System

Abstract

A system is provided.SOLUTION: A system including means for acquiring basic information of a user, means for initializing a generative AI model, means for initiating a AI with the user using the generative dialog model, means for analyzing an input of the user and generating a question or a rehabilitation menu that elicits a motivation, means for providing the generated rehabilitation menu to the user, and means for adjusting a next rehabilitation plan based on feedback from the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Among elderly people who require assistance or care, many find it difficult to maintain motivation for rehabilitation, or do not even understand the need for rehabilitation. This situation leads to a decline in their quality of life (QOL) and activities of daily living (ADL), which in turn leads to social problems such as increased social insurance premiums and reduced tax revenues. Furthermore, existing rehabilitation support systems lack the ability to provide personalized support tailored to each individual elderly person, making it difficult for elderly people to continue rehabilitation. [Means for solving the problem]

[0005] To address the above-mentioned challenges, the present invention provides a system for improving the motivation of elderly people to undergo rehabilitation through dialogue with them using a generative AI model. The system includes a means for acquiring basic user information, a means for initializing a generative AI model, a means for initiating a dialogue with the user using the generative AI model, a means for analyzing the user's input and generating motivational questions and rehabilitation menus, a means for providing the generated rehabilitation menu to the user, and a means for adjusting the next rehabilitation plan based on user feedback. The system also features a means for tuning the generative AI model to realize a dialogue that deepens the user's self-understanding by digging deeper into the problem rather than providing easy answers, and a rehabilitation menu that is personalized based on the user's health condition and rehabilitation goals. This allows elderly people to continue rehabilitation with a sense of satisfaction, which is expected to maintain and improve their quality of life and activities of daily living (ADL).

[0006] "Users" refer to elderly people who require assistance or nursing care and who undergo rehabilitation using the generative AI system.

[0007] "Basic information" refers to information necessary for the system to personalize the rehabilitation menu, such as the user's name, age, health condition, and rehabilitation goals.

[0008] A "generative AI model" refers to an artificial intelligence model that interacts with users and generates questions and rehabilitation menus to increase their motivation for rehabilitation.

[0009] "Initial settings" refers to the settings that the generative AI model makes to generate a rehabilitation menu appropriate for each individual user based on the user's basic information.

[0010] "Dialogue" refers to communication between a user and an artificial intelligence using a generative AI model.

[0011] "Input" refers to information that the user provides to the system via a terminal about the progress of rehabilitation and their feelings.

[0012] "Analysis" refers to the process by which the generative AI model analyzes the user's input and generates appropriate questions and rehabilitation menus.

[0013] "Questions" refer to the questions that the generative AI model asks to motivate the user.

[0014] The "rehabilitation menu" refers to the specific rehabilitation content that the user will undergo, and is generated by the generative AI model based on the user's health condition and rehabilitation goals.

[0015] "Providing" refers to the act of presenting the rehabilitation menu and questions generated by the generative AI model to the user.

[0016] "Feedback" refers to information that a user reports to the system about their impressions and results after implementing a rehabilitation menu.

[0017] "Adjustment" refers to the process by which the generative AI model modifies and updates the next rehabilitation plan based on user feedback.

[0018] "Personalization" refers to customizing the rehabilitation menu and questions according to the user's individual health condition and rehabilitation goals.

[0019] "Tuning" refers to the adjustments that generative AI models are made to in advance to enable effective dialogue.

[0020] "Deep dive" refers to the process in which a generative AI model avoids superficial answers in dialogue with a user and asks deeper questions to help the user deepen their self-understanding. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] Hereinafter, an embodiment of the present invention will be described.

[0043] This invention is a system that uses generative AI models to promote rehabilitation for elderly people. Specifically, it consists of the following elements:

[0044] 1. Enter your user data:

[0045] The terminal provides an interface for acquiring basic information about the user (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and their rehabilitation goal is to be able to play in the park with their grandchildren, they would input this information.

[0046] 2. Initial setup of the generative AI model:

[0047] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals and health status, preparing the system to generate the optimal rehabilitation menu for each individual user.

[0048] 3. Initiating dialogue and proposing rehabilitation options:

[0049] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Then, based on the user's answer (e.g., "My lower back hurts a little today"), the generative AI model suggests an appropriate rehabilitation menu. The rehabilitation menu suggested might be something like, "If you have lower back pain, start with some short stretches without overdoing it. What do you think?"

[0050] 4. Ongoing rehabilitation support:

[0051] The user performs the proposed rehabilitation program and inputs the results and feedback to the server via their device. For example, the user might say, "I felt a little better after doing some short stretches." Based on this information, the generative AI model adjusts the next rehabilitation plan and provides ongoing support.

[0052] As a concrete example, let's say there is a 75-year-old female user (let's call her Tanaka). Tanaka's goal is to relieve her lower back pain. Tanaka operates the device to input basic information, and the generative AI model performs initial settings based on her information. In the first dialogue, Tanaka inputs, "My lower back hurts a little today." The generative AI model analyzes this and suggests, "If you have lower back pain, try doing five minutes of stretching." Tanaka follows this suggestion, performs the stretches, and provides feedback that, as a result, "I feel a little better." The server receives this feedback, adjusts the next rehabilitation plan, and continues to provide Tanaka with a continuous rehabilitation menu.

[0053] In this way, a personalized rehabilitation menu tailored to each user's needs is generated, and the generation AI asks in-depth questions to ensure a satisfactory rehabilitation experience. This system is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The terminal provides an interface for inputting basic user information (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, a 75-year-old senior citizen inputs their rehabilitation goal of "being able to play in the park with their grandchildren" and their health condition of lower back pain.

[0057] Step 2:

[0058] The server initializes the generative AI model based on the input user data. This initial setting takes into account the user's rehabilitation goals and health status, and helps generate a personalized rehabilitation menu.

[0059] Step 3:

[0060] Through the device, the generative AI model begins a dialogue with the user, starting with general exchanges such as greetings and checking in on how you're feeling. For example, the model might ask questions like, "Hello, how are you?"

[0061] Step 4:

[0062] The user responds to questions posed by the generative AI model, for example, by typing, "My back hurts a little today."

[0063] Step 5:

[0064] The server analyzes user input in real time. The generative AI model generates motivational questions and rehabilitation menus based on the user's input. For example, it might generate a menu that suggests, "If you have lower back pain, try doing some short stretches without straining yourself."

[0065] Step 6:

[0066] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[0067] Step 7:

[0068] The user carries out the proposed rehabilitation program and provides feedback on the results to the server via the terminal, for example, by inputting something like, "I did a short stretch and felt a little better."

[0069] Step 8:

[0070] The server adjusts the next rehabilitation plan based on the user's feedback. The generative AI model takes the new feedback into account and generates the next rehabilitation menu and motivational questions. This loop enables continuous rehabilitation support.

[0071] Example 1

[0072] 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."

[0073] Rehabilitation for elderly people requires personalization based on each individual's health condition and rehabilitation goals, while continuity is also important. However, conventional rehabilitation systems and programs are unable to flexibly respond to individual needs, making it difficult for users to maintain their motivation. Furthermore, they lack the functionality to continuously adjust the next rehabilitation plan based on user feedback, making it difficult to achieve effective rehabilitation.

[0074] 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.

[0075] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for starting a dialogue with the user using the generative AI model, means for analyzing the user's input and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, means for adjusting the next rehabilitation plan based on feedback from the user, and means for transmitting feedback to the server via the terminal. This makes it possible to provide an individually customized rehabilitation menu, thereby enabling users to maintain their motivation and achieve effective rehabilitation.

[0076] "Means for obtaining basic user information" refers to equipment or software for inputting and collecting personal information such as the user's age, health condition, and rehabilitation goals.

[0077] The "means for initializing the generative AI model" refers to the process of customizing the generative AI model based on the collected basic information of the user and performing initial settings to generate an individual rehabilitation menu.

[0078] "Means for initiating a dialogue with a user using a generative AI model" refers to a function for initiating an interactive dialogue with a user using a generative AI model and checking the user's situation and state.

[0079] The "means for analyzing user input and generating motivational questions and rehabilitation menus" refers to a process for analyzing the current situation and condition input by the user and generating motivational questions and individually customized rehabilitation menus based on the results.

[0080] "Means for providing the generated rehabilitation menu to the user" refers to a function that displays the rehabilitation menu created by the generative AI model in a visible form to the user and encourages them to carry it out.

[0081] "Means for adjusting the next rehabilitation plan based on user feedback" refers to the process of collecting and analyzing the results and impressions of the user's rehabilitation, and then adjusting the next rehabilitation menu and plan based on that information.

[0082] The "means for transmitting feedback to the server via the terminal" is a function that allows the user to use the terminal to input the results of the rehabilitation menu implementation and feedback, and transmit this to the server.

[0083] A "generative AI model" is a model that uses artificial intelligence technology to generate rehabilitation menus and dialogues that meet the individual needs of each user.

[0084] A "rehabilitation menu" is a specific exercise and training plan proposed for the user to undergo rehabilitation.

[0085] "Feedback" is information about the rehabilitation results, such as the user's impressions after completing the rehabilitation menu and changes in physical condition.

[0086] The following describes an embodiment of the present invention. The present invention is a system that promotes rehabilitation for elderly people by using a generative AI model. Specifically, it is composed of the following elements:

[0087] Entering User Data

[0088] The device provides an interface for acquiring basic information about the user. This interface is displayed on a computer, tablet, or smartphone (Windows, iOS, Android, etc.). The user enters their own information through this interface. For example, information such as name, age, health condition, and rehabilitation goals may be entered. As a specific example, a 75-year-old user may enter "back pain" and the rehabilitation goal of "being able to play in the park with my grandchildren."

[0089] Initial setup of generative AI models

[0090] The server receives user data sent from the device. The received data includes the user's basic information and rehabilitation goals. The server initializes a generative AI model (such as GPT-4) and customizes it taking into account the user's rehabilitation goals and health condition. This completes the process of generating the optimal rehabilitation menu for each individual user.

[0091] Initiating dialogue and proposing rehabilitation menus

[0092] The device launches the generative AI model sent from the server and begins a dialogue session. An initial greeting and questions to check the user's health are displayed. For example, a question such as "Hello, how are you feeling today?" is presented. The user responds to this question with, for example, "My lower back hurts a little today." The device inputs the user's response into the generative AI model and suggests an appropriate rehabilitation menu. For example, a specific rehabilitation menu such as "If you have lower back pain, try doing five minutes of stretching" is presented.

[0093] Ongoing rehabilitation support

[0094] The user performs the proposed rehabilitation menu and inputs the results and feedback into the device. For example, the user may input feedback such as, "I felt a little better after doing a short stretch." The server receives this feedback and uses the generative AI model to adjust the next rehabilitation menu. The new rehabilitation menu is then proposed to the user again via the device. For example, a suggestion may be made such as, "Next time, try stretching for a longer period of time."

[0095] Specific examples

[0096] Mr. Tanaka, 75, begins rehabilitation to relieve his lower back pain. Mr. Tanaka enters his name and rehabilitation goals into the device, which the server receives. The generative AI model is initialized and asked through dialogue, "How are you feeling today?" When Mr. Tanaka responds, "My lower back hurts a little today," the generative AI model suggests a rehabilitation menu: "If you have lower back pain, try doing five minutes of stretching." When Mr. Tanaka performs the menu and sends feedback saying, "I feel a little better," the server adjusts the next rehabilitation menu and makes new suggestions.

[0097] Prompt Sentence Examples

[0098] Suggest an appropriate rehabilitation program for a 75-year-old woman with back pain. Her goal is to be able to play with her grandchildren at the park.

[0099] The present invention aims to provide a rehabilitation menu tailored to the individual needs of the user, thereby maintaining motivation and achieving effective rehabilitation. Furthermore, by continuously adjusting the rehabilitation plan based on feedback from the user, more personalized rehabilitation is possible.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The terminal displays an interface for obtaining basic information about the user.

[0103] Input: Basic information such as your name, age, health status, and rehabilitation goals

[0104] Specific behavior: A form or question is displayed, and the user fills in the relevant fields. For example, the user enters "back pain" and the goal "I want to be able to play in the park with my grandchildren."

[0105] Output: The entered user information is saved on the device.

[0106] Step 2:

[0107] The terminal transmits the collected user basic information to the server.

[0108] Input: User information stored on the device

[0109] Specific operation: When the user has finished entering information, they press the "Submit" button to send the data to the server.

[0110] Output: The server receives the user basic information.

[0111] Step 3:

[0112] The server initializes the generative AI model based on the received basic information.

[0113] Input: User's basic information (name, age, health status, rehabilitation goals, etc.)

[0114] Specific operation: User information is input into the generative AI model to create customized settings.

[0115] Output: A customized generative AI model is generated.

[0116] Step 4:

[0117] The server sends the initially configured generative AI model to the device.

[0118] Input: A customized generative AI model

[0119] Specific operation: The server sends data over the network to transmit the AI ​​model to the device.

[0120] Output: The device receives the generated AI model.

[0121] Step 5:

[0122] The device launches the generative AI model and begins a dialogue with the user.

[0123] Input: Generative AI model

[0124] Specific behavior: The device uses the generative AI model to conduct an initial interaction (e.g., greeting or checking how you are feeling). For example, it might ask, "Hello, how are you feeling today?"

[0125] Output: User input in response to a question (e.g., "My back hurts a little today").

[0126] Step 6:

[0127] The device inputs the user's answers into a generative AI model and suggests an appropriate rehabilitation menu.

[0128] Input: User response (e.g., "My back hurts a little today.")

[0129] Specific operation: The generative AI model analyzes the user's answers and generates an appropriate rehabilitation menu (e.g., "Try five minutes of stretching").

[0130] Output: The suggested rehabilitation menu is displayed to the user.

[0131] Step 7:

[0132] The user carries out the proposed rehabilitation menu and inputs the results and feedback into the terminal.

[0133] Input: Results and impressions of the rehabilitation menu performed by the user (e.g., "I feel a little better").

[0134] Specific operation: The user performs the rehabilitation menu and then inputs feedback into the terminal.

[0135] Output: The entered feedback is saved on the device.

[0136] Step 8:

[0137] The terminal transmits the user's feedback to the server.

[0138] Input: User feedback (e.g., "This is a bit easier now.")

[0139] Specific operation: The device sends data over the network to send feedback to the server.

[0140] Output: The server receives the feedback.

[0141] Step 9:

[0142] The server adjusts the generative AI model based on the feedback and generates the next rehabilitation menu.

[0143] Input: User feedback (e.g., "This is a bit easier now.")

[0144] Specific operation: The generative AI model analyzes the feedback and generates the next rehabilitation menu (e.g., "Try a longer stretch next time").

[0145] Output: A tailored rehabilitation menu is generated.

[0146] Step 10:

[0147] The server transmits a new rehabilitation menu to the terminal, which then provides it to the user.

[0148] Enter: Adjusted Rehab Menu

[0149] Specific operation: The server sends the rehabilitation menu to the terminal, and the terminal displays it to the user.

[0150] Output: The new rehab menu is displayed to the user.

[0151] (Application example 1)

[0152] 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."

[0153] When elderly people undergo rehabilitation, maintaining their motivation and providing them with an appropriate rehabilitation menu are important, but dietary habits that help them maintain a healthy lifestyle are equally important. However, there is no system that integrates personalized nutrition planning and meal delivery, making it difficult for elderly people to effectively undergo rehabilitation while eating a healthy diet. The present invention aims to solve this problem by providing a system that allows elderly people to consume appropriate nutrition while undergoing rehabilitation.

[0154] 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.

[0155] In this invention, the server includes a means for acquiring basic information about the user, a means for initializing the generative AI model, a means for analyzing the user's input and generating motivational questions and rehabilitation menus, and a means for using the generative AI model to propose a nutrition plan suitable for the user and manage meal delivery. This makes it possible to use the generative AI model not only to personalize rehabilitation menus but also to propose optimal nutrition plans for individual users and smoothly manage meal delivery.

[0156] The "means for acquiring basic information about the user" is a means for collecting data such as the user's personal information, health condition, rehabilitation goals, etc. via the terminal.

[0157] The "means for initially setting the generative AI model" is a means for setting the generative AI model to an appropriate state based on collected user information.

[0158] "Means for initiating a dialogue with a user using a generative AI model" refers to means for initiating communication with a user using a generative AI model.

[0159] The "means for analyzing user input and generating questions and rehabilitation menus that will motivate the user" refers to a means for proposing questions and rehabilitation menus that are optimal for the user based on the data input by the user.

[0160] The "means for providing the generated rehabilitation menu to the user" refers to a means for presenting the generated rehabilitation menu to the user and encouraging them to carry it out.

[0161] The "means for adjusting the next rehabilitation plan based on feedback from the user" refers to a means for analyzing feedback provided by the user and adjusting the next rehabilitation plan based on the feedback.

[0162] "Means for using a generative AI model to propose an optimal nutrition plan for a user and manage meal delivery" refers to a means for generating an optimal nutrition plan based on user information and managing meal ordering and delivery in accordance with that plan.

[0163] This invention is a system that uses generative AI models to provide rehabilitation and nutritional planning for seniors and manage meal delivery. The system consists of the following components:

[0164] 1. Enter your user data:

[0165] The terminal provides an interface for obtaining basic information about the user (such as name, age, health condition, rehabilitation goals, food preferences, and allergy information). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and a rehabilitation goal of "being able to play in the park with their grandchildren," and is also allergic to certain foods, this information can be entered.

[0166] 2. Initial setup of the generative AI model:

[0167] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals, health status, dietary preferences, and allergy information. This sets the stage for generating an optimal rehabilitation menu and nutrition plan for each individual user.

[0168] 3. Initiating a dialogue and proposing rehabilitation and nutritional plans:

[0169] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health, followed by a rehabilitation menu and nutrition plan. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Based on the user's answers, a rehabilitation menu and nutrition plan is then presented, such as "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we'll suggest a menu using ingredients that are good for your lower back."

[0170] 4. Meal delivery management:

[0171] The server manages meal delivery based on the generated nutrition plan. Specifically, it coordinates with delivery companies to arrange for meals appropriate for the user to be delivered at the specified time. For example, information such as "Grilled chicken breast and salad will be delivered for dinner tonight" is sent to the device, and the meal is delivered at the specified time.

[0172] 5. Ongoing rehabilitation and nutritional support:

[0173] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback to the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." Based on this information, the generative AI model adjusts the next rehabilitation and nutrition plan and provides ongoing support.

[0174] Hardware and software used:

[0175] Smartphone: A device for installing the app. Supports iOS or Android.

[0176] React Native: A cross-platform framework used to develop mobile applications.

[0177] Firebase: Used as a database to store and retrieve user data.

[0178] OpenAI API: Uses a generative AI model (GPT-4) to generate rehabilitation menus and nutrition plans.

[0179] Node.js: Manages the server-side logic and communicates with the generative AI model.

[0180] Examples of prompts:

[0181] Prompt for Mr. Tanaka (75 years old, suffers from back pain) who has the goal of "being able to play in the park with his grandchildren."

[0182] "Ms. Tanaka, a 75-year-old woman, suffers from back pain and wants to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate healthy menus that don't put strain on her back. Please suggest today's menu."

[0183] This system will enable elderly people to receive personalized support in both rehabilitation and nutrition, which is expected to improve their quality of life.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The terminal obtains basic information about the user. Specifically, it provides an interface where the user can input their name, age, health condition, rehabilitation goal, food preferences, allergy information, etc. This data is collected and sent to the server. The input data includes name = "Mr. Tanaka", age = "75 years old", health condition = "suffers from back pain", rehabilitation goal = "to be able to play in the park with my grandchildren", food preferences = "Japanese food", and allergy information = "shellfish allergy". This information is transferred to the server.

[0187] Step 2:

[0188] The server initializes the generative AI model based on the received user data. During this process, the settings of the generative AI model are customized based on the received data (name, age, health condition, rehabilitation goals, dietary preferences, and allergy information). For example, taking into account Mr. Tanaka's age and health condition, the server generates prompts for generating a rehabilitation menu and nutrition plan that is effective for his lower back pain.

[0189] Step 3:

[0190] The device uses the generative AI model to initiate a dialogue with the user. Specifically, the device uses the generated prompt to greet the user and ask questions about their health. A message such as "Hello, how are you feeling today?" is displayed. The user's response is received as input and analyzed in the next processing step.

[0191] Step 4:

[0192] The server analyzes the user's input and generates a rehabilitation menu and nutrition plan. It analyzes the captured user's response data (e.g., "My lower back hurts a little today") and uses a generative AI model to generate an appropriate rehabilitation menu and nutrition plan. For example, using the prompt, "Ms. Tanaka, a 75-year-old woman, suffers from lower back pain and aims to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate a healthy menu that puts less strain on her lower back. Please suggest today's menu," it generates "Try five minutes of stretching" as the rehabilitation menu and "Grilled chicken breast and salad made with ingredients that are good for the lower back" as the nutrition plan.

[0193] Step 5:

[0194] The device provides the generated rehabilitation menu and nutrition plan to the user. The device displays the generated menu to the user through its interface and encourages them to follow it. For example, the device may provide a notification such as, "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we suggest grilled chicken breast and a salad, which are good for your lower back."

[0195] Step 6:

[0196] The server manages meal delivery based on the generated nutrition plan. Specifically, it sends the generated meal information to the delivery company's API and arranges for the meal to be delivered to the user's address at the specified time. For example, it issues delivery instructions based on information such as "For tonight's dinner, we'll deliver grilled chicken breast and salad."

[0197] Step 7:

[0198] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback into the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." The server receives this feedback data and adjusts the next rehabilitation and nutrition plan, providing ongoing support.

[0199] Step 8:

[0200] The server adjusts the next rehabilitation and nutrition plan based on the user's feedback. It analyzes the received feedback and uses a generative AI model to optimize the next plan. For example, based on feedback such as "Stretching has become easier, but I would like to make it a little more difficult," it suggests a more intense rehabilitation menu and more nutritious meals for the next time.

[0201] This allows users to receive personalized rehabilitation and nutritional support while improving their quality of life.

[0202] 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.

[0203] Hereinafter, an embodiment of the present invention will be described.

[0204] This invention is a system for promoting rehabilitation for elderly people who require assistance or nursing care, and combines a generative AI model and an emotion engine to provide a rehabilitation menu according to the user's emotional state.

[0205] 1. Enter your user data:

[0206] The device provides an interface for entering basic user information (such as name, age, health condition, and rehabilitation goals). Elderly users enter their own information through this interface. For example, if 75-year-old Mr. Tanaka suffers from back pain and has a rehabilitation goal of "being able to play with his grandchildren in the park," he or she would enter this information.

[0207] 2. Initial setup of the generative AI model:

[0208] The server initializes the generative AI model based on the input user data. The generative AI model is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health condition.

[0209] 3. Initial setting of emotion engine:

[0210] The server initializes the emotion engine, which is designed to analyze the user's input voice and facial expression data and recognize the user's emotional state.

[0211] 4. Dialogue initiation and emotion recognition:

[0212] The generative AI model and emotion engine begin a dialogue with the user via the device. First, a general greeting and a check on the user's health are conducted. For example, a question such as "Hello, Tanaka-san. How are you feeling today?" is asked. Once the user's response (e.g., "My back hurts a little today, but I feel good") is entered, the emotion engine recognizes the user's emotional state from their voice and facial expressions.

[0213] 5. Rehabilitation menu suggestions:

[0214] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[0215] 6. Providing the generated rehabilitation menu:

[0216] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[0217] 7. Gathering Feedback:

[0218] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and their emotional state. For example, the user might input, "After a short stretch, I feel a little better. I'm feeling good."

[0219] 8. Adjusting your next rehabilitation plan:

[0220] Based on user feedback and emotion recognition data from the emotion engine, the server uses a generative AI model to adjust the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[0221] As a specific example, consider a 75-year-old female user named Tanaka. Tanaka's goal is to relieve her lower back pain. Tanaka operates her device to input basic information, and the server initializes the generative AI model and emotion engine. In the first dialogue, Tanaka inputs, "My lower back hurts a little today," and the emotion engine recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." Tanaka then performs rehabilitation and provides feedback, saying, "I feel a little better." The server uses this feedback to adjust the next rehabilitation menu and provides Tanaka with an ongoing rehabilitation menu.

[0222] In this way, this invention provides a personalized rehabilitation menu that takes into account the user's emotional state, promoting effective rehabilitation. Furthermore, by combining generative AI with an emotion engine, it is possible to support the user's psychological and emotional aspects. This is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[0223] The processing flow will be explained below.

[0224] Step 1:

[0225] The device provides an interface for entering basic user information, such as the user's name, age, health condition, and rehabilitation goals. For example, Mr. Tanaka (75 years old) suffers from back pain and enters his goal of "being able to play in the park with his grandchildren."

[0226] Step 2:

[0227] The server initializes the generative AI model based on the acquired user data, which reflects the user's rehabilitation goals and health status.

[0228] Step 3:

[0229] The server initializes the emotion engine, which analyzes the user's input voice and facial expression data and prepares it to recognize the user's emotional state.

[0230] Step 4:

[0231] Through the device, the generative AI model and emotion engine begin a dialogue with the user, starting with a general greeting such as "Hello, how are you feeling today?" and a check-up on their health.

[0232] Step 5:

[0233] The user responds to questions posed by the AI ​​generator, for example, by typing, "My back hurts a little today."

[0234] Step 6:

[0235] The server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and the analysis results are embodied as "I feel good, but I have back pain."

[0236] Step 7:

[0237] The server uses a generative AI model to generate a rehabilitation menu based on user data and emotion analysis results. This rehabilitation menu takes into account the user's emotional state. For example, it might suggest, "You have lower back pain, so try some short, relaxing stretches without overdoing it."

[0238] Step 8:

[0239] The terminal provides the generated rehabilitation menu to the user, allowing the user to receive specific instructions and begin rehabilitation.

[0240] Step 9:

[0241] The user performs the provided rehabilitation program and provides feedback on the results and their impressions via the device. For example, they can send feedback such as, "I felt a little better after doing some short stretches."

[0242] Step 10:

[0243] The server adjusts the next rehabilitation plan based on the user's feedback and the emotion analysis results of the emotion engine. The generative AI model generates the next rehabilitation menu based on the new feedback.

[0244] Specifically, in Tanaka's case,

[0245] 1. Enter your name, age, health condition, and rehabilitation goals on the device.

[0246] 2. Initialize the generated AI model on the server.

[0247] 3. Initialize the emotion engine on the server.

[0248] 4. Ask Tanaka from the device, "How are you feeling today?"

[0249] 5. User Tanaka replies, "My back hurts a little today."

[0250] 6. The server uses its emotion engine to analyze Tanaka's situation and conclude that "I feel good, but I have back pain."

[0251] 7. The server suggested "short, relaxed stretches for lower back pain."

[0252] 8. Provide rehabilitation menu suggestions on the terminal.

[0253] 9. User Tanaka underwent rehabilitation and gave feedback that "stretching made me feel a little better."

[0254] 10. The server adjusts the next rehabilitation plan based on the feedback and emotion engine data.

[0255] This allows Tanaka to continually acquire and implement rehabilitation programs that suit his emotional state. By repeating this process, the elderly person's motivation can be maintained, enabling high-quality rehabilitation.

[0256] Example 2

[0257] 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."

[0258] To effectively promote elderly rehabilitation, it is important to provide a personalized rehabilitation menu tailored to each individual. However, conventional systems often provide a uniform rehabilitation menu without considering the user's emotional state, which can lead to a decline in user motivation. While there are also systems that adjust rehabilitation plans based on user feedback, most of these systems do not take into account feedback about the user's emotional state, and therefore are unable to provide adequately personalized support. This can lead to a decline in elderly people's motivation to undergo rehabilitation, making it difficult for them to continue.

[0259] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0260] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for initializing the emotion engine, means for initiating a dialogue with the user using the generative AI model and the emotion engine and recognizing the emotional state, means for analyzing the user's input and emotional state to generate motivational questions and a rehabilitation menu, means for providing the generated rehabilitation menu to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration, thereby increasing the elderly's motivation for rehabilitation and promoting continued rehabilitation.

[0261] The "means for acquiring basic information about the user" is a mechanism for providing an interface that allows the user to input information such as their name, age, health condition, and rehabilitation goals.

[0262] The "means for initializing the generative AI model" is a function that configures the generative AI model based on the user's basic information, enabling the generation of a rehabilitation menu that is optimal for the user.

[0263] The "means for initializing the emotion engine" is a means for setting up an emotion engine that can analyze the user's voice and facial expression data, and for preparing to recognize the user's emotional state.

[0264] "Means for initiating a dialogue with a user and recognizing the emotional state using a generative AI model and an emotion engine" refers to a mechanism that links a generative AI model with an emotion engine to identify the emotional state from voice and facial expressions through dialogue with the user.

[0265] "Means for analyzing a user's input and emotional state to generate questions and rehabilitation menus that motivate the user" refers to a method for generating questions and appropriate rehabilitation menus that motivate the user based on the user's input and emotional state.

[0266] "Means for providing the generated rehabilitation menu to the user" refers to a mechanism that provides an interface for presenting the rehabilitation menu created by the generative AI model to the user and having them carry it out.

[0267] The "means for adjusting the next rehabilitation plan based on feedback from the user" is a method for analyzing the feedback and emotion recognition data provided by the user after rehabilitation and optimizing the next rehabilitation menu.

[0268] A specific example for implementing the present invention will be described. The present invention is a system that provides a personalized rehabilitation menu that takes into account the user's basic information and emotional state in order to effectively promote rehabilitation for elderly people. The specific configuration and operation of this system will be described below.

[0269] Entering User Data

[0270] The terminal provides an interface for inputting the user's basic information. This interface includes input fields for name, age, health condition, rehabilitation purpose, etc. The user enters information in these fields and clicks the send button to send the data. This inputs the user's basic information into the system.

[0271] Initial setup of generative AI models

[0272] The server receives basic information entered by the user and uses it to initialize the generative AI model, which is then configured to generate an optimal rehabilitation menu for each individual user, taking into account their rehabilitation goals and health condition.

[0273] Initial setting of emotion engine

[0274] The server initializes the emotion engine, which is designed to analyze the user's voice and facial expression data and recognize the user's emotional state. The server loads the voice recognition module and facial expression recognition module into the emotion engine and verifies that they are working properly.

[0275] Dialogue initiation and emotion recognition

[0276] The device uses a generative AI model and an emotion engine to initiate a dialogue with the user. First, a general greeting and a health check are performed. For example, a question such as "Hello, how are you feeling today?" is displayed and played back. The user's response is input via voice or text, and the device sends that data to the emotion engine. The emotion engine recognizes the user's emotional state from their voice and facial expressions.

[0277] Rehabilitation menu suggestions

[0278] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and proposes the optimal rehabilitation menu for the user. For example, it might generate a menu such as, "You have lower back pain today, so let's start with a short stretch without overdoing it. Can you do it while relaxing?"

[0279] Providing the generated rehabilitation menu

[0280] The terminal presents the generated rehabilitation menu to the user, who then checks the rehabilitation menu displayed on the terminal and performs rehabilitation according to the instructions.

[0281] Gathering feedback

[0282] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and emotional state. For example, the user can input something like, "After a short stretch, I feel a little better. I'm feeling good."

[0283] Adjusting the next rehabilitation plan

[0284] The server updates the generative AI model based on user feedback and recognition data from the emotion engine, adjusting the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[0285] Specific examples

[0286] For example, if a 75-year-old user has a goal of relieving lower back pain, the system operates as follows: The user enters basic information such as "I have lower back pain, and my goal for rehabilitation is to be able to play at the park with my grandchildren." The server initializes the generative AI model and emotion engine, and asks "How are you feeling today?" in the first dialogue. If the user replies "My lower back hurts a little," the emotion engine recognizes this as "I feel good." The generative AI model suggests a rehabilitation menu such as "When you have lower back pain, do you do short stretches?" After completing the rehabilitation, the user provides feedback such as "I feel a little better." The server then adjusts the next rehabilitation plan and provides it to the user.

[0287] Prompt Sentence Examples

[0288] 1. "What is the goal of rehabilitation?"

[0289] 2. "How are you feeling?"

[0290] 3. "How did you feel about the rehabilitation program?"

[0291] In this way, providing a personalized rehabilitation menu that takes into account the user's emotional state can increase the elderly person's motivation for rehabilitation and promote continued rehabilitation.

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] Step 1: Enter user data

[0294] The terminal provides an interface for users to enter basic information, including fields for name, age, health status, rehabilitation goals, etc.

[0295] Specific operation: When the user enters information into these fields and clicks the submit button, the device sends the data to the server.

[0296] Input: User's basic information (name, age, health condition, rehabilitation purpose, etc.)

[0297] Output: Basic information about the user sent to the server

[0298] Step 2: Initializing the Generative AI Model

[0299] The server performs initial settings for the generative AI model based on the received user data.

[0300] Specific operation: The server inputs user data into the generative AI model and creates personalized settings based on rehabilitation goals and health status, enabling the generation of an individual rehabilitation menu.

[0301] Input: User basic information

[0302] Output: Initialized generative AI model

[0303] Step 3: Initializing the Emotion Engine

[0304] The server initializes the emotion engine, which includes a voice recognition module and a facial expression recognition module.

[0305] Specific operation: The server loads the necessary modules (voice and facial expression recognition) into the emotion engine, preparing it to analyze the user's emotional state.

[0306] Input: Required modules

[0307] Output: Initialized emotion engine

[0308] Step 4: Initiating a dialogue and recognizing emotions

[0309] The device initiates a dialogue with the user using a generative AI model and an emotion engine.

[0310] Specific operation: The device activates voice input and camera functions and presents prompts to the user. The user's response is sent to the emotion engine, which recognizes the user's emotional state from their voice and facial expressions. For example, the device asks, "How are you feeling today?" and the user replies, "My back hurts a little." The emotion engine analyzes this response and recognizes the user's emotional state.

[0311] Input: User voice or text input

[0312] Output: Recognized emotional state of the user

[0313] Step 5: Proposing a rehabilitation menu

[0314] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates a rehabilitation menu.

[0315] Specific operation: The generative AI model generates a rehabilitation menu based on the user's health and emotional state. For example, it may suggest, "If you have lower back pain, start with a short stretch without overdoing it."

[0316] Input: User's emotional state, health status

[0317] Output: Generated rehabilitation menu

[0318] Step 6: Providing the generated rehabilitation menu

[0319] The terminal presents the generated rehabilitation menu to the user.

[0320] Specific operation: The device displays a rehabilitation menu on the screen and guides the user to confirm and carry out the rehabilitation menu.

[0321] Input: Generated rehabilitation menu

[0322] Output: Rehabilitation menu confirmed by the user

[0323] Step 7: Gather feedback

[0324] The user carries out the proposed rehabilitation menu and feeds back the results and emotional state to the server via the terminal.

[0325] Specific operation: The user uses the device to input and send feedback such as, "I felt a little better after doing a short stretch."

[0326] Input: User feedback

[0327] Output: Feedback sent to the server

[0328] Step 8: Adjust your next rehabilitation plan

[0329] The server uses user feedback and data from the emotion engine to allow the generative AI model to adjust the next rehabilitation plan.

[0330] Specific actions: The server analyzes the received feedback and data and optimizes the next rehabilitation menu, for example, planning to "do the same stretches for a little longer next time, and add new exercises if you feel better."

[0331] Input: User feedback, emotional state

[0332] Output: Adjusted next rehabilitation menu

[0333] (Application example 2)

[0334] 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."

[0335] In elderly rehabilitation, there is a need to provide personalized rehabilitation menus that correspond to each individual's emotions and health status. However, current systems have difficulty accurately recognizing the user's emotional state and presenting appropriate rehabilitation menus based on that. Furthermore, they lack a mechanism for effectively collecting feedback from users and reflecting it in the next rehabilitation menu. This situation reduces the motivation of elderly people to continue rehabilitation, and there is a problem in that rehabilitation is not fully effective.

[0336] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0337] In this invention, the server includes emotion recognition means, means for initializing the generative AI model, means for starting a dialogue with the user, means for analyzing the user's input and emotional state and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration and improve the user's motivation for rehabilitation.

[0338] The "means for obtaining basic information" is an interface for inputting and collecting basic information such as the user's name, age, health condition, and rehabilitation goals.

[0339] A "generative AI model" is an artificial intelligence model that generates a personalized rehabilitation menu based on the user's rehabilitation goals and health condition.

[0340] The "means for initiating dialogue" is a mechanism for initiating an initial dialogue between the user and the generative AI model and emotion recognition system.

[0341] An "emotion recognition means" is a system or device designed to analyze and recognize a user's emotional state from their voice and facial expressions.

[0342] "Emotional state" refers to the psychological and emotional state of the user when undergoing rehabilitation, such as feeling good, bad, tired, etc.

[0343] The "means for generating questions and rehabilitation menus" refers to an algorithm or system that analyzes the user's basic information and emotional state, and automatically creates questions and rehabilitation menus that motivate the user.

[0344] The "means for providing a rehabilitation menu" is an interface that displays or conveys the generated rehabilitation menu to the user.

[0345] The "means for adjusting the next rehabilitation plan based on feedback" is a system that optimizes and adjusts the next rehabilitation menu based on feedback collected from the user about the rehabilitation results and emotional state.

[0346] This invention is a system for promoting rehabilitation for elderly people who require assistance or care, and combines a generative AI model and emotion recognition means to provide a rehabilitation menu that corresponds to the user's emotional state.

[0347] This system is implemented according to the following procedure.

[0348] First, the user uses a terminal to input basic information (name, age, health condition, rehabilitation goals, etc.). This basic information can be acquired, for example, through the interface of a tablet or smartphone. Specifically, the information entered is "75-year-old elderly person suffering from back pain."

[0349] The server then initializes a generative AI model based on the acquired user data, which is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health status.

[0350] Next, the server initializes the emotion recognition means. This emotion recognition means analyzes the user's input voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to collect and analyze the user's facial expressions and voice.

[0351] The generative AI model and emotion recognition system then begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, a question like "Hello, how are you feeling today?" is asked, and when the user responds (e.g., "My back hurts a little today, but I'm feeling good"), the emotion recognition means recognizes their emotional state from their voice and facial expression.

[0352] Next, the server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion recognition means, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[0353] The generated rehabilitation menu is provided to the user via the terminal, and the user can follow the menu to carry out rehabilitation.

[0354] The user provides feedback on the results of the rehabilitation and their emotional state. For example, they might say, "I felt a little better after a short stretch. I'm feeling good." Based on this feedback, the server uses the generative AI model and emotion recognition tools to adjust the next rehabilitation plan. For example, the server might adjust the plan so that next time, the user performs the same stretches for a little longer, and add a new exercise if they feel better.

[0355] The hardware required is a camera and microphone, which are used to capture the user's facial expressions and voice. For software, the OpenCV library is used for computer vision, and the emotion recognition model is implemented using the TensorFlow / Keras model. For generative AI models, high-performance generative models such as GPT-3 are used.

[0356] As a concrete example, suppose a 75-year-old female user has a rehabilitation goal of relieving lower back pain. She operates the device to input her basic information, and the server initializes the generative AI model and emotion recognition means. In the first dialogue, she inputs, "My lower back hurts a little today," and the emotion recognition means recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." The user performs this rehabilitation menu and provides feedback that "it feels a little better." The server uses this feedback to adjust the next rehabilitation menu and provides the user with an ongoing rehabilitation menu.

[0357] An example of a prompt is as follows:

[0358] User data: {Name: "Tanaka", Age: 75, Health condition: "Low back pain", Rehabilitation goal: "Playing with grandchildren in the park"},

[0359] Emotional state: "Energetic"

[0360] Generate an appropriate rehabilitation menu.

[0361] This system provides a personalized rehabilitation menu that takes into account the user's emotional state, improving the user's motivation for rehabilitation and supporting continuous rehabilitation.

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] The user uses a terminal to input basic information (such as name, age, health status, rehabilitation goals, etc.). This basic information is sent to the server through the terminal interface. The input data is stored on the server as the user's personalized profile.

[0365] Step 2:

[0366] The server initializes the generative AI model based on the acquired user data. The AI ​​model used here is configured to generate an optimal rehabilitation menu based on the user's rehabilitation goals and health condition. This initialization takes the user's basic information as input and outputs a rehabilitation menu template.

[0367] Step 3:

[0368] The server initializes the emotion recognition means. This emotion recognition means analyzes the user's voice and facial expression data acquired from the terminal and recognizes the user's emotional state. For example, a model is set up that acquires the user's voice and video data using a camera and microphone, and uses this as input to output the user's emotional state.

[0369] Step 4:

[0370] The generative AI model and emotion recognition system begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, the device may ask the user, "Hello, how are you feeling today?" The user's response (e.g., "My back hurts a little today, but I feel good") is entered and sent to the server.

[0371] Step 5:

[0372] The server uses emotion recognition means to analyze the user's emotional state and inputs this into the generative AI model. This generates questions and rehabilitation menus that take the user's emotional state into consideration and motivate them. For example, a rehabilitation menu such as "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try it while relaxing?" is generated and output.

[0373] Step 6:

[0374] The generated rehabilitation menu is provided to the user via a terminal, and the user then follows the menu to carry out rehabilitation. Because the rehabilitation menu is optimized based on the user's current situation and emotional state, effective rehabilitation can be expected.

[0375] Step 7:

[0376] The user provides feedback on the results of the rehabilitation and their emotional state, for example, "I feel a little better after a short stretch. I'm feeling good," which is input into the device and sent to the server.

[0377] Step 8:

[0378] Based on the user's feedback and data from the emotion recognition tool, the generative AI model adjusts the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better." This information is provided to the user during their next rehabilitation session.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] [Second embodiment]

[0383] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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."

[0395] Hereinafter, an embodiment of the present invention will be described.

[0396] This invention is a system that uses generative AI models to promote rehabilitation for elderly people. Specifically, it consists of the following elements:

[0397] 1. Enter your user data:

[0398] The terminal provides an interface for acquiring basic information about the user (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and their rehabilitation goal is to be able to play in the park with their grandchildren, they would input this information.

[0399] 2. Initial setup of the generative AI model:

[0400] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals and health status, preparing the system to generate the optimal rehabilitation menu for each individual user.

[0401] 3. Initiating dialogue and proposing rehabilitation options:

[0402] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Then, based on the user's answer (e.g., "My lower back hurts a little today"), the generative AI model suggests an appropriate rehabilitation menu. The rehabilitation menu suggested might be something like, "If you have lower back pain, start with some short stretches without overdoing it. What do you think?"

[0403] 4. Ongoing rehabilitation support:

[0404] The user performs the proposed rehabilitation program and inputs the results and feedback to the server via their device. For example, the user might say, "I felt a little better after doing some short stretches." Based on this information, the generative AI model adjusts the next rehabilitation plan and provides ongoing support.

[0405] As a concrete example, let's say there is a 75-year-old female user (let's call her Tanaka). Tanaka's goal is to relieve her lower back pain. Tanaka operates the device to input basic information, and the generative AI model performs initial settings based on her information. In the first dialogue, Tanaka inputs, "My lower back hurts a little today." The generative AI model analyzes this and suggests, "If you have lower back pain, try doing five minutes of stretching." Tanaka follows this suggestion, performs the stretches, and provides feedback that, as a result, "I feel a little better." The server receives this feedback, adjusts the next rehabilitation plan, and continues to provide Tanaka with a continuous rehabilitation menu.

[0406] In this way, a personalized rehabilitation menu tailored to each user's needs is generated, and the generation AI asks in-depth questions to ensure a satisfactory rehabilitation experience. This system is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[0407] The processing flow will be explained below.

[0408] Step 1:

[0409] The terminal provides an interface for inputting basic user information (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, a 75-year-old senior citizen inputs their rehabilitation goal of "being able to play in the park with their grandchildren" and their health condition of lower back pain.

[0410] Step 2:

[0411] The server initializes the generative AI model based on the input user data. This initial setting takes into account the user's rehabilitation goals and health status, and helps generate a personalized rehabilitation menu.

[0412] Step 3:

[0413] Through the device, the generative AI model begins a dialogue with the user, starting with general exchanges such as greetings and checking in on how you're feeling. For example, the model might ask questions like, "Hello, how are you?"

[0414] Step 4:

[0415] The user responds to questions posed by the generative AI model, for example, by typing, "My back hurts a little today."

[0416] Step 5:

[0417] The server analyzes user input in real time. The generative AI model generates motivational questions and rehabilitation menus based on the user's input. For example, it might generate a menu that suggests, "If you have lower back pain, try doing some short stretches without straining yourself."

[0418] Step 6:

[0419] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[0420] Step 7:

[0421] The user carries out the proposed rehabilitation program and provides feedback on the results to the server via the terminal, for example, by inputting something like, "I did a short stretch and felt a little better."

[0422] Step 8:

[0423] The server adjusts the next rehabilitation plan based on the user's feedback. The generative AI model takes the new feedback into account and generates the next rehabilitation menu and motivational questions. This loop enables continuous rehabilitation support.

[0424] Example 1

[0425] 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."

[0426] Rehabilitation for elderly people requires personalization based on each individual's health condition and rehabilitation goals, while continuity is also important. However, conventional rehabilitation systems and programs are unable to flexibly respond to individual needs, making it difficult for users to maintain their motivation. Furthermore, they lack the functionality to continuously adjust the next rehabilitation plan based on user feedback, making it difficult to achieve effective rehabilitation.

[0427] 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.

[0428] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for starting a dialogue with the user using the generative AI model, means for analyzing the user's input and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, means for adjusting the next rehabilitation plan based on feedback from the user, and means for transmitting feedback to the server via the terminal. This makes it possible to provide an individually customized rehabilitation menu, thereby enabling users to maintain their motivation and achieve effective rehabilitation.

[0429] "Means for obtaining basic user information" refers to equipment or software for inputting and collecting personal information such as the user's age, health condition, and rehabilitation goals.

[0430] The "means for initializing the generative AI model" refers to the process of customizing the generative AI model based on the collected basic information of the user and performing initial settings to generate an individual rehabilitation menu.

[0431] "Means for initiating a dialogue with a user using a generative AI model" refers to a function for initiating an interactive dialogue with a user using a generative AI model and checking the user's situation and state.

[0432] The "means for analyzing user input and generating motivational questions and rehabilitation menus" refers to a process for analyzing the current situation and condition input by the user and generating motivational questions and individually customized rehabilitation menus based on the results.

[0433] "Means for providing the generated rehabilitation menu to the user" refers to a function that displays the rehabilitation menu created by the generative AI model in a visible form to the user and encourages them to carry it out.

[0434] "Means for adjusting the next rehabilitation plan based on user feedback" refers to the process of collecting and analyzing the results and impressions of the user's rehabilitation, and then adjusting the next rehabilitation menu and plan based on that information.

[0435] The "means for transmitting feedback to the server via the terminal" is a function that allows the user to use the terminal to input the results of the rehabilitation menu implementation and feedback, and transmit this to the server.

[0436] A "generative AI model" is a model that uses artificial intelligence technology to generate rehabilitation menus and dialogues that meet the individual needs of each user.

[0437] A "rehabilitation menu" is a specific exercise and training plan proposed for the user to undergo rehabilitation.

[0438] "Feedback" is information about the rehabilitation results, such as the user's impressions after completing the rehabilitation menu and changes in physical condition.

[0439] The following describes an embodiment of the present invention. The present invention is a system that promotes rehabilitation for elderly people by using a generative AI model. Specifically, it is composed of the following elements:

[0440] Entering User Data

[0441] The device provides an interface for acquiring basic information about the user. This interface is displayed on a computer, tablet, or smartphone (Windows, iOS, Android, etc.). The user enters their own information through this interface. For example, information such as name, age, health condition, and rehabilitation goals may be entered. As a specific example, a 75-year-old user may enter "back pain" and the rehabilitation goal of "being able to play in the park with my grandchildren."

[0442] Initial setup of generative AI models

[0443] The server receives user data sent from the device. The received data includes the user's basic information and rehabilitation goals. The server initializes a generative AI model (such as GPT-4) and customizes it taking into account the user's rehabilitation goals and health condition. This completes the process of generating the optimal rehabilitation menu for each individual user.

[0444] Initiating dialogue and proposing rehabilitation menus

[0445] The device launches the generative AI model sent from the server and begins a dialogue session. An initial greeting and questions to check the user's health are displayed. For example, a question such as "Hello, how are you feeling today?" is presented. The user responds to this question with, for example, "My lower back hurts a little today." The device inputs the user's response into the generative AI model and suggests an appropriate rehabilitation menu. For example, a specific rehabilitation menu such as "If you have lower back pain, try doing five minutes of stretching" is presented.

[0446] Ongoing rehabilitation support

[0447] The user performs the proposed rehabilitation menu and inputs the results and feedback into the device. For example, the user may input feedback such as, "I felt a little better after doing a short stretch." The server receives this feedback and uses the generative AI model to adjust the next rehabilitation menu. The new rehabilitation menu is then proposed to the user again via the device. For example, a suggestion may be made such as, "Next time, try stretching for a longer period of time."

[0448] Specific examples

[0449] Mr. Tanaka, 75, begins rehabilitation to relieve his lower back pain. Mr. Tanaka enters his name and rehabilitation goals into the device, which the server receives. The generative AI model is initialized and asked through dialogue, "How are you feeling today?" When Mr. Tanaka responds, "My lower back hurts a little today," the generative AI model suggests a rehabilitation menu: "If you have lower back pain, try doing five minutes of stretching." When Mr. Tanaka performs the menu and sends feedback saying, "I feel a little better," the server adjusts the next rehabilitation menu and makes new suggestions.

[0450] Prompt Sentence Examples

[0451] Suggest an appropriate rehabilitation program for a 75-year-old woman with back pain. Her goal is to be able to play with her grandchildren at the park.

[0452] The present invention aims to provide a rehabilitation menu tailored to the individual needs of the user, thereby maintaining motivation and achieving effective rehabilitation. Furthermore, by continuously adjusting the rehabilitation plan based on feedback from the user, more personalized rehabilitation is possible.

[0453] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0454] Step 1:

[0455] The terminal displays an interface for obtaining basic information about the user.

[0456] Input: Basic information such as your name, age, health status, and rehabilitation goals

[0457] Specific behavior: A form or question is displayed, and the user fills in the relevant fields. For example, the user enters "back pain" and the goal "I want to be able to play in the park with my grandchildren."

[0458] Output: The entered user information is saved on the device.

[0459] Step 2:

[0460] The terminal transmits the collected user basic information to the server.

[0461] Input: User information stored on the device

[0462] Specific operation: When the user has finished entering information, they press the "Submit" button to send the data to the server.

[0463] Output: The server receives the user basic information.

[0464] Step 3:

[0465] The server initializes the generative AI model based on the received basic information.

[0466] Input: User's basic information (name, age, health status, rehabilitation goals, etc.)

[0467] Specific operation: User information is input into the generative AI model to create customized settings.

[0468] Output: A customized generative AI model is generated.

[0469] Step 4:

[0470] The server sends the initially configured generative AI model to the device.

[0471] Input: A customized generative AI model

[0472] Specific operation: The server sends data over the network to transmit the AI ​​model to the device.

[0473] Output: The device receives the generated AI model.

[0474] Step 5:

[0475] The device launches the generative AI model and begins a dialogue with the user.

[0476] Input: Generative AI model

[0477] Specific behavior: The device uses the generative AI model to conduct an initial interaction (e.g., greeting or checking how you are feeling). For example, it might ask, "Hello, how are you feeling today?"

[0478] Output: User input in response to a question (e.g., "My back hurts a little today").

[0479] Step 6:

[0480] The device inputs the user's answers into a generative AI model and suggests an appropriate rehabilitation menu.

[0481] Input: User response (e.g., "My back hurts a little today.")

[0482] Specific operation: The generative AI model analyzes the user's answers and generates an appropriate rehabilitation menu (e.g., "Try five minutes of stretching").

[0483] Output: The suggested rehabilitation menu is displayed to the user.

[0484] Step 7:

[0485] The user carries out the proposed rehabilitation menu and inputs the results and feedback into the terminal.

[0486] Input: Results and impressions of the rehabilitation menu performed by the user (e.g., "I feel a little better").

[0487] Specific operation: The user performs the rehabilitation menu and then inputs feedback into the terminal.

[0488] Output: The entered feedback is saved on the device.

[0489] Step 8:

[0490] The terminal transmits the user's feedback to the server.

[0491] Input: User feedback (e.g., "This is a bit easier now.")

[0492] Specific operation: The device sends data over the network to send feedback to the server.

[0493] Output: The server receives the feedback.

[0494] Step 9:

[0495] The server adjusts the generative AI model based on the feedback and generates the next rehabilitation menu.

[0496] Input: User feedback (e.g., "This is a bit easier now.")

[0497] Specific operation: The generative AI model analyzes the feedback and generates the next rehabilitation menu (e.g., "Try a longer stretch next time").

[0498] Output: A tailored rehabilitation menu is generated.

[0499] Step 10:

[0500] The server transmits a new rehabilitation menu to the terminal, which then provides it to the user.

[0501] Enter: Adjusted Rehab Menu

[0502] Specific operation: The server sends the rehabilitation menu to the terminal, and the terminal displays it to the user.

[0503] Output: The new rehab menu is displayed to the user.

[0504] (Application example 1)

[0505] 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."

[0506] When elderly people undergo rehabilitation, maintaining their motivation and providing them with an appropriate rehabilitation menu are important, but dietary habits that help them maintain a healthy lifestyle are equally important. However, there is no system that integrates personalized nutrition planning and meal delivery, making it difficult for elderly people to effectively undergo rehabilitation while eating a healthy diet. The present invention aims to solve this problem by providing a system that allows elderly people to consume appropriate nutrition while undergoing rehabilitation.

[0507] 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.

[0508] In this invention, the server includes a means for acquiring basic information about the user, a means for initializing the generative AI model, a means for analyzing the user's input and generating motivational questions and rehabilitation menus, and a means for using the generative AI model to propose a nutrition plan suitable for the user and manage meal delivery. This makes it possible to use the generative AI model not only to personalize rehabilitation menus but also to propose optimal nutrition plans for individual users and smoothly manage meal delivery.

[0509] The "means for acquiring basic information about the user" is a means for collecting data such as the user's personal information, health condition, rehabilitation goals, etc. via the terminal.

[0510] The "means for initially setting the generative AI model" is a means for setting the generative AI model to an appropriate state based on collected user information.

[0511] "Means for initiating a dialogue with a user using a generative AI model" refers to means for initiating communication with a user using a generative AI model.

[0512] The "means for analyzing user input and generating questions and rehabilitation menus that will motivate the user" refers to a means for proposing questions and rehabilitation menus that are optimal for the user based on the data input by the user.

[0513] The "means for providing the generated rehabilitation menu to the user" refers to a means for presenting the generated rehabilitation menu to the user and encouraging them to carry it out.

[0514] The "means for adjusting the next rehabilitation plan based on feedback from the user" refers to a means for analyzing feedback provided by the user and adjusting the next rehabilitation plan based on the feedback.

[0515] "Means for using a generative AI model to propose an optimal nutrition plan for a user and manage meal delivery" refers to a means for generating an optimal nutrition plan based on user information and managing meal ordering and delivery in accordance with that plan.

[0516] This invention is a system that uses generative AI models to provide rehabilitation and nutritional planning for seniors and manage meal delivery. The system consists of the following components:

[0517] 1. Enter your user data:

[0518] The terminal provides an interface for obtaining basic information about the user (such as name, age, health condition, rehabilitation goals, food preferences, and allergy information). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and a rehabilitation goal of "being able to play in the park with their grandchildren," and is also allergic to certain foods, this information can be entered.

[0519] 2. Initial setup of the generative AI model:

[0520] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals, health status, dietary preferences, and allergy information. This sets the stage for generating an optimal rehabilitation menu and nutrition plan for each individual user.

[0521] 3. Initiating a dialogue and proposing rehabilitation and nutritional plans:

[0522] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health, followed by a rehabilitation menu and nutrition plan. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Based on the user's answers, a rehabilitation menu and nutrition plan is then presented, such as "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we'll suggest a menu using ingredients that are good for your lower back."

[0523] 4. Meal delivery management:

[0524] The server manages meal delivery based on the generated nutrition plan. Specifically, it coordinates with delivery companies to arrange for meals appropriate for the user to be delivered at the specified time. For example, information such as "Grilled chicken breast and salad will be delivered for dinner tonight" is sent to the device, and the meal is delivered at the specified time.

[0525] 5. Ongoing rehabilitation and nutritional support:

[0526] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback to the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." Based on this information, the generative AI model adjusts the next rehabilitation and nutrition plan and provides ongoing support.

[0527] Hardware and software used:

[0528] Smartphone: A device for installing the app. Supports iOS or Android.

[0529] React Native: A cross-platform framework used to develop mobile applications.

[0530] Firebase: Used as a database to store and retrieve user data.

[0531] OpenAI API: Uses a generative AI model (GPT-4) to generate rehabilitation menus and nutrition plans.

[0532] Node.js: Manages the server-side logic and communicates with the generative AI model.

[0533] Examples of prompts:

[0534] Prompt for Mr. Tanaka (75 years old, suffers from back pain) who has the goal of "being able to play in the park with his grandchildren."

[0535] "Ms. Tanaka, a 75-year-old woman, suffers from back pain and wants to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate healthy menus that don't put strain on her back. Please suggest today's menu."

[0536] This system will enable elderly people to receive personalized support in both rehabilitation and nutrition, which is expected to improve their quality of life.

[0537] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0538] Step 1:

[0539] The terminal obtains basic information about the user. Specifically, it provides an interface where the user can input their name, age, health condition, rehabilitation goal, food preferences, allergy information, etc. This data is collected and sent to the server. The input data includes name = "Mr. Tanaka", age = "75 years old", health condition = "suffers from back pain", rehabilitation goal = "to be able to play in the park with my grandchildren", food preferences = "Japanese food", and allergy information = "shellfish allergy". This information is transferred to the server.

[0540] Step 2:

[0541] The server initializes the generative AI model based on the received user data. During this process, the settings of the generative AI model are customized based on the received data (name, age, health condition, rehabilitation goals, dietary preferences, and allergy information). For example, taking into account Mr. Tanaka's age and health condition, the server generates prompts for generating a rehabilitation menu and nutrition plan that is effective for his lower back pain.

[0542] Step 3:

[0543] The device uses the generative AI model to initiate a dialogue with the user. Specifically, the device uses the generated prompt to greet the user and ask questions about their health. A message such as "Hello, how are you feeling today?" is displayed. The user's response is received as input and analyzed in the next processing step.

[0544] Step 4:

[0545] The server analyzes the user's input and generates a rehabilitation menu and nutrition plan. It analyzes the captured user's response data (e.g., "My lower back hurts a little today") and uses a generative AI model to generate an appropriate rehabilitation menu and nutrition plan. For example, using the prompt, "Ms. Tanaka, a 75-year-old woman, suffers from lower back pain and aims to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate a healthy menu that puts less strain on her lower back. Please suggest today's menu," it generates "Try five minutes of stretching" as the rehabilitation menu and "Grilled chicken breast and salad made with ingredients that are good for the lower back" as the nutrition plan.

[0546] Step 5:

[0547] The device provides the generated rehabilitation menu and nutrition plan to the user. The device displays the generated menu to the user through its interface and encourages them to follow it. For example, the device may provide a notification such as, "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we suggest grilled chicken breast and a salad, which are good for your lower back."

[0548] Step 6:

[0549] The server manages meal delivery based on the generated nutrition plan. Specifically, it sends the generated meal information to the delivery company's API and arranges for the meal to be delivered to the user's address at the specified time. For example, it issues delivery instructions based on information such as "For tonight's dinner, we'll deliver grilled chicken breast and salad."

[0550] Step 7:

[0551] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback into the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." The server receives this feedback data and adjusts the next rehabilitation and nutrition plan, providing ongoing support.

[0552] Step 8:

[0553] The server adjusts the next rehabilitation and nutrition plan based on the user's feedback. It analyzes the received feedback and uses a generative AI model to optimize the next plan. For example, based on feedback such as "Stretching has become easier, but I would like to make it a little more difficult," it suggests a more intense rehabilitation menu and more nutritious meals for the next time.

[0554] This allows users to receive personalized rehabilitation and nutritional support while improving their quality of life.

[0555] 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.

[0556] Hereinafter, an embodiment of the present invention will be described.

[0557] This invention is a system for promoting rehabilitation for elderly people who require assistance or nursing care, and combines a generative AI model and an emotion engine to provide a rehabilitation menu according to the user's emotional state.

[0558] 1. Enter your user data:

[0559] The device provides an interface for entering basic user information (such as name, age, health condition, and rehabilitation goals). Elderly users enter their own information through this interface. For example, if 75-year-old Mr. Tanaka suffers from back pain and has a rehabilitation goal of "being able to play with his grandchildren in the park," he or she would enter this information.

[0560] 2. Initial setup of the generative AI model:

[0561] The server initializes the generative AI model based on the input user data. The generative AI model is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health condition.

[0562] 3. Initial setting of emotion engine:

[0563] The server initializes the emotion engine, which is designed to analyze the user's input voice and facial expression data and recognize the user's emotional state.

[0564] 4. Dialogue initiation and emotion recognition:

[0565] The generative AI model and emotion engine begin a dialogue with the user via the device. First, a general greeting and a check on the user's health are conducted. For example, a question such as "Hello, Tanaka-san. How are you feeling today?" is asked. Once the user's response (e.g., "My back hurts a little today, but I feel good") is entered, the emotion engine recognizes the user's emotional state from their voice and facial expressions.

[0566] 5. Rehabilitation menu suggestions:

[0567] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[0568] 6. Providing the generated rehabilitation menu:

[0569] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[0570] 7. Gathering Feedback:

[0571] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and their emotional state. For example, the user might input, "After a short stretch, I feel a little better. I'm feeling good."

[0572] 8. Adjusting your next rehabilitation plan:

[0573] Based on user feedback and emotion recognition data from the emotion engine, the server uses a generative AI model to adjust the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[0574] As a specific example, consider a 75-year-old female user named Tanaka. Tanaka's goal is to relieve her lower back pain. Tanaka operates her device to input basic information, and the server initializes the generative AI model and emotion engine. In the first dialogue, Tanaka inputs, "My lower back hurts a little today," and the emotion engine recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." Tanaka then performs rehabilitation and provides feedback, saying, "I feel a little better." The server uses this feedback to adjust the next rehabilitation menu and provides Tanaka with an ongoing rehabilitation menu.

[0575] In this way, this invention provides a personalized rehabilitation menu that takes into account the user's emotional state, promoting effective rehabilitation. Furthermore, by combining generative AI with an emotion engine, it is possible to support the user's psychological and emotional aspects. This is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[0576] The processing flow will be explained below.

[0577] Step 1:

[0578] The device provides an interface for entering basic user information, such as the user's name, age, health condition, and rehabilitation goals. For example, Mr. Tanaka (75 years old) suffers from back pain and enters his goal of "being able to play in the park with his grandchildren."

[0579] Step 2:

[0580] The server initializes the generative AI model based on the acquired user data, which reflects the user's rehabilitation goals and health status.

[0581] Step 3:

[0582] The server initializes the emotion engine, which analyzes the user's input voice and facial expression data and prepares it to recognize the user's emotional state.

[0583] Step 4:

[0584] Through the device, the generative AI model and emotion engine begin a dialogue with the user, starting with a general greeting such as "Hello, how are you feeling today?" and a check-up on their health.

[0585] Step 5:

[0586] The user responds to questions posed by the AI ​​generator, for example, by typing, "My back hurts a little today."

[0587] Step 6:

[0588] The server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and the analysis results are embodied as "I feel good, but I have back pain."

[0589] Step 7:

[0590] The server uses a generative AI model to generate a rehabilitation menu based on user data and emotion analysis results. This rehabilitation menu takes into account the user's emotional state. For example, it might suggest, "You have lower back pain, so try some short, relaxing stretches without overdoing it."

[0591] Step 8:

[0592] The terminal provides the generated rehabilitation menu to the user, allowing the user to receive specific instructions and begin rehabilitation.

[0593] Step 9:

[0594] The user performs the provided rehabilitation program and provides feedback on the results and their impressions via the device. For example, they can send feedback such as, "I felt a little better after doing some short stretches."

[0595] Step 10:

[0596] The server adjusts the next rehabilitation plan based on the user's feedback and the emotion analysis results of the emotion engine. The generative AI model generates the next rehabilitation menu based on the new feedback.

[0597] Specifically, in Tanaka's case,

[0598] 1. Enter your name, age, health condition, and rehabilitation goals on the device.

[0599] 2. Initialize the generated AI model on the server.

[0600] 3. Initialize the emotion engine on the server.

[0601] 4. Ask Tanaka from the device, "How are you feeling today?"

[0602] 5. User Tanaka replies, "My back hurts a little today."

[0603] 6. The server uses its emotion engine to analyze Tanaka's situation and conclude that "I feel good, but I have back pain."

[0604] 7. The server suggested "short, relaxed stretches for lower back pain."

[0605] 8. Provide rehabilitation menu suggestions on the terminal.

[0606] 9. User Tanaka underwent rehabilitation and gave feedback that "stretching made me feel a little better."

[0607] 10. The server adjusts the next rehabilitation plan based on the feedback and emotion engine data.

[0608] This allows Tanaka to continually acquire and implement rehabilitation programs that suit his emotional state. By repeating this process, the elderly person's motivation can be maintained, enabling high-quality rehabilitation.

[0609] Example 2

[0610] 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."

[0611] To effectively promote elderly rehabilitation, it is important to provide a personalized rehabilitation menu tailored to each individual. However, conventional systems often provide a uniform rehabilitation menu without considering the user's emotional state, which can lead to a decline in user motivation. While there are also systems that adjust rehabilitation plans based on user feedback, most of these systems do not take into account feedback about the user's emotional state, and therefore are unable to provide adequately personalized support. This can lead to a decline in elderly people's motivation to undergo rehabilitation, making it difficult for them to continue.

[0612] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0613] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for initializing the emotion engine, means for initiating a dialogue with the user using the generative AI model and the emotion engine and recognizing the emotional state, means for analyzing the user's input and emotional state to generate motivational questions and a rehabilitation menu, means for providing the generated rehabilitation menu to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration, thereby increasing the elderly's motivation for rehabilitation and promoting continued rehabilitation.

[0614] The "means for acquiring basic information about the user" is a mechanism for providing an interface that allows the user to input information such as their name, age, health condition, and rehabilitation goals.

[0615] The "means for initializing the generative AI model" is a function that configures the generative AI model based on the user's basic information, enabling the generation of a rehabilitation menu that is optimal for the user.

[0616] The "means for initializing the emotion engine" is a means for setting up an emotion engine that can analyze the user's voice and facial expression data, and for preparing to recognize the user's emotional state.

[0617] "Means for initiating a dialogue with a user and recognizing the emotional state using a generative AI model and an emotion engine" refers to a mechanism that links a generative AI model with an emotion engine to identify the emotional state from voice and facial expressions through dialogue with the user.

[0618] "Means for analyzing a user's input and emotional state to generate questions and rehabilitation menus that motivate the user" refers to a method for generating questions and appropriate rehabilitation menus that motivate the user based on the user's input and emotional state.

[0619] "Means for providing the generated rehabilitation menu to the user" refers to a mechanism that provides an interface for presenting the rehabilitation menu created by the generative AI model to the user and having them carry it out.

[0620] The "means for adjusting the next rehabilitation plan based on feedback from the user" is a method for analyzing the feedback and emotion recognition data provided by the user after rehabilitation and optimizing the next rehabilitation menu.

[0621] A specific example for implementing the present invention will be described. The present invention is a system that provides a personalized rehabilitation menu that takes into account the user's basic information and emotional state in order to effectively promote rehabilitation for elderly people. The specific configuration and operation of this system will be described below.

[0622] Entering User Data

[0623] The terminal provides an interface for inputting the user's basic information. This interface includes input fields for name, age, health condition, rehabilitation purpose, etc. The user enters information in these fields and clicks the send button to send the data. This inputs the user's basic information into the system.

[0624] Initial setup of generative AI models

[0625] The server receives basic information entered by the user and uses it to initialize the generative AI model, which is then configured to generate an optimal rehabilitation menu for each individual user, taking into account their rehabilitation goals and health condition.

[0626] Initial setting of emotion engine

[0627] The server initializes the emotion engine, which is designed to analyze the user's voice and facial expression data and recognize the user's emotional state. The server loads the voice recognition module and facial expression recognition module into the emotion engine and verifies that they are working properly.

[0628] Dialogue initiation and emotion recognition

[0629] The device uses a generative AI model and an emotion engine to initiate a dialogue with the user. First, a general greeting and a health check are performed. For example, a question such as "Hello, how are you feeling today?" is displayed and played back. The user's response is input via voice or text, and the device sends that data to the emotion engine. The emotion engine recognizes the user's emotional state from their voice and facial expressions.

[0630] Rehabilitation menu suggestions

[0631] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and proposes the optimal rehabilitation menu for the user. For example, it might generate a menu such as, "You have lower back pain today, so let's start with a short stretch without overdoing it. Can you do it while relaxing?"

[0632] Providing the generated rehabilitation menu

[0633] The terminal presents the generated rehabilitation menu to the user, who then checks the rehabilitation menu displayed on the terminal and performs rehabilitation according to the instructions.

[0634] Gathering feedback

[0635] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and emotional state. For example, the user can input something like, "After a short stretch, I feel a little better. I'm feeling good."

[0636] Adjusting the next rehabilitation plan

[0637] The server updates the generative AI model based on user feedback and recognition data from the emotion engine, adjusting the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[0638] Specific examples

[0639] For example, if a 75-year-old user has a goal of relieving lower back pain, the system operates as follows: The user enters basic information such as "I have lower back pain, and my goal for rehabilitation is to be able to play at the park with my grandchildren." The server initializes the generative AI model and emotion engine, and asks "How are you feeling today?" in the first dialogue. If the user replies "My lower back hurts a little," the emotion engine recognizes this as "I feel good." The generative AI model suggests a rehabilitation menu such as "When you have lower back pain, do you do short stretches?" After completing the rehabilitation, the user provides feedback such as "I feel a little better." The server then adjusts the next rehabilitation plan and provides it to the user.

[0640] Prompt Sentence Examples

[0641] 1. "What is the goal of rehabilitation?"

[0642] 2. "How are you feeling?"

[0643] 3. "How did you feel about the rehabilitation program?"

[0644] In this way, providing a personalized rehabilitation menu that takes into account the user's emotional state can increase the elderly person's motivation for rehabilitation and promote continued rehabilitation.

[0645] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0646] Step 1: Enter user data

[0647] The terminal provides an interface for users to enter basic information, including fields for name, age, health status, rehabilitation goals, etc.

[0648] Specific operation: When the user enters information into these fields and clicks the submit button, the device sends the data to the server.

[0649] Input: User's basic information (name, age, health condition, rehabilitation purpose, etc.)

[0650] Output: Basic information about the user sent to the server

[0651] Step 2: Initializing the Generative AI Model

[0652] The server performs initial settings for the generative AI model based on the received user data.

[0653] Specific operation: The server inputs user data into the generative AI model and creates personalized settings based on rehabilitation goals and health status, enabling the generation of an individual rehabilitation menu.

[0654] Input: User basic information

[0655] Output: Initialized generative AI model

[0656] Step 3: Initializing the Emotion Engine

[0657] The server initializes the emotion engine, which includes a voice recognition module and a facial expression recognition module.

[0658] Specific operation: The server loads the necessary modules (voice and facial expression recognition) into the emotion engine, preparing it to analyze the user's emotional state.

[0659] Input: Required modules

[0660] Output: Initialized emotion engine

[0661] Step 4: Initiating a dialogue and recognizing emotions

[0662] The device initiates a dialogue with the user using a generative AI model and an emotion engine.

[0663] Specific operation: The device activates voice input and camera functions and presents prompts to the user. The user's response is sent to the emotion engine, which recognizes the user's emotional state from their voice and facial expressions. For example, the device asks, "How are you feeling today?" and the user replies, "My back hurts a little." The emotion engine analyzes this response and recognizes the user's emotional state.

[0664] Input: User voice or text input

[0665] Output: Recognized emotional state of the user

[0666] Step 5: Proposing a rehabilitation menu

[0667] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates a rehabilitation menu.

[0668] Specific operation: The generative AI model generates a rehabilitation menu based on the user's health and emotional state. For example, it may suggest, "If you have lower back pain, start with a short stretch without overdoing it."

[0669] Input: User's emotional state, health status

[0670] Output: Generated rehabilitation menu

[0671] Step 6: Providing the generated rehabilitation menu

[0672] The terminal presents the generated rehabilitation menu to the user.

[0673] Specific operation: The device displays a rehabilitation menu on the screen and guides the user to confirm and carry out the rehabilitation menu.

[0674] Input: Generated rehabilitation menu

[0675] Output: Rehabilitation menu confirmed by the user

[0676] Step 7: Gather feedback

[0677] The user carries out the proposed rehabilitation menu and feeds back the results and emotional state to the server via the terminal.

[0678] Specific operation: The user uses the device to input and send feedback such as, "I felt a little better after doing a short stretch."

[0679] Input: User feedback

[0680] Output: Feedback sent to the server

[0681] Step 8: Adjust your next rehabilitation plan

[0682] The server uses user feedback and data from the emotion engine to allow the generative AI model to adjust the next rehabilitation plan.

[0683] Specific actions: The server analyzes the received feedback and data and optimizes the next rehabilitation menu, for example, planning to "do the same stretches for a little longer next time, and add new exercises if you feel better."

[0684] Input: User feedback, emotional state

[0685] Output: Adjusted next rehabilitation menu

[0686] (Application example 2)

[0687] 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."

[0688] In elderly rehabilitation, there is a need to provide personalized rehabilitation menus that correspond to each individual's emotions and health status. However, current systems have difficulty accurately recognizing the user's emotional state and presenting appropriate rehabilitation menus based on that. Furthermore, they lack a mechanism for effectively collecting feedback from users and reflecting it in the next rehabilitation menu. This situation reduces the motivation of elderly people to continue rehabilitation, and there is a problem in that rehabilitation is not fully effective.

[0689] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0690] In this invention, the server includes emotion recognition means, means for initializing the generative AI model, means for starting a dialogue with the user, means for analyzing the user's input and emotional state and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration and improve the user's motivation for rehabilitation.

[0691] The "means for obtaining basic information" is an interface for inputting and collecting basic information such as the user's name, age, health condition, and rehabilitation goals.

[0692] A "generative AI model" is an artificial intelligence model that generates a personalized rehabilitation menu based on the user's rehabilitation goals and health condition.

[0693] The "means for initiating dialogue" is a mechanism for initiating an initial dialogue between the user and the generative AI model and emotion recognition system.

[0694] An "emotion recognition means" is a system or device designed to analyze and recognize a user's emotional state from their voice and facial expressions.

[0695] "Emotional state" refers to the psychological and emotional state of the user when undergoing rehabilitation, such as feeling good, bad, tired, etc.

[0696] The "means for generating questions and rehabilitation menus" refers to an algorithm or system that analyzes the user's basic information and emotional state, and automatically creates questions and rehabilitation menus that motivate the user.

[0697] The "means for providing a rehabilitation menu" is an interface that displays or conveys the generated rehabilitation menu to the user.

[0698] The "means for adjusting the next rehabilitation plan based on feedback" is a system that optimizes and adjusts the next rehabilitation menu based on feedback collected from the user about the rehabilitation results and emotional state.

[0699] This invention is a system for promoting rehabilitation for elderly people who require assistance or care, and combines a generative AI model and emotion recognition means to provide a rehabilitation menu that corresponds to the user's emotional state.

[0700] This system is implemented according to the following procedure.

[0701] First, the user uses a terminal to input basic information (name, age, health condition, rehabilitation goals, etc.). This basic information can be acquired, for example, through the interface of a tablet or smartphone. Specifically, the information entered is "75-year-old elderly person suffering from back pain."

[0702] The server then initializes a generative AI model based on the acquired user data, which is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health status.

[0703] Next, the server initializes the emotion recognition means. This emotion recognition means analyzes the user's input voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to collect and analyze the user's facial expressions and voice.

[0704] The generative AI model and emotion recognition system then begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, a question like "Hello, how are you feeling today?" is asked, and when the user responds (e.g., "My back hurts a little today, but I'm feeling good"), the emotion recognition means recognizes their emotional state from their voice and facial expression.

[0705] Next, the server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion recognition means, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[0706] The generated rehabilitation menu is provided to the user via the terminal, and the user can follow the menu to carry out rehabilitation.

[0707] The user provides feedback on the results of the rehabilitation and their emotional state. For example, they might say, "I felt a little better after a short stretch. I'm feeling good." Based on this feedback, the server uses the generative AI model and emotion recognition tools to adjust the next rehabilitation plan. For example, the server might adjust the plan so that next time, the user performs the same stretches for a little longer, and add a new exercise if they feel better.

[0708] The hardware required is a camera and microphone, which are used to capture the user's facial expressions and voice. For software, the OpenCV library is used for computer vision, and the emotion recognition model is implemented using the TensorFlow / Keras model. For generative AI models, high-performance generative models such as GPT-3 are used.

[0709] As a concrete example, suppose a 75-year-old female user has a rehabilitation goal of relieving lower back pain. She operates the device to input her basic information, and the server initializes the generative AI model and emotion recognition means. In the first dialogue, she inputs, "My lower back hurts a little today," and the emotion recognition means recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." The user performs this rehabilitation menu and provides feedback that "it feels a little better." The server uses this feedback to adjust the next rehabilitation menu and provides the user with an ongoing rehabilitation menu.

[0710] An example of a prompt is as follows:

[0711] User data: {Name: "Tanaka", Age: 75, Health condition: "Low back pain", Rehabilitation goal: "Playing with grandchildren in the park"},

[0712] Emotional state: "Energetic"

[0713] Generate an appropriate rehabilitation menu.

[0714] This system provides a personalized rehabilitation menu that takes into account the user's emotional state, improving the user's motivation for rehabilitation and supporting continuous rehabilitation.

[0715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0716] Step 1:

[0717] The user uses a terminal to input basic information (such as name, age, health status, rehabilitation goals, etc.). This basic information is sent to the server through the terminal interface. The input data is stored on the server as the user's personalized profile.

[0718] Step 2:

[0719] The server initializes the generative AI model based on the acquired user data. The AI ​​model used here is configured to generate an optimal rehabilitation menu based on the user's rehabilitation goals and health condition. This initialization takes the user's basic information as input and outputs a rehabilitation menu template.

[0720] Step 3:

[0721] The server initializes the emotion recognition means. This emotion recognition means analyzes the user's voice and facial expression data acquired from the terminal and recognizes the user's emotional state. For example, a model is set up that acquires the user's voice and video data using a camera and microphone, and uses this as input to output the user's emotional state.

[0722] Step 4:

[0723] The generative AI model and emotion recognition system begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, the device may ask the user, "Hello, how are you feeling today?" The user's response (e.g., "My back hurts a little today, but I feel good") is entered and sent to the server.

[0724] Step 5:

[0725] The server uses emotion recognition means to analyze the user's emotional state and inputs this into the generative AI model. This generates questions and rehabilitation menus that take the user's emotional state into consideration and motivate them. For example, a rehabilitation menu such as "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try it while relaxing?" is generated and output.

[0726] Step 6:

[0727] The generated rehabilitation menu is provided to the user via a terminal, and the user then follows the menu to carry out rehabilitation. Because the rehabilitation menu is optimized based on the user's current situation and emotional state, effective rehabilitation can be expected.

[0728] Step 7:

[0729] The user provides feedback on the results of the rehabilitation and their emotional state, for example, "I feel a little better after a short stretch. I'm feeling good," which is input into the device and sent to the server.

[0730] Step 8:

[0731] Based on the user's feedback and data from the emotion recognition tool, the generative AI model adjusts the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better." This information is provided to the user during their next rehabilitation session.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] [Third embodiment]

[0736] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0737] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0738] 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).

[0739] 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.

[0740] 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.

[0741] 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).

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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."

[0748] Hereinafter, an embodiment of the present invention will be described.

[0749] This invention is a system that uses generative AI models to promote rehabilitation for elderly people. Specifically, it consists of the following elements:

[0750] 1. Enter your user data:

[0751] The terminal provides an interface for acquiring basic information about the user (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and their rehabilitation goal is to be able to play in the park with their grandchildren, they would input this information.

[0752] 2. Initial setup of the generative AI model:

[0753] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals and health status, preparing the system to generate the optimal rehabilitation menu for each individual user.

[0754] 3. Initiating dialogue and proposing rehabilitation options:

[0755] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Then, based on the user's answer (e.g., "My lower back hurts a little today"), the generative AI model suggests an appropriate rehabilitation menu. The rehabilitation menu suggested might be something like, "If you have lower back pain, start with some short stretches without overdoing it. What do you think?"

[0756] 4. Ongoing rehabilitation support:

[0757] The user performs the proposed rehabilitation program and inputs the results and feedback to the server via their device. For example, the user might say, "I felt a little better after doing some short stretches." Based on this information, the generative AI model adjusts the next rehabilitation plan and provides ongoing support.

[0758] As a concrete example, let's say there is a 75-year-old female user (let's call her Tanaka). Tanaka's goal is to relieve her lower back pain. Tanaka operates the device to input basic information, and the generative AI model performs initial settings based on her information. In the first dialogue, Tanaka inputs, "My lower back hurts a little today." The generative AI model analyzes this and suggests, "If you have lower back pain, try doing five minutes of stretching." Tanaka follows this suggestion, performs the stretches, and provides feedback that, as a result, "I feel a little better." The server receives this feedback, adjusts the next rehabilitation plan, and continues to provide Tanaka with a continuous rehabilitation menu.

[0759] In this way, a personalized rehabilitation menu tailored to each user's needs is generated, and the generation AI asks in-depth questions to ensure a satisfactory rehabilitation experience. This system is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] The terminal provides an interface for inputting basic user information (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, a 75-year-old senior citizen inputs their rehabilitation goal of "being able to play in the park with their grandchildren" and their health condition of lower back pain.

[0763] Step 2:

[0764] The server initializes the generative AI model based on the input user data. This initial setting takes into account the user's rehabilitation goals and health status, and helps generate a personalized rehabilitation menu.

[0765] Step 3:

[0766] Through the device, the generative AI model begins a dialogue with the user, starting with general exchanges such as greetings and checking in on how you're feeling. For example, the model might ask questions like, "Hello, how are you?"

[0767] Step 4:

[0768] The user responds to questions posed by the generative AI model, for example, by typing, "My back hurts a little today."

[0769] Step 5:

[0770] The server analyzes user input in real time. The generative AI model generates motivational questions and rehabilitation menus based on the user's input. For example, it might generate a menu that suggests, "If you have lower back pain, try doing some short stretches without straining yourself."

[0771] Step 6:

[0772] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[0773] Step 7:

[0774] The user carries out the proposed rehabilitation program and provides feedback on the results to the server via the terminal, for example, by inputting something like, "I did a short stretch and felt a little better."

[0775] Step 8:

[0776] The server adjusts the next rehabilitation plan based on the user's feedback. The generative AI model takes the new feedback into account and generates the next rehabilitation menu and motivational questions. This loop enables continuous rehabilitation support.

[0777] Example 1

[0778] 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."

[0779] Rehabilitation for elderly people requires personalization based on each individual's health condition and rehabilitation goals, while continuity is also important. However, conventional rehabilitation systems and programs are unable to flexibly respond to individual needs, making it difficult for users to maintain their motivation. Furthermore, they lack the functionality to continuously adjust the next rehabilitation plan based on user feedback, making it difficult to achieve effective rehabilitation.

[0780] 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.

[0781] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for starting a dialogue with the user using the generative AI model, means for analyzing the user's input and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, means for adjusting the next rehabilitation plan based on feedback from the user, and means for transmitting feedback to the server via the terminal. This makes it possible to provide an individually customized rehabilitation menu, thereby enabling users to maintain their motivation and achieve effective rehabilitation.

[0782] "Means for obtaining basic user information" refers to equipment or software for inputting and collecting personal information such as the user's age, health condition, and rehabilitation goals.

[0783] The "means for initializing the generative AI model" refers to the process of customizing the generative AI model based on the collected basic information of the user and performing initial settings to generate an individual rehabilitation menu.

[0784] "Means for initiating a dialogue with a user using a generative AI model" refers to a function for initiating an interactive dialogue with a user using a generative AI model and checking the user's situation and state.

[0785] The "means for analyzing user input and generating motivational questions and rehabilitation menus" refers to a process for analyzing the current situation and condition input by the user and generating motivational questions and individually customized rehabilitation menus based on the results.

[0786] "Means for providing the generated rehabilitation menu to the user" refers to a function that displays the rehabilitation menu created by the generative AI model in a visible form to the user and encourages them to carry it out.

[0787] "Means for adjusting the next rehabilitation plan based on user feedback" refers to the process of collecting and analyzing the results and impressions of the user's rehabilitation, and then adjusting the next rehabilitation menu and plan based on that information.

[0788] The "means for transmitting feedback to the server via the terminal" is a function that allows the user to use the terminal to input the results of the rehabilitation menu implementation and feedback, and transmit this to the server.

[0789] A "generative AI model" is a model that uses artificial intelligence technology to generate rehabilitation menus and dialogues that meet the individual needs of each user.

[0790] A "rehabilitation menu" is a specific exercise and training plan proposed for the user to undergo rehabilitation.

[0791] "Feedback" is information about the rehabilitation results, such as the user's impressions after completing the rehabilitation menu and changes in physical condition.

[0792] The following describes an embodiment of the present invention. The present invention is a system that promotes rehabilitation for elderly people by using a generative AI model. Specifically, it is composed of the following elements:

[0793] Entering User Data

[0794] The device provides an interface for acquiring basic information about the user. This interface is displayed on a computer, tablet, or smartphone (Windows, iOS, Android, etc.). The user enters their own information through this interface. For example, information such as name, age, health condition, and rehabilitation goals may be entered. As a specific example, a 75-year-old user may enter "back pain" and the rehabilitation goal of "being able to play in the park with my grandchildren."

[0795] Initial setup of generative AI models

[0796] The server receives user data sent from the device. The received data includes the user's basic information and rehabilitation goals. The server initializes a generative AI model (such as GPT-4) and customizes it taking into account the user's rehabilitation goals and health condition. This completes the process of generating the optimal rehabilitation menu for each individual user.

[0797] Initiating dialogue and proposing rehabilitation menus

[0798] The device launches the generative AI model sent from the server and begins a dialogue session. An initial greeting and questions to check the user's health are displayed. For example, a question such as "Hello, how are you feeling today?" is presented. The user responds to this question with, for example, "My lower back hurts a little today." The device inputs the user's response into the generative AI model and suggests an appropriate rehabilitation menu. For example, a specific rehabilitation menu such as "If you have lower back pain, try doing five minutes of stretching" is presented.

[0799] Ongoing rehabilitation support

[0800] The user performs the proposed rehabilitation menu and inputs the results and feedback into the device. For example, the user may input feedback such as, "I felt a little better after doing a short stretch." The server receives this feedback and uses the generative AI model to adjust the next rehabilitation menu. The new rehabilitation menu is then proposed to the user again via the device. For example, a suggestion may be made such as, "Next time, try stretching for a longer period of time."

[0801] Specific examples

[0802] Mr. Tanaka, 75, begins rehabilitation to relieve his lower back pain. Mr. Tanaka enters his name and rehabilitation goals into the device, which the server receives. The generative AI model is initialized and asked through dialogue, "How are you feeling today?" When Mr. Tanaka responds, "My lower back hurts a little today," the generative AI model suggests a rehabilitation menu: "If you have lower back pain, try doing five minutes of stretching." When Mr. Tanaka performs the menu and sends feedback saying, "I feel a little better," the server adjusts the next rehabilitation menu and makes new suggestions.

[0803] Prompt Sentence Examples

[0804] Suggest an appropriate rehabilitation program for a 75-year-old woman with back pain. Her goal is to be able to play with her grandchildren at the park.

[0805] The present invention aims to provide a rehabilitation menu tailored to the individual needs of the user, thereby maintaining motivation and achieving effective rehabilitation. Furthermore, by continuously adjusting the rehabilitation plan based on feedback from the user, more personalized rehabilitation is possible.

[0806] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0807] Step 1:

[0808] The terminal displays an interface for obtaining basic information about the user.

[0809] Input: Basic information such as your name, age, health status, and rehabilitation goals

[0810] Specific behavior: A form or question is displayed, and the user fills in the relevant fields. For example, the user enters "back pain" and the goal "I want to be able to play in the park with my grandchildren."

[0811] Output: The entered user information is saved on the device.

[0812] Step 2:

[0813] The terminal transmits the collected user basic information to the server.

[0814] Input: User information stored on the device

[0815] Specific operation: When the user has finished entering information, they press the "Submit" button to send the data to the server.

[0816] Output: The server receives the user basic information.

[0817] Step 3:

[0818] The server initializes the generative AI model based on the received basic information.

[0819] Input: User's basic information (name, age, health status, rehabilitation goals, etc.)

[0820] Specific operation: User information is input into the generative AI model to create customized settings.

[0821] Output: A customized generative AI model is generated.

[0822] Step 4:

[0823] The server sends the initially configured generative AI model to the device.

[0824] Input: A customized generative AI model

[0825] Specific operation: The server sends data over the network to transmit the AI ​​model to the device.

[0826] Output: The device receives the generated AI model.

[0827] Step 5:

[0828] The device launches the generative AI model and begins a dialogue with the user.

[0829] Input: Generative AI model

[0830] Specific behavior: The device uses the generative AI model to conduct an initial interaction (e.g., greeting or checking how you are feeling). For example, it might ask, "Hello, how are you feeling today?"

[0831] Output: User input in response to a question (e.g., "My back hurts a little today").

[0832] Step 6:

[0833] The device inputs the user's answers into a generative AI model and suggests an appropriate rehabilitation menu.

[0834] Input: User response (e.g., "My back hurts a little today.")

[0835] Specific operation: The generative AI model analyzes the user's answers and generates an appropriate rehabilitation menu (e.g., "Try five minutes of stretching").

[0836] Output: The suggested rehabilitation menu is displayed to the user.

[0837] Step 7:

[0838] The user carries out the proposed rehabilitation menu and inputs the results and feedback into the terminal.

[0839] Input: Results and impressions of the rehabilitation menu performed by the user (e.g., "I feel a little better").

[0840] Specific operation: The user performs the rehabilitation menu and then inputs feedback into the terminal.

[0841] Output: The entered feedback is saved on the device.

[0842] Step 8:

[0843] The terminal transmits the user's feedback to the server.

[0844] Input: User feedback (e.g., "This is a bit easier now.")

[0845] Specific operation: The device sends data over the network to send feedback to the server.

[0846] Output: The server receives the feedback.

[0847] Step 9:

[0848] The server adjusts the generative AI model based on the feedback and generates the next rehabilitation menu.

[0849] Input: User feedback (e.g., "This is a bit easier now.")

[0850] Specific operation: The generative AI model analyzes the feedback and generates the next rehabilitation menu (e.g., "Try a longer stretch next time").

[0851] Output: A tailored rehabilitation menu is generated.

[0852] Step 10:

[0853] The server transmits a new rehabilitation menu to the terminal, which then provides it to the user.

[0854] Enter: Adjusted Rehab Menu

[0855] Specific operation: The server sends the rehabilitation menu to the terminal, and the terminal displays it to the user.

[0856] Output: The new rehab menu is displayed to the user.

[0857] (Application example 1)

[0858] 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."

[0859] When elderly people undergo rehabilitation, maintaining their motivation and providing them with an appropriate rehabilitation menu are important, but dietary habits that help them maintain a healthy lifestyle are equally important. However, there is no system that integrates personalized nutrition planning and meal delivery, making it difficult for elderly people to effectively undergo rehabilitation while eating a healthy diet. The present invention aims to solve this problem by providing a system that allows elderly people to consume appropriate nutrition while undergoing rehabilitation.

[0860] 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.

[0861] In this invention, the server includes a means for acquiring basic information about the user, a means for initializing the generative AI model, a means for analyzing the user's input and generating motivational questions and rehabilitation menus, and a means for using the generative AI model to propose a nutrition plan suitable for the user and manage meal delivery. This makes it possible to use the generative AI model not only to personalize rehabilitation menus but also to propose optimal nutrition plans for individual users and smoothly manage meal delivery.

[0862] The "means for acquiring basic information about the user" is a means for collecting data such as the user's personal information, health condition, rehabilitation goals, etc. via the terminal.

[0863] The "means for initially setting the generative AI model" is a means for setting the generative AI model to an appropriate state based on collected user information.

[0864] "Means for initiating a dialogue with a user using a generative AI model" refers to means for initiating communication with a user using a generative AI model.

[0865] The "means for analyzing user input and generating questions and rehabilitation menus that will motivate the user" refers to a means for proposing questions and rehabilitation menus that are optimal for the user based on the data input by the user.

[0866] The "means for providing the generated rehabilitation menu to the user" refers to a means for presenting the generated rehabilitation menu to the user and encouraging them to carry it out.

[0867] The "means for adjusting the next rehabilitation plan based on feedback from the user" refers to a means for analyzing feedback provided by the user and adjusting the next rehabilitation plan based on the feedback.

[0868] "Means for using a generative AI model to propose an optimal nutrition plan for a user and manage meal delivery" refers to a means for generating an optimal nutrition plan based on user information and managing meal ordering and delivery in accordance with that plan.

[0869] This invention is a system that uses generative AI models to provide rehabilitation and nutritional planning for seniors and manage meal delivery. The system consists of the following components:

[0870] 1. Enter your user data:

[0871] The terminal provides an interface for obtaining basic information about the user (such as name, age, health condition, rehabilitation goals, food preferences, and allergy information). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and a rehabilitation goal of "being able to play in the park with their grandchildren," and is also allergic to certain foods, this information can be entered.

[0872] 2. Initial setup of the generative AI model:

[0873] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals, health status, dietary preferences, and allergy information. This sets the stage for generating an optimal rehabilitation menu and nutrition plan for each individual user.

[0874] 3. Initiating a dialogue and proposing rehabilitation and nutritional plans:

[0875] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health, followed by a rehabilitation menu and nutrition plan. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Based on the user's answers, a rehabilitation menu and nutrition plan is then presented, such as "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we'll suggest a menu using ingredients that are good for your lower back."

[0876] 4. Meal delivery management:

[0877] The server manages meal delivery based on the generated nutrition plan. Specifically, it coordinates with delivery companies to arrange for meals appropriate for the user to be delivered at the specified time. For example, information such as "Grilled chicken breast and salad will be delivered for dinner tonight" is sent to the device, and the meal is delivered at the specified time.

[0878] 5. Ongoing rehabilitation and nutritional support:

[0879] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback to the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." Based on this information, the generative AI model adjusts the next rehabilitation and nutrition plan and provides ongoing support.

[0880] Hardware and software used:

[0881] Smartphone: A device for installing the app. Supports iOS or Android.

[0882] React Native: A cross-platform framework used to develop mobile applications.

[0883] Firebase: Used as a database to store and retrieve user data.

[0884] OpenAI API: Uses a generative AI model (GPT-4) to generate rehabilitation menus and nutrition plans.

[0885] Node.js: Manages the server-side logic and communicates with the generative AI model.

[0886] Examples of prompts:

[0887] Prompt for Mr. Tanaka (75 years old, suffers from back pain) who has the goal of "being able to play in the park with his grandchildren."

[0888] "Ms. Tanaka, a 75-year-old woman, suffers from back pain and wants to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate healthy menus that don't put strain on her back. Please suggest today's menu."

[0889] This system will enable elderly people to receive personalized support in both rehabilitation and nutrition, which is expected to improve their quality of life.

[0890] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0891] Step 1:

[0892] The terminal obtains basic information about the user. Specifically, it provides an interface where the user can input their name, age, health condition, rehabilitation goal, food preferences, allergy information, etc. This data is collected and sent to the server. The input data includes name = "Mr. Tanaka", age = "75 years old", health condition = "suffers from back pain", rehabilitation goal = "to be able to play in the park with my grandchildren", food preferences = "Japanese food", and allergy information = "shellfish allergy". This information is transferred to the server.

[0893] Step 2:

[0894] The server initializes the generative AI model based on the received user data. During this process, the settings of the generative AI model are customized based on the received data (name, age, health condition, rehabilitation goals, dietary preferences, and allergy information). For example, taking into account Mr. Tanaka's age and health condition, the server generates prompts for generating a rehabilitation menu and nutrition plan that is effective for his lower back pain.

[0895] Step 3:

[0896] The device uses the generative AI model to initiate a dialogue with the user. Specifically, the device uses the generated prompt to greet the user and ask questions about their health. A message such as "Hello, how are you feeling today?" is displayed. The user's response is received as input and analyzed in the next processing step.

[0897] Step 4:

[0898] The server analyzes the user's input and generates a rehabilitation menu and nutrition plan. It analyzes the captured user's response data (e.g., "My lower back hurts a little today") and uses a generative AI model to generate an appropriate rehabilitation menu and nutrition plan. For example, using the prompt, "Ms. Tanaka, a 75-year-old woman, suffers from lower back pain and aims to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate a healthy menu that puts less strain on her lower back. Please suggest today's menu," it generates "Try five minutes of stretching" as the rehabilitation menu and "Grilled chicken breast and salad made with ingredients that are good for the lower back" as the nutrition plan.

[0899] Step 5:

[0900] The device provides the generated rehabilitation menu and nutrition plan to the user. The device displays the generated menu to the user through its interface and encourages them to follow it. For example, the device may provide a notification such as, "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we suggest grilled chicken breast and a salad, which are good for your lower back."

[0901] Step 6:

[0902] The server manages meal delivery based on the generated nutrition plan. Specifically, it sends the generated meal information to the delivery company's API and arranges for the meal to be delivered to the user's address at the specified time. For example, it issues delivery instructions based on information such as "For tonight's dinner, we'll deliver grilled chicken breast and salad."

[0903] Step 7:

[0904] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback into the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." The server receives this feedback data and adjusts the next rehabilitation and nutrition plan, providing ongoing support.

[0905] Step 8:

[0906] The server adjusts the next rehabilitation and nutrition plan based on the user's feedback. It analyzes the received feedback and uses a generative AI model to optimize the next plan. For example, based on feedback such as "Stretching has become easier, but I would like to make it a little more difficult," it suggests a more intense rehabilitation menu and more nutritious meals for the next time.

[0907] This allows users to receive personalized rehabilitation and nutritional support while improving their quality of life.

[0908] 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.

[0909] Hereinafter, an embodiment of the present invention will be described.

[0910] This invention is a system for promoting rehabilitation for elderly people who require assistance or nursing care, and combines a generative AI model and an emotion engine to provide a rehabilitation menu according to the user's emotional state.

[0911] 1. Enter your user data:

[0912] The device provides an interface for entering basic user information (such as name, age, health condition, and rehabilitation goals). Elderly users enter their own information through this interface. For example, if 75-year-old Mr. Tanaka suffers from back pain and has a rehabilitation goal of "being able to play with his grandchildren in the park," he or she would enter this information.

[0913] 2. Initial setup of the generative AI model:

[0914] The server initializes the generative AI model based on the input user data. The generative AI model is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health condition.

[0915] 3. Initial setting of emotion engine:

[0916] The server initializes the emotion engine, which is designed to analyze the user's input voice and facial expression data and recognize the user's emotional state.

[0917] 4. Dialogue initiation and emotion recognition:

[0918] The generative AI model and emotion engine begin a dialogue with the user via the device. First, a general greeting and a check on the user's health are conducted. For example, a question such as "Hello, Tanaka-san. How are you feeling today?" is asked. Once the user's response (e.g., "My back hurts a little today, but I feel good") is entered, the emotion engine recognizes the user's emotional state from their voice and facial expressions.

[0919] 5. Rehabilitation menu suggestions:

[0920] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[0921] 6. Providing the generated rehabilitation menu:

[0922] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[0923] 7. Gathering Feedback:

[0924] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and their emotional state. For example, the user might input, "After a short stretch, I feel a little better. I'm feeling good."

[0925] 8. Adjusting your next rehabilitation plan:

[0926] Based on user feedback and emotion recognition data from the emotion engine, the server uses a generative AI model to adjust the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[0927] As a specific example, consider a 75-year-old female user named Tanaka. Tanaka's goal is to relieve her lower back pain. Tanaka operates her device to input basic information, and the server initializes the generative AI model and emotion engine. In the first dialogue, Tanaka inputs, "My lower back hurts a little today," and the emotion engine recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." Tanaka then performs rehabilitation and provides feedback, saying, "I feel a little better." The server uses this feedback to adjust the next rehabilitation menu and provides Tanaka with an ongoing rehabilitation menu.

[0928] In this way, this invention provides a personalized rehabilitation menu that takes into account the user's emotional state, promoting effective rehabilitation. Furthermore, by combining generative AI with an emotion engine, it is possible to support the user's psychological and emotional aspects. This is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[0929] The processing flow will be explained below.

[0930] Step 1:

[0931] The device provides an interface for entering basic user information, such as the user's name, age, health condition, and rehabilitation goals. For example, Mr. Tanaka (75 years old) suffers from back pain and enters his goal of "being able to play in the park with his grandchildren."

[0932] Step 2:

[0933] The server initializes the generative AI model based on the acquired user data, which reflects the user's rehabilitation goals and health status.

[0934] Step 3:

[0935] The server initializes the emotion engine, which analyzes the user's input voice and facial expression data and prepares it to recognize the user's emotional state.

[0936] Step 4:

[0937] Through the device, the generative AI model and emotion engine begin a dialogue with the user, starting with a general greeting such as "Hello, how are you feeling today?" and a check-up on their health.

[0938] Step 5:

[0939] The user responds to questions posed by the AI ​​generator, for example, by typing, "My back hurts a little today."

[0940] Step 6:

[0941] The server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and the analysis results are embodied as "I feel good, but I have back pain."

[0942] Step 7:

[0943] The server uses a generative AI model to generate a rehabilitation menu based on user data and emotion analysis results. This rehabilitation menu takes into account the user's emotional state. For example, it might suggest, "You have lower back pain, so try some short, relaxing stretches without overdoing it."

[0944] Step 8:

[0945] The terminal provides the generated rehabilitation menu to the user, allowing the user to receive specific instructions and begin rehabilitation.

[0946] Step 9:

[0947] The user performs the provided rehabilitation program and provides feedback on the results and their impressions via the device. For example, they can send feedback such as, "I felt a little better after doing some short stretches."

[0948] Step 10:

[0949] The server adjusts the next rehabilitation plan based on the user's feedback and the emotion analysis results of the emotion engine. The generative AI model generates the next rehabilitation menu based on the new feedback.

[0950] Specifically, in Tanaka's case,

[0951] 1. Enter your name, age, health condition, and rehabilitation goals on the device.

[0952] 2. Initialize the generated AI model on the server.

[0953] 3. Initialize the emotion engine on the server.

[0954] 4. Ask Tanaka from the device, "How are you feeling today?"

[0955] 5. User Tanaka replies, "My back hurts a little today."

[0956] 6. The server uses its emotion engine to analyze Tanaka's situation and conclude that "I feel good, but I have back pain."

[0957] 7. The server suggested "short, relaxed stretches for lower back pain."

[0958] 8. Provide rehabilitation menu suggestions on the terminal.

[0959] 9. User Tanaka underwent rehabilitation and gave feedback that "stretching made me feel a little better."

[0960] 10. The server adjusts the next rehabilitation plan based on the feedback and emotion engine data.

[0961] This allows Tanaka to continually acquire and implement rehabilitation programs that suit his emotional state. By repeating this process, the elderly person's motivation can be maintained, enabling high-quality rehabilitation.

[0962] Example 2

[0963] 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."

[0964] To effectively promote elderly rehabilitation, it is important to provide a personalized rehabilitation menu tailored to each individual. However, conventional systems often provide a uniform rehabilitation menu without considering the user's emotional state, which can lead to a decline in user motivation. While there are also systems that adjust rehabilitation plans based on user feedback, most of these systems do not take into account feedback about the user's emotional state, and therefore are unable to provide adequately personalized support. This can lead to a decline in elderly people's motivation to undergo rehabilitation, making it difficult for them to continue.

[0965] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0966] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for initializing the emotion engine, means for initiating a dialogue with the user using the generative AI model and the emotion engine and recognizing the emotional state, means for analyzing the user's input and emotional state to generate motivational questions and a rehabilitation menu, means for providing the generated rehabilitation menu to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration, thereby increasing the elderly's motivation for rehabilitation and promoting continued rehabilitation.

[0967] The "means for acquiring basic information about the user" is a mechanism for providing an interface that allows the user to input information such as their name, age, health condition, and rehabilitation goals.

[0968] The "means for initializing the generative AI model" is a function that configures the generative AI model based on the user's basic information, enabling the generation of a rehabilitation menu that is optimal for the user.

[0969] The "means for initializing the emotion engine" is a means for setting up an emotion engine that can analyze the user's voice and facial expression data, and for preparing to recognize the user's emotional state.

[0970] "Means for initiating a dialogue with a user and recognizing the emotional state using a generative AI model and an emotion engine" refers to a mechanism that links a generative AI model with an emotion engine to identify the emotional state from voice and facial expressions through dialogue with the user.

[0971] "Means for analyzing a user's input and emotional state to generate questions and rehabilitation menus that motivate the user" refers to a method for generating questions and appropriate rehabilitation menus that motivate the user based on the user's input and emotional state.

[0972] "Means for providing the generated rehabilitation menu to the user" refers to a mechanism that provides an interface for presenting the rehabilitation menu created by the generative AI model to the user and having them carry it out.

[0973] The "means for adjusting the next rehabilitation plan based on feedback from the user" is a method for analyzing the feedback and emotion recognition data provided by the user after rehabilitation and optimizing the next rehabilitation menu.

[0974] A specific example for implementing the present invention will be described. The present invention is a system that provides a personalized rehabilitation menu that takes into account the user's basic information and emotional state in order to effectively promote rehabilitation for elderly people. The specific configuration and operation of this system will be described below.

[0975] Entering User Data

[0976] The terminal provides an interface for inputting the user's basic information. This interface includes input fields for name, age, health condition, rehabilitation purpose, etc. The user enters information in these fields and clicks the send button to send the data. This inputs the user's basic information into the system.

[0977] Initial setup of generative AI models

[0978] The server receives basic information entered by the user and uses it to initialize the generative AI model, which is then configured to generate an optimal rehabilitation menu for each individual user, taking into account their rehabilitation goals and health condition.

[0979] Initial setting of emotion engine

[0980] The server initializes the emotion engine, which is designed to analyze the user's voice and facial expression data and recognize the user's emotional state. The server loads the voice recognition module and facial expression recognition module into the emotion engine and verifies that they are working properly.

[0981] Dialogue initiation and emotion recognition

[0982] The device uses a generative AI model and an emotion engine to initiate a dialogue with the user. First, a general greeting and a health check are performed. For example, a question such as "Hello, how are you feeling today?" is displayed and played back. The user's response is input via voice or text, and the device sends that data to the emotion engine. The emotion engine recognizes the user's emotional state from their voice and facial expressions.

[0983] Rehabilitation menu suggestions

[0984] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and proposes the optimal rehabilitation menu for the user. For example, it might generate a menu such as, "You have lower back pain today, so let's start with a short stretch without overdoing it. Can you do it while relaxing?"

[0985] Providing the generated rehabilitation menu

[0986] The terminal presents the generated rehabilitation menu to the user, who then checks the rehabilitation menu displayed on the terminal and performs rehabilitation according to the instructions.

[0987] Gathering feedback

[0988] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and emotional state. For example, the user can input something like, "After a short stretch, I feel a little better. I'm feeling good."

[0989] Adjusting the next rehabilitation plan

[0990] The server updates the generative AI model based on user feedback and recognition data from the emotion engine, adjusting the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[0991] Specific examples

[0992] For example, if a 75-year-old user has a goal of relieving lower back pain, the system operates as follows: The user enters basic information such as "I have lower back pain, and my goal for rehabilitation is to be able to play at the park with my grandchildren." The server initializes the generative AI model and emotion engine, and asks "How are you feeling today?" in the first dialogue. If the user replies "My lower back hurts a little," the emotion engine recognizes this as "I feel good." The generative AI model suggests a rehabilitation menu such as "When you have lower back pain, do you do short stretches?" After completing the rehabilitation, the user provides feedback such as "I feel a little better." The server then adjusts the next rehabilitation plan and provides it to the user.

[0993] Prompt Sentence Examples

[0994] 1. "What is the goal of rehabilitation?"

[0995] 2. "How are you feeling?"

[0996] 3. "How did you feel about the rehabilitation program?"

[0997] In this way, providing a personalized rehabilitation menu that takes into account the user's emotional state can increase the elderly person's motivation for rehabilitation and promote continued rehabilitation.

[0998] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0999] Step 1: Enter user data

[1000] The terminal provides an interface for users to enter basic information, including fields for name, age, health status, rehabilitation goals, etc.

[1001] Specific operation: When the user enters information into these fields and clicks the submit button, the device sends the data to the server.

[1002] Input: User's basic information (name, age, health condition, rehabilitation purpose, etc.)

[1003] Output: Basic information about the user sent to the server

[1004] Step 2: Initializing the Generative AI Model

[1005] The server performs initial settings for the generative AI model based on the received user data.

[1006] Specific operation: The server inputs user data into the generative AI model and creates personalized settings based on rehabilitation goals and health status, enabling the generation of an individual rehabilitation menu.

[1007] Input: User basic information

[1008] Output: Initialized generative AI model

[1009] Step 3: Initializing the Emotion Engine

[1010] The server initializes the emotion engine, which includes a voice recognition module and a facial expression recognition module.

[1011] Specific operation: The server loads the necessary modules (voice and facial expression recognition) into the emotion engine, preparing it to analyze the user's emotional state.

[1012] Input: Required modules

[1013] Output: Initialized emotion engine

[1014] Step 4: Initiating a dialogue and recognizing emotions

[1015] The device initiates a dialogue with the user using a generative AI model and an emotion engine.

[1016] Specific operation: The device activates voice input and camera functions and presents prompts to the user. The user's response is sent to the emotion engine, which recognizes the user's emotional state from their voice and facial expressions. For example, the device asks, "How are you feeling today?" and the user replies, "My back hurts a little." The emotion engine analyzes this response and recognizes the user's emotional state.

[1017] Input: User voice or text input

[1018] Output: Recognized emotional state of the user

[1019] Step 5: Proposing a rehabilitation menu

[1020] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates a rehabilitation menu.

[1021] Specific operation: The generative AI model generates a rehabilitation menu based on the user's health and emotional state. For example, it may suggest, "If you have lower back pain, start with a short stretch without overdoing it."

[1022] Input: User's emotional state, health status

[1023] Output: Generated rehabilitation menu

[1024] Step 6: Providing the generated rehabilitation menu

[1025] The terminal presents the generated rehabilitation menu to the user.

[1026] Specific operation: The device displays a rehabilitation menu on the screen and guides the user to confirm and carry out the rehabilitation menu.

[1027] Input: Generated rehabilitation menu

[1028] Output: Rehabilitation menu confirmed by the user

[1029] Step 7: Gather feedback

[1030] The user carries out the proposed rehabilitation menu and feeds back the results and emotional state to the server via the terminal.

[1031] Specific operation: The user uses the device to input and send feedback such as, "I felt a little better after doing a short stretch."

[1032] Input: User feedback

[1033] Output: Feedback sent to the server

[1034] Step 8: Adjust your next rehabilitation plan

[1035] The server uses user feedback and data from the emotion engine to allow the generative AI model to adjust the next rehabilitation plan.

[1036] Specific actions: The server analyzes the received feedback and data and optimizes the next rehabilitation menu, for example, planning to "do the same stretches for a little longer next time, and add new exercises if you feel better."

[1037] Input: User feedback, emotional state

[1038] Output: Adjusted next rehabilitation menu

[1039] (Application example 2)

[1040] 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."

[1041] In elderly rehabilitation, there is a need to provide personalized rehabilitation menus that correspond to each individual's emotions and health status. However, current systems have difficulty accurately recognizing the user's emotional state and presenting appropriate rehabilitation menus based on that. Furthermore, they lack a mechanism for effectively collecting feedback from users and reflecting it in the next rehabilitation menu. This situation reduces the motivation of elderly people to continue rehabilitation, and there is a problem in that rehabilitation is not fully effective.

[1042] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1043] In this invention, the server includes emotion recognition means, means for initializing the generative AI model, means for starting a dialogue with the user, means for analyzing the user's input and emotional state and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration and improve the user's motivation for rehabilitation.

[1044] The "means for obtaining basic information" is an interface for inputting and collecting basic information such as the user's name, age, health condition, and rehabilitation goals.

[1045] A "generative AI model" is an artificial intelligence model that generates a personalized rehabilitation menu based on the user's rehabilitation goals and health condition.

[1046] The "means for initiating dialogue" is a mechanism for initiating an initial dialogue between the user and the generative AI model and emotion recognition system.

[1047] An "emotion recognition means" is a system or device designed to analyze and recognize a user's emotional state from their voice and facial expressions.

[1048] "Emotional state" refers to the psychological and emotional state of the user when undergoing rehabilitation, such as feeling good, bad, tired, etc.

[1049] The "means for generating questions and rehabilitation menus" refers to an algorithm or system that analyzes the user's basic information and emotional state, and automatically creates questions and rehabilitation menus that motivate the user.

[1050] The "means for providing a rehabilitation menu" is an interface that displays or conveys the generated rehabilitation menu to the user.

[1051] The "means for adjusting the next rehabilitation plan based on feedback" is a system that optimizes and adjusts the next rehabilitation menu based on feedback collected from the user about the rehabilitation results and emotional state.

[1052] This invention is a system for promoting rehabilitation for elderly people who require assistance or care, and combines a generative AI model and emotion recognition means to provide a rehabilitation menu that corresponds to the user's emotional state.

[1053] This system is implemented according to the following procedure.

[1054] First, the user uses a terminal to input basic information (name, age, health condition, rehabilitation goals, etc.). This basic information can be acquired, for example, through the interface of a tablet or smartphone. Specifically, the information entered is "75-year-old elderly person suffering from back pain."

[1055] The server then initializes a generative AI model based on the acquired user data, which is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health status.

[1056] Next, the server initializes the emotion recognition means. This emotion recognition means analyzes the user's input voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to collect and analyze the user's facial expressions and voice.

[1057] The generative AI model and emotion recognition system then begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, a question like "Hello, how are you feeling today?" is asked, and when the user responds (e.g., "My back hurts a little today, but I'm feeling good"), the emotion recognition means recognizes their emotional state from their voice and facial expression.

[1058] Next, the server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion recognition means, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[1059] The generated rehabilitation menu is provided to the user via the terminal, and the user can follow the menu to carry out rehabilitation.

[1060] The user provides feedback on the results of the rehabilitation and their emotional state. For example, they might say, "I felt a little better after a short stretch. I'm feeling good." Based on this feedback, the server uses the generative AI model and emotion recognition tools to adjust the next rehabilitation plan. For example, the server might adjust the plan so that next time, the user performs the same stretches for a little longer, and add a new exercise if they feel better.

[1061] The hardware required is a camera and microphone, which are used to capture the user's facial expressions and voice. For software, the OpenCV library is used for computer vision, and the emotion recognition model is implemented using the TensorFlow / Keras model. For generative AI models, high-performance generative models such as GPT-3 are used.

[1062] As a concrete example, suppose a 75-year-old female user has a rehabilitation goal of relieving lower back pain. She operates the device to input her basic information, and the server initializes the generative AI model and emotion recognition means. In the first dialogue, she inputs, "My lower back hurts a little today," and the emotion recognition means recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." The user performs this rehabilitation menu and provides feedback that "it feels a little better." The server uses this feedback to adjust the next rehabilitation menu and provides the user with an ongoing rehabilitation menu.

[1063] An example of a prompt is as follows:

[1064] User data: {Name: "Tanaka", Age: 75, Health condition: "Low back pain", Rehabilitation goal: "Playing with grandchildren in the park"},

[1065] Emotional state: "Energetic"

[1066] Generate an appropriate rehabilitation menu.

[1067] This system provides a personalized rehabilitation menu that takes into account the user's emotional state, improving the user's motivation for rehabilitation and supporting continuous rehabilitation.

[1068] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1069] Step 1:

[1070] The user uses a terminal to input basic information (such as name, age, health status, rehabilitation goals, etc.). This basic information is sent to the server through the terminal interface. The input data is stored on the server as the user's personalized profile.

[1071] Step 2:

[1072] The server initializes the generative AI model based on the acquired user data. The AI ​​model used here is configured to generate an optimal rehabilitation menu based on the user's rehabilitation goals and health condition. This initialization takes the user's basic information as input and outputs a rehabilitation menu template.

[1073] Step 3:

[1074] The server initializes the emotion recognition means. This emotion recognition means analyzes the user's voice and facial expression data acquired from the terminal and recognizes the user's emotional state. For example, a model is set up that acquires the user's voice and video data using a camera and microphone, and uses this as input to output the user's emotional state.

[1075] Step 4:

[1076] The generative AI model and emotion recognition system begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, the device may ask the user, "Hello, how are you feeling today?" The user's response (e.g., "My back hurts a little today, but I feel good") is entered and sent to the server.

[1077] Step 5:

[1078] The server uses emotion recognition means to analyze the user's emotional state and inputs this into the generative AI model. This generates questions and rehabilitation menus that take the user's emotional state into consideration and motivate them. For example, a rehabilitation menu such as "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try it while relaxing?" is generated and output.

[1079] Step 6:

[1080] The generated rehabilitation menu is provided to the user via a terminal, and the user then follows the menu to carry out rehabilitation. Because the rehabilitation menu is optimized based on the user's current situation and emotional state, effective rehabilitation can be expected.

[1081] Step 7:

[1082] The user provides feedback on the results of the rehabilitation and their emotional state, for example, "I feel a little better after a short stretch. I'm feeling good," which is input into the device and sent to the server.

[1083] Step 8:

[1084] Based on the user's feedback and data from the emotion recognition tool, the generative AI model adjusts the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better." This information is provided to the user during their next rehabilitation session.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] [Fourth embodiment]

[1089] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1090] 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.

[1091] 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).

[1092] 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.

[1093] 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.

[1094] 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).

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] 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.

[1100] 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.

[1101] 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."

[1102] Hereinafter, an embodiment of the present invention will be described.

[1103] This invention is a system that uses generative AI models to promote rehabilitation for elderly people. Specifically, it consists of the following elements:

[1104] 1. Enter your user data:

[1105] The terminal provides an interface for acquiring basic information about the user (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and their rehabilitation goal is to be able to play in the park with their grandchildren, they would input this information.

[1106] 2. Initial setup of the generative AI model:

[1107] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals and health status, preparing the system to generate the optimal rehabilitation menu for each individual user.

[1108] 3. Initiating dialogue and proposing rehabilitation options:

[1109] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Then, based on the user's answer (e.g., "My lower back hurts a little today"), the generative AI model suggests an appropriate rehabilitation menu. The rehabilitation menu suggested might be something like, "If you have lower back pain, start with some short stretches without overdoing it. What do you think?"

[1110] 4. Ongoing rehabilitation support:

[1111] The user performs the proposed rehabilitation program and inputs the results and feedback to the server via their device. For example, the user might say, "I felt a little better after doing some short stretches." Based on this information, the generative AI model adjusts the next rehabilitation plan and provides ongoing support.

[1112] As a concrete example, let's say there is a 75-year-old female user (let's call her Tanaka). Tanaka's goal is to relieve her lower back pain. Tanaka operates the device to input basic information, and the generative AI model performs initial settings based on her information. In the first dialogue, Tanaka inputs, "My lower back hurts a little today." The generative AI model analyzes this and suggests, "If you have lower back pain, try doing five minutes of stretching." Tanaka follows this suggestion, performs the stretches, and provides feedback that, as a result, "I feel a little better." The server receives this feedback, adjusts the next rehabilitation plan, and continues to provide Tanaka with a continuous rehabilitation menu.

[1113] In this way, a personalized rehabilitation menu tailored to each user's needs is generated, and the generation AI asks in-depth questions to ensure a satisfactory rehabilitation experience. This system is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[1114] The processing flow will be explained below.

[1115] Step 1:

[1116] The terminal provides an interface for inputting basic user information (such as name, age, health condition, and rehabilitation goal). The user inputs their own information through this interface. For example, a 75-year-old senior citizen inputs their rehabilitation goal of "being able to play in the park with their grandchildren" and their health condition of lower back pain.

[1117] Step 2:

[1118] The server initializes the generative AI model based on the input user data. This initial setting takes into account the user's rehabilitation goals and health status, and helps generate a personalized rehabilitation menu.

[1119] Step 3:

[1120] Through the device, the generative AI model begins a dialogue with the user, starting with general exchanges such as greetings and checking in on how you're feeling. For example, the model might ask questions like, "Hello, how are you?"

[1121] Step 4:

[1122] The user responds to questions posed by the generative AI model, for example, by typing, "My back hurts a little today."

[1123] Step 5:

[1124] The server analyzes user input in real time. The generative AI model generates motivational questions and rehabilitation menus based on the user's input. For example, it might generate a menu that suggests, "If you have lower back pain, try doing some short stretches without straining yourself."

[1125] Step 6:

[1126] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[1127] Step 7:

[1128] The user carries out the proposed rehabilitation program and provides feedback on the results to the server via the terminal, for example, by inputting something like, "I did a short stretch and felt a little better."

[1129] Step 8:

[1130] The server adjusts the next rehabilitation plan based on the user's feedback. The generative AI model takes the new feedback into account and generates the next rehabilitation menu and motivational questions. This loop enables continuous rehabilitation support.

[1131] Example 1

[1132] 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."

[1133] Rehabilitation for elderly people requires personalization based on each individual's health condition and rehabilitation goals, while continuity is also important. However, conventional rehabilitation systems and programs are unable to flexibly respond to individual needs, making it difficult for users to maintain their motivation. Furthermore, they lack the functionality to continuously adjust the next rehabilitation plan based on user feedback, making it difficult to achieve effective rehabilitation.

[1134] 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.

[1135] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for starting a dialogue with the user using the generative AI model, means for analyzing the user's input and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, means for adjusting the next rehabilitation plan based on feedback from the user, and means for transmitting feedback to the server via the terminal. This makes it possible to provide an individually customized rehabilitation menu, thereby enabling users to maintain their motivation and achieve effective rehabilitation.

[1136] "Means for obtaining basic user information" refers to equipment or software for inputting and collecting personal information such as the user's age, health condition, and rehabilitation goals.

[1137] The "means for initializing the generative AI model" refers to the process of customizing the generative AI model based on the collected basic information of the user and performing initial settings to generate an individual rehabilitation menu.

[1138] "Means for initiating a dialogue with a user using a generative AI model" refers to a function for initiating an interactive dialogue with a user using a generative AI model and checking the user's situation and state.

[1139] The "means for analyzing user input and generating motivational questions and rehabilitation menus" refers to a process for analyzing the current situation and condition input by the user and generating motivational questions and individually customized rehabilitation menus based on the results.

[1140] "Means for providing the generated rehabilitation menu to the user" refers to a function that displays the rehabilitation menu created by the generative AI model in a visible form to the user and encourages them to carry it out.

[1141] "Means for adjusting the next rehabilitation plan based on user feedback" refers to the process of collecting and analyzing the results and impressions of the user's rehabilitation, and then adjusting the next rehabilitation menu and plan based on that information.

[1142] The "means for transmitting feedback to the server via the terminal" is a function that allows the user to use the terminal to input the results of the rehabilitation menu implementation and feedback, and transmit this to the server.

[1143] A "generative AI model" is a model that uses artificial intelligence technology to generate rehabilitation menus and dialogues that meet the individual needs of each user.

[1144] A "rehabilitation menu" is a specific exercise and training plan proposed for the user to undergo rehabilitation.

[1145] "Feedback" is information about the rehabilitation results, such as the user's impressions after completing the rehabilitation menu and changes in physical condition.

[1146] The following describes an embodiment of the present invention. The present invention is a system that promotes rehabilitation for elderly people by using a generative AI model. Specifically, it is composed of the following elements:

[1147] Entering User Data

[1148] The device provides an interface for acquiring basic information about the user. This interface is displayed on a computer, tablet, or smartphone (Windows, iOS, Android, etc.). The user enters their own information through this interface. For example, information such as name, age, health condition, and rehabilitation goals may be entered. As a specific example, a 75-year-old user may enter "back pain" and the rehabilitation goal of "being able to play in the park with my grandchildren."

[1149] Initial setup of generative AI models

[1150] The server receives user data sent from the device. The received data includes the user's basic information and rehabilitation goals. The server initializes a generative AI model (such as GPT-4) and customizes it taking into account the user's rehabilitation goals and health condition. This completes the process of generating the optimal rehabilitation menu for each individual user.

[1151] Initiating dialogue and proposing rehabilitation menus

[1152] The device launches the generative AI model sent from the server and begins a dialogue session. An initial greeting and questions to check the user's health are displayed. For example, a question such as "Hello, how are you feeling today?" is presented. The user responds to this question with, for example, "My lower back hurts a little today." The device inputs the user's response into the generative AI model and suggests an appropriate rehabilitation menu. For example, a specific rehabilitation menu such as "If you have lower back pain, try doing five minutes of stretching" is presented.

[1153] Ongoing rehabilitation support

[1154] The user performs the proposed rehabilitation menu and inputs the results and feedback into the device. For example, the user may input feedback such as, "I felt a little better after doing a short stretch." The server receives this feedback and uses the generative AI model to adjust the next rehabilitation menu. The new rehabilitation menu is then proposed to the user again via the device. For example, a suggestion may be made such as, "Next time, try stretching for a longer period of time."

[1155] Specific examples

[1156] Mr. Tanaka, 75, begins rehabilitation to relieve his lower back pain. Mr. Tanaka enters his name and rehabilitation goals into the device, which the server receives. The generative AI model is initialized and asked through dialogue, "How are you feeling today?" When Mr. Tanaka responds, "My lower back hurts a little today," the generative AI model suggests a rehabilitation menu: "If you have lower back pain, try doing five minutes of stretching." When Mr. Tanaka performs the menu and sends feedback saying, "I feel a little better," the server adjusts the next rehabilitation menu and makes new suggestions.

[1157] Prompt Sentence Examples

[1158] Suggest an appropriate rehabilitation program for a 75-year-old woman with back pain. Her goal is to be able to play with her grandchildren at the park.

[1159] The present invention aims to provide a rehabilitation menu tailored to the individual needs of the user, thereby maintaining motivation and achieving effective rehabilitation. Furthermore, by continuously adjusting the rehabilitation plan based on feedback from the user, more personalized rehabilitation is possible.

[1160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1161] Step 1:

[1162] The terminal displays an interface for obtaining basic information about the user.

[1163] Input: Basic information such as your name, age, health status, and rehabilitation goals

[1164] Specific behavior: A form or question is displayed, and the user fills in the relevant fields. For example, the user enters "back pain" and the goal "I want to be able to play in the park with my grandchildren."

[1165] Output: The entered user information is saved on the device.

[1166] Step 2:

[1167] The terminal transmits the collected user basic information to the server.

[1168] Input: User information stored on the device

[1169] Specific operation: When the user has finished entering information, they press the "Submit" button to send the data to the server.

[1170] Output: The server receives the user basic information.

[1171] Step 3:

[1172] The server initializes the generative AI model based on the received basic information.

[1173] Input: User's basic information (name, age, health status, rehabilitation goals, etc.)

[1174] Specific operation: User information is input into the generative AI model to create customized settings.

[1175] Output: A customized generative AI model is generated.

[1176] Step 4:

[1177] The server sends the initially configured generative AI model to the device.

[1178] Input: A customized generative AI model

[1179] Specific operation: The server sends data over the network to transmit the AI ​​model to the device.

[1180] Output: The device receives the generated AI model.

[1181] Step 5:

[1182] The device launches the generative AI model and begins a dialogue with the user.

[1183] Input: Generative AI model

[1184] Specific behavior: The device uses the generative AI model to conduct an initial interaction (e.g., greeting or checking how you are feeling). For example, it might ask, "Hello, how are you feeling today?"

[1185] Output: User input in response to a question (e.g., "My back hurts a little today").

[1186] Step 6:

[1187] The device inputs the user's answers into a generative AI model and suggests an appropriate rehabilitation menu.

[1188] Input: User response (e.g., "My back hurts a little today.")

[1189] Specific operation: The generative AI model analyzes the user's answers and generates an appropriate rehabilitation menu (e.g., "Try five minutes of stretching").

[1190] Output: The suggested rehabilitation menu is displayed to the user.

[1191] Step 7:

[1192] The user carries out the proposed rehabilitation menu and inputs the results and feedback into the terminal.

[1193] Input: Results and impressions of the rehabilitation menu performed by the user (e.g., "I feel a little better").

[1194] Specific operation: The user performs the rehabilitation menu and then inputs feedback into the terminal.

[1195] Output: The entered feedback is saved on the device.

[1196] Step 8:

[1197] The terminal transmits the user's feedback to the server.

[1198] Input: User feedback (e.g., "This is a bit easier now.")

[1199] Specific operation: The device sends data over the network to send feedback to the server.

[1200] Output: The server receives the feedback.

[1201] Step 9:

[1202] The server adjusts the generative AI model based on the feedback and generates the next rehabilitation menu.

[1203] Input: User feedback (e.g., "This is a bit easier now.")

[1204] Specific operation: The generative AI model analyzes the feedback and generates the next rehabilitation menu (e.g., "Try a longer stretch next time").

[1205] Output: A tailored rehabilitation menu is generated.

[1206] Step 10:

[1207] The server transmits a new rehabilitation menu to the terminal, which then provides it to the user.

[1208] Enter: Adjusted Rehab Menu

[1209] Specific operation: The server sends the rehabilitation menu to the terminal, and the terminal displays it to the user.

[1210] Output: The new rehab menu is displayed to the user.

[1211] (Application example 1)

[1212] 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."

[1213] When elderly people undergo rehabilitation, maintaining their motivation and providing them with an appropriate rehabilitation menu are important, but dietary habits that help them maintain a healthy lifestyle are equally important. However, there is no system that integrates personalized nutrition planning and meal delivery, making it difficult for elderly people to effectively undergo rehabilitation while eating a healthy diet. The present invention aims to solve this problem by providing a system that allows elderly people to consume appropriate nutrition while undergoing rehabilitation.

[1214] 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.

[1215] In this invention, the server includes a means for acquiring basic information about the user, a means for initializing the generative AI model, a means for analyzing the user's input and generating motivational questions and rehabilitation menus, and a means for using the generative AI model to propose a nutrition plan suitable for the user and manage meal delivery. This makes it possible to use the generative AI model not only to personalize rehabilitation menus but also to propose optimal nutrition plans for individual users and smoothly manage meal delivery.

[1216] The "means for acquiring basic information about the user" is a means for collecting data such as the user's personal information, health condition, rehabilitation goals, etc. via the terminal.

[1217] The "means for initially setting the generative AI model" is a means for setting the generative AI model to an appropriate state based on collected user information.

[1218] "Means for initiating a dialogue with a user using a generative AI model" refers to means for initiating communication with a user using a generative AI model.

[1219] The "means for analyzing user input and generating questions and rehabilitation menus that will motivate the user" refers to a means for proposing questions and rehabilitation menus that are optimal for the user based on the data input by the user.

[1220] The "means for providing the generated rehabilitation menu to the user" refers to a means for presenting the generated rehabilitation menu to the user and encouraging them to carry it out.

[1221] The "means for adjusting the next rehabilitation plan based on feedback from the user" refers to a means for analyzing feedback provided by the user and adjusting the next rehabilitation plan based on the feedback.

[1222] "Means for using a generative AI model to propose an optimal nutrition plan for a user and manage meal delivery" refers to a means for generating an optimal nutrition plan based on user information and managing meal ordering and delivery in accordance with that plan.

[1223] This invention is a system that uses generative AI models to provide rehabilitation and nutritional planning for seniors and manage meal delivery. The system consists of the following components:

[1224] 1. Enter your user data:

[1225] The terminal provides an interface for obtaining basic information about the user (such as name, age, health condition, rehabilitation goals, food preferences, and allergy information). The user inputs their own information through this interface. For example, if a 75-year-old person has back pain and a rehabilitation goal of "being able to play in the park with their grandchildren," and is also allergic to certain foods, this information can be entered.

[1226] 2. Initial setup of the generative AI model:

[1227] The server initializes a generative AI model based on user data. This model is then customized to take into account the user's rehabilitation goals, health status, dietary preferences, and allergy information. This sets the stage for generating an optimal rehabilitation menu and nutrition plan for each individual user.

[1228] 3. Initiating a dialogue and proposing rehabilitation and nutritional plans:

[1229] The generative AI model begins a dialogue with the user via the device. The dialogue begins with general exchanges such as greetings and checking the user's health, followed by a rehabilitation menu and nutrition plan. For example, an opening question such as "Hello, how are you feeling today?" is suggested. Based on the user's answers, a rehabilitation menu and nutrition plan is then presented, such as "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we'll suggest a menu using ingredients that are good for your lower back."

[1230] 4. Meal delivery management:

[1231] The server manages meal delivery based on the generated nutrition plan. Specifically, it coordinates with delivery companies to arrange for meals appropriate for the user to be delivered at the specified time. For example, information such as "Grilled chicken breast and salad will be delivered for dinner tonight" is sent to the device, and the meal is delivered at the specified time.

[1232] 5. Ongoing rehabilitation and nutritional support:

[1233] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback to the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." Based on this information, the generative AI model adjusts the next rehabilitation and nutrition plan and provides ongoing support.

[1234] Hardware and software used:

[1235] Smartphone: A device for installing the app. Supports iOS or Android.

[1236] React Native: A cross-platform framework used to develop mobile applications.

[1237] Firebase: Used as a database to store and retrieve user data.

[1238] OpenAI API: Uses a generative AI model (GPT-4) to generate rehabilitation menus and nutrition plans.

[1239] Node.js: Manages the server-side logic and communicates with the generative AI model.

[1240] Examples of prompts:

[1241] Prompt for Mr. Tanaka (75 years old, suffers from back pain) who has the goal of "being able to play in the park with his grandchildren."

[1242] "Ms. Tanaka, a 75-year-old woman, suffers from back pain and wants to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate healthy menus that don't put strain on her back. Please suggest today's menu."

[1243] This system will enable elderly people to receive personalized support in both rehabilitation and nutrition, which is expected to improve their quality of life.

[1244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1245] Step 1:

[1246] The terminal obtains basic information about the user. Specifically, it provides an interface where the user can input their name, age, health condition, rehabilitation goal, food preferences, allergy information, etc. This data is collected and sent to the server. The input data includes name = "Mr. Tanaka", age = "75 years old", health condition = "suffers from back pain", rehabilitation goal = "to be able to play in the park with my grandchildren", food preferences = "Japanese food", and allergy information = "shellfish allergy". This information is transferred to the server.

[1247] Step 2:

[1248] The server initializes the generative AI model based on the received user data. During this process, the settings of the generative AI model are customized based on the received data (name, age, health condition, rehabilitation goals, dietary preferences, and allergy information). For example, taking into account Mr. Tanaka's age and health condition, the server generates prompts for generating a rehabilitation menu and nutrition plan that is effective for his lower back pain.

[1249] Step 3:

[1250] The device uses the generative AI model to initiate a dialogue with the user. Specifically, the device uses the generated prompt to greet the user and ask questions about their health. A message such as "Hello, how are you feeling today?" is displayed. The user's response is received as input and analyzed in the next processing step.

[1251] Step 4:

[1252] The server analyzes the user's input and generates a rehabilitation menu and nutrition plan. It analyzes the captured user's response data (e.g., "My lower back hurts a little today") and uses a generative AI model to generate an appropriate rehabilitation menu and nutrition plan. For example, using the prompt, "Ms. Tanaka, a 75-year-old woman, suffers from lower back pain and aims to be able to play in the park with her grandchildren. To provide daily meal suggestions, please generate a healthy menu that puts less strain on her lower back. Please suggest today's menu," it generates "Try five minutes of stretching" as the rehabilitation menu and "Grilled chicken breast and salad made with ingredients that are good for the lower back" as the nutrition plan.

[1253] Step 5:

[1254] The device provides the generated rehabilitation menu and nutrition plan to the user. The device displays the generated menu to the user through its interface and encourages them to follow it. For example, the device may provide a notification such as, "If you have lower back pain, start with a short stretch without overdoing it. For dinner, we suggest grilled chicken breast and a salad, which are good for your lower back."

[1255] Step 6:

[1256] The server manages meal delivery based on the generated nutrition plan. Specifically, it sends the generated meal information to the delivery company's API and arranges for the meal to be delivered to the user's address at the specified time. For example, it issues delivery instructions based on information such as "For tonight's dinner, we'll deliver grilled chicken breast and salad."

[1257] Step 7:

[1258] The user acts according to the proposed rehabilitation menu and nutrition plan, and inputs the results and feedback into the server via their device. For example, the user might enter feedback such as, "I felt a little better after doing a short stretch. Dinner was also delicious." The server receives this feedback data and adjusts the next rehabilitation and nutrition plan, providing ongoing support.

[1259] Step 8:

[1260] The server adjusts the next rehabilitation and nutrition plan based on the user's feedback. It analyzes the received feedback and uses a generative AI model to optimize the next plan. For example, based on feedback such as "Stretching has become easier, but I would like to make it a little more difficult," it suggests a more intense rehabilitation menu and more nutritious meals for the next time.

[1261] This allows users to receive personalized rehabilitation and nutritional support while improving their quality of life.

[1262] 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.

[1263] Hereinafter, an embodiment of the present invention will be described.

[1264] This invention is a system for promoting rehabilitation for elderly people who require assistance or nursing care, and combines a generative AI model and an emotion engine to provide a rehabilitation menu according to the user's emotional state.

[1265] 1. Enter your user data:

[1266] The device provides an interface for entering basic user information (such as name, age, health condition, and rehabilitation goals). Elderly users enter their own information through this interface. For example, if 75-year-old Mr. Tanaka suffers from back pain and has a rehabilitation goal of "being able to play with his grandchildren in the park," he or she would enter this information.

[1267] 2. Initial setup of the generative AI model:

[1268] The server initializes the generative AI model based on the input user data. The generative AI model is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health condition.

[1269] 3. Initial setting of emotion engine:

[1270] The server initializes the emotion engine, which is designed to analyze the user's input voice and facial expression data and recognize the user's emotional state.

[1271] 4. Dialogue initiation and emotion recognition:

[1272] The generative AI model and emotion engine begin a dialogue with the user via the device. First, a general greeting and a check on the user's health are conducted. For example, a question such as "Hello, Tanaka-san. How are you feeling today?" is asked. Once the user's response (e.g., "My back hurts a little today, but I feel good") is entered, the emotion engine recognizes the user's emotional state from their voice and facial expressions.

[1273] 5. Rehabilitation menu suggestions:

[1274] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[1275] 6. Providing the generated rehabilitation menu:

[1276] The terminal provides the user with the generated rehabilitation menu and questions, which allows the user to obtain specific instructions for proceeding with the actual rehabilitation.

[1277] 7. Gathering Feedback:

[1278] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and their emotional state. For example, the user might input, "After a short stretch, I feel a little better. I'm feeling good."

[1279] 8. Adjusting your next rehabilitation plan:

[1280] Based on user feedback and emotion recognition data from the emotion engine, the server uses a generative AI model to adjust the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[1281] As a specific example, consider a 75-year-old female user named Tanaka. Tanaka's goal is to relieve her lower back pain. Tanaka operates her device to input basic information, and the server initializes the generative AI model and emotion engine. In the first dialogue, Tanaka inputs, "My lower back hurts a little today," and the emotion engine recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." Tanaka then performs rehabilitation and provides feedback, saying, "I feel a little better." The server uses this feedback to adjust the next rehabilitation menu and provides Tanaka with an ongoing rehabilitation menu.

[1282] In this way, this invention provides a personalized rehabilitation menu that takes into account the user's emotional state, promoting effective rehabilitation. Furthermore, by combining generative AI with an emotion engine, it is possible to support the user's psychological and emotional aspects. This is expected to improve elderly people's motivation for rehabilitation and promote the maintenance and improvement of their quality of life (QOL) and activities of daily living (ADL).

[1283] The processing flow will be explained below.

[1284] Step 1:

[1285] The device provides an interface for entering basic user information, such as the user's name, age, health condition, and rehabilitation goals. For example, Mr. Tanaka (75 years old) suffers from back pain and enters his goal of "being able to play in the park with his grandchildren."

[1286] Step 2:

[1287] The server initializes the generative AI model based on the acquired user data, which reflects the user's rehabilitation goals and health status.

[1288] Step 3:

[1289] The server initializes the emotion engine, which analyzes the user's input voice and facial expression data and prepares it to recognize the user's emotional state.

[1290] Step 4:

[1291] Through the device, the generative AI model and emotion engine begin a dialogue with the user, starting with a general greeting such as "Hello, how are you feeling today?" and a check-up on their health.

[1292] Step 5:

[1293] The user responds to questions posed by the AI ​​generator, for example, by typing, "My back hurts a little today."

[1294] Step 6:

[1295] The server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and the analysis results are embodied as "I feel good, but I have back pain."

[1296] Step 7:

[1297] The server uses a generative AI model to generate a rehabilitation menu based on user data and emotion analysis results. This rehabilitation menu takes into account the user's emotional state. For example, it might suggest, "You have lower back pain, so try some short, relaxing stretches without overdoing it."

[1298] Step 8:

[1299] The terminal provides the generated rehabilitation menu to the user, allowing the user to receive specific instructions and begin rehabilitation.

[1300] Step 9:

[1301] The user performs the provided rehabilitation program and provides feedback on the results and their impressions via the device. For example, they can send feedback such as, "I felt a little better after doing some short stretches."

[1302] Step 10:

[1303] The server adjusts the next rehabilitation plan based on the user's feedback and the emotion analysis results of the emotion engine. The generative AI model generates the next rehabilitation menu based on the new feedback.

[1304] Specifically, in Tanaka's case,

[1305] 1. Enter your name, age, health condition, and rehabilitation goals on the device.

[1306] 2. Initialize the generated AI model on the server.

[1307] 3. Initialize the emotion engine on the server.

[1308] 4. Ask Tanaka from the device, "How are you feeling today?"

[1309] 5. User Tanaka replies, "My back hurts a little today."

[1310] 6. The server uses its emotion engine to analyze Tanaka's situation and conclude that "I feel good, but I have back pain."

[1311] 7. The server suggested "short, relaxed stretches for lower back pain."

[1312] 8. Provide rehabilitation menu suggestions on the terminal.

[1313] 9. User Tanaka underwent rehabilitation and gave feedback that "stretching made me feel a little better."

[1314] 10. The server adjusts the next rehabilitation plan based on the feedback and emotion engine data.

[1315] This allows Tanaka to continually acquire and implement rehabilitation programs that suit his emotional state. By repeating this process, the elderly person's motivation can be maintained, enabling high-quality rehabilitation.

[1316] Example 2

[1317] 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."

[1318] To effectively promote elderly rehabilitation, it is important to provide a personalized rehabilitation menu tailored to each individual. However, conventional systems often provide a uniform rehabilitation menu without considering the user's emotional state, which can lead to a decline in user motivation. While there are also systems that adjust rehabilitation plans based on user feedback, most of these systems do not take into account feedback about the user's emotional state, and therefore are unable to provide adequately personalized support. This can lead to a decline in elderly people's motivation to undergo rehabilitation, making it difficult for them to continue.

[1319] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1320] In this invention, the server includes means for acquiring basic information about the user, means for initializing the generative AI model, means for initializing the emotion engine, means for initiating a dialogue with the user using the generative AI model and the emotion engine and recognizing the emotional state, means for analyzing the user's input and emotional state to generate motivational questions and a rehabilitation menu, means for providing the generated rehabilitation menu to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration, thereby increasing the elderly's motivation for rehabilitation and promoting continued rehabilitation.

[1321] The "means for acquiring basic information about the user" is a mechanism for providing an interface that allows the user to input information such as their name, age, health condition, and rehabilitation goals.

[1322] The "means for initializing the generative AI model" is a function that configures the generative AI model based on the user's basic information, enabling the generation of a rehabilitation menu that is optimal for the user.

[1323] The "means for initializing the emotion engine" is a means for setting up an emotion engine that can analyze the user's voice and facial expression data, and for preparing to recognize the user's emotional state.

[1324] "Means for initiating a dialogue with a user and recognizing the emotional state using a generative AI model and an emotion engine" refers to a mechanism that links a generative AI model with an emotion engine to identify the emotional state from voice and facial expressions through dialogue with the user.

[1325] "Means for analyzing a user's input and emotional state to generate questions and rehabilitation menus that motivate the user" refers to a method for generating questions and appropriate rehabilitation menus that motivate the user based on the user's input and emotional state.

[1326] "Means for providing the generated rehabilitation menu to the user" refers to a mechanism that provides an interface for presenting the rehabilitation menu created by the generative AI model to the user and having them carry it out.

[1327] The "means for adjusting the next rehabilitation plan based on feedback from the user" is a method for analyzing the feedback and emotion recognition data provided by the user after rehabilitation and optimizing the next rehabilitation menu.

[1328] A specific example for implementing the present invention will be described. The present invention is a system that provides a personalized rehabilitation menu that takes into account the user's basic information and emotional state in order to effectively promote rehabilitation for elderly people. The specific configuration and operation of this system will be described below.

[1329] Entering User Data

[1330] The terminal provides an interface for inputting the user's basic information. This interface includes input fields for name, age, health condition, rehabilitation purpose, etc. The user enters information in these fields and clicks the send button to send the data. This inputs the user's basic information into the system.

[1331] Initial setup of generative AI models

[1332] The server receives basic information entered by the user and uses it to initialize the generative AI model, which is then configured to generate an optimal rehabilitation menu for each individual user, taking into account their rehabilitation goals and health condition.

[1333] Initial setting of emotion engine

[1334] The server initializes the emotion engine, which is designed to analyze the user's voice and facial expression data and recognize the user's emotional state. The server loads the voice recognition module and facial expression recognition module into the emotion engine and verifies that they are working properly.

[1335] Dialogue initiation and emotion recognition

[1336] The device uses a generative AI model and an emotion engine to initiate a dialogue with the user. First, a general greeting and a health check are performed. For example, a question such as "Hello, how are you feeling today?" is displayed and played back. The user's response is input via voice or text, and the device sends that data to the emotion engine. The emotion engine recognizes the user's emotional state from their voice and facial expressions.

[1337] Rehabilitation menu suggestions

[1338] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and proposes the optimal rehabilitation menu for the user. For example, it might generate a menu such as, "You have lower back pain today, so let's start with a short stretch without overdoing it. Can you do it while relaxing?"

[1339] Providing the generated rehabilitation menu

[1340] The terminal presents the generated rehabilitation menu to the user, who then checks the rehabilitation menu displayed on the terminal and performs rehabilitation according to the instructions.

[1341] Gathering feedback

[1342] The user performs the proposed rehabilitation program and provides feedback to the server via the device about the results and emotional state. For example, the user can input something like, "After a short stretch, I feel a little better. I'm feeling good."

[1343] Adjusting the next rehabilitation plan

[1344] The server updates the generative AI model based on user feedback and recognition data from the emotion engine, adjusting the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better."

[1345] Specific examples

[1346] For example, if a 75-year-old user has a goal of relieving lower back pain, the system operates as follows: The user enters basic information such as "I have lower back pain, and my goal for rehabilitation is to be able to play at the park with my grandchildren." The server initializes the generative AI model and emotion engine, and asks "How are you feeling today?" in the first dialogue. If the user replies "My lower back hurts a little," the emotion engine recognizes this as "I feel good." The generative AI model suggests a rehabilitation menu such as "When you have lower back pain, do you do short stretches?" After completing the rehabilitation, the user provides feedback such as "I feel a little better." The server then adjusts the next rehabilitation plan and provides it to the user.

[1347] Prompt Sentence Examples

[1348] 1. "What is the goal of rehabilitation?"

[1349] 2. "How are you feeling?"

[1350] 3. "How did you feel about the rehabilitation program?"

[1351] In this way, providing a personalized rehabilitation menu that takes into account the user's emotional state can increase the elderly person's motivation for rehabilitation and promote continued rehabilitation.

[1352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1353] Step 1: Enter user data

[1354] The terminal provides an interface for users to enter basic information, including fields for name, age, health status, rehabilitation goals, etc.

[1355] Specific operation: When the user enters information into these fields and clicks the submit button, the device sends the data to the server.

[1356] Input: User's basic information (name, age, health condition, rehabilitation purpose, etc.)

[1357] Output: Basic information about the user sent to the server

[1358] Step 2: Initializing the Generative AI Model

[1359] The server performs initial settings for the generative AI model based on the received user data.

[1360] Specific operation: The server inputs user data into the generative AI model and creates personalized settings based on rehabilitation goals and health status, enabling the generation of an individual rehabilitation menu.

[1361] Input: User basic information

[1362] Output: Initialized generative AI model

[1363] Step 3: Initializing the Emotion Engine

[1364] The server initializes the emotion engine, which includes a voice recognition module and a facial expression recognition module.

[1365] Specific operation: The server loads the necessary modules (voice and facial expression recognition) into the emotion engine, preparing it to analyze the user's emotional state.

[1366] Input: Required modules

[1367] Output: Initialized emotion engine

[1368] Step 4: Initiating a dialogue and recognizing emotions

[1369] The device initiates a dialogue with the user using a generative AI model and an emotion engine.

[1370] Specific operation: The device activates voice input and camera functions and presents prompts to the user. The user's response is sent to the emotion engine, which recognizes the user's emotional state from their voice and facial expressions. For example, the device asks, "How are you feeling today?" and the user replies, "My back hurts a little." The emotion engine analyzes this response and recognizes the user's emotional state.

[1371] Input: User voice or text input

[1372] Output: Recognized emotional state of the user

[1373] Step 5: Proposing a rehabilitation menu

[1374] The server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion engine, and generates a rehabilitation menu.

[1375] Specific operation: The generative AI model generates a rehabilitation menu based on the user's health and emotional state. For example, it may suggest, "If you have lower back pain, start with a short stretch without overdoing it."

[1376] Input: User's emotional state, health status

[1377] Output: Generated rehabilitation menu

[1378] Step 6: Providing the generated rehabilitation menu

[1379] The terminal presents the generated rehabilitation menu to the user.

[1380] Specific operation: The device displays a rehabilitation menu on the screen and guides the user to confirm and carry out the rehabilitation menu.

[1381] Input: Generated rehabilitation menu

[1382] Output: Rehabilitation menu confirmed by the user

[1383] Step 7: Gather feedback

[1384] The user carries out the proposed rehabilitation menu and feeds back the results and emotional state to the server via the terminal.

[1385] Specific operation: The user uses the device to input and send feedback such as, "I felt a little better after doing a short stretch."

[1386] Input: User feedback

[1387] Output: Feedback sent to the server

[1388] Step 8: Adjust your next rehabilitation plan

[1389] The server uses user feedback and data from the emotion engine to allow the generative AI model to adjust the next rehabilitation plan.

[1390] Specific actions: The server analyzes the received feedback and data and optimizes the next rehabilitation menu, for example, planning to "do the same stretches for a little longer next time, and add new exercises if you feel better."

[1391] Input: User feedback, emotional state

[1392] Output: Adjusted next rehabilitation menu

[1393] (Application example 2)

[1394] 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."

[1395] In elderly rehabilitation, there is a need to provide personalized rehabilitation menus that correspond to each individual's emotions and health status. However, current systems have difficulty accurately recognizing the user's emotional state and presenting appropriate rehabilitation menus based on that. Furthermore, they lack a mechanism for effectively collecting feedback from users and reflecting it in the next rehabilitation menu. This situation reduces the motivation of elderly people to continue rehabilitation, and there is a problem in that rehabilitation is not fully effective.

[1396] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1397] In this invention, the server includes emotion recognition means, means for initializing the generative AI model, means for starting a dialogue with the user, means for analyzing the user's input and emotional state and generating motivational questions and rehabilitation menus, means for providing the generated rehabilitation menus to the user, and means for adjusting the next rehabilitation plan based on feedback from the user. This makes it possible to provide a personalized rehabilitation menu that takes the user's emotional state into consideration and improve the user's motivation for rehabilitation.

[1398] The "means for obtaining basic information" is an interface for inputting and collecting basic information such as the user's name, age, health condition, and rehabilitation goals.

[1399] A "generative AI model" is an artificial intelligence model that generates a personalized rehabilitation menu based on the user's rehabilitation goals and health condition.

[1400] The "means for initiating dialogue" is a mechanism for initiating an initial dialogue between the user and the generative AI model and emotion recognition system.

[1401] An "emotion recognition means" is a system or device designed to analyze and recognize a user's emotional state from their voice and facial expressions.

[1402] "Emotional state" refers to the psychological and emotional state of the user when undergoing rehabilitation, such as feeling good, bad, tired, etc.

[1403] The "means for generating questions and rehabilitation menus" refers to an algorithm or system that analyzes the user's basic information and emotional state, and automatically creates questions and rehabilitation menus that motivate the user.

[1404] The "means for providing a rehabilitation menu" is an interface that displays or conveys the generated rehabilitation menu to the user.

[1405] The "means for adjusting the next rehabilitation plan based on feedback" is a system that optimizes and adjusts the next rehabilitation menu based on feedback collected from the user about the rehabilitation results and emotional state.

[1406] This invention is a system for promoting rehabilitation for elderly people who require assistance or care, and combines a generative AI model and emotion recognition means to provide a rehabilitation menu that corresponds to the user's emotional state.

[1407] This system is implemented according to the following procedure.

[1408] First, the user uses a terminal to input basic information (name, age, health condition, rehabilitation goals, etc.). This basic information can be acquired, for example, through the interface of a tablet or smartphone. Specifically, the information entered is "75-year-old elderly person suffering from back pain."

[1409] The server then initializes a generative AI model based on the acquired user data, which is configured to generate a personalized rehabilitation menu taking into account the user's rehabilitation goals and health status.

[1410] Next, the server initializes the emotion recognition means. This emotion recognition means analyzes the user's input voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to collect and analyze the user's facial expressions and voice.

[1411] The generative AI model and emotion recognition system then begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, a question like "Hello, how are you feeling today?" is asked, and when the user responds (e.g., "My back hurts a little today, but I'm feeling good"), the emotion recognition means recognizes their emotional state from their voice and facial expression.

[1412] Next, the server uses a generative AI model to analyze the user's input and the emotional state obtained from the emotion recognition means, and generates motivational questions and rehabilitation menus. For example, a rehabilitation menu might be presented such as, "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try doing it while relaxing?"

[1413] The generated rehabilitation menu is provided to the user via the terminal, and the user can follow the menu to carry out rehabilitation.

[1414] The user provides feedback on the results of the rehabilitation and their emotional state. For example, they might say, "I felt a little better after a short stretch. I'm feeling good." Based on this feedback, the server uses the generative AI model and emotion recognition tools to adjust the next rehabilitation plan. For example, the server might adjust the plan so that next time, the user performs the same stretches for a little longer, and add a new exercise if they feel better.

[1415] The hardware required is a camera and microphone, which are used to capture the user's facial expressions and voice. For software, the OpenCV library is used for computer vision, and the emotion recognition model is implemented using the TensorFlow / Keras model. For generative AI models, high-performance generative models such as GPT-3 are used.

[1416] As a concrete example, suppose a 75-year-old female user has a rehabilitation goal of relieving lower back pain. She operates the device to input her basic information, and the server initializes the generative AI model and emotion recognition means. In the first dialogue, she inputs, "My lower back hurts a little today," and the emotion recognition means recognizes this as, "I feel good." The generative AI model analyzes this data and suggests a rehabilitation menu: "If you have lower back pain, don't push yourself too hard, and start with some short stretches." The user performs this rehabilitation menu and provides feedback that "it feels a little better." The server uses this feedback to adjust the next rehabilitation menu and provides the user with an ongoing rehabilitation menu.

[1417] An example of a prompt is as follows:

[1418] User data: {Name: "Tanaka", Age: 75, Health condition: "Low back pain", Rehabilitation goal: "Playing with grandchildren in the park"},

[1419] Emotional state: "Energetic"

[1420] Generate an appropriate rehabilitation menu.

[1421] This system provides a personalized rehabilitation menu that takes into account the user's emotional state, improving the user's motivation for rehabilitation and supporting continuous rehabilitation.

[1422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1423] Step 1:

[1424] The user uses a terminal to input basic information (such as name, age, health status, rehabilitation goals, etc.). This basic information is sent to the server through the terminal interface. The input data is stored on the server as the user's personalized profile.

[1425] Step 2:

[1426] The server initializes the generative AI model based on the acquired user data. The AI ​​model used here is configured to generate an optimal rehabilitation menu based on the user's rehabilitation goals and health condition. This initialization takes the user's basic information as input and outputs a rehabilitation menu template.

[1427] Step 3:

[1428] The server initializes the emotion recognition means. This emotion recognition means analyzes the user's voice and facial expression data acquired from the terminal and recognizes the user's emotional state. For example, a model is set up that acquires the user's voice and video data using a camera and microphone, and uses this as input to output the user's emotional state.

[1429] Step 4:

[1430] The generative AI model and emotion recognition system begin a dialogue with the user via the device. First, a general greeting and a check on their health are conducted. For example, the device may ask the user, "Hello, how are you feeling today?" The user's response (e.g., "My back hurts a little today, but I feel good") is entered and sent to the server.

[1431] Step 5:

[1432] The server uses emotion recognition means to analyze the user's emotional state and inputs this into the generative AI model. This generates questions and rehabilitation menus that take the user's emotional state into consideration and motivate them. For example, a rehabilitation menu such as "If you have lower back pain, start with a short stretch without overdoing it. You seem to be feeling good, so why not try it while relaxing?" is generated and output.

[1433] Step 6:

[1434] The generated rehabilitation menu is provided to the user via a terminal, and the user then follows the menu to carry out rehabilitation. Because the rehabilitation menu is optimized based on the user's current situation and emotional state, effective rehabilitation can be expected.

[1435] Step 7:

[1436] The user provides feedback on the results of the rehabilitation and their emotional state, for example, "I feel a little better after a short stretch. I'm feeling good," which is input into the device and sent to the server.

[1437] Step 8:

[1438] Based on the user's feedback and data from the emotion recognition tool, the generative AI model adjusts the next rehabilitation plan, for example, "Next time, do the same stretches for a little longer, and add new exercises if you feel better." This information is provided to the user during their next rehabilitation session.

[1439] 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.

[1440] 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.

[1441] 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 robot 414.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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).

[1446] 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.

[1447] 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."

[1448] 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.

[1449] 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).

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1459] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1460] The following is further disclosed regarding the above embodiment.

[1461] (Claim 1)

[1462] A means for obtaining basic information about a user;

[1463] a means for initializing the generative AI model;

[1464] a means for initiating a dialogue with a user utilizing the generative AI model;

[1465] A means for analyzing user input and generating motivational questions and rehabilitation menus;

[1466] a means for providing the generated rehabilitation menu to a user;

[1467] a means of adjusting the next rehabilitation plan based on user feedback;

[1468] A system including:

[1469] (Claim 2)

[1470] The system of claim 1 further comprising means for tuning the generative AI model and realizing a dialogue that deepens the user's self-understanding by digging deeper into the problem without providing easy answers.

[1471] (Claim 3)

[1472] 2. The system of claim 1, wherein the generated rehabilitation menu is personalized based on the user's health condition and rehabilitation goals.

[1473] "Example 1"

[1474] (Claim 1)

[1475] A means for obtaining basic information about a user;

[1476] a means for initializing the generative AI model;

[1477] a means for initiating a dialogue with a user utilizing the generative AI model;

[1478] A means for analyzing user input and generating motivational questions and rehabilitation menus;

[1479] a means for providing the generated rehabilitation menu to a user;

[1480] a means of adjusting the next rehabilitation plan based on user feedback;

[1481] The system includes means for transmitting feedback to a server through the terminal.

[1482] (Claim 2)

[1483] The system of claim 1 further comprising means for tuning the generative AI model and realizing a dialogue that deepens the user's self-understanding by digging deeper into the problem without providing easy answers.

[1484] (Claim 3)

[1485] 2. The system of claim 1, wherein the generated rehabilitation menu is personalized based on the user's health condition and rehabilitation goals.

[1486] (Claim 4)

[1487] The system of claim 1, wherein the generated rehabilitation menu suggestions are sequentially adjusted by a generative AI model.

[1488] "Application Example 1"

[1489] (Claim 1)

[1490] A means for obtaining basic information about a user;

[1491] a means for initializing the generative AI model;

[1492] a means for initiating a dialogue with a user utilizing the generative AI model;

[1493] A means for analyzing user input and generating motivational questions and rehabilitation menus;

[1494] a means for providing the generated rehabilitation menu to a user;

[1495] a means of adjusting the next rehabilitation plan based on user feedback;

[1496] A means to use generative AI models to recommend nutrition plans and manage meal delivery tailored to the user;

[1497] A system including:

[1498] (Claim 2)

[1499] The system of claim 1 further includes a means for tuning the generative AI model to realize a dialogue that deepens the user's self-understanding by digging deeper into the problem without providing easy answers, a means for providing an individualized nutrition plan based on the generative AI model, and a means for adjusting next meal suggestions based on the user's dietary feedback.

[1500] (Claim 3)

[1501] The system of claim 1, wherein the generated rehabilitation menu is personalized based on the user's health condition and rehabilitation goals, and the generated nutrition plan is personalized based on the user's health condition and rehabilitation goals.

[1502] "Example 2: Combining Emotion Engines"

[1503] (Claim 1)

[1504] A means for obtaining basic information about a user;

[1505] a means for initializing the generative AI model;

[1506] a means for initializing the emotion engine;

[1507] a means for initiating a dialogue with a user utilizing a generative AI model and an emotion engine to recognize the user's emotional state;

[1508] A means for analyzing the user's input and emotional state to generate motivational questions and rehabilitation menus;

[1509] a means for providing the generated rehabilitation menu to a user;

[1510] a means of adjusting the next rehabilitation plan based on user feedback;

[1511] A system including:

[1512] (Claim 2)

[1513] The system of claim 1 further comprising means for tuning the generative AI model and realizing a dialogue that deepens the user's self-understanding by digging deeper into the problem without providing easy answers.

[1514] (Claim 3)

[1515] 2. The system of claim 1, wherein the generated rehabilitation menu is personalized based on the user's health and emotional state.

[1516] "Application example 2 when combining emotion engines"

[1517] (Claim 1)

[1518] A means for obtaining basic information about a user;

[1519] a means for initializing the generative AI model;

[1520] a means for initiating a dialogue with a user utilizing the generative AI model;

[1521] emotion recognition means for recognizing an emotional state of a user;

[1522] A means for analyzing the user's input and emotional state and generating motivational questions and rehabilitation menus;

[1523] a means for providing the generated rehabilitation menu to a user;

[1524] a means of adjusting the next rehabilitation plan based on user feedback;

[1525] A system including:

[1526] (Claim 2)

[1527] The system of claim 1 further comprising means for tuning the generative AI model and realizing a dialogue that deepens the user's self-understanding by digging deeper into the problem without providing easy answers.

[1528] (Claim 3)

[1529] 2. The system according to claim 1, wherein the generated rehabilitation menu is personalized based on the user's health condition and rehabilitation goals, and corresponds to the emotional state obtained by the emotion recognition means. [Explanation of symbols]

[1530] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining basic information about a user; a means for initializing the generative AI model; a means for initiating a dialogue with a user utilizing the generative AI model; A means for analyzing user input and generating motivational questions and rehabilitation menus; a means for providing the generated rehabilitation menu to a user; a means of adjusting the next rehabilitation plan based on user feedback; A system including:

2. The system of claim 1, further comprising means for tuning the generative AI model and realizing a dialogue that allows the user to deepen their self-understanding by digging deeper into the problem without providing an easy answer.

3. The system according to claim 1 , wherein the generated rehabilitation menu is personalized based on the user's health condition and rehabilitation goals.

Images