System

Abstract

A system is provided.SOLUTION: A system including means for acquiring health data from a user, means for receiving a picture of a meal taken by the user and identifying nutrients, means for monitoring a mental state on the basis of an answer of the user, means for comparing and analyzing these data with big data, means for predicting a poor physical condition or mental down and generating a proposal for an appropriate rest or meal menu, and means for notifying the user of a proposal content.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Employee performance is heavily dependent on their physical and mental state, but many employees find it difficult to properly manage their health and nutritional status. As a result, they are more likely to experience poor physical and mental health, which can lead to reduced work efficiency and increased absenteeism. The present invention aims to solve this problem and maximize employee performance by understanding employees' health status in advance and encouraging appropriate measures. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a means for acquiring health data (exercise volume, pulse rate, and blood pressure data) from users, a means for receiving photos of meals taken by the user and identifying nutrients using a deep learning model, and a means for monitoring the user's mental state based on the user's responses to questions from LINE OA. Furthermore, this data is compared and analyzed with large-scale big data, and AI is used to predict the possibility of poor physical condition or mental breakdown. Based on the prediction results, the system also provides a means for generating specific suggestions, such as appropriate rest and meal menus, and notifying the user of the suggested content. This allows users to take proactive measures and maintain optimal health.

[0006] "Health data" refers to data obtained from a user, including vital signs such as the amount of exercise, pulse rate, and blood pressure.

[0007] "Meal photos" are image data of the meals a user takes each day.

[0008] "Nutrients" are components of the user's diet, such as carbohydrates, proteins, fats, and vitamins, identified using deep learning models.

[0009] "Mental state" refers to the user's psychological health state, such as stress level and fatigue level, and is evaluated by analyzing the text of the user's answers.

[0010] "Big data" refers to datasets containing large amounts of historical health and mental data that can be used for data analysis and predictive models.

[0011] "Comparative analysis" is the process of comparing data obtained from users with existing big data to detect anomalies and patterns.

[0012] A "predictive model" is an AI algorithm that predicts the possibility of physical or mental illness based on past and current data.

[0013] A "suggestion" is specific advice to the user, such as rest and meal menus, that is generated based on the prediction results.

[0014] "Notification" refers to a means such as a push notification or a message to inform the user of the generated proposal. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. The program processing of the system is explained in detail below.

[0037] 1. Health Data Collection

[0038] server

[0039] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[0040] Specific examples

[0041] The server makes an API call such as GET / health-data?date=2023-10-10 to retrieve data for the previous day.

[0042] 2. Analysis of food photos

[0043] Terminal

[0044] Users upload photos of their meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[0045] server

[0046] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[0047] Specific examples

[0048] When a user uploads a photo of their lunch to the app, it is sent to a server, which analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[0049] 3. Mental state monitoring

[0050] User

[0051] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[0052] server

[0053] The server collects responses from users and performs text analysis to assess their mental state.

[0054] Specific examples

[0055] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[0056] 4. Comparative analysis with big data

[0057] server

[0058] The server compares the acquired data with existing big data and performs analysis to check for any abnormalities. It also refers to past data to track changes in health status.

[0059] Specific examples

[0060] The server compares the data from the past month and detects that the recent pulse rate is abnormally high.

[0061] 5. Predicting and suggesting physical and mental health issues

[0062] server

[0063] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates appropriate rest and meal suggestions according to the predicted risk.

[0064] Specific examples

[0065] The server predicts that User A is under high stress and generates a suggestion that says, "You may be under high stress. Try meditating for 10 minutes."

[0066] 6. User Notices

[0067] server

[0068] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[0069] Specific examples

[0070] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[0071] Through the above series of processes, the present invention can manage the health status of employees in real time and provide optimal advice at the right time, thereby preventing physical and mental illnesses from occurring, thereby maximizing employee performance.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] server

[0075] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[0076] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[0077] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[0078] Specific examples

[0079] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[0080] Step 2:

[0081] Terminal

[0082] Users upload photos of their daily meals to a dedicated app.

[0083] The dedicated app has a camera function that allows users to take and send photos of their meals.

[0084] The photos are sent from the device to the server.

[0085] Specific examples

[0086] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[0087] Step 3:

[0088] server

[0089] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[0090] Deep learning models are used to analyze food photos and identify the nutritional components ingested (e.g., carbohydrates, proteins, fats, etc.).

[0091] Specific examples

[0092] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0093] Step 4:

[0094] User

[0095] Users answer questions about their mental state that are sent periodically by LINE OA.

[0096] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[0097] Specific examples

[0098] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[0099] Step 5:

[0100] server

[0101] The server collects the user's responses and performs text analysis to assess their mental state.

[0102] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[0103] Specific examples

[0104] The responses are analyzed and the stress level is classified as high, medium, or low.

[0105] Step 6:

[0106] server

[0107] The server compares and analyzes the acquired health data, nutritional data, and mental state data with existing big data.

[0108] This allows abnormal values ​​and patterns to be detected and the user's health status to be assessed.

[0109] Specific examples

[0110] The server compares the recent pulse rate with data from the past month and detects that it is abnormally high.

[0111] Step 7:

[0112] server

[0113] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[0114] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[0115] Specific examples

[0116] It predicts that user A is under a lot of stress and suggests that they "meditate for 10 minutes."

[0117] Step 8:

[0118] server

[0119] The server notifies the user of the generated proposal.

[0120] Notifications will be sent via app push notifications or LINE messages.

[0121] Specific examples

[0122] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[0123] Example 1

[0124] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] In modern society, employee health management has become an important issue. However, many companies find it difficult to monitor employees' physical and mental health in real time and provide necessary advice at the appropriate time. As a result, poor physical and mental health cannot be prevented, leading to problems such as a decline in employee performance and increased absenteeism. With conventional methods, individual health data, dietary information, and mental state monitoring are not managed centrally, making it difficult to grasp a comprehensive health status and make appropriate recommendations.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0127] In this invention, the server includes a means for acquiring health data from users, a means for receiving images of meals taken by users and identifying nutrients, and a means for monitoring mental states based on users' responses. This makes it possible to grasp employees' health and mental states in real time and provide necessary advice at appropriate times.

[0128] "Health data" refers to physiological information such as the user's exercise volume, heart rate, and blood pressure.

[0129] A "meal image" refers to a photograph of a meal taken by a user, which includes information for identifying the contents and nutrients of the meal.

[0130] "Means for identifying nutrients" refers to the technology or method used by the server to analyze the image of the meal received and identify the ingredients and their nutritional components.

[0131] "Means for monitoring mental state" refers to methods or systems for evaluating and monitoring a user's mental health state by performing text analysis based on the user's answers and input data.

[0132] "Big data" refers to a wide range of existing data sets that can be compared to assess health and mental health.

[0133] "Suggesting rest and meal menus" refers to providing advice on appropriate rest methods and meal contents based on the user's current health, nutritional, and mental state.

[0134] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. This system includes the following components:

[0135] 1. Health Data Collection

[0136] server

[0137] The server works with the health care application on the smartwatch or smartphone to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, heart rate, and blood pressure every day. This data is obtained via an API. For example, at midnight, the previous day's data is obtained in the form of GET / health-data?date=2023-10-10.

[0138] 2. Analysis of food photos

[0139] Terminal

[0140] Using a dedicated app, users take pictures of their meals and upload them, which are then sent to a server.

[0141] server

[0142] The server uses a deep learning model to analyze the received meal images, identify the ingredients contained in the image, and evaluate the nutritional value. Specifically, when a user uploads a photo of their lunch to the app, it is sent to the server. The server analyzes the photo and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[0143] 3. Mental state monitoring

[0144] User

[0145] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[0146] server

[0147] The server collects the user's responses and performs text analysis to evaluate their mental state. For example, if a user receives a message on LINE at 8 p.m. asking, "How were you feeling today?" and the user replies, "I'm pretty tired today," the information is analyzed by the server.

[0148] 4. Comparative analysis with big data

[0149] server

[0150] The server compares the acquired data with a large amount of existing data and performs analysis. This checks for any abnormalities. It also refers to past data to track changes in health status. For example, the server compares data from the past month and detects that a recent heart rate is abnormally high.

[0151] 5. Predicting and suggesting physical and mental health issues

[0152] server

[0153] The server uses a generative AI model to predict the possibility of poor physical condition or mental breakdown based on the analysis results. Depending on the predicted risk, it generates appropriate rest and meal suggestions. For example, the server predicts that User A is in a high stress state and generates a suggestion such as, "You may be in a high stress state. Try meditating for 10 minutes."

[0154] 6. User Notices

[0155] server

[0156] The server notifies the user of the generated suggestions. The notification is sent via a push notification or a LINE message. Specifically, a notification will appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[0157] In this way, the present invention manages employees' health status in real time and provides optimal advice at the right time, thereby preventing physical and mental illness and maximizing employee performance.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1:

[0160] Health Data Requests

[0161] server

[0162] Every day at midnight, the server requests health data from the health care application on the user's smartwatch or smartphone. Specifically, it obtains data such as the amount of exercise, heart rate, and blood pressure from the previous day via an API.

[0163] Input: API call GET / health-data?date=2023-10-10

[0164] Output: Health data (exercise volume, heart rate, blood pressure)

[0165] Specific operation: The server sends an API request at the specified date and time to request health data.

[0166] Step 2:

[0167] Receiving and storing health data

[0168] server

[0169] The server receives the acquired health data and stores it in a database for later analysis and comparison.

[0170] Input: Health data as API response

[0171] Output: Health data stored in a database

[0172] Specific operation: The server analyzes the received data and records it in a database.

[0173] Step 3:

[0174] Upload a meal photo

[0175] Terminal

[0176] Users use a dedicated app to take pictures of their meals and upload them.

[0177] Input: Food image (user-taken photo)

[0178] Output: Image file sent to the server

[0179] Specific operation: The user selects a photo of a meal from the dedicated app and presses the "Upload" button.

[0180] Step 4:

[0181] Receiving meal photos

[0182] server

[0183] The server receives the uploaded food images and prepares them for analysis.

[0184] Input: Image file sent by the user

[0185] Output: Meal images saved in temporary storage

[0186] Specific operation: The server receives the image file and temporarily stores it.

[0187] Step 5:

[0188] Ingredient and nutrient analysis

[0189] server

[0190] The server uses deep learning models to analyze the received photos, identify the ingredients in the photos, and assess their nutritional value.

[0191] Input: Food images stored in temporary storage

[0192] Output: Analysis results (carbohydrates 50g, protein 30g, fat 20g, etc.)

[0193] Specific operation: The server invokes the deep learning model to extract nutritional information from the image.

[0194] Step 6:

[0195] Submit a mental health question

[0196] server

[0197] The server periodically sends questions to the user via LINE OA to assess their mental state.

[0198] Input: Fixed message "How were you feeling today?"

[0199] Output: The question message sent to the user

[0200] Specific operation: The server sends a LINE message to the user at 8pm.

[0201] Step 7:

[0202] Receiving and processing responses

[0203] server

[0204] The server collects responses from users and performs text analysis to assess their mental state.

[0205] Input: User response text, e.g. "I'm pretty tired today"

[0206] Output: Mental state evaluation results

[0207] Specific operation: The server analyzes the received text and evaluates the mental state.

[0208] Step 8:

[0209] Data collection and comparison

[0210] server

[0211] The server compares the collected health and mental status data with a large amount of existing data to check for abnormalities, and also refers to past data to track changes in health status.

[0212] Input: Collected data and existing bulk data

[0213] Output: Analysis results (no anomalies, anomalies detected, etc.)

[0214] Specific operation: The server compares data from the past month and detects abnormalities such as high pulse rate.

[0215] Step 9:

[0216] Situation assessment and forecasting

[0217] server

[0218] The server uses a generative AI model that predicts the likelihood of physical or mental illness based on the analysis results.

[0219] Input: Analysis results and generated AI model

[0220] Output: Prediction results of poor physical condition and mental downturn

[0221] How it works: The server uses the generated AI model to predict the user's stress level and physical condition abnormalities.

[0222] Step 10:

[0223] Proposal Generation

[0224] server

[0225] The server generates appropriate rest and meal suggestions based on the predicted risk.

[0226] Input: Prediction result

[0227] Output: Specific suggestions (resting methods and meal menu)

[0228] Specific behavior: The server generates a suggestion such as "You may be under high stress. Try meditating for 10 minutes."

[0229] Step 11:

[0230] Sending notifications

[0231] server

[0232] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[0233] Input: Proposal

[0234] Output: Notification message sent to the user

[0235] Specific operation: The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[0236] (Application example 1)

[0237] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0238] There is a need to appropriately monitor the physical and mental states of employees and prevent them from becoming ill or suffering from mental breakdowns. Security employees, in particular, need to be aware of their health status in real time and take appropriate measures, as abnormal physical or mental states directly affect the safety and efficiency of their work. However, current systems lack the ability to detect abnormalities in real time or propose specific countermeasures. Therefore, the objective of this invention is to accurately and quickly manage the physical and mental states of employees and provide appropriate warnings and advice.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0240] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's responses, means for comparing and analyzing these data with big data, means for predicting poor physical condition or mental breakdown and generating appropriate rest and meal menu suggestions, means for notifying the user of the suggestions, and means for monitoring the physical and mental state of security employees in real time and detecting and warning of abnormalities. This makes it possible to monitor the physical and mental state of employees in real time and take prompt and appropriate measures if an abnormality is detected.

[0241] "Health data" is information related to the user's physical activity, and is data related to the user's health condition, including the amount of exercise, pulse rate, blood pressure, etc.

[0242] A "meal photo" is an image that visually records the meal a user has eaten, and is used to analyze the contents of the image to identify nutrients.

[0243] "Mental state" indicates the mental health state of the user, and refers to the state of mind and emotions.

[0244] "Big data" refers to large amounts of digital information that can be used to analyze data and detect anomalies.

[0245] "Comparative analysis" is a method for analyzing acquired data against large amounts of existing data, in order to identify abnormalities and trends.

[0246] "Poor health" refers to an abnormality in the user's physical activity or health condition, which interferes with the performance of normal business operations.

[0247] "Mental down" refers to a state in which the user's mental state is abnormal and the user is mentally unstable.

[0248] "Rest" refers to rest or activities that a user undertakes to refresh their body and mind and restore their health.

[0249] A "meal menu" refers to the combination of foods and menu items that a user will consume, and suggestions are made taking into consideration nutrient balance.

[0250] "Notification" refers to the transmission of information from the system to the user, including alerts and advice.

[0251] "Real-time" refers to the state in which data is collected, analyzed, and notified immediately, and processing is carried out without delay.

[0252] "Anomaly detection" is the process of discovering deviations from normal health or mental states, and is an important step in responding quickly.

[0253] A "warning" is a notification that alerts the user to a detected abnormality and urges the user to take appropriate action.

[0254] To implement the present invention, the system is configured as follows.

[0255] Hardware and software:

[0256] 1. Server:

[0257] Hardware: Cloud server (e.g. AWS, GCP)

[0258] software:

[0259] Health data APIs (e.g., HealthKit API)

[0260] Deep learning models (e.g. TensorFlow)

[0261] NLP analysis libraries (e.g. NLTK, spaCy)

[0262] Big data analysis tools (e.g., Apache Hadoop, Spark)

[0263] Notification API (e.g. Firebase Cloud Messaging)

[0264] 2. Terminal:

[0265] Hardware: Smartwatches, smartphone cameras

[0266] Software: Dedicated health management application

[0267] Detailed description of the process:

[0268] 1. Health Data Collection:

[0269] The server works in conjunction with the smartwatch or smartphone's healthcare application to collect daily health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, it uses an API to obtain the previous day's data at midnight.

[0270] For example, the server makes an API call like GET / health-data?date=2023-10-10 to retrieve data from the previous day.

[0271] 2. Analysis of food photographs:

[0272] When users upload photos of their meals to the app, the photos are sent to a server, which then analyzes them using a deep learning model to identify the ingredients and evaluate their nutritional value.

[0273] For example, when a user uploads a photo of their lunch to the app, the server analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[0274] 3. Mental state monitoring:

[0275] Users answer questions sent periodically to assess their mental state. The server collects the answers from users and performs text analysis to assess their mental state.

[0276] For example, if a message asking "How were you feeling today?" is sent via LINE at 8pm and the user replies "I'm pretty tired today," that information is analyzed on the server.

[0277] 4. Comparative analysis with big data:

[0278] The server compares the acquired data with existing big data to detect anomalies, and compares it with past data to track changes in health status.

[0279] As a specific example, the server compares data from the past month and detects that the recent pulse rate is abnormally high.

[0280] 5. Prediction and suggestions for physical and mental illness:

[0281] Based on the analysis results, the server predicts the possibility of poor physical or mental health and generates appropriate rest and meal recommendations. The advice is generated by an AI model.

[0282] As a specific example, the server predicts that the user is under high stress and generates a suggestion such as, "You may be under high stress. Try meditating for 10 minutes."

[0283] 6. User Notice:

[0284] The server notifies the user of the generated suggestions via app push notifications or messages.

[0285] As a specific example, a notification may appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[0286] An example prompt for a generative AI model would be:

[0287] The user's health data indicates high stress levels and fatigue. Please provide three appropriate health tips for this user:

[0288] 1. Relaxation techniques such as meditation and stretching

[0289] 2. Proposing nutritionally balanced meals

[0290] 3. Mental health advice

[0291] In this way, the "Security Guard Health Monitor" application becomes a powerful tool for maintaining optimal physical and mental health of security employees.

[0292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0293] Step 1:

[0294] The server obtains the user's health data (such as exercise volume, pulse rate, and blood pressure) from the smartwatch or smartphone via API. As input, it receives the user ID and date and time information and sends an API request. As output, it receives the previous day's health data and stores it in a database.

[0295] Step 2:

[0296] Users upload photos of their meals to a dedicated app. As input, the app takes photos of the meal taken with a smartphone camera and sends them to the server. As output, the photo data is sent to the server, ready for analysis.

[0297] Step 3:

[0298] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained and evaluate the nutrients consumed. As input, the photo data of the meal is obtained and input into the AI ​​model. As output, the analysis results are obtained and nutritional information such as "carbohydrates, protein, fat" is stored in a database.

[0299] Step 4:

[0300] Users answer questions about their mental state that are periodically sent via LINE OA. As input, the system obtains the user's text responses on LINE OA. As output, the text responses are sent to the server.

[0301] Step 5:

[0302] The server analyzes the user's responses using a text analysis tool to evaluate their mental state. As input, it obtains the user's text responses and inputs them into an NLP analysis library. As output, it obtains the mental state evaluation results, and information such as "stress level" and "emotional state" is stored in a database.

[0303] Step 6:

[0304] The server uses a big data analysis tool to compare and analyze the collected health, nutritional, and mental state data with past data. Current user data and past big data are taken as input. Abnormal patterns and abnormal health status are detected as output, and the results are stored in a database.

[0305] Step 7:

[0306] The server uses an AI model to predict the likelihood of poor physical or mental health based on the comparative analysis results, and generates recommendations for appropriate rest and meal plans. The analysis results are input into the AI ​​model, and specific advice for the user is generated as output.

[0307] Step 8:

[0308] The server notifies the user of the generated suggestions via push notification or message to the user's smartphone. As input, it receives the suggestion content and the user information of the notification recipient. As output, a notification is displayed on the user's smartphone. For example, a notification may be displayed saying, "You seem tired today, so let's do some short stretches to relax."

[0309] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0310] The present invention is a system that monitors the physical condition, nutritional intake, and mental state of employees, and not only predicts poor physical condition or mental breakdown, but also recognizes the user's emotions, thereby achieving more accurate health management and maximizing performance. The system's program processing is described in detail below.

[0311] 1. Health Data Collection

[0312] server

[0313] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[0314] Specific examples

[0315] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[0316] 2. Analysis of food photos

[0317] Terminal

[0318] Users upload photos of their daily meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[0319] server

[0320] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[0321] Specific examples

[0322] A user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0323] 3. Mental state monitoring

[0324] User

[0325] Users answer questions about their mental state that are periodically sent by LINE OA. The questions are designed to assess the user's mental state.

[0326] server

[0327] The server collects responses from users and performs text analysis to assess their mental state.

[0328] Specific examples

[0329] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[0330] 4. Emotion Recognition by Emotion Engine

[0331] server

[0332] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[0333] Specific examples

[0334] If a user texts "I'm very happy today," the emotion engine will recognize this as a positive emotion.

[0335] 5. Comparative analysis of data and synthesis of results

[0336] server

[0337] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data recognized by the emotion engine with existing big data, thereby detecting abnormal values ​​and patterns and comprehensively assessing the user's health condition.

[0338] Specific examples

[0339] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[0340] 6. Predicting and suggesting physical and mental health issues

[0341] server

[0342] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[0343] Specific examples

[0344] The server predicts that User A is under a lot of stress and suggests that he "meditate for 10 minutes." It also suggests activities to increase positive emotions based on emotional data.

[0345] 7. User Notices

[0346] server

[0347] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[0348] Specific examples

[0349] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[0350] Through the above series of processes, the present invention not only manages employees' health status in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management. This system can prevent employees from becoming physically or mentally unwell, maximizing their performance.

[0351] The processing flow will be explained below.

[0352] Step 1:

[0353] server

[0354] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[0355] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[0356] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[0357] Specific examples

[0358] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[0359] Step 2:

[0360] Terminal

[0361] Users upload photos of their daily meals to a dedicated app.

[0362] The dedicated app has a camera function that allows users to take and send photos of their meals.

[0363] The photos are sent from the device to the server.

[0364] Specific examples

[0365] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[0366] Step 3:

[0367] server

[0368] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[0369] Using a deep learning model, it analyzes photos of meals and identifies the nutritional components (carbohydrates, proteins, fats, etc.) ingested.

[0370] Specific examples

[0371] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0372] Step 4:

[0373] User

[0374] Users answer questions about their mental state that are sent periodically by LINE OA.

[0375] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[0376] Specific examples

[0377] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[0378] Step 5:

[0379] server

[0380] The server collects the user's responses and performs text analysis to assess their mental state.

[0381] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[0382] Specific examples

[0383] The responses are analyzed and the stress level is classified as high, medium, or low.

[0384] Step 6:

[0385] server

[0386] The server uses an emotion engine that recognizes emotions from the user's voice and text input.

[0387] The emotion engine classifies the user's emotions into positive and negative, and integrates this into a mental state assessment.

[0388] Specific examples

[0389] If a user texts "I'm very happy today," the emotion engine will recognize this as positive.

[0390] Step 7:

[0391] server

[0392] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data with existing big data.

[0393] This allows for the detection of abnormal values ​​and patterns and a comprehensive assessment of the user's health status.

[0394] Specific examples

[0395] The server detects if the health data deviates from the average for the past month, and if the emotional data is negative, it assesses the overall health risk as high.

[0396] Step 8:

[0397] server

[0398] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[0399] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[0400] Specific examples

[0401] The server predicts that User A is in a high stress state and suggests that he or she "meditate for 10 minutes." It also suggests activities to increase positive emotions.

[0402] Step 9:

[0403] server

[0404] The server notifies the user of the generated proposal.

[0405] Notifications will be sent via app push notifications or LINE messages.

[0406] Specific examples

[0407] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax," and also includes a suggestion based on emotional data, "Let's refresh ourselves by listening to our favorite music."

[0408] Example 2

[0409] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0410] Employee health management requires preventing poor physical and mental health before they occur. However, conventional health management systems are limited to analyzing individual data points alone, making it difficult to evaluate overall health status. It is also difficult to provide personalized advice that reflects the user's emotional state. Therefore, there is a need for a system that can achieve more accurate health management and maximize performance.

[0411] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0412] In this invention, the server includes means for acquiring health data from users and storing the data in a database, means for receiving photos of meals taken by users and identifying nutrients using a deep learning model, means for performing text analysis based on the user's responses and monitoring the mental state, means for analyzing voice input and text input with an emotion engine and classifying the user's emotions, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating suggestions for appropriate rest and meal menus, and means for notifying the user of the suggestions. This makes it possible to manage employee health conditions in real time and provide accurate advice based on a comprehensive evaluation.

[0413] "Health data" refers to data relating to the user's physical condition, such as the user's amount of exercise, pulse rate, blood pressure, etc.

[0414] A "database" is a system for efficiently storing, managing, and searching acquired data.

[0415] A "meal photo" is an image of the ingredients and meal contents consumed by the user.

[0416] A "deep learning model" is an artificial intelligence technique that uses large data sets to extract features and perform classification.

[0417] "Nutrients" are substances such as proteins, carbohydrates, fats, vitamins, and minerals found in food.

[0418] "Text analysis" is a method of extracting meaning and emotion from user responses and sentences using natural language processing technology.

[0419] "Mental state" refers to the user's psychological health and stress level.

[0420] An "emotion engine" is an analysis system for identifying a user's emotions from voice and text data.

[0421] "Big data" refers to a large amount of data in a variety of formats, and analyzing this data can provide new information and insights.

[0422] "Comparative analysis" is a technique for comparing multiple data sets to find specific patterns or anomalies.

[0423] "Poor physical condition" refers to a state in which the user is unable to maintain normal bodily functions.

[0424] "Mental down" refers to a user's mental state deteriorating due to psychological fatigue or stress.

[0425] "Suggestions" are specific advice about behaviors and diets generated based on the user's health status.

[0426] "Notification" is a communication method for presenting information or suggestions from the server to the user.

[0427] The system of the present invention is designed to monitor employees' physical condition, nutritional intake, and mental state in real time and to predict poor physical and mental health before they occur. This system aims to maximize employee performance. Specific embodiments of the system are described below.

[0428] The system consists of a server, a user's device, and a dedicated AI model.

[0429] The server works with the healthcare application installed on the user's smartwatch or smartphone to collect health data. Specifically, data such as exercise volume, pulse rate, and blood pressure is collected periodically every day. For example, the server executes an API request (GET / health-data?date=<previous day's date>) at midnight every night to retrieve the previous day's health data.

[0430] Users take and upload photos of their daily meals using a dedicated app. The uploaded photos are sent to a server and analyzed using a deep learning model. This model identifies the ingredients in the photo and evaluates their nutritional value. For example, a user can take a photo of their lunch and send it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0431] The server also periodically sends questions to employees using LINE OA to monitor their mental state. For example, at 8 p.m., a message asking "How were you feeling today?" is sent to the user's LINE. If the user replies "I'm pretty tired today," the server analyzes the text and converts it into a score to evaluate their mental state.

[0432] Furthermore, the server is integrated with an emotion engine that recognizes emotions from voice and text input. This engine analyzes the user's input and classifies emotions as positive, negative, etc. For example, if you enter the text "I'm very happy today," the server will input this into the emotion engine and recognize it as a positive emotion.

[0433] The server centrally manages the acquired health, nutrition, mental state, and emotional data, and compares and analyzes it with big data. It can detect abnormal values ​​and patterns by comparing it with data from the past month and standard data. For example, if the pulse rate is higher than normal or the emotional data is negative, it will assess the overall state of high stress.

[0434] Finally, the server predicts the possibility of poor physical or mental health based on the analysis results and generates recommendations for appropriate rest, meal options, etc. For example, it may generate specific suggestions such as "Try meditating for 10 minutes" and notify the user via push notification or LINE message.

[0435] In this way, the present invention is built by combining a server, user devices, a dedicated application, and a deep learning model. This system can comprehensively monitor employees' health status and provide prompt and appropriate advice.

[0436] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0437] Step 1:

[0438] Acquisition of health data

[0439] server

[0440] The server works with the healthcare application installed on the smartwatch or smartphone to collect the user's health data. Specifically, it executes an API request GET / health-data?date=<previous day's date> every night at midnight to obtain the previous day's exercise amount, pulse rate, and blood pressure data. The input is the response data to the API request from the health app, and the output is the health data stored in the database. The collected data is stored in the database and validated to ensure data integrity and consistency.

[0441] Step 2:

[0442] Upload a meal photo

[0443] User

[0444] Users take photos of their daily meals using a dedicated app and upload them. The input is the photo of the meal taken by the user, and the output is image data sent to the server. The photo is sent to the endpoint POST / upload-photo, and is sent when the user selects a photo in the app and presses the upload button.

[0445] Step 3:

[0446] Food photo analysis

[0447] server

[0448] The server analyzes the received meal photos using a deep learning model. This model identifies the ingredients contained in the photos and evaluates their nutritional value. The input is the meal photo uploaded by the user, and the output is the analyzed nutritional information. Specifically, the server inputs the photo into the deep learning model and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[0449] Step 4:

[0450] Mental state monitoring

[0451] Server, User

[0452] At 8 p.m., the server sends the user a message via LINE OA asking, "How were you feeling today?" The input is the question in the LINE message, and the output is the user's answer. If the user answers, "I'm pretty tired today," the answer data is sent to the server, which performs text analysis. Specifically, the server analyzes the text using natural language processing technology and generates a score to evaluate the user's mental state.

[0453] Step 5:

[0454] Emotion recognition

[0455] server

[0456] The server uses an emotion engine that recognizes emotions from the user's voice or text input. The input is the user's voice or text data, and the output is emotion data categorized as positive, negative, etc. For example, if the user inputs the text "I'm very happy today," the server inputs that text into the emotion engine and recognizes it as a positive emotion.

[0457] Step 6:

[0458] Comparative analysis of data and synthesis of results

[0459] server

[0460] The server collects and centrally manages the acquired health, nutritional, mental state, and emotional data. The input is a collection of various data, and the output is the integrated analysis results. Specifically, the server compares and analyzes this data with past data and standard big data to detect abnormal values ​​and patterns. For example, it compares pulse rate data from the past month with the latest data to detect abnormally high values, and if the emotional data is negative, it evaluates the overall state as high stress.

[0461] Step 7:

[0462] Prediction and suggestions for poor physical and mental health

[0463] server

[0464] The server uses an AI model to predict the possibility of poor physical or mental health. The input is the integrated analysis data, and the output is specific suggestions. Specifically, the server inputs data into the AI ​​model and generates specific suggestions, such as "Meditate for 10 minutes" or "Do some short stretches for relaxation."

[0465] Step 8:

[0466] User Notification

[0467] server

[0468] The server notifies the user of the generated suggestions. The input is the generated suggestions, and the output is the notification to the user. The notification is sent via push notification or LINE message. For example, a message saying "You seem tired today, so try doing a short stretch to relax" is sent to the user's smartphone. This notification also includes suggestions based on the results of the emotion engine, such as "Refresh yourself with your favorite music."

[0469] (Application example 2)

[0470] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0471] The purpose of this invention is to prevent poor physical and mental health by efficiently monitoring the physical and mental state of employees, and to maximize performance by suggesting appropriate rest and meal plans at the right time. In particular, by introducing emotion recognition functionality to security service staff, the purpose is to achieve more effective health management and improved service quality in situations where a quick response is required.

[0472] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0473] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's answers, means for recognizing emotions from the user's voice input or text input, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating appropriate rest and meal menu suggestions, and means for notifying the user of the suggestions. This enables more accurate and comprehensive health management of employees, real-time evaluation of their health condition, and timely and appropriate suggestions to be made.

[0474] "Health data" refers to biometric information such as the user's amount of exercise, pulse rate, blood pressure, etc.

[0475] "Nutrition data" refers to information about the nutritional composition of the food a user has eaten, analyzed.

[0476] "Mental state data" refers to information for assessing the psychological state of a user.

[0477] "Emotion data" refers to emotional information recognized based on a user's voice or text input.

[0478] "Big data" refers to technology for processing and analyzing large amounts of data at high speed.

[0479] "Comparative analysis" refers to the process of comparing multiple data sets and analyzing their differences and commonalities.

[0480] "Predicting poor health" refers to the process of predicting the likelihood of a user experiencing poor health in the future based on the user's health data and mental state data.

[0481] "Mental down prediction" refers to a process of predicting the possibility of a mentally unstable state occurring in the future based on the user's mental state data and emotion data.

[0482] "Suggestion generation" refers to the process of recommending appropriate rest, meal plans, and other actions to the user based on the predicted results.

[0483] "Notification means" refers to the method or device used to notify the user of the generated suggestions.

[0484] MODE FOR CARRYING OUT THE INVENTION

[0485] The present invention is a system for managing the physical condition and optimizing the performance of employees and users. The system comprehensively analyzes health data, nutritional data, mental state data, and emotional data, generates appropriate suggestions, and notifies the user. The following describes in detail the embodiments of the present invention.

[0486] 1. Health Data Collection

[0487] server

[0488] The server works with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. The server executes an API request every night at midnight to obtain the previous day's health data.

[0489] Specific examples

[0490] The server executes the API request "GET / health-data?date=2023-10-10" every night at midnight to retrieve health data.

[0491] 2. Analysis of food photos

[0492] Terminal

[0493] Users use a specific application to take photos of their daily meals and upload them to a server, which then uses deep learning models to identify ingredients and analyze their nutritional content.

[0494] server

[0495] The server uses AI to analyze the received meal photos, identify the ingredients contained in the photos, and evaluate the proportions of nutrients.

[0496] Specific examples

[0497] The user takes a photo of their lunch using a dedicated app and sends it via "POST / upload-photo." The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0498] 3. Mental state monitoring

[0499] User

[0500] Users report their mental state by answering questions that are sent periodically, for example via messaging apps such as LINE.

[0501] server

[0502] The server receives the user's answers and performs natural language analysis to assess the mental state.

[0503] Specific examples

[0504] At 8pm, a message is sent to the user asking "How were you feeling today?" If the user replies "I'm pretty tired today," the information is analyzed on the server.

[0505] 4. Emotion Recognition by Emotion Engine

[0506] server

[0507] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[0508] Specific examples

[0509] If the user texts "I'm very happy today," the server recognizes this as a positive emotion.

[0510] 5. Comparative analysis of data and synthesis of results

[0511] server

[0512] The server integrates the acquired health, nutrition, mental state, and emotional data and compares and analyzes it with big data to detect abnormal values ​​and patterns and comprehensively evaluate the user's health condition.

[0513] Specific examples

[0514] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[0515] 6. Predicting and suggesting physical and mental health issues

[0516] server

[0517] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[0518] Specific examples

[0519] The server predicts that the user is under high stress and suggests that they "take 10 minutes of meditation." It also suggests activities to increase positive emotions based on emotional data.

[0520] 7. User Notices

[0521] server

[0522] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[0523] Specific examples

[0524] The server sends a notification to the user's device saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[0525] Prompt Sentence Examples

[0526] 1. Health data collection:

[0527] Get your health data.

[0528] 2. Mental state monitoring:

[0529] How were you feeling today?

[0530] As described above, the present invention not only manages the health status of employees and users in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management, thereby preventing employees from becoming physically or mentally unwell and maximizing their performance.

[0531] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0532] Step 1:

[0533] Health Data Collection

[0534] The server works in conjunction with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, the server executes an API request every night at midnight to obtain the previous day's health data.

[0535] Input: API request (e.g. "GET / health-data?date=2023-10-10")

[0536] Data processing: Formatting data obtained from healthcare applications and storing it in a database

[0537] Output: Stored health data (e.g., exercise amount, pulse rate, blood pressure)

[0538] Step 2:

[0539] Food photo analysis

[0540] The device allows users to take photos of their meals using a dedicated app and upload them to a server, which then analyzes the photos using a deep learning model to identify the ingredients in the photo and evaluate their nutritional value.

[0541] Input: Uploaded food photo (e.g. "POST / upload-photo")

[0542] Data processing: Analyze photos using a deep learning model to extract information about ingredients and nutrients

[0543] Output: Analyzed nutritional data (e.g., carbohydrates 50g, protein 30g, fat 20g)

[0544] Step 3:

[0545] Mental state monitoring

[0546] Users answer questions sent periodically via messaging apps such as LINE. The server receives the user's answers and performs natural language analysis to evaluate their mental state.

[0547] Input: Answer about the user's mental state (e.g., "I'm pretty tired today")

[0548] Data processing: Evaluate users' responses using natural language processing to generate mental state data

[0549] Output: Mental state data (e.g., fatigue level, stress level)

[0550] Step 4:

[0551] Emotion recognition by emotion engine

[0552] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[0553] Input: Voice or text input from the user (e.g., "I'm very happy today")

[0554] Data processing: Analyze input data using an emotion engine to generate emotion data

[0555] Output: Emotion data (e.g., positive, negative)

[0556] Step 5:

[0557] Comparative analysis of data and synthesis of results

[0558] The server compares the acquired health, nutrition, mental state, and emotional data with past data and big data, detects abnormal values ​​and patterns, and comprehensively evaluates the user's health condition.

[0559] Input: Health data, nutrition data, mental state data, emotional data

[0560] Data processing: Matching with big data and analyzing it to detect outliers and patterns

[0561] Output: Comprehensive health assessment data (e.g., high stress levels, nutritional imbalances)

[0562] Step 6:

[0563] Prediction and suggestions for poor physical and mental health

[0564] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[0565] Input: Health assessment data

[0566] Data processing: Using AI models to predict risks and generate specific recommendations

[0567] Output: Suggestions (e.g., 10 minutes of meditation, stretches to relax)

[0568] Step 7:

[0569] User Notifications

[0570] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[0571] Input: Proposal

[0572] Data processing: Converting the data into notification format and sending it to the user's device

[0573] Output: User notification (e.g., "You seem tired today, let's do some short stretches for relaxation")

[0574] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0575] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0576] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0577] [Second embodiment]

[0578] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0579] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0580] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0581] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0582] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0583] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0584] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0585] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0586] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0587] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0588] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0589] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0590] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. The program processing of the system is explained in detail below.

[0591] 1. Health Data Collection

[0592] server

[0593] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[0594] Specific examples

[0595] The server makes an API call such as GET / health-data?date=2023-10-10 to retrieve data for the previous day.

[0596] 2. Analysis of food photos

[0597] Terminal

[0598] Users upload photos of their meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[0599] server

[0600] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[0601] Specific examples

[0602] When a user uploads a photo of their lunch to the app, it is sent to a server, which analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[0603] 3. Mental state monitoring

[0604] User

[0605] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[0606] server

[0607] The server collects responses from users and performs text analysis to assess their mental state.

[0608] Specific examples

[0609] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[0610] 4. Comparative analysis with big data

[0611] server

[0612] The server compares the acquired data with existing big data and performs analysis to check for any abnormalities. It also refers to past data to track changes in health status.

[0613] Specific examples

[0614] The server compares the data from the past month and detects that the recent pulse rate is abnormally high.

[0615] 5. Predicting and suggesting physical and mental health issues

[0616] server

[0617] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates appropriate rest and meal suggestions according to the predicted risk.

[0618] Specific examples

[0619] The server predicts that User A is under high stress and generates a suggestion that says, "You may be under high stress. Try meditating for 10 minutes."

[0620] 6. User Notices

[0621] server

[0622] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[0623] Specific examples

[0624] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[0625] Through the above series of processes, the present invention can manage the health status of employees in real time and provide optimal advice at the right time, thereby preventing physical and mental illnesses from occurring, thereby maximizing employee performance.

[0626] The processing flow will be explained below.

[0627] Step 1:

[0628] server

[0629] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[0630] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[0631] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[0632] Specific examples

[0633] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[0634] Step 2:

[0635] Terminal

[0636] Users upload photos of their daily meals to a dedicated app.

[0637] The dedicated app has a camera function that allows users to take and send photos of their meals.

[0638] The photos are sent from the device to the server.

[0639] Specific examples

[0640] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[0641] Step 3:

[0642] server

[0643] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[0644] Deep learning models are used to analyze food photos and identify the nutritional components ingested (e.g., carbohydrates, proteins, fats, etc.).

[0645] Specific examples

[0646] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0647] Step 4:

[0648] User

[0649] Users answer questions about their mental state that are sent periodically by LINE OA.

[0650] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[0651] Specific examples

[0652] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[0653] Step 5:

[0654] server

[0655] The server collects the user's responses and performs text analysis to assess their mental state.

[0656] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[0657] Specific examples

[0658] The responses are analyzed and the stress level is classified as high, medium, or low.

[0659] Step 6:

[0660] server

[0661] The server compares and analyzes the acquired health data, nutritional data, and mental state data with existing big data.

[0662] This allows abnormal values ​​and patterns to be detected and the user's health status to be assessed.

[0663] Specific examples

[0664] The server compares the recent pulse rate with data from the past month and detects that it is abnormally high.

[0665] Step 7:

[0666] server

[0667] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[0668] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[0669] Specific examples

[0670] It predicts that user A is under a lot of stress and suggests that they "meditate for 10 minutes."

[0671] Step 8:

[0672] server

[0673] The server notifies the user of the generated proposal.

[0674] Notifications will be sent via app push notifications or LINE messages.

[0675] Specific examples

[0676] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[0677] Example 1

[0678] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0679] In modern society, employee health management has become an important issue. However, many companies find it difficult to monitor employees' physical and mental health in real time and provide necessary advice at the appropriate time. As a result, poor physical and mental health cannot be prevented, leading to problems such as a decline in employee performance and increased absenteeism. With conventional methods, individual health data, dietary information, and mental state monitoring are not managed centrally, making it difficult to grasp a comprehensive health status and make appropriate recommendations.

[0680] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0681] In this invention, the server includes a means for acquiring health data from users, a means for receiving images of meals taken by users and identifying nutrients, and a means for monitoring mental states based on users' responses. This makes it possible to grasp employees' health and mental states in real time and provide necessary advice at appropriate times.

[0682] "Health data" refers to physiological information such as the user's exercise volume, heart rate, and blood pressure.

[0683] A "meal image" refers to a photograph of a meal taken by a user, which includes information for identifying the contents and nutrients of the meal.

[0684] "Means for identifying nutrients" refers to the technology or method used by the server to analyze the image of the meal received and identify the ingredients and their nutritional components.

[0685] "Means for monitoring mental state" refers to methods or systems for evaluating and monitoring a user's mental health state by performing text analysis based on the user's answers and input data.

[0686] "Big data" refers to a wide range of existing data sets that can be compared to assess health and mental health.

[0687] "Suggesting rest and meal menus" refers to providing advice on appropriate rest methods and meal contents based on the user's current health, nutritional, and mental state.

[0688] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. This system includes the following components:

[0689] 1. Health Data Collection

[0690] server

[0691] The server works with the health care application on the smartwatch or smartphone to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, heart rate, and blood pressure every day. This data is obtained via an API. For example, at midnight, the previous day's data is obtained in the form of GET / health-data?date=2023-10-10.

[0692] 2. Analysis of food photos

[0693] Terminal

[0694] Using a dedicated app, users take pictures of their meals and upload them, which are then sent to a server.

[0695] server

[0696] The server uses a deep learning model to analyze the received meal images, identify the ingredients contained in the image, and evaluate the nutritional value. Specifically, when a user uploads a photo of their lunch to the app, it is sent to the server. The server analyzes the photo and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[0697] 3. Mental state monitoring

[0698] User

[0699] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[0700] server

[0701] The server collects the user's responses and performs text analysis to evaluate their mental state. For example, if a user receives a message on LINE at 8 p.m. asking, "How were you feeling today?" and the user replies, "I'm pretty tired today," the information is analyzed by the server.

[0702] 4. Comparative analysis with big data

[0703] server

[0704] The server compares the acquired data with a large amount of existing data and performs analysis. This checks for any abnormalities. It also refers to past data to track changes in health status. For example, the server compares data from the past month and detects that a recent heart rate is abnormally high.

[0705] 5. Predicting and suggesting physical and mental health issues

[0706] server

[0707] The server uses a generative AI model to predict the possibility of poor physical condition or mental breakdown based on the analysis results. Depending on the predicted risk, it generates appropriate rest and meal suggestions. For example, the server predicts that User A is in a high stress state and generates a suggestion such as, "You may be in a high stress state. Try meditating for 10 minutes."

[0708] 6. User Notices

[0709] server

[0710] The server notifies the user of the generated suggestions. The notification is sent via a push notification or a LINE message. Specifically, a notification will appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[0711] In this way, the present invention manages employees' health status in real time and provides optimal advice at the right time, thereby preventing physical and mental illness and maximizing employee performance.

[0712] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0713] Step 1:

[0714] Health Data Requests

[0715] server

[0716] Every day at midnight, the server requests health data from the health care application on the user's smartwatch or smartphone. Specifically, it obtains data such as the amount of exercise, heart rate, and blood pressure from the previous day via an API.

[0717] Input: API call GET / health-data?date=2023-10-10

[0718] Output: Health data (exercise volume, heart rate, blood pressure)

[0719] Specific operation: The server sends an API request at the specified date and time to request health data.

[0720] Step 2:

[0721] Receiving and storing health data

[0722] server

[0723] The server receives the acquired health data and stores it in a database for later analysis and comparison.

[0724] Input: Health data as API response

[0725] Output: Health data stored in a database

[0726] Specific operation: The server analyzes the received data and records it in a database.

[0727] Step 3:

[0728] Upload a meal photo

[0729] Terminal

[0730] Users use a dedicated app to take pictures of their meals and upload them.

[0731] Input: Food image (user-taken photo)

[0732] Output: Image file sent to the server

[0733] Specific operation: The user selects a photo of a meal from the dedicated app and presses the "Upload" button.

[0734] Step 4:

[0735] Receiving meal photos

[0736] server

[0737] The server receives the uploaded food images and prepares them for analysis.

[0738] Input: Image file sent by the user

[0739] Output: Meal images saved in temporary storage

[0740] Specific operation: The server receives the image file and temporarily stores it.

[0741] Step 5:

[0742] Ingredient and nutrient analysis

[0743] server

[0744] The server uses deep learning models to analyze the received photos, identify the ingredients in the photos, and assess their nutritional value.

[0745] Input: Food images stored in temporary storage

[0746] Output: Analysis results (carbohydrates 50g, protein 30g, fat 20g, etc.)

[0747] Specific operation: The server invokes the deep learning model to extract nutritional information from the image.

[0748] Step 6:

[0749] Submit a mental health question

[0750] server

[0751] The server periodically sends questions to the user via LINE OA to assess their mental state.

[0752] Input: Fixed message "How were you feeling today?"

[0753] Output: The question message sent to the user

[0754] Specific operation: The server sends a LINE message to the user at 8pm.

[0755] Step 7:

[0756] Receiving and processing responses

[0757] server

[0758] The server collects responses from users and performs text analysis to assess their mental state.

[0759] Input: User response text, e.g. "I'm pretty tired today"

[0760] Output: Mental state evaluation results

[0761] Specific operation: The server analyzes the received text and evaluates the mental state.

[0762] Step 8:

[0763] Data collection and comparison

[0764] server

[0765] The server compares the collected health and mental status data with a large amount of existing data to check for abnormalities, and also refers to past data to track changes in health status.

[0766] Input: Collected data and existing bulk data

[0767] Output: Analysis results (no anomalies, anomalies detected, etc.)

[0768] Specific operation: The server compares data from the past month and detects abnormalities such as high pulse rate.

[0769] Step 9:

[0770] Situation assessment and forecasting

[0771] server

[0772] The server uses a generative AI model that predicts the likelihood of physical or mental illness based on the analysis results.

[0773] Input: Analysis results and generated AI model

[0774] Output: Prediction results of poor physical condition and mental downturn

[0775] How it works: The server uses the generated AI model to predict the user's stress level and physical condition abnormalities.

[0776] Step 10:

[0777] Proposal Generation

[0778] server

[0779] The server generates appropriate rest and meal suggestions based on the predicted risk.

[0780] Input: Prediction result

[0781] Output: Specific suggestions (resting methods and meal menu)

[0782] Specific behavior: The server generates a suggestion such as "You may be under high stress. Try meditating for 10 minutes."

[0783] Step 11:

[0784] Sending notifications

[0785] server

[0786] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[0787] Input: Proposal

[0788] Output: Notification message sent to the user

[0789] Specific operation: The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[0790] (Application example 1)

[0791] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0792] There is a need to appropriately monitor the physical and mental states of employees and prevent them from becoming ill or suffering from mental breakdowns. Security employees, in particular, need to be aware of their health status in real time and take appropriate measures, as abnormal physical or mental states directly affect the safety and efficiency of their work. However, current systems lack the ability to detect abnormalities in real time or propose specific countermeasures. Therefore, the objective of this invention is to accurately and quickly manage the physical and mental states of employees and provide appropriate warnings and advice.

[0793] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0794] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's responses, means for comparing and analyzing these data with big data, means for predicting poor physical condition or mental breakdown and generating appropriate rest and meal menu suggestions, means for notifying the user of the suggestions, and means for monitoring the physical and mental state of security employees in real time and detecting and warning of abnormalities. This makes it possible to monitor the physical and mental state of employees in real time and take prompt and appropriate measures if an abnormality is detected.

[0795] "Health data" is information related to the user's physical activity, and is data related to the user's health condition, including the amount of exercise, pulse rate, blood pressure, etc.

[0796] A "meal photo" is an image that visually records the meal a user has eaten, and is used to analyze the contents of the image to identify nutrients.

[0797] "Mental state" indicates the mental health state of the user, and refers to the state of mind and emotions.

[0798] "Big data" refers to large amounts of digital information that can be used to analyze data and detect anomalies.

[0799] "Comparative analysis" is a method for analyzing acquired data against large amounts of existing data, in order to identify abnormalities and trends.

[0800] "Poor health" refers to an abnormality in the user's physical activity or health condition, which interferes with the performance of normal business operations.

[0801] "Mental down" refers to a state in which the user's mental state is abnormal and the user is mentally unstable.

[0802] "Rest" refers to rest or activities that a user undertakes to refresh their body and mind and restore their health.

[0803] A "meal menu" refers to the combination of foods and menu items that a user will consume, and suggestions are made taking into consideration nutrient balance.

[0804] "Notification" refers to the transmission of information from the system to the user, including alerts and advice.

[0805] "Real-time" refers to the state in which data is collected, analyzed, and notified immediately, and processing is carried out without delay.

[0806] "Anomaly detection" is the process of discovering deviations from normal health or mental states, and is an important step in responding quickly.

[0807] A "warning" is a notification that alerts the user to a detected abnormality and urges the user to take appropriate action.

[0808] To implement the present invention, the system is configured as follows.

[0809] Hardware and software:

[0810] 1. Server:

[0811] Hardware: Cloud server (e.g. AWS, GCP)

[0812] software:

[0813] Health data APIs (e.g., HealthKit API)

[0814] Deep learning models (e.g. TensorFlow)

[0815] NLP analysis libraries (e.g. NLTK, spaCy)

[0816] Big data analysis tools (e.g., Apache Hadoop, Spark)

[0817] Notification API (e.g. Firebase Cloud Messaging)

[0818] 2. Terminal:

[0819] Hardware: Smartwatches, smartphone cameras

[0820] Software: Dedicated health management application

[0821] Detailed description of the process:

[0822] 1. Health Data Collection:

[0823] The server works in conjunction with the smartwatch or smartphone's healthcare application to collect daily health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, it uses an API to obtain the previous day's data at midnight.

[0824] For example, the server makes an API call like GET / health-data?date=2023-10-10 to retrieve data from the previous day.

[0825] 2. Analysis of food photographs:

[0826] When users upload photos of their meals to the app, the photos are sent to a server, which then analyzes them using a deep learning model to identify the ingredients and evaluate their nutritional value.

[0827] For example, when a user uploads a photo of their lunch to the app, the server analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[0828] 3. Mental state monitoring:

[0829] Users answer questions sent periodically to assess their mental state. The server collects the answers from users and performs text analysis to assess their mental state.

[0830] For example, if a message asking "How were you feeling today?" is sent via LINE at 8pm and the user replies "I'm pretty tired today," that information is analyzed on the server.

[0831] 4. Comparative analysis with big data:

[0832] The server compares the acquired data with existing big data to detect anomalies, and compares it with past data to track changes in health status.

[0833] As a specific example, the server compares data from the past month and detects that the recent pulse rate is abnormally high.

[0834] 5. Prediction and suggestions for physical and mental illness:

[0835] Based on the analysis results, the server predicts the possibility of poor physical or mental health and generates appropriate rest and meal recommendations. The advice is generated by an AI model.

[0836] As a specific example, the server predicts that the user is under high stress and generates a suggestion such as, "You may be under high stress. Try meditating for 10 minutes."

[0837] 6. User Notice:

[0838] The server notifies the user of the generated suggestions via app push notifications or messages.

[0839] As a specific example, a notification may appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[0840] An example prompt for a generative AI model would be:

[0841] The user's health data indicates high stress levels and fatigue. Please provide three appropriate health tips for this user:

[0842] 1. Relaxation techniques such as meditation and stretching

[0843] 2. Proposing nutritionally balanced meals

[0844] 3. Mental health advice

[0845] In this way, the "Security Guard Health Monitor" application becomes a powerful tool for maintaining optimal physical and mental health of security employees.

[0846] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0847] Step 1:

[0848] The server obtains the user's health data (such as exercise volume, pulse rate, and blood pressure) from the smartwatch or smartphone via API. As input, it receives the user ID and date and time information and sends an API request. As output, it receives the previous day's health data and stores it in a database.

[0849] Step 2:

[0850] Users upload photos of their meals to a dedicated app. As input, the app takes photos of the meal taken with a smartphone camera and sends them to the server. As output, the photo data is sent to the server, ready for analysis.

[0851] Step 3:

[0852] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained and evaluate the nutrients consumed. As input, the photo data of the meal is obtained and input into the AI ​​model. As output, the analysis results are obtained and nutritional information such as "carbohydrates, protein, fat" is stored in a database.

[0853] Step 4:

[0854] Users answer questions about their mental state that are periodically sent via LINE OA. As input, the system obtains the user's text responses on LINE OA. As output, the text responses are sent to the server.

[0855] Step 5:

[0856] The server analyzes the user's responses using a text analysis tool to evaluate their mental state. As input, it obtains the user's text responses and inputs them into an NLP analysis library. As output, it obtains the mental state evaluation results, and information such as "stress level" and "emotional state" is stored in a database.

[0857] Step 6:

[0858] The server uses a big data analysis tool to compare and analyze the collected health, nutritional, and mental state data with past data. Current user data and past big data are taken as input. Abnormal patterns and abnormal health status are detected as output, and the results are stored in a database.

[0859] Step 7:

[0860] The server uses an AI model to predict the likelihood of poor physical or mental health based on the comparative analysis results, and generates recommendations for appropriate rest and meal plans. The analysis results are input into the AI ​​model, and specific advice for the user is generated as output.

[0861] Step 8:

[0862] The server notifies the user of the generated suggestions via push notification or message to the user's smartphone. As input, it receives the suggestion content and the user information of the notification recipient. As output, a notification is displayed on the user's smartphone. For example, a notification may be displayed saying, "You seem tired today, so let's do some short stretches to relax."

[0863] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0864] The present invention is a system that monitors the physical condition, nutritional intake, and mental state of employees, and not only predicts poor physical condition or mental breakdown, but also recognizes the user's emotions, thereby achieving more accurate health management and maximizing performance. The system's program processing is described in detail below.

[0865] 1. Health Data Collection

[0866] server

[0867] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[0868] Specific examples

[0869] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[0870] 2. Analysis of food photos

[0871] Terminal

[0872] Users upload photos of their daily meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[0873] server

[0874] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[0875] Specific examples

[0876] A user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0877] 3. Mental state monitoring

[0878] User

[0879] Users answer questions about their mental state that are periodically sent by LINE OA. The questions are designed to assess the user's mental state.

[0880] server

[0881] The server collects responses from users and performs text analysis to assess their mental state.

[0882] Specific examples

[0883] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[0884] 4. Emotion Recognition by Emotion Engine

[0885] server

[0886] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[0887] Specific examples

[0888] If a user texts "I'm very happy today," the emotion engine will recognize this as a positive emotion.

[0889] 5. Comparative analysis of data and synthesis of results

[0890] server

[0891] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data recognized by the emotion engine with existing big data, thereby detecting abnormal values ​​and patterns and comprehensively assessing the user's health condition.

[0892] Specific examples

[0893] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[0894] 6. Predicting and suggesting physical and mental health issues

[0895] server

[0896] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[0897] Specific examples

[0898] The server predicts that User A is under a lot of stress and suggests that he "meditate for 10 minutes." It also suggests activities to increase positive emotions based on emotional data.

[0899] 7. User Notices

[0900] server

[0901] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[0902] Specific examples

[0903] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[0904] Through the above series of processes, the present invention not only manages employees' health status in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management. This system can prevent employees from becoming physically or mentally unwell, maximizing their performance.

[0905] The processing flow will be explained below.

[0906] Step 1:

[0907] server

[0908] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[0909] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[0910] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[0911] Specific examples

[0912] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[0913] Step 2:

[0914] Terminal

[0915] Users upload photos of their daily meals to a dedicated app.

[0916] The dedicated app has a camera function that allows users to take and send photos of their meals.

[0917] The photos are sent from the device to the server.

[0918] Specific examples

[0919] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[0920] Step 3:

[0921] server

[0922] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[0923] Using a deep learning model, it analyzes photos of meals and identifies the nutritional components (carbohydrates, proteins, fats, etc.) ingested.

[0924] Specific examples

[0925] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0926] Step 4:

[0927] User

[0928] Users answer questions about their mental state that are sent periodically by LINE OA.

[0929] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[0930] Specific examples

[0931] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[0932] Step 5:

[0933] server

[0934] The server collects the user's responses and performs text analysis to assess their mental state.

[0935] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[0936] Specific examples

[0937] The responses are analyzed and the stress level is classified as high, medium, or low.

[0938] Step 6:

[0939] server

[0940] The server uses an emotion engine that recognizes emotions from the user's voice and text input.

[0941] The emotion engine classifies the user's emotions into positive and negative, and integrates this into a mental state assessment.

[0942] Specific examples

[0943] If a user texts "I'm very happy today," the emotion engine will recognize this as positive.

[0944] Step 7:

[0945] server

[0946] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data with existing big data.

[0947] This allows for the detection of abnormal values ​​and patterns and a comprehensive assessment of the user's health status.

[0948] Specific examples

[0949] The server detects if the health data deviates from the average for the past month, and if the emotional data is negative, it assesses the overall health risk as high.

[0950] Step 8:

[0951] server

[0952] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[0953] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[0954] Specific examples

[0955] The server predicts that User A is in a high stress state and suggests that he or she "meditate for 10 minutes." It also suggests activities to increase positive emotions.

[0956] Step 9:

[0957] server

[0958] The server notifies the user of the generated proposal.

[0959] Notifications will be sent via app push notifications or LINE messages.

[0960] Specific examples

[0961] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax," and also includes a suggestion based on emotional data, "Let's refresh ourselves by listening to our favorite music."

[0962] Example 2

[0963] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0964] Employee health management requires preventing poor physical and mental health before they occur. However, conventional health management systems are limited to analyzing individual data points alone, making it difficult to evaluate overall health status. It is also difficult to provide personalized advice that reflects the user's emotional state. Therefore, there is a need for a system that can achieve more accurate health management and maximize performance.

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

[0966] In this invention, the server includes means for acquiring health data from users and storing the data in a database, means for receiving photos of meals taken by users and identifying nutrients using a deep learning model, means for performing text analysis based on the user's responses and monitoring the mental state, means for analyzing voice input and text input with an emotion engine and classifying the user's emotions, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating suggestions for appropriate rest and meal menus, and means for notifying the user of the suggestions. This makes it possible to manage employee health conditions in real time and provide accurate advice based on a comprehensive evaluation.

[0967] "Health data" refers to data relating to the user's physical condition, such as the user's amount of exercise, pulse rate, blood pressure, etc.

[0968] A "database" is a system for efficiently storing, managing, and searching acquired data.

[0969] A "meal photo" is an image of the ingredients and meal contents consumed by the user.

[0970] A "deep learning model" is an artificial intelligence technique that uses large data sets to extract features and perform classification.

[0971] "Nutrients" are substances such as proteins, carbohydrates, fats, vitamins, and minerals found in food.

[0972] "Text analysis" is a method of extracting meaning and emotion from user responses and sentences using natural language processing technology.

[0973] "Mental state" refers to the user's psychological health and stress level.

[0974] An "emotion engine" is an analysis system for identifying a user's emotions from voice and text data.

[0975] "Big data" refers to a large amount of data in a variety of formats, and analyzing this data can provide new information and insights.

[0976] "Comparative analysis" is a technique for comparing multiple data sets to find specific patterns or anomalies.

[0977] "Poor physical condition" refers to a state in which the user is unable to maintain normal bodily functions.

[0978] "Mental down" refers to a user's mental state deteriorating due to psychological fatigue or stress.

[0979] "Suggestions" are specific advice about behaviors and diets generated based on the user's health status.

[0980] "Notification" is a communication method for presenting information or suggestions from the server to the user.

[0981] The system of the present invention is designed to monitor employees' physical condition, nutritional intake, and mental state in real time and to predict poor physical and mental health before they occur. This system aims to maximize employee performance. Specific embodiments of the system are described below.

[0982] The system consists of a server, a user's device, and a dedicated AI model.

[0983] The server works with the healthcare application installed on the user's smartwatch or smartphone to collect health data. Specifically, data such as exercise volume, pulse rate, and blood pressure is collected periodically every day. For example, the server executes an API request (GET / health-data?date=<previous day's date>) at midnight every night to retrieve the previous day's health data.

[0984] Users take and upload photos of their daily meals using a dedicated app. The uploaded photos are sent to a server and analyzed using a deep learning model. This model identifies the ingredients in the photo and evaluates their nutritional value. For example, a user can take a photo of their lunch and send it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[0985] The server also periodically sends questions to employees using LINE OA to monitor their mental state. For example, at 8 p.m., a message asking "How were you feeling today?" is sent to the user's LINE. If the user replies "I'm pretty tired today," the server analyzes the text and converts it into a score to evaluate their mental state.

[0986] Furthermore, the server is integrated with an emotion engine that recognizes emotions from voice and text input. This engine analyzes the user's input and classifies emotions as positive, negative, etc. For example, if you enter the text "I'm very happy today," the server will input this into the emotion engine and recognize it as a positive emotion.

[0987] The server centrally manages the acquired health, nutrition, mental state, and emotional data, and compares and analyzes it with big data. It can detect abnormal values ​​and patterns by comparing it with data from the past month and standard data. For example, if the pulse rate is higher than normal or the emotional data is negative, it will assess the overall state of high stress.

[0988] Finally, the server predicts the possibility of poor physical or mental health based on the analysis results and generates recommendations for appropriate rest, meal options, etc. For example, it may generate specific suggestions such as "Try meditating for 10 minutes" and notify the user via push notification or LINE message.

[0989] In this way, the present invention is built by combining a server, user devices, a dedicated application, and a deep learning model. This system can comprehensively monitor employees' health status and provide prompt and appropriate advice.

[0990] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0991] Step 1:

[0992] Acquisition of health data

[0993] server

[0994] The server works with the healthcare application installed on the smartwatch or smartphone to collect the user's health data. Specifically, it executes an API request GET / health-data?date=<previous day's date> every night at midnight to obtain the previous day's exercise amount, pulse rate, and blood pressure data. The input is the response data to the API request from the health app, and the output is the health data stored in the database. The collected data is stored in the database and validated to ensure data integrity and consistency.

[0995] Step 2:

[0996] Upload a meal photo

[0997] User

[0998] Users take photos of their daily meals using a dedicated app and upload them. The input is the photo of the meal taken by the user, and the output is image data sent to the server. The photo is sent to the endpoint POST / upload-photo, and is sent when the user selects a photo in the app and presses the upload button.

[0999] Step 3:

[1000] Food photo analysis

[1001] server

[1002] The server analyzes the received meal photos using a deep learning model. This model identifies the ingredients contained in the photos and evaluates their nutritional value. The input is the meal photo uploaded by the user, and the output is the analyzed nutritional information. Specifically, the server inputs the photo into the deep learning model and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[1003] Step 4:

[1004] Mental state monitoring

[1005] Server, User

[1006] At 8 p.m., the server sends the user a message via LINE OA asking, "How were you feeling today?" The input is the question in the LINE message, and the output is the user's answer. If the user answers, "I'm pretty tired today," the answer data is sent to the server, which performs text analysis. Specifically, the server analyzes the text using natural language processing technology and generates a score to evaluate the user's mental state.

[1007] Step 5:

[1008] Emotion recognition

[1009] server

[1010] The server uses an emotion engine that recognizes emotions from the user's voice or text input. The input is the user's voice or text data, and the output is emotion data categorized as positive, negative, etc. For example, if the user inputs the text "I'm very happy today," the server inputs that text into the emotion engine and recognizes it as a positive emotion.

[1011] Step 6:

[1012] Comparative analysis of data and synthesis of results

[1013] server

[1014] The server collects and centrally manages the acquired health, nutritional, mental state, and emotional data. The input is a collection of various data, and the output is the integrated analysis results. Specifically, the server compares and analyzes this data with past data and standard big data to detect abnormal values ​​and patterns. For example, it compares pulse rate data from the past month with the latest data to detect abnormally high values, and if the emotional data is negative, it evaluates the overall state as high stress.

[1015] Step 7:

[1016] Prediction and suggestions for poor physical and mental health

[1017] server

[1018] The server uses an AI model to predict the possibility of poor physical or mental health. The input is the integrated analysis data, and the output is specific suggestions. Specifically, the server inputs data into the AI ​​model and generates specific suggestions, such as "Meditate for 10 minutes" or "Do some short stretches for relaxation."

[1019] Step 8:

[1020] User Notification

[1021] server

[1022] The server notifies the user of the generated suggestions. The input is the generated suggestions, and the output is the notification to the user. The notification is sent via push notification or LINE message. For example, a message saying "You seem tired today, so try doing a short stretch to relax" is sent to the user's smartphone. This notification also includes suggestions based on the results of the emotion engine, such as "Refresh yourself with your favorite music."

[1023] (Application example 2)

[1024] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1025] The purpose of this invention is to prevent poor physical and mental health by efficiently monitoring the physical and mental state of employees, and to maximize performance by suggesting appropriate rest and meal plans at the right time. In particular, by introducing emotion recognition functionality to security service staff, the purpose is to achieve more effective health management and improved service quality in situations where a quick response is required.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1027] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's answers, means for recognizing emotions from the user's voice input or text input, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating appropriate rest and meal menu suggestions, and means for notifying the user of the suggestions. This enables more accurate and comprehensive health management of employees, real-time evaluation of their health condition, and timely and appropriate suggestions to be made.

[1028] "Health data" refers to biometric information such as the user's amount of exercise, pulse rate, blood pressure, etc.

[1029] "Nutrition data" refers to information about the nutritional composition of the food a user has eaten, analyzed.

[1030] "Mental state data" refers to information for assessing the psychological state of a user.

[1031] "Emotion data" refers to emotional information recognized based on a user's voice or text input.

[1032] "Big data" refers to technology for processing and analyzing large amounts of data at high speed.

[1033] "Comparative analysis" refers to the process of comparing multiple data sets and analyzing their differences and commonalities.

[1034] "Predicting poor health" refers to the process of predicting the likelihood of a user experiencing poor health in the future based on the user's health data and mental state data.

[1035] "Mental down prediction" refers to a process of predicting the possibility of a mentally unstable state occurring in the future based on the user's mental state data and emotion data.

[1036] "Suggestion generation" refers to the process of recommending appropriate rest, meal plans, and other actions to the user based on the predicted results.

[1037] "Notification means" refers to the method or device used to notify the user of the generated suggestions.

[1038] MODE FOR CARRYING OUT THE INVENTION

[1039] The present invention is a system for managing the physical condition and optimizing the performance of employees and users. The system comprehensively analyzes health data, nutritional data, mental state data, and emotional data, generates appropriate suggestions, and notifies the user. The following describes in detail the embodiments of the present invention.

[1040] 1. Health Data Collection

[1041] server

[1042] The server works with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. The server executes an API request every night at midnight to obtain the previous day's health data.

[1043] Specific examples

[1044] The server executes the API request "GET / health-data?date=2023-10-10" every night at midnight to retrieve health data.

[1045] 2. Analysis of food photos

[1046] Terminal

[1047] Users use a specific application to take photos of their daily meals and upload them to a server, which then uses deep learning models to identify ingredients and analyze their nutritional content.

[1048] server

[1049] The server uses AI to analyze the received meal photos, identify the ingredients contained in the photos, and evaluate the proportions of nutrients.

[1050] Specific examples

[1051] The user takes a photo of their lunch using a dedicated app and sends it via "POST / upload-photo." The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1052] 3. Mental state monitoring

[1053] User

[1054] Users report their mental state by answering questions that are sent periodically, for example via messaging apps such as LINE.

[1055] server

[1056] The server receives the user's answers and performs natural language analysis to assess the mental state.

[1057] Specific examples

[1058] At 8pm, a message is sent to the user asking "How were you feeling today?" If the user replies "I'm pretty tired today," the information is analyzed on the server.

[1059] 4. Emotion Recognition by Emotion Engine

[1060] server

[1061] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[1062] Specific examples

[1063] If the user texts "I'm very happy today," the server recognizes this as a positive emotion.

[1064] 5. Comparative analysis of data and synthesis of results

[1065] server

[1066] The server integrates the acquired health, nutrition, mental state, and emotional data and compares and analyzes it with big data to detect abnormal values ​​and patterns and comprehensively evaluate the user's health condition.

[1067] Specific examples

[1068] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[1069] 6. Predicting and suggesting physical and mental health issues

[1070] server

[1071] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[1072] Specific examples

[1073] The server predicts that the user is under high stress and suggests that they "take 10 minutes of meditation." It also suggests activities to increase positive emotions based on emotional data.

[1074] 7. User Notices

[1075] server

[1076] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[1077] Specific examples

[1078] The server sends a notification to the user's device saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[1079] Prompt Sentence Examples

[1080] 1. Health data collection:

[1081] Get your health data.

[1082] 2. Mental state monitoring:

[1083] How were you feeling today?

[1084] As described above, the present invention not only manages the health status of employees and users in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management, thereby preventing employees from becoming physically or mentally unwell and maximizing their performance.

[1085] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1086] Step 1:

[1087] Health Data Collection

[1088] The server works in conjunction with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, the server executes an API request every night at midnight to obtain the previous day's health data.

[1089] Input: API request (e.g. "GET / health-data?date=2023-10-10")

[1090] Data processing: Formatting data obtained from healthcare applications and storing it in a database

[1091] Output: Stored health data (e.g., exercise amount, pulse rate, blood pressure)

[1092] Step 2:

[1093] Food photo analysis

[1094] The device allows users to take photos of their meals using a dedicated app and upload them to a server, which then analyzes the photos using a deep learning model to identify the ingredients in the photo and evaluate their nutritional value.

[1095] Input: Uploaded food photo (e.g. "POST / upload-photo")

[1096] Data processing: Analyze photos using a deep learning model to extract information about ingredients and nutrients

[1097] Output: Analyzed nutritional data (e.g., carbohydrates 50g, protein 30g, fat 20g)

[1098] Step 3:

[1099] Mental state monitoring

[1100] Users answer questions sent periodically via messaging apps such as LINE. The server receives the user's answers and performs natural language analysis to evaluate their mental state.

[1101] Input: Answer about the user's mental state (e.g., "I'm pretty tired today")

[1102] Data processing: Evaluate users' responses using natural language processing to generate mental state data

[1103] Output: Mental state data (e.g., fatigue level, stress level)

[1104] Step 4:

[1105] Emotion recognition by emotion engine

[1106] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[1107] Input: Voice or text input from the user (e.g., "I'm very happy today")

[1108] Data processing: Analyze input data using an emotion engine to generate emotion data

[1109] Output: Emotion data (e.g., positive, negative)

[1110] Step 5:

[1111] Comparative analysis of data and synthesis of results

[1112] The server compares the acquired health, nutrition, mental state, and emotional data with past data and big data, detects abnormal values ​​and patterns, and comprehensively evaluates the user's health condition.

[1113] Input: Health data, nutrition data, mental state data, emotional data

[1114] Data processing: Matching with big data and analyzing it to detect outliers and patterns

[1115] Output: Comprehensive health assessment data (e.g., high stress levels, nutritional imbalances)

[1116] Step 6:

[1117] Prediction and suggestions for poor physical and mental health

[1118] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[1119] Input: Health assessment data

[1120] Data processing: Using AI models to predict risks and generate specific recommendations

[1121] Output: Suggestions (e.g., 10 minutes of meditation, stretches to relax)

[1122] Step 7:

[1123] User Notifications

[1124] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[1125] Input: Proposal

[1126] Data processing: Converting the data into notification format and sending it to the user's device

[1127] Output: User notification (e.g., "You seem tired today, let's do some short stretches for relaxation")

[1128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1129] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1130] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1131] [Third embodiment]

[1132] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1133] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1135] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1136] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1139] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1140] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1142] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1143] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1144] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. The program processing of the system is explained in detail below.

[1145] 1. Health Data Collection

[1146] server

[1147] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[1148] Specific examples

[1149] The server makes an API call such as GET / health-data?date=2023-10-10 to retrieve data for the previous day.

[1150] 2. Analysis of food photos

[1151] Terminal

[1152] Users upload photos of their meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[1153] server

[1154] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[1155] Specific examples

[1156] When a user uploads a photo of their lunch to the app, it is sent to a server, which analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[1157] 3. Mental state monitoring

[1158] User

[1159] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[1160] server

[1161] The server collects responses from users and performs text analysis to assess their mental state.

[1162] Specific examples

[1163] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[1164] 4. Comparative analysis with big data

[1165] server

[1166] The server compares the acquired data with existing big data and performs analysis to check for any abnormalities. It also refers to past data to track changes in health status.

[1167] Specific examples

[1168] The server compares the data from the past month and detects that the recent pulse rate is abnormally high.

[1169] 5. Predicting and suggesting physical and mental health issues

[1170] server

[1171] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates appropriate rest and meal suggestions according to the predicted risk.

[1172] Specific examples

[1173] The server predicts that User A is under high stress and generates a suggestion that says, "You may be under high stress. Try meditating for 10 minutes."

[1174] 6. User Notices

[1175] server

[1176] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[1177] Specific examples

[1178] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[1179] Through the above series of processes, the present invention can manage the health status of employees in real time and provide optimal advice at the right time, thereby preventing physical and mental illnesses from occurring, thereby maximizing employee performance.

[1180] The processing flow will be explained below.

[1181] Step 1:

[1182] server

[1183] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[1184] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[1185] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[1186] Specific examples

[1187] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[1188] Step 2:

[1189] Terminal

[1190] Users upload photos of their daily meals to a dedicated app.

[1191] The dedicated app has a camera function that allows users to take and send photos of their meals.

[1192] The photos are sent from the device to the server.

[1193] Specific examples

[1194] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[1195] Step 3:

[1196] server

[1197] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[1198] Deep learning models are used to analyze food photos and identify the nutritional components ingested (e.g., carbohydrates, proteins, fats, etc.).

[1199] Specific examples

[1200] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1201] Step 4:

[1202] User

[1203] Users answer questions about their mental state that are sent periodically by LINE OA.

[1204] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[1205] Specific examples

[1206] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[1207] Step 5:

[1208] server

[1209] The server collects the user's responses and performs text analysis to assess their mental state.

[1210] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[1211] Specific examples

[1212] The responses are analyzed and the stress level is classified as high, medium, or low.

[1213] Step 6:

[1214] server

[1215] The server compares and analyzes the acquired health data, nutritional data, and mental state data with existing big data.

[1216] This allows abnormal values ​​and patterns to be detected and the user's health status to be assessed.

[1217] Specific examples

[1218] The server compares the recent pulse rate with data from the past month and detects that it is abnormally high.

[1219] Step 7:

[1220] server

[1221] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[1222] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[1223] Specific examples

[1224] It predicts that user A is under a lot of stress and suggests that they "meditate for 10 minutes."

[1225] Step 8:

[1226] server

[1227] The server notifies the user of the generated proposal.

[1228] Notifications will be sent via app push notifications or LINE messages.

[1229] Specific examples

[1230] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[1231] Example 1

[1232] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1233] In modern society, employee health management has become an important issue. However, many companies find it difficult to monitor employees' physical and mental health in real time and provide necessary advice at the appropriate time. As a result, poor physical and mental health cannot be prevented, leading to problems such as a decline in employee performance and increased absenteeism. With conventional methods, individual health data, dietary information, and mental state monitoring are not managed centrally, making it difficult to grasp a comprehensive health status and make appropriate recommendations.

[1234] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1235] In this invention, the server includes a means for acquiring health data from users, a means for receiving images of meals taken by users and identifying nutrients, and a means for monitoring mental states based on users' responses. This makes it possible to grasp employees' health and mental states in real time and provide necessary advice at appropriate times.

[1236] "Health data" refers to physiological information such as the user's exercise volume, heart rate, and blood pressure.

[1237] A "meal image" refers to a photograph of a meal taken by a user, which includes information for identifying the contents and nutrients of the meal.

[1238] "Means for identifying nutrients" refers to the technology or method used by the server to analyze the image of the meal received and identify the ingredients and their nutritional components.

[1239] "Means for monitoring mental state" refers to methods or systems for evaluating and monitoring a user's mental health state by performing text analysis based on the user's answers and input data.

[1240] "Big data" refers to a wide range of existing data sets that can be compared to assess health and mental health.

[1241] "Suggesting rest and meal menus" refers to providing advice on appropriate rest methods and meal contents based on the user's current health, nutritional, and mental state.

[1242] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. This system includes the following components:

[1243] 1. Health Data Collection

[1244] server

[1245] The server works with the health care application on the smartwatch or smartphone to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, heart rate, and blood pressure every day. This data is obtained via an API. For example, at midnight, the previous day's data is obtained in the form of GET / health-data?date=2023-10-10.

[1246] 2. Analysis of food photos

[1247] Terminal

[1248] Using a dedicated app, users take pictures of their meals and upload them, which are then sent to a server.

[1249] server

[1250] The server uses a deep learning model to analyze the received meal images, identify the ingredients contained in the image, and evaluate the nutritional value. Specifically, when a user uploads a photo of their lunch to the app, it is sent to the server. The server analyzes the photo and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[1251] 3. Mental state monitoring

[1252] User

[1253] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[1254] server

[1255] The server collects the user's responses and performs text analysis to evaluate their mental state. For example, if a user receives a message on LINE at 8 p.m. asking, "How were you feeling today?" and the user replies, "I'm pretty tired today," the information is analyzed by the server.

[1256] 4. Comparative analysis with big data

[1257] server

[1258] The server compares the acquired data with a large amount of existing data and performs analysis. This checks for any abnormalities. It also refers to past data to track changes in health status. For example, the server compares data from the past month and detects that a recent heart rate is abnormally high.

[1259] 5. Predicting and suggesting physical and mental health issues

[1260] server

[1261] The server uses a generative AI model to predict the possibility of poor physical condition or mental breakdown based on the analysis results. Depending on the predicted risk, it generates appropriate rest and meal suggestions. For example, the server predicts that User A is in a high stress state and generates a suggestion such as, "You may be in a high stress state. Try meditating for 10 minutes."

[1262] 6. User Notices

[1263] server

[1264] The server notifies the user of the generated suggestions. The notification is sent via a push notification or a LINE message. Specifically, a notification will appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[1265] In this way, the present invention manages employees' health status in real time and provides optimal advice at the right time, thereby preventing physical and mental illness and maximizing employee performance.

[1266] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1267] Step 1:

[1268] Health Data Requests

[1269] server

[1270] Every day at midnight, the server requests health data from the health care application on the user's smartwatch or smartphone. Specifically, it obtains data such as the amount of exercise, heart rate, and blood pressure from the previous day via an API.

[1271] Input: API call GET / health-data?date=2023-10-10

[1272] Output: Health data (exercise volume, heart rate, blood pressure)

[1273] Specific operation: The server sends an API request at the specified date and time to request health data.

[1274] Step 2:

[1275] Receiving and storing health data

[1276] server

[1277] The server receives the acquired health data and stores it in a database for later analysis and comparison.

[1278] Input: Health data as API response

[1279] Output: Health data stored in a database

[1280] Specific operation: The server analyzes the received data and records it in a database.

[1281] Step 3:

[1282] Upload a meal photo

[1283] Terminal

[1284] Users use a dedicated app to take pictures of their meals and upload them.

[1285] Input: Food image (user-taken photo)

[1286] Output: Image file sent to the server

[1287] Specific operation: The user selects a photo of a meal from the dedicated app and presses the "Upload" button.

[1288] Step 4:

[1289] Receiving meal photos

[1290] server

[1291] The server receives the uploaded food images and prepares them for analysis.

[1292] Input: Image file sent by the user

[1293] Output: Meal images saved in temporary storage

[1294] Specific operation: The server receives the image file and temporarily stores it.

[1295] Step 5:

[1296] Ingredient and nutrient analysis

[1297] server

[1298] The server uses deep learning models to analyze the received photos, identify the ingredients in the photos, and assess their nutritional value.

[1299] Input: Food images stored in temporary storage

[1300] Output: Analysis results (carbohydrates 50g, protein 30g, fat 20g, etc.)

[1301] Specific operation: The server invokes the deep learning model to extract nutritional information from the image.

[1302] Step 6:

[1303] Submit a mental health question

[1304] server

[1305] The server periodically sends questions to the user via LINE OA to assess their mental state.

[1306] Input: Fixed message "How were you feeling today?"

[1307] Output: The question message sent to the user

[1308] Specific operation: The server sends a LINE message to the user at 8pm.

[1309] Step 7:

[1310] Receiving and processing responses

[1311] server

[1312] The server collects responses from users and performs text analysis to assess their mental state.

[1313] Input: User response text, e.g. "I'm pretty tired today"

[1314] Output: Mental state evaluation results

[1315] Specific operation: The server analyzes the received text and evaluates the mental state.

[1316] Step 8:

[1317] Data collection and comparison

[1318] server

[1319] The server compares the collected health and mental status data with a large amount of existing data to check for abnormalities, and also refers to past data to track changes in health status.

[1320] Input: Collected data and existing bulk data

[1321] Output: Analysis results (no anomalies, anomalies detected, etc.)

[1322] Specific operation: The server compares data from the past month and detects abnormalities such as high pulse rate.

[1323] Step 9:

[1324] Situation assessment and forecasting

[1325] server

[1326] The server uses a generative AI model that predicts the likelihood of physical or mental illness based on the analysis results.

[1327] Input: Analysis results and generated AI model

[1328] Output: Prediction results of poor physical condition and mental downturn

[1329] How it works: The server uses the generated AI model to predict the user's stress level and physical condition abnormalities.

[1330] Step 10:

[1331] Proposal Generation

[1332] server

[1333] The server generates appropriate rest and meal suggestions based on the predicted risk.

[1334] Input: Prediction result

[1335] Output: Specific suggestions (resting methods and meal menu)

[1336] Specific behavior: The server generates a suggestion such as "You may be under high stress. Try meditating for 10 minutes."

[1337] Step 11:

[1338] Sending notifications

[1339] server

[1340] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[1341] Input: Proposal

[1342] Output: Notification message sent to the user

[1343] Specific operation: The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[1344] (Application example 1)

[1345] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1346] There is a need to appropriately monitor the physical and mental states of employees and prevent them from becoming ill or suffering from mental breakdowns. Security employees, in particular, need to be aware of their health status in real time and take appropriate measures, as abnormal physical or mental states directly affect the safety and efficiency of their work. However, current systems lack the ability to detect abnormalities in real time or propose specific countermeasures. Therefore, the objective of this invention is to accurately and quickly manage the physical and mental states of employees and provide appropriate warnings and advice.

[1347] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1348] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's responses, means for comparing and analyzing these data with big data, means for predicting poor physical condition or mental breakdown and generating appropriate rest and meal menu suggestions, means for notifying the user of the suggestions, and means for monitoring the physical and mental state of security employees in real time and detecting and warning of abnormalities. This makes it possible to monitor the physical and mental state of employees in real time and take prompt and appropriate measures if an abnormality is detected.

[1349] "Health data" is information related to the user's physical activity, and is data related to the user's health condition, including the amount of exercise, pulse rate, blood pressure, etc.

[1350] A "meal photo" is an image that visually records the meal a user has eaten, and is used to analyze the contents of the image to identify nutrients.

[1351] "Mental state" indicates the mental health state of the user, and refers to the state of mind and emotions.

[1352] "Big data" refers to large amounts of digital information that can be used to analyze data and detect anomalies.

[1353] "Comparative analysis" is a method for analyzing acquired data against large amounts of existing data, in order to identify abnormalities and trends.

[1354] "Poor health" refers to an abnormality in the user's physical activity or health condition, which interferes with the performance of normal business operations.

[1355] "Mental down" refers to a state in which the user's mental state is abnormal and the user is mentally unstable.

[1356] "Rest" refers to rest or activities that a user undertakes to refresh their body and mind and restore their health.

[1357] A "meal menu" refers to the combination of foods and menu items that a user will consume, and suggestions are made taking into consideration nutrient balance.

[1358] "Notification" refers to the transmission of information from the system to the user, including alerts and advice.

[1359] "Real-time" refers to the state in which data is collected, analyzed, and notified immediately, and processing is carried out without delay.

[1360] "Anomaly detection" is the process of discovering deviations from normal health or mental states, and is an important step in responding quickly.

[1361] A "warning" is a notification that alerts the user to a detected abnormality and urges the user to take appropriate action.

[1362] To implement the present invention, the system is configured as follows.

[1363] Hardware and software:

[1364] 1. Server:

[1365] Hardware: Cloud server (e.g. AWS, GCP)

[1366] software:

[1367] Health data APIs (e.g., HealthKit API)

[1368] Deep learning models (e.g. TensorFlow)

[1369] NLP analysis libraries (e.g. NLTK, spaCy)

[1370] Big data analysis tools (e.g., Apache Hadoop, Spark)

[1371] Notification API (e.g. Firebase Cloud Messaging)

[1372] 2. Terminal:

[1373] Hardware: Smartwatches, smartphone cameras

[1374] Software: Dedicated health management application

[1375] Detailed description of the process:

[1376] 1. Health Data Collection:

[1377] The server works in conjunction with the smartwatch or smartphone's healthcare application to collect daily health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, it uses an API to obtain the previous day's data at midnight.

[1378] For example, the server makes an API call like GET / health-data?date=2023-10-10 to retrieve data from the previous day.

[1379] 2. Analysis of food photographs:

[1380] When users upload photos of their meals to the app, the photos are sent to a server, which then analyzes them using a deep learning model to identify the ingredients and evaluate their nutritional value.

[1381] For example, when a user uploads a photo of their lunch to the app, the server analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[1382] 3. Mental state monitoring:

[1383] Users answer questions sent periodically to assess their mental state. The server collects the answers from users and performs text analysis to assess their mental state.

[1384] For example, if a message asking "How were you feeling today?" is sent via LINE at 8pm and the user replies "I'm pretty tired today," that information is analyzed on the server.

[1385] 4. Comparative analysis with big data:

[1386] The server compares the acquired data with existing big data to detect anomalies, and compares it with past data to track changes in health status.

[1387] As a specific example, the server compares data from the past month and detects that the recent pulse rate is abnormally high.

[1388] 5. Prediction and suggestions for physical and mental illness:

[1389] Based on the analysis results, the server predicts the possibility of poor physical or mental health and generates appropriate rest and meal recommendations. The advice is generated by an AI model.

[1390] As a specific example, the server predicts that the user is under high stress and generates a suggestion such as, "You may be under high stress. Try meditating for 10 minutes."

[1391] 6. User Notice:

[1392] The server notifies the user of the generated suggestions via app push notifications or messages.

[1393] As a specific example, a notification may appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[1394] An example prompt for a generative AI model would be:

[1395] The user's health data indicates high stress levels and fatigue. Please provide three appropriate health tips for this user:

[1396] 1. Relaxation techniques such as meditation and stretching

[1397] 2. Proposing nutritionally balanced meals

[1398] 3. Mental health advice

[1399] In this way, the "Security Guard Health Monitor" application becomes a powerful tool for maintaining optimal physical and mental health of security employees.

[1400] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1401] Step 1:

[1402] The server obtains the user's health data (such as exercise volume, pulse rate, and blood pressure) from the smartwatch or smartphone via API. As input, it receives the user ID and date and time information and sends an API request. As output, it receives the previous day's health data and stores it in a database.

[1403] Step 2:

[1404] Users upload photos of their meals to a dedicated app. As input, the app takes photos of the meal taken with a smartphone camera and sends them to the server. As output, the photo data is sent to the server, ready for analysis.

[1405] Step 3:

[1406] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained and evaluate the nutrients consumed. As input, the photo data of the meal is obtained and input into the AI ​​model. As output, the analysis results are obtained and nutritional information such as "carbohydrates, protein, fat" is stored in a database.

[1407] Step 4:

[1408] Users answer questions about their mental state that are periodically sent via LINE OA. As input, the system obtains the user's text responses on LINE OA. As output, the text responses are sent to the server.

[1409] Step 5:

[1410] The server analyzes the user's responses using a text analysis tool to evaluate their mental state. As input, it obtains the user's text responses and inputs them into an NLP analysis library. As output, it obtains the mental state evaluation results, and information such as "stress level" and "emotional state" is stored in a database.

[1411] Step 6:

[1412] The server uses a big data analysis tool to compare and analyze the collected health, nutritional, and mental state data with past data. Current user data and past big data are taken as input. Abnormal patterns and abnormal health status are detected as output, and the results are stored in a database.

[1413] Step 7:

[1414] The server uses an AI model to predict the likelihood of poor physical or mental health based on the comparative analysis results, and generates recommendations for appropriate rest and meal plans. The analysis results are input into the AI ​​model, and specific advice for the user is generated as output.

[1415] Step 8:

[1416] The server notifies the user of the generated suggestions via push notification or message to the user's smartphone. As input, it receives the suggestion content and the user information of the notification recipient. As output, a notification is displayed on the user's smartphone. For example, a notification may be displayed saying, "You seem tired today, so let's do some short stretches to relax."

[1417] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1418] The present invention is a system that monitors the physical condition, nutritional intake, and mental state of employees, and not only predicts poor physical condition or mental breakdown, but also recognizes the user's emotions, thereby achieving more accurate health management and maximizing performance. The system's program processing is described in detail below.

[1419] 1. Health Data Collection

[1420] server

[1421] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[1422] Specific examples

[1423] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[1424] 2. Analysis of food photos

[1425] Terminal

[1426] Users upload photos of their daily meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[1427] server

[1428] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[1429] Specific examples

[1430] A user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1431] 3. Mental state monitoring

[1432] User

[1433] Users answer questions about their mental state that are periodically sent by LINE OA. The questions are designed to assess the user's mental state.

[1434] server

[1435] The server collects responses from users and performs text analysis to assess their mental state.

[1436] Specific examples

[1437] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[1438] 4. Emotion Recognition by Emotion Engine

[1439] server

[1440] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[1441] Specific examples

[1442] If a user texts "I'm very happy today," the emotion engine will recognize this as a positive emotion.

[1443] 5. Comparative analysis of data and synthesis of results

[1444] server

[1445] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data recognized by the emotion engine with existing big data, thereby detecting abnormal values ​​and patterns and comprehensively assessing the user's health condition.

[1446] Specific examples

[1447] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[1448] 6. Predicting and suggesting physical and mental health issues

[1449] server

[1450] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[1451] Specific examples

[1452] The server predicts that User A is under a lot of stress and suggests that he "meditate for 10 minutes." It also suggests activities to increase positive emotions based on emotional data.

[1453] 7. User Notices

[1454] server

[1455] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[1456] Specific examples

[1457] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[1458] Through the above series of processes, the present invention not only manages employees' health status in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management. This system can prevent employees from becoming physically or mentally unwell, maximizing their performance.

[1459] The processing flow will be explained below.

[1460] Step 1:

[1461] server

[1462] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[1463] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[1464] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[1465] Specific examples

[1466] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[1467] Step 2:

[1468] Terminal

[1469] Users upload photos of their daily meals to a dedicated app.

[1470] The dedicated app has a camera function that allows users to take and send photos of their meals.

[1471] The photos are sent from the device to the server.

[1472] Specific examples

[1473] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[1474] Step 3:

[1475] server

[1476] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[1477] Using a deep learning model, it analyzes photos of meals and identifies the nutritional components (carbohydrates, proteins, fats, etc.) ingested.

[1478] Specific examples

[1479] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1480] Step 4:

[1481] User

[1482] Users answer questions about their mental state that are sent periodically by LINE OA.

[1483] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[1484] Specific examples

[1485] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[1486] Step 5:

[1487] server

[1488] The server collects the user's responses and performs text analysis to assess their mental state.

[1489] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[1490] Specific examples

[1491] The responses are analyzed and the stress level is classified as high, medium, or low.

[1492] Step 6:

[1493] server

[1494] The server uses an emotion engine that recognizes emotions from the user's voice and text input.

[1495] The emotion engine classifies the user's emotions into positive and negative, and integrates this into a mental state assessment.

[1496] Specific examples

[1497] If a user texts "I'm very happy today," the emotion engine will recognize this as positive.

[1498] Step 7:

[1499] server

[1500] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data with existing big data.

[1501] This allows for the detection of abnormal values ​​and patterns and a comprehensive assessment of the user's health status.

[1502] Specific examples

[1503] The server detects if the health data deviates from the average for the past month, and if the emotional data is negative, it assesses the overall health risk as high.

[1504] Step 8:

[1505] server

[1506] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[1507] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[1508] Specific examples

[1509] The server predicts that User A is in a high stress state and suggests that he or she "meditate for 10 minutes." It also suggests activities to increase positive emotions.

[1510] Step 9:

[1511] server

[1512] The server notifies the user of the generated proposal.

[1513] Notifications will be sent via app push notifications or LINE messages.

[1514] Specific examples

[1515] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax," and also includes a suggestion based on emotional data, "Let's refresh ourselves by listening to our favorite music."

[1516] Example 2

[1517] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1518] Employee health management requires preventing poor physical and mental health before they occur. However, conventional health management systems are limited to analyzing individual data points alone, making it difficult to evaluate overall health status. It is also difficult to provide personalized advice that reflects the user's emotional state. Therefore, there is a need for a system that can achieve more accurate health management and maximize performance.

[1519] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1520] In this invention, the server includes means for acquiring health data from users and storing the data in a database, means for receiving photos of meals taken by users and identifying nutrients using a deep learning model, means for performing text analysis based on the user's responses and monitoring the mental state, means for analyzing voice input and text input with an emotion engine and classifying the user's emotions, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating suggestions for appropriate rest and meal menus, and means for notifying the user of the suggestions. This makes it possible to manage employee health conditions in real time and provide accurate advice based on a comprehensive evaluation.

[1521] "Health data" refers to data relating to the user's physical condition, such as the user's amount of exercise, pulse rate, blood pressure, etc.

[1522] A "database" is a system for efficiently storing, managing, and searching acquired data.

[1523] A "meal photo" is an image of the ingredients and meal contents consumed by the user.

[1524] A "deep learning model" is an artificial intelligence technique that uses large data sets to extract features and perform classification.

[1525] "Nutrients" are substances such as proteins, carbohydrates, fats, vitamins, and minerals found in food.

[1526] "Text analysis" is a method of extracting meaning and emotion from user responses and sentences using natural language processing technology.

[1527] "Mental state" refers to the user's psychological health and stress level.

[1528] An "emotion engine" is an analysis system for identifying a user's emotions from voice and text data.

[1529] "Big data" refers to a large amount of data in a variety of formats, and analyzing this data can provide new information and insights.

[1530] "Comparative analysis" is a technique for comparing multiple data sets to find specific patterns or anomalies.

[1531] "Poor physical condition" refers to a state in which the user is unable to maintain normal bodily functions.

[1532] "Mental down" refers to a user's mental state deteriorating due to psychological fatigue or stress.

[1533] "Suggestions" are specific advice about behaviors and diets generated based on the user's health status.

[1534] "Notification" is a communication method for presenting information or suggestions from the server to the user.

[1535] The system of the present invention is designed to monitor employees' physical condition, nutritional intake, and mental state in real time and to predict poor physical and mental health before they occur. This system aims to maximize employee performance. Specific embodiments of the system are described below.

[1536] The system consists of a server, a user's device, and a dedicated AI model.

[1537] The server works with the healthcare application installed on the user's smartwatch or smartphone to collect health data. Specifically, data such as exercise volume, pulse rate, and blood pressure is collected periodically every day. For example, the server executes an API request (GET / health-data?date=<previous day's date>) at midnight every night to retrieve the previous day's health data.

[1538] Users take and upload photos of their daily meals using a dedicated app. The uploaded photos are sent to a server and analyzed using a deep learning model. This model identifies the ingredients in the photo and evaluates their nutritional value. For example, a user can take a photo of their lunch and send it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1539] The server also periodically sends questions to employees using LINE OA to monitor their mental state. For example, at 8 p.m., a message asking "How were you feeling today?" is sent to the user's LINE. If the user replies "I'm pretty tired today," the server analyzes the text and converts it into a score to evaluate their mental state.

[1540] Furthermore, the server is integrated with an emotion engine that recognizes emotions from voice and text input. This engine analyzes the user's input and classifies emotions as positive, negative, etc. For example, if you enter the text "I'm very happy today," the server will input this into the emotion engine and recognize it as a positive emotion.

[1541] The server centrally manages the acquired health, nutrition, mental state, and emotional data, and compares and analyzes it with big data. It can detect abnormal values ​​and patterns by comparing it with data from the past month and standard data. For example, if the pulse rate is higher than normal or the emotional data is negative, it will assess the overall state of high stress.

[1542] Finally, the server predicts the possibility of poor physical or mental health based on the analysis results and generates recommendations for appropriate rest, meal options, etc. For example, it may generate specific suggestions such as "Try meditating for 10 minutes" and notify the user via push notification or LINE message.

[1543] In this way, the present invention is built by combining a server, user devices, a dedicated application, and a deep learning model. This system can comprehensively monitor employees' health status and provide prompt and appropriate advice.

[1544] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1545] Step 1:

[1546] Acquisition of health data

[1547] server

[1548] The server works with the healthcare application installed on the smartwatch or smartphone to collect the user's health data. Specifically, it executes an API request GET / health-data?date=<previous day's date> every night at midnight to obtain the previous day's exercise amount, pulse rate, and blood pressure data. The input is the response data to the API request from the health app, and the output is the health data stored in the database. The collected data is stored in the database and validated to ensure data integrity and consistency.

[1549] Step 2:

[1550] Upload a meal photo

[1551] User

[1552] Users take photos of their daily meals using a dedicated app and upload them. The input is the photo of the meal taken by the user, and the output is image data sent to the server. The photo is sent to the endpoint POST / upload-photo, and is sent when the user selects a photo in the app and presses the upload button.

[1553] Step 3:

[1554] Food photo analysis

[1555] server

[1556] The server analyzes the received meal photos using a deep learning model. This model identifies the ingredients contained in the photos and evaluates their nutritional value. The input is the meal photo uploaded by the user, and the output is the analyzed nutritional information. Specifically, the server inputs the photo into the deep learning model and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[1557] Step 4:

[1558] Mental state monitoring

[1559] Server, User

[1560] At 8 p.m., the server sends the user a message via LINE OA asking, "How were you feeling today?" The input is the question in the LINE message, and the output is the user's answer. If the user answers, "I'm pretty tired today," the answer data is sent to the server, which performs text analysis. Specifically, the server analyzes the text using natural language processing technology and generates a score to evaluate the user's mental state.

[1561] Step 5:

[1562] Emotion recognition

[1563] server

[1564] The server uses an emotion engine that recognizes emotions from the user's voice or text input. The input is the user's voice or text data, and the output is emotion data categorized as positive, negative, etc. For example, if the user inputs the text "I'm very happy today," the server inputs that text into the emotion engine and recognizes it as a positive emotion.

[1565] Step 6:

[1566] Comparative analysis of data and synthesis of results

[1567] server

[1568] The server collects and centrally manages the acquired health, nutritional, mental state, and emotional data. The input is a collection of various data, and the output is the integrated analysis results. Specifically, the server compares and analyzes this data with past data and standard big data to detect abnormal values ​​and patterns. For example, it compares pulse rate data from the past month with the latest data to detect abnormally high values, and if the emotional data is negative, it evaluates the overall state as high stress.

[1569] Step 7:

[1570] Prediction and suggestions for poor physical and mental health

[1571] server

[1572] The server uses an AI model to predict the possibility of poor physical or mental health. The input is the integrated analysis data, and the output is specific suggestions. Specifically, the server inputs data into the AI ​​model and generates specific suggestions, such as "Meditate for 10 minutes" or "Do some short stretches for relaxation."

[1573] Step 8:

[1574] User Notification

[1575] server

[1576] The server notifies the user of the generated suggestions. The input is the generated suggestions, and the output is the notification to the user. The notification is sent via push notification or LINE message. For example, a message saying "You seem tired today, so try doing a short stretch to relax" is sent to the user's smartphone. This notification also includes suggestions based on the results of the emotion engine, such as "Refresh yourself with your favorite music."

[1577] (Application example 2)

[1578] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1579] The purpose of this invention is to prevent poor physical and mental health by efficiently monitoring the physical and mental state of employees, and to maximize performance by suggesting appropriate rest and meal plans at the right time. In particular, by introducing emotion recognition functionality to security service staff, the purpose is to achieve more effective health management and improved service quality in situations where a quick response is required.

[1580] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1581] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's answers, means for recognizing emotions from the user's voice input or text input, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating appropriate rest and meal menu suggestions, and means for notifying the user of the suggestions. This enables more accurate and comprehensive health management of employees, real-time evaluation of their health condition, and timely and appropriate suggestions to be made.

[1582] "Health data" refers to biometric information such as the user's amount of exercise, pulse rate, blood pressure, etc.

[1583] "Nutrition data" refers to information about the nutritional composition of the food a user has eaten, analyzed.

[1584] "Mental state data" refers to information for assessing the psychological state of a user.

[1585] "Emotion data" refers to emotional information recognized based on a user's voice or text input.

[1586] "Big data" refers to technology for processing and analyzing large amounts of data at high speed.

[1587] "Comparative analysis" refers to the process of comparing multiple data sets and analyzing their differences and commonalities.

[1588] "Predicting poor health" refers to the process of predicting the likelihood of a user experiencing poor health in the future based on the user's health data and mental state data.

[1589] "Mental down prediction" refers to a process of predicting the possibility of a mentally unstable state occurring in the future based on the user's mental state data and emotion data.

[1590] "Suggestion generation" refers to the process of recommending appropriate rest, meal plans, and other actions to the user based on the predicted results.

[1591] "Notification means" refers to the method or device used to notify the user of the generated suggestions.

[1592] MODE FOR CARRYING OUT THE INVENTION

[1593] The present invention is a system for managing the physical condition and optimizing the performance of employees and users. The system comprehensively analyzes health data, nutritional data, mental state data, and emotional data, generates appropriate suggestions, and notifies the user. The following describes in detail the embodiments of the present invention.

[1594] 1. Health Data Collection

[1595] server

[1596] The server works with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. The server executes an API request every night at midnight to obtain the previous day's health data.

[1597] Specific examples

[1598] The server executes the API request "GET / health-data?date=2023-10-10" every night at midnight to retrieve health data.

[1599] 2. Analysis of food photos

[1600] Terminal

[1601] Users use a specific application to take photos of their daily meals and upload them to a server, which then uses deep learning models to identify ingredients and analyze their nutritional content.

[1602] server

[1603] The server uses AI to analyze the received meal photos, identify the ingredients contained in the photos, and evaluate the proportions of nutrients.

[1604] Specific examples

[1605] The user takes a photo of their lunch using a dedicated app and sends it via "POST / upload-photo." The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1606] 3. Mental state monitoring

[1607] User

[1608] Users report their mental state by answering questions that are sent periodically, for example via messaging apps such as LINE.

[1609] server

[1610] The server receives the user's answers and performs natural language analysis to assess the mental state.

[1611] Specific examples

[1612] At 8pm, a message is sent to the user asking "How were you feeling today?" If the user replies "I'm pretty tired today," the information is analyzed on the server.

[1613] 4. Emotion Recognition by Emotion Engine

[1614] server

[1615] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[1616] Specific examples

[1617] If the user texts "I'm very happy today," the server recognizes this as a positive emotion.

[1618] 5. Comparative analysis of data and synthesis of results

[1619] server

[1620] The server integrates the acquired health, nutrition, mental state, and emotional data and compares and analyzes it with big data to detect abnormal values ​​and patterns and comprehensively evaluate the user's health condition.

[1621] Specific examples

[1622] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[1623] 6. Predicting and suggesting physical and mental health issues

[1624] server

[1625] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[1626] Specific examples

[1627] The server predicts that the user is under high stress and suggests that they "take 10 minutes of meditation." It also suggests activities to increase positive emotions based on emotional data.

[1628] 7. User Notices

[1629] server

[1630] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[1631] Specific examples

[1632] The server sends a notification to the user's device saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[1633] Prompt Sentence Examples

[1634] 1. Health data collection:

[1635] Get your health data.

[1636] 2. Mental state monitoring:

[1637] How were you feeling today?

[1638] As described above, the present invention not only manages the health status of employees and users in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management, thereby preventing employees from becoming physically or mentally unwell and maximizing their performance.

[1639] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1640] Step 1:

[1641] Health Data Collection

[1642] The server works in conjunction with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, the server executes an API request every night at midnight to obtain the previous day's health data.

[1643] Input: API request (e.g. "GET / health-data?date=2023-10-10")

[1644] Data processing: Formatting data obtained from healthcare applications and storing it in a database

[1645] Output: Stored health data (e.g., exercise amount, pulse rate, blood pressure)

[1646] Step 2:

[1647] Food photo analysis

[1648] The device allows users to take photos of their meals using a dedicated app and upload them to a server, which then analyzes the photos using a deep learning model to identify the ingredients in the photo and evaluate their nutritional value.

[1649] Input: Uploaded food photo (e.g. "POST / upload-photo")

[1650] Data processing: Analyze photos using a deep learning model to extract information about ingredients and nutrients

[1651] Output: Analyzed nutritional data (e.g., carbohydrates 50g, protein 30g, fat 20g)

[1652] Step 3:

[1653] Mental state monitoring

[1654] Users answer questions sent periodically via messaging apps such as LINE. The server receives the user's answers and performs natural language analysis to evaluate their mental state.

[1655] Input: Answer about the user's mental state (e.g., "I'm pretty tired today")

[1656] Data processing: Evaluate users' responses using natural language processing to generate mental state data

[1657] Output: Mental state data (e.g., fatigue level, stress level)

[1658] Step 4:

[1659] Emotion recognition by emotion engine

[1660] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[1661] Input: Voice or text input from the user (e.g., "I'm very happy today")

[1662] Data processing: Analyze input data using an emotion engine to generate emotion data

[1663] Output: Emotion data (e.g., positive, negative)

[1664] Step 5:

[1665] Comparative analysis of data and synthesis of results

[1666] The server compares the acquired health, nutrition, mental state, and emotional data with past data and big data, detects abnormal values ​​and patterns, and comprehensively evaluates the user's health condition.

[1667] Input: Health data, nutrition data, mental state data, emotional data

[1668] Data processing: Matching with big data and analyzing it to detect outliers and patterns

[1669] Output: Comprehensive health assessment data (e.g., high stress levels, nutritional imbalances)

[1670] Step 6:

[1671] Prediction and suggestions for poor physical and mental health

[1672] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[1673] Input: Health assessment data

[1674] Data processing: Using AI models to predict risks and generate specific recommendations

[1675] Output: Suggestions (e.g., 10 minutes of meditation, stretches to relax)

[1676] Step 7:

[1677] User Notifications

[1678] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[1679] Input: Proposal

[1680] Data processing: Converting the data into notification format and sending it to the user's device

[1681] Output: User notification (e.g., "You seem tired today, let's do some short stretches for relaxation")

[1682] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1683] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1684] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1685] [Fourth embodiment]

[1686] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1687] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1688] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1689] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1690] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1691] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1692] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1693] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1694] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1695] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1696] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1697] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1698] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1699] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. The program processing of the system is explained in detail below.

[1700] 1. Health Data Collection

[1701] server

[1702] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[1703] Specific examples

[1704] The server makes an API call such as GET / health-data?date=2023-10-10 to retrieve data for the previous day.

[1705] 2. Analysis of food photos

[1706] Terminal

[1707] Users upload photos of their meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[1708] server

[1709] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[1710] Specific examples

[1711] When a user uploads a photo of their lunch to the app, it is sent to a server, which analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[1712] 3. Mental state monitoring

[1713] User

[1714] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[1715] server

[1716] The server collects responses from users and performs text analysis to assess their mental state.

[1717] Specific examples

[1718] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[1719] 4. Comparative analysis with big data

[1720] server

[1721] The server compares the acquired data with existing big data and performs analysis to check for any abnormalities. It also refers to past data to track changes in health status.

[1722] Specific examples

[1723] The server compares the data from the past month and detects that the recent pulse rate is abnormally high.

[1724] 5. Predicting and suggesting physical and mental health issues

[1725] server

[1726] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates appropriate rest and meal suggestions according to the predicted risk.

[1727] Specific examples

[1728] The server predicts that User A is under high stress and generates a suggestion that says, "You may be under high stress. Try meditating for 10 minutes."

[1729] 6. User Notices

[1730] server

[1731] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[1732] Specific examples

[1733] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[1734] Through the above series of processes, the present invention can manage the health status of employees in real time and provide optimal advice at the right time, thereby preventing physical and mental illnesses from occurring, thereby maximizing employee performance.

[1735] The processing flow will be explained below.

[1736] Step 1:

[1737] server

[1738] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[1739] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[1740] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[1741] Specific examples

[1742] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[1743] Step 2:

[1744] Terminal

[1745] Users upload photos of their daily meals to a dedicated app.

[1746] The dedicated app has a camera function that allows users to take and send photos of their meals.

[1747] The photos are sent from the device to the server.

[1748] Specific examples

[1749] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[1750] Step 3:

[1751] server

[1752] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[1753] Deep learning models are used to analyze food photos and identify the nutritional components ingested (e.g., carbohydrates, proteins, fats, etc.).

[1754] Specific examples

[1755] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1756] Step 4:

[1757] User

[1758] Users answer questions about their mental state that are sent periodically by LINE OA.

[1759] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[1760] Specific examples

[1761] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[1762] Step 5:

[1763] server

[1764] The server collects the user's responses and performs text analysis to assess their mental state.

[1765] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[1766] Specific examples

[1767] The responses are analyzed and the stress level is classified as high, medium, or low.

[1768] Step 6:

[1769] server

[1770] The server compares and analyzes the acquired health data, nutritional data, and mental state data with existing big data.

[1771] This allows abnormal values ​​and patterns to be detected and the user's health status to be assessed.

[1772] Specific examples

[1773] The server compares the recent pulse rate with data from the past month and detects that it is abnormally high.

[1774] Step 7:

[1775] server

[1776] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[1777] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[1778] Specific examples

[1779] It predicts that user A is under a lot of stress and suggests that they "meditate for 10 minutes."

[1780] Step 8:

[1781] server

[1782] The server notifies the user of the generated proposal.

[1783] Notifications will be sent via app push notifications or LINE messages.

[1784] Specific examples

[1785] A notification appears on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[1786] Example 1

[1787] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1788] In modern society, employee health management has become an important issue. However, many companies find it difficult to monitor employees' physical and mental health in real time and provide necessary advice at the appropriate time. As a result, poor physical and mental health cannot be prevented, leading to problems such as a decline in employee performance and increased absenteeism. With conventional methods, individual health data, dietary information, and mental state monitoring are not managed centrally, making it difficult to grasp a comprehensive health status and make appropriate recommendations.

[1789] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1790] In this invention, the server includes a means for acquiring health data from users, a means for receiving images of meals taken by users and identifying nutrients, and a means for monitoring mental states based on users' responses. This makes it possible to grasp employees' health and mental states in real time and provide necessary advice at appropriate times.

[1791] "Health data" refers to physiological information such as the user's exercise volume, heart rate, and blood pressure.

[1792] A "meal image" refers to a photograph of a meal taken by a user, which includes information for identifying the contents and nutrients of the meal.

[1793] "Means for identifying nutrients" refers to the technology or method used by the server to analyze the image of the meal received and identify the ingredients and their nutritional components.

[1794] "Means for monitoring mental state" refers to methods or systems for evaluating and monitoring a user's mental health state by performing text analysis based on the user's answers and input data.

[1795] "Big data" refers to a wide range of existing data sets that can be compared to assess health and mental health.

[1796] "Suggesting rest and meal menus" refers to providing advice on appropriate rest methods and meal contents based on the user's current health, nutritional, and mental state.

[1797] The present invention is a system for monitoring the physical condition, nutritional intake, and mental state of employees based on their health data, and predicting poor physical and mental health. This system includes the following components:

[1798] 1. Health Data Collection

[1799] server

[1800] The server works with the health care application on the smartwatch or smartphone to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, heart rate, and blood pressure every day. This data is obtained via an API. For example, at midnight, the previous day's data is obtained in the form of GET / health-data?date=2023-10-10.

[1801] 2. Analysis of food photos

[1802] Terminal

[1803] Using a dedicated app, users take pictures of their meals and upload them, which are then sent to a server.

[1804] server

[1805] The server uses a deep learning model to analyze the received meal images, identify the ingredients contained in the image, and evaluate the nutritional value. Specifically, when a user uploads a photo of their lunch to the app, it is sent to the server. The server analyzes the photo and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[1806] 3. Mental state monitoring

[1807] User

[1808] Users answer simple questions sent periodically by LINE OA, which are designed to assess the user's mental state.

[1809] server

[1810] The server collects the user's responses and performs text analysis to evaluate their mental state. For example, if a user receives a message on LINE at 8 p.m. asking, "How were you feeling today?" and the user replies, "I'm pretty tired today," the information is analyzed by the server.

[1811] 4. Comparative analysis with big data

[1812] server

[1813] The server compares the acquired data with a large amount of existing data and performs analysis. This checks for any abnormalities. It also refers to past data to track changes in health status. For example, the server compares data from the past month and detects that a recent heart rate is abnormally high.

[1814] 5. Predicting and suggesting physical and mental health issues

[1815] server

[1816] The server uses a generative AI model to predict the possibility of poor physical condition or mental breakdown based on the analysis results. Depending on the predicted risk, it generates appropriate rest and meal suggestions. For example, the server predicts that User A is in a high stress state and generates a suggestion such as, "You may be in a high stress state. Try meditating for 10 minutes."

[1817] 6. User Notices

[1818] server

[1819] The server notifies the user of the generated suggestions. The notification is sent via a push notification or a LINE message. Specifically, a notification will appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[1820] In this way, the present invention manages employees' health status in real time and provides optimal advice at the right time, thereby preventing physical and mental illness and maximizing employee performance.

[1821] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1822] Step 1:

[1823] Health Data Requests

[1824] server

[1825] Every day at midnight, the server requests health data from the health care application on the user's smartwatch or smartphone. Specifically, it obtains data such as the amount of exercise, heart rate, and blood pressure from the previous day via an API.

[1826] Input: API call GET / health-data?date=2023-10-10

[1827] Output: Health data (exercise volume, heart rate, blood pressure)

[1828] Specific operation: The server sends an API request at the specified date and time to request health data.

[1829] Step 2:

[1830] Receiving and storing health data

[1831] server

[1832] The server receives the acquired health data and stores it in a database for later analysis and comparison.

[1833] Input: Health data as API response

[1834] Output: Health data stored in a database

[1835] Specific operation: The server analyzes the received data and records it in a database.

[1836] Step 3:

[1837] Upload a meal photo

[1838] Terminal

[1839] Users use a dedicated app to take pictures of their meals and upload them.

[1840] Input: Food image (user-taken photo)

[1841] Output: Image file sent to the server

[1842] Specific operation: The user selects a photo of a meal from the dedicated app and presses the "Upload" button.

[1843] Step 4:

[1844] Receiving meal photos

[1845] server

[1846] The server receives the uploaded food images and prepares them for analysis.

[1847] Input: Image file sent by the user

[1848] Output: Meal images saved in temporary storage

[1849] Specific operation: The server receives the image file and temporarily stores it.

[1850] Step 5:

[1851] Ingredient and nutrient analysis

[1852] server

[1853] The server uses deep learning models to analyze the received photos, identify the ingredients in the photos, and assess their nutritional value.

[1854] Input: Food images stored in temporary storage

[1855] Output: Analysis results (carbohydrates 50g, protein 30g, fat 20g, etc.)

[1856] Specific operation: The server invokes the deep learning model to extract nutritional information from the image.

[1857] Step 6:

[1858] Submit a mental health question

[1859] server

[1860] The server periodically sends questions to the user via LINE OA to assess their mental state.

[1861] Input: Fixed message "How were you feeling today?"

[1862] Output: The question message sent to the user

[1863] Specific operation: The server sends a LINE message to the user at 8pm.

[1864] Step 7:

[1865] Receiving and processing responses

[1866] server

[1867] The server collects responses from users and performs text analysis to assess their mental state.

[1868] Input: User response text, e.g. "I'm pretty tired today"

[1869] Output: Mental state evaluation results

[1870] Specific operation: The server analyzes the received text and evaluates the mental state.

[1871] Step 8:

[1872] Data collection and comparison

[1873] server

[1874] The server compares the collected health and mental status data with a large amount of existing data to check for abnormalities, and also refers to past data to track changes in health status.

[1875] Input: Collected data and existing bulk data

[1876] Output: Analysis results (no anomalies, anomalies detected, etc.)

[1877] Specific operation: The server compares data from the past month and detects abnormalities such as high pulse rate.

[1878] Step 9:

[1879] Situation assessment and forecasting

[1880] server

[1881] The server uses a generative AI model that predicts the likelihood of physical or mental illness based on the analysis results.

[1882] Input: Analysis results and generated AI model

[1883] Output: Prediction results of poor physical condition and mental downturn

[1884] How it works: The server uses the generated AI model to predict the user's stress level and physical condition abnormalities.

[1885] Step 10:

[1886] Proposal Generation

[1887] server

[1888] The server generates appropriate rest and meal suggestions based on the predicted risk.

[1889] Input: Prediction result

[1890] Output: Specific suggestions (resting methods and meal menu)

[1891] Specific behavior: The server generates a suggestion such as "You may be under high stress. Try meditating for 10 minutes."

[1892] Step 11:

[1893] Sending notifications

[1894] server

[1895] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[1896] Input: Proposal

[1897] Output: Notification message sent to the user

[1898] Specific operation: The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax."

[1899] (Application example 1)

[1900] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1901] There is a need to appropriately monitor the physical and mental states of employees and prevent them from becoming ill or suffering from mental breakdowns. Security employees, in particular, need to be aware of their health status in real time and take appropriate measures, as abnormal physical or mental states directly affect the safety and efficiency of their work. However, current systems lack the ability to detect abnormalities in real time or propose specific countermeasures. Therefore, the objective of this invention is to accurately and quickly manage the physical and mental states of employees and provide appropriate warnings and advice.

[1902] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1903] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's responses, means for comparing and analyzing these data with big data, means for predicting poor physical condition or mental breakdown and generating appropriate rest and meal menu suggestions, means for notifying the user of the suggestions, and means for monitoring the physical and mental state of security employees in real time and detecting and warning of abnormalities. This makes it possible to monitor the physical and mental state of employees in real time and take prompt and appropriate measures if an abnormality is detected.

[1904] "Health data" is information related to the user's physical activity, and is data related to the user's health condition, including the amount of exercise, pulse rate, blood pressure, etc.

[1905] A "meal photo" is an image that visually records the meal a user has eaten, and is used to analyze the contents of the image to identify nutrients.

[1906] "Mental state" indicates the mental health state of the user, and refers to the state of mind and emotions.

[1907] "Big data" refers to large amounts of digital information that can be used to analyze data and detect anomalies.

[1908] "Comparative analysis" is a method for analyzing acquired data against large amounts of existing data, in order to identify abnormalities and trends.

[1909] "Poor health" refers to an abnormality in the user's physical activity or health condition, which interferes with the performance of normal business operations.

[1910] "Mental down" refers to a state in which the user's mental state is abnormal and the user is mentally unstable.

[1911] "Rest" refers to rest or activities that a user undertakes to refresh their body and mind and restore their health.

[1912] A "meal menu" refers to the combination of foods and menu items that a user will consume, and suggestions are made taking into consideration nutrient balance.

[1913] "Notification" refers to the transmission of information from the system to the user, including alerts and advice.

[1914] "Real-time" refers to the state in which data is collected, analyzed, and notified immediately, and processing is carried out without delay.

[1915] "Anomaly detection" is the process of discovering deviations from normal health or mental states, and is an important step in responding quickly.

[1916] A "warning" is a notification that alerts the user to a detected abnormality and urges the user to take appropriate action.

[1917] To implement the present invention, the system is configured as follows.

[1918] Hardware and software:

[1919] 1. Server:

[1920] Hardware: Cloud server (e.g. AWS, GCP)

[1921] software:

[1922] Health data APIs (e.g., HealthKit API)

[1923] Deep learning models (e.g. TensorFlow)

[1924] NLP analysis libraries (e.g. NLTK, spaCy)

[1925] Big data analysis tools (e.g., Apache Hadoop, Spark)

[1926] Notification API (e.g. Firebase Cloud Messaging)

[1927] 2. Terminal:

[1928] Hardware: Smartwatches, smartphone cameras

[1929] Software: Dedicated health management application

[1930] Detailed description of the process:

[1931] 1. Health Data Collection:

[1932] The server works in conjunction with the smartwatch or smartphone's healthcare application to collect daily health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, it uses an API to obtain the previous day's data at midnight.

[1933] For example, the server makes an API call like GET / health-data?date=2023-10-10 to retrieve data from the previous day.

[1934] 2. Analysis of food photographs:

[1935] When users upload photos of their meals to the app, the photos are sent to a server, which then analyzes them using a deep learning model to identify the ingredients and evaluate their nutritional value.

[1936] For example, when a user uploads a photo of their lunch to the app, the server analyzes the photo and extracts information such as "50g carbs, 30g protein, 20g fat."

[1937] 3. Mental state monitoring:

[1938] Users answer questions sent periodically to assess their mental state. The server collects the answers from users and performs text analysis to assess their mental state.

[1939] For example, if a message asking "How were you feeling today?" is sent via LINE at 8pm and the user replies "I'm pretty tired today," that information is analyzed on the server.

[1940] 4. Comparative analysis with big data:

[1941] The server compares the acquired data with existing big data to detect anomalies, and compares it with past data to track changes in health status.

[1942] As a specific example, the server compares data from the past month and detects that the recent pulse rate is abnormally high.

[1943] 5. Prediction and suggestions for physical and mental illness:

[1944] Based on the analysis results, the server predicts the possibility of poor physical or mental health and generates appropriate rest and meal recommendations. The advice is generated by an AI model.

[1945] As a specific example, the server predicts that the user is under high stress and generates a suggestion such as, "You may be under high stress. Try meditating for 10 minutes."

[1946] 6. User Notice:

[1947] The server notifies the user of the generated suggestions via app push notifications or messages.

[1948] As a specific example, a notification may appear on the user's smartphone saying, "You seem tired today, so let's do some short stretches for relaxation."

[1949] An example prompt for a generative AI model would be:

[1950] The user's health data indicates high stress levels and fatigue. Please provide three appropriate health tips for this user:

[1951] 1. Relaxation techniques such as meditation and stretching

[1952] 2. Proposing nutritionally balanced meals

[1953] 3. Mental health advice

[1954] In this way, the "Security Guard Health Monitor" application becomes a powerful tool for maintaining optimal physical and mental health of security employees.

[1955] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1956] Step 1:

[1957] The server obtains the user's health data (such as exercise volume, pulse rate, and blood pressure) from the smartwatch or smartphone via API. As input, it receives the user ID and date and time information and sends an API request. As output, it receives the previous day's health data and stores it in a database.

[1958] Step 2:

[1959] Users upload photos of their meals to a dedicated app. As input, the app takes photos of the meal taken with a smartphone camera and sends them to the server. As output, the photo data is sent to the server, ready for analysis.

[1960] Step 3:

[1961] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained and evaluate the nutrients consumed. As input, the photo data of the meal is obtained and input into the AI ​​model. As output, the analysis results are obtained and nutritional information such as "carbohydrates, protein, fat" is stored in a database.

[1962] Step 4:

[1963] Users answer questions about their mental state that are periodically sent via LINE OA. As input, the system obtains the user's text responses on LINE OA. As output, the text responses are sent to the server.

[1964] Step 5:

[1965] The server analyzes the user's responses using a text analysis tool to evaluate their mental state. As input, it obtains the user's text responses and inputs them into an NLP analysis library. As output, it obtains the mental state evaluation results, and information such as "stress level" and "emotional state" is stored in a database.

[1966] Step 6:

[1967] The server uses a big data analysis tool to compare and analyze the collected health, nutritional, and mental state data with past data. Current user data and past big data are taken as input. Abnormal patterns and abnormal health status are detected as output, and the results are stored in a database.

[1968] Step 7:

[1969] The server uses an AI model to predict the likelihood of poor physical or mental health based on the comparative analysis results, and generates recommendations for appropriate rest and meal plans. The analysis results are input into the AI ​​model, and specific advice for the user is generated as output.

[1970] Step 8:

[1971] The server notifies the user of the generated suggestions via push notification or message to the user's smartphone. As input, it receives the suggestion content and the user information of the notification recipient. As output, a notification is displayed on the user's smartphone. For example, a notification may be displayed saying, "You seem tired today, so let's do some short stretches to relax."

[1972] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1973] The present invention is a system that monitors the physical condition, nutritional intake, and mental state of employees, and not only predicts poor physical condition or mental breakdown, but also recognizes the user's emotions, thereby achieving more accurate health management and maximizing performance. The system's program processing is described in detail below.

[1974] 1. Health Data Collection

[1975] server

[1976] The server works with the smartwatch or smartphone's healthcare application to collect the user's health data. Specifically, it periodically obtains data such as exercise volume, pulse rate, and blood pressure every day. For example, it obtains the previous day's data via API at midnight.

[1977] Specific examples

[1978] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[1979] 2. Analysis of food photos

[1980] Terminal

[1981] Users upload photos of their daily meals to a dedicated app, which then sends the photos to a server where they are analyzed by AI.

[1982] server

[1983] The server analyzes the received meal photos using a deep learning model to identify the ingredients contained in the photos and evaluate their nutritional value.

[1984] Specific examples

[1985] A user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[1986] 3. Mental state monitoring

[1987] User

[1988] Users answer questions about their mental state that are periodically sent by LINE OA. The questions are designed to assess the user's mental state.

[1989] server

[1990] The server collects responses from users and performs text analysis to assess their mental state.

[1991] Specific examples

[1992] At 8pm, a message is sent to the user on LINE asking, "How were you feeling today?" If the user replies, "I'm pretty tired today," the information is analyzed on the server.

[1993] 4. Emotion Recognition by Emotion Engine

[1994] server

[1995] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[1996] Specific examples

[1997] If a user texts "I'm very happy today," the emotion engine will recognize this as a positive emotion.

[1998] 5. Comparative analysis of data and synthesis of results

[1999] server

[2000] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data recognized by the emotion engine with existing big data, thereby detecting abnormal values ​​and patterns and comprehensively assessing the user's health condition.

[2001] Specific examples

[2002] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[2003] 6. Predicting and suggesting physical and mental health issues

[2004] server

[2005] The server uses an AI model to predict the likelihood of physical or mental illness based on the analysis results, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[2006] Specific examples

[2007] The server predicts that User A is under a lot of stress and suggests that he "meditate for 10 minutes." It also suggests activities to increase positive emotions based on emotional data.

[2008] 7. User Notices

[2009] server

[2010] The server notifies the user of the generated suggestions via app push notifications or LINE messages.

[2011] Specific examples

[2012] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[2013] Through the above series of processes, the present invention not only manages employees' health status in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management. This system can prevent employees from becoming physically or mentally unwell, maximizing their performance.

[2014] The processing flow will be explained below.

[2015] Step 1:

[2016] server

[2017] It works in conjunction with smartwatches and smartphone healthcare applications to collect user health data.

[2018] The server uses the healthcare API to periodically obtain the user's exercise volume, pulse rate, and blood pressure data.

[2019] For example, at midnight, the system performs a process to obtain the previous day's health data via API.

[2020] Specific examples

[2021] The server executes the API request GET / health-data?date=2023-10-10 every night at midnight to retrieve health data.

[2022] Step 2:

[2023] Terminal

[2024] Users upload photos of their daily meals to a dedicated app.

[2025] The dedicated app has a camera function that allows users to take and send photos of their meals.

[2026] The photos are sent from the device to the server.

[2027] Specific examples

[2028] The user takes a photo of their lunch using a dedicated app and sends it to POST / upload-photo .

[2029] Step 3:

[2030] server

[2031] The server uses AI to analyze the received meal photos and identify the ingredients and nutrients contained in the photos.

[2032] Using a deep learning model, it analyzes photos of meals and identifies the nutritional components (carbohydrates, proteins, fats, etc.) ingested.

[2033] Specific examples

[2034] The server analyzes the uploaded photo using the eval_photo(photo_data) function and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[2035] Step 4:

[2036] User

[2037] Users answer questions about their mental state that are sent periodically by LINE OA.

[2038] The questions assess the user's mental state and are presented in the form of simple multiple choice or open-ended questions.

[2039] Specific examples

[2040] LINE sends a message asking, "How were you feeling today?" and the user replies, "I'm pretty tired today."

[2041] Step 5:

[2042] server

[2043] The server collects the user's responses and performs text analysis to assess their mental state.

[2044] The collected responses are analyzed using natural language processing technology to quantify stress levels and fatigue levels.

[2045] Specific examples

[2046] The responses are analyzed and the stress level is classified as high, medium, or low.

[2047] Step 6:

[2048] server

[2049] The server uses an emotion engine that recognizes emotions from the user's voice and text input.

[2050] The emotion engine classifies the user's emotions into positive and negative, and integrates this into a mental state assessment.

[2051] Specific examples

[2052] If a user texts "I'm very happy today," the emotion engine will recognize this as positive.

[2053] Step 7:

[2054] server

[2055] The server compares and analyzes the acquired health data, nutritional data, mental state data, and emotional data with existing big data.

[2056] This allows for the detection of abnormal values ​​and patterns and a comprehensive assessment of the user's health status.

[2057] Specific examples

[2058] The server detects if the health data deviates from the average for the past month, and if the emotional data is negative, it assesses the overall health risk as high.

[2059] Step 8:

[2060] server

[2061] The server uses an AI model to predict the possibility of poor physical health or mental breakdown.

[2062] Based on the prediction results, specific suggestions such as appropriate rest and meal menus are generated.

[2063] Specific examples

[2064] The server predicts that User A is in a high stress state and suggests that he or she "meditate for 10 minutes." It also suggests activities to increase positive emotions.

[2065] Step 9:

[2066] server

[2067] The server notifies the user of the generated proposal.

[2068] Notifications will be sent via app push notifications or LINE messages.

[2069] Specific examples

[2070] The server sends a notification to the user's smartphone saying, "You seem tired today, so let's do some short stretches to relax," and also includes a suggestion based on emotional data, "Let's refresh ourselves by listening to our favorite music."

[2071] Example 2

[2072] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2073] Employee health management requires preventing poor physical and mental health before they occur. However, conventional health management systems are limited to analyzing individual data points alone, making it difficult to evaluate overall health status. It is also difficult to provide personalized advice that reflects the user's emotional state. Therefore, there is a need for a system that can achieve more accurate health management and maximize performance.

[2074] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2075] In this invention, the server includes means for acquiring health data from users and storing the data in a database, means for receiving photos of meals taken by users and identifying nutrients using a deep learning model, means for performing text analysis based on the user's responses and monitoring the mental state, means for analyzing voice input and text input with an emotion engine and classifying the user's emotions, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating suggestions for appropriate rest and meal menus, and means for notifying the user of the suggestions. This makes it possible to manage employee health conditions in real time and provide accurate advice based on a comprehensive evaluation.

[2076] "Health data" refers to data relating to the user's physical condition, such as the user's amount of exercise, pulse rate, blood pressure, etc.

[2077] A "database" is a system for efficiently storing, managing, and searching acquired data.

[2078] A "meal photo" is an image of the ingredients and meal contents consumed by the user.

[2079] A "deep learning model" is an artificial intelligence technique that uses large data sets to extract features and perform classification.

[2080] "Nutrients" are substances such as proteins, carbohydrates, fats, vitamins, and minerals found in food.

[2081] "Text analysis" is a method of extracting meaning and emotion from user responses and sentences using natural language processing technology.

[2082] "Mental state" refers to the user's psychological health and stress level.

[2083] An "emotion engine" is an analysis system for identifying a user's emotions from voice and text data.

[2084] "Big data" refers to a large amount of data in a variety of formats, and analyzing this data can provide new information and insights.

[2085] "Comparative analysis" is a technique for comparing multiple data sets to find specific patterns or anomalies.

[2086] "Poor physical condition" refers to a state in which the user is unable to maintain normal bodily functions.

[2087] "Mental down" refers to a user's mental state deteriorating due to psychological fatigue or stress.

[2088] "Suggestions" are specific advice about behaviors and diets generated based on the user's health status.

[2089] "Notification" is a communication method for presenting information or suggestions from the server to the user.

[2090] The system of the present invention is designed to monitor employees' physical condition, nutritional intake, and mental state in real time and to predict poor physical and mental health before they occur. This system aims to maximize employee performance. Specific embodiments of the system are described below.

[2091] The system consists of a server, a user's device, and a dedicated AI model.

[2092] The server works with the healthcare application installed on the user's smartwatch or smartphone to collect health data. Specifically, data such as exercise volume, pulse rate, and blood pressure is collected periodically every day. For example, the server executes an API request (GET / health-data?date=<previous day's date>) at midnight every night to retrieve the previous day's health data.

[2093] Users take and upload photos of their daily meals using a dedicated app. The uploaded photos are sent to a server and analyzed using a deep learning model. This model identifies the ingredients in the photo and evaluates their nutritional value. For example, a user can take a photo of their lunch and send it to POST / upload-photo. The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[2094] The server also periodically sends questions to employees using LINE OA to monitor their mental state. For example, at 8 p.m., a message asking "How were you feeling today?" is sent to the user's LINE. If the user replies "I'm pretty tired today," the server analyzes the text and converts it into a score to evaluate their mental state.

[2095] Furthermore, the server is integrated with an emotion engine that recognizes emotions from voice and text input. This engine analyzes the user's input and classifies emotions as positive, negative, etc. For example, if you enter the text "I'm very happy today," the server will input this into the emotion engine and recognize it as a positive emotion.

[2096] The server centrally manages the acquired health, nutrition, mental state, and emotional data, and compares and analyzes it with big data. It can detect abnormal values ​​and patterns by comparing it with data from the past month and standard data. For example, if the pulse rate is higher than normal or the emotional data is negative, it will assess the overall state of high stress.

[2097] Finally, the server predicts the possibility of poor physical or mental health based on the analysis results and generates recommendations for appropriate rest, meal options, etc. For example, it may generate specific suggestions such as "Try meditating for 10 minutes" and notify the user via push notification or LINE message.

[2098] In this way, the present invention is built by combining a server, user devices, a dedicated application, and a deep learning model. This system can comprehensively monitor employees' health status and provide prompt and appropriate advice.

[2099] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2100] Step 1:

[2101] Acquisition of health data

[2102] server

[2103] The server works with the healthcare application installed on the smartwatch or smartphone to collect the user's health data. Specifically, it executes an API request GET / health-data?date=<previous day's date> every night at midnight to obtain the previous day's exercise amount, pulse rate, and blood pressure data. The input is the response data to the API request from the health app, and the output is the health data stored in the database. The collected data is stored in the database and validated to ensure data integrity and consistency.

[2104] Step 2:

[2105] Upload a meal photo

[2106] User

[2107] Users take photos of their daily meals using a dedicated app and upload them. The input is the photo of the meal taken by the user, and the output is image data sent to the server. The photo is sent to the endpoint POST / upload-photo, and is sent when the user selects a photo in the app and presses the upload button.

[2108] Step 3:

[2109] Food photo analysis

[2110] server

[2111] The server analyzes the received meal photos using a deep learning model. This model identifies the ingredients contained in the photos and evaluates their nutritional value. The input is the meal photo uploaded by the user, and the output is the analyzed nutritional information. Specifically, the server inputs the photo into the deep learning model and extracts information such as "50g of carbohydrates, 30g of protein, 20g of fat."

[2112] Step 4:

[2113] Mental state monitoring

[2114] Server, User

[2115] At 8 p.m., the server sends the user a message via LINE OA asking, "How were you feeling today?" The input is the question in the LINE message, and the output is the user's answer. If the user answers, "I'm pretty tired today," the answer data is sent to the server, which performs text analysis. Specifically, the server analyzes the text using natural language processing technology and generates a score to evaluate the user's mental state.

[2116] Step 5:

[2117] Emotion recognition

[2118] server

[2119] The server uses an emotion engine that recognizes emotions from the user's voice or text input. The input is the user's voice or text data, and the output is emotion data categorized as positive, negative, etc. For example, if the user inputs the text "I'm very happy today," the server inputs that text into the emotion engine and recognizes it as a positive emotion.

[2120] Step 6:

[2121] Comparative analysis of data and synthesis of results

[2122] server

[2123] The server collects and centrally manages the acquired health, nutritional, mental state, and emotional data. The input is a collection of various data, and the output is the integrated analysis results. Specifically, the server compares and analyzes this data with past data and standard big data to detect abnormal values ​​and patterns. For example, it compares pulse rate data from the past month with the latest data to detect abnormally high values, and if the emotional data is negative, it evaluates the overall state as high stress.

[2124] Step 7:

[2125] Prediction and suggestions for poor physical and mental health

[2126] server

[2127] The server uses an AI model to predict the possibility of poor physical or mental health. The input is the integrated analysis data, and the output is specific suggestions. Specifically, the server inputs data into the AI ​​model and generates specific suggestions, such as "Meditate for 10 minutes" or "Do some short stretches for relaxation."

[2128] Step 8:

[2129] User Notification

[2130] server

[2131] The server notifies the user of the generated suggestions. The input is the generated suggestions, and the output is the notification to the user. The notification is sent via push notification or LINE message. For example, a message saying "You seem tired today, so try doing a short stretch to relax" is sent to the user's smartphone. This notification also includes suggestions based on the results of the emotion engine, such as "Refresh yourself with your favorite music."

[2132] (Application example 2)

[2133] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2134] The purpose of this invention is to prevent poor physical and mental health by efficiently monitoring the physical and mental state of employees, and to maximize performance by suggesting appropriate rest and meal plans at the right time. In particular, by introducing emotion recognition functionality to security service staff, the purpose is to achieve more effective health management and improved service quality in situations where a quick response is required.

[2135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2136] In this invention, the server includes means for acquiring health data from the user, means for receiving photos of meals taken by the user and identifying nutrients, means for monitoring the mental state based on the user's answers, means for recognizing emotions from the user's voice input or text input, means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data, means for predicting poor physical condition or mental downturn and generating appropriate rest and meal menu suggestions, and means for notifying the user of the suggestions. This enables more accurate and comprehensive health management of employees, real-time evaluation of their health condition, and timely and appropriate suggestions to be made.

[2137] "Health data" refers to biometric information such as the user's amount of exercise, pulse rate, blood pressure, etc.

[2138] "Nutrition data" refers to information about the nutritional composition of the food a user has eaten, analyzed.

[2139] "Mental state data" refers to information for assessing the psychological state of a user.

[2140] "Emotion data" refers to emotional information recognized based on a user's voice or text input.

[2141] "Big data" refers to technology for processing and analyzing large amounts of data at high speed.

[2142] "Comparative analysis" refers to the process of comparing multiple data sets and analyzing their differences and commonalities.

[2143] "Predicting poor health" refers to the process of predicting the likelihood of a user experiencing poor health in the future based on the user's health data and mental state data.

[2144] "Mental down prediction" refers to a process of predicting the possibility of a mentally unstable state occurring in the future based on the user's mental state data and emotion data.

[2145] "Suggestion generation" refers to the process of recommending appropriate rest, meal plans, and other actions to the user based on the predicted results.

[2146] "Notification means" refers to the method or device used to notify the user of the generated suggestions.

[2147] MODE FOR CARRYING OUT THE INVENTION

[2148] The present invention is a system for managing the physical condition and optimizing the performance of employees and users. The system comprehensively analyzes health data, nutritional data, mental state data, and emotional data, generates appropriate suggestions, and notifies the user. The following describes in detail the embodiments of the present invention.

[2149] 1. Health Data Collection

[2150] server

[2151] The server works with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. The server executes an API request every night at midnight to obtain the previous day's health data.

[2152] Specific examples

[2153] The server executes the API request "GET / health-data?date=2023-10-10" every night at midnight to retrieve health data.

[2154] 2. Analysis of food photos

[2155] Terminal

[2156] Users use a specific application to take photos of their daily meals and upload them to a server, which then uses deep learning models to identify ingredients and analyze their nutritional content.

[2157] server

[2158] The server uses AI to analyze the received meal photos, identify the ingredients contained in the photos, and evaluate the proportions of nutrients.

[2159] Specific examples

[2160] The user takes a photo of their lunch using a dedicated app and sends it via "POST / upload-photo." The server analyzes the photo and extracts information such as "50g carbohydrates, 30g protein, 20g fat."

[2161] 3. Mental state monitoring

[2162] User

[2163] Users report their mental state by answering questions that are sent periodically, for example via messaging apps such as LINE.

[2164] server

[2165] The server receives the user's answers and performs natural language analysis to assess the mental state.

[2166] Specific examples

[2167] At 8pm, a message is sent to the user asking "How were you feeling today?" If the user replies "I'm pretty tired today," the information is analyzed on the server.

[2168] 4. Emotion Recognition by Emotion Engine

[2169] server

[2170] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[2171] Specific examples

[2172] If the user texts "I'm very happy today," the server recognizes this as a positive emotion.

[2173] 5. Comparative analysis of data and synthesis of results

[2174] server

[2175] The server integrates the acquired health, nutrition, mental state, and emotional data and compares and analyzes it with big data to detect abnormal values ​​and patterns and comprehensively evaluate the user's health condition.

[2176] Specific examples

[2177] The server detects that the recent pulse rate is abnormally high compared to data from the past month, and since the most recent emotional data is negative, it assesses the overall state of high stress.

[2178] 6. Predicting and suggesting physical and mental health issues

[2179] server

[2180] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[2181] Specific examples

[2182] The server predicts that the user is under high stress and suggests that they "take 10 minutes of meditation." It also suggests activities to increase positive emotions based on emotional data.

[2183] 7. User Notices

[2184] server

[2185] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[2186] Specific examples

[2187] The server sends a notification to the user's device saying, "You seem tired today, so let's do some short stretches to relax." Based on the results of the emotion engine, it also includes suggestions such as, "Listen to your favorite music to refresh yourself."

[2188] Prompt Sentence Examples

[2189] 1. Health data collection:

[2190] Get your health data.

[2191] 2. Mental state monitoring:

[2192] How were you feeling today?

[2193] As described above, the present invention not only manages the health status of employees and users in real time and provides optimal advice at the right time, but also utilizes emotional data to achieve more effective health management, thereby preventing employees from becoming physically or mentally unwell and maximizing their performance.

[2194] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2195] Step 1:

[2196] Health Data Collection

[2197] The server works in conjunction with the health care application on the smartwatch or smartphone to periodically obtain health data such as the user's exercise volume, pulse rate, blood pressure, etc. Specifically, the server executes an API request every night at midnight to obtain the previous day's health data.

[2198] Input: API request (e.g. "GET / health-data?date=2023-10-10")

[2199] Data processing: Formatting data obtained from healthcare applications and storing it in a database

[2200] Output: Stored health data (e.g., exercise amount, pulse rate, blood pressure)

[2201] Step 2:

[2202] Food photo analysis

[2203] The device allows users to take photos of their meals using a dedicated app and upload them to a server, which then analyzes the photos using a deep learning model to identify the ingredients in the photo and evaluate their nutritional value.

[2204] Input: Uploaded food photo (e.g. "POST / upload-photo")

[2205] Data processing: Analyze photos using a deep learning model to extract information about ingredients and nutrients

[2206] Output: Analyzed nutritional data (e.g., carbohydrates 50g, protein 30g, fat 20g)

[2207] Step 3:

[2208] Mental state monitoring

[2209] Users answer questions sent periodically via messaging apps such as LINE. The server receives the user's answers and performs natural language analysis to evaluate their mental state.

[2210] Input: Answer about the user's mental state (e.g., "I'm pretty tired today")

[2211] Data processing: Evaluate users' responses using natural language processing to generate mental state data

[2212] Output: Mental state data (e.g., fatigue level, stress level)

[2213] Step 4:

[2214] Emotion recognition by emotion engine

[2215] The server uses an emotion engine that recognizes emotions from the user's voice and text input, and classifies the user's emotions as positive, negative, etc.

[2216] Input: Voice or text input from the user (e.g., "I'm very happy today")

[2217] Data processing: Analyze input data using an emotion engine to generate emotion data

[2218] Output: Emotion data (e.g., positive, negative)

[2219] Step 5:

[2220] Comparative analysis of data and synthesis of results

[2221] The server compares the acquired health, nutrition, mental state, and emotional data with past data and big data, detects abnormal values ​​and patterns, and comprehensively evaluates the user's health condition.

[2222] Input: Health data, nutrition data, mental state data, emotional data

[2223] Data processing: Matching with big data and analyzing it to detect outliers and patterns

[2224] Output: Comprehensive health assessment data (e.g., high stress levels, nutritional imbalances)

[2225] Step 6:

[2226] Prediction and suggestions for poor physical and mental health

[2227] Based on the analysis results, the server uses an AI model to predict the likelihood of physical or mental illness, and generates specific recommendations such as appropriate rest and meal plans depending on the predicted risk.

[2228] Input: Health assessment data

[2229] Data processing: Using AI models to predict risks and generate specific recommendations

[2230] Output: Suggestions (e.g., 10 minutes of meditation, stretches to relax)

[2231] Step 7:

[2232] User Notifications

[2233] The server notifies the user of the generated suggestions via application push notifications or messaging apps.

[2234] Input: Proposal

[2235] Data processing: Converting the data into notification format and sending it to the user's device

[2236] Output: User notification (e.g., "You seem tired today, let's do some short stretches for relaxation")

[2237] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2238] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2239] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2240] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2241] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2242] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2243] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2244] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2245] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2246] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2247] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2248] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2249] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2250] 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.

[2251] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2252] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2253] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2254] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2255] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2256] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2257] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2258] The following is further disclosed regarding the above embodiment.

[2259] (Claim 1)

[2260] a means for acquiring health data from a user;

[2261] means for receiving a photograph of a meal taken by a user and identifying nutrients;

[2262] means for monitoring a mental state based on the user's responses;

[2263] A means of comparing and analyzing these data with big data,

[2264] A means of predicting poor physical condition and mental downturns and generating suggestions for appropriate rest and meal menus;

[2265] a means for notifying the user of the proposal;

[2266] A system including:

[2267] (Claim 2)

[2268] 10. The system of claim 1, further comprising means for analyzing the acquired health data based on the amount of exercise, pulse rate, and blood pressure data.

[2269] (Claim 3)

[2270] 10. The system of claim 1, further comprising means for identifying nutrient intake based on the analyzed meal photographs using a deep learning model.

[2271] "Example 1"

[2272] (Claim 1)

[2273] a means for acquiring health data from a user;

[2274] means for receiving an image of a meal taken by a user and identifying nutrients;

[2275] means for monitoring a mental state based on the user's responses;

[2276] A means of comparing and analyzing these data with large amounts of data,

[2277] A means for predicting poor physical condition and mental decline and generating suggestions for appropriate rest and meal menus;

[2278] a means for notifying the user of the proposal;

[2279] A system including:

[2280] (Claim 2)

[2281] 10. The system of claim 1, further comprising means for analyzing the acquired health data based on the amount of exercise, heart rate, and blood pressure data.

[2282] (Claim 3)

[2283] 10. The system of claim 1, further comprising means for identifying ingested nutrients based on the analyzed meal images using a deep learning model.

[2284] "Application Example 1"

[2285] (Claim 1)

[2286] a means for acquiring health data from a user;

[2287] means for receiving a photograph of a meal taken by a user and identifying nutrients;

[2288] means for monitoring a mental state based on the user's responses;

[2289] A means of comparing and analyzing these data with big data,

[2290] A means of predicting poor physical condition and mental downturns and generating suggestions for appropriate rest and meal menus;

[2291] a means for notifying the user of the proposal;

[2292] Real-time physical and mental health monitoring for security employees, detecting and alerting to abnormalities, and

[2293] A system including:

[2294] (Claim 2)

[2295] 10. The system of claim 1, further comprising means for analyzing the acquired health data based on the amount of exercise, pulse rate, and blood pressure data.

[2296] (Claim 3)

[2297] 10. The system of claim 1, further comprising means for identifying nutrient intake based on the analyzed meal photographs using a deep learning model.

[2298] "Example 2: Combining Emotion Engines"

[2299] (Claim 1)

[2300] means for acquiring health data from a user and storing said data in a database;

[2301] means for receiving a photograph of a meal taken by a user and identifying nutrients using a deep learning model;

[2302] A means for performing text analysis based on the user's responses and monitoring their mental state;

[2303] A means of analyzing voice input and text input with an emotion engine and classifying the user's emotions;

[2304] A means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data;

[2305] A means of predicting poor physical condition and mental downturns and generating suggestions for appropriate rest and meal menus;

[2306] a means for notifying the user of the proposal;

[2307] A system including:

[2308] (Claim 2)

[2309] 10. The system of claim 1, further comprising means for analyzing the acquired health data based on the amount of exercise, pulse rate, and blood pressure data.

[2310] (Claim 3)

[2311] 10. The system of claim 1, further comprising means for identifying nutrient intake based on the analyzed meal photographs using a deep learning model.

[2312] "Application example 2 when combining emotion engines"

[2313] (Claim 1)

[2314] a means for acquiring health data from a user;

[2315] means for receiving a photograph of a meal taken by a user and identifying nutrients;

[2316] means for monitoring a mental state based on the user's responses;

[2317] means for recognizing emotions from a user's voice or text input;

[2318] A means for comparing and analyzing the acquired health data, nutritional data, mental state data, and emotion data with big data;

[2319] A means of predicting poor physical condition and mental downturns and generating suggestions for appropriate rest and meal menus;

[2320] a means for notifying the user of the proposal;

[2321] A system including:

[2322] (Claim 2)

[2323] 10. The system of claim 1, further comprising means for analyzing the acquired health data based on the amount of exercise, pulse rate, and blood pressure data.

[2324] (Claim 3)

[2325] 10. The system of claim 1, further comprising means for identifying nutrient intake based on the analyzed meal photographs using a deep learning model. [Explanation of symbols]

[2326] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for acquiring health data from a user; means for receiving a photograph of a meal taken by a user and identifying nutrients; means for monitoring a mental state based on the user's responses; A means of comparing and analyzing these data with big data, A means of predicting poor physical condition and mental downturns and generating suggestions for appropriate rest and meal menus; a means for notifying the user of the proposal; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the acquired health data based on the amount of exercise, pulse rate, and blood pressure data.

3. The system of claim 1 , further comprising means for identifying nutrient intake based on the analyzed meal photographs using a deep learning model.

Images