system

Abstract

We provide the system. [Solution] A means of receiving natural language input from users, An analysis means for analyzing the aforementioned input and identifying the user's emotional state, A generation means for generating stress management suggestions based on identified emotional states, A means for presenting the aforementioned proposal to the user, An analytical means that acquires user meal data and estimates nutrient amounts through image analysis, A predictive method that uses past health data to predict future health risks, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Diabetic patients face the problem that it is difficult to manage the associated mental stress and maintain appropriate lifestyle habits. This mental stress may reduce the quality of life. Also, family members and friends who support diabetic patients may sometimes be unable to provide appropriate support due to insufficient knowledge and understanding. Therefore, there is a need for an integrated system to reduce the stress of diabetic patients and support a healthy life.

Means for Solving the Problems

[0005] This invention provides a system that accepts patient input in natural language, analyzes their emotional state, and offers suggestions for stress management. Furthermore, it provides comprehensive health management support to patients by evaluating dietary data through image analysis, estimating nutrients, and predicting future health risks based on past health data. It also promotes understanding and support from those around the patient by sharing educational information with family and friends. In this way, it aims to reduce the mental stress experienced by diabetic patients in their daily lives and support the maintenance of healthy lifestyle habits.

[0006] A "user" is a diabetic patient who uses this system to receive support for health management.

[0007] "Input" refers to natural language data that users use to communicate their emotional state and meal contents to the system.

[0008] "Emotional state" refers to information that represents the user's mental and psychological condition.

[0009] "Stress management" refers to specific strategies that users employ to reduce their stress and maintain their mental health.

[0010] A "suggestion" is a set of specific action plans for stress reduction and health maintenance that the system generates based on the user's emotional and health status.

[0011] "Meal data" refers to information provided by users to record the contents of their meals, and may include image formats.

[0012] "Image analysis" is a technical method for evaluating nutrient content from images provided as dietary data.

[0013] "Health data" refers to information about a user's health, such as their blood sugar levels, from the past.

[0014] "Health risk" refers to factors or conditions that may affect a user's health in the future.

[0015] "Educational information" refers to information that explains knowledge and management methods related to diabetes and is provided to the supporters of patients.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of a data processing system in Embodiment 2 when a sentiment engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] To implement the present invention, a system comprising multiple elements is required. This system operates with a configuration including a user, a terminal, and a server.

[0038] User-device interaction

[0039] Users utilize the system via their devices for daily health management. Users can input information about their emotions and health status in natural language. They can also take photos of their meals and input health data such as blood sugar levels into the device. The device collects this data and transmits it to the server.

[0040] Server-based data analysis and proposal generation.

[0041] The server receives input data sent from the terminal and analyzes the user's emotions using a natural language processing engine. This analysis identifies the user's stress level and specific stressors. Furthermore, the server utilizes an AI model to generate stress management suggestions that can help reduce stress. These suggestions may include relaxation techniques and lifestyle improvements.

[0042] The server also uses image analysis technology to process the user's dietary data and estimate the amount of nutrients. This allows it to indicate the amount of insulin the user needs and provide other nutritional advice. At the same time, it analyzes past health data to predict the user's future health risks. Based on this risk prediction, it suggests specific actions to maintain good health.

[0043] Provision of educational information

[0044] Furthermore, the server provides educational information to patients' families and caregivers, based on user permission. This information includes basic knowledge and management methods regarding diabetes. By providing educational information, the aim is to enable those around the user to gain a deeper understanding and provide appropriate support.

[0045] Specific example

[0046] When a user enters "I've been feeling stressed lately and can't sleep at night," the server analyzes this information, identifies the stressors, and suggests simple deep breathing exercises for relaxation. It also analyzes the carbohydrate content from a photo of the user's lunch and notifies the user of the optimal insulin dosage based on their daily activity level. This allows users to receive personalized health management support.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] Users input information about their emotional state and health, and the device receives this data. Input is done in natural language and can be via text or voice.

[0050] Step 2:

[0051] The terminal receives input from the user and sends it to the server in text format. If voice input is used, it is converted to text using speech recognition technology.

[0052] Step 3:

[0053] The server passes the received text data to a natural language processing engine to analyze the user's emotional state. Using an emotion analysis algorithm, it identifies the user's stressors and psychological state.

[0054] Step 4:

[0055] Based on the analysis results, the server generates stress management suggestions tailored to the transitional emotional state. It also refers to an internal knowledge base to provide appropriate lifestyle advice and psychological care suggestions.

[0056] Step 5:

[0057] The device receives suggestions generated from the server and displays the information to the user visually or audibly. The user can then review and implement the suggestions through the application.

[0058] Step 6:

[0059] Users take photos of their meals and upload them to their devices along with meal data. This data can include information such as ingredient names and quantities consumed.

[0060] Step 7:

[0061] The terminal sends meal images and related data to the server, which analyzes the meal content using image analysis techniques. It estimates the amount of nutrients and carbohydrates and calculates the required amount of insulin.

[0062] Step 8:

[0063] The server uses dietary data and historical health data to run a machine learning model and predict the user's future health risks. Based on the prediction results, it generates specific health management suggestions for the user.

[0064] Step 9:

[0065] The device receives prediction results and suggestions from the server and presents them to the user. The user can then refer to this information and use it for daily health management.

[0066] Step 10:

[0067] The server provides educational information to family members and caregivers based on the user's permission. The educational information is shared via the device in an appropriate format, making it accessible to recipients.

[0068] (Example 1)

[0069] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0070] In modern life, personalized health management and daily stress reduction are crucial issues. However, users often struggle to properly manage their emotions and health status, making it difficult to cope with stress and health risks in their daily lives. Furthermore, family members and caregivers around users often have limited access to accurate and useful health information, resulting in a lack of adequate support.

[0071] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0072] In this invention, the server includes means for analyzing the user's natural language input and identifying their emotional state, means for acquiring health data and estimating nutrient levels through image analysis, and means for predicting health risks and generating recommended actions using past health information. This enables the provision of personalized stress management suggestions and health advice.

[0073] "Natural language input" refers to text-based information written in a language that a user normally uses, and is an input method for a computer system to interpret it.

[0074] "Emotional state" refers to information that indicates the user's psychological state and emotional fluctuations, including emotions such as stress and happiness.

[0075] "Generation means" refers to a device or program that has the function of generating suggestions for the user, and in particular, one that uses an AI model to make stress management suggestions.

[0076] A "presentation method" is a means by which a system provides information or advice it has generated to a user, either visually or audibly.

[0077] "Image analysis" refers to the process of processing digital images, extracting and analyzing the information contained within them, and obtaining specific data such as nutrient content.

[0078] "Health risk prediction" is a process that evaluates a user's future health status and potential risks based on their past health information, and suggests actions to maintain their health over time.

[0079] "Recommended actions" are suggestions based on analysis results that users should take to improve or maintain their health.

[0080] "Educational information" refers to information provided to users and their supporters with the aim of improving specific health-related knowledge and skills.

[0081] The embodiment of the invention is a system realized through the cooperation of a user, a terminal, and a server, which enables user health management and emotion analysis. In this system, the terminal receives natural language input from the user and transmits this input data to the server. The server uses an advanced natural language processing engine to analyze the user's emotions and identify their stress levels and causes.

[0082] The server uses a generative AI model based on the results of emotion analysis to generate suggestions for stress management. These suggestions include specific examples such as relaxation techniques like deep breathing and lifestyle adjustments. These suggestions are presented to the user via a terminal, allowing them to receive advice tailored to their individual situation. Furthermore, image analysis software can be used to process photos of meals taken by the user, estimate the nutrient content, and advise on the appropriate amount of insulin.

[0083] Furthermore, the server has a data analysis function that uses past health data to predict future health risks and suggests specific actions to the user based on those predictions. This function is an important tool for users to continuously manage their health.

[0084] Regarding the provision of educational information, the server, with the user's permission, provides information on basic knowledge and management methods for diabetes to family members and caregivers, supporting the user's health management. This allows caregivers to deepen their understanding in order to provide appropriate support.

[0085] As a concrete example, consider a scenario where a user enters into their device, "I've been feeling stressed lately and can't sleep at night." When this information is sent to the server, the server analyzes the data, identifies the source of the stress, and suggests a simple deep breathing technique. Furthermore, it analyzes the carbohydrate content using an image of lunch and provides advice on adjusting insulin levels based on the day's activity level. This enables personalized health management support.

[0086] An example of a prompt message is as follows: "The user has entered information about their stress levels. Based on this data, please generate suggestions to help reduce stress."

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The user uses the device to input information about their health and emotions in natural language. For example, they might input text such as, "I've been feeling stressed lately." The user also inputs health-related data such as photos of their daily meals and blood sugar levels into the device. The device temporarily stores this data and prepares the input data for later processing.

[0090] Step 2:

[0091] The terminal sends text and image data entered by the user to the server. Encryption technology is used during this transmission process to ensure the secure transfer of input data. After transmission, the terminal remains in a waiting state until the data is processed on the server.

[0092] Step 3:

[0093] The server analyzes the received natural language data using a natural language processing engine. Specifically, it analyzes text data and performs calculations to identify the user's emotional state. The results of this analysis reveal the user's stress level and its contributing factors, and the output serves as foundational data for stress management suggestions.

[0094] Step 4:

[0095] The server processes received meal images using an image analysis algorithm. This image processing estimates the types and amounts of nutrients contained in the meal. The resulting nutritional information is used as basic data for providing specific health advice based on the user's diet and for adjusting insulin dosages.

[0096] Step 5:

[0097] The server analyzes past user health data and performs data calculations to predict future health risks. It utilizes statistical models and machine learning algorithms to identify trends in health status. Based on the analysis results, specific recommendations for maintaining health are generated and provided as feedback to the user.

[0098] Step 6:

[0099] The server sends users stress management suggestions and health advice based on the analysis results. This delivery utilizes the device's display function, allowing users to see and act upon the information. For example, simple breathing exercises or dietary improvements may be displayed.

[0100] Step 7:

[0101] The server will only provide health-related educational information to family members and caregivers with the user's permission. This information is intended to improve the knowledge of those around the user so that they can understand their health status and provide appropriate support.

[0102] (Application Example 1)

[0103] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0104] In modern society, individual health management is a crucial issue, yet many people find it difficult to obtain appropriate advice. Furthermore, there is a need to accurately understand the impact of stress and emotional fluctuations on health and to propose concrete actions that are useful in daily life based on that understanding. However, conventional systems have struggled to comprehensively analyze a user's emotions and health status and provide individually optimized health management and product recommendations.

[0105] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0106] In this invention, the server includes means for receiving natural language input from the user, analysis means for analyzing the input and identifying the user's emotional state, generation means for generating stress management suggestions based on the identified emotional state, analysis means for acquiring the user's dietary data and estimating nutrient amounts through image analysis, prediction means for predicting future health risks using past health data, and product recommendation means for recommending relevant products based on the emotional state and health data. As a result, the user can receive accurate advice tailored to their health condition and product recommendations to enrich their daily life.

[0107] "Means for accepting natural language input" refers to a function that provides an interface for receiving text data entered by the user and incorporating it into the system.

[0108] "Analysis means" refers to a function that analyzes user input data and processes it to identify the user's emotional state.

[0109] "Generative means" refers to a function that constructs methods for proposing stress management that is useful to the user, based on identified emotional states.

[0110] "Presentation means" refers to a medium or device for visually or audibly communicating the generated stress management suggestions to the user.

[0111] The "analysis means" refers to a function that processes the collected user meal data based on image analysis technology to estimate the types and amounts of nutrients.

[0112] A "predictive tool" is a function that analyzes past health data and processes it to estimate the user's future health risks.

[0113] "Product recommendation methods" refer to algorithms and technologies that take into account a user's emotional state and health data, and then suggest appropriate products to the user based on that information.

[0114] The system implementing this invention consists of a user, a terminal, and a server. The user accesses the system via a terminal such as a smartphone or tablet and inputs emotional and health information in natural language. The terminal plays the role of transmitting this information to the server.

[0115] The server plays a central role in processing the received information. First, it uses a natural language processing engine (e.g., Google® Cloud Natural Language) to analyze the user's emotional state. This makes it possible to identify the causes and degree of stress. Next, it uses an AI model (e.g., TENSORFLOW®) to generate stress management suggestions tailored to the emotional state. These suggestions include relaxation techniques and lifestyle improvements. In addition, it uses image analysis technology (e.g., OpenCV) to estimate nutrient content from images of meals taken by the user. Based on this information, nutritional guidance is provided that is tailored to the user's health condition.

[0116] Furthermore, the server analyzes past health data and predicts future health risks. Based on these predictions, it generates personalized action suggestions. The server also considers the user's emotional state and health data to execute a product recommendation algorithm that suggests appropriate products. This allows users to receive product information optimized for them.

[0117] For example, if a user enters "I've been feeling tired lately and can't concentrate on my work," the server analyzes this information and recommends relaxation products from the online store. It also analyzes the user's dietary data and provides nutritional advice to encourage a healthier lifestyle.

[0118] An example of a prompt would be the question, "Based on the emotional state and health data obtained from the user, suggest the most suitable health-related products for this user." This allows the system to generate the most effective suggestions for the user.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] Users use their devices to input information about their emotions and health in natural language. This input is then sent to the server as text data by the device.

[0122] Step 2:

[0123] The server passes the received text data to a natural language processing engine, which analyzes the user's emotional state. Here, the input text data is analyzed, and identified emotional states and stressors are output. This process identifies the user's psychological burden and emotional tendencies.

[0124] Step 3:

[0125] Based on the analyzed emotional state, the server uses a generative AI model to generate stress management suggestions. In this step, the results of the emotional analysis are taken as input, and relaxation techniques and lifestyle improvement suggestions are output. The AI ​​model uses data on past effective stress reduction strategies to personalize the suggestions.

[0126] Step 4:

[0127] The user sends a photo of their meal to the server via their device. The device sends the captured image data to the server, and this data forms the basis for the subsequent analysis.

[0128] Step 5:

[0129] The server uses image analysis technology to convert images of meals provided by the user into nutritional information. The type and amount of nutrients are estimated from the input image data, and the results are output. This data is then used to analyze the components within the image and estimate the nutritional value.

[0130] Step 6:

[0131] The server predicts future health risks based on past health data. A history of health data is input, and a future health status prediction is output. This analysis then prompts the system to suggest preventative measures to help the user maintain their health.

[0132] Step 7:

[0133] The server uses product recommendation tools to suggest relevant products based on the user's emotional state and health data. In this step, emotional and health data are used as input to output a list of products best suited to the user. The product recommendation algorithm works by referring to past purchase history to present products that it deems appropriate.

[0134] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0135] To implement the present invention, a system having an emotion engine for inputting and analyzing information from the user is required. This system operates with a configuration including the user, a terminal, and a server, and in particular, by incorporating the emotion engine, it analyzes the user's emotional state in detail.

[0136] User-device interaction

[0137] Users can input information about their emotions and health status through the system using natural language. Input can be done via voice or text. Users can also take photos of their meals and upload them to the device as meal data. The device aggregates this information and sends it to a server for processing.

[0138] Utilizing the Emotion Engine

[0139] The server passes the information sent from the terminal to the emotion engine for analysis. This emotion engine accurately recognizes the user's emotions using voice analysis and facial expression analysis technologies. For example, it can read emotions from the user's voice tone and facial expressions, and based on this, identify the stress and psychological state the user is experiencing.

[0140] Data analysis and proposal generation

[0141] The server generates stress management suggestions based on the emotional state obtained through analysis. Here, it provides users with customized stress reduction measures and health maintenance behavior suggestions, taking into account past health data and emotional states.

[0142] The server also processes the user's meal data through image analysis to evaluate the amount of nutrients consumed. Using these results, it can suggest appropriate insulin dosages and nutritional advice. In addition, it analyzes past health data to predict future health risks and provides the user with a concrete action plan.

[0143] Providing educational information to family members and supporters

[0144] The server also provides educational information to family members and caregivers, based on the user's permission. This information includes knowledge to promote a basic understanding of diabetes, creating an environment where those around the user can provide appropriate support.

[0145] Specific example

[0146] Specifically, if a user voice-inputs, "I've been feeling irritable lately and can't sleep at night," the emotion engine identifies the stress level from the tone of their voice. Based on this, the server suggests meditation and breathing exercises. It also takes a photo of the user's lunch, analyzes the nutrients consumed, calculates the appropriate insulin dosage, and notifies the user. Through these processes, users can efficiently manage their own health while receiving psychological support.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] Users input information about their emotions and health status in natural language and provide it as voice or text data through their device. Users can also upload photos of their meals to their device.

[0150] Step 2:

[0151] The terminal receives voice data from the user and converts it into text data using speech recognition technology as needed. The input data is then sent to the server.

[0152] Step 3:

[0153] The server receives text data sent from the terminal and image data of the user's meal.

[0154] Step 4:

[0155] The server uses an emotion engine to analyze the user's emotions from text or audio. The emotion engine recognizes emotions and identifies emotional states using speech tone analysis and, if possible, facial expression data.

[0156] Step 5:

[0157] The server generates specific suggestions for stress management based on the user's emotional state. For example, it might suggest breathing exercises to reduce stress or daily relaxation techniques.

[0158] Step 6:

[0159] The server processes the user's meal images using image analysis technology to analyze the nutrients in the food. It calculates the amount of nutrients and then calculates the required amount of insulin.

[0160] Step 7:

[0161] The server uses past health data to predict future health risks. Based on these predictions, it provides users with suggestions for maintaining their health.

[0162] Step 8:

[0163] The terminal displays stress management suggestions, nutritional advice, and health risk predictions received from the server to the user.

[0164] Step 9:

[0165] The server sends educational information to family members and caregivers based on the user's consent. This enables caregivers to properly support the user's health management.

[0166] (Example 2)

[0167] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0168] In modern society, there is a need to quickly understand an individual's stress level and health status and provide appropriate countermeasures. However, conventional systems struggle to accurately analyze a user's emotional state and provide appropriate suggestions tailored to their individual health condition. Furthermore, the provision of health information to family members and caregivers is insufficient, limiting the support users receive. To improve this situation, technology is needed that comprehensively analyzes a user's emotional and health status and enables reliable health management and support based on that analysis.

[0169] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0170] In this invention, the server includes means for inputting information from the user in the form of voice or text, means for analyzing the information using speech recognition and natural language processing technologies to identify the user's emotional state, and means for inputting image data of the meal contents via a terminal and estimating the amount of nutrients using image analysis technology. This enables accurate analysis of the user's emotional state and health state, and allows for the provision of appropriate stress management suggestions and nutritional guidance based on the results. Furthermore, by providing health-related information to family members and caregivers, the support system surrounding the user can be strengthened.

[0171] "Speech recognition" is a technology that analyzes a user's voice data and converts it into text data.

[0172] "Natural language processing" is a technology that analyzes natural language data input by users to understand its meaning and context.

[0173] "Emotional state" refers to the user's psychological state and stress level, and is identified through analysis.

[0174] "Image analysis" is a technique that analyzes captured image data and extracts information from the image.

[0175] "Nutrient content" refers to the types and amounts of nutrients contained in the food consumed by the user.

[0176] "Stress management" refers to strategies aimed at alleviating users' mental stress and promoting psychological stability.

[0177] "Health management" refers to a series of actions and guidance taken to maintain and improve the user's health status.

[0178] A "supporter" is a person or organization that plays a role in assisting users with their health management and provides appropriate information and support.

[0179] To implement this invention, a system consisting of a user, a terminal, and a server is used. The user inputs their emotions and health status in voice or text format, and also uploads photos of meals to the terminal. The terminal converts the input voice into text using speech recognition software and sends the text data and image data to the server. General speech recognition and image processing technologies are used in this process.

[0180] The server analyzes received text and audio data using natural language processing technology and identifies the user's emotional state using an emotion engine. For example, it can understand a user's psychological state from their tone of voice and word choice. Additionally, image data is analyzed using image analysis algorithms to evaluate the nutrients contained in their meals. This allows the system to determine the appropriate insulin dosage and provide nutritional guidance based on the user's diet.

[0181] Based on the analysis results, the server provides users with suggestions for stress reduction and health management, including meditation and breathing exercises. Furthermore, with the user's permission, it provides health-related educational information to family members and caregivers.

[0182] For example, if a user prompts them with a message like, "I've been feeling irritable lately. I had a healthy lunch today," the server will use an emotion engine to assess the user's stress level and suggest appropriate relaxation methods. It can also analyze a photo of the lunch and provide nutritional advice based on the balance of the food.

[0183] Thus, the present invention can provide users with comprehensive health support through a detailed analysis of their emotional and physical states.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] Users input information about their emotions and health status via voice or text, and upload photos of their meals to the device. The input information is converted into text data by voice recognition software and aggregated on the device. In this process, voice data is converted into text data, and image data is formatted and prepared.

[0187] Step 2:

[0188] The terminal sends aggregated data from the user to the server. Text data and image data are separated and transferred to the server. The input received by the server consists of text information about the user's emotions and images of the food they ate.

[0189] Step 3:

[0190] The server analyzes the received text data using a natural language processing engine to determine the emotional tone and content. This analysis identifies the user's emotional state. The analyzed emotional state is then output. During this process, a generative AI model can be used to capture subtle emotional nuances.

[0191] Step 4:

[0192] The server evaluates stress levels and psychological states based on emotional states obtained from the emotion engine, and generates stress relief measures tailored to the user. The generated suggestions are output in text format and used for the user's stress management.

[0193] Step 5:

[0194] The server applies an image analysis algorithm to analyze image data of meals and calculate the amount of nutrients consumed. The analysis results include the type and amount of each nutrient, and nutritional advice tailored to the user's health condition is generated.

[0195] Step 6:

[0196] The server combines emotion analysis results and nutritional analysis results to customize optimal health suggestions for the user. This includes suggestions for a balanced diet, appropriate exercise, and relaxation methods. The customized suggestions are output and sent to the terminal.

[0197] Step 7:

[0198] The device notifies the user of suggestions received from the server. Based on the notification, the user can manage their emotions and health and try the suggested methods.

[0199] This series of steps allows users to gain a detailed understanding of their health status in their daily lives and receive appropriate care.

[0200] (Application Example 2)

[0201] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0202] In modern society, many people are exposed to stress, making health management crucial. Furthermore, consumers face the challenge of not being able to obtain health- and emotionally balanced information when shopping in stores, making it difficult to select appropriate products. In this context, there is a need for methods to improve the in-store shopping experience while considering health and emotional states.

[0203] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0204] In this invention, the server includes processing means for identifying the user's emotional state, analysis means for predicting health risks, and a function for recommending product information in physical stores. This enables users to make appropriate product choices based on their health and emotions in a real-world shopping environment.

[0205] "Natural language input" refers to users providing information using voice or text in the form of language that humans normally use.

[0206] "Processing methods for identifying emotional states" refer to technologies that analyze voice and text data obtained from users to determine their psychological state.

[0207] A "stress management suggestion generation mechanism" is a system that automatically devises methods and actions to reduce stress based on the user's emotional state.

[0208] "Display function" refers to technology that presents generated suggestions and analysis results to the user visually or audibly.

[0209] The "processing method for estimating nutrient content through image analysis" is a technology that analyzes images of meals taken by the user to estimate the types and amounts of nutrients contained within.

[0210] "Analysis methods" refer to methods for evaluating future health risks using a user's past health data.

[0211] The "function to recommend product information in a real-world shopping environment" is a technology that suggests the most suitable products to users when they are choosing products in an actual store, based on their health condition and emotions.

[0212] This invention requires a system in which a user, a terminal, and a server work together. The system receives natural language data (voice or text) input by the user at the terminal and sends it to the server for analysis. The server uses emotion analysis software (e.g., Affectiva SDK) to identify the user's emotional state. Image data captured by the user is also sent from the terminal, and the server uses image analysis technology to estimate nutrient levels. Furthermore, the server refers to past health data to analyze future health risks.

[0213] When users select products in physical stores, smart glasses or smartphones (e.g., Google Glass®, iPhone®) are utilized. A server supports the shopping experience by recommending the most suitable products, taking into account the user's health and emotional state. In this process, health risk presentations based on past health data and real-time emotional and health management information from the physical store are integrated and utilized.

[0214] As a concrete example, if a user in a physical store says, "I've been feeling tired lately, so I'd like a healthy snack," through smart glasses, the system will perform sentiment analysis and recommend products that suit the user's state. For instance, if the user has a history of limiting sugar intake, it will suggest low-sugar snacks. In this way, the system helps users make healthy and satisfying product choices.

[0215] An example of an input prompt statement for a generative AI model is as follows:

[0216] "A user says in a store, 'I'm tired and want something sweet.' This user has a history of limiting sugar intake. Please design a system that suggests healthy sweets to them."

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The user provides natural language voice input through their device. The input voice data is collected using a smartphone or smart glasses and converted into text. In this process, a speech recognition API is used to convert the voice data into text data. The input is natural speech such as "I've been tired lately and want to eat something sweet."

[0220] Step 2:

[0221] The terminal sends text data from the user to a server for sentiment analysis. The server uses sentiment analysis software to analyze the voice or text data and identify the user's emotional state. For example, it might determine that the user is feeling stressed. The input is text data, and the output is emotional state data.

[0222] Step 3:

[0223] A user takes a photo of a product, which is then sent to a server via their device. The server uses image analysis technology to estimate detailed product information, including the types and amounts of nutrients it contains, from this photo data. Image data is received as input, and nutritional information data is obtained as output. Specifically, a machine learning algorithm is used to recognize the product label from the image, and then the nutritional information is retrieved by searching a database based on that information.

[0224] Step 4:

[0225] The server compares the user's emotional state information with past health data to analyze future health risks. For example, it assesses the risk of sugar intake based on past data. In this process, emotional state and health data are used as input, and risk assessment data is generated as output.

[0226] Step 5:

[0227] The server recommends the most suitable products to the user based on emotional state data, health risk data, and nutritional information data. This recommendation supports in-store purchases. Specifically, it selects the product best suited to the user's preferences and health condition from the product database and sends that information to the terminal. Recommended product information is generated as output.

[0228] Step 6:

[0229] The terminal displays product recommendation information received from the server to the user. Users can receive information on suitable products through smart glasses or smartphones. The displayed information includes product name, nutrients, and health effects. Recommended product information is the input, and visual information presented to the user is generated as the output.

[0230] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0231] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0232] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0236] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0237] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0238] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0239] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0240] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0241] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0242] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0243] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0244] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0245] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0246] To implement the present invention, a system comprising multiple elements is required. This system operates with a configuration including a user, a terminal, and a server.

[0247] User-device interaction

[0248] Users utilize the system via their devices for daily health management. Users can input information about their emotions and health status in natural language. They can also take photos of their meals and input health data such as blood sugar levels into the device. The device collects this data and transmits it to the server.

[0249] Server-based data analysis and proposal generation

[0250] The server receives input data sent from the terminal and analyzes the user's emotions using a natural language processing engine. This analysis identifies the user's stress level and specific stressors. Furthermore, the server utilizes an AI model to generate stress management suggestions that can help reduce stress. These suggestions may include relaxation techniques and lifestyle improvements.

[0251] The server also uses image analysis technology to process the user's dietary data and estimate the amount of nutrients. This allows it to indicate the amount of insulin the user needs and provide other nutritional advice. At the same time, it analyzes past health data to predict the user's future health risks. Based on this risk prediction, it suggests specific actions to maintain good health.

[0252] Provision of educational information

[0253] Furthermore, the server provides educational information to patients' families and caregivers, based on user permission. This information includes basic knowledge and management methods regarding diabetes. By providing educational information, the aim is to enable those around the user to gain a deeper understanding and provide appropriate support.

[0254] Specific example

[0255] When a user enters "I've been feeling stressed lately and can't sleep at night," the server analyzes this information, identifies the stressors, and suggests simple deep breathing exercises for relaxation. It also analyzes the carbohydrate content from a photo of the user's lunch and notifies the user of the optimal insulin dosage based on their daily activity level. This allows users to receive personalized health management support.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] Users input information about their emotional state and health, and the device receives this data. Input is done in natural language and can be via text or voice.

[0259] Step 2:

[0260] The terminal receives input from the user and sends it to the server in text format. If voice input is used, it is converted to text using speech recognition technology.

[0261] Step 3:

[0262] The server passes the received text data to a natural language processing engine to analyze the user's emotional state. Using an emotion analysis algorithm, it identifies the user's stressors and psychological state.

[0263] Step 4:

[0264] Based on the analysis results, the server generates stress management suggestions tailored to the transitional emotional state. It also refers to an internal knowledge base to provide appropriate lifestyle advice and psychological care suggestions.

[0265] Step 5:

[0266] The device receives suggestions generated from the server and displays the information to the user visually or audibly. The user can then review and implement the suggestions through the application.

[0267] Step 6:

[0268] Users take photos of their meals and upload them to their devices along with meal data. This data can include information such as ingredient names and quantities consumed.

[0269] Step 7:

[0270] The terminal sends meal images and related data to the server, which analyzes the meal content using image analysis techniques. It estimates the amount of nutrients and carbohydrates and calculates the required amount of insulin.

[0271] Step 8:

[0272] The server uses dietary data and historical health data to run a machine learning model and predict the user's future health risks. Based on the prediction results, it generates specific health management suggestions for the user.

[0273] Step 9:

[0274] The device receives prediction results and suggestions from the server and presents them to the user. The user can then refer to this information and use it for daily health management.

[0275] Step 10:

[0276] The server provides educational information to family members and caregivers based on the user's permission. The educational information is shared via the device in an appropriate format, making it accessible to recipients.

[0277] (Example 1)

[0278] Next, we will describe Example 1. 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."

[0279] In modern life, personalized health management and daily stress reduction are crucial issues. However, users often struggle to properly manage their emotions and health status, making it difficult to cope with stress and health risks in their daily lives. Furthermore, family members and caregivers around users often have limited access to accurate and useful health information, resulting in a lack of adequate support.

[0280] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 1 is realized by the following means.

[0281] In this invention, the server includes means for analyzing the natural language input of the user to identify the emotional state, means for obtaining health data and estimating the amount of nutrients by image analysis, and means for predicting health risks using past health information and generating recommended actions. Thereby, it becomes possible to propose individualized stress management and provide health advice.

[0282] "Input by natural language" refers to text-based information described in the language that the user normally uses, and is an input method for the computer system to interpret it.

[0283] "Emotional state" refers to information indicating the psychological state and emotional movements of the user, and includes emotions such as stress and happiness.

[0284] "Generation means" refers to a device or program having a function for generating proposals for the user, and particularly refers to a means for proposing stress management using an AI model.

[0285] "Presentation means" is a means for the system to provide the information and advice generated for the user visually or audibly.

[0286] "Image analysis" refers to the process of processing a digital image, extracting and analyzing the information contained therein, and obtaining specific data such as the amount of nutrients.

[0287] "Health risk prediction" is a process of evaluating the future health status and potential risks based on the past health information of the user, and suggesting actions for maintaining health in the future.

[0288] "Recommended action" refers to a proposal for specific actions that the user should take to improve or maintain health based on the analysis results.

[0289] "Educational information" refers to information provided to users and their supporters with the aim of improving specific health-related knowledge and skills.

[0290] The embodiment of the invention is a system realized through the cooperation of a user, a terminal, and a server, which enables user health management and emotion analysis. In this system, the terminal receives natural language input from the user and transmits this input data to the server. The server uses an advanced natural language processing engine to analyze the user's emotions and identify their stress levels and causes.

[0291] The server uses a generative AI model based on the results of emotion analysis to generate suggestions for stress management. These suggestions include specific examples such as relaxation techniques like deep breathing and lifestyle adjustments. These suggestions are presented to the user via a terminal, allowing them to receive advice tailored to their individual situation. Furthermore, image analysis software can be used to process photos of meals taken by the user, estimate the nutrient content, and advise on the appropriate amount of insulin.

[0292] Furthermore, the server has a data analysis function that uses past health data to predict future health risks and suggests specific actions to the user based on those predictions. This function is an important tool for users to continuously manage their health.

[0293] Regarding the provision of educational information, the server, with the user's permission, provides information on basic knowledge and management methods for diabetes to family members and caregivers, supporting the user's health management. This allows caregivers to deepen their understanding in order to provide appropriate support.

[0294] As a concrete example, consider a scenario where a user enters into their device, "I've been feeling stressed lately and can't sleep at night." When this information is sent to the server, the server analyzes the data, identifies the source of the stress, and suggests a simple deep breathing technique. Furthermore, it analyzes the carbohydrate content using an image of lunch and provides advice on adjusting insulin levels based on the day's activity level. This enables personalized health management support.

[0295] An example of a prompt message is as follows: "The user has entered information about their stress levels. Based on this data, please generate suggestions to help reduce stress."

[0296] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0297] Step 1:

[0298] The user uses the device to input information about their health and emotions in natural language. For example, they might input text such as, "I've been feeling stressed lately." The user also inputs health-related data such as photos of their daily meals and blood sugar levels into the device. The device temporarily stores this data and prepares the input data for later processing.

[0299] Step 2:

[0300] The terminal sends text and image data entered by the user to the server. Encryption technology is used during this transmission process to ensure the secure transfer of input data. After transmission, the terminal remains in a waiting state until the data is processed on the server.

[0301] Step 3:

[0302] The server analyzes the received natural language data by means of a natural language processing engine. Specifically, it analyzes the text data and performs operations to identify the user's emotional state. Based on the analysis results, the user's stress state and its causes are revealed, and the output serves as the basic data for proposals for stress management.

[0303] Step 4:

[0304] The server processes the received meal image using an image analysis algorithm. Through this image processing, the types and amounts of nutrients contained in the meal are estimated. The obtained nutritional information is used as basic data for specific health advice based on the user's diet and for adjusting the insulin dosage.

[0305] Step 5:

[0306] The server analyzes the past health data of the user and performs data operations to predict future health risks. At this time, statistical models and machine learning algorithms are utilized to clarify the trends in the health status. Based on the analysis results, specific recommended actions for maintaining health are generated and fed back to the user as the output.

[0307] Step 6:

[0308] The server sends proposals for stress management and health advice based on the analysis results to the user. For this delivery, the display function of the terminal is used, and the user visually recognizes it and reflects it in their actions. For example, simple deep breathing methods or proposals for improving the diet may be displayed.

[0309] Step 7:

[0310] The server provides health-related educational information to family members and supporters only when it has obtained the user's permission. This information provision aims to improve the knowledge of the people around so that they can understand the user's health status and provide appropriate support.

[0311] (Application Example 1)

[0312] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0313] In modern society, individual health management is a crucial issue, yet many people find it difficult to obtain appropriate advice. Furthermore, there is a need to accurately understand the impact of stress and emotional fluctuations on health and to propose concrete actions that are useful in daily life based on that understanding. However, conventional systems have struggled to comprehensively analyze a user's emotions and health status and provide individually optimized health management and product recommendations.

[0314] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0315] In this invention, the server includes means for receiving natural language input from the user, analysis means for analyzing the input and identifying the user's emotional state, generation means for generating stress management suggestions based on the identified emotional state, analysis means for acquiring the user's dietary data and estimating nutrient amounts through image analysis, prediction means for predicting future health risks using past health data, and product recommendation means for recommending relevant products based on the emotional state and health data. As a result, the user can receive accurate advice tailored to their health condition and product recommendations to enrich their daily life.

[0316] "Means for accepting natural language input" refers to a function that provides an interface for receiving text data entered by the user and incorporating it into the system.

[0317] "Analysis means" refers to a function that analyzes user input data and processes it to identify the user's emotional state.

[0318] "Generative means" refers to a function that constructs methods for proposing stress management that is useful to the user, based on identified emotional states.

[0319] "Presentation means" refers to a medium or device for visually or audibly communicating the generated stress management suggestions to the user.

[0320] The "analysis means" refers to a function that processes the collected user meal data based on image analysis technology to estimate the types and amounts of nutrients.

[0321] A "predictive tool" is a function that analyzes past health data and processes it to estimate the user's future health risks.

[0322] "Product recommendation methods" refer to algorithms and technologies that take into account a user's emotional state and health data, and then suggest appropriate products to the user based on that information.

[0323] The system implementing this invention consists of a user, a terminal, and a server. The user accesses the system via a terminal such as a smartphone or tablet and inputs emotional and health information in natural language. The terminal plays the role of transmitting this information to the server.

[0324] The server plays a central role in processing the received information. First, it uses a natural language processing engine (e.g., Google Cloud Natural Language) to analyze the user's emotional state. This makes it possible to identify the causes and degree of stress. Next, it uses an AI model (e.g., TensorFlow) to generate stress management suggestions tailored to the emotional state. These suggestions include relaxation techniques and lifestyle improvements. In addition, it uses image analysis technology (e.g., OpenCV) to estimate nutrient content from images of meals taken by the user. Based on this information, nutritional guidance is provided that is tailored to the user's health condition.

[0325] Furthermore, the server analyzes past health data and predicts future health risks. Based on these predictions, it generates personalized action suggestions. The server also considers the user's emotional state and health data to execute a product recommendation algorithm that suggests appropriate products. This allows users to receive product information optimized for them.

[0326] For example, if a user enters "I've been feeling tired lately and can't concentrate on my work," the server analyzes this information and recommends relaxation products from the online store. It also analyzes the user's dietary data and provides nutritional advice to encourage a healthier lifestyle.

[0327] An example of a prompt would be the question, "Based on the emotional state and health data obtained from the user, suggest the most suitable health-related products for this user." This allows the system to generate the most effective suggestions for the user.

[0328] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0329] Step 1:

[0330] Users use their devices to input information about their emotions and health in natural language. This input is then sent to the server as text data by the device.

[0331] Step 2:

[0332] The server passes the received text data to a natural language processing engine, which analyzes the user's emotional state. Here, the input text data is analyzed, and identified emotional states and stressors are output. This process identifies the user's psychological burden and emotional tendencies.

[0333] Step 3:

[0334] Based on the analyzed emotional state, the server uses a generative AI model to generate stress management suggestions. In this step, the results of the emotional analysis are taken as input, and relaxation techniques and lifestyle improvement suggestions are output. The AI ​​model uses data on past effective stress reduction strategies to personalize the suggestions.

[0335] Step 4:

[0336] The user sends a photo of their meal to the server via their device. The device sends the captured image data to the server, and this data forms the basis for the subsequent analysis.

[0337] Step 5:

[0338] The server uses image analysis technology to convert images of meals provided by the user into nutritional information. The type and amount of nutrients are estimated from the input image data, and the results are output. This data is then used to analyze the components within the image and estimate the nutritional value.

[0339] Step 6:

[0340] The server predicts future health risks based on past health data. A history of health data is input, and a future health status prediction is output. This analysis then prompts the system to suggest preventative measures to help the user maintain their health.

[0341] Step 7:

[0342] The server uses product recommendation tools to suggest relevant products based on the user's emotional state and health data. In this step, emotional and health data are used as input to output a list of products best suited to the user. The product recommendation algorithm works by referring to past purchase history to present products that it deems appropriate.

[0343] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0344] To implement the present invention, a system having an emotion engine for inputting and analyzing information from the user is required. This system operates with a configuration including the user, a terminal, and a server, and in particular, by incorporating the emotion engine, it analyzes the user's emotional state in detail.

[0345] User-device interaction

[0346] Users can input information about their emotions and health status through the system using natural language. Input can be done via voice or text. Users can also take photos of their meals and upload them to the device as meal data. The device aggregates this information and sends it to a server for processing.

[0347] Utilizing the Emotion Engine

[0348] The server passes the information sent from the terminal to the emotion engine for analysis. This emotion engine accurately recognizes the user's emotions using voice analysis and facial expression analysis technologies. For example, it can read emotions from the user's voice tone and facial expressions, and based on this, identify the stress and psychological state the user is experiencing.

[0349] Data analysis and proposal generation

[0350] The server generates stress management suggestions based on the emotional state obtained through analysis. Here, it provides users with customized stress reduction measures and health maintenance behavior suggestions, taking into account past health data and emotional states.

[0351] The server also processes the user's meal data through image analysis to evaluate the amount of nutrients consumed. Using these results, it can suggest appropriate insulin dosages and nutritional advice. In addition, it analyzes past health data to predict future health risks and provides the user with a concrete action plan.

[0352] Providing educational information to family members and supporters

[0353] The server also provides educational information to family members and caregivers, based on the user's permission. This information includes knowledge to promote a basic understanding of diabetes, creating an environment where those around the user can provide appropriate support.

[0354] Specific example

[0355] Specifically, if a user voice-inputs, "I've been feeling irritable lately and can't sleep at night," the emotion engine identifies the stress level from the tone of their voice. Based on this, the server suggests meditation and breathing exercises. It also takes a photo of the user's lunch, analyzes the nutrients consumed, calculates the appropriate insulin dosage, and notifies the user. Through these processes, users can efficiently manage their own health while receiving psychological support.

[0356] The following describes the processing flow.

[0357] Step 1:

[0358] Users input information about their emotions and health status in natural language and provide it as voice or text data through their device. Users can also upload photos of their meals to their device.

[0359] Step 2:

[0360] The terminal receives voice data from the user and converts it into text data using speech recognition technology as needed. The input data is then sent to the server.

[0361] Step 3:

[0362] The server receives text data sent from the terminal and image data of the user's meal.

[0363] Step 4:

[0364] The server uses an emotion engine to analyze the user's emotions from text or audio. The emotion engine recognizes emotions and identifies emotional states using speech tone analysis and, if possible, facial expression data.

[0365] Step 5:

[0366] The server generates specific suggestions for stress management based on the user's emotional state. For example, it might suggest breathing exercises to reduce stress or daily relaxation techniques.

[0367] Step 6:

[0368] The server processes the user's meal images using image analysis technology to analyze the nutrients in the food. It calculates the amount of nutrients and then calculates the required amount of insulin.

[0369] Step 7:

[0370] The server uses past health data to predict future health risks. Based on these predictions, it provides users with suggestions for maintaining their health.

[0371] Step 8:

[0372] The terminal displays stress management suggestions, nutritional advice, and health risk predictions received from the server to the user.

[0373] Step 9:

[0374] The server sends educational information to family members and caregivers based on the user's consent. This enables caregivers to properly support the user's health management.

[0375] (Example 2)

[0376] Next, we will describe Example 2. 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".

[0377] In modern society, there is a need to quickly understand an individual's stress level and health status and provide appropriate countermeasures. However, conventional systems struggle to accurately analyze a user's emotional state and provide appropriate suggestions tailored to their individual health condition. Furthermore, the provision of health information to family members and caregivers is insufficient, limiting the support users receive. To improve this situation, technology is needed that comprehensively analyzes a user's emotional and health status and enables reliable health management and support based on that analysis.

[0378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0379] In this invention, the server includes means for inputting information from the user in the form of voice or text, means for analyzing the information using speech recognition and natural language processing technologies to identify the user's emotional state, and means for inputting image data of the meal contents via a terminal and estimating the amount of nutrients using image analysis technology. This enables accurate analysis of the user's emotional state and health state, and allows for the provision of appropriate stress management suggestions and nutritional guidance based on the results. Furthermore, by providing health-related information to family members and caregivers, the support system surrounding the user can be strengthened.

[0380] "Speech recognition" is a technology that analyzes a user's voice data and converts it into text data.

[0381] "Natural language processing" is a technology that analyzes natural language data input by users to understand its meaning and context.

[0382] "Emotional state" refers to the user's psychological state and stress level, and is identified through analysis.

[0383] "Image analysis" is a technique that analyzes captured image data and extracts information from the image.

[0384] "Nutrient content" refers to the types and amounts of nutrients contained in the food consumed by the user.

[0385] "Stress management" refers to strategies aimed at alleviating users' mental stress and promoting psychological stability.

[0386] "Health management" refers to a series of actions and guidance taken to maintain and improve the user's health status.

[0387] A "supporter" is a person or organization that plays a role in assisting users with their health management and provides appropriate information and support.

[0388] To implement this invention, a system consisting of a user, a terminal, and a server is used. The user inputs their emotions and health status in voice or text format, and also uploads photos of meals to the terminal. The terminal converts the input voice into text using speech recognition software and sends the text data and image data to the server. General speech recognition and image processing technologies are used in this process.

[0389] The server analyzes received text and audio data using natural language processing technology and identifies the user's emotional state using an emotion engine. For example, it can understand a user's psychological state from their tone of voice and word choice. Additionally, image data is analyzed using image analysis algorithms to evaluate the nutrients contained in their meals. This allows the system to determine the appropriate insulin dosage and provide nutritional guidance based on the user's diet.

[0390] Based on the analysis results, the server provides users with suggestions for stress reduction and health management, including meditation and breathing exercises. Furthermore, with the user's permission, it provides health-related educational information to family members and caregivers.

[0391] For example, if a user prompts them with a message like, "I've been feeling irritable lately. I had a healthy lunch today," the server will use an emotion engine to assess the user's stress level and suggest appropriate relaxation methods. It can also analyze a photo of the lunch and provide nutritional advice based on the balance of the food.

[0392] Thus, the present invention can provide users with comprehensive health support through a detailed analysis of their emotional and physical states.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] Users input information about their emotions and health status via voice or text, and upload photos of their meals to the device. The input information is converted into text data by voice recognition software and aggregated on the device. In this process, voice data is converted into text data, and image data is formatted and prepared.

[0396] Step 2:

[0397] The terminal sends aggregated data from the user to the server. Text data and image data are separated and transferred to the server. The input received by the server consists of text information about the user's emotions and images of the food they ate.

[0398] Step 3:

[0399] The server analyzes the received text data using a natural language processing engine to determine the emotional tone and content. This analysis identifies the user's emotional state. The analyzed emotional state is then output. During this process, a generative AI model can be used to capture subtle emotional nuances.

[0400] Step 4:

[0401] The server evaluates stress levels and psychological states based on emotional states obtained from the emotion engine, and generates stress relief measures tailored to the user. The generated suggestions are output in text format and used for the user's stress management.

[0402] Step 5:

[0403] The server applies an image analysis algorithm to analyze image data of meals and calculate the amount of nutrients consumed. The analysis results include the type and amount of each nutrient, and nutritional advice tailored to the user's health condition is generated.

[0404] Step 6:

[0405] The server combines emotion analysis results and nutritional analysis results to customize optimal health suggestions for the user. This includes suggestions for a balanced diet, appropriate exercise, and relaxation methods. The customized suggestions are output and sent to the terminal.

[0406] Step 7:

[0407] The device notifies the user of suggestions received from the server. Based on the notification, the user can manage their emotions and health and try the suggested methods.

[0408] This series of steps allows users to gain a detailed understanding of their health status in their daily lives and receive appropriate care.

[0409] (Application Example 2)

[0410] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0411] In modern society, many people are exposed to stress, making health management crucial. Furthermore, consumers face the challenge of not being able to obtain health- and emotionally balanced information when shopping in stores, making it difficult to select appropriate products. In this context, there is a need for methods to improve the in-store shopping experience while considering health and emotional states.

[0412] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0413] In this invention, the server includes processing means for identifying the user's emotional state, analysis means for predicting health risks, and a function for recommending product information in physical stores. This enables users to make appropriate product choices based on their health and emotions in a real-world shopping environment.

[0414] "Natural language input" refers to users providing information using voice or text in the form of language that humans normally use.

[0415] "Processing methods for identifying emotional states" refer to technologies that analyze voice and text data obtained from users to determine their psychological state.

[0416] A "stress management suggestion generation mechanism" is a system that automatically devises methods and actions to reduce stress based on the user's emotional state.

[0417] "Display function" refers to technology that presents generated suggestions and analysis results to the user visually or audibly.

[0418] The "processing method for estimating nutrient content through image analysis" is a technology that analyzes images of meals taken by the user to estimate the types and amounts of nutrients contained within.

[0419] "Analysis methods" refer to methods for evaluating future health risks using a user's past health data.

[0420] The "function to recommend product information in a real-world shopping environment" is a technology that suggests the most suitable products to users when they are choosing products in an actual store, based on their health condition and emotions.

[0421] This invention requires a system in which a user, a terminal, and a server work together. The system receives natural language data (voice or text) input by the user at the terminal and sends it to the server for analysis. The server uses emotion analysis software (e.g., Affectiva SDK) to identify the user's emotional state. Image data captured by the user is also sent from the terminal, and the server uses image analysis technology to estimate nutrient levels. Furthermore, the server refers to past health data to analyze future health risks.

[0422] When users select products in physical stores, smart glasses and smartphones (e.g., Google Glass, iPhone) are utilized. A server supports the shopping experience by recommending the most suitable products, taking into account the user's health and emotional state. In this process, health risk presentations based on past health data and real-time emotional and health management information from the physical store are integrated and utilized.

[0423] As a concrete example, if a user in a physical store says, "I've been feeling tired lately, so I'd like a healthy snack," through smart glasses, the system will perform sentiment analysis and recommend products that suit the user's state. For instance, if the user has a history of limiting sugar intake, it will suggest low-sugar snacks. In this way, the system helps users make healthy and satisfying product choices.

[0424] An example of an input prompt statement for a generative AI model is as follows:

[0425] "A user says in a store, 'I'm tired and want something sweet.' This user has a history of limiting sugar intake. Please design a system that suggests healthy sweets to them."

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The user provides natural language voice input through their device. The input voice data is collected using a smartphone or smart glasses and converted into text. In this process, a speech recognition API is used to convert the voice data into text data. The input is natural speech such as "I've been tired lately and want to eat something sweet."

[0429] Step 2:

[0430] The terminal sends text data from the user to a server for sentiment analysis. The server uses sentiment analysis software to analyze the voice or text data and identify the user's emotional state. For example, it might determine that the user is feeling stressed. The input is text data, and the output is emotional state data.

[0431] Step 3:

[0432] A user takes a photo of a product, which is then sent to a server via their device. The server uses image analysis technology to estimate detailed product information, including the types and amounts of nutrients it contains, from this photo data. Image data is received as input, and nutritional information data is obtained as output. Specifically, a machine learning algorithm is used to recognize the product label from the image, and then the nutritional information is retrieved by searching a database based on that information.

[0433] Step 4:

[0434] The server compares the user's emotional state information with past health data to analyze future health risks. For example, it assesses the risk of sugar intake based on past data. In this process, emotional state and health data are used as input, and risk assessment data is generated as output.

[0435] Step 5:

[0436] The server recommends the most suitable products to the user based on emotional state data, health risk data, and nutritional information data. This recommendation supports in-store purchases. Specifically, it selects the product best suited to the user's preferences and health condition from the product database and sends that information to the terminal. Recommended product information is generated as output.

[0437] Step 6:

[0438] The terminal displays product recommendation information received from the server to the user. Users can receive information on suitable products through smart glasses or smartphones. The displayed information includes product name, nutrients, and health effects. Recommended product information is the input, and visual information presented to the user is generated as the output.

[0439] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0440] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0441] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0442] [Third Embodiment]

[0443] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0444] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0445] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0446] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0447] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0448] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0449] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0450] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0451] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0452] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0453] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0454] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0455] To implement the present invention, a system comprising multiple elements is required. This system operates with a configuration including a user, a terminal, and a server.

[0456] User-device interaction

[0457] Users utilize the system via their devices for daily health management. Users can input information about their emotions and health status in natural language. They can also take photos of their meals and input health data such as blood sugar levels into the device. The device collects this data and transmits it to the server.

[0458] Server-based data analysis and proposal generation

[0459] The server receives input data sent from the terminal and analyzes the user's emotions using a natural language processing engine. This analysis identifies the user's stress level and specific stressors. Furthermore, the server utilizes an AI model to generate stress management suggestions that can help reduce stress. These suggestions may include relaxation techniques and lifestyle improvements.

[0460] The server also uses image analysis technology to process the user's dietary data and estimate the amount of nutrients. This allows it to indicate the amount of insulin the user needs and provide other nutritional advice. At the same time, it analyzes past health data to predict the user's future health risks. Based on this risk prediction, it suggests specific actions to maintain good health.

[0461] Provision of educational information

[0462] Furthermore, the server provides educational information to patients' families and caregivers, based on user permission. This information includes basic knowledge and management methods regarding diabetes. By providing educational information, the aim is to enable those around the user to gain a deeper understanding and provide appropriate support.

[0463] Specific example

[0464] When a user enters "I've been feeling stressed lately and can't sleep at night," the server analyzes this information, identifies the stressors, and suggests simple deep breathing exercises for relaxation. It also analyzes the carbohydrate content from a photo of the user's lunch and notifies the user of the optimal insulin dosage based on their daily activity level. This allows users to receive personalized health management support.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] Users input information about their emotional state and health, and the device receives this data. Input is done in natural language and can be via text or voice.

[0468] Step 2:

[0469] The terminal receives input from the user and sends it to the server in text format. If voice input is used, it is converted to text using speech recognition technology.

[0470] Step 3:

[0471] The server passes the received text data to a natural language processing engine to analyze the user's emotional state. Using an emotion analysis algorithm, it identifies the user's stressors and psychological state.

[0472] Step 4:

[0473] Based on the analysis results, the server generates stress management suggestions tailored to the transitional emotional state. It also refers to an internal knowledge base to provide appropriate lifestyle advice and psychological care suggestions.

[0474] Step 5:

[0475] The device receives suggestions generated from the server and displays the information to the user visually or audibly. The user can then review and implement the suggestions through the application.

[0476] Step 6:

[0477] Users take photos of their meals and upload them to their devices along with meal data. This data can include information such as ingredient names and quantities consumed.

[0478] Step 7:

[0479] The terminal sends meal images and related data to the server, which analyzes the meal content using image analysis techniques. It estimates the amount of nutrients and carbohydrates and calculates the required amount of insulin.

[0480] Step 8:

[0481] The server uses dietary data and historical health data to run a machine learning model and predict the user's future health risks. Based on the prediction results, it generates specific health management suggestions for the user.

[0482] Step 9:

[0483] The device receives prediction results and suggestions from the server and presents them to the user. The user can then refer to this information and use it for daily health management.

[0484] Step 10:

[0485] The server provides educational information to family members and caregivers based on the user's permission. The educational information is shared via the device in an appropriate format, making it accessible to recipients.

[0486] (Example 1)

[0487] Next, we will describe Example 1. 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."

[0488] In modern life, personalized health management and daily stress reduction are crucial issues. However, users often struggle to properly manage their emotions and health status, making it difficult to cope with stress and health risks in their daily lives. Furthermore, family members and caregivers around users often have limited access to accurate and useful health information, resulting in a lack of adequate support.

[0489] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0490] In this invention, the server includes means for analyzing the user's natural language input and identifying their emotional state, means for acquiring health data and estimating nutrient levels through image analysis, and means for predicting health risks and generating recommended actions using past health information. This enables the provision of personalized stress management suggestions and health advice.

[0491] "Natural language input" refers to text-based information written in a language that a user normally uses, and is an input method for a computer system to interpret it.

[0492] "Emotional state" refers to information that indicates the user's psychological state and emotional fluctuations, including emotions such as stress and happiness.

[0493] "Generation means" refers to a device or program that has the function of generating suggestions for the user, and in particular, one that uses an AI model to make stress management suggestions.

[0494] A "presentation method" is a means by which a system provides information or advice it has generated to a user, either visually or audibly.

[0495] "Image analysis" refers to the process of processing digital images, extracting and analyzing the information contained within them, and obtaining specific data such as nutrient content.

[0496] "Health risk prediction" is a process that evaluates a user's future health status and potential risks based on their past health information, and suggests actions to maintain their health over time.

[0497] "Recommended actions" are suggestions based on analysis results that users should take to improve or maintain their health.

[0498] "Educational information" refers to information provided to users and their supporters with the aim of improving specific health-related knowledge and skills.

[0499] The embodiment of the invention is a system realized through the cooperation of a user, a terminal, and a server, which enables user health management and emotion analysis. In this system, the terminal receives natural language input from the user and transmits this input data to the server. The server uses an advanced natural language processing engine to analyze the user's emotions and identify their stress levels and causes.

[0500] The server uses a generative AI model based on the results of emotion analysis to generate suggestions for stress management. These suggestions include specific examples such as relaxation techniques like deep breathing and lifestyle adjustments. These suggestions are presented to the user via a terminal, allowing them to receive advice tailored to their individual situation. Furthermore, image analysis software can be used to process photos of meals taken by the user, estimate the nutrient content, and advise on the appropriate amount of insulin.

[0501] Furthermore, the server has a data analysis function that uses past health data to predict future health risks and suggests specific actions to the user based on those predictions. This function is an important tool for users to continuously manage their health.

[0502] Regarding the provision of educational information, the server, with the user's permission, provides information on basic knowledge and management methods for diabetes to family members and caregivers, supporting the user's health management. This allows caregivers to deepen their understanding in order to provide appropriate support.

[0503] As a concrete example, consider a scenario where a user enters into their device, "I've been feeling stressed lately and can't sleep at night." When this information is sent to the server, the server analyzes the data, identifies the source of the stress, and suggests a simple deep breathing technique. Furthermore, it analyzes the carbohydrate content using an image of lunch and provides advice on adjusting insulin levels based on the day's activity level. This enables personalized health management support.

[0504] An example of a prompt message is as follows: "The user has entered information about their stress levels. Based on this data, please generate suggestions to help reduce stress."

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The user uses the device to input information about their health and emotions in natural language. For example, they might input text such as, "I've been feeling stressed lately." The user also inputs health-related data such as photos of their daily meals and blood sugar levels into the device. The device temporarily stores this data and prepares the input data for later processing.

[0508] Step 2:

[0509] The terminal sends text and image data entered by the user to the server. Encryption technology is used during this transmission process to ensure the secure transfer of input data. After transmission, the terminal remains in a waiting state until the data is processed on the server.

[0510] Step 3:

[0511] The server analyzes the received natural language data using a natural language processing engine. Specifically, it analyzes text data and performs calculations to identify the user's emotional state. The results of this analysis reveal the user's stress level and its contributing factors, and the output serves as foundational data for stress management suggestions.

[0512] Step 4:

[0513] The server processes received meal images using an image analysis algorithm. This image processing estimates the types and amounts of nutrients contained in the meal. The resulting nutritional information is used as foundational data for providing specific health advice based on the user's diet and for adjusting insulin dosages.

[0514] Step 5:

[0515] The server analyzes past user health data and performs data calculations to predict future health risks. It utilizes statistical models and machine learning algorithms to identify trends in health status. Based on the analysis results, specific recommendations for maintaining health are generated and provided as feedback to the user.

[0516] Step 6:

[0517] The server sends users stress management suggestions and health advice based on the analysis results. This delivery utilizes the device's display function, allowing users to see and act upon the information. For example, simple breathing exercises or dietary improvements may be displayed.

[0518] Step 7:

[0519] The server will provide health education information to family members and caregivers only with the user's permission. This information is intended to improve the knowledge of those around the user so that they can understand their health status and provide appropriate support.

[0520] (Application Example 1)

[0521] Next, we will explain Application Example 1. In the following explanation, 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."

[0522] In modern society, individual health management is a crucial issue, yet many people find it difficult to obtain appropriate advice. Furthermore, there is a need to accurately understand the impact of stress and emotional fluctuations on health and to propose concrete actions that are useful in daily life based on that understanding. However, conventional systems have struggled to comprehensively analyze a user's emotions and health status and provide individually optimized health management and product recommendations.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0524] In this invention, the server includes means for receiving natural language input from the user, analysis means for analyzing the input and identifying the user's emotional state, generation means for generating stress management suggestions based on the identified emotional state, analysis means for acquiring the user's dietary data and estimating nutrient amounts through image analysis, prediction means for predicting future health risks using past health data, and product recommendation means for recommending relevant products based on the emotional state and health data. As a result, the user can receive accurate advice tailored to their health condition and product recommendations to enrich their daily life.

[0525] "Means for accepting natural language input" refers to a function that provides an interface for receiving text data entered by the user and incorporating it into the system.

[0526] "Analysis means" refers to a function that analyzes user input data and processes it to identify the user's emotional state.

[0527] "Generative means" refers to a function that constructs methods for proposing stress management that is useful to the user, based on identified emotional states.

[0528] "Presentation means" refers to a medium or device for visually or audibly communicating the generated stress management suggestions to the user.

[0529] The "analysis means" refers to a function that processes the collected user meal data based on image analysis technology to estimate the types and amounts of nutrients.

[0530] A "predictive tool" is a function that analyzes past health data and processes it to estimate the user's future health risks.

[0531] "Product recommendation methods" refer to algorithms and technologies that take into account a user's emotional state and health data, and then suggest appropriate products to the user based on that information.

[0532] The system implementing this invention consists of a user, a terminal, and a server. The user accesses the system via a terminal such as a smartphone or tablet and inputs emotional and health information in natural language. The terminal plays the role of transmitting this information to the server.

[0533] The server plays a central role in processing the received information. First, it uses a natural language processing engine (e.g., Google Cloud Natural Language) to analyze the user's emotional state. This makes it possible to identify the causes and degree of stress. Next, it uses an AI model (e.g., TensorFlow) to generate stress management suggestions tailored to the emotional state. These suggestions include relaxation techniques and lifestyle improvements. In addition, it uses image analysis technology (e.g., OpenCV) to estimate nutrient content from images of meals taken by the user. Based on this information, nutritional guidance is provided that is tailored to the user's health condition.

[0534] Furthermore, the server analyzes past health data and predicts future health risks. Based on these predictions, it generates personalized action suggestions. The server also considers the user's emotional state and health data to execute a product recommendation algorithm that suggests appropriate products. This allows users to receive product information optimized for them.

[0535] For example, if a user enters "I've been feeling tired lately and can't concentrate on my work," the server analyzes this information and recommends relaxation products from the online store. It also analyzes the user's dietary data and provides nutritional advice to encourage a healthier lifestyle.

[0536] An example of a prompt would be the question, "Based on the emotional state and health data obtained from the user, suggest the most suitable health-related products for this user." This allows the system to generate the most effective suggestions for the user.

[0537] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0538] Step 1:

[0539] Users use their devices to input information about their emotions and health in natural language. This input is then sent to the server as text data by the device.

[0540] Step 2:

[0541] The server passes the received text data to a natural language processing engine, which analyzes the user's emotional state. Here, the input text data is analyzed, and identified emotional states and stressors are output. This process identifies the user's psychological burden and emotional tendencies.

[0542] Step 3:

[0543] Based on the analyzed emotional state, the server uses a generative AI model to generate stress management suggestions. In this step, the results of the emotional analysis are taken as input, and relaxation techniques and lifestyle improvement suggestions are output. The AI ​​model uses data on past effective stress reduction strategies to personalize the suggestions.

[0544] Step 4:

[0545] The user sends a photo of their meal to the server via their device. The device sends the captured image data to the server, and this data forms the basis for the subsequent analysis.

[0546] Step 5:

[0547] The server uses image analysis technology to convert images of meals provided by the user into nutritional information. The type and amount of nutrients are estimated from the input image data, and the results are output. This data is then used to analyze the components within the image and estimate the nutritional value.

[0548] Step 6:

[0549] The server predicts future health risks based on past health data. A history of health data is input, and a future health status prediction is output. This analysis then prompts the system to suggest preventative measures to help the user maintain their health.

[0550] Step 7:

[0551] The server uses product recommendation tools to suggest relevant products based on the user's emotional state and health data. In this step, emotional and health data are used as input to output a list of products best suited to the user. The product recommendation algorithm works by referring to past purchase history to present products that it deems appropriate.

[0552] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0553] To implement the present invention, a system having an emotion engine for inputting and analyzing information from the user is required. This system operates with a configuration including the user, a terminal, and a server, and in particular, by incorporating the emotion engine, it analyzes the user's emotional state in detail.

[0554] User-device interaction

[0555] Users can input information about their emotions and health status through the system using natural language. Input can be done via voice or text. Users can also take photos of their meals and upload them to the device as meal data. The device aggregates this information and sends it to a server for processing.

[0556] Utilizing the Emotion Engine

[0557] The server passes the information sent from the terminal to the emotion engine for analysis. This emotion engine accurately recognizes the user's emotions using voice analysis and facial expression analysis technologies. For example, it can read emotions from the user's voice tone and facial expressions, and based on this, identify the stress and psychological state the user is experiencing.

[0558] Data analysis and proposal generation

[0559] The server generates stress management suggestions based on the emotional state obtained through analysis. Here, it provides users with customized stress reduction measures and health maintenance behavior suggestions, taking into account past health data and emotional states.

[0560] The server also processes the user's meal data through image analysis to evaluate the amount of nutrients consumed. Using these results, it can suggest appropriate insulin dosages and nutritional advice. In addition, it analyzes past health data to predict future health risks and provides the user with a concrete action plan.

[0561] Providing educational information to family members and supporters

[0562] The server also provides educational information to family members and caregivers, based on the user's permission. This information includes knowledge to promote a basic understanding of diabetes, creating an environment where those around the user can provide appropriate support.

[0563] Specific example

[0564] Specifically, if a user voice-inputs, "I've been feeling irritable lately and can't sleep at night," the emotion engine identifies the stress level from the tone of their voice. Based on this, the server suggests meditation and breathing exercises. It also takes a photo of the user's lunch, analyzes the nutrients consumed, calculates the appropriate insulin dosage, and notifies the user. Through these processes, users can efficiently manage their own health while receiving psychological support.

[0565] The following describes the processing flow.

[0566] Step 1:

[0567] Users input information about their emotions and health status in natural language and provide it as voice or text data through their device. Users can also upload photos of their meals to their device.

[0568] Step 2:

[0569] The terminal receives voice data from the user and converts it into text data using speech recognition technology as needed. The input data is then sent to the server.

[0570] Step 3:

[0571] The server receives text data sent from the terminal and image data of the user's meal.

[0572] Step 4:

[0573] The server uses an emotion engine to analyze the user's emotions from text or audio. The emotion engine recognizes emotions and identifies emotional states using speech tone analysis and, if possible, facial expression data.

[0574] Step 5:

[0575] The server generates specific suggestions for stress management based on the user's emotional state. For example, it might suggest breathing exercises to reduce stress or daily relaxation techniques.

[0576] Step 6:

[0577] The server processes the user's meal images using image analysis technology to analyze the nutrients in the food. It calculates the amount of nutrients and then calculates the required amount of insulin.

[0578] Step 7:

[0579] The server uses past health data to predict future health risks. Based on these predictions, it provides users with suggestions for maintaining their health.

[0580] Step 8:

[0581] The terminal displays stress management suggestions, nutritional advice, and health risk predictions received from the server to the user.

[0582] Step 9:

[0583] The server sends educational information to family members and caregivers based on the user's consent. This enables caregivers to properly support the user's health management.

[0584] (Example 2)

[0585] Next, we will describe Example 2. 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."

[0586] In modern society, there is a need to quickly understand an individual's stress level and health status and provide appropriate countermeasures. However, conventional systems struggle to accurately analyze a user's emotional state and provide appropriate suggestions tailored to their individual health condition. Furthermore, the provision of health information to family members and caregivers is insufficient, limiting the support users receive. To improve this situation, technology is needed that comprehensively analyzes a user's emotional and health status and enables reliable health management and support based on that analysis.

[0587] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0588] In this invention, the server includes means for inputting information from the user in the form of voice or text, means for analyzing the information using speech recognition and natural language processing technologies to identify the user's emotional state, and means for inputting image data of the meal contents via a terminal and estimating the amount of nutrients using image analysis technology. This enables accurate analysis of the user's emotional state and health state, and allows for the provision of appropriate stress management suggestions and nutritional guidance based on the results. Furthermore, by providing health-related information to family members and caregivers, the support system surrounding the user can be strengthened.

[0589] "Speech recognition" is a technology that analyzes a user's voice data and converts it into text data.

[0590] "Natural language processing" is a technology that analyzes natural language data input by users to understand its meaning and context.

[0591] "Emotional state" refers to the user's psychological state and stress level, and is identified through analysis.

[0592] "Image analysis" is a technique that analyzes captured image data and extracts information from the image.

[0593] "Nutrient content" refers to the types and amounts of nutrients contained in the food consumed by the user.

[0594] "Stress management" refers to strategies aimed at alleviating users' mental stress and promoting psychological stability.

[0595] "Health management" refers to a series of actions and guidance taken to maintain and improve the user's health status.

[0596] A "supporter" is a person or organization that plays a role in assisting users with their health management and provides appropriate information and support.

[0597] To implement this invention, a system consisting of a user, a terminal, and a server is used. The user inputs their emotions and health status in voice or text format, and also uploads photos of meals to the terminal. The terminal converts the input voice into text using speech recognition software and sends the text data and image data to the server. General speech recognition and image processing technologies are used in this process.

[0598] The server analyzes received text and audio data using natural language processing technology and identifies the user's emotional state using an emotion engine. For example, it can understand a user's psychological state from their tone of voice and word choice. Additionally, image data is analyzed using image analysis algorithms to evaluate the nutrients contained in their meals. This allows the system to determine the appropriate insulin dosage and provide nutritional guidance based on the user's diet.

[0599] Based on the analysis results, the server provides users with suggestions for stress reduction and health management, including meditation and breathing exercises. Furthermore, with the user's permission, it provides health-related educational information to family members and caregivers.

[0600] For example, if a user prompts them with a message like, "I've been feeling irritable lately. I had a healthy lunch today," the server will use an emotion engine to assess the user's stress level and suggest appropriate relaxation methods. It can also analyze a photo of the lunch and provide nutritional advice based on the balance of the food.

[0601] Thus, the present invention can provide users with comprehensive health support through a detailed analysis of their emotional and physical states.

[0602] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0603] Step 1:

[0604] Users input information about their emotions and health status via voice or text, and upload photos of their meals to the device. The input information is converted into text data by voice recognition software and aggregated on the device. In this process, voice data is converted into text data, and image data is formatted and prepared.

[0605] Step 2:

[0606] The terminal sends aggregated data from the user to the server. Text data and image data are separated and transferred to the server. The input received by the server consists of text information about the user's emotions and images of the food they ate.

[0607] Step 3:

[0608] The server analyzes the received text data using a natural language processing engine to determine the emotional tone and content. This analysis identifies the user's emotional state. The analyzed emotional state is then output. During this process, a generative AI model can be used to capture subtle emotional nuances.

[0609] Step 4:

[0610] The server evaluates stress levels and psychological states based on emotional states obtained from the emotion engine, and generates stress relief measures tailored to the user. The generated suggestions are output in text format and used for the user's stress management.

[0611] Step 5:

[0612] The server applies an image analysis algorithm to analyze image data of meals and calculate the amount of nutrients consumed. The analysis results include the type and amount of each nutrient, and nutritional advice tailored to the user's health condition is generated.

[0613] Step 6:

[0614] The server combines emotion analysis results and nutritional analysis results to customize optimal health suggestions for the user. This includes suggestions for a balanced diet, appropriate exercise, and relaxation methods. The customized suggestions are output and sent to the terminal.

[0615] Step 7:

[0616] The device notifies the user of suggestions received from the server. Based on the notification, the user can manage their emotions and health and try the suggested methods.

[0617] This series of steps allows users to gain a detailed understanding of their health status in their daily lives and receive appropriate care.

[0618] (Application Example 2)

[0619] Next, we will explain application example 2. In the following explanation, 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."

[0620] In modern society, many people are exposed to stress, making health management crucial. Furthermore, consumers face the challenge of not being able to obtain health- and emotionally balanced information when shopping in stores, making it difficult to select appropriate products. In this context, there is a need for methods to improve the in-store shopping experience while considering health and emotional states.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0622] In this invention, the server includes processing means for identifying the user's emotional state, analysis means for predicting health risks, and a function for recommending product information in physical stores. This enables users to make appropriate product choices based on their health and emotions in a real-world shopping environment.

[0623] "Natural language input" refers to users providing information using voice or text in the form of language that humans normally use.

[0624] "Processing methods for identifying emotional states" refer to technologies that analyze voice and text data obtained from users to determine their psychological state.

[0625] A "stress management suggestion generation mechanism" is a system that automatically devises methods and actions to reduce stress based on the user's emotional state.

[0626] "Display function" refers to technology that presents generated suggestions and analysis results to the user visually or audibly.

[0627] The "processing method for estimating nutrient content through image analysis" is a technology that analyzes images of meals taken by the user to estimate the types and amounts of nutrients contained within.

[0628] "Analysis methods" refer to methods for evaluating future health risks using a user's past health data.

[0629] The "function to recommend product information in a real-world shopping environment" is a technology that suggests the most suitable products to users when they are choosing products in an actual store, based on their health condition and emotions.

[0630] This invention requires a system in which a user, a terminal, and a server work together. The system receives natural language data (voice or text) input by the user at the terminal and sends it to the server for analysis. The server uses emotion analysis software (e.g., Affectiva SDK) to identify the user's emotional state. Image data captured by the user is also sent from the terminal, and the server uses image analysis technology to estimate nutrient levels. Furthermore, the server refers to past health data to analyze future health risks.

[0631] When users select products in physical stores, smart glasses and smartphones (e.g., Google Glass, iPhone) are utilized. A server supports the shopping experience by recommending the most suitable products, taking into account the user's health and emotional state. In this process, health risk presentations based on past health data and real-time emotional and health management information from the physical store are integrated and utilized.

[0632] As a concrete example, if a user in a physical store says, "I've been feeling tired lately, so I'd like a healthy snack," through smart glasses, the system will perform sentiment analysis and recommend products that suit the user's state. For instance, if the user has a history of limiting sugar intake, it will suggest low-sugar snacks. In this way, the system helps users make healthy and satisfying product choices.

[0633] An example of an input prompt statement for a generative AI model is as follows:

[0634] "A user says in a store, 'I'm tired and want something sweet.' This user has a history of limiting sugar intake. Please design a system that suggests healthy sweets to them."

[0635] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0636] Step 1:

[0637] The user provides natural language voice input through their device. The input voice data is collected using a smartphone or smart glasses and converted into text. In this process, a speech recognition API is used to convert the voice data into text data. The input is natural speech such as "I've been tired lately and want to eat something sweet."

[0638] Step 2:

[0639] The terminal sends text data from the user to a server for sentiment analysis. The server uses sentiment analysis software to analyze the voice or text data and identify the user's emotional state. For example, it might determine that the user is feeling stressed. The input is text data, and the output is emotional state data.

[0640] Step 3:

[0641] A user takes a photo of a product, which is then sent to a server via their device. The server uses image analysis technology to estimate detailed product information, including the types and amounts of nutrients it contains, from this photo data. Image data is received as input, and nutritional information data is obtained as output. Specifically, a machine learning algorithm is used to recognize the product label from the image, and then the nutritional information is retrieved by searching a database based on that information.

[0642] Step 4:

[0643] The server compares the user's emotional state information with past health data to analyze future health risks. For example, it assesses the risk of sugar intake based on past data. In this process, emotional state and health data are used as input, and risk assessment data is generated as output.

[0644] Step 5:

[0645] The server recommends the most suitable products to the user based on emotional state data, health risk data, and nutritional information data. This recommendation supports in-store purchases. Specifically, it selects the product best suited to the user's preferences and health condition from the product database and sends that information to the terminal. Recommended product information is generated as output.

[0646] Step 6:

[0647] The terminal displays product recommendation information received from the server to the user. Users can receive information on suitable products through smart glasses or smartphones. The displayed information includes product name, nutrients, and health effects. Recommended product information is the input, and visual information presented to the user is generated as the output.

[0648] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0649] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0650] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0651] [Fourth Embodiment]

[0652] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0653] As shown in Figure 7, the 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.

[0654] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0655] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0656] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0657] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0658] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0659] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0660] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0661] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0662] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0663] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0664] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] To implement the present invention, a system comprising multiple elements is required. This system operates with a configuration including a user, a terminal, and a server.

[0666] User-device interaction

[0667] Users utilize the system via their devices for daily health management. Users can input information about their emotions and health status in natural language. They can also take photos of their meals and input health data such as blood sugar levels into the device. The device collects this data and transmits it to the server.

[0668] Server-based data analysis and proposal generation

[0669] The server receives input data sent from the terminal and analyzes the user's emotions using a natural language processing engine. This analysis identifies the user's stress level and specific stressors. Furthermore, the server utilizes an AI model to generate stress management suggestions that can help reduce stress. These suggestions may include relaxation techniques and lifestyle improvements.

[0670] The server also uses image analysis technology to process the user's dietary data and estimate the amount of nutrients. This allows it to indicate the amount of insulin the user needs and provide other nutritional advice. At the same time, it analyzes past health data to predict the user's future health risks. Based on this risk prediction, it suggests specific actions to maintain good health.

[0671] Provision of educational information

[0672] Furthermore, the server provides educational information to patients' families and caregivers, based on user permission. This information includes basic knowledge and management methods regarding diabetes. By providing educational information, the aim is to enable those around the user to gain a deeper understanding and provide appropriate support.

[0673] Specific example

[0674] When a user enters "I've been feeling stressed lately and can't sleep at night," the server analyzes this information, identifies the stressors, and suggests simple deep breathing exercises for relaxation. It also analyzes the carbohydrate content from a photo of the user's lunch and notifies the user of the optimal insulin dosage based on their daily activity level. This allows users to receive personalized health management support.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] Users input information about their emotional state and health, and the device receives this data. Input is done in natural language and can be via text or voice.

[0678] Step 2:

[0679] The terminal receives input from the user and sends it to the server in text format. If voice input is used, it is converted to text using speech recognition technology.

[0680] Step 3:

[0681] The server passes the received text data to a natural language processing engine to analyze the user's emotional state. Using an emotion analysis algorithm, it identifies the user's stressors and psychological state.

[0682] Step 4:

[0683] Based on the analysis results, the server generates stress management suggestions tailored to the transitional emotional state. It also refers to an internal knowledge base to provide appropriate lifestyle advice and psychological care suggestions.

[0684] Step 5:

[0685] The device receives suggestions generated from the server and displays the information to the user visually or audibly. The user can then review and implement the suggestions through the application.

[0686] Step 6:

[0687] Users take photos of their meals and upload them to their devices along with meal data. This data can include information such as ingredient names and quantities consumed.

[0688] Step 7:

[0689] The terminal sends meal images and related data to the server, which analyzes the meal content using image analysis techniques. It estimates the amount of nutrients and carbohydrates and calculates the required amount of insulin.

[0690] Step 8:

[0691] The server uses dietary data and historical health data to run a machine learning model and predict the user's future health risks. Based on the prediction results, it generates specific health management suggestions for the user.

[0692] Step 9:

[0693] The device receives prediction results and suggestions from the server and presents them to the user. The user can then refer to this information and use it for daily health management.

[0694] Step 10:

[0695] The server provides educational information to family members and caregivers based on the user's permission. The educational information is shared via the device in an appropriate format, making it accessible to recipients.

[0696] (Example 1)

[0697] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In modern life, personalized health management and daily stress reduction are crucial issues. However, users often struggle to properly manage their emotions and health status, making it difficult to cope with stress and health risks in their daily lives. Furthermore, family members and caregivers around users often have limited access to accurate and useful health information, resulting in a lack of adequate support.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0700] In this invention, the server includes means for analyzing the user's natural language input and identifying their emotional state, means for acquiring health data and estimating nutrient levels through image analysis, and means for predicting health risks and generating recommended actions using past health information. This enables the provision of personalized stress management suggestions and health advice.

[0701] "Natural language input" refers to text-based information written in a language that a user normally uses, and is an input method for a computer system to interpret it.

[0702] "Emotional state" refers to information that indicates the user's psychological state and emotional fluctuations, including emotions such as stress and happiness.

[0703] "Generation means" refers to a device or program that has the function of generating suggestions for the user, and in particular, one that uses an AI model to make stress management suggestions.

[0704] A "presentation method" is a means by which a system provides information or advice it has generated to a user, either visually or audibly.

[0705] "Image analysis" refers to the process of processing digital images, extracting and analyzing the information contained within them, and obtaining specific data such as nutrient content.

[0706] "Health risk prediction" is a process that evaluates a user's future health status and potential risks based on their past health information, and suggests actions to maintain their health over time.

[0707] "Recommended actions" are suggestions based on analysis results that users should take to improve or maintain their health.

[0708] "Educational information" refers to information provided to users and their supporters with the aim of improving specific health-related knowledge and skills.

[0709] The embodiment of the invention is a system realized through the cooperation of a user, a terminal, and a server, which enables user health management and emotion analysis. In this system, the terminal receives natural language input from the user and transmits this input data to the server. The server uses an advanced natural language processing engine to analyze the user's emotions and identify their stress levels and causes.

[0710] The server uses a generative AI model based on the results of emotion analysis to generate suggestions for stress management. These suggestions include specific examples such as relaxation techniques like deep breathing and lifestyle adjustments. These suggestions are presented to the user via a terminal, allowing them to receive advice tailored to their individual situation. Furthermore, image analysis software can be used to process photos of meals taken by the user, estimate the nutrient content, and advise on the appropriate amount of insulin.

[0711] Furthermore, the server has a data analysis function that uses past health data to predict future health risks and suggests specific actions to the user based on those predictions. This function is an important tool for users to continuously manage their health.

[0712] Regarding the provision of educational information, the server, with the user's permission, provides information on basic knowledge and management methods for diabetes to family members and caregivers, supporting the user's health management. This allows caregivers to deepen their understanding in order to provide appropriate support.

[0713] As a concrete example, consider a scenario where a user enters into their device, "I've been feeling stressed lately and can't sleep at night." When this information is sent to the server, the server analyzes the data, identifies the source of the stress, and suggests a simple deep breathing technique. Furthermore, it analyzes the carbohydrate content using an image of lunch and provides advice on adjusting insulin levels based on the day's activity level. This enables personalized health management support.

[0714] An example of a prompt message is as follows: "The user has entered information about their stress levels. Based on this data, please generate suggestions to help reduce stress."

[0715] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0716] Step 1:

[0717] The user uses the device to input information about their health and emotions in natural language. For example, they might input text such as, "I've been feeling stressed lately." The user also inputs health-related data such as photos of their daily meals and blood sugar levels into the device. The device temporarily stores this data and prepares the input data for later processing.

[0718] Step 2:

[0719] The terminal sends text and image data entered by the user to the server. Encryption technology is used during this transmission process to ensure the secure transfer of input data. After transmission, the terminal remains in a waiting state until the data is processed on the server.

[0720] Step 3:

[0721] The server analyzes the received natural language data using a natural language processing engine. Specifically, it analyzes text data and performs calculations to identify the user's emotional state. The results of this analysis reveal the user's stress level and its contributing factors, and the output serves as foundational data for stress management suggestions.

[0722] Step 4:

[0723] The server processes received meal images using an image analysis algorithm. This image processing estimates the types and amounts of nutrients contained in the meal. The resulting nutritional information is used as foundational data for providing specific health advice based on the user's diet and for adjusting insulin dosages.

[0724] Step 5:

[0725] The server analyzes past user health data and performs data calculations to predict future health risks. It utilizes statistical models and machine learning algorithms to identify trends in health status. Based on the analysis results, specific recommendations for maintaining health are generated and provided as feedback to the user.

[0726] Step 6:

[0727] The server sends users stress management suggestions and health advice based on the analysis results. This delivery utilizes the device's display function, allowing users to see and act upon the information. For example, simple breathing exercises or dietary improvements may be displayed.

[0728] Step 7:

[0729] The server will provide health education information to family members and caregivers only with the user's permission. This information is intended to improve the knowledge of those around the user so that they can understand their health status and provide appropriate support.

[0730] (Application Example 1)

[0731] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0732] In modern society, individual health management is a crucial issue, yet many people find it difficult to obtain appropriate advice. Furthermore, there is a need to accurately understand the impact of stress and emotional fluctuations on health and to propose concrete actions that are useful in daily life based on that understanding. However, conventional systems have struggled to comprehensively analyze a user's emotions and health status and provide individually optimized health management and product recommendations.

[0733] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0734] In this invention, the server includes means for receiving natural language input from the user, analysis means for analyzing the input and identifying the user's emotional state, generation means for generating stress management suggestions based on the identified emotional state, analysis means for acquiring the user's dietary data and estimating nutrient amounts through image analysis, prediction means for predicting future health risks using past health data, and product recommendation means for recommending relevant products based on the emotional state and health data. As a result, the user can receive accurate advice tailored to their health condition and product recommendations to enrich their daily life.

[0735] "Means for accepting natural language input" refers to a function that provides an interface for receiving text data entered by the user and incorporating it into the system.

[0736] "Analysis means" refers to a function that analyzes user input data and processes it to identify the user's emotional state.

[0737] "Generative means" refers to a function that constructs methods for proposing stress management that is useful to the user, based on identified emotional states.

[0738] "Presentation means" refers to a medium or device for visually or audibly communicating the generated stress management suggestions to the user.

[0739] The "analysis means" refers to a function that processes the collected user meal data based on image analysis technology to estimate the types and amounts of nutrients.

[0740] A "predictive tool" is a function that analyzes past health data and processes it to estimate the user's future health risks.

[0741] "Product recommendation methods" refer to algorithms and technologies that take into account a user's emotional state and health data, and then suggest appropriate products to the user based on that information.

[0742] The system implementing this invention consists of a user, a terminal, and a server. The user accesses the system via a terminal such as a smartphone or tablet and inputs emotional and health information in natural language. The terminal plays the role of transmitting this information to the server.

[0743] The server plays a central role in processing the received information. First, it uses a natural language processing engine (e.g., Google Cloud Natural Language) to analyze the user's emotional state. This makes it possible to identify the causes and degree of stress. Next, it uses an AI model (e.g., TensorFlow) to generate stress management suggestions tailored to the emotional state. These suggestions include relaxation techniques and lifestyle improvements. In addition, it uses image analysis technology (e.g., OpenCV) to estimate nutrient content from images of meals taken by the user. Based on this information, nutritional guidance is provided that is tailored to the user's health condition.

[0744] Furthermore, the server analyzes past health data and predicts future health risks. Based on these predictions, it generates personalized action suggestions. The server also considers the user's emotional state and health data to execute a product recommendation algorithm that suggests appropriate products. This allows users to receive product information optimized for them.

[0745] For example, if a user enters "I've been feeling tired lately and can't concentrate on my work," the server analyzes this information and recommends relaxation products from the online store. It also analyzes the user's dietary data and provides nutritional advice to encourage a healthier lifestyle.

[0746] An example of a prompt would be the question, "Based on the emotional state and health data obtained from the user, suggest the most suitable health-related products for this user." This allows the system to generate the most effective suggestions for the user.

[0747] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0748] Step 1:

[0749] Users use their devices to input information about their emotions and health in natural language. This input is then sent to the server as text data by the device.

[0750] Step 2:

[0751] The server passes the received text data to a natural language processing engine, which analyzes the user's emotional state. Here, the input text data is analyzed, and identified emotional states and stressors are output. This process identifies the user's psychological burden and emotional tendencies.

[0752] Step 3:

[0753] Based on the analyzed emotional state, the server uses a generative AI model to generate stress management suggestions. In this step, the results of the emotional analysis are taken as input, and relaxation techniques and lifestyle improvement suggestions are output. The AI ​​model uses data on past effective stress reduction strategies to personalize the suggestions.

[0754] Step 4:

[0755] The user sends a photo of their meal to the server via their device. The device sends the captured image data to the server, and this data forms the basis for the subsequent analysis.

[0756] Step 5:

[0757] The server uses image analysis technology to convert images of meals provided by the user into nutritional information. The type and amount of nutrients are estimated from the input image data, and the results are output. This data is then used to analyze the components within the image and estimate the nutritional value.

[0758] Step 6:

[0759] The server predicts future health risks based on past health data. A history of health data is input, and a future health status prediction is output. This analysis then prompts the system to suggest preventative measures to help the user maintain their health.

[0760] Step 7:

[0761] The server uses product recommendation tools to suggest relevant products based on the user's emotional state and health data. In this step, emotional and health data are used as input to output a list of products best suited to the user. The product recommendation algorithm works by referring to past purchase history to present products that it deems appropriate.

[0762] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0763] To implement the present invention, a system having an emotion engine for inputting and analyzing information from the user is required. This system operates with a configuration including the user, a terminal, and a server, and in particular, by incorporating the emotion engine, it analyzes the user's emotional state in detail.

[0764] User-device interaction

[0765] Users can input information about their emotions and health status through the system using natural language. Input can be done via voice or text. Users can also take photos of their meals and upload them to the device as meal data. The device aggregates this information and sends it to a server for processing.

[0766] Utilizing the Emotion Engine

[0767] The server passes the information sent from the terminal to the emotion engine for analysis. This emotion engine accurately recognizes the user's emotions using voice analysis and facial expression analysis technologies. For example, it can read emotions from the user's voice tone and facial expressions, and based on this, identify the stress and psychological state the user is experiencing.

[0768] Data analysis and proposal generation

[0769] The server generates stress management suggestions based on the emotional state obtained through analysis. Here, it provides users with customized stress reduction measures and health maintenance behavior suggestions, taking into account past health data and emotional states.

[0770] The server also processes the user's meal data through image analysis to evaluate the amount of nutrients consumed. Using these results, it can suggest appropriate insulin dosages and nutritional advice. In addition, it analyzes past health data to predict future health risks and provides the user with a concrete action plan.

[0771] Providing educational information to family members and supporters

[0772] The server also provides educational information to family members and caregivers, based on the user's permission. This information includes knowledge to promote a basic understanding of diabetes, creating an environment where those around the user can provide appropriate support.

[0773] Specific example

[0774] Specifically, if a user voice-inputs, "I've been feeling irritable lately and can't sleep at night," the emotion engine identifies the stress level from the tone of their voice. Based on this, the server suggests meditation and breathing exercises. It also takes a photo of the user's lunch, analyzes the nutrients consumed, calculates the appropriate insulin dosage, and notifies the user. Through these processes, users can efficiently manage their own health while receiving psychological support.

[0775] The following describes the processing flow.

[0776] Step 1:

[0777] Users input information about their emotions and health status in natural language and provide it as voice or text data through their device. Users can also upload photos of their meals to their device.

[0778] Step 2:

[0779] The terminal receives voice data from the user and converts it into text data using speech recognition technology as needed. The input data is then sent to the server.

[0780] Step 3:

[0781] The server receives text data sent from the terminal and image data of the user's meal.

[0782] Step 4:

[0783] The server uses an emotion engine to analyze the user's emotions from text or audio. The emotion engine recognizes emotions and identifies emotional states using speech tone analysis and, if possible, facial expression data.

[0784] Step 5:

[0785] The server generates specific suggestions for stress management based on the user's emotional state. For example, it might suggest breathing exercises to reduce stress or daily relaxation techniques.

[0786] Step 6:

[0787] The server processes the user's meal images using image analysis technology to analyze the nutrients in the food. It calculates the amount of nutrients and then calculates the required amount of insulin.

[0788] Step 7:

[0789] The server uses past health data to predict future health risks. Based on these predictions, it provides users with suggestions for maintaining their health.

[0790] Step 8:

[0791] The terminal displays stress management suggestions, nutritional advice, and health risk predictions received from the server to the user.

[0792] Step 9:

[0793] The server sends educational information to family members and caregivers based on the user's consent. This enables caregivers to properly support the user's health management.

[0794] (Example 2)

[0795] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0796] In modern society, there is a need to quickly understand an individual's stress level and health status and provide appropriate countermeasures. However, conventional systems struggle to accurately analyze a user's emotional state and provide appropriate suggestions tailored to their individual health condition. Furthermore, the provision of health information to family members and caregivers is insufficient, limiting the support users receive. To improve this situation, technology is needed that comprehensively analyzes a user's emotional and health status and enables reliable health management and support based on that analysis.

[0797] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0798] In this invention, the server includes means for inputting information from the user in the form of voice or text, means for analyzing the information using speech recognition and natural language processing technologies to identify the user's emotional state, and means for inputting image data of the meal contents via a terminal and estimating the amount of nutrients using image analysis technology. This enables accurate analysis of the user's emotional state and health state, and allows for the provision of appropriate stress management suggestions and nutritional guidance based on the results. Furthermore, by providing health-related information to family members and caregivers, the support system surrounding the user can be strengthened.

[0799] "Speech recognition" is a technology that analyzes a user's voice data and converts it into text data.

[0800] "Natural language processing" is a technology that analyzes natural language data input by users to understand its meaning and context.

[0801] "Emotional state" refers to the user's psychological state and stress level, and is identified through analysis.

[0802] "Image analysis" is a technique that analyzes captured image data and extracts information from the image.

[0803] "Nutrient content" refers to the types and amounts of nutrients contained in the food consumed by the user.

[0804] "Stress management" refers to strategies aimed at alleviating users' mental stress and promoting psychological stability.

[0805] "Health management" refers to a series of actions and guidance taken to maintain and improve the user's health status.

[0806] A "supporter" is a person or organization that plays a role in assisting users with their health management and provides appropriate information and support.

[0807] To implement this invention, a system consisting of a user, a terminal, and a server is used. The user inputs their emotions and health status in voice or text format, and also uploads photos of meals to the terminal. The terminal converts the input voice into text using speech recognition software and sends the text data and image data to the server. General speech recognition and image processing technologies are used in this process.

[0808] The server analyzes received text and audio data using natural language processing technology and identifies the user's emotional state using an emotion engine. For example, it can understand a user's psychological state from their tone of voice and word choice. Additionally, image data is analyzed using image analysis algorithms to evaluate the nutrients contained in their meals. This allows the system to determine the appropriate insulin dosage and provide nutritional guidance based on the user's diet.

[0809] Based on the analysis results, the server provides users with suggestions for stress reduction and health management, including meditation and breathing exercises. Furthermore, with the user's permission, it provides health-related educational information to family members and caregivers.

[0810] For example, if a user prompts them with a message like, "I've been feeling irritable lately. I had a healthy lunch today," the server will use an emotion engine to assess the user's stress level and suggest appropriate relaxation methods. It can also analyze a photo of the lunch and provide nutritional advice based on the balance of the food.

[0811] Thus, the present invention can provide users with comprehensive health support through a detailed analysis of their emotional and physical states.

[0812] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0813] Step 1:

[0814] Users input information about their emotions and health status via voice or text, and upload photos of their meals to the device. The input information is converted into text data by voice recognition software and aggregated on the device. In this process, voice data is converted into text data, and image data is formatted and prepared.

[0815] Step 2:

[0816] The terminal sends aggregated data from the user to the server. Text data and image data are separated and transferred to the server. The input received by the server consists of text information about the user's emotions and images of the food they ate.

[0817] Step 3:

[0818] The server analyzes the received text data using a natural language processing engine to determine the emotional tone and content. This analysis identifies the user's emotional state. The analyzed emotional state is then output. During this process, a generative AI model can be used to capture subtle emotional nuances.

[0819] Step 4:

[0820] The server evaluates stress levels and psychological states based on emotional states obtained from the emotion engine, and generates stress relief measures tailored to the user. The generated suggestions are output in text format and used for the user's stress management.

[0821] Step 5:

[0822] The server applies an image analysis algorithm to analyze image data of meals and calculate the amount of nutrients consumed. The analysis results include the type and amount of each nutrient, and nutritional advice tailored to the user's health condition is generated.

[0823] Step 6:

[0824] The server combines emotion analysis results and nutritional analysis results to customize optimal health suggestions for the user. This includes suggestions for a balanced diet, appropriate exercise, and relaxation methods. The customized suggestions are output and sent to the terminal.

[0825] Step 7:

[0826] The device notifies the user of suggestions received from the server. Based on the notification, the user can manage their emotions and health and try the suggested methods.

[0827] This series of steps allows users to gain a detailed understanding of their health status in their daily lives and receive appropriate care.

[0828] (Application Example 2)

[0829] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0830] In modern society, many people are exposed to stress, making health management crucial. Furthermore, consumers face the challenge of not being able to obtain health- and emotionally balanced information when shopping in stores, making it difficult to select appropriate products. In this context, there is a need for methods to improve the in-store shopping experience while considering health and emotional states.

[0831] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0832] In this invention, the server includes processing means for identifying the user's emotional state, analysis means for predicting health risks, and a function for recommending product information in physical stores. This enables users to make appropriate product choices based on their health and emotions in a real-world shopping environment.

[0833] "Natural language input" refers to users providing information using voice or text in the form of language that humans normally use.

[0834] "Processing methods for identifying emotional states" refer to technologies that analyze voice and text data obtained from users to determine their psychological state.

[0835] A "stress management suggestion generation mechanism" is a system that automatically devises methods and actions to reduce stress based on the user's emotional state.

[0836] "Display function" refers to technology that presents generated suggestions and analysis results to the user visually or audibly.

[0837] The "processing method for estimating nutrient content through image analysis" is a technology that analyzes images of meals taken by the user to estimate the types and amounts of nutrients contained within.

[0838] "Analysis methods" refer to methods for evaluating future health risks using a user's past health data.

[0839] The "function to recommend product information in a real-world shopping environment" is a technology that suggests the most suitable products to users when they are choosing products in an actual store, based on their health condition and emotions.

[0840] This invention requires a system in which a user, a terminal, and a server work together. The system receives natural language data (voice or text) input by the user at the terminal and sends it to the server for analysis. The server uses emotion analysis software (e.g., Affectiva SDK) to identify the user's emotional state. Image data captured by the user is also sent from the terminal, and the server uses image analysis technology to estimate nutrient levels. Furthermore, the server refers to past health data to analyze future health risks.

[0841] When users select products in physical stores, smart glasses and smartphones (e.g., Google Glass, iPhone) are utilized. A server supports the shopping experience by recommending the most suitable products, taking into account the user's health and emotional state. In this process, health risk presentations based on past health data and real-time emotional and health management information from the physical store are integrated and utilized.

[0842] As a concrete example, if a user in a physical store says, "I've been feeling tired lately, so I'd like a healthy snack," through smart glasses, the system will perform sentiment analysis and recommend products that suit the user's state. For instance, if the user has a history of limiting sugar intake, it will suggest low-sugar snacks. In this way, the system helps users make healthy and satisfying product choices.

[0843] An example of an input prompt statement for a generative AI model is as follows:

[0844] "A user says in a store, 'I'm tired and want something sweet.' This user has a history of limiting sugar intake. Please design a system that suggests healthy sweets to them."

[0845] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0846] Step 1:

[0847] The user provides natural language voice input through their device. The input voice data is collected using a smartphone or smart glasses and converted into text. In this process, a speech recognition API is used to convert the voice data into text data. The input is natural speech such as "I've been tired lately and want to eat something sweet."

[0848] Step 2:

[0849] The terminal sends text data from the user to a server for sentiment analysis. The server uses sentiment analysis software to analyze the voice or text data and identify the user's emotional state. For example, it might determine that the user is feeling stressed. The input is text data, and the output is emotional state data.

[0850] Step 3:

[0851] A user takes a photo of a product, which is then sent to a server via their device. The server uses image analysis technology to estimate detailed product information, including the types and amounts of nutrients it contains, from this photo data. Image data is received as input, and nutritional information data is obtained as output. Specifically, a machine learning algorithm is used to recognize the product label from the image, and then the nutritional information is retrieved by searching a database based on that information.

[0852] Step 4:

[0853] The server compares the user's emotional state information with past health data to analyze future health risks. For example, it assesses the risk of sugar intake based on past data. In this process, emotional state and health data are used as input, and risk assessment data is generated as output.

[0854] Step 5:

[0855] The server recommends the most suitable products to the user based on emotional state data, health risk data, and nutritional information data. This recommendation supports in-store purchases. Specifically, it selects the product best suited to the user's preferences and health condition from the product database and sends that information to the terminal. Recommended product information is generated as output.

[0856] Step 6:

[0857] The terminal displays product recommendation information received from the server to the user. Users can receive information on suitable products through smart glasses or smartphones. The displayed information includes product name, nutrients, and health effects. Recommended product information is the input, and visual information presented to the user is generated as the output.

[0858] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0859] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0860] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0861] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0862] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0863] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0864] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0865] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0866] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0867] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0868] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0869] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0870] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0871] 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.

[0872] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0873] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0874] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0875] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0876] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0877] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0878] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0879] The following is further disclosed regarding the embodiments described above.

[0880] (Claim 1)

[0881] A means of receiving natural language input from users,

[0882] An analysis means for analyzing the aforementioned input and identifying the user's emotional state,

[0883] A generation means for generating stress management suggestions based on identified emotional states,

[0884] A means for presenting the aforementioned proposal to the user,

[0885] An analytical means that acquires user meal data and estimates nutrient amounts through image analysis,

[0886] A predictive method that uses past health data to predict future health risks,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, wherein the prediction means generates recommended actions for future health risks based on the health data.

[0890] (Claim 3)

[0891] The system according to claim 1, further comprising means for providing health-related educational information to the user's family or caregivers.

[0892] "Example 1"

[0893] (Claim 1)

[0894] A means of receiving natural language input from users,

[0895] An analysis means for analyzing the aforementioned input and identifying the user's emotional state,

[0896] A generation means for generating stress management suggestions based on identified emotional states,

[0897] A means for presenting the aforementioned proposal to the user,

[0898] An analytical means that acquires user meal data and estimates nutrient amounts through image analysis,

[0899] A predictive method that uses past health information to predict future health risks,

[0900] Means for securely transmitting data through security protocols,

[0901] A means of providing individualized health management advice tailored to the user's health condition,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, wherein the predictive means generates recommended actions for future health risks based on the health information.

[0905] (Claim 3)

[0906] The system according to claim 1, further comprising means for providing health-related educational information to the user's family or caregivers.

[0907] "Application Example 1"

[0908] (Claim 1)

[0909] A means of receiving natural language input from users,

[0910] An analysis means for analyzing the aforementioned input and identifying the user's emotional state,

[0911] A generation means for generating stress management suggestions based on identified emotional states,

[0912] A means for presenting the aforementioned proposal to the user,

[0913] An analytical means that acquires user meal data and estimates nutrient amounts through image analysis,

[0914] A predictive method that uses past health data to predict future health risks,

[0915] A product recommendation method that recommends relevant products based on the aforementioned emotional state and health data,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, wherein the prediction means generates recommended actions for future health risks based on the health data.

[0919] (Claim 3)

[0920] The system according to claim 1, further comprising means for providing health-related educational information to the user's family or caregivers.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] A means of inputting information from the user via voice or text,

[0924] The aforementioned information is analyzed using speech recognition and natural language processing technologies to identify the user's emotional state,

[0925] A means of inputting image data of meal contents via a terminal and estimating the amount of nutrients using image analysis technology,

[0926] A means for generating stress management suggestions based on the identified emotional state, and for generating behavioral suggestions that take into account past health data and emotional history,

[0927] A means of notifying the user of the aforementioned proposal and nutritional guidance,

[0928] A means of providing health education information to family members and caregivers, based on the user's permission,

[0929] Information processing device including

[0930] (Claim 2)

[0931] The information processing device according to claim 1, which generates appropriate insulin dosages and nutritional advice based on the results of an analysis of ingested nutrients and emotional state.

[0932] (Claim 3)

[0933] The information processing apparatus according to claim 1, further comprising means for proposing stress relief measures tailored to the user's emotional state, which has been analyzed in detail.

[0934] "Application example 2 when combining with an emotional engine"

[0935] (Claim 1)

[0936] A function that accepts natural language input from users,

[0937] Processing means for analyzing the aforementioned input and identifying the user's emotional state,

[0938] A mechanism that generates stress management suggestions based on identified emotional states,

[0939] A display function that presents the aforementioned proposal to the user,

[0940] A processing means for acquiring user meal data and estimating nutrient amounts through image analysis,

[0941] An analytical method for predicting future health risks using past health data,

[0942] A function that recommends product information based on the user's health and emotional state in a real-world shopping environment,

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, wherein the analysis means generates recommended actions for future health risks based on the health data and the environment of the physical store.

[0946] (Claim 3)

[0947] The system according to claim 1, further comprising a function to provide health-related educational information to the user's family or caregivers. [Explanation of Symbols]

[0948] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving natural language input from users, An analysis means for analyzing the aforementioned input and identifying the user's emotional state, A generation means for generating stress management suggestions based on identified emotional states, A means for presenting the aforementioned proposal to the user, An analytical means that acquires user meal data and estimates nutrient amounts through image analysis, A predictive method that uses past health data to predict future health risks, A system that includes this.

2. The system according to claim 1, wherein the prediction means generates recommended actions for future health risks based on the health data.

3. The system according to claim 1, further comprising means for providing health-related educational information to the user's family or caregivers.

Images