history, exercise history, medication history, etc.

[0108] "Data analysis" refers to the process of using statistical methods and algorithms based on the acquired data to extract the user's health condition and the causes of problems.

[0109] "Improvement ideas" are specific suggestions or advice for addressing identified health problems or their contributing factors.

[0110] A "natural language processing engine" is an artificial intelligence technology for analyzing text data and understanding its meaning.

[0111] "Preprocessing" refers to processing that is performed before data analysis, and includes data imputation and normalization.

[0112] "User feedback" is any additional input or reaction a user gives to advice or suggestions provided by the system.

[0113] The present invention is a chatbot system that allows users to easily consult with the system about minor health problems. The chatbot system works in conjunction with multiple health management applications to collect the user's health data, identify the causes of the problems, and provide suggestions for improvement. A specific embodiment of the system is described below.

[0114] System Configuration and Operation

[0115] Receiving and Parsing User Input

[0116] A user launches the chatbot interface using a smartphone or tablet. For example, they input something like, "I haven't been feeling any better lately." The device receives this input and sends it to a server. The server then sends the received input to a natural language processing engine (e.g., Google® Cloud Natural Language API) and analyzes the text. The natural language processing engine identifies specific health issues, such as "fatigue," from the user's input.

[0117] Data linkage and acquisition

[0118] After a health problem is identified, the server, with the user's consent, connects with relevant existing health management applications (e.g., dietary management apps, exercise management apps, medication management apps). The server obtains the necessary data (dietary history, exercise history, medication history) from each application via API. To improve the accuracy of the obtained data, the device displays the data to the user and prompts them to correct any omissions or errors.

[0119] Factor analysis and generation of improvement proposals

[0120] The server uses Python's Pandas library to analyze the acquired data. It preprocesses the dataset, for example, by filling in missing data and normalizing it. Next, it analyzes the diet history to check for vitamin B deficiency, exercise history to check for excessive exercise, and medication history to check for side effects. Based on the analysis results, it generates specific improvement suggestions (for example, if vitamin B is deficient, advice such as "We suggest consuming foods rich in vitamin B").

[0121] Notifying users and getting feedback

[0122] The server notifies the user of the generated improvement suggestions. The device displays the suggestions on the chatbot interface. For example, it may say, "You are deficient in vitamin B. Eat fish, chicken, and beans, which are rich in vitamin B." The user checks the suggestions and enters additional inquiries or feedback as needed. The device sends this feedback to the server, which analyzes the received feedback and generates additional advice or corrections as needed.

[0123] Specific examples

[0124] Example 1: Dietary nutrient deficiency

[0125] 1. User: Type "I'm tired" into the chatbot.

[0126] 2. Terminal: Sends input data to the server.

[0127] 3. Server: Uses a natural language processing engine to identify "fatigue."

[0128] 4. Server: Obtains meal history data using the meal management app's API.

[0129] 5. Server: Analyze the data using the Pandas library and identify vitamin B deficiencies.

[0130] 6. Server: Produces "You are deficient in Vitamin B. We suggest consuming foods rich in Vitamin B (e.g., fish, chicken, beans)."

[0131] 7. Terminal: Show this suggestion to the user.

[0132] Example 2: Fatigue due to excessive exercise

[0133] 1. User: Type into the chatbot, "I've been feeling really tired lately."

[0134] 2. Terminal: Sends input data to the server.

[0135] 3. Server: Uses a natural language processing engine to identify "fatigue."

[0136] 4. Server: Obtains exercise history data through the running app's API.

[0137] 5. Server: Analyze the data using the Pandas library to identify hyperactivity.

[0138] 6. Server: Generate "You've been exercising too much recently. We suggest you increase your rest time and adjust your exercise accordingly."

[0139] 7. Terminal: Show this suggestion to the user.

[0140] As described above, by utilizing this system, users can eliminate the need to operate individual applications, centrally collect and analyze health data, and quickly receive appropriate advice.

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

[0142] Step 1:

[0143] User: The user launches the chatbot interface on their smartphone or tablet, for example by typing, "I've been feeling tired lately."

[0144] Input: A health-related message (e.g., "I've been feeling tired lately").

[0145] Output: The input data is displayed on the terminal device.

[0146] Step 2:

[0147] Terminal: Sends input data to the server. Specifically, the communication module in the terminal sends message data to the server as an HTTP request.

[0148] Input: A health-related message entered by the user.

[0149] Output: A message from the user is sent to the server.

[0150] Step 3:

[0151] Server: The server sends the received message to a natural language processing engine to analyze the text, for example using the Google Cloud Natural Language API.

[0152] Input: A health-related message sent by the user.

[0153] Output: The natural language processing engine returns the health issue (e.g., "feeling tired") as the analysis result.

[0154] Step 4:

[0155] Server: After a health problem is identified, the server obtains the user's consent and connects with the relevant applications to obtain the necessary data through APIs. Specifically, it issues API requests to the diet management app, exercise management app, and medication management app.

[0156] Input: Analysis results from a natural language processing engine (e.g., "fatigue").

[0157] Output: Dietary history, exercise history, and medication history data obtained from each application.

[0158] Step 5:

[0159] Terminal: If necessary, display the acquired data to the user and prompt them to correct any deficiencies or errors. Specifically, the acquired data is temporarily saved and an interface for user confirmation is displayed.

[0160] Input: Health data obtained from each application.

[0161] Output: The data displayed to the user and the modified data (if any).

[0162] Step 6:

[0163] Server: To analyze the acquired data, we use the Python Pandas library. We preprocess the dataset (implanting missing data and normalizing it) and analyze the dietary history, exercise history, and medication history.

[0164] Input: Data obtained from each application and data modified by the user.

[0165] Output: Contributing factors to the health problem (e.g., vitamin B deficiency).

[0166] Step 7:

[0167] Server: Generates specific improvement suggestions based on the analysis results. For example, if a vitamin B deficiency is identified, the server will suggest "consuming foods rich in vitamin B."

[0168] Input: Contributors to health problems.

[0169] Output: Specific improvement suggestions.

[0170] Step 8:

[0171] Server: Notifies the user of the generated improvement suggestions. Converts the improvement suggestions into a display format for notifications and sends them to the device.

[0172] Input: Generated improvement suggestions.

[0173] Output: The improvement suggestions converted into a display format.

[0174] Step 9:

[0175] Terminal: The improvement suggestions are displayed in the chatbot interface. Specifically, the improvement suggestions are displayed as chatbot messages.

[0176] Input: The improvement suggestion sent by the server.

[0177] Output: Suggested improvements that users can see on their screen.

[0178] Step 10:

[0179] User: Review the suggested improvements and enter any additional questions or feedback as needed.

[0180] Input: User feedback on the proposed improvements.

[0181] Output: User feedback.

[0182] Step 11:

[0183] Terminal: Sends user feedback to the server. The terminal sends the input data back to the server.

[0184] Input: Additional feedback from the user.

[0185] Output: Feedback sent to the server.

[0186] Step 12:

[0187] Server: Analyzes the received feedback and generates additional advice and corrections as needed, again using a natural language processing engine.

[0188] Input: User feedback.

[0189] Output: Additional advice and suggested fixes.

[0190] These are the specific processing steps of this system. At each step, various data processing and calculations are performed based on the input data, and ultimately the optimal health advice is provided to the user. The results displayed to the user are then checked and further improvements are made as necessary.

[0191] (Application example 1)

[0192] 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."

[0193] In today's busy lifestyles, many people have little time to address minor health issues. Finding appropriate solutions is difficult, especially when diet, exercise, and medication management are factors. Furthermore, there is no system that centrally manages health data and recommends meal plans appropriate for individual health conditions. Therefore, there is a need for a system that allows users to easily obtain effective improvement measures tailored to their health condition.

[0194] 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.

[0195] In this invention, the server includes means for receiving health-related messages from users, means for analyzing the messages to identify health problems of the users, means for acquiring data related to the identified health problems from other applications, means for analyzing the acquired data to identify causes of the health problems, means for generating improvement proposals based on the identified causes, means for notifying the users of the generated improvement proposals, and means for recommending appropriate meal menus based on the users' health conditions. This allows users to centrally manage their health data and easily obtain effective dietary improvement measures suited to their individual health conditions.

[0196] "User" refers to an individual who uses the System.

[0197] "Health-related message" refers to text information entered by a user to describe their health condition or any issues they may be experiencing.

[0198] "Means for identifying a health issue" refers to a method or apparatus for analyzing a received health-related message and identifying a user's specific health issue.

[0199] "Means for acquiring data" refers to a method or device for acquiring relevant data based on the identified health problem from an external application (such as a diet management app, exercise management app, or medication management app).

[0200] "Means for identifying causes" refers to a method or device for analyzing the acquired data and clarifying the causes of the user's health problem.

[0201] "Means for generating improvement suggestions" refers to a method or device that creates specific suggestions for resolving a user's health problem based on the identified factors.

[0202] "Means for notifying users" refers to methods or devices for notifying users of generated improvement proposals or recommendations.

[0203] "Means for recommending appropriate meal menus based on health status" refers to a method or device that analyzes a user's health data and, based on the results, suggests a meal plan appropriate for the user's health status.

[0204] The term "system" refers to a mechanism in which a series of components including the above-mentioned means work together.

[0205] This invention provides a system for users to solve minor health problems, linked to a food delivery application equipped with a meal menu recommendation function. The system includes a user terminal, a cloud server, and an existing health management application. Specific embodiments are described below.

[0206] Key Components of the System

[0207] 1. User Device

[0208] Smartphone: A device where the user can input health-related messages and receive feedback from the system.

[0209] 2. Cloud Server

[0210] Server: A central processing unit that analyzes messages from users and identifies health issues, as well as retrieves and analyzes data from related apps.

[0211] Natural language processing engine (e.g., Google NLP API): Used to analyze user messages and identify specific health issues.

[0212] 3. Related Applications

[0213] Meal management app: An application that records meal history data.

[0214] Exercise management app: An application that records exercise history data.

[0215] Medication management app: An application that records medication usage history data.

[0216] Food delivery app: An application that recommends healthy meal menus based on health data and delivers them to users.

[0217] System processing overview

[0218] 1. Receiving and Parsing User Input

[0219] A user types "I've been feeling a bit tired lately" into a food delivery app chatbot, and their smartphone sends this message to a cloud server.

[0220] The cloud server uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[0221] 2. Data linkage and acquisition

[0222] After a health problem is identified, the cloud server connects with the diet management app, exercise management app, and medication management app to obtain the necessary data through APIs.

[0223] The smartphone displays the acquired data to the user and prompts them to make corrections if there are any errors.

[0224] 3. Factor analysis and recommendation generation

[0225] The cloud server analyzes the acquired data and identifies the cause of the user's health problem (e.g., vitamin B deficiency).

[0226] Based on the results of the factor analysis, the cloud server generates a meal menu that takes nutritional balance into consideration.

[0227] 4. User Notification and Feedback

[0228] The cloud server sends the generated menu suggestions to the user.

[0229] The smartphone displays the suggestions to the user and accepts their ratings and feedback.

[0230] Specific examples

[0231] If a user types "I've been feeling tired lately" into a food delivery app, the system will follow this flow:

[0232] 1. Input Analysis

[0233] Cloud Server: Identifying "fatigue."

[0234] 2. Data Acquisition

[0235] Cloud server: Acquires data from a dietary management app and identifies vitamin B deficiencies.

[0236] 3. Proposal generation

[0237] Cloud server: Generates the message, "You are lacking in vitamin B. We will suggest a menu using ingredients that are rich in vitamin B."

[0238] 4. User Notices

[0239] Smartphone: Suggestions are displayed to the user.

[0240] Prompt Sentence Examples

[0241] The following prompts can be used to instruct the generative AI model to proceed:

[0242] If a user types in "I've been feeling a bit tired lately," the app will identify the health issue of "fatigue" and retrieve data from related apps. It will then identify a vitamin B deficiency and suggest a menu using ingredients rich in vitamin B.

[0243] The system will enable users to easily access fast, accurate solutions to minor health issues they experience in their daily lives.

[0244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0245] Step 1:

[0246] A user can send a health-related message to a chatbot in a food delivery app by inputting "I've been feeling a bit tired lately." The input data is in text format and is sent from the user's device to a cloud server. The input of this step is the user's message, and the output is the message sent to the cloud server.

[0247] Step 2:

[0248] The cloud server analyzes the received message using a natural language processing engine (e.g., Google NLP API). The server processes the text data and identifies specific health problems, such as "feeling tired." The input for this step is the user's message, and the output is the data on the identified health problem.

[0249] Step 3:

[0250] Based on the identified health problem, the server retrieves relevant data from the diet management app, exercise management app, and medication management app. The retrieved data includes diet history, exercise history, and medication history. Data is shared via API, and user consent is required. The input of this step is the identified health problem data, and the output is related history data.

[0251] Step 4:

[0252] The cloud server analyzes and processes the acquired historical data. It checks the intake of vitamin B in the dietary history and analyzes the exercise history to check for excessive exercise. The input of this step is the acquired historical data, and the output is the specific factors that cause health problems.

[0253] Step 5:

[0254] After the factors are identified, the cloud server generates improvement suggestions and meal menu recommendations based on the user's health condition. For example, if a user is deficient in vitamin B, it will suggest a menu using ingredients rich in vitamin B. The input of this step is the identified factors of the health problem, and the output is improvement suggestions and recommendations.

[0255] Step 6:

[0256] The cloud server notifies the user device of the generated improvement plan and meal recommendation. The notified content is displayed to the user through the chatbot interface. The input of this step is the generated improvement plan and recommendation, and the output is a notification to the user.

[0257] Step 7:

[0258] The user checks the notified improvement proposals and meal recommendations, and provides an evaluation and feedback. This feedback is sent back to the cloud server and used to improve the accuracy of the system. The input of this step is the user's feedback, and the output is the feedback sent to the cloud server.

[0259] Specific examples

[0260] If a user types "I've been feeling tired lately" into a food delivery app, here's what the system will flow:

[0261] 1. Input Reception

[0262] User device: Type "I've been feeling a bit tired lately" and send it to the cloud server.

[0263] 2. Input Analysis

[0264] Cloud server: Identifies "fatigue" using a natural language processing engine.

[0265] 3. Data Acquisition

[0266] Cloud server: Collects data from dietary management apps and identifies vitamin B deficiencies.

[0267] 4. Factor analysis

[0268] Cloud server: Data analysis identifies vitamin B deficiency and excessive exercise.

[0269] 5. Proposal generation

[0270] Cloud server: Generates a menu using ingredients rich in vitamin B, saying, "You are lacking vitamin B."

[0271] 6. User Notices

[0272] User device: Display the proposal.

[0273] 7. Get feedback

[0274] User device: Send feedback on suggested improvements.

[0275] 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.

[0276] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a dietary management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. Furthermore, by combining the present invention with an emotion engine that recognizes the user's emotions, it is possible to provide more sophisticated and user-friendly responses. An embodiment of this system is described below.

[0277] System Overview

[0278] The system consists of the following main components:

[0279] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[0280] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[0281] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[0282] Emotion engine: Combined with natural language processing, it recognizes user emotions and adjusts responses and data acquisition.

[0283] Program processing

[0284] Receiving and Parsing User Input

[0285] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[0286] Terminal: Sends received messages to the server.

[0287] Server: Uses a natural language processing engine to analyze user messages and identify specific health issues, such as "feeling tired," and an emotion engine to recognize the user's emotions in the messages.

[0288] Data linkage and acquisition

[0289] Server: Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management apps, exercise management apps, medicine notebooks) to obtain the user's latest data. For example, if the user is feeling very stressed, the server also obtains additional data related to stress reduction.

[0290] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[0291] Factor analysis and generation of improvement proposals

[0292] Server: Analyzes the acquired data (dietary history, exercise history, medication history) to identify the causes of health problems. It also performs analysis taking into account the results of the emotion engine. For example, if the user is feeling stressed, it will analyze stress-related factors as well.

[0293] Server: Generates specific improvement proposals based on the results of factor analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest consuming foods rich in vitamin B" is generated.

[0294] Notifying users and getting feedback

[0295] Server: Sends the generated improvement suggestions to the user. Based on the results of the emotion engine, the suggestion content is also adjusted. For example, if the user tends to feel depressed, the suggestion will be given more gentle and encouraging language.

[0296] Terminal: Show improvement suggestions to the user through a chatbot interface.

[0297] Users: Review the proposal and provide additional inquiries or feedback as needed.

[0298] Specific examples

[0299] Example 1: Dietary nutrient deficiency

[0300] 1. Terminal: The user types, "I feel tired."

[0301] 2. Server: Identify "fatigue" using a natural language processing engine and recognize the emotion of "fatigue" using an emotion engine.

[0302] 3. Server: Acquires food history data from the food management app.

[0303] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[0304] 5. Server: Generates an improvement suggestion such as, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[0305] 6. Terminal: Display the suggestions to the user.

[0306] Example 2: Fatigue due to excessive exercise

[0307] 1. Device: The user types, "I've been feeling really tired lately."

[0308] 2. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[0309] 3. Server: Obtains exercise history data from the running app.

[0310] 4. Server: Analyzes the data and identifies hyperactivity.

[0311] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[0312] 6. Terminal: Display the suggestions to the user.

[0313] Benefits of adding an emotion engine

[0314] The introduction of an emotion engine makes it possible to respond to users' emotional states and provide more personalized services. For example, if a user is feeling stressed, the system can provide suggestions for relaxation techniques and advice on how to deal with stress. In this way, emotion recognition can enable more accurate healthcare advice.

[0315] The processing flow will be explained below.

[0316] Step 1:

[0317] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[0318] Step 2:

[0319] Terminal: Sends the entered message to the server.

[0320] Step 3:

[0321] Server: The received message is passed to a natural language processing engine for analysis. Specifically, the context is analyzed to identify the user's health issue (in this case, "fatigue"). The emotion engine is also used to identify the user's emotion from the message. For example, if the user types "tired," the emotion engine will identify the emotion as "fatigue."

[0322] Step 4:

[0323] Server: Taking into account the emotion recognition results from the emotion engine, the server sends an API request to obtain data related to the user's health issues from related applications (diet management app, exercise management app, medicine record). For example, if the user is feeling "fatigue" or "stressed," the server obtains data related to stress reduction in addition to their diet history and exercise history.

[0324] Step 5:

[0325] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[0326] Step 6:

[0327] Server: Analyzes the acquired data and identifies specific factors that contribute to health problems. For example:

[0328] Dietary data: Identify nutrient deficiencies and excesses.

[0329] Exercise data: Identify over- or under-exercise.

[0330] Drug data: Identify potential health problems caused by medication side effects.

[0331] It also takes into account the results of the emotion engine to analyze factors related to stress and emotional ups and downs.

[0332] Step 7:

[0333] Server: Generates specific improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is found, specific advice such as "We suggest consuming foods rich in vitamin B" is generated. Furthermore, depending on the results of the emotion engine, the suggestion content is adjusted to suit the user's emotions. For example, if the user is feeling very stressed, advice on relaxation techniques and mental care will be included.

[0334] Step 8:

[0335] Server: Sends the generated improvement suggestions to the user.

[0336] Step 9:

[0337] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[0338] Step 10:

[0339] Users: Review the proposal and provide additional inquiries or feedback as needed.

[0340] Specific examples

[0341] Example 1: Dietary nutrient deficiency

[0342] 1. Terminal: The user types, "I feel tired."

[0343] 2. Terminal: Sends the entered message to the server.

[0344] 3. Server: Identify "fatigue" using a natural language processing engine and recognize "fatigue emotion" using an emotion engine.

[0345] 4. Server: Obtains food history data from the food management app.

[0346] 5. Device: Displays the acquired meal data to the user and allows them to correct any errors.

[0347] 6. Server: Analyze the data and identify vitamin B deficiencies.

[0348] 7. Server: Create a specific improvement suggestion, such as "You are lacking in vitamin B. We suggest that you eat foods that are rich in vitamin B (e.g., fish, chicken, beans)." Because the user's emotion is "fatigue," include gentle, encouraging words.

[0349] 8. Server: Sends improvement suggestions to the user.

[0350] 9. Terminal: Display the suggestions to the user.

[0351] 10. User: Review the proposal and make any further enquiries as necessary.

[0352] Example 2: Fatigue due to excessive exercise

[0353] 1. Device: The user types, "I've been feeling really tired lately."

[0354] 2. Terminal: Sends the entered message to the server.

[0355] 3. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[0356] 4. Server: Obtains exercise history data from the running app.

[0357] 5. Device: Displays the acquired exercise data to the user and allows them to correct any errors.

[0358] 6. Server: Analyzes data and identifies hyperactivity.

[0359] 7. Server: Create a specific improvement suggestion, such as, "It seems you've been exercising too much recently. We suggest that you increase your rest time and adjust your exercise appropriately." Because the user's emotion is "irritation," include gentle words encouraging relaxation.

[0360] 8. Server: Sends improvement suggestions to the user.

[0361] 9. Terminal: Display the suggestions to the user.

[0362] 10. User: Review the proposal and make any further enquiries as necessary.

[0363] The addition of an emotion engine allows responses to be made that take into account the user's emotional state, enabling more precise and user-friendly responses.

[0364] Example 2

[0365] 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."

[0366] In modern society, users face a wide range of health problems, requiring prompt and accurate responses. However, conventional systems do not adequately take into account the user's emotional state, making it difficult to provide personalized advice. Furthermore, when linking data from multiple health management applications, the integration and analysis of that data is cumbersome, making it difficult for users to use.

[0367] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedy based on the identified cause, means for notifying the user of the generated remedy, and means for recognizing the user's emotions and adjusting the response content and data acquisition. This enables a more sophisticated and user-friendly response that takes the user's emotional state into consideration.

[0368] "Health-related messages from users" are text data of health-related questions or inquiries entered by users through the chatbot interface.

[0369] "Means for analyzing messages to identify a user's health issue" refers to the process of using a natural language processing engine to identify the type and specific content of a health issue from a received text message.

[0370] "Means for obtaining data related to the identified health problem from other applications" refers to the process of obtaining data from the diet management application, exercise management application, and medication management application to collect information related to the user's health problem.

[0371] "Means for analyzing acquired data to identify the causes of health problems" refers to the process of analyzing data to identify the root cause of a user's health problem based on the collected data.

[0372] "Means for generating improvement proposals based on identified factors" refers to the process of generating specific measures and advice for identified causes.

[0373] "Means of notifying users of generated improvement suggestions" refers to the process of communicating the generated advice and measures to users through the chatbot interface.

[0374] "Means for recognizing user emotions and adjusting response content and data acquisition" refers to the process of identifying emotions from a user's text message and adjusting appropriate responses and data acquisition based on those emotions.

[0375] This invention is a chatbot system that allows users to easily consult about minor health issues. This system works in conjunction with the user's various health management applications (diet management app, exercise management app, medication management app) to collect and analyze the user's health status as data. Furthermore, by combining it with an emotion engine, it responds according to the user's emotions. The following describes in detail the modes for implementing the present invention.

[0376] System configuration

[0377] The system consists of the following main components:

[0378] User device: A device where the user inputs health issues and receives feedback from the system (e.g., smartphone, tablet).

[0379] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analysis results and improvement suggestions.

[0380] Related applications: Existing applications that record various health-related data, such as diet management apps, exercise management apps, and medication management apps.

[0381] Emotion engine: Combined with natural language processing, this engine recognizes user emotions and adjusts response content and data acquisition.

[0382] Processing flow

[0383] 1. Receiving and Parsing User Input

[0384] Using the chatbot interface, users can input content such as "I've been feeling tired lately," and the device will then send this message to the server.

[0385] The server analyzes the received message using a natural language processing engine (e.g., spaCy or BERT) to identify health issues such as "fatigue," and then uses an emotion engine to recognize the user's emotion (e.g., "tired") in the message.

[0386] 2. Data linkage and acquisition

[0387] Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management app, exercise management app, medication management app) to obtain the user's latest data.

[0388] The terminal displays the acquired data to the user, and if there are any errors, the user can correct them.

[0389] 3. Factor analysis and generation of improvement proposals

[0390] The server analyzes the acquired data and identifies the cause of the health problem. For example, if the cause is a vitamin B deficiency, it will identify it as "vitamin B deficiency."

[0391] The server generates specific improvement suggestions based on the identified factors, such as "You are lacking in vitamin B. We suggest that you consume foods rich in vitamin B."

[0392] 4. Notifying users and getting feedback

[0393] The server sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine, for example, choosing words that are kind and encouraging if the user is feeling down.

[0394] The device will display suggested improvements to the user, allowing the user to provide additional inquiries or feedback.

[0395] Specific examples

[0396] Example 1: Dietary nutrient deficiency

[0397] 1. The user types, "I feel tired."

[0398] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "fatigue."

[0399] 3. The server retrieves the meal history data from the meal management app.

[0400] 4. The server analyzes the data and identifies vitamin B deficiencies.

[0401] 5. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[0402] 6. The device displays the suggestions to the user.

[0403] Example 2: Fatigue due to excessive exercise

[0404] 1. The user types, "I've been feeling really tired lately."

[0405] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "irritation."

[0406] 3. The server obtains exercise history data from the exercise management app.

[0407] 4. The server analyzes the data and identifies excessive exercise.

[0408] 5. The server generates an improvement suggestion saying, "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[0409] 6. The device displays the suggestions to the user.

[0410] As described above, this invention is a system that quickly and accurately analyzes a user's health problems and provides specific improvement proposals based on data. By using an emotion engine in combination, it realizes customized responses according to the user's emotional state.

[0411] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0412] Step 1:

[0413] User: Enters a health-related message into the chatbot interface. For example, "I've been feeling really tired lately."

[0414] Input: User's text message

[0415] Output: Text data sent to the terminal

[0416] Specific actions: The user enters text into the chatbot interface on their smartphone and presses the send button.

[0417] Step 2:

[0418] Terminal: Sends received messages to the server.

[0419] Input: Text data entered by the user

[0420] Output: Text data sent to the server

[0421] Specific operation: Text data is sent to the server via an HTTP request via the terminal's network module.

[0422] Step 3:

[0423] Server: Passes the received message to the natural language processing engine for analysis.

[0424] Input: Text data sent from the terminal

[0425] Output: Health issue identification results and emotion recognition results

[0426] What it does: It uses an NLP engine built in Python (e.g., spaCy or BERT) to tokenize text messages and identify health issues and sentiment.

[0427] Step 4:

[0428] Server: Uses an emotion engine to recognize user emotions from messages.

[0429] Input: Analysis results of the natural language processing engine

[0430] Output: User emotion label (e.g. "tired")

[0431] What it does: Apply a pre-trained emotion recognition model (e.g., Hugging Face emotion analysis model) to extract emotion labels from text.

[0432] Step 5:

[0433] Server: Based on the identified health issues and emotion recognition results, it sends API requests to relevant applications to retrieve the latest user data.

[0434] Input: Health issue identification results and emotion recognition results

[0435] Output: Food data, exercise data, medication data (JSON format)

[0436] Specific behavior: Sends an HTTP GET request to a RESTful API endpoint to retrieve data in JSON format from the associated application.

[0437] Step 6:

[0438] Terminal: The data sent from the server is displayed to the user. If there are any errors, the user can correct them.

[0439] Input: Latest data retrieved from the server

[0440] Output: Data confirmed and corrected by the user

[0441] Specific behavior: The retrieved data is displayed on the device UI, and the user can edit it by pressing the edit button.

[0442] Step 7:

[0443] Server: Analyzes the acquired data and identifies the causes of health problems.

[0444] Input: dietary data, exercise data, medication data

[0445] Output: Cause of health problem (e.g. "Vitamin B deficiency")

[0446] Specific operation: Reads food history, exercise history, and medication history from an SQL database and cross-references and analyzes the data using Python data analysis libraries (e.g., pandas).

[0447] Step 8:

[0448] Server: Generates specific improvement proposals based on the identified factors.

[0449] Input: Contributors to health problems

[0450] Output: Suggested improvement (e.g., "I suggest you eat foods rich in vitamin B.")

[0451] What it does: Uses rule-based engines and machine learning models to generate appropriate advice from analysis results.

[0452] Step 9:

[0453] Server: Sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine.

[0454] Input: Improvement suggestions and user sentiment labels

[0455] Output: Tailored recommendations for improvement (e.g., "Try eating these foods to feel better")

[0456] What it does: Generates textual suggestions for improvement and adjusts them based on the user's emotional state.

[0457] Step 10:

[0458] Terminal: The improvement suggestions sent from the server are displayed to the user through the chatbot interface.

[0459] Input: Improvement suggestions sent from the server

[0460] Output: Improvement suggestions for user review

[0461] Specific behavior: Display the text of the improvement suggestions in the chatbot UI.

[0462] Step 11:

[0463] User: Review the proposal and enter any feedback or follow-up inquiries.

[0464] Input: Feedback on the proposal or follow-up questions

[0465] Output: Further inquiries and feedback

[0466] What happens: Enter your feedback into the chatbot interface and hit submit. For example, enter something like "This suggestion was very helpful" or "I'd like more information."

[0467] (Application example 2)

[0468] 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."

[0469] In today's busy society, proper diet, exercise, and medication management are essential for users to maintain their health in their busy daily lives. However, it is difficult to manage this data individually and investigate and improve one's own health problems in between busy schedules. Furthermore, there is a lack of systems that provide appropriate health advice and meal plans that take into account the user's emotional state. As a result, users may make incorrect health management decisions, which could lead to further health problems. To solve these problems, there is a need for a system that allows users to easily understand their health status and receive personalized improvement suggestions that take their emotional state into account.

[0470] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedial action based on the identified cause, means for notifying the user of the generated remedial action, means for recognizing the user's emotional state, and means for adjusting the proposed action based on the recognized emotional state. This allows users to receive accurate health advice and meal plans based on centralized health management data, even in the midst of a busy lifestyle. Furthermore, personalized responses that take emotional state into account are expected to increase user satisfaction and improve their health.

[0471] A "health-related message from a user" is a text message in which a user enters information about or seeks advice regarding their health condition.

[0472] "Means for analyzing messages and identifying user health problems" refers to a method or device for analyzing received messages using natural language processing technology, etc., and identifying health problems reported by users from among the messages.

[0473] The "means for obtaining data related to health issues from other applications" refers to an interface or protocol for collecting health-related data from health management applications, etc., that the user is using.

[0474] "Means for analyzing acquired data to identify the causes of health problems" refers to a method or device that analyzes collected data using techniques such as statistical analysis and machine learning to identify the root cause of a user's health problem.

[0475] The "means for generating improvement proposals based on identified factors" refers to a method or device for generating specific proposals for improving the user's health condition based on the analysis results.

[0476] The "means for notifying the user of the generated improvement proposal" refers to a notification function or interface for informing the user of the generated improvement proposal.

[0477] "Means for recognizing a user's emotional state" refers to technology or devices for analyzing and recognizing emotions from messages or other data entered by a user.

[0478] "Means for adjusting suggestions based on a recognized emotional state" refers to a method or device for adjusting the suggestions and how they are presented depending on the user's emotional state.

[0479] The "means for acquiring dietary data from a health management application" is an interface or protocol for collecting dietary data from a diet management application used by a user.

[0480] The "means for acquiring exercise data from an exercise management application" refers to an interface or protocol for collecting exercise-related data from the exercise management application used by the user.

[0481] A "means for obtaining medication data from a medication management application" is an interface or protocol for collecting data about medication use from the medication management application being used by the user.

[0482] A "service that provides food and meals based on a meal plan" is a service that delivers appropriate food and meals to a user based on a generated meal plan.

[0483] A "natural language processing engine" is software or technology used to perform semantic analysis and information extraction on text data entered by a user.

[0484] An "emotion engine" is software or technology for analyzing and recognizing a user's emotions.

[0485] This invention is a chatbot system that allows users to easily consult about their health condition. It works in conjunction with multiple health management-related applications to collect and analyze data and provide improvement suggestions that take emotional state into consideration.

[0486] System Overview

[0487] The system consists of the following main components:

[0488] User device: The device (smartphone, tablet, etc.) where the user enters health-related messages and receives feedback from the system.

[0489] Server system: A central processing unit that analyzes user input, collects relevant data, and generates analytical results. It uses natural language processing engines such as Google Cloud NLP and emotion engines such as Affectiva SDK.

[0490] Related applications: Existing applications that record health-related data (diet management apps, exercise management apps, medication management apps).

[0491] Delivery services: Services that deliver food or meals based on suggested meal plans (e.g., meal delivery service APIs).

[0492] What the program does

[0493] Receiving and Parsing User Input

[0494] Users input their health concerns using the chatbot interface. The device then sends the received message to the server, which uses Google Cloud NLP to analyze the user's message and identify the health issue being raised. The server also uses the Affectiva SDK to recognize the user's emotional state.

[0495] Data linkage and acquisition

[0496] The server retrieves data from the user's diet management app, exercise management app, and medication management app via API, and also retrieves additional data based on the results of the emotion engine.

[0497] Factor analysis and generation of improvement proposals

[0498] Using the acquired data, the server performs various statistical analyses and machine learning to identify the causes of health problems. Based on the identified causes, it generates specific improvement suggestions, such as vitamin B deficiency. It also takes into account the patient's emotional state and selects positive language.

[0499] User notification and delivery

[0500] The server generates an appropriate message to notify the user of the proposed improvements, and sends it to the device. The user can then confirm the suggestions and place an order with a delivery service if necessary.

[0501] Specific examples

[0502] 1. The user types, "I've been feeling tired lately."

[0503] 2. The server identifies "fatigue" using Google Cloud NLP and recognizes "fatigue" using the Affectiva SDK.

[0504] 3. The server retrieves the diet history data from the diet management app and analyzes vitamin B deficiency.

[0505] 4. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[0506] 5. Display the suggestions on the user's device and deliver the appropriate food using the relevant delivery service.

[0507] Prompt Sentence Examples

[0508] Example user input: "I've been feeling really tired lately. What should I eat?"

[0509] Example system output: "You may be lacking in vitamin B. Try eating foods rich in vitamin B, such as liver, fish, and eggs."

[0510] In this way, the system of the present invention comprehensively manages the user's health condition, provides appropriate health advice that also takes into account the user's emotional state, and delivers food and meals based on that advice, allowing users to efficiently improve their health even in their busy daily lives.

[0511] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0512] Step 1:

[0513] Receive health-related messages from users.

[0514] Input: A user uses the chatbot interface on their device to type a message such as, "I've been feeling really tired lately."

[0515] Specific operation: The device receives user input and sends the message to the server.

[0516] Output: The server receives the user's message.

[0517] Step 2:

[0518] Analyze messages and identify health issues.

[0519] Input: The user's message received in step 1.

[0520] How it works: The server uses Google Cloud NLP to analyze the message and identify health issues such as "fatigue."

[0521] Output: Identified health problem (e.g., fatigue).

[0522] Step 3:

[0523] Recognize the user's emotional state.

[0524] Input: The user's message received in step 1.

[0525] Specific operation: The server uses the Affectiva SDK to recognize the emotional state from messages, user facial expressions, etc.

[0526] Output: Perceived emotional state (e.g., "tired").

[0527] Step 4:

[0528] Obtaining data related to health issues from other applications.

[0529] Input: Identified health problems (Step 2) and perceived emotional states (Step 3).

[0530] Specific operation: The server calls APIs for dietary management apps, exercise management apps, medicine records, etc. to collect the latest health data.

[0531] Output: Acquired health data (dietary history, exercise history, medication history, etc.).

[0532] Step 5:

[0533] The acquired data is analyzed to identify the causes of health problems.

[0534] Input: Acquired health data (Step 4).

[0535] What it does: The server analyzes the data using statistical analysis and machine learning to identify the causes of health problems (e.g., vitamin B deficiency).

[0536] Output: Identified contributing factors to health problems.

[0537] Step 6:

[0538] Generate improvement recommendations based on the identified factors.

[0539] Input: Identified contributing factors to the health problem (Step 5).

[0540] Specific operation: The server uses the generated AI model to generate specific suggestions (e.g., consuming foods rich in vitamin B).

[0541] Output: Generated improvement suggestions.

[0542] Step 7:

[0543] Notify the user of the generated improvement suggestions.

[0544] Input: Generated improvement proposals (Step 6).

[0545] Specific operation: The server adjusts the suggestion content based on the user's emotional state, creates a notification message, and sends it to the device.

[0546] Output: The improvement suggestions sent to the user's device.

[0547] Step 8:

[0548] The user delivers based on the suggestions.

[0549] Input: The improvement proposal notified to the user's device (Step 7).

[0550] Specific behavior: The user confirms the notification message and uses the meal delivery service based on the suggested meal plan.

[0551] Output: The user's order is sent to the delivery service and the food or meal is delivered.

[0552] 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.

[0553] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0554] 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.

[0555] [Second embodiment]

[0556] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0557] 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.

[0558] 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).

[0559] 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.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] 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."

[0568] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a diet management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. The following describes an embodiment of this system.

[0569] System Overview

[0570] The system consists of the following main components:

[0571] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[0572] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[0573] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[0574] Program processing

[0575] Receiving and Parsing User Input

[0576] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[0577] Terminal: Sends received messages to the server.

[0578] Server: Uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[0579] Data linkage and acquisition

[0580] Server: After a health problem is identified, the server, with the user's consent, connects with relevant applications (diet management app, exercise management app, medication management app) and obtains the necessary data via API.

[0581] Terminal: Display the acquired data to the user and ask them to correct any errors.

[0582] Factor analysis and generation of improvement proposals

[0583] Server: Analyzes the acquired data (dietary history, exercise history, medication history) and clarifies the causes of identified health problems (e.g., fatigue).

[0584] Server: Generates specific improvement proposals based on the results of the factor analysis. For example, if a lack of vitamin B is the cause, the server generates advice such as "We suggest that you consume foods rich in vitamin B."

[0585] Notifying users and getting feedback

[0586] Server: Sends the generated improvement suggestions to the user.

[0587] On the device: Show the user suggested improvements and accept additional inquiries and feedback as needed.

[0588] Specific examples

[0589] Example 1: Dietary nutrient deficiency

[0590] 1. Terminal: The user types, "I feel tired."

[0591] 2. Server: Identify "fatigue" using a natural language processing engine.

[0592] 3. Server: Acquires food history data from the food management app.

[0593] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[0594] 5. Server: Generates an improvement suggestion: "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B (e.g., fish, chicken, beans)."

[0595] 6. Terminal: Display the suggestions to the user.

[0596] Example 2: Fatigue due to excessive exercise

[0597] 1. Device: The user types, "I've been feeling really tired lately."

[0598] 2. Server: Identify "fatigue" using a natural language processing engine.

[0599] 3. Server: Obtains exercise history data from the running app.

[0600] 4. Server: Analyzes the data and identifies hyperactivity.

[0601] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[0602] 6. Terminal: Display the suggestions to the user.

[0603] Through this system, users can receive prompt and appropriate treatment for even mild illnesses that do not require a visit to the hospital, and by linking and analyzing data, they can receive more accurate and personalized health advice.

[0604] The processing flow will be explained below.

[0605] Step 1:

[0606] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[0607] Step 2:

[0608] Terminal: Sends the entered message to the server.

[0609] Step 3:

[0610] Server: Passes the received message to a natural language processing engine for analysis. Specifically, it analyzes the context and identifies the user's health problem (in this case, "fatigue").

[0611] Step 4:

[0612] Server: Based on the identified health issue, it sends API requests to relevant applications (diet management app, exercise management app, medicine record book) to obtain the user's latest data.

[0613] Step 5:

[0614] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[0615] Step 6:

[0616] Server: Analyzes the acquired data and identifies the causes of health problems. Specifically, it analyzes the following data individually:

[0617] Dietary data: Identify nutrient deficiencies and excesses.

[0618] Exercise data: Identify over- or under-exercise.

[0619] Drug data: Identify potential health issues caused by medication side effects.

[0620] Step 7:

[0621] Server: Generates improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest eating foods rich in vitamin B" is generated.

[0622] Step 8:

[0623] Server: Sends the generated improvement suggestions to the user.

[0624] Step 9:

[0625] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[0626] Step 10:

[0627] Users: Review the proposal and provide additional inquiries or feedback as needed.

[0628] Example 1

[0629] 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."

[0630] In today's modern living environment, it is important to detect minor health problems early and take appropriate measures. However, conventional methods require users to operate health management applications individually, and collect and analyze data, which is time-consuming. In addition, integrating and analyzing data from each application is technically difficult, and some factors may be overlooked. This makes it difficult for users to quickly receive appropriate health advice.

[0631] 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.

[0632] In this invention, the server includes means for receiving health-related messages from a user, means for analyzing the messages to identify a health problem of the user, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating an improvement plan based on the identified cause, means for notifying the user of the generated improvement plan, means for displaying the acquired data to the user to encourage correction, and means for receiving user feedback based on the generated improvement plan. This eliminates the need for users to operate individual applications, and enables the centralized collection and analysis of health data to quickly receive appropriate advice.

[0633] "Health-related messages" are text data in which users write about their health status and physical condition.

[0634] A "health issue" is a specific health problem or symptom that a user is experiencing.

[0635] An "application" is a software program that users use on their smartphones or tablets to manage their health and record data.

[0636] "Data" refers to records of health information about the user, including dietary history, exercise history, medication history, etc.

[0637] "Data analysis" refers to the process of using statistical methods and algorithms based on the acquired data to extract the user's health condition and the causes of problems.

[0638] "Improvement ideas" are specific suggestions or advice for addressing identified health problems or their contributing factors.

[0639] A "natural language processing engine" is an artificial intelligence technology for analyzing text data and understanding its meaning.

[0640] "Preprocessing" refers to processing that is performed before data analysis, and includes data imputation and normalization.

[0641] "User feedback" is any additional input or reaction a user gives to advice or suggestions provided by the system.

[0642] The present invention is a chatbot system that allows users to easily consult with the system about minor health problems. The chatbot system works in conjunction with multiple health management applications to collect the user's health data, identify the causes of the problems, and provide suggestions for improvement. A specific embodiment of the system is described below.

[0643] System Configuration and Operation

[0644] Receiving and Parsing User Input

[0645] A user launches the chatbot interface using a smartphone or tablet. For example, they might input something like, "I haven't been feeling any better lately." The device receives this input and sends it to a server. The server then sends the received input to a natural language processing engine (e.g., Google Cloud Natural Language API) and analyzes the text. The natural language processing engine then identifies specific health issues, such as "feeling tired," from the user's input.

[0646] Data linkage and acquisition

[0647] After a health problem is identified, the server, with the user's consent, connects with relevant existing health management applications (e.g., dietary management apps, exercise management apps, medication management apps). The server obtains the necessary data (dietary history, exercise history, medication history) from each application via API. To improve the accuracy of the obtained data, the device displays the data to the user and prompts them to correct any omissions or errors.

[0648] Factor analysis and generation of improvement proposals

[0649] The server uses Python's Pandas library to analyze the acquired data. It preprocesses the dataset, for example, by filling in missing data and normalizing it. Next, it analyzes the diet history to check for vitamin B deficiency, exercise history to check for excessive exercise, and medication history to check for side effects. Based on the analysis results, it generates specific improvement suggestions (for example, if vitamin B is deficient, advice such as "We suggest consuming foods rich in vitamin B").

[0650] Notifying users and getting feedback

[0651] The server notifies the user of the generated improvement suggestions. The device displays the suggestions on the chatbot interface. For example, it may say, "You are deficient in vitamin B. Eat fish, chicken, and beans, which are rich in vitamin B." The user checks the suggestions and enters additional inquiries or feedback as needed. The device sends this feedback to the server, which analyzes the received feedback and generates additional advice or corrections as needed.

[0652] Specific examples

[0653] Example 1: Dietary nutrient deficiency

[0654] 1. User: Type "I'm tired" into the chatbot.

[0655] 2. Terminal: Sends input data to the server.

[0656] 3. Server: Uses a natural language processing engine to identify "fatigue."

[0657] 4. Server: Obtains meal history data using the meal management app's API.

[0658] 5. Server: Analyze the data using the Pandas library and identify vitamin B deficiencies.

[0659] 6. Server: Produces "You are deficient in Vitamin B. We suggest consuming foods rich in Vitamin B (e.g., fish, chicken, beans)."

[0660] 7. Terminal: Show this suggestion to the user.

[0661] Example 2: Fatigue due to excessive exercise

[0662] 1. User: Type into the chatbot, "I've been feeling really tired lately."

[0663] 2. Terminal: Sends input data to the server.

[0664] 3. Server: Uses a natural language processing engine to identify "fatigue."

[0665] 4. Server: Obtains exercise history data through the running app's API.

[0666] 5. Server: Analyze the data using the Pandas library to identify hyperactivity.

[0667] 6. Server: Generate "You've been exercising too much recently. We suggest you increase your rest time and adjust your exercise accordingly."

[0668] 7. Terminal: Show this suggestion to the user.

[0669] As described above, by utilizing this system, users can eliminate the need to operate individual applications, centrally collect and analyze health data, and quickly receive appropriate advice.

[0670] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0671] Step 1:

[0672] User: The user launches the chatbot interface on their smartphone or tablet, for example by typing, "I've been feeling tired lately."

[0673] Input: A health-related message (e.g., "I've been feeling tired lately").

[0674] Output: The input data is displayed on the terminal device.

[0675] Step 2:

[0676] Terminal: Sends input data to the server. Specifically, the communication module in the terminal sends message data to the server as an HTTP request.

[0677] Input: A health-related message entered by the user.

[0678] Output: A message from the user is sent to the server.

[0679] Step 3:

[0680] Server: The server sends the received message to a natural language processing engine to analyze the text, for example using the Google Cloud Natural Language API.

[0681] Input: A health-related message sent by the user.

[0682] Output: The natural language processing engine returns the health issue (e.g., "feeling tired") as the analysis result.

[0683] Step 4:

[0684] Server: After a health problem is identified, the server obtains the user's consent and connects with the relevant applications to obtain the necessary data through APIs. Specifically, it issues API requests to the diet management app, exercise management app, and medication management app.

[0685] Input: Analysis results from a natural language processing engine (e.g., "fatigue").

[0686] Output: Dietary history, exercise history, and medication history data obtained from each application.

[0687] Step 5:

[0688] Terminal: If necessary, display the acquired data to the user and prompt them to correct any deficiencies or errors. Specifically, the acquired data is temporarily saved and an interface for user confirmation is displayed.

[0689] Input: Health data obtained from each application.

[0690] Output: The data displayed to the user and the modified data (if any).

[0691] Step 6:

[0692] Server: To analyze the acquired data, we use the Python Pandas library. We preprocess the dataset (implanting missing data and normalizing it) and analyze the dietary history, exercise history, and medication history.

[0693] Input: Data obtained from each application and data modified by the user.

[0694] Output: Contributing factors to the health problem (e.g., vitamin B deficiency).

[0695] Step 7:

[0696] Server: Generates specific improvement suggestions based on the analysis results. For example, if a vitamin B deficiency is identified, the server will suggest "consuming foods rich in vitamin B."

[0697] Input: Contributors to health problems.

[0698] Output: Specific improvement suggestions.

[0699] Step 8:

[0700] Server: Notifies the user of the generated improvement suggestions. Converts the improvement suggestions into a display format for notifications and sends them to the device.

[0701] Input: Generated improvement suggestions.

[0702] Output: The improvement suggestions converted into a display format.

[0703] Step 9:

[0704] Terminal: The improvement suggestions are displayed in the chatbot interface. Specifically, the improvement suggestions are displayed as chatbot messages.

[0705] Input: The improvement suggestion sent by the server.

[0706] Output: Suggested improvements that users can see on their screen.

[0707] Step 10:

[0708] User: Review the suggested improvements and enter any additional questions or feedback as needed.

[0709] Input: User feedback on the proposed improvements.

[0710] Output: User feedback.

[0711] Step 11:

[0712] Terminal: Sends user feedback to the server. The terminal sends the input data back to the server.

[0713] Input: Additional feedback from the user.

[0714] Output: Feedback sent to the server.

[0715] Step 12:

[0716] Server: Analyzes the received feedback and generates additional advice and corrections as needed, again using a natural language processing engine.

[0717] Input: User feedback.

[0718] Output: Additional advice and suggested fixes.

[0719] These are the specific processing steps of this system. At each step, various data processing and calculations are performed based on the input data, and ultimately the optimal health advice is provided to the user. The results displayed to the user are then checked and further improvements are made as necessary.

[0720] (Application example 1)

[0721] 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."

[0722] In today's busy lifestyles, many people have little time to address minor health issues. Finding appropriate solutions is difficult, especially when diet, exercise, and medication management are factors. Furthermore, there is no system that centrally manages health data and recommends meal plans appropriate for individual health conditions. Therefore, there is a need for a system that allows users to easily obtain effective improvement measures tailored to their health condition.

[0723] 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.

[0724] In this invention, the server includes means for receiving health-related messages from users, means for analyzing the messages to identify health problems of the users, means for acquiring data related to the identified health problems from other applications, means for analyzing the acquired data to identify causes of the health problems, means for generating improvement proposals based on the identified causes, means for notifying the users of the generated improvement proposals, and means for recommending appropriate meal menus based on the users' health conditions. This allows users to centrally manage their health data and easily obtain effective dietary improvement measures suited to their individual health conditions.

[0725] "User" refers to an individual who uses the System.

[0726] "Health-related message" refers to text information entered by a user to describe their health condition or any issues they may be experiencing.

[0727] "Means for identifying a health issue" refers to a method or apparatus for analyzing a received health-related message and identifying a user's specific health issue.

[0728] "Means for acquiring data" refers to a method or device for acquiring relevant data based on the identified health problem from an external application (such as a diet management app, exercise management app, or medication management app).

[0729] "Means for identifying causes" refers to a method or device for analyzing the acquired data and clarifying the causes of the user's health problem.

[0730] "Means for generating improvement suggestions" refers to a method or device that creates specific suggestions for resolving a user's health problem based on the identified factors.

[0731] "Means for notifying users" refers to methods or devices for notifying users of generated improvement proposals or recommendations.

[0732] "Means for recommending appropriate meal menus based on health status" refers to a method or device that analyzes a user's health data and, based on the results, suggests a meal plan appropriate for the user's health status.

[0733] The term "system" refers to a mechanism in which a series of components including the above-mentioned means work together.

[0734] This invention provides a system for users to solve minor health problems, linked to a food delivery application equipped with a meal menu recommendation function. The system includes a user terminal, a cloud server, and an existing health management application. Specific embodiments are described below.

[0735] Key Components of the System

[0736] 1. User Device

[0737] Smartphone: A device where the user can input health-related messages and receive feedback from the system.

[0738] 2. Cloud Server

[0739] Server: A central processing unit that analyzes messages from users and identifies health issues, as well as retrieves and analyzes data from related apps.

[0740] Natural language processing engine (e.g., Google NLP API): Used to analyze user messages and identify specific health issues.

[0741] 3. Related Applications

[0742] Meal management app: An application that records meal history data.

[0743] Exercise management app: An application that records exercise history data.

[0744] Medication management app: An application that records medication usage history data.

[0745] Food delivery app: An application that recommends healthy meal menus based on health data and delivers them to users.

[0746] System processing overview

[0747] 1. Receiving and Parsing User Input

[0748] A user types "I've been feeling a bit tired lately" into a food delivery app chatbot, and their smartphone sends this message to a cloud server.

[0749] The cloud server uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[0750] 2. Data linkage and acquisition

[0751] After a health problem is identified, the cloud server connects with the diet management app, exercise management app, and medication management app to obtain the necessary data through APIs.

[0752] The smartphone displays the acquired data to the user and prompts them to make corrections if there are any errors.

[0753] 3. Factor analysis and recommendation generation

[0754] The cloud server analyzes the acquired data and identifies the cause of the user's health problem (e.g., vitamin B deficiency).

[0755] Based on the results of the factor analysis, the cloud server generates a meal menu that takes nutritional balance into consideration.

[0756] 4. User Notification and Feedback

[0757] The cloud server sends the generated menu suggestions to the user.

[0758] The smartphone displays the suggestions to the user and accepts their ratings and feedback.

[0759] Specific examples

[0760] If a user types "I've been feeling tired lately" into a food delivery app, the system will follow this flow:

[0761] 1. Input Analysis

[0762] Cloud Server: Identifying "fatigue."

[0763] 2. Data Acquisition

[0764] Cloud server: Acquires data from a dietary management app and identifies vitamin B deficiencies.

[0765] 3. Proposal generation

[0766] Cloud server: Generates the message, "You are lacking in vitamin B. We will suggest a menu using ingredients that are rich in vitamin B."

[0767] 4. User Notices

[0768] Smartphone: Suggestions are displayed to the user.

[0769] Prompt Sentence Examples

[0770] The following prompts can be used to instruct the generative AI model to proceed:

[0771] If a user types in "I've been feeling a bit tired lately," the app will identify the health issue of "fatigue" and retrieve data from related apps. It will then identify a vitamin B deficiency and suggest a menu using ingredients rich in vitamin B.

[0772] The system will enable users to easily access fast, accurate solutions to minor health issues they experience in their daily lives.

[0773] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0774] Step 1:

[0775] A user can send a health-related message to a chatbot in a food delivery app by inputting "I've been feeling a bit tired lately." The input data is in text format and is sent from the user's device to a cloud server. The input of this step is the user's message, and the output is the message sent to the cloud server.

[0776] Step 2:

[0777] The cloud server analyzes the received message using a natural language processing engine (e.g., Google NLP API). The server processes the text data and identifies specific health problems, such as "feeling tired." The input for this step is the user's message, and the output is the data on the identified health problem.

[0778] Step 3:

[0779] Based on the identified health problem, the server retrieves relevant data from the diet management app, exercise management app, and medication management app. The retrieved data includes diet history, exercise history, and medication history. Data is shared via API, and user consent is required. The input of this step is the identified health problem data, and the output is related history data.

[0780] Step 4:

[0781] The cloud server analyzes and processes the acquired historical data. It checks the intake of vitamin B in the dietary history and analyzes the exercise history to check for excessive exercise. The input of this step is the acquired historical data, and the output is the specific factors that cause health problems.

[0782] Step 5:

[0783] After the factors are identified, the cloud server generates improvement suggestions and meal menu recommendations based on the user's health condition. For example, if a user is deficient in vitamin B, it will suggest a menu using ingredients rich in vitamin B. The input of this step is the identified factors of the health problem, and the output is improvement suggestions and recommendations.

[0784] Step 6:

[0785] The cloud server notifies the user device of the generated improvement plan and meal recommendation. The notified content is displayed to the user through the chatbot interface. The input of this step is the generated improvement plan and recommendation, and the output is a notification to the user.

[0786] Step 7:

[0787] The user checks the notified improvement proposals and meal recommendations, and provides an evaluation and feedback. This feedback is sent back to the cloud server and used to improve the accuracy of the system. The input of this step is the user's feedback, and the output is the feedback sent to the cloud server.

[0788] Specific examples

[0789] If a user types "I've been feeling tired lately" into a food delivery app, here's what the system will flow:

[0790] 1. Input Reception

[0791] User device: Type "I've been feeling a bit tired lately" and send it to the cloud server.

[0792] 2. Input Analysis

[0793] Cloud server: Identifies "fatigue" using a natural language processing engine.

[0794] 3. Data Acquisition

[0795] Cloud server: Collects data from dietary management apps and identifies vitamin B deficiencies.

[0796] 4. Factor analysis

[0797] Cloud server: Data analysis identifies vitamin B deficiency and excessive exercise.

[0798] 5. Proposal generation

[0799] Cloud server: Generates a menu using ingredients rich in vitamin B, saying, "You are lacking vitamin B."

[0800] 6. User Notices

[0801] User device: Display the proposal.

[0802] 7. Get feedback

[0803] User device: Send feedback on suggested improvements.

[0804] 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.

[0805] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a dietary management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. Furthermore, by combining the present invention with an emotion engine that recognizes the user's emotions, it is possible to provide more sophisticated and user-friendly responses. An embodiment of this system is described below.

[0806] System Overview

[0807] The system consists of the following main components:

[0808] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[0809] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[0810] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[0811] Emotion engine: Combined with natural language processing, it recognizes user emotions and adjusts responses and data acquisition.

[0812] Program processing

[0813] Receiving and Parsing User Input

[0814] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[0815] Terminal: Sends received messages to the server.

[0816] Server: Uses a natural language processing engine to analyze user messages and identify specific health issues, such as "feeling tired," and an emotion engine to recognize the user's emotions in the messages.

[0817] Data linkage and acquisition

[0818] Server: Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management apps, exercise management apps, medicine notebooks) to obtain the user's latest data. For example, if the user is feeling very stressed, the server also obtains additional data related to stress reduction.

[0819] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[0820] Factor analysis and generation of improvement proposals

[0821] Server: Analyzes the acquired data (dietary history, exercise history, medication history) to identify the causes of health problems. It also performs analysis taking into account the results of the emotion engine. For example, if the user is feeling stressed, it will analyze stress-related factors as well.

[0822] Server: Generates specific improvement proposals based on the results of factor analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest consuming foods rich in vitamin B" is generated.

[0823] Notifying users and getting feedback

[0824] Server: Sends the generated improvement suggestions to the user. Based on the results of the emotion engine, the suggestion content is also adjusted. For example, if the user tends to feel depressed, the suggestion will be given more gentle and encouraging language.

[0825] Terminal: Show improvement suggestions to the user through a chatbot interface.

[0826] Users: Review the proposal and provide additional inquiries or feedback as needed.

[0827] Specific examples

[0828] Example 1: Dietary nutrient deficiency

[0829] 1. Terminal: The user types, "I feel tired."

[0830] 2. Server: Identify "fatigue" using a natural language processing engine and recognize the emotion of "fatigue" using an emotion engine.

[0831] 3. Server: Acquires food history data from the food management app.

[0832] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[0833] 5. Server: Generates an improvement suggestion such as, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[0834] 6. Terminal: Display the suggestions to the user.

[0835] Example 2: Fatigue due to excessive exercise

[0836] 1. Device: The user types, "I've been feeling really tired lately."

[0837] 2. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[0838] 3. Server: Obtains exercise history data from the running app.

[0839] 4. Server: Analyzes the data and identifies hyperactivity.

[0840] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[0841] 6. Terminal: Display the suggestions to the user.

[0842] Benefits of adding an emotion engine

[0843] The introduction of an emotion engine makes it possible to respond to users' emotional states and provide more personalized services. For example, if a user is feeling stressed, the system can provide suggestions for relaxation techniques and advice on how to deal with stress. In this way, emotion recognition can enable more accurate healthcare advice.

[0844] The processing flow will be explained below.

[0845] Step 1:

[0846] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[0847] Step 2:

[0848] Terminal: Sends the entered message to the server.

[0849] Step 3:

[0850] Server: The received message is passed to a natural language processing engine for analysis. Specifically, the context is analyzed to identify the user's health issue (in this case, "fatigue"). The emotion engine is also used to identify the user's emotion from the message. For example, if the user types "tired," the emotion engine will identify the emotion as "fatigue."

[0851] Step 4:

[0852] Server: Taking into account the emotion recognition results from the emotion engine, the server sends an API request to obtain data related to the user's health issues from related applications (diet management app, exercise management app, medicine record). For example, if the user is feeling "fatigue" or "stressed," the server obtains data related to stress reduction in addition to their diet history and exercise history.

[0853] Step 5:

[0854] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[0855] Step 6:

[0856] Server: Analyzes the acquired data and identifies specific factors that contribute to health problems. For example:

[0857] Dietary data: Identify nutrient deficiencies and excesses.

[0858] Exercise data: Identify over- or under-exercise.

[0859] Drug data: Identify potential health problems caused by medication side effects.

[0860] It also takes into account the results of the emotion engine to analyze factors related to stress and emotional ups and downs.

[0861] Step 7:

[0862] Server: Generates specific improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is found, specific advice such as "We suggest consuming foods rich in vitamin B" is generated. Furthermore, depending on the results of the emotion engine, the suggestion content is adjusted to suit the user's emotions. For example, if the user is feeling very stressed, advice on relaxation techniques and mental care will be included.

[0863] Step 8:

[0864] Server: Sends the generated improvement suggestions to the user.

[0865] Step 9:

[0866] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[0867] Step 10:

[0868] Users: Review the proposal and provide additional inquiries or feedback as needed.

[0869] Specific examples

[0870] Example 1: Dietary nutrient deficiency

[0871] 1. Terminal: The user types, "I feel tired."

[0872] 2. Terminal: Sends the entered message to the server.

[0873] 3. Server: Identify "fatigue" using a natural language processing engine and recognize "fatigue emotion" using an emotion engine.

[0874] 4. Server: Obtains food history data from the food management app.

[0875] 5. Device: Displays the acquired meal data to the user and allows them to correct any errors.

[0876] 6. Server: Analyze the data and identify vitamin B deficiencies.

[0877] 7. Server: Create a specific improvement suggestion, such as "You are lacking in vitamin B. We suggest that you eat foods that are rich in vitamin B (e.g., fish, chicken, beans)." Because the user's emotion is "fatigue," include gentle, encouraging words.

[0878] 8. Server: Sends improvement suggestions to the user.

[0879] 9. Terminal: Display the suggestions to the user.

[0880] 10. User: Review the proposal and make any further enquiries as necessary.

[0881] Example 2: Fatigue due to excessive exercise

[0882] 1. Device: The user types, "I've been feeling really tired lately."

[0883] 2. Terminal: Sends the entered message to the server.

[0884] 3. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[0885] 4. Server: Obtains exercise history data from the running app.

[0886] 5. Device: Displays the acquired exercise data to the user and allows them to correct any errors.

[0887] 6. Server: Analyzes data and identifies hyperactivity.

[0888] 7. Server: Create a specific improvement suggestion, such as, "It seems you've been exercising too much recently. We suggest that you increase your rest time and adjust your exercise appropriately." Because the user's emotion is "irritation," include gentle words encouraging relaxation.

[0889] 8. Server: Sends improvement suggestions to the user.

[0890] 9. Terminal: Display the suggestions to the user.

[0891] 10. User: Review the proposal and make any further enquiries as necessary.

[0892] The addition of an emotion engine allows responses to be made that take into account the user's emotional state, enabling more precise and user-friendly responses.

[0893] Example 2

[0894] 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."

[0895] In modern society, users face a wide range of health problems, requiring prompt and accurate responses. However, conventional systems do not adequately take into account the user's emotional state, making it difficult to provide personalized advice. Furthermore, when linking data from multiple health management applications, the integration and analysis of that data is cumbersome, making it difficult for users to use.

[0896] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedy based on the identified cause, means for notifying the user of the generated remedy, and means for recognizing the user's emotions and adjusting the response content and data acquisition. This enables a more sophisticated and user-friendly response that takes the user's emotional state into consideration.

[0897] "Health-related messages from users" are text data of health-related questions or inquiries entered by users through the chatbot interface.

[0898] "Means for analyzing messages to identify a user's health issue" refers to the process of using a natural language processing engine to identify the type and specific content of a health issue from a received text message.

[0899] "Means for obtaining data related to the identified health problem from other applications" refers to the process of obtaining data from the diet management application, exercise management application, and medication management application to collect information related to the user's health problem.

[0900] "Means for analyzing acquired data to identify the causes of health problems" refers to the process of analyzing data to identify the root cause of a user's health problem based on the collected data.

[0901] "Means for generating improvement proposals based on identified factors" refers to the process of generating specific measures and advice for identified causes.

[0902] "Means of notifying users of generated improvement suggestions" refers to the process of communicating the generated advice and measures to users through the chatbot interface.

[0903] "Means for recognizing user emotions and adjusting response content and data acquisition" refers to the process of identifying emotions from a user's text message and adjusting appropriate responses and data acquisition based on those emotions.

[0904] This invention is a chatbot system that allows users to easily consult about minor health issues. This system works in conjunction with the user's various health management applications (diet management app, exercise management app, medication management app) to collect and analyze the user's health status as data. Furthermore, by combining it with an emotion engine, it responds according to the user's emotions. The following describes in detail the modes for implementing the present invention.

[0905] System configuration

[0906] The system consists of the following main components:

[0907] User device: A device where the user inputs health issues and receives feedback from the system (e.g., smartphone, tablet).

[0908] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analysis results and improvement suggestions.

[0909] Related applications: Existing applications that record various health-related data, such as diet management apps, exercise management apps, and medication management apps.

[0910] Emotion engine: Combined with natural language processing, this engine recognizes user emotions and adjusts response content and data acquisition.

[0911] Processing flow

[0912] 1. Receiving and Parsing User Input

[0913] Using the chatbot interface, users can input content such as "I've been feeling tired lately," and the device will then send this message to the server.

[0914] The server analyzes the received message using a natural language processing engine (e.g., spaCy or BERT) to identify health issues such as "fatigue," and then uses an emotion engine to recognize the user's emotion (e.g., "tired") in the message.

[0915] 2. Data linkage and acquisition

[0916] Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management app, exercise management app, medication management app) to obtain the user's latest data.

[0917] The terminal displays the acquired data to the user, and if there are any errors, the user can correct them.

[0918] 3. Factor analysis and generation of improvement proposals

[0919] The server analyzes the acquired data and identifies the cause of the health problem. For example, if the cause is a vitamin B deficiency, it will identify it as "vitamin B deficiency."

[0920] The server generates specific improvement suggestions based on the identified factors, such as "You are lacking in vitamin B. We suggest that you consume foods rich in vitamin B."

[0921] 4. Notifying users and getting feedback

[0922] The server sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine, for example, choosing words that are kind and encouraging if the user is feeling down.

[0923] The device will display suggested improvements to the user, allowing the user to provide additional inquiries or feedback.

[0924] Specific examples

[0925] Example 1: Dietary nutrient deficiency

[0926] 1. The user types, "I feel tired."

[0927] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "fatigue."

[0928] 3. The server retrieves the meal history data from the meal management app.

[0929] 4. The server analyzes the data and identifies vitamin B deficiencies.

[0930] 5. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[0931] 6. The device displays the suggestions to the user.

[0932] Example 2: Fatigue due to excessive exercise

[0933] 1. The user types, "I've been feeling really tired lately."

[0934] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "irritation."

[0935] 3. The server obtains exercise history data from the exercise management app.

[0936] 4. The server analyzes the data and identifies excessive exercise.

[0937] 5. The server generates an improvement suggestion saying, "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[0938] 6. The device displays the suggestions to the user.

[0939] As described above, this invention is a system that quickly and accurately analyzes a user's health problems and provides specific improvement proposals based on data. By using an emotion engine in combination, it realizes customized responses according to the user's emotional state.

[0940] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0941] Step 1:

[0942] User: Enters a health-related message into the chatbot interface. For example, "I've been feeling really tired lately."

[0943] Input: User's text message

[0944] Output: Text data sent to the terminal

[0945] Specific actions: The user enters text into the chatbot interface on their smartphone and presses the send button.

[0946] Step 2:

[0947] Terminal: Sends received messages to the server.

[0948] Input: Text data entered by the user

[0949] Output: Text data sent to the server

[0950] Specific operation: Text data is sent to the server via an HTTP request via the terminal's network module.

[0951] Step 3:

[0952] Server: Passes the received message to the natural language processing engine for analysis.

[0953] Input: Text data sent from the terminal

[0954] Output: Health issue identification results and emotion recognition results

[0955] What it does: It uses an NLP engine built in Python (e.g., spaCy or BERT) to tokenize text messages and identify health issues and sentiment.

[0956] Step 4:

[0957] Server: Uses an emotion engine to recognize user emotions from messages.

[0958] Input: Analysis results of the natural language processing engine

[0959] Output: User emotion label (e.g. "tired")

[0960] What it does: Apply a pre-trained emotion recognition model (e.g., Hugging Face emotion analysis model) to extract emotion labels from text.

[0961] Step 5:

[0962] Server: Based on the identified health issues and emotion recognition results, it sends API requests to relevant applications to retrieve the latest user data.

[0963] Input: Health issue identification results and emotion recognition results

[0964] Output: Food data, exercise data, medication data (JSON format)

[0965] Specific behavior: Sends an HTTP GET request to a RESTful API endpoint to retrieve data in JSON format from the associated application.

[0966] Step 6:

[0967] Terminal: The data sent from the server is displayed to the user. If there are any errors, the user can correct them.

[0968] Input: Latest data retrieved from the server

[0969] Output: Data confirmed and corrected by the user

[0970] Specific behavior: The retrieved data is displayed on the device UI, and the user can edit it by pressing the edit button.

[0971] Step 7:

[0972] Server: Analyzes the acquired data and identifies the causes of health problems.

[0973] Input: dietary data, exercise data, medication data

[0974] Output: Cause of health problem (e.g. "Vitamin B deficiency")

[0975] Specific operation: Reads food history, exercise history, and medication history from an SQL database and cross-references and analyzes the data using Python data analysis libraries (e.g., pandas).

[0976] Step 8:

[0977] Server: Generates specific improvement proposals based on the identified factors.

[0978] Input: Contributors to health problems

[0979] Output: Suggested improvement (e.g., "I suggest you eat foods rich in vitamin B.")

[0980] What it does: Uses rule-based engines and machine learning models to generate appropriate advice from analysis results.

[0981] Step 9:

[0982] Server: Sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine.

[0983] Input: Improvement suggestions and user sentiment labels

[0984] Output: Tailored recommendations for improvement (e.g., "Try eating these foods to feel better")

[0985] What it does: Generates textual suggestions for improvement and adjusts them based on the user's emotional state.

[0986] Step 10:

[0987] Terminal: The improvement suggestions sent from the server are displayed to the user through the chatbot interface.

[0988] Input: Improvement suggestions sent from the server

[0989] Output: Improvement suggestions for user review

[0990] Specific behavior: Display the text of the improvement suggestions in the chatbot UI.

[0991] Step 11:

[0992] User: Review the proposal and enter any feedback or follow-up inquiries.

[0993] Input: Feedback on the proposal or follow-up questions

[0994] Output: Further inquiries and feedback

[0995] What happens: Enter your feedback into the chatbot interface and hit submit. For example, enter something like "This suggestion was very helpful" or "I'd like more information."

[0996] (Application example 2)

[0997] 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."

[0998] In today's busy society, proper diet, exercise, and medication management are essential for users to maintain their health in their busy daily lives. However, it is difficult to manage this data individually and investigate and improve one's own health problems in between busy schedules. Furthermore, there is a lack of systems that provide appropriate health advice and meal plans that take into account the user's emotional state. As a result, users may make incorrect health management decisions, which could lead to further health problems. To solve these problems, there is a need for a system that allows users to easily understand their health status and receive personalized improvement suggestions that take their emotional state into account.

[0999] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedial action based on the identified cause, means for notifying the user of the generated remedial action, means for recognizing the user's emotional state, and means for adjusting the proposed action based on the recognized emotional state. This allows users to receive accurate health advice and meal plans based on centralized health management data, even in the midst of a busy lifestyle. Furthermore, personalized responses that take emotional state into account are expected to increase user satisfaction and improve their health.

[1000] A "health-related message from a user" is a text message in which a user enters information about or seeks advice regarding their health condition.

[1001] "Means for analyzing messages and identifying user health problems" refers to a method or device for analyzing received messages using natural language processing technology, etc., and identifying health problems reported by users from among the messages.

[1002] The "means for obtaining data related to health issues from other applications" refers to an interface or protocol for collecting health-related data from health management applications, etc., that the user is using.

[1003] "Means for analyzing acquired data to identify the causes of health problems" refers to a method or device that analyzes collected data using techniques such as statistical analysis and machine learning to identify the root cause of a user's health problem.

[1004] The "means for generating improvement proposals based on identified factors" refers to a method or device for generating specific proposals for improving the user's health condition based on the analysis results.

[1005] The "means for notifying the user of the generated improvement proposal" refers to a notification function or interface for informing the user of the generated improvement proposal.

[1006] "Means for recognizing a user's emotional state" refers to technology or devices for analyzing and recognizing emotions from messages or other data entered by a user.

[1007] "Means for adjusting suggestions based on a recognized emotional state" refers to a method or device for adjusting the suggestions and how they are presented depending on the user's emotional state.

[1008] The "means for acquiring dietary data from a health management application" is an interface or protocol for collecting dietary data from a diet management application used by a user.

[1009] The "means for acquiring exercise data from an exercise management application" refers to an interface or protocol for collecting exercise-related data from the exercise management application used by the user.

[1010] A "means for obtaining medication data from a medication management application" is an interface or protocol for collecting data about medication use from the medication management application being used by the user.

[1011] A "service that provides food and meals based on a meal plan" is a service that delivers appropriate food and meals to a user based on a generated meal plan.

[1012] A "natural language processing engine" is software or technology used to perform semantic analysis and information extraction on text data entered by a user.

[1013] An "emotion engine" is software or technology for analyzing and recognizing a user's emotions.

[1014] This invention is a chatbot system that allows users to easily consult about their health condition. It works in conjunction with multiple health management-related applications to collect and analyze data and provide improvement suggestions that take emotional state into consideration.

[1015] System Overview

[1016] The system consists of the following main components:

[1017] User device: The device (smartphone, tablet, etc.) where the user enters health-related messages and receives feedback from the system.

[1018] Server system: A central processing unit that analyzes user input, collects relevant data, and generates analytical results. It uses natural language processing engines such as Google Cloud NLP and emotion engines such as Affectiva SDK.

[1019] Related applications: Existing applications that record health-related data (diet management apps, exercise management apps, medication management apps).

[1020] Delivery services: Services that deliver food or meals based on suggested meal plans (e.g., meal delivery service APIs).

[1021] What the program does

[1022] Receiving and Parsing User Input

[1023] Users input their health concerns using the chatbot interface. The device then sends the received message to the server, which uses Google Cloud NLP to analyze the user's message and identify the health issue being raised. The server also uses the Affectiva SDK to recognize the user's emotional state.

[1024] Data linkage and acquisition

[1025] The server retrieves data from the user's diet management app, exercise management app, and medication management app via API, and also retrieves additional data based on the results of the emotion engine.

[1026] Factor analysis and generation of improvement proposals

[1027] Using the acquired data, the server performs various statistical analyses and machine learning to identify the causes of health problems. Based on the identified causes, it generates specific improvement suggestions, such as vitamin B deficiency. It also takes into account the patient's emotional state and selects positive language.

[1028] User notification and delivery

[1029] The server generates an appropriate message to notify the user of the proposed improvements, and sends it to the device. The user can then confirm the suggestions and place an order with a delivery service if necessary.

[1030] Specific examples

[1031] 1. The user types, "I've been feeling tired lately."

[1032] 2. The server identifies "fatigue" using Google Cloud NLP and recognizes "fatigue" using the Affectiva SDK.

[1033] 3. The server retrieves the diet history data from the diet management app and analyzes vitamin B deficiency.

[1034] 4. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[1035] 5. Display the suggestions on the user's device and deliver the appropriate food using the relevant delivery service.

[1036] Prompt Sentence Examples

[1037] Example user input: "I've been feeling really tired lately. What should I eat?"

[1038] Example system output: "You may be lacking in vitamin B. Try eating foods rich in vitamin B, such as liver, fish, and eggs."

[1039] In this way, the system of the present invention comprehensively manages the user's health condition, provides appropriate health advice that also takes into account the user's emotional state, and delivers food and meals based on that advice, allowing users to efficiently improve their health even in their busy daily lives.

[1040] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1041] Step 1:

[1042] Receive health-related messages from users.

[1043] Input: A user uses the chatbot interface on their device to type a message such as, "I've been feeling really tired lately."

[1044] Specific operation: The device receives user input and sends the message to the server.

[1045] Output: The server receives the user's message.

[1046] Step 2:

[1047] Analyze messages and identify health issues.

[1048] Input: The user's message received in step 1.

[1049] How it works: The server uses Google Cloud NLP to analyze the message and identify health issues such as "fatigue."

[1050] Output: Identified health problem (e.g., fatigue).

[1051] Step 3:

[1052] Recognize the user's emotional state.

[1053] Input: The user's message received in step 1.

[1054] Specific operation: The server uses the Affectiva SDK to recognize the emotional state from messages, user facial expressions, etc.

[1055] Output: Perceived emotional state (e.g., "tired").

[1056] Step 4:

[1057] Obtaining data related to health issues from other applications.

[1058] Input: Identified health problems (Step 2) and perceived emotional states (Step 3).

[1059] Specific operation: The server calls APIs for dietary management apps, exercise management apps, medicine records, etc. to collect the latest health data.

[1060] Output: Acquired health data (dietary history, exercise history, medication history, etc.).

[1061] Step 5:

[1062] The acquired data is analyzed to identify the causes of health problems.

[1063] Input: Acquired health data (Step 4).

[1064] What it does: The server analyzes the data using statistical analysis and machine learning to identify the causes of health problems (e.g., vitamin B deficiency).

[1065] Output: Identified contributing factors to health problems.

[1066] Step 6:

[1067] Generate improvement recommendations based on the identified factors.

[1068] Input: Identified contributing factors to the health problem (Step 5).

[1069] Specific operation: The server uses the generated AI model to generate specific suggestions (e.g., consuming foods rich in vitamin B).

[1070] Output: Generated improvement suggestions.

[1071] Step 7:

[1072] Notify the user of the generated improvement suggestions.

[1073] Input: Generated improvement proposals (Step 6).

[1074] Specific operation: The server adjusts the suggestion content based on the user's emotional state, creates a notification message, and sends it to the device.

[1075] Output: The improvement suggestions sent to the user's device.

[1076] Step 8:

[1077] The user delivers based on the suggestions.

[1078] Input: The improvement proposal notified to the user's device (Step 7).

[1079] Specific behavior: The user confirms the notification message and uses the meal delivery service based on the suggested meal plan.

[1080] Output: The user's order is sent to the delivery service and the food or meal is delivered.

[1081] 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.

[1082] 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.

[1083] 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.

[1084] [Third embodiment]

[1085] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1086] 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.

[1087] 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).

[1088] 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.

[1089] 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.

[1090] 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).

[1091] 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.

[1092] 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.

[1093] 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.

[1094] 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.

[1095] 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.

[1096] 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."

[1097] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a diet management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. The following describes an embodiment of this system.

[1098] System Overview

[1099] The system consists of the following main components:

[1100] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[1101] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[1102] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[1103] Program processing

[1104] Receiving and Parsing User Input

[1105] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[1106] Terminal: Sends received messages to the server.

[1107] Server: Uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[1108] Data linkage and acquisition

[1109] Server: After a health problem is identified, the server, with the user's consent, connects with relevant applications (diet management app, exercise management app, medication management app) and obtains the necessary data via API.

[1110] Terminal: Display the acquired data to the user and ask them to correct any errors.

[1111] Factor analysis and generation of improvement proposals

[1112] Server: Analyzes the acquired data (dietary history, exercise history, medication history) and clarifies the causes of identified health problems (e.g., fatigue).

[1113] Server: Generates specific improvement proposals based on the results of the factor analysis. For example, if a lack of vitamin B is the cause, the server generates advice such as "We suggest that you consume foods rich in vitamin B."

[1114] Notifying users and getting feedback

[1115] Server: Sends the generated improvement suggestions to the user.

[1116] On the device: Show the user suggested improvements and accept additional inquiries and feedback as needed.

[1117] Specific examples

[1118] Example 1: Dietary nutrient deficiency

[1119] 1. Terminal: The user types, "I feel tired."

[1120] 2. Server: Identify "fatigue" using a natural language processing engine.

[1121] 3. Server: Acquires food history data from the food management app.

[1122] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[1123] 5. Server: Generates an improvement suggestion: "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B (e.g., fish, chicken, beans)."

[1124] 6. Terminal: Display the suggestions to the user.

[1125] Example 2: Fatigue due to excessive exercise

[1126] 1. Device: The user types, "I've been feeling really tired lately."

[1127] 2. Server: Identify "fatigue" using a natural language processing engine.

[1128] 3. Server: Obtains exercise history data from the running app.

[1129] 4. Server: Analyzes the data and identifies hyperactivity.

[1130] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[1131] 6. Terminal: Display the suggestions to the user.

[1132] Through this system, users can receive prompt and appropriate treatment for even mild illnesses that do not require a visit to the hospital, and by linking and analyzing data, they can receive more accurate and personalized health advice.

[1133] The processing flow will be explained below.

[1134] Step 1:

[1135] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[1136] Step 2:

[1137] Terminal: Sends the entered message to the server.

[1138] Step 3:

[1139] Server: Passes the received message to a natural language processing engine for analysis. Specifically, it analyzes the context and identifies the user's health problem (in this case, "fatigue").

[1140] Step 4:

[1141] Server: Based on the identified health issue, it sends API requests to relevant applications (diet management app, exercise management app, medicine record book) to obtain the user's latest data.

[1142] Step 5:

[1143] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[1144] Step 6:

[1145] Server: Analyzes the acquired data and identifies the causes of health problems. Specifically, it analyzes the following data individually:

[1146] Dietary data: Identify nutrient deficiencies and excesses.

[1147] Exercise data: Identify over- or under-exercise.

[1148] Drug data: Identify potential health issues caused by medication side effects.

[1149] Step 7:

[1150] Server: Generates improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest eating foods rich in vitamin B" is generated.

[1151] Step 8:

[1152] Server: Sends the generated improvement suggestions to the user.

[1153] Step 9:

[1154] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[1155] Step 10:

[1156] Users: Review the proposal and provide additional inquiries or feedback as needed.

[1157] Example 1

[1158] 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."

[1159] In today's modern living environment, it is important to detect minor health problems early and take appropriate measures. However, conventional methods require users to operate health management applications individually, and collect and analyze data, which is time-consuming. In addition, integrating and analyzing data from each application is technically difficult, and some factors may be overlooked. This makes it difficult for users to quickly receive appropriate health advice.

[1160] 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.

[1161] In this invention, the server includes means for receiving health-related messages from a user, means for analyzing the messages to identify a health problem of the user, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating an improvement plan based on the identified cause, means for notifying the user of the generated improvement plan, means for displaying the acquired data to the user to encourage correction, and means for receiving user feedback based on the generated improvement plan. This eliminates the need for users to operate individual applications, and enables the centralized collection and analysis of health data to quickly receive appropriate advice.

[1162] "Health-related messages" are text data in which users write about their health status and physical condition.

[1163] A "health issue" is a specific health problem or symptom that a user is experiencing.

[1164] An "application" is a software program that users use on their smartphones or tablets to manage their health and record data.

[1165] "Data" refers to records of health information about the user, including dietary history, exercise history, medication history, etc.

[1166] "Data analysis" refers to the process of using statistical methods and algorithms based on the acquired data to extract the user's health condition and the causes of problems.

[1167] "Improvement ideas" are specific suggestions or advice for addressing identified health problems or their contributing factors.

[1168] A "natural language processing engine" is an artificial intelligence technology for analyzing text data and understanding its meaning.

[1169] "Preprocessing" refers to processing that is performed before data analysis, and includes data imputation and normalization.

[1170] "User feedback" is any additional input or reaction a user gives to advice or suggestions provided by the system.

[1171] The present invention is a chatbot system that allows users to easily consult with the system about minor health problems. The chatbot system works in conjunction with multiple health management applications to collect the user's health data, identify the causes of the problems, and provide suggestions for improvement. A specific embodiment of the system is described below.

[1172] System Configuration and Operation

[1173] Receiving and Parsing User Input

[1174] A user launches the chatbot interface using a smartphone or tablet. For example, they might input something like, "I haven't been feeling any better lately." The device receives this input and sends it to a server. The server then sends the received input to a natural language processing engine (e.g., Google Cloud Natural Language API) and analyzes the text. The natural language processing engine then identifies specific health issues, such as "feeling tired," from the user's input.

[1175] Data linkage and acquisition

[1176] After a health problem is identified, the server, with the user's consent, connects with relevant existing health management applications (e.g., dietary management apps, exercise management apps, medication management apps). The server obtains the necessary data (dietary history, exercise history, medication history) from each application via API. To improve the accuracy of the obtained data, the device displays the data to the user and prompts them to correct any omissions or errors.

[1177] Factor analysis and generation of improvement proposals

[1178] The server uses Python's Pandas library to analyze the acquired data. It preprocesses the dataset, for example, by filling in missing data and normalizing it. Next, it analyzes the diet history to check for vitamin B deficiency, exercise history to check for excessive exercise, and medication history to check for side effects. Based on the analysis results, it generates specific improvement suggestions (for example, if vitamin B is deficient, advice such as "We suggest consuming foods rich in vitamin B").

[1179] Notifying users and getting feedback

[1180] The server notifies the user of the generated improvement suggestions. The device displays the suggestions on the chatbot interface. For example, it may say, "You are deficient in vitamin B. Eat fish, chicken, and beans, which are rich in vitamin B." The user checks the suggestions and enters additional inquiries or feedback as needed. The device sends this feedback to the server, which analyzes the received feedback and generates additional advice or corrections as needed.

[1181] Specific examples

[1182] Example 1: Dietary nutrient deficiency

[1183] 1. User: Type "I'm tired" into the chatbot.

[1184] 2. Terminal: Sends input data to the server.

[1185] 3. Server: Uses a natural language processing engine to identify "fatigue."

[1186] 4. Server: Obtains meal history data using the meal management app's API.

[1187] 5. Server: Analyze the data using the Pandas library and identify vitamin B deficiencies.

[1188] 6. Server: Produces "You are deficient in Vitamin B. We suggest consuming foods rich in Vitamin B (e.g., fish, chicken, beans)."

[1189] 7. Terminal: Show this suggestion to the user.

[1190] Example 2: Fatigue due to excessive exercise

[1191] 1. User: Type into the chatbot, "I've been feeling really tired lately."

[1192] 2. Terminal: Sends input data to the server.

[1193] 3. Server: Uses a natural language processing engine to identify "fatigue."

[1194] 4. Server: Obtains exercise history data through the running app's API.

[1195] 5. Server: Analyze the data using the Pandas library to identify hyperactivity.

[1196] 6. Server: Generate "You've been exercising too much recently. We suggest you increase your rest time and adjust your exercise accordingly."

[1197] 7. Terminal: Show this suggestion to the user.

[1198] As described above, by utilizing this system, users can eliminate the need to operate individual applications, centrally collect and analyze health data, and quickly receive appropriate advice.

[1199] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1200] Step 1:

[1201] User: The user launches the chatbot interface on their smartphone or tablet, for example by typing, "I've been feeling tired lately."

[1202] Input: A health-related message (e.g., "I've been feeling tired lately").

[1203] Output: The input data is displayed on the terminal device.

[1204] Step 2:

[1205] Terminal: Sends input data to the server. Specifically, the communication module in the terminal sends message data to the server as an HTTP request.

[1206] Input: A health-related message entered by the user.

[1207] Output: A message from the user is sent to the server.

[1208] Step 3:

[1209] Server: The server sends the received message to a natural language processing engine to analyze the text, for example using the Google Cloud Natural Language API.

[1210] Input: A health-related message sent by the user.

[1211] Output: The natural language processing engine returns the health issue (e.g., "feeling tired") as the analysis result.

[1212] Step 4:

[1213] Server: After a health problem is identified, the server obtains the user's consent and connects with the relevant applications to obtain the necessary data through APIs. Specifically, it issues API requests to the diet management app, exercise management app, and medication management app.

[1214] Input: Analysis results from a natural language processing engine (e.g., "fatigue").

[1215] Output: Dietary history, exercise history, and medication history data obtained from each application.

[1216] Step 5:

[1217] Terminal: If necessary, display the acquired data to the user and prompt them to correct any deficiencies or errors. Specifically, the acquired data is temporarily saved and an interface for user confirmation is displayed.

[1218] Input: Health data obtained from each application.

[1219] Output: The data displayed to the user and the modified data (if any).

[1220] Step 6:

[1221] Server: To analyze the acquired data, we use the Python Pandas library. We preprocess the dataset (implanting missing data and normalizing it) and analyze the dietary history, exercise history, and medication history.

[1222] Input: Data obtained from each application and data modified by the user.

[1223] Output: Contributing factors to the health problem (e.g., vitamin B deficiency).

[1224] Step 7:

[1225] Server: Generates specific improvement suggestions based on the analysis results. For example, if a vitamin B deficiency is identified, the server will suggest "consuming foods rich in vitamin B."

[1226] Input: Contributors to health problems.

[1227] Output: Specific improvement suggestions.

[1228] Step 8:

[1229] Server: Notifies the user of the generated improvement suggestions. Converts the improvement suggestions into a display format for notifications and sends them to the device.

[1230] Input: Generated improvement suggestions.

[1231] Output: The improvement suggestions converted into a display format.

[1232] Step 9:

[1233] Terminal: The improvement suggestions are displayed in the chatbot interface. Specifically, the improvement suggestions are displayed as chatbot messages.

[1234] Input: The improvement suggestion sent by the server.

[1235] Output: Suggested improvements that users can see on their screen.

[1236] Step 10:

[1237] User: Review the suggested improvements and enter any additional questions or feedback as needed.

[1238] Input: User feedback on the proposed improvements.

[1239] Output: User feedback.

[1240] Step 11:

[1241] Terminal: Sends user feedback to the server. The terminal sends the input data back to the server.

[1242] Input: Additional feedback from the user.

[1243] Output: Feedback sent to the server.

[1244] Step 12:

[1245] Server: Analyzes the received feedback and generates additional advice and corrections as needed, again using a natural language processing engine.

[1246] Input: User feedback.

[1247] Output: Additional advice and suggested fixes.

[1248] These are the specific processing steps of this system. At each step, various data processing and calculations are performed based on the input data, and ultimately the optimal health advice is provided to the user. The results displayed to the user are then checked and further improvements are made as necessary.

[1249] (Application example 1)

[1250] 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."

[1251] In today's busy lifestyles, many people have little time to address minor health issues. Finding appropriate solutions is difficult, especially when diet, exercise, and medication management are factors. Furthermore, there is no system that centrally manages health data and recommends meal plans appropriate for individual health conditions. Therefore, there is a need for a system that allows users to easily obtain effective improvement measures tailored to their health condition.

[1252] 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.

[1253] In this invention, the server includes means for receiving health-related messages from users, means for analyzing the messages to identify health problems of the users, means for acquiring data related to the identified health problems from other applications, means for analyzing the acquired data to identify causes of the health problems, means for generating improvement proposals based on the identified causes, means for notifying the users of the generated improvement proposals, and means for recommending appropriate meal menus based on the users' health conditions. This allows users to centrally manage their health data and easily obtain effective dietary improvement measures suited to their individual health conditions.

[1254] "User" refers to an individual who uses the System.

[1255] "Health-related message" refers to text information entered by a user to describe their health condition or any issues they may be experiencing.

[1256] "Means for identifying a health issue" refers to a method or apparatus for analyzing a received health-related message and identifying a user's specific health issue.

[1257] "Means for acquiring data" refers to a method or device for acquiring relevant data based on the identified health problem from an external application (such as a diet management app, exercise management app, or medication management app).

[1258] "Means for identifying causes" refers to a method or device for analyzing the acquired data and clarifying the causes of the user's health problem.

[1259] "Means for generating improvement suggestions" refers to a method or device that creates specific suggestions for resolving a user's health problem based on the identified factors.

[1260] "Means for notifying users" refers to methods or devices for notifying users of generated improvement proposals or recommendations.

[1261] "Means for recommending appropriate meal menus based on health status" refers to a method or device that analyzes a user's health data and, based on the results, suggests a meal plan appropriate for the user's health status.

[1262] The term "system" refers to a mechanism in which a series of components including the above-mentioned means work together.

[1263] This invention provides a system for users to solve minor health problems, linked to a food delivery application equipped with a meal menu recommendation function. The system includes a user terminal, a cloud server, and an existing health management application. Specific embodiments are described below.

[1264] Key Components of the System

[1265] 1. User Device

[1266] Smartphone: A device where the user can input health-related messages and receive feedback from the system.

[1267] 2. Cloud Server

[1268] Server: A central processing unit that analyzes messages from users and identifies health issues, as well as retrieves and analyzes data from related apps.

[1269] Natural language processing engine (e.g., Google NLP API): Used to analyze user messages and identify specific health issues.

[1270] 3. Related Applications

[1271] Meal management app: An application that records meal history data.

[1272] Exercise management app: An application that records exercise history data.

[1273] Medication management app: An application that records medication usage history data.

[1274] Food delivery app: An application that recommends healthy meal menus based on health data and delivers them to users.

[1275] System processing overview

[1276] 1. Receiving and Parsing User Input

[1277] A user types "I've been feeling a bit tired lately" into a food delivery app chatbot, and their smartphone sends this message to a cloud server.

[1278] The cloud server uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[1279] 2. Data linkage and acquisition

[1280] After a health problem is identified, the cloud server connects with the diet management app, exercise management app, and medication management app to obtain the necessary data through APIs.

[1281] The smartphone displays the acquired data to the user and prompts them to make corrections if there are any errors.

[1282] 3. Factor analysis and recommendation generation

[1283] The cloud server analyzes the acquired data and identifies the cause of the user's health problem (e.g., vitamin B deficiency).

[1284] Based on the results of the factor analysis, the cloud server generates a meal menu that takes nutritional balance into consideration.

[1285] 4. User Notification and Feedback

[1286] The cloud server sends the generated menu suggestions to the user.

[1287] The smartphone displays the suggestions to the user and accepts their ratings and feedback.

[1288] Specific examples

[1289] If a user types "I've been feeling tired lately" into a food delivery app, the system will follow this flow:

[1290] 1. Input Analysis

[1291] Cloud Server: Identifying "fatigue."

[1292] 2. Data Acquisition

[1293] Cloud server: Acquires data from a dietary management app and identifies vitamin B deficiencies.

[1294] 3. Proposal generation

[1295] Cloud server: Generates the message, "You are lacking in vitamin B. We will suggest a menu using ingredients that are rich in vitamin B."

[1296] 4. User Notices

[1297] Smartphone: Suggestions are displayed to the user.

[1298] Prompt Sentence Examples

[1299] The following prompts can be used to instruct the generative AI model to proceed:

[1300] If a user types in "I've been feeling a bit tired lately," the app will identify the health issue of "fatigue" and retrieve data from related apps. It will then identify a vitamin B deficiency and suggest a menu using ingredients rich in vitamin B.

[1301] The system will enable users to easily access fast, accurate solutions to minor health issues they experience in their daily lives.

[1302] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1303] Step 1:

[1304] A user can send a health-related message to a chatbot in a food delivery app by inputting "I've been feeling a bit tired lately." The input data is in text format and is sent from the user's device to a cloud server. The input of this step is the user's message, and the output is the message sent to the cloud server.

[1305] Step 2:

[1306] The cloud server analyzes the received message using a natural language processing engine (e.g., Google NLP API). The server processes the text data and identifies specific health problems, such as "feeling tired." The input for this step is the user's message, and the output is the data on the identified health problem.

[1307] Step 3:

[1308] Based on the identified health problem, the server retrieves relevant data from the diet management app, exercise management app, and medication management app. The retrieved data includes diet history, exercise history, and medication history. Data is shared via API, and user consent is required. The input of this step is the identified health problem data, and the output is related history data.

[1309] Step 4:

[1310] The cloud server analyzes and processes the acquired historical data. It checks the intake of vitamin B in the dietary history and analyzes the exercise history to check for excessive exercise. The input of this step is the acquired historical data, and the output is the specific factors that cause health problems.

[1311] Step 5:

[1312] After the factors are identified, the cloud server generates improvement suggestions and meal menu recommendations based on the user's health condition. For example, if a user is deficient in vitamin B, it will suggest a menu using ingredients rich in vitamin B. The input of this step is the identified factors of the health problem, and the output is improvement suggestions and recommendations.

[1313] Step 6:

[1314] The cloud server notifies the user device of the generated improvement plan and meal recommendation. The notified content is displayed to the user through the chatbot interface. The input of this step is the generated improvement plan and recommendation, and the output is a notification to the user.

[1315] Step 7:

[1316] The user checks the notified improvement proposals and meal recommendations, and provides an evaluation and feedback. This feedback is sent back to the cloud server and used to improve the accuracy of the system. The input of this step is the user's feedback, and the output is the feedback sent to the cloud server.

[1317] Specific examples

[1318] If a user types "I've been feeling tired lately" into a food delivery app, here's what the system will flow:

[1319] 1. Input Reception

[1320] User device: Type "I've been feeling a bit tired lately" and send it to the cloud server.

[1321] 2. Input Analysis

[1322] Cloud server: Identifies "fatigue" using a natural language processing engine.

[1323] 3. Data Acquisition

[1324] Cloud server: Collects data from dietary management apps and identifies vitamin B deficiencies.

[1325] 4. Factor analysis

[1326] Cloud server: Data analysis identifies vitamin B deficiency and excessive exercise.

[1327] 5. Proposal generation

[1328] Cloud server: Generates a menu using ingredients rich in vitamin B, saying, "You are lacking vitamin B."

[1329] 6. User Notices

[1330] User device: Display the proposal.

[1331] 7. Get feedback

[1332] User device: Send feedback on suggested improvements.

[1333] 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.

[1334] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a dietary management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. Furthermore, by combining the present invention with an emotion engine that recognizes the user's emotions, it is possible to provide more sophisticated and user-friendly responses. An embodiment of this system is described below.

[1335] System Overview

[1336] The system consists of the following main components:

[1337] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[1338] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[1339] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[1340] Emotion engine: Combined with natural language processing, it recognizes user emotions and adjusts responses and data acquisition.

[1341] Program processing

[1342] Receiving and Parsing User Input

[1343] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[1344] Terminal: Sends received messages to the server.

[1345] Server: Uses a natural language processing engine to analyze user messages and identify specific health issues, such as "feeling tired," and an emotion engine to recognize the user's emotions in the messages.

[1346] Data linkage and acquisition

[1347] Server: Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management apps, exercise management apps, medicine notebooks) to obtain the user's latest data. For example, if the user is feeling very stressed, the server also obtains additional data related to stress reduction.

[1348] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[1349] Factor analysis and generation of improvement proposals

[1350] Server: Analyzes the acquired data (dietary history, exercise history, medication history) to identify the causes of health problems. It also performs analysis taking into account the results of the emotion engine. For example, if the user is feeling stressed, it will analyze stress-related factors as well.

[1351] Server: Generates specific improvement proposals based on the results of factor analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest consuming foods rich in vitamin B" is generated.

[1352] Notifying users and getting feedback

[1353] Server: Sends the generated improvement suggestions to the user. Based on the results of the emotion engine, the suggestion content is also adjusted. For example, if the user tends to feel depressed, the suggestion will be given more gentle and encouraging language.

[1354] Terminal: Show improvement suggestions to the user through a chatbot interface.

[1355] Users: Review the proposal and provide additional inquiries or feedback as needed.

[1356] Specific examples

[1357] Example 1: Dietary nutrient deficiency

[1358] 1. Terminal: The user types, "I feel tired."

[1359] 2. Server: Identify "fatigue" using a natural language processing engine and recognize the emotion of "fatigue" using an emotion engine.

[1360] 3. Server: Acquires food history data from the food management app.

[1361] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[1362] 5. Server: Generates an improvement suggestion such as, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[1363] 6. Terminal: Display the suggestions to the user.

[1364] Example 2: Fatigue due to excessive exercise

[1365] 1. Device: The user types, "I've been feeling really tired lately."

[1366] 2. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[1367] 3. Server: Obtains exercise history data from the running app.

[1368] 4. Server: Analyzes the data and identifies hyperactivity.

[1369] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[1370] 6. Terminal: Display the suggestions to the user.

[1371] Benefits of adding an emotion engine

[1372] The introduction of an emotion engine makes it possible to respond to users' emotional states and provide more personalized services. For example, if a user is feeling stressed, the system can provide suggestions for relaxation techniques and advice on how to deal with stress. In this way, emotion recognition can enable more accurate healthcare advice.

[1373] The processing flow will be explained below.

[1374] Step 1:

[1375] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[1376] Step 2:

[1377] Terminal: Sends the entered message to the server.

[1378] Step 3:

[1379] Server: The received message is passed to a natural language processing engine for analysis. Specifically, the context is analyzed to identify the user's health issue (in this case, "fatigue"). The emotion engine is also used to identify the user's emotion from the message. For example, if the user types "tired," the emotion engine will identify the emotion as "fatigue."

[1380] Step 4:

[1381] Server: Taking into account the emotion recognition results from the emotion engine, the server sends an API request to obtain data related to the user's health issues from related applications (diet management app, exercise management app, medicine record). For example, if the user is feeling "fatigue" or "stressed," the server obtains data related to stress reduction in addition to their diet history and exercise history.

[1382] Step 5:

[1383] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[1384] Step 6:

[1385] Server: Analyzes the acquired data and identifies specific factors that contribute to health problems. For example:

[1386] Dietary data: Identify nutrient deficiencies and excesses.

[1387] Exercise data: Identify over- or under-exercise.

[1388] Drug data: Identify potential health problems caused by medication side effects.

[1389] It also takes into account the results of the emotion engine to analyze factors related to stress and emotional ups and downs.

[1390] Step 7:

[1391] Server: Generates specific improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is found, specific advice such as "We suggest consuming foods rich in vitamin B" is generated. Furthermore, depending on the results of the emotion engine, the suggestion content is adjusted to suit the user's emotions. For example, if the user is feeling very stressed, advice on relaxation techniques and mental care will be included.

[1392] Step 8:

[1393] Server: Sends the generated improvement suggestions to the user.

[1394] Step 9:

[1395] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[1396] Step 10:

[1397] Users: Review the proposal and provide additional inquiries or feedback as needed.

[1398] Specific examples

[1399] Example 1: Dietary nutrient deficiency

[1400] 1. Terminal: The user types, "I feel tired."

[1401] 2. Terminal: Sends the entered message to the server.

[1402] 3. Server: Identify "fatigue" using a natural language processing engine and recognize "fatigue emotion" using an emotion engine.

[1403] 4. Server: Obtains food history data from the food management app.

[1404] 5. Device: Displays the acquired meal data to the user and allows them to correct any errors.

[1405] 6. Server: Analyze the data and identify vitamin B deficiencies.

[1406] 7. Server: Create a specific improvement suggestion, such as "You are lacking in vitamin B. We suggest that you eat foods that are rich in vitamin B (e.g., fish, chicken, beans)." Because the user's emotion is "fatigue," include gentle, encouraging words.

[1407] 8. Server: Sends improvement suggestions to the user.

[1408] 9. Terminal: Display the suggestions to the user.

[1409] 10. User: Review the proposal and make any further enquiries as necessary.

[1410] Example 2: Fatigue due to excessive exercise

[1411] 1. Device: The user types, "I've been feeling really tired lately."

[1412] 2. Terminal: Sends the entered message to the server.

[1413] 3. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[1414] 4. Server: Obtains exercise history data from the running app.

[1415] 5. Device: Displays the acquired exercise data to the user and allows them to correct any errors.

[1416] 6. Server: Analyzes data and identifies hyperactivity.

[1417] 7. Server: Create a specific improvement suggestion, such as, "It seems you've been exercising too much recently. We suggest that you increase your rest time and adjust your exercise appropriately." Because the user's emotion is "irritation," include gentle words encouraging relaxation.

[1418] 8. Server: Sends improvement suggestions to the user.

[1419] 9. Terminal: Display the suggestions to the user.

[1420] 10. User: Review the proposal and make any further enquiries as necessary.

[1421] The addition of an emotion engine allows responses to be made that take into account the user's emotional state, enabling more precise and user-friendly responses.

[1422] Example 2

[1423] 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."

[1424] In modern society, users face a wide range of health problems, requiring prompt and accurate responses. However, conventional systems do not adequately take into account the user's emotional state, making it difficult to provide personalized advice. Furthermore, when linking data from multiple health management applications, the integration and analysis of that data is cumbersome, making it difficult for users to use.

[1425] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedy based on the identified cause, means for notifying the user of the generated remedy, and means for recognizing the user's emotions and adjusting the response content and data acquisition. This enables a more sophisticated and user-friendly response that takes the user's emotional state into consideration.

[1426] "Health-related messages from users" are text data of health-related questions or inquiries entered by users through the chatbot interface.

[1427] "Means for analyzing messages to identify a user's health issue" refers to the process of using a natural language processing engine to identify the type and specific content of a health issue from a received text message.

[1428] "Means for obtaining data related to the identified health problem from other applications" refers to the process of obtaining data from the diet management application, exercise management application, and medication management application to collect information related to the user's health problem.

[1429] "Means for analyzing acquired data to identify the causes of health problems" refers to the process of analyzing data to identify the root cause of a user's health problem based on the collected data.

[1430] "Means for generating improvement proposals based on identified factors" refers to the process of generating specific measures and advice for identified causes.

[1431] "Means of notifying users of generated improvement suggestions" refers to the process of communicating the generated advice and measures to users through the chatbot interface.

[1432] "Means for recognizing user emotions and adjusting response content and data acquisition" refers to the process of identifying emotions from a user's text message and adjusting appropriate responses and data acquisition based on those emotions.

[1433] This invention is a chatbot system that allows users to easily consult about minor health issues. This system works in conjunction with the user's various health management applications (diet management app, exercise management app, medication management app) to collect and analyze the user's health status as data. Furthermore, by combining it with an emotion engine, it responds according to the user's emotions. The following describes in detail the modes for implementing the present invention.

[1434] System configuration

[1435] The system consists of the following main components:

[1436] User device: A device where the user inputs health issues and receives feedback from the system (e.g., smartphone, tablet).

[1437] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analysis results and improvement suggestions.

[1438] Related applications: Existing applications that record various health-related data, such as diet management apps, exercise management apps, and medication management apps.

[1439] Emotion engine: Combined with natural language processing, this engine recognizes user emotions and adjusts response content and data acquisition.

[1440] Processing flow

[1441] 1. Receiving and Parsing User Input

[1442] Using the chatbot interface, users can input content such as "I've been feeling tired lately," and the device will then send this message to the server.

[1443] The server analyzes the received message using a natural language processing engine (e.g., spaCy or BERT) to identify health issues such as "fatigue," and then uses an emotion engine to recognize the user's emotion (e.g., "tired") in the message.

[1444] 2. Data linkage and acquisition

[1445] Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management app, exercise management app, medication management app) to obtain the user's latest data.

[1446] The terminal displays the acquired data to the user, and if there are any errors, the user can correct them.

[1447] 3. Factor analysis and generation of improvement proposals

[1448] The server analyzes the acquired data and identifies the cause of the health problem. For example, if the cause is a vitamin B deficiency, it will identify it as "vitamin B deficiency."

[1449] The server generates specific improvement suggestions based on the identified factors, such as "You are lacking in vitamin B. We suggest that you consume foods rich in vitamin B."

[1450] 4. Notifying users and getting feedback

[1451] The server sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine, for example, choosing words that are kind and encouraging if the user is feeling down.

[1452] The device will display suggested improvements to the user, allowing the user to provide additional inquiries or feedback.

[1453] Specific examples

[1454] Example 1: Dietary nutrient deficiency

[1455] 1. The user types, "I feel tired."

[1456] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "fatigue."

[1457] 3. The server retrieves the meal history data from the meal management app.

[1458] 4. The server analyzes the data and identifies vitamin B deficiencies.

[1459] 5. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[1460] 6. The device displays the suggestions to the user.

[1461] Example 2: Fatigue due to excessive exercise

[1462] 1. The user types, "I've been feeling really tired lately."

[1463] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "irritation."

[1464] 3. The server obtains exercise history data from the exercise management app.

[1465] 4. The server analyzes the data and identifies excessive exercise.

[1466] 5. The server generates an improvement suggestion saying, "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[1467] 6. The device displays the suggestions to the user.

[1468] As described above, this invention is a system that quickly and accurately analyzes a user's health problems and provides specific improvement proposals based on data. By using an emotion engine in combination, it realizes customized responses according to the user's emotional state.

[1469] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1470] Step 1:

[1471] User: Enters a health-related message into the chatbot interface. For example, "I've been feeling really tired lately."

[1472] Input: User's text message

[1473] Output: Text data sent to the terminal

[1474] Specific actions: The user enters text into the chatbot interface on their smartphone and presses the send button.

[1475] Step 2:

[1476] Terminal: Sends received messages to the server.

[1477] Input: Text data entered by the user

[1478] Output: Text data sent to the server

[1479] Specific operation: Text data is sent to the server via an HTTP request via the terminal's network module.

[1480] Step 3:

[1481] Server: Passes the received message to the natural language processing engine for analysis.

[1482] Input: Text data sent from the terminal

[1483] Output: Health issue identification results and emotion recognition results

[1484] What it does: It uses an NLP engine built in Python (e.g., spaCy or BERT) to tokenize text messages and identify health issues and sentiment.

[1485] Step 4:

[1486] Server: Uses an emotion engine to recognize user emotions from messages.

[1487] Input: Analysis results of the natural language processing engine

[1488] Output: User emotion label (e.g. "tired")

[1489] What it does: Apply a pre-trained emotion recognition model (e.g., Hugging Face emotion analysis model) to extract emotion labels from text.

[1490] Step 5:

[1491] Server: Based on the identified health issues and emotion recognition results, it sends API requests to relevant applications to retrieve the latest user data.

[1492] Input: Health issue identification results and emotion recognition results

[1493] Output: Food data, exercise data, medication data (JSON format)

[1494] Specific behavior: Sends an HTTP GET request to a RESTful API endpoint to retrieve data in JSON format from the associated application.

[1495] Step 6:

[1496] Terminal: The data sent from the server is displayed to the user. If there are any errors, the user can correct them.

[1497] Input: Latest data retrieved from the server

[1498] Output: Data confirmed and corrected by the user

[1499] Specific behavior: The retrieved data is displayed on the device UI, and the user can edit it by pressing the edit button.

[1500] Step 7:

[1501] Server: Analyzes the acquired data and identifies the causes of health problems.

[1502] Input: dietary data, exercise data, medication data

[1503] Output: Cause of health problem (e.g. "Vitamin B deficiency")

[1504] Specific operation: Reads food history, exercise history, and medication history from an SQL database and cross-references and analyzes the data using Python data analysis libraries (e.g., pandas).

[1505] Step 8:

[1506] Server: Generates specific improvement proposals based on the identified factors.

[1507] Input: Contributors to health problems

[1508] Output: Suggested improvement (e.g., "I suggest you eat foods rich in vitamin B.")

[1509] What it does: Uses rule-based engines and machine learning models to generate appropriate advice from analysis results.

[1510] Step 9:

[1511] Server: Sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine.

[1512] Input: Improvement suggestions and user sentiment labels

[1513] Output: Tailored recommendations for improvement (e.g., "Try eating these foods to feel better")

[1514] What it does: Generates textual suggestions for improvement and adjusts them based on the user's emotional state.

[1515] Step 10:

[1516] Terminal: The improvement suggestions sent from the server are displayed to the user through the chatbot interface.

[1517] Input: Improvement suggestions sent from the server

[1518] Output: Improvement suggestions for user review

[1519] Specific behavior: Display the text of the improvement suggestions in the chatbot UI.

[1520] Step 11:

[1521] User: Review the proposal and enter any feedback or follow-up inquiries.

[1522] Input: Feedback on the proposal or follow-up questions

[1523] Output: Further inquiries and feedback

[1524] What happens: Enter your feedback into the chatbot interface and hit submit. For example, enter something like "This suggestion was very helpful" or "I'd like more information."

[1525] (Application example 2)

[1526] 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."

[1527] In today's busy society, proper diet, exercise, and medication management are essential for users to maintain their health in their busy daily lives. However, it is difficult to manage this data individually and investigate and improve one's own health problems in between busy schedules. Furthermore, there is a lack of systems that provide appropriate health advice and meal plans that take into account the user's emotional state. As a result, users may make incorrect health management decisions, which could lead to further health problems. To solve these problems, there is a need for a system that allows users to easily understand their health status and receive personalized improvement suggestions that take their emotional state into account.

[1528] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedial action based on the identified cause, means for notifying the user of the generated remedial action, means for recognizing the user's emotional state, and means for adjusting the proposed action based on the recognized emotional state. This allows users to receive accurate health advice and meal plans based on centralized health management data, even in the midst of a busy lifestyle. Furthermore, personalized responses that take emotional state into account are expected to increase user satisfaction and improve their health.

[1529] A "health-related message from a user" is a text message in which a user enters information about or seeks advice regarding their health condition.

[1530] "Means for analyzing messages and identifying user health problems" refers to a method or device for analyzing received messages using natural language processing technology, etc., and identifying health problems reported by users from among the messages.

[1531] The "means for obtaining data related to health issues from other applications" refers to an interface or protocol for collecting health-related data from health management applications, etc., that the user is using.

[1532] "Means for analyzing acquired data to identify the causes of health problems" refers to a method or device that analyzes collected data using techniques such as statistical analysis and machine learning to identify the root cause of a user's health problem.

[1533] The "means for generating improvement proposals based on identified factors" refers to a method or device for generating specific proposals for improving the user's health condition based on the analysis results.

[1534] The "means for notifying the user of the generated improvement proposal" refers to a notification function or interface for informing the user of the generated improvement proposal.

[1535] "Means for recognizing a user's emotional state" refers to technology or devices for analyzing and recognizing emotions from messages or other data entered by a user.

[1536] "Means for adjusting suggestions based on a recognized emotional state" refers to a method or device for adjusting the suggestions and how they are presented depending on the user's emotional state.

[1537] The "means for acquiring dietary data from a health management application" is an interface or protocol for collecting dietary data from a diet management application used by a user.

[1538] The "means for acquiring exercise data from an exercise management application" refers to an interface or protocol for collecting exercise-related data from the exercise management application used by the user.

[1539] A "means for obtaining medication data from a medication management application" is an interface or protocol for collecting data about medication use from the medication management application being used by the user.

[1540] A "service that provides food and meals based on a meal plan" is a service that delivers appropriate food and meals to a user based on a generated meal plan.

[1541] A "natural language processing engine" is software or technology used to perform semantic analysis and information extraction on text data entered by a user.

[1542] An "emotion engine" is software or technology for analyzing and recognizing a user's emotions.

[1543] This invention is a chatbot system that allows users to easily consult about their health condition. It works in conjunction with multiple health management-related applications to collect and analyze data and provide improvement suggestions that take emotional state into consideration.

[1544] System Overview

[1545] The system consists of the following main components:

[1546] User device: The device (smartphone, tablet, etc.) where the user enters health-related messages and receives feedback from the system.

[1547] Server system: A central processing unit that analyzes user input, collects relevant data, and generates analytical results. It uses natural language processing engines such as Google Cloud NLP and emotion engines such as Affectiva SDK.

[1548] Related applications: Existing applications that record health-related data (diet management apps, exercise management apps, medication management apps).

[1549] Delivery services: Services that deliver food or meals based on suggested meal plans (e.g., meal delivery service APIs).

[1550] What the program does

[1551] Receiving and Parsing User Input

[1552] Users input their health concerns using the chatbot interface. The device then sends the received message to the server, which uses Google Cloud NLP to analyze the user's message and identify the health issue being raised. The server also uses the Affectiva SDK to recognize the user's emotional state.

[1553] Data linkage and acquisition

[1554] The server retrieves data from the user's diet management app, exercise management app, and medication management app via API, and also retrieves additional data based on the results of the emotion engine.

[1555] Factor analysis and generation of improvement proposals

[1556] Using the acquired data, the server performs various statistical analyses and machine learning to identify the causes of health problems. Based on the identified causes, it generates specific improvement suggestions, such as vitamin B deficiency. It also takes into account the patient's emotional state and selects positive language.

[1557] User notification and delivery

[1558] The server generates an appropriate message to notify the user of the proposed improvements, and sends it to the device. The user can then confirm the suggestions and place an order with a delivery service if necessary.

[1559] Specific examples

[1560] 1. The user types, "I've been feeling tired lately."

[1561] 2. The server identifies "fatigue" using Google Cloud NLP and recognizes "fatigue" using the Affectiva SDK.

[1562] 3. The server retrieves the diet history data from the diet management app and analyzes vitamin B deficiency.

[1563] 4. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[1564] 5. Display the suggestions on the user's device and deliver the appropriate food using the relevant delivery service.

[1565] Prompt Sentence Examples

[1566] Example user input: "I've been feeling really tired lately. What should I eat?"

[1567] Example system output: "You may be lacking in vitamin B. Try eating foods rich in vitamin B, such as liver, fish, and eggs."

[1568] In this way, the system of the present invention comprehensively manages the user's health condition, provides appropriate health advice that also takes into account the user's emotional state, and delivers food and meals based on that advice, allowing users to efficiently improve their health even in their busy daily lives.

[1569] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1570] Step 1:

[1571] Receive health-related messages from users.

[1572] Input: A user uses the chatbot interface on their device to type a message such as, "I've been feeling really tired lately."

[1573] Specific operation: The device receives user input and sends the message to the server.

[1574] Output: The server receives the user's message.

[1575] Step 2:

[1576] Analyze messages and identify health issues.

[1577] Input: The user's message received in step 1.

[1578] How it works: The server uses Google Cloud NLP to analyze the message and identify health issues such as "fatigue."

[1579] Output: Identified health problem (e.g., fatigue).

[1580] Step 3:

[1581] Recognize the user's emotional state.

[1582] Input: The user's message received in step 1.

[1583] Specific operation: The server uses the Affectiva SDK to recognize the emotional state from messages, user facial expressions, etc.

[1584] Output: Perceived emotional state (e.g., "tired").

[1585] Step 4:

[1586] Obtaining data related to health issues from other applications.

[1587] Input: Identified health problems (Step 2) and perceived emotional states (Step 3).

[1588] Specific operation: The server calls APIs for dietary management apps, exercise management apps, medicine records, etc. to collect the latest health data.

[1589] Output: Acquired health data (dietary history, exercise history, medication history, etc.).

[1590] Step 5:

[1591] The acquired data is analyzed to identify the causes of health problems.

[1592] Input: Acquired health data (Step 4).

[1593] What it does: The server analyzes the data using statistical analysis and machine learning to identify the causes of health problems (e.g., vitamin B deficiency).

[1594] Output: Identified contributing factors to health problems.

[1595] Step 6:

[1596] Generate improvement recommendations based on the identified factors.

[1597] Input: Identified contributing factors to the health problem (Step 5).

[1598] Specific operation: The server uses the generated AI model to generate specific suggestions (e.g., consuming foods rich in vitamin B).

[1599] Output: Generated improvement suggestions.

[1600] Step 7:

[1601] Notify the user of the generated improvement suggestions.

[1602] Input: Generated improvement proposals (Step 6).

[1603] Specific operation: The server adjusts the suggestion content based on the user's emotional state, creates a notification message, and sends it to the device.

[1604] Output: The improvement suggestions sent to the user's device.

[1605] Step 8:

[1606] The user delivers based on the suggestions.

[1607] Input: The improvement proposal notified to the user's device (Step 7).

[1608] Specific behavior: The user confirms the notification message and uses the meal delivery service based on the suggested meal plan.

[1609] Output: The user's order is sent to the delivery service and the food or meal is delivered.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] [Fourth embodiment]

[1614] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1615] 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.

[1616] 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).

[1617] 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.

[1618] 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.

[1619] 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).

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] 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."

[1627] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a diet management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. The following describes an embodiment of this system.

[1628] System Overview

[1629] The system consists of the following main components:

[1630] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[1631] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[1632] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[1633] Program processing

[1634] Receiving and Parsing User Input

[1635] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[1636] Terminal: Sends received messages to the server.

[1637] Server: Uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[1638] Data linkage and acquisition

[1639] Server: After a health problem is identified, the server, with the user's consent, connects with relevant applications (diet management app, exercise management app, medication management app) and obtains the necessary data via API.

[1640] Terminal: Display the acquired data to the user and ask them to correct any errors.

[1641] Factor analysis and generation of improvement proposals

[1642] Server: Analyzes the acquired data (dietary history, exercise history, medication history) and clarifies the causes of identified health problems (e.g., fatigue).

[1643] Server: Generates specific improvement proposals based on the results of the factor analysis. For example, if a lack of vitamin B is the cause, the server generates advice such as "We suggest that you consume foods rich in vitamin B."

[1644] Notifying users and getting feedback

[1645] Server: Sends the generated improvement suggestions to the user.

[1646] On the device: Show the user suggested improvements and accept additional inquiries and feedback as needed.

[1647] Specific examples

[1648] Example 1: Dietary nutrient deficiency

[1649] 1. Terminal: The user types, "I feel tired."

[1650] 2. Server: Identify "fatigue" using a natural language processing engine.

[1651] 3. Server: Acquires food history data from the food management app.

[1652] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[1653] 5. Server: Generates an improvement suggestion: "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B (e.g., fish, chicken, beans)."

[1654] 6. Terminal: Display the suggestions to the user.

[1655] Example 2: Fatigue due to excessive exercise

[1656] 1. Device: The user types, "I've been feeling really tired lately."

[1657] 2. Server: Identify "fatigue" using a natural language processing engine.

[1658] 3. Server: Obtains exercise history data from the running app.

[1659] 4. Server: Analyzes the data and identifies hyperactivity.

[1660] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[1661] 6. Terminal: Display the suggestions to the user.

[1662] Through this system, users can receive prompt and appropriate treatment for even mild illnesses that do not require a visit to the hospital, and by linking and analyzing data, they can receive more accurate and personalized health advice.

[1663] The processing flow will be explained below.

[1664] Step 1:

[1665] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[1666] Step 2:

[1667] Terminal: Sends the entered message to the server.

[1668] Step 3:

[1669] Server: Passes the received message to a natural language processing engine for analysis. Specifically, it analyzes the context and identifies the user's health problem (in this case, "fatigue").

[1670] Step 4:

[1671] Server: Based on the identified health issue, it sends API requests to relevant applications (diet management app, exercise management app, medicine record book) to obtain the user's latest data.

[1672] Step 5:

[1673] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[1674] Step 6:

[1675] Server: Analyzes the acquired data and identifies the causes of health problems. Specifically, it analyzes the following data individually:

[1676] Dietary data: Identify nutrient deficiencies and excesses.

[1677] Exercise data: Identify over- or under-exercise.

[1678] Drug data: Identify potential health issues caused by medication side effects.

[1679] Step 7:

[1680] Server: Generates improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest eating foods rich in vitamin B" is generated.

[1681] Step 8:

[1682] Server: Sends the generated improvement suggestions to the user.

[1683] Step 9:

[1684] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[1685] Step 10:

[1686] Users: Review the proposal and provide additional inquiries or feedback as needed.

[1687] Example 1

[1688] 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."

[1689] In today's modern living environment, it is important to detect minor health problems early and take appropriate measures. However, conventional methods require users to operate health management applications individually, and collect and analyze data, which is time-consuming. In addition, integrating and analyzing data from each application is technically difficult, and some factors may be overlooked. This makes it difficult for users to quickly receive appropriate health advice.

[1690] 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.

[1691] In this invention, the server includes means for receiving health-related messages from a user, means for analyzing the messages to identify a health problem of the user, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating an improvement plan based on the identified cause, means for notifying the user of the generated improvement plan, means for displaying the acquired data to the user to encourage correction, and means for receiving user feedback based on the generated improvement plan. This eliminates the need for users to operate individual applications, and enables the centralized collection and analysis of health data to quickly receive appropriate advice.

[1692] "Health-related messages" are text data in which users write about their health status and physical condition.

[1693] A "health issue" is a specific health problem or symptom that a user is experiencing.

[1694] An "application" is a software program that users use on their smartphones or tablets to manage their health and record data.

[1695] "Data" refers to records of health information about the user, including dietary history, exercise history, medication history, etc.

[1696] "Data analysis" refers to the process of using statistical methods and algorithms based on the acquired data to extract the user's health condition and the causes of problems.

[1697] "Improvement ideas" are specific suggestions or advice for addressing identified health problems or their contributing factors.

[1698] A "natural language processing engine" is an artificial intelligence technology for analyzing text data and understanding its meaning.

[1699] "Preprocessing" refers to processing that is performed before data analysis, and includes data imputation and normalization.

[1700] "User feedback" is any additional input or reaction a user gives to advice or suggestions provided by the system.

[1701] The present invention is a chatbot system that allows users to easily consult with the system about minor health problems. The chatbot system works in conjunction with multiple health management applications to collect the user's health data, identify the causes of the problems, and provide suggestions for improvement. A specific embodiment of the system is described below.

[1702] System Configuration and Operation

[1703] Receiving and Parsing User Input

[1704] A user launches the chatbot interface using a smartphone or tablet. For example, they might input something like, "I haven't been feeling any better lately." The device receives this input and sends it to a server. The server then sends the received input to a natural language processing engine (e.g., Google Cloud Natural Language API) and analyzes the text. The natural language processing engine then identifies specific health issues, such as "feeling tired," from the user's input.

[1705] Data linkage and acquisition

[1706] After a health problem is identified, the server, with the user's consent, connects with relevant existing health management applications (e.g., dietary management apps, exercise management apps, medication management apps). The server obtains the necessary data (dietary history, exercise history, medication history) from each application via API. To improve the accuracy of the obtained data, the device displays the data to the user and prompts them to correct any omissions or errors.

[1707] Factor analysis and generation of improvement proposals

[1708] The server uses Python's Pandas library to analyze the acquired data. It preprocesses the dataset, for example, by filling in missing data and normalizing it. Next, it analyzes the diet history to check for vitamin B deficiency, exercise history to check for excessive exercise, and medication history to check for side effects. Based on the analysis results, it generates specific improvement suggestions (for example, if vitamin B is deficient, advice such as "We suggest consuming foods rich in vitamin B").

[1709] Notifying users and getting feedback

[1710] The server notifies the user of the generated improvement suggestions. The device displays the suggestions on the chatbot interface. For example, it may say, "You are deficient in vitamin B. Eat fish, chicken, and beans, which are rich in vitamin B." The user checks the suggestions and enters additional inquiries or feedback as needed. The device sends this feedback to the server, which analyzes the received feedback and generates additional advice or corrections as needed.

[1711] Specific examples

[1712] Example 1: Dietary nutrient deficiency

[1713] 1. User: Type "I'm tired" into the chatbot.

[1714] 2. Terminal: Sends input data to the server.

[1715] 3. Server: Uses a natural language processing engine to identify "fatigue."

[1716] 4. Server: Obtains meal history data using the meal management app's API.

[1717] 5. Server: Analyze the data using the Pandas library and identify vitamin B deficiencies.

[1718] 6. Server: Produces "You are deficient in Vitamin B. We suggest consuming foods rich in Vitamin B (e.g., fish, chicken, beans)."

[1719] 7. Terminal: Show this suggestion to the user.

[1720] Example 2: Fatigue due to excessive exercise

[1721] 1. User: Type into the chatbot, "I've been feeling really tired lately."

[1722] 2. Terminal: Sends input data to the server.

[1723] 3. Server: Uses a natural language processing engine to identify "fatigue."

[1724] 4. Server: Obtains exercise history data through the running app's API.

[1725] 5. Server: Analyze the data using the Pandas library to identify hyperactivity.

[1726] 6. Server: Generate "You've been exercising too much recently. We suggest you increase your rest time and adjust your exercise accordingly."

[1727] 7. Terminal: Show this suggestion to the user.

[1728] As described above, by utilizing this system, users can eliminate the need to operate individual applications, centrally collect and analyze health data, and quickly receive appropriate advice.

[1729] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1730] Step 1:

[1731] User: The user launches the chatbot interface on their smartphone or tablet, for example by typing, "I've been feeling tired lately."

[1732] Input: A health-related message (e.g., "I've been feeling tired lately").

[1733] Output: The input data is displayed on the terminal device.

[1734] Step 2:

[1735] Terminal: Sends input data to the server. Specifically, the communication module in the terminal sends message data to the server as an HTTP request.

[1736] Input: A health-related message entered by the user.

[1737] Output: A message from the user is sent to the server.

[1738] Step 3:

[1739] Server: The server sends the received message to a natural language processing engine to analyze the text, for example using the Google Cloud Natural Language API.

[1740] Input: A health-related message sent by the user.

[1741] Output: The natural language processing engine returns the health issue (e.g., "feeling tired") as the analysis result.

[1742] Step 4:

[1743] Server: After a health problem is identified, the server obtains the user's consent and connects with the relevant applications to obtain the necessary data through APIs. Specifically, it issues API requests to the diet management app, exercise management app, and medication management app.

[1744] Input: Analysis results from a natural language processing engine (e.g., "fatigue").

[1745] Output: Dietary history, exercise history, and medication history data obtained from each application.

[1746] Step 5:

[1747] Terminal: If necessary, display the acquired data to the user and prompt them to correct any deficiencies or errors. Specifically, the acquired data is temporarily saved and an interface for user confirmation is displayed.

[1748] Input: Health data obtained from each application.

[1749] Output: The data displayed to the user and the modified data (if any).

[1750] Step 6:

[1751] Server: To analyze the acquired data, we use the Python Pandas library. We preprocess the dataset (implanting missing data and normalizing it) and analyze the dietary history, exercise history, and medication history.

[1752] Input: Data obtained from each application and data modified by the user.

[1753] Output: Contributing factors to the health problem (e.g., vitamin B deficiency).

[1754] Step 7:

[1755] Server: Generates specific improvement suggestions based on the analysis results. For example, if a vitamin B deficiency is identified, the server will suggest "consuming foods rich in vitamin B."

[1756] Input: Contributors to health problems.

[1757] Output: Specific improvement suggestions.

[1758] Step 8:

[1759] Server: Notifies the user of the generated improvement suggestions. Converts the improvement suggestions into a display format for notifications and sends them to the device.

[1760] Input: Generated improvement suggestions.

[1761] Output: The improvement suggestions converted into a display format.

[1762] Step 9:

[1763] Terminal: The improvement suggestions are displayed in the chatbot interface. Specifically, the improvement suggestions are displayed as chatbot messages.

[1764] Input: The improvement suggestion sent by the server.

[1765] Output: Suggested improvements that users can see on their screen.

[1766] Step 10:

[1767] User: Review the suggested improvements and enter any additional questions or feedback as needed.

[1768] Input: User feedback on the proposed improvements.

[1769] Output: User feedback.

[1770] Step 11:

[1771] Terminal: Sends user feedback to the server. The terminal sends the input data back to the server.

[1772] Input: Additional feedback from the user.

[1773] Output: Feedback sent to the server.

[1774] Step 12:

[1775] Server: Analyzes the received feedback and generates additional advice and corrections as needed, again using a natural language processing engine.

[1776] Input: User feedback.

[1777] Output: Additional advice and suggested fixes.

[1778] These are the specific processing steps of this system. At each step, various data processing and calculations are performed based on the input data, and ultimately the optimal health advice is provided to the user. The results displayed to the user are then checked and further improvements are made as necessary.

[1779] (Application example 1)

[1780] 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."

[1781] In today's busy lifestyles, many people have little time to address minor health issues. Finding appropriate solutions is difficult, especially when diet, exercise, and medication management are factors. Furthermore, there is no system that centrally manages health data and recommends meal plans appropriate for individual health conditions. Therefore, there is a need for a system that allows users to easily obtain effective improvement measures tailored to their health condition.

[1782] 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.

[1783] In this invention, the server includes means for receiving health-related messages from users, means for analyzing the messages to identify health problems of the users, means for acquiring data related to the identified health problems from other applications, means for analyzing the acquired data to identify causes of the health problems, means for generating improvement proposals based on the identified causes, means for notifying the users of the generated improvement proposals, and means for recommending appropriate meal menus based on the users' health conditions. This allows users to centrally manage their health data and easily obtain effective dietary improvement measures suited to their individual health conditions.

[1784] "User" refers to an individual who uses the System.

[1785] "Health-related message" refers to text information entered by a user to describe their health condition or any issues they may be experiencing.

[1786] "Means for identifying a health issue" refers to a method or apparatus for analyzing a received health-related message and identifying a user's specific health issue.

[1787] "Means for acquiring data" refers to a method or device for acquiring relevant data based on the identified health problem from an external application (such as a diet management app, exercise management app, or medication management app).

[1788] "Means for identifying causes" refers to a method or device for analyzing the acquired data and clarifying the causes of the user's health problem.

[1789] "Means for generating improvement suggestions" refers to a method or device that creates specific suggestions for resolving a user's health problem based on the identified factors.

[1790] "Means for notifying users" refers to methods or devices for notifying users of generated improvement proposals or recommendations.

[1791] "Means for recommending appropriate meal menus based on health status" refers to a method or device that analyzes a user's health data and, based on the results, suggests a meal plan appropriate for the user's health status.

[1792] The term "system" refers to a mechanism in which a series of components including the above-mentioned means work together.

[1793] This invention provides a system for users to solve minor health problems, linked to a food delivery application equipped with a meal menu recommendation function. The system includes a user terminal, a cloud server, and an existing health management application. Specific embodiments are described below.

[1794] Key Components of the System

[1795] 1. User Device

[1796] Smartphone: A device where the user can input health-related messages and receive feedback from the system.

[1797] 2. Cloud Server

[1798] Server: A central processing unit that analyzes messages from users and identifies health issues, as well as retrieves and analyzes data from related apps.

[1799] Natural language processing engine (e.g., Google NLP API): Used to analyze user messages and identify specific health issues.

[1800] 3. Related Applications

[1801] Meal management app: An application that records meal history data.

[1802] Exercise management app: An application that records exercise history data.

[1803] Medication management app: An application that records medication usage history data.

[1804] Food delivery app: An application that recommends healthy meal menus based on health data and delivers them to users.

[1805] System processing overview

[1806] 1. Receiving and Parsing User Input

[1807] A user types "I've been feeling a bit tired lately" into a food delivery app chatbot, and their smartphone sends this message to a cloud server.

[1808] The cloud server uses a natural language processing engine to analyze the user's message and identify specific health issues, such as "fatigue."

[1809] 2. Data linkage and acquisition

[1810] After a health problem is identified, the cloud server connects with the diet management app, exercise management app, and medication management app to obtain the necessary data through APIs.

[1811] The smartphone displays the acquired data to the user and prompts them to make corrections if there are any errors.

[1812] 3. Factor analysis and recommendation generation

[1813] The cloud server analyzes the acquired data and identifies the cause of the user's health problem (e.g., vitamin B deficiency).

[1814] Based on the results of the factor analysis, the cloud server generates a meal menu that takes nutritional balance into consideration.

[1815] 4. User Notification and Feedback

[1816] The cloud server sends the generated menu suggestions to the user.

[1817] The smartphone displays the suggestions to the user and accepts their ratings and feedback.

[1818] Specific examples

[1819] If a user types "I've been feeling tired lately" into a food delivery app, the system will follow this flow:

[1820] 1. Input Analysis

[1821] Cloud Server: Identifying "fatigue."

[1822] 2. Data Acquisition

[1823] Cloud server: Acquires data from a dietary management app and identifies vitamin B deficiencies.

[1824] 3. Proposal generation

[1825] Cloud server: Generates the message, "You are lacking in vitamin B. We will suggest a menu using ingredients that are rich in vitamin B."

[1826] 4. User Notices

[1827] Smartphone: Suggestions are displayed to the user.

[1828] Prompt Sentence Examples

[1829] The following prompts can be used to instruct the generative AI model to proceed:

[1830] If a user types in "I've been feeling a bit tired lately," the app will identify the health issue of "fatigue" and retrieve data from related apps. It will then identify a vitamin B deficiency and suggest a menu using ingredients rich in vitamin B.

[1831] The system will enable users to easily access fast, accurate solutions to minor health issues they experience in their daily lives.

[1832] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1833] Step 1:

[1834] A user can send a health-related message to a chatbot in a food delivery app by inputting "I've been feeling a bit tired lately." The input data is in text format and is sent from the user's device to a cloud server. The input of this step is the user's message, and the output is the message sent to the cloud server.

[1835] Step 2:

[1836] The cloud server analyzes the received message using a natural language processing engine (e.g., Google NLP API). The server processes the text data and identifies specific health problems, such as "feeling tired." The input for this step is the user's message, and the output is the data on the identified health problem.

[1837] Step 3:

[1838] Based on the identified health problem, the server retrieves relevant data from the diet management app, exercise management app, and medication management app. The retrieved data includes diet history, exercise history, and medication history. Data is shared via API, and user consent is required. The input of this step is the identified health problem data, and the output is related history data.

[1839] Step 4:

[1840] The cloud server analyzes and processes the acquired historical data. It checks the intake of vitamin B in the dietary history and analyzes the exercise history to check for excessive exercise. The input of this step is the acquired historical data, and the output is the specific factors that cause health problems.

[1841] Step 5:

[1842] After the factors are identified, the cloud server generates improvement suggestions and meal menu recommendations based on the user's health condition. For example, if a user is deficient in vitamin B, it will suggest a menu using ingredients rich in vitamin B. The input of this step is the identified factors of the health problem, and the output is improvement suggestions and recommendations.

[1843] Step 6:

[1844] The cloud server notifies the user device of the generated improvement plan and meal recommendation. The notified content is displayed to the user through the chatbot interface. The input of this step is the generated improvement plan and recommendation, and the output is a notification to the user.

[1845] Step 7:

[1846] The user checks the notified improvement proposals and meal recommendations, and provides an evaluation and feedback. This feedback is sent back to the cloud server and used to improve the accuracy of the system. The input of this step is the user's feedback, and the output is the feedback sent to the cloud server.

[1847] Specific examples

[1848] If a user types "I've been feeling tired lately" into a food delivery app, here's what the system will flow:

[1849] 1. Input Reception

[1850] User device: Type "I've been feeling a bit tired lately" and send it to the cloud server.

[1851] 2. Input Analysis

[1852] Cloud server: Identifies "fatigue" using a natural language processing engine.

[1853] 3. Data Acquisition

[1854] Cloud server: Collects data from dietary management apps and identifies vitamin B deficiencies.

[1855] 4. Factor analysis

[1856] Cloud server: Data analysis identifies vitamin B deficiency and excessive exercise.

[1857] 5. Proposal generation

[1858] Cloud server: Generates a menu using ingredients rich in vitamin B, saying, "You are lacking vitamin B."

[1859] 6. User Notices

[1860] User device: Display the proposal.

[1861] 7. Get feedback

[1862] User device: Send feedback on suggested improvements.

[1863] 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.

[1864] The present invention is a chatbot system that allows users to easily consult about minor health issues. It works in conjunction with a medicine notebook, a dietary management app, and a running app to collect the user's health data, identify the cause of the problem, and provide suggestions for improvement. Furthermore, by combining the present invention with an emotion engine that recognizes the user's emotions, it is possible to provide more sophisticated and user-friendly responses. An embodiment of this system is described below.

[1865] System Overview

[1866] The system consists of the following main components:

[1867] User device: The device (smartphone, tablet, etc.) where the user inputs health issues and receives feedback from the system.

[1868] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analytical results.

[1869] Related applications (diet management apps, exercise management apps, medication management apps): Existing applications that record various health-related data

[1870] Emotion engine: Combined with natural language processing, it recognizes user emotions and adjusts responses and data acquisition.

[1871] Program processing

[1872] Receiving and Parsing User Input

[1873] On the device: The user uses the chatbot interface to input a health-related message, such as "I've been feeling tired lately."

[1874] Terminal: Sends received messages to the server.

[1875] Server: Uses a natural language processing engine to analyze user messages and identify specific health issues, such as "feeling tired," and an emotion engine to recognize the user's emotions in the messages.

[1876] Data linkage and acquisition

[1877] Server: Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management apps, exercise management apps, medicine notebooks) to obtain the user's latest data. For example, if the user is feeling very stressed, the server also obtains additional data related to stress reduction.

[1878] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[1879] Factor analysis and generation of improvement proposals

[1880] Server: Analyzes the acquired data (dietary history, exercise history, medication history) to identify the causes of health problems. It also performs analysis taking into account the results of the emotion engine. For example, if the user is feeling stressed, it will analyze stress-related factors as well.

[1881] Server: Generates specific improvement proposals based on the results of factor analysis. For example, if a vitamin B deficiency is identified, specific advice such as "We suggest consuming foods rich in vitamin B" is generated.

[1882] Notifying users and getting feedback

[1883] Server: Sends the generated improvement suggestions to the user. Based on the results of the emotion engine, the suggestion content is also adjusted. For example, if the user tends to feel depressed, the suggestion will be given more gentle and encouraging language.

[1884] Terminal: Show improvement suggestions to the user through a chatbot interface.

[1885] Users: Review the proposal and provide additional inquiries or feedback as needed.

[1886] Specific examples

[1887] Example 1: Dietary nutrient deficiency

[1888] 1. Terminal: The user types, "I feel tired."

[1889] 2. Server: Identify "fatigue" using a natural language processing engine and recognize the emotion of "fatigue" using an emotion engine.

[1890] 3. Server: Acquires food history data from the food management app.

[1891] 4. Server: Analyzes data and identifies vitamin B deficiencies.

[1892] 5. Server: Generates an improvement suggestion such as, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[1893] 6. Terminal: Display the suggestions to the user.

[1894] Example 2: Fatigue due to excessive exercise

[1895] 1. Device: The user types, "I've been feeling really tired lately."

[1896] 2. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[1897] 3. Server: Obtains exercise history data from the running app.

[1898] 4. Server: Analyzes the data and identifies hyperactivity.

[1899] 5. Server: Generates an improvement suggestion: "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[1900] 6. Terminal: Display the suggestions to the user.

[1901] Benefits of adding an emotion engine

[1902] The introduction of an emotion engine makes it possible to respond to users' emotional states and provide more personalized services. For example, if a user is feeling stressed, the system can provide suggestions for relaxation techniques and advice on how to deal with stress. In this way, emotion recognition can enable more accurate healthcare advice.

[1903] The processing flow will be explained below.

[1904] Step 1:

[1905] On the device: The user types a health-related message (e.g., "I've been feeling tired lately") into the chatbot interface.

[1906] Step 2:

[1907] Terminal: Sends the entered message to the server.

[1908] Step 3:

[1909] Server: The received message is passed to a natural language processing engine for analysis. Specifically, the context is analyzed to identify the user's health issue (in this case, "fatigue"). The emotion engine is also used to identify the user's emotion from the message. For example, if the user types "tired," the emotion engine will identify the emotion as "fatigue."

[1910] Step 4:

[1911] Server: Taking into account the emotion recognition results from the emotion engine, the server sends an API request to obtain data related to the user's health issues from related applications (diet management app, exercise management app, medicine record). For example, if the user is feeling "fatigue" or "stressed," the server obtains data related to stress reduction in addition to their diet history and exercise history.

[1912] Step 5:

[1913] Terminal: The acquired data is displayed to the user, and if there are any errors, the user can correct them.

[1914] Step 6:

[1915] Server: Analyzes the acquired data and identifies specific factors that contribute to health problems. For example:

[1916] Dietary data: Identify nutrient deficiencies and excesses.

[1917] Exercise data: Identify over- or under-exercise.

[1918] Drug data: Identify potential health problems caused by medication side effects.

[1919] It also takes into account the results of the emotion engine to analyze factors related to stress and emotional ups and downs.

[1920] Step 7:

[1921] Server: Generates specific improvement suggestions based on the results of data analysis. For example, if a vitamin B deficiency is found, specific advice such as "We suggest consuming foods rich in vitamin B" is generated. Furthermore, depending on the results of the emotion engine, the suggestion content is adjusted to suit the user's emotions. For example, if the user is feeling very stressed, advice on relaxation techniques and mental care will be included.

[1922] Step 8:

[1923] Server: Sends the generated improvement suggestions to the user.

[1924] Step 9:

[1925] Terminal: Improvement suggestions are presented to the user through a chatbot interface.

[1926] Step 10:

[1927] Users: Review the proposal and provide additional inquiries or feedback as needed.

[1928] Specific examples

[1929] Example 1: Dietary nutrient deficiency

[1930] 1. Terminal: The user types, "I feel tired."

[1931] 2. Terminal: Sends the entered message to the server.

[1932] 3. Server: Identify "fatigue" using a natural language processing engine and recognize "fatigue emotion" using an emotion engine.

[1933] 4. Server: Obtains food history data from the food management app.

[1934] 5. Device: Displays the acquired meal data to the user and allows them to correct any errors.

[1935] 6. Server: Analyze the data and identify vitamin B deficiencies.

[1936] 7. Server: Create a specific improvement suggestion, such as "You are lacking in vitamin B. We suggest that you eat foods that are rich in vitamin B (e.g., fish, chicken, beans)." Because the user's emotion is "fatigue," include gentle, encouraging words.

[1937] 8. Server: Sends improvement suggestions to the user.

[1938] 9. Terminal: Display the suggestions to the user.

[1939] 10. User: Review the proposal and make any further enquiries as necessary.

[1940] Example 2: Fatigue due to excessive exercise

[1941] 1. Device: The user types, "I've been feeling really tired lately."

[1942] 2. Terminal: Sends the entered message to the server.

[1943] 3. Server: Identify the feeling of "fatigue" using a natural language processing engine and recognize the feeling of "irritation" using an emotion engine.

[1944] 4. Server: Obtains exercise history data from the running app.

[1945] 5. Device: Displays the acquired exercise data to the user and allows them to correct any errors.

[1946] 6. Server: Analyzes data and identifies hyperactivity.

[1947] 7. Server: Create a specific improvement suggestion, such as, "It seems you've been exercising too much recently. We suggest that you increase your rest time and adjust your exercise appropriately." Because the user's emotion is "irritation," include gentle words encouraging relaxation.

[1948] 8. Server: Sends improvement suggestions to the user.

[1949] 9. Terminal: Display the suggestions to the user.

[1950] 10. User: Review the proposal and make any further enquiries as necessary.

[1951] The addition of an emotion engine allows responses to be made that take into account the user's emotional state, enabling more precise and user-friendly responses.

[1952] Example 2

[1953] 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."

[1954] In modern society, users face a wide range of health problems, requiring prompt and accurate responses. However, conventional systems do not adequately take into account the user's emotional state, making it difficult to provide personalized advice. Furthermore, when linking data from multiple health management applications, the integration and analysis of that data is cumbersome, making it difficult for users to use.

[1955] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedy based on the identified cause, means for notifying the user of the generated remedy, and means for recognizing the user's emotions and adjusting the response content and data acquisition. This enables a more sophisticated and user-friendly response that takes the user's emotional state into consideration.

[1956] "Health-related messages from users" are text data of health-related questions or inquiries entered by users through the chatbot interface.

[1957] "Means for analyzing messages to identify a user's health issue" refers to the process of using a natural language processing engine to identify the type and specific content of a health issue from a received text message.

[1958] "Means for obtaining data related to the identified health problem from other applications" refers to the process of obtaining data from the diet management application, exercise management application, and medication management application to collect information related to the user's health problem.

[1959] "Means for analyzing acquired data to identify the causes of health problems" refers to the process of analyzing data to identify the root cause of a user's health problem based on the collected data.

[1960] "Means for generating improvement proposals based on identified factors" refers to the process of generating specific measures and advice for identified causes.

[1961] "Means of notifying users of generated improvement suggestions" refers to the process of communicating the generated advice and measures to users through the chatbot interface.

[1962] "Means for recognizing user emotions and adjusting response content and data acquisition" refers to the process of identifying emotions from a user's text message and adjusting appropriate responses and data acquisition based on those emotions.

[1963] This invention is a chatbot system that allows users to easily consult about minor health issues. This system works in conjunction with the user's various health management applications (diet management app, exercise management app, medication management app) to collect and analyze the user's health status as data. Furthermore, by combining it with an emotion engine, it responds according to the user's emotions. The following describes in detail the modes for implementing the present invention.

[1964] System configuration

[1965] The system consists of the following main components:

[1966] User device: A device where the user inputs health issues and receives feedback from the system (e.g., smartphone, tablet).

[1967] Server System: A central processing unit that analyzes user input, collects relevant data, and generates analysis results and improvement suggestions.

[1968] Related applications: Existing applications that record various health-related data, such as diet management apps, exercise management apps, and medication management apps.

[1969] Emotion engine: Combined with natural language processing, this engine recognizes user emotions and adjusts response content and data acquisition.

[1970] Processing flow

[1971] 1. Receiving and Parsing User Input

[1972] Using the chatbot interface, users can input content such as "I've been feeling tired lately," and the device will then send this message to the server.

[1973] The server analyzes the received message using a natural language processing engine (e.g., spaCy or BERT) to identify health issues such as "fatigue," and then uses an emotion engine to recognize the user's emotion (e.g., "tired") in the message.

[1974] 2. Data linkage and acquisition

[1975] Based on the identified health issues and the recognition results of the emotion engine, the server sends API requests to related applications (diet management app, exercise management app, medication management app) to obtain the user's latest data.

[1976] The terminal displays the acquired data to the user, and if there are any errors, the user can correct them.

[1977] 3. Factor analysis and generation of improvement proposals

[1978] The server analyzes the acquired data and identifies the cause of the health problem. For example, if the cause is a vitamin B deficiency, it will identify it as "vitamin B deficiency."

[1979] The server generates specific improvement suggestions based on the identified factors, such as "You are lacking in vitamin B. We suggest that you consume foods rich in vitamin B."

[1980] 4. Notifying users and getting feedback

[1981] The server sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine, for example, choosing words that are kind and encouraging if the user is feeling down.

[1982] The device will display suggested improvements to the user, allowing the user to provide additional inquiries or feedback.

[1983] Specific examples

[1984] Example 1: Dietary nutrient deficiency

[1985] 1. The user types, "I feel tired."

[1986] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "fatigue."

[1987] 3. The server retrieves the meal history data from the meal management app.

[1988] 4. The server analyzes the data and identifies vitamin B deficiencies.

[1989] 5. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[1990] 6. The device displays the suggestions to the user.

[1991] Example 2: Fatigue due to excessive exercise

[1992] 1. The user types, "I've been feeling really tired lately."

[1993] 2. The server uses a natural language processing engine to identify "fatigue" and an emotion engine to recognize "irritation."

[1994] 3. The server obtains exercise history data from the exercise management app.

[1995] 4. The server analyzes the data and identifies excessive exercise.

[1996] 5. The server generates an improvement suggestion saying, "It seems you've been exercising too much recently. We suggest you increase your rest time and adjust your exercise volume appropriately."

[1997] 6. The device displays the suggestions to the user.

[1998] As described above, this invention is a system that quickly and accurately analyzes a user's health problems and provides specific improvement proposals based on data. By using an emotion engine in combination, it realizes customized responses according to the user's emotional state.

[1999] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2000] Step 1:

[2001] User: Enters a health-related message into the chatbot interface. For example, "I've been feeling really tired lately."

[2002] Input: User's text message

[2003] Output: Text data sent to the terminal

[2004] Specific actions: The user enters text into the chatbot interface on their smartphone and presses the send button.

[2005] Step 2:

[2006] Terminal: Sends received messages to the server.

[2007] Input: Text data entered by the user

[2008] Output: Text data sent to the server

[2009] Specific operation: Text data is sent to the server via an HTTP request via the terminal's network module.

[2010] Step 3:

[2011] Server: Passes the received message to the natural language processing engine for analysis.

[2012] Input: Text data sent from the terminal

[2013] Output: Health issue identification results and emotion recognition results

[2014] What it does: It uses an NLP engine built in Python (e.g., spaCy or BERT) to tokenize text messages and identify health issues and sentiment.

[2015] Step 4:

[2016] Server: Uses an emotion engine to recognize user emotions from messages.

[2017] Input: Analysis results of the natural language processing engine

[2018] Output: User emotion label (e.g. "tired")

[2019] What it does: Apply a pre-trained emotion recognition model (e.g., Hugging Face emotion analysis model) to extract emotion labels from text.

[2020] Step 5:

[2021] Server: Based on the identified health issues and emotion recognition results, it sends API requests to relevant applications to retrieve the latest user data.

[2022] Input: Health issue identification results and emotion recognition results

[2023] Output: Food data, exercise data, medication data (JSON format)

[2024] Specific behavior: Sends an HTTP GET request to a RESTful API endpoint to retrieve data in JSON format from the associated application.

[2025] Step 6:

[2026] Terminal: The data sent from the server is displayed to the user. If there are any errors, the user can correct them.

[2027] Input: Latest data retrieved from the server

[2028] Output: Data confirmed and corrected by the user

[2029] Specific behavior: The retrieved data is displayed on the device UI, and the user can edit it by pressing the edit button.

[2030] Step 7:

[2031] Server: Analyzes the acquired data and identifies the causes of health problems.

[2032] Input: dietary data, exercise data, medication data

[2033] Output: Cause of health problem (e.g. "Vitamin B deficiency")

[2034] Specific operation: Reads food history, exercise history, and medication history from an SQL database and cross-references and analyzes the data using Python data analysis libraries (e.g., pandas).

[2035] Step 8:

[2036] Server: Generates specific improvement proposals based on the identified factors.

[2037] Input: Contributors to health problems

[2038] Output: Suggested improvement (e.g., "I suggest you eat foods rich in vitamin B.")

[2039] What it does: Uses rule-based engines and machine learning models to generate appropriate advice from analysis results.

[2040] Step 9:

[2041] Server: Sends the generated improvement suggestions to the user and adjusts the suggestions based on the results of the emotion engine.

[2042] Input: Improvement suggestions and user sentiment labels

[2043] Output: Tailored recommendations for improvement (e.g., "Try eating these foods to feel better")

[2044] What it does: Generates textual suggestions for improvement and adjusts them based on the user's emotional state.

[2045] Step 10:

[2046] Terminal: The improvement suggestions sent from the server are displayed to the user through the chatbot interface.

[2047] Input: Improvement suggestions sent from the server

[2048] Output: Improvement suggestions for user review

[2049] Specific behavior: Display the text of the improvement suggestions in the chatbot UI.

[2050] Step 11:

[2051] User: Review the proposal and enter any feedback or follow-up inquiries.

[2052] Input: Feedback on the proposal or follow-up questions

[2053] Output: Further inquiries and feedback

[2054] What happens: Enter your feedback into the chatbot interface and hit submit. For example, enter something like "This suggestion was very helpful" or "I'd like more information."

[2055] (Application example 2)

[2056] 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."

[2057] In today's busy society, proper diet, exercise, and medication management are essential for users to maintain their health in their busy daily lives. However, it is difficult to manage this data individually and investigate and improve one's own health problems in between busy schedules. Furthermore, there is a lack of systems that provide appropriate health advice and meal plans that take into account the user's emotional state. As a result, users may make incorrect health management decisions, which could lead to further health problems. To solve these problems, there is a need for a system that allows users to easily understand their health status and receive personalized improvement suggestions that take their emotional state into account.

[2058] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a health-related message from a user, means for analyzing the message to identify the user's health problem, means for acquiring data related to the identified health problem from another application, means for analyzing the acquired data to identify the cause of the health problem, means for generating a remedial action based on the identified cause, means for notifying the user of the generated remedial action, means for recognizing the user's emotional state, and means for adjusting the proposed action based on the recognized emotional state. This allows users to receive accurate health advice and meal plans based on centralized health management data, even in the midst of a busy lifestyle. Furthermore, personalized responses that take emotional state into account are expected to increase user satisfaction and improve their health.

[2059] A "health-related message from a user" is a text message in which a user enters information about or seeks advice regarding their health condition.

[2060] "Means for analyzing messages and identifying user health problems" refers to a method or device for analyzing received messages using natural language processing technology, etc., and identifying health problems reported by users from among the messages.

[2061] The "means for obtaining data related to health issues from other applications" refers to an interface or protocol for collecting health-related data from health management applications, etc., that the user is using.

[2062] "Means for analyzing acquired data to identify the causes of health problems" refers to a method or device that analyzes collected data using techniques such as statistical analysis and machine learning to identify the root cause of a user's health problem.

[2063] The "means for generating improvement proposals based on identified factors" refers to a method or device for generating specific proposals for improving the user's health condition based on the analysis results.

[2064] The "means for notifying the user of the generated improvement proposal" refers to a notification function or interface for informing the user of the generated improvement proposal.

[2065] "Means for recognizing a user's emotional state" refers to technology or devices for analyzing and recognizing emotions from messages or other data entered by a user.

[2066] "Means for adjusting suggestions based on a recognized emotional state" refers to a method or device for adjusting the suggestions and how they are presented depending on the user's emotional state.

[2067] The "means for acquiring dietary data from a health management application" is an interface or protocol for collecting dietary data from a diet management application used by a user.

[2068] The "means for acquiring exercise data from an exercise management application" refers to an interface or protocol for collecting exercise-related data from the exercise management application used by the user.

[2069] A "means for obtaining medication data from a medication management application" is an interface or protocol for collecting data about medication use from the medication management application being used by the user.

[2070] A "service that provides food and meals based on a meal plan" is a service that delivers appropriate food and meals to a user based on a generated meal plan.

[2071] A "natural language processing engine" is software or technology used to perform semantic analysis and information extraction on text data entered by a user.

[2072] An "emotion engine" is software or technology for analyzing and recognizing a user's emotions.

[2073] This invention is a chatbot system that allows users to easily consult about their health condition. It works in conjunction with multiple health management-related applications to collect and analyze data and provide improvement suggestions that take emotional state into consideration.

[2074] System Overview

[2075] The system consists of the following main components:

[2076] User device: The device (smartphone, tablet, etc.) where the user enters health-related messages and receives feedback from the system.

[2077] Server system: A central processing unit that analyzes user input, collects relevant data, and generates analytical results. It uses natural language processing engines such as Google Cloud NLP and emotion engines such as Affectiva SDK.

[2078] Related applications: Existing applications that record health-related data (diet management apps, exercise management apps, medication management apps).

[2079] Delivery services: Services that deliver food or meals based on suggested meal plans (e.g., meal delivery service APIs).

[2080] What the program does

[2081] Receiving and Parsing User Input

[2082] Users input their health concerns using the chatbot interface. The device then sends the received message to the server, which uses Google Cloud NLP to analyze the user's message and identify the health issue being raised. The server also uses the Affectiva SDK to recognize the user's emotional state.

[2083] Data linkage and acquisition

[2084] The server retrieves data from the user's diet management app, exercise management app, and medication management app via API, and also retrieves additional data based on the results of the emotion engine.

[2085] Factor analysis and generation of improvement proposals

[2086] Using the acquired data, the server performs various statistical analyses and machine learning to identify the causes of health problems. Based on the identified causes, it generates specific improvement suggestions, such as vitamin B deficiency. It also takes into account the patient's emotional state and selects positive language.

[2087] User notification and delivery

[2088] The server generates an appropriate message to notify the user of the proposed improvements, and sends it to the device. The user can then confirm the suggestions and place an order with a delivery service if necessary.

[2089] Specific examples

[2090] 1. The user types, "I've been feeling tired lately."

[2091] 2. The server identifies "fatigue" using Google Cloud NLP and recognizes "fatigue" using the Affectiva SDK.

[2092] 3. The server retrieves the diet history data from the diet management app and analyzes vitamin B deficiency.

[2093] 4. The server generates an improvement suggestion, saying, "You are lacking in vitamin B. We suggest that you consume foods that are rich in vitamin B."

[2094] 5. Display the suggestions on the user's device and deliver the appropriate food using the relevant delivery service.

[2095] Prompt Sentence Examples

[2096] Example user input: "I've been feeling really tired lately. What should I eat?"

[2097] Example system output: "You may be lacking in vitamin B. Try eating foods rich in vitamin B, such as liver, fish, and eggs."

[2098] In this way, the system of the present invention comprehensively manages the user's health condition, provides appropriate health advice that also takes into account the user's emotional state, and delivers food and meals based on that advice, allowing users to efficiently improve their health even in their busy daily lives.

[2099] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2100] Step 1:

[2101] Receive health-related messages from users.

[2102] Input: A user uses the chatbot interface on their device to type a message such as, "I've been feeling really tired lately."

[2103] Specific operation: The device receives user input and sends the message to the server.

[2104] Output: The server receives the user's message.

[2105] Step 2:

[2106] Analyze messages and identify health issues.

[2107] Input: The user's message received in step 1.

[2108] How it works: The server uses Google Cloud NLP to analyze the message and identify health issues such as "fatigue."

[2109] Output: Identified health problem (e.g., fatigue).

[2110] Step 3:

[2111] Recognize the user's emotional state.

[2112] Input: The user's message received in step 1.

[2113] Specific operation: The server uses the Affectiva SDK to recognize the emotional state from messages, user facial expressions, etc.

[2114] Output: Perceived emotional state (e.g., "tired").

[2115] Step 4:

[2116] Obtaining data related to health issues from other applications.

[2117] Input: Identified health problems (Step 2) and perceived emotional states (Step 3).

[2118] Specific operation: The server calls APIs for dietary management apps, exercise management apps, medicine records, etc. to collect the latest health data.

[2119] Output: Acquired health data (dietary history, exercise history, medication history, etc.).

[2120] Step 5:

[2121] The acquired data is analyzed to identify the causes of health problems.

[2122] Input: Acquired health data (Step 4).

[2123] What it does: The server analyzes the data using statistical analysis and machine learning to identify the causes of health problems (e.g., vitamin B deficiency).

[2124] Output: Identified contributing factors to health problems.

[2125] Step 6:

[2126] Generate improvement recommendations based on the identified factors.

[2127] Input: Identified contributing factors to the health problem (Step 5).

[2128] Specific operation: The server uses the generated AI model to generate specific suggestions (e.g., consuming foods rich in vitamin B).

[2129] Output: Generated improvement suggestions.

[2130] Step 7:

[2131] Notify the user of the generated improvement suggestions.

[2132] Input: Generated improvement proposals (Step 6).

[2133] Specific operation: The server adjusts the suggestion content based on the user's emotional state, creates a notification message, and sends it to the device.

[2134] Output: The improvement suggestions sent to the user's device.

[2135] Step 8:

[2136] The user delivers based on the suggestions.

[2137] Input: The improvement proposal notified to the user's device (Step 7).

[2138] Specific behavior: The user confirms the notification message and uses the meal delivery service based on the suggested meal plan.

[2139] Output: The user's order is sent to the delivery service and the food or meal is delivered.

[2140] 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.

[2141] 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.

[2142] 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.

[2143] 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.

[2144] 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.

[2145] 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.

[2146] 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).

[2147] 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.

[2148] 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."

[2149] 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.

[2150] 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).

[2151] 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.

[2152] 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.

[2153] 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.

[2154] 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.

[2155] 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.

[2156] 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.

[2157] 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.

[2158] 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.

[2159] 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 d...

Claims

1. a means for receiving health-related messages from users; means for analyzing the message to identify a health problem of the user; a means for obtaining data related to the identified health problem from other applications; A means of analyzing the acquired data to identify the causes of health problems; a means for generating improvement recommendations based on the identified factors; a means for notifying the user of the generated improvement suggestions; A system including:

2. A means for acquiring dietary data from a health management application; means for obtaining exercise data from an exercise management application; a means for obtaining medication data from a medication management application; The system of claim 1 further comprising:

3. 2. The system of claim 1, wherein the analyzing means includes means for analyzing the user's message using a natural language processing engine.

Images